results/omni_finetune/dataset_manifest.json

{
  "run_id": "xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset",
  "dataset_path": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/dataset.jsonl",
  "num_samples": 3808,
  "num_episodes": 119,
  "split_counts": {
    "train": 2848,
    "val": 512,
    "test": 448
  },
  "label_counts": {
    "Fold paper strip": 84,
    "Cut cardboard": 76,
    "Manipulate paper strip": 51,
    "Cut cardboard shape": 50,
    "Draw line on cardboard": 29,
    "Cut cardboard piece": 27,
    "Place cardboard piece": 23,
    "Pick up phone": 23,
    "Sort beads": 23,
    "Hold smartphone": 19,
    "Pick up scissors": 18,
    "Manipulate paper star": 18,
    "Mark cardboard with pen": 17,
    "Use phone": 17,
    "Fold paper strip into lucky star": 17,
    "Observe workspace": 17,
    "Sort beads by color": 16,
    "Reach for beads": 16,
    "Pick up smartphone": 15,
    "Mark cardboard piece": 15,
    "Mark cardboard": 14,
    "Trim cardboard piece": 14,
    "Fold paper strip into star": 14,
    "Place product on shelf": 13,
    "Cut cardboard with scissors": 13,
    "Pick up product": 12,
    "Release paper strip": 12,
    "Place item on shelf": 12,
    "Hold paper strip": 12,
    "Pick up container": 12,
    "Cut cardboard square": 12,
    "Pick up product from box": 11,
    "Place can on shelf": 11,
    "Place phone on desk": 11,
    "Fold cardboard": 11,
    "Use smartphone": 11,
    "Move phone": 11,
    "Reposition ruler": 11,
    "Type on smartphone": 10,
    "Draw lines on cardboard": 10,
    "Pick up paper strip": 10,
    "Fold paper star": 10,
    "Hold product": 9,
    "Cut cardboard with utility knife": 9,
    "Approach desk": 9,
    "Pick up utility knife": 9,
    "Adjust item on shelf": 9,
    "Adjust ruler position": 9,
    "Approach workstation": 9,
    "Cut cardboard triangle": 9,
    "Cut cardboard strip": 9,
    "Hold cardboard piece": 9,
    "Marking cardboard piece": 9,
    "Hold ruler and mark cardboard": 9,
    "Grasp paper strip": 9,
    "Place down scissors": 8,
    "Continue folding paper strip": 8,
    "Fold paper strip into knot": 8,
    "Inflate paper star": 8,
    "Pick up canned food": 8,
    "Move towards shelf": 8,
    "Move ruler": 8,
    "Mark cardboard with marker": 8,
    "Inspect jar": 8,
    "Organize cardboard pieces": 8,
    "Interact with smartphone": 8,
    "Place scissors on table": 8,
    "Arrange buttons": 8,
    "Write on paper": 8,
    "Write on notepad": 8,
    "Writing on notepad": 8,
    "Mark line on cardboard": 7,
    "Reach for phone": 7,
    "Walk towards table": 7,
    "Place canned food on shelf": 7,
    "Cut along the marked line": 7,
    "Pick up can": 7,
    "Adjust puzzle piece": 7,
    "Carry cardboard piece": 7,
    "Fold cardboard shape": 7,
    "Arrange Mahjong tiles": 7,
    "Cut newspaper": 7,
    "Finish wiping and inspect jar": 7,
    "Hold items and inspect shelf": 7,
    "Hold and mark cardboard piece": 7,
    "Move away from workstation": 6,
    "Remove ruler": 6,
    "Reach for product": 6,
    "Pick up pen": 6,
    "Holding marker": 6,
    "Pick up cardboard": 6,
    "Pick up cardboard strip": 6,
    "Pick up new cardboard piece": 6,
    "Place puzzle piece": 6,
    "Manipulate puzzle pieces": 6,
    "Mark lines on cardboard": 6,
    "Release cardboard shape": 6,
    "Hold water bottle": 6,
    "Hold phone": 6,
    "Rearrange Mahjong tiles": 6,
    "Release cardboard": 6,
    "Browsing smartphone content": 6,
    "Wipe the plastic jar": 6,
    "Pick up tin can": 6,
    "Pick up stapler": 6,
    "Draw grid line with pen": 6,
    "Draw grid line": 6,
    "Sort buttons": 6,
    "Reach for next item": 5,
    "Reach into box": 5,
    "Move product to shelf": 5,
    "Reach for button": 5,
    "Release scissors": 5,
    "Interact with phone": 5,
    "Place phone down": 5,
    "Separate cardboard piece": 5,
    "Move smartphone": 5,
    "Hold ruler on cardboard": 5,
    "Reposition hands": 5,
    "Move along shelf": 5,
    "Hold ruler": 5,
    "Cut cardboard piece with scissors": 5,
    "Position cardboard piece": 5,
    "Place marker down": 5,
    "Sort paper star": 5,
    "Sort paper stars": 5,
    "Release puzzle piece": 5,
    "Search for puzzle piece": 5,
    "Hold beads": 5,
    "Move along the shelves": 5,
    "Manipulate small component": 5,
    "Manipulate component on strip": 5,
    "Place strip on table": 5,
    "Manipulate component": 5,
    "Align canned goods on shelf": 5,
    "Drawing grid line with ruler": 5,
    "Drawing grid line with pen and ruler": 5,
    "Drawing grid line": 5,
    "Fold lucky star": 5,
    "Sort colored tiles": 5,
    "Pick up colored tile": 5,
    "Place colored tile": 5,
    "Sort tiles": 5,
    "Sort tiles by color": 5,
    "Initiate star folding": 5,
    "Manipulate paper decoration": 5,
    "Manipulate paper edge": 5,
    "Manipulate adhesive strip": 5,
    "Place jar on shelf": 4,
    "Place product in box": 4,
    "Pick up button": 4,
    "Place button": 4,
    "Put down scissors": 4,
    "Mark cardboard with pen and ruler": 4,
    "Hold cardboard pieces": 4,
    "Hold portable charger": 4,
    "Fold purple paper strip": 4,
    "Fold purple paper": 4,
    "Hold and crease purple paper": 4,
    "Release paper": 4,
    "Retrieve paper strips": 4,
    "Fold and organize paper strips": 4,
    "Reach into bag": 4,
    "Position hands for work": 4,
    "Manipulate quilling strip": 4,
    "Begin rolling quilling strip": 4,
    "Examine item": 4,
    "Move cardboard box": 4,
    "Walk towards aisle": 4,
    "Hold cardboard": 4,
    "Walk through workspace": 4,
    "Manipulate quilled paper strip": 4,
    "Cut cardboard tube": 4,
    "Cut cardboard into triangles": 4,
    "Reach for container": 4,
    "Move container toward shelf": 4,
    "Move away from shelf": 4,
    "Pick up marker": 4,
    "Walk away": 4,
    "Pick up paper star": 4,
    "Marking lines on cardboard": 4,
    "Adjusting a puzzle piece": 4,
    "Draw line along ruler": 4,
    "Cap marker": 4,
    "Manipulate craft piece": 4,
    "Manipulate craft paper strips": 4,
    "Operate smartphone": 4,
    "Pick up item from shelf": 4,
    "Sort star-shaped beads": 4,
    "Sort beads on table": 4,
    "Hold instructional sign": 4,
    "Pick up star-shaped bead": 4,
    "Place bead on table": 4,
    "Draw lines with ruler": 4,
    "Grasp origami stars": 4,
    "Place water bottle on table": 4,
    "Vacuum the carpet": 4,
    "Push vacuum cleaner": 4,
    "Adjust vacuum cleaner position": 4,
    "Vacuum edge of carpet": 4,
    "Move vacuum cleaner": 4,
    "Place finished star on table": 4,
    "Adjust Mahjong tiles": 4,
    "Reach for Mahjong tiles": 4,
    "Rearrange Mahjong tile": 4,
    "Adjust Mahjong tile": 4,
    "Align Mahjong tiles": 4,
    "Move Mahjong tile": 4,
    "Fold ribbon": 4,
    "Hold small piece of ribbon": 4,
    "Manipulate ribbon piece": 4,
    "Fold and manipulate ribbon": 4,
    "Manipulate ribbon knot": 4,
    "Continue cutting newspaper": 4,
    "Adjust tile row alignment": 4,
    "Adjust Mahjong tile alignment": 4,
    "Adjust Mahjong tile on the stack": 4,
    "Measure and mark cardboard": 4,
    "Cut cardboard strip with scissors": 4,
    "Scroll on smartphone": 4,
    "Align ruler and mark cardboard": 4,
    "Assemble cardboard pieces": 4,
    "Arrange cardboard piece": 4,
    "Cut along the line": 4,
    "Place cardboard piece on stack": 4,
    "Arrange buttons on the table": 4,
    "Move hand over button pile": 4,
    "Arrange orange buttons": 4,
    "Move pen away": 4,
    "Gathering star beads": 4,
    "Manipulate paper stars": 4,
    "Adjust cardboard": 4,
    "Set down scissors and pick up power bank": 4,
    "Reposition cardboard for cutting": 4,
    "Arrange cardboard pieces": 4,
    "Mark cardboard strip with pen": 4,
    "Pick up pink water bottle": 4,
    "Place down pink water bottle": 4,
    "Place star in row": 4,
    "Pick up star": 4,
    "Begin folding paper strip": 4,
    "Fold paper strip into a star": 4,
    "Manipulate folded paper star": 4,
    "Reaching for beads": 4,
    "Place cardboard square": 4,
    "Arrange buttons in a line": 4,
    "Approaching and pressing the door switch": 4,
    "Bend and manipulate plastic strip": 4,
    "Pick up and sort cardboard": 4,
    "Move camera over surface": 4,
    "Observe sorting progress": 4,
    "Lock phone": 4,
    "Reach for cardboard box": 4,
    "Reach for object": 4,
    "Move to desk": 4,
    "Gathering items": 4,
    "Place items on table": 4,
    "Gathering colored beads": 4,
    "Arrange beads by color": 4,
    "Sort star-shaped objects by color": 4,
    "Sort star-shaped objects": 4,
    "Sort yellow star-shaped objects": 4,
    "Sort purple star-shaped objects": 4,
    "View phone screen": 4,
    "Viewing phone screen": 4,
    "Placing phone down": 4,
    "Place button in group": 4,
    "Move away from table": 4,
    "Placing paper strip": 4,
    "Securing paper structure": 4,
    "Secure paper edges with adhesive": 4,
    "Pick up product from bin": 3,
    "Reach for next product": 3,
    "Arrange canned products on shelf": 3,
    "Move bin to shelf area": 3,
    "Hold item and adjust posture": 3,
    "Grasp product from box": 3,
    "Grasp product from shelf": 3,
    "Move product to box": 3,
    "Manipulate cardboard piece": 3,
    "Position ruler on cardboard": 3,
    "Stack cardboard pieces": 3,
    "Place cardboard": 3,
    "Place down paper pieces": 3,
    "Release folded paper": 3,
    "Release quilling strip": 3,
    "Inspect cardboard piece": 3,
    "Reposition hand": 3,
    "Touch shelf edge": 3,
    "Release label": 3,
    "Remove shelf label": 3,
    "Carry stool to next shelf": 3,
    "Place stool on floor": 3,
    "Observe shelf": 3,
    "Adjust hand position": 3,
    "Arrange star-shaped beads": 3,
    "Move pen": 3,
    "Move towards table": 3,
    "Observe room": 3,
    "Check watch": 3,
    "Manipulate and inspect colorful pieces": 3,
    "Manipulate colorful pieces": 3,
    "Hold power bank and cable": 3,
    "Interact with colleagues": 3,
    "Hold small white box": 3,
    "Adjust smartphone and sort pieces": 3,
    "Pick up cardboard piece": 3,
    "Release cardboard piece": 3,
    "Walk across office": 3,
    "Pick up cardboard cutout": 3,
    "Walk with cardboard cutout": 3,
    "Finish placing cardboard cutouts": 3,
    "Organize tools and materials": 3,
    "Move cardboard piece": 3,
    "Hold cardboard strip": 3,
    "Reposition scissors": 3,
    "Move away from desk": 3,
    "Move to shelf": 3,
    "Move marker and adjust hand": 3,
    "Identify next cardboard piece": 3,
    "Reach for can": 3,
    "Open door": 3,
    "Hold craft tool": 3,
    "Approach table": 3,
    "Arrange paper strips": 3,
    "Hold and bend paper strip": 3,
    "Scan for next piece": 3,
    "Positioning puzzle piece": 3,
    "Move puzzle piece": 3,
    "Adjusting puzzle piece": 3,
    "Hold ruler and pen steady": 3,
    "Moving ruler": 3,
    "Approach packing area": 3,
    "Deposit beads into box": 3,
    "Combine bead piles": 3,
    "Cut light green fabric": 3,
    "Continue cutting fabric": 3,
    "Cut fabric with scissors": 3,
    "Adjusting fabric for cutting": 3,
    "Adjusting fabric position": 3,
    "Cutting fabric": 3,
    "Mark fabric with pen": 3,
    "Mark fabric": 3,
    "Manipulate cardboard shape": 3,
    "Hold small cardboard pieces": 3,
    "sort craft materials": 3,
    "Release smartphone": 3,
    "Sort small craft pieces": 3,
    "Move product towards shelf": 3,
    "Move to box": 3,
    "Place container on shelf": 3,
    "Place item in shopping bag": 3,
    "Sort beads on the table": 3,
    "Reposition ruler and pen": 3,
    "Reposition pen and prepare for next line": 3,
    "Place pen on cardboard": 3,
    "Draw straight lines on cardboard": 3,
    "Sort origami stars": 3,
    "Walk in hallway": 3,
    "Reach for stars": 3,
    "Walk towards desk": 3,
    "Sort light blue origami stars": 3,
    "Sort origami stars by color": 3,
    "Move origami stars": 3,
    "Hold and view phone": 3,
    "Cut cardboard pieces with scissors": 3,
    "Vacuuming carpet edge": 3,
    "Vacuuming carpet corner": 3,
    "Vacuuming the carpet edge": 3,
    "Vacuuming along the wall edge": 3,
    "Hold product package": 3,
    "Check phone": 3,
    "Hold charging cable": 3,
    "Hold items in hand": 3,
    "Hold and examine item": 3,
    "Pick up pack from shelf": 3,
    "fold purple ribbon": 3,
    "Position ribbon piece": 3,
    "Place ribbon onto project": 3,
    "Secure ribbon with needle": 3,
    "Reach for shelf": 3,
    "Place smartphone on desk": 3,
    "Reach for water bottle": 3,
    "Hold scissors": 3,
    "Move scissors away": 3,
    "Place scissors down": 3,
    "Arrange tiles into row": 3,
    "Pick up Mahjong tile": 3,
    "Place Mahjong tile on the stack": 3,
    "Place Mahjong tile on stack": 3,
    "Hold ruler and draw line": 3,
    "Draw line": 3,
    "Hold ruler and marker": 3,
    "Tap smartphone screen": 3,
    "Scroll through photo gallery": 3,
    "Typing message on smartphone": 3,
    "Typing on smartphone": 3,
    "Tapping smartphone screen": 3,
    "Tapping on smartphone screen": 3,
    "Putting away smartphone": 3,
    "Stop measuring and put down tools": 3,
    "Positioning ruler on cardboard": 3,
    "Draw line with pen": 3,
    "Prepare to draw lines": 3,
    "Remove ruler and marker": 3,
    "Walking through classroom": 3,
    "Move marker away": 3,
    "Position ruler and mark cardboard": 3,
    "Mark cardboard with ruler": 3,
    "Reposition utility knife": 3,
    "Tear off cardboard segment": 3,
    "Reach for craft items": 3,
    "Sort craft items": 3,
    "Place hand on table": 3,
    "Browse smartphone screen": 3,
    "Scroll smartphone screen": 3,
    "Put down smartphone": 3,
    "Place smartphone down": 3,
    "Adjust container on shelf": 3,
    "Adjust cans in container": 3,
    "Adjust cans in tray": 3,
    "Adjusting canned goods on shelf": 3,
    "Sorting buttons": 3,
    "Sort orange buttons": 3,
    "Sort orange button": 3,
    "Move orange buttons": 3,
    "Sort purple beads": 3,
    "Sort beads by hand": 3,
    "Count and record paper stars": 3,
    "Connect cable to device": 3,
    "Count and arrange paper stars": 3,
    "Count paper stars": 3,
    "Pick up puzzle piece": 3,
    "Place piece into puzzle": 3,
    "Manipulate puzzle piece": 3,
    "Observe puzzle progress": 3,
    "Attempt to fit puzzle piece": 3,
    "Hold tray of canned goods": 3,
    "Position tray": 3,
    "Carry crate of cans": 3,
    "Place crate on floor": 3,
    "Wipe item": 3,
    "Place item back": 3,
    "Reach for retail item": 3,
    "Grasp retail item": 3,
    "Adjust retail items on shelf": 3,
    "Pick up retail item": 3,
    "Align and place retail item": 3,
    "Arrange items on shelf": 3,
    "Adjust retail item position": 3,
    "Reach for star": 3,
    "Retrieve star": 3,
    "Cut cardboard grid": 3,
    "Prepare paper strip": 3,
    "Place star on table": 3,
    "Place phone on table": 3,
    "Cut along the edge of the newspaper": 3,
    "Cut along the newspaper edge": 3,
    "Browsing mobile phone": 3,
    "Browse mobile phone": 3,
    "Cut newspaper with scissors": 3,
    "Gather pieces": 3,
    "Move pieces into box": 3,
    "Gather pieces into box": 3,
    "Scrolling or navigating on phone": 3,
    "Scrolling and viewing content on phone": 3,
    "Sort and arrange buttons": 3,
    "Sort button": 3,
    "Sort and adjust button line": 3,
    "Sort and place buttons": 3,
    "Walking in the hallway": 3,
    "Entering the VR training room": 3,
    "Greeting/acknowledging participants": 3,
    "Move through the training room": 3,
    "Manipulate plastic strips": 3,
    "Manipulate plastic strip": 3,
    "Hold and bend plastic strip": 3,
    "Fold plastic strip": 3,
    "Pick up charging cable": 3,
    "Hold electronic item": 3,
    "Pick up electronic item": 3,
    "Inspect electronic item": 3,
    "Inspect smartphone box": 3,
    "Hold smartphone box": 3,
    "Examine product": 3,
    "Move plastic storage bin": 3,
    "Hold container of canned food": 3,
    "Move towards aisle": 3,
    "Approach restocking supplies": 3,
    "Move pineapple chips": 3,
    "Sort and arrange cardboard pieces": 3,
    "Reach for cardboard piece": 3,
    "Sort and stack cardboard pieces": 3,
    "Walking towards workstation": 3,
    "Sort small objects": 3,
    "Sort buttons by color": 3,
    "Sort button by color": 3,
    "Reach for item in box": 2,
    "Pick up nut bar box": 2,
    "Place canned product on shelf": 2,
    "Pick up canned product": 2,
    "Reach for next canned product": 2,
    "Pick up plastic bin": 2,
    "Retract hand": 2,
    "Hold and wipe product": 2,
    "Wipe down shelf": 2,
    "Wipe product": 2,
    "Place jar in box": 2,
    "Wipe shelf": 2,
    "Pick up pickle jar": 2,
    "Hold pickle jar": 2,
    "Hold cleaning cloth": 2,
    "Pick up product from shelf": 2,
    "Move to next section": 2,
    "Prepare to place product": 2,
    "Grasp next item": 2,
    "Position scissors to cut cardboard": 2,
    "Position scissors": 2,
    "Walk through corridor": 2,
    "Arrive at a different workstation": 2,
    "Move vacuum cleaner hose": 2,
    "Mark cardboard with ruler and pen": 2,
    "Hold ruler steady": 2,
    "Move marker and ruler": 2,
    "Align ruler on cardboard": 2,
    "Plug cable into portable charger": 2,
    "Pick up portable charger": 2,
    "Place charger on table": 2,
    "Hold charger and cable": 2,
    "Manipulate power cable plug": 2,
    "Insert plug into power adapter": 2,
    "Hold power adapter": 2,
    "Align charging cable": 2,
    "Insert charging cable": 2,
    "Observe desktop layout": 2,
    "Pick up yellow paper strip": 2,
    "Adjust paper strip": 2,
    "Hold charger": 2,
    "Open small case": 2,
    "Measure cardboard with ruler": 2,
    "Pick up yellow item": 2,
    "Hold blue product box": 2,
    "Wipe shelf surface": 2,
    "Inspect product": 2,
    "Clean shelf": 2,
    "Place ketchup bottle on shelf": 2,
    "Draw line with marker": 2,
    "Draw straight line": 2,
    "Mark straight line": 2,
    "Move ruler and tools": 2,
    "Pick up small cardboard piece": 2,
    "Cut cardboard along line": 2,
    "Align ruler with crease": 2,
    "Cut cardboard strip with utility knife": 2,
    "Hold container lid": 2,
    "Closing the door": 2,
    "Grasp cleaning bottle": 2,
    "Grasping cleaning cloth": 2,
    "Adjust pot position": 2,
    "Start cutting": 2,
    "Organize products": 2,
    "Close cardboard box": 2,
    "Grasp package": 2,
    "Observe shelf status": 2,
    "Inspect product lid": 2,
    "Reach for another item": 2,
    "Discard item into bin": 2,
    "Walk towards next aisle": 2,
    "Reach for product labels": 2,
    "Hold product labels": 2,
    "Examine labels": 2,
    "Pick up bottled sauce": 2,
    "Pick up supplement bottle": 2,
    "Hold supplement bottle": 2,
    "Open supplement bottle": 2,
    "Pick up item": 2,
    "Place item in container": 2,
    "Pick up another item": 2,
    "Adjust grip on container": 2,
    "Pick up oil bottle": 2,
    "Inspect supplement bottle": 2,
    "Pick up spice jar": 2,
    "Stand up and walk away": 2,
    "Prepare to sort beads": 2,
    "Align ruler": 2,
    "Adjust grip": 2,
    "Drawing lines on cardboard": 2,
    "Reposition marker": 2,
    "Mark lines with marker": 2,
    "Position the ruler": 2,
    "Insert charging cable into power bank": 2,
    "Sort colorful pieces": 2,
    "Touch pieces in box": 2,
    "Place white box on table": 2,
    "Sort small colorful pieces": 2,
    "Sorting colorful paper pieces": 2,
    "Manipulate paper piece": 2,
    "Use phone to check instructions": 2,
    "Trace pattern on cardboard": 2,
    "Remove cardboard pattern": 2,
    "Remove cardboard pattern piece": 2,
    "Cut out cardboard pattern": 2,
    "Cut cardboard pattern": 2,
    "Adjust cardboard position": 2,
    "Interact with smartphone screen": 2,
    "Pick up metal ruler": 2,
    "Move pen aside": 2,
    "Reposition and cut": 2,
    "Hold quilling paper": 2,
    "Hold quilled paper coil": 2,
    "Manipulate small paper segment": 2,
    "Place down paper segment": 2,
    "Browse and interact with phone interface": 2,
    "Interacting with phone screen": 2,
    "Pick up light blue strip": 2,
    "Inspect strip": 2,
    "Manipulate light blue strip": 2,
    "Place scissors aside": 2,
    "Stacking cardboard pieces": 2,
    "Moving hand towards cardboard stack": 2,
    "Moving hand": 2,
    "Position cardboard for cutting": 2,
    "Put down water bottle": 2,
    "Placing piece on stack": 2,
    "Reach for and pick up smartphone": 2,
    "Pick up item from bin": 2,
    "Pick up next item from bin": 2,
    "Hold item": 2,
    "Inspect and place item on shelf": 2,
    "Check smart watch": 2,
    "Withdraw hand": 2,
    "Pick up jar": 2,
    "Pick up sauce bottle": 2,
    "Hold empty container": 2,
    "Assess shelf arrangement": 2,
    "Observe and walk through store": 2,
    "Inspect shelf condition": 2,
    "Observe colleague and workspace": 2,
    "Walk towards shelves": 2,
    "Approach boxes": 2,
    "Extract wire hangers from box": 2,
    "Bundle display hooks": 2,
    "Move through aisle": 2,
    "Pick up items from the shopping bag": 2,
    "Place items on the shelf": 2,
    "Place marked piece down": 2,
    "Release cardboard piece and gesture": 2,
    "Observe and pause": 2,
    "Gesturing": 2,
    "Resume observation": 2,
    "Place cans into box": 2,
    "Arrange cans in box": 2,
    "Arrange cans on shelf": 2,
    "Adjust position": 2,
    "Place container in bin": 2,
    "Adjust cans in bin": 2,
    "Hold and inspect can": 2,
    "Adjust perspective": 2,
    "Inspect shelf and organize stock": 2,
    "Picking up stock": 2,
    "Placing stock on shelf": 2,
    "Hold small product bag": 2,
    "Carry container": 2,
    "Pick up cleaning cloth": 2,
    "Pick up product box": 2,
    "Place box on shelf": 2,
    "Place plush toy on shelf": 2,
    "Adjust placement on shelf": 2,
    "Move plush toy": 2,
    "Arrange cardboard": 2,
    "Walk with marker": 2,
    "Pick up small object": 2,
    "Walk across room": 2,
    "Place cardboard square on stack": 2,
    "Arrange cardboard squares": 2,
    "Stacking cardboard squares": 2,
    "Positioning cardboard on workspace": 2,
    "Stacking cardboard square": 2,
    "Stack cardboard square": 2,
    "Stack cardboard squares": 2,
    "Sorting paper stars": 2,
    "Place star": 2,
    "Place paper star": 2,
    "Stop sorting stars": 2,
    "Walk through doorway": 2,
    "Pick up object": 2,
    "Place item on table": 2,
    "Sort and place paper star": 2,
    "Place knife down": 2,
    "Align cardboard strip": 2,
    "Hold cardboard with ruler": 2,
    "Move utility knife along ruler": 2,
    "Slide utility knife along ruler": 2,
    "Guide utility knife along ruler": 2,
    "Place tool on table": 2,
    "Move hand toward craft materials": 2,
    "Manipulate paper strips": 2,
    "Pick up blue paper strip": 2,
    "Hold small object": 2,
    "Place down strip": 2,
    "Move hand away from workspace": 2,
    "Lift pen and shift ruler": 2,
    "Walk across the room": 2,
    "Pack beads into box": 2,
    "Pick up beads": 2,
    "Pick up cardboard tray": 2,
    "Move tray towards packing area": 2,
    "Position cardboard tray": 2,
    "Mark fabric with pen and ruler": 2,
    "Gather cardboard pieces": 2,
    "Examine canned goods": 2,
    "Pick up Dior gift box": 2,
    "Inspect Dior gift box": 2,
    "Place back Dior gift box": 2,
    "Move along the shelf": 2,
    "Pick up another bottle": 2,
    "Inspect bottle": 2,
    "Inspect almond package": 2,
    "Move along the supermarket aisle": 2,
    "Pick up canned good": 2,
    "Prepare to place cardboard": 2,
    "Prepare to resume cutting": 2,
    "Hold canned food": 2,
    "Align canned food on shelf": 2,
    "Place another canned food on shelf": 2,
    "Adjust canned food on shelf": 2,
    "Move hand away from shelf": 2,
    "Move hand away": 2,
    "Hold earbud case": 2,
    "Open earbud case": 2,
    "Hold electronic accessory": 2,
    "Pick up accessory": 2,
    "Pick up electronic accessory": 2,
    "Move hand back to box": 2,
    "Move towards box": 2,
    "Hold items": 2,
    "Place items on shelf": 2,
    "Grasp snack package": 2,
    "Hold snack package": 2,
    "Hold snack packages": 2,
    "Adjust snack package": 2,
    "Align plastic containers": 2,
    "Reach for items": 2,
    "Adjust containers on shelf": 2,
    "Adjust container position": 2,
    "Grasp item": 2,
    "Move item to bag": 2,
    "Organize item on shelf": 2,
    "Grasp shopping bag": 2,
    "Organize bag contents": 2,
    "Grasp and retrieve item": 2,
    "Reposition sign and organize beads": 2,
    "Draw lines with pen and ruler": 2,
    "Place stars in container": 2,
    "Adjust cardboard divider": 2,
    "Put down phone": 2,
    "Pick up water bottle": 2,
    "Retrieve items from bag": 2,
    "Remove item from bag": 2,
    "Open paper lantern": 2,
    "Fold paper lantern": 2,
    "Grasp lantern": 2,
    "Grasp lantern component": 2,
    "Align paper lantern edges": 2,
    "Adjust lantern string": 2,
    "Handle paper lantern component": 2,
    "Open folded paper lantern": 2,
    "Adjust lantern shape": 2,
    "Hold paper lantern": 2,
    "Apply adhesive tape to lantern": 2,
    "Open paper lantern component": 2,
    "Expand paper lantern": 2,
    "Align edges of paper lantern": 2,
    "Carry cereal boxes": 2,
    "Carry cereal towards aisle": 2,
    "Carry pasta box towards aisle": 2,
    "Hold container": 2,
    "Carry item to shelf": 2,
    "Inspect shelf": 2,
    "Move to stock products": 2,
    "Move to shelf base": 2,
    "Pick up gift box": 2,
    "Pick up next gift box": 2,
    "Pick up snack pouch": 2,
    "Move storage bin": 2,
    "Hold bin and move through aisle": 2,
    "Grasp plastic bag on shelf": 2,
    "Arrange plastic containers": 2,
    "Arrange container on shelf": 2,
    "Sort Mahjong tiles": 2,
    "Mark lines with pen along ruler": 2,
    "Pick up charging case": 2,
    "Inspect charging case": 2,
    "Place charging case down": 2,
    "Place ruler on cardboard": 2,
    "Hold and align cardboard": 2,
    "Reposition tools": 2,
    "Position cardboard tube": 2,
    "Position scissors for next cut": 2,
    "Place canned good on shelf": 2,
    "Move canned goods container": 2,
    "Position container near shelf": 2,
    "Place canned food in container": 2,
    "Reach for next canned food item": 2,
    "Move cardboard": 2,
    "Labeling cardboard squares": 2,
    "Labeling cardboard square": 2,
    "Labeling cardboard piece": 2,
    "Marking cardboard with pen": 2,
    "Folding cardboard": 2,
    "Manipulate cardboard sheet": 2,
    "Record count on notepad": 2,
    "Record star count on paper": 2,
    "Pick up electronic device": 2,
    "Place device on lap": 2,
    "Move hand to paper stars": 2,
    "Resume counting stars": 2,
    "Reviewing count record": 2,
    "Write on paper record": 2,
    "Update paper record": 2,
    "Reach for puzzle piece": 2,
    "Sort puzzle pieces": 2,
    "Approaching the table": 2,
    "Preparing to craft": 2,
    "Picking up crafting material": 2,
    "Pick up small piece of material": 2,
    "Manipulate material": 2,
    "Place material": 2,
    "Manipulate yellow strip": 2,
    "Manipulating paper strips": 2,
    "Manipulate bead": 2,
    "Manipulate beads": 2,
    "Hold and manipulate paper strip": 2,
    "Sort canned goods in tray": 2,
    "Move can towards shelf": 2,
    "Wipe retail item": 2,
    "Hold recording sheet and pen": 2,
    "Record star count": 2,
    "Hold pen and paper": 2,
    "Observe surroundings": 2,
    "Observe paper and count objects": 2,
    "Write count on paper": 2,
    "Place pen on table": 2,
    "Place smartphone on table": 2,
    "Resume writing on paper": 2,
    "Place paper star in row": 2,
    "Manipulate star": 2,
    "Arrange paper stars": 2,
    "Pick up power bank": 2,
    "Pick up small item": 2,
    "Walking to sink": 2,
    "Washing hands": 2,
    "Rub hands together": 2,
    "Finish washing hands": 2,
    "Pick up paper towel": 2,
    "Dry hands": 2,
    "Discard paper towel": 2,
    "Release paper star": 2,
    "Cut section from newspaper": 2,
    "Tear newspaper": 2,
    "Hold newspaper": 2,
    "Hold and align newspaper": 2,
    "Fold newspaper": 2,
    "Reposition newspaper": 2,
    "Sort blue star-shaped pieces": 2,
    "Sort small plastic pieces": 2,
    "Reach for more pieces": 2,
    "Sort plastic pieces": 2,
    "Typing on phone": 2,
    "Repositioning ruler": 2,
    "Place down ruler and pen": 2,
    "Walk through hallway": 2,
    "Fold cardboard edge": 2,
    "Drop cardboard square into box": 2,
    "Deposit cardboard squares": 2,
    "Approaching work table": 2,
    "Cut cardboard sheet with scissors": 2,
    "Cut cardboard sheet": 2,
    "Wipe electronic item": 2,
    "Place item in bag": 2,
    "Select another item": 2,
    "Pick up canned item": 2,
    "Pick up another canned item": 2,
    "Carry plastic container": 2,
    "Pick up canned goods": 2,
    "Move bin": 2,
    "Walking along the aisle": 2,
    "Observe stocking": 2,
    "Place canned food in bin": 2,
    "Pick up plastic container": 2,
    "Forming quilled paper shape": 2,
    "Manipulate quilled paper shape": 2,
    "Place quilled paper shape": 2,
    "Retrieve paper strip": 2,
    "Select paper strip": 2,
    "Manipulate quilled paper strips": 2,
    "Transition to standing position": 2,
    "Observe paper quilling station": 2,
    "Sort quilled paper pieces": 2,
    "Walk towards storage area": 2,
    "Hold device and cable": 2,
    "Move piece to pile": 2,
    "Manipulate quilled paper": 2,
    "Mark list with pen": 2,
    "Mark paper list": 2,
    "Adjust bead piles": 2,
    "Sort blue beads": 2,
    "Move blue beads": 2,
    "Place down pen": 2,
    "Walking through the office": 2,
    "Place controller on table": 2,
    "Resume sorting blue beads": 2,
    "Finishing coil": 2,
    "Folding paper strip": 2,
    "Manipulate quilling paper": 2,
    "Grasp electronic object": 2,
    "Interaction with coworker": 2,
    "Manipulate small object": 2,
    "Manipulate paper quilling piece": 2,
    "Hold quilled paper piece": 2,
    "Hold and align paper strip": 2,
    "Hold and rotate paper strip": 2,
    "Move cardboard sheet": 2,
    "Trim cardboard": 2,
    "Return to sorting": 2,
    "Record count": 2,
    "Counting and organizing beads": 2,
    "Pick up star bead": 2,
    "Place and count bead": 2,
    "Arrange star beads": 2,
    "Counting star beads": 2,
    "Retrieving more beads": 2,
    "Adjust paper": 2,
    "Gather star beads": 2,
    "Arrange star beads for counting": 2,
    "Sort and count beads": 2,
    "Wipe food product": 1,
    "Wipe jar": 1,
    "Place pickle jar in box": 1,
    "Release pickle jar": 1,
    "Wipe the shelf": 1,
    "Wipe the product jar": 1,
    "Place jar into shelf box": 1,
    "Wipe grocery shelf": 1,
    "Align button in row": 1,
    "Place button in row": 1,
    "Pick up orange button": 1,
    "Arrange small buttons": 1,
    "Align button": 1,
    "Align buttons": 1,
    "Arrange button cluster": 1,
    "Align button row": 1,
    "Arrange buttons on table": 1,
    "Look around the table": 1,
    "Adjust red button in row": 1,
    "Adjust red button": 1,
    "Pull back hand": 1,
    "Align red buttons": 1,
    "Reach for black button": 1,
    "Arrange black buttons": 1,
    "Pick up black button": 1,
    "Move black button": 1,
    "Pick up red button": 1,
    "Place red button": 1,
    "Move and place black buttons": 1,
    "Arrange buttons in row": 1,
    "Arrange red buttons": 1,
    "Align red button in row": 1,
    "Reach and sort buttons": 1,
    "Adjust red button position": 1,
    "Place and align button": 1,
    "Move hand": 1,
    "Move button to line": 1,
    "Reach for utility knife": 1,
    "Place smartphone on cardboard": 1,
    "Walk towards room": 1,
    "Retract camera/reposition view": 1,
    "Switch to scissors": 1,
    "Retract hand from bag": 1,
    "Reach for canned food": 1,
    "Walk towards shelf": 1,
    "Select product from box": 1,
    "Wipe ketchup bottle": 1,
    "Prepare to place bottle on shelf": 1,
    "Walk through office": 1,
    "Transition to cutting": 1,
    "Reposition hands and ruler": 1,
    "Press fold": 1,
    "Position utility knife on cardboard": 1,
    "Place smartphone on stand": 1,
    "Pick up dustpan": 1,
    "Move dustpan to side": 1,
    "Move towards the stove": 1,
    "Open stove pot lid": 1,
    "Walking towards door": 1,
    "Picking up bottle": 1,
    "Wipe kitchen counter": 1,
    "Rinse cloth in sink": 1,
    "Move towards kitchen area": 1,
    "Place cloth on floor": 1,
    "Reach for cleaning supplies": 1,
    "Remove cleaning bottle": 1,
    "Washing hands in sink": 1,
    "Wiping countertop": 1,
    "Lift pot lid": 1,
    "Stir contents": 1,
    "Place lid back": 1,
    "Move pot": 1,
    "Place towel": 1,
    "Use phone to check stock": 1,
    "Place phone on shelf": 1,
    "Remove item from shelf": 1,
    "Sweep debris": 1,
    "Sweep floor debris": 1,
    "Place sauce in container": 1,
    "Walk through store": 1,
    "Reach for item on shelf": 1,
    "Place oil in container": 1,
    "Place supplement bottle in container": 1,
    "Place spice jar in container": 1,
    "Walking in the workspace": 1,
    "Roll quilling paper": 1,
    "Release paper coil": 1,
    "Release and prepare new strip": 1,
    "Reach for paper strips": 1,
    "Place item into bag": 1,
    "Position utility knife": 1,
    "Lift utility knife": 1,
    "Fold cut cardboard": 1,
    "Look away": 1,
    "Align scissors": 1,
    "Position cardboard strip": 1,
    "Inspect cardboard strip": 1,
    "Pick up cut cardboard piece": 1,
    "Move cardboard to pile": 1,
    "Align cardboard piece": 1,
    "Fold cardboard sheet": 1,
    "Complete the cut": 1,
    "Put down utility knife": 1,
    "Hold utility knife": 1,
    "Place cardboard strip": 1,
    "Place sauce bottle on shelf": 1,
    "Align foam piece": 1,
    "Pick up bottle": 1,
    "Observe craft layout": 1,
    "Assemble foam strips": 1,
    "Adjust foam strip": 1,
    "Align foam strip": 1,
    "Attach foam strip": 1,
    "Curve foam strip into loop": 1,
    "Fold foam piece": 1,
    "Pick up blue foam piece": 1,
    "Hold foam pieces": 1,
    "Peel foam strip": 1,
    "Move small blue foam piece towards the strip": 1,
    "Align blue strip": 1,
    "Lift blue strip": 1,
    "Hold blue strip": 1,
    "Peel blue strip": 1,
    "Fold blue strip": 1,
    "Align paper strip": 1,
    "Interlock paper strips": 1,
    "Pick up craft material": 1,
    "Attach material to paper strip": 1,
    "Pick up tool": 1,
    "Enter workspace": 1,
    "Grasp door handle": 1,
    "Pick up supplies from box": 1,
    "Enter the room": 1,
    "Approach work table": 1,
    "Reach for wire hangers": 1,
    "Release hook": 1,
    "Walk towards other aisles": 1,
    "Reach for additional items": 1,
    "Prepare to pick up item": 1,
    "Reach for shelving divider": 1,
    "Position shelving divider": 1,
    "Rearrange shelf item": 1,
    "Reach for product on shelf": 1,
    "Release food item": 1,
    "Reach for and examine canned goods": 1,
    "Select and pick up a canned item": 1,
    "Place item back on shelf": 1,
    "Select a bottle": 1,
    "Place bottle back on shelf": 1,
    "Release bottle": 1,
    "Scan supermarket shelves": 1,
    "Reach for canned goods": 1,
    "Touch canned goods": 1,
    "Reach for next can": 1,
    "Retrieve next canned food item": 1,
    "Reach for next canned food": 1,
    "Retrieve canned food from box": 1,
    "Pick up electronic accessory from box": 1,
    "Place accessory on shelf": 1,
    "Reach towards shelf": 1,
    "Place accessory into box": 1,
    "Place accessory box": 1,
    "Pick up new electronic product": 1,
    "Pick up electronic product": 1,
    "Release product on shelf": 1,
    "Pick up new product from box": 1,
    "Pick up shopping bag": 1,
    "Walk with shopping bag": 1,
    "Pick up item from box": 1,
    "Move box to next position": 1,
    "Place snack package on shelf": 1,
    "Place snack package in box": 1,
    "Place snack in box": 1,
    "Place snack packages on shelf": 1,
    "Pick up snack packages": 1,
    "Pick up snack package": 1,
    "Organize snacks in box": 1,
    "Reach for snack package": 1,
    "Open cardboard box": 1,
    "Remove cardboard flap": 1,
    "Reach for item": 1,
    "Pick up plush toy": 1,
    "Place plush toy into bag": 1,
    "Prepare to place item in bag": 1,
    "Place item into shopping bag": 1,
    "Realign Mahjong tiles": 1,
    "Release lantern": 1,
    "Pick up packaged paper lantern component": 1,
    "Remove paper lantern part from packaging": 1,
    "Remove plastic packaging": 1,
    "Pick up food item": 1,
    "Pick up cereal boxes": 1,
    "Pick up pasta box": 1,
    "Pick up container from box": 1,
    "Reach for items in box": 1,
    "Pick up grocery item": 1,
    "Pick up snack packs": 1,
    "Place snack on shelf": 1,
    "Retrieve snack from container": 1,
    "Place gift box into bin": 1,
    "Place gift box on shelf": 1,
    "Place snack pouch in container": 1,
    "Reach for snack pouch": 1,
    "Place snack pouch on shelf": 1,
    "Remove storage bin from shelf": 1,
    "Reach for empty shelf space": 1,
    "Remove plastic container from shelf": 1,
    "Remove plastic container from storage box": 1,
    "Retrieve another container": 1,
    "Stabilize cardboard": 1,
    "Stabilize ruler": 1,
    "Moving cardboard square": 1,
    "Placing labeled square": 1,
    "Starting to label next square": 1,
    "Placing labeled cardboard square": 1,
    "Switching marker": 1,
    "Reach for next piece": 1,
    "Placing pen on table": 1,
    "Repositioning ruler and cardboard": 1,
    "Walking across the room": 1,
    "Use phone while crafting": 1,
    "View content on smartphone": 1,
    "Pick up cardboard square": 1,
    "Retrieve hand to table": 1,
    "Pick up cardboard stack": 1,
    "Walk with cardboard": 1,
    "Move away from collection box": 1,
    "Walking through office hallway": 1,
    "Grasp cardboard sheet": 1,
    "Set down utility knife": 1,
    "Sort cut cardboard": 1,
    "Prepare to cut cardboard": 1,
    "Score cardboard": 1,
    "Place container on floor": 1,
    "Reach for another container": 1,
    "Place storage container on floor": 1,
    "Release container": 1,
    "Pick up storage container": 1,
    "Position container on shelf": 1,
    "Remove lid from container": 1,
    "Place canned goods in container": 1,
    "Pick up next product from bin": 1,
    "Reorganize bin contents": 1,
    "Rolling paper strip": 1,
    "Selecting new paper strip": 1,
    "Start folding paper strip": 1,
    "Positioning paper strip": 1,
    "Walk towards workspace": 1,
    "Reach for paper strip": 1,
    "Pull paper strip": 1,
    "Sort beads and write count": 1
  },
  "action_options": [
    "Adjust Mahjong tile",
    "Adjust Mahjong tile alignment",
    "Adjust Mahjong tile on the stack",
    "Adjust Mahjong tiles",
    "Adjust bead piles",
    "Adjust canned food on shelf",
    "Adjust cans in bin",
    "Adjust cans in container",
    "Adjust cans in tray",
    "Adjust cardboard",
    "Adjust cardboard divider",
    "Adjust cardboard position",
    "Adjust container on shelf",
    "Adjust container position",
    "Adjust containers on shelf",
    "Adjust foam strip",
    "Adjust grip",
    "Adjust grip on container",
    "Adjust hand position",
    "Adjust item on shelf",
    "Adjust lantern shape",
    "Adjust lantern string",
    "Adjust paper",
    "Adjust paper strip",
    "Adjust perspective",
    "Adjust placement on shelf",
    "Adjust position",
    "Adjust pot position",
    "Adjust puzzle piece",
    "Adjust red button",
    "Adjust red button in row",
    "Adjust red button position",
    "Adjust retail item position",
    "Adjust retail items on shelf",
    "Adjust ruler position",
    "Adjust smartphone and sort pieces",
    "Adjust snack package",
    "Adjust tile row alignment",
    "Adjust vacuum cleaner position",
    "Adjusting a puzzle piece",
    "Adjusting canned goods on shelf",
    "Adjusting fabric for cutting",
    "Adjusting fabric position",
    "Adjusting puzzle piece",
    "Align Mahjong tiles",
    "Align and place retail item",
    "Align blue strip",
    "Align button",
    "Align button in row",
    "Align button row",
    "Align buttons",
    "Align canned food on shelf",
    "Align canned goods on shelf",
    "Align cardboard piece",
    "Align cardboard strip",
    "Align charging cable",
    "Align edges of paper lantern",
    "Align foam piece",
    "Align foam strip",
    "Align paper lantern edges",
    "Align paper strip",
    "Align plastic containers",
    "Align red button in row",
    "Align red buttons",
    "Align ruler",
    "Align ruler and mark cardboard",
    "Align ruler on cardboard",
    "Align ruler with crease",
    "Align scissors",
    "Apply adhesive tape to lantern",
    "Approach boxes",
    "Approach desk",
    "Approach packing area",
    "Approach restocking supplies",
    "Approach table",
    "Approach work table",
    "Approach workstation",
    "Approaching and pressing the door switch",
    "Approaching the table",
    "Approaching work table",
    "Arrange Mahjong tiles",
    "Arrange beads by color",
    "Arrange black buttons",
    "Arrange button cluster",
    "Arrange buttons",
    "Arrange buttons in a line",
    "Arrange buttons in row",
    "Arrange buttons on table",
    "Arrange buttons on the table",
    "Arrange canned products on shelf",
    "Arrange cans in box",
    "Arrange cans on shelf",
    "Arrange cardboard",
    "Arrange cardboard piece",
    "Arrange cardboard pieces",
    "Arrange cardboard squares",
    "Arrange container on shelf",
    "Arrange items on shelf",
    "Arrange orange buttons",
    "Arrange paper stars",
    "Arrange paper strips",
    "Arrange plastic containers",
    "Arrange red buttons",
    "Arrange small buttons",
    "Arrange star beads",
    "Arrange star beads for counting",
    "Arrange star-shaped beads",
    "Arrange tiles into row",
    "Arrive at a different workstation",
    "Assemble cardboard pieces",
    "Assemble foam strips",
    "Assess shelf arrangement",
    "Attach foam strip",
    "Attach material to paper strip",
    "Attempt to fit puzzle piece",
    "Begin folding paper strip",
    "Begin rolling quilling strip",
    "Bend and manipulate plastic strip",
    "Browse and interact with phone interface",
    "Browse mobile phone",
    "Browse smartphone screen",
    "Browsing mobile phone",
    "Browsing smartphone content",
    "Bundle display hooks",
    "Cap marker",
    "Carry cardboard piece",
    "Carry cereal boxes",
    "Carry cereal towards aisle",
    "Carry container",
    "Carry crate of cans",
    "Carry item to shelf",
    "Carry pasta box towards aisle",
    "Carry plastic container",
    "Carry stool to next shelf",
    "Check phone",
    "Check smart watch",
    "Check watch",
    "Clean shelf",
    "Close cardboard box",
    "Closing the door",
    "Combine bead piles",
    "Complete the cut",
    "Connect cable to device",
    "Continue cutting fabric",
    "Continue cutting newspaper",
    "Continue folding paper strip",
    "Count and arrange paper stars",
    "Count and record paper stars",
    "Count paper stars",
    "Counting and organizing beads",
    "Counting star beads",
    "Curve foam strip into loop",
    "Cut along the edge of the newspaper",
    "Cut along the line",
    "Cut along the marked line",
    "Cut along the newspaper edge",
    "Cut cardboard",
    "Cut cardboard along line",
    "Cut cardboard grid",
    "Cut cardboard into triangles",
    "Cut cardboard pattern",
    "Cut cardboard piece",
    "Cut cardboard piece with scissors",
    "Cut cardboard pieces with scissors",
    "Cut cardboard shape",
    "Cut cardboard sheet",
    "Cut cardboard sheet with scissors",
    "Cut cardboard square",
    "Cut cardboard strip",
    "Cut cardboard strip with scissors",
    "Cut cardboard strip with utility knife",
    "Cut cardboard triangle",
    "Cut cardboard tube",
    "Cut cardboard with scissors",
    "Cut cardboard with utility knife",
    "Cut fabric with scissors",
    "Cut light green fabric",
    "Cut newspaper",
    "Cut newspaper with scissors",
    "Cut out cardboard pattern",
    "Cut section from newspaper",
    "Cutting fabric",
    "Deposit beads into box",
    "Deposit cardboard squares",
    "Discard item into bin",
    "Discard paper towel",
    "Draw grid line",
    "Draw grid line with pen",
    "Draw line",
    "Draw line along ruler",
    "Draw line on cardboard",
    "Draw line with marker",
    "Draw line with pen",
    "Draw lines on cardboard",
    "Draw lines with pen and ruler",
    "Draw lines with ruler",
    "Draw straight line",
    "Draw straight lines on cardboard",
    "Drawing grid line",
    "Drawing grid line with pen and ruler",
    "Drawing grid line with ruler",
    "Drawing lines on cardboard",
    "Drop cardboard square into box",
    "Dry hands",
    "Enter the room",
    "Enter workspace",
    "Entering the VR training room",
    "Examine canned goods",
    "Examine item",
    "Examine labels",
    "Examine product",
    "Expand paper lantern",
    "Extract wire hangers from box",
    "Finish placing cardboard cutouts",
    "Finish washing hands",
    "Finish wiping and inspect jar",
    "Finishing coil",
    "Fold and manipulate ribbon",
    "Fold and organize paper strips",
    "Fold blue strip",
    "Fold cardboard",
    "Fold cardboard edge",
    "Fold cardboard shape",
    "Fold cardboard sheet",
    "Fold cut cardboard",
    "Fold foam piece",
    "Fold lucky star",
    "Fold newspaper",
    "Fold paper lantern",
    "Fold paper star",
    "Fold paper strip",
    "Fold paper strip into a star",
    "Fold paper strip into knot",
    "Fold paper strip into lucky star",
    "Fold paper strip into star",
    "Fold plastic strip",
    "Fold purple paper",
    "Fold purple paper strip",
    "Fold ribbon",
    "Folding cardboard",
    "Folding paper strip",
    "Forming quilled paper shape",
    "Gather cardboard pieces",
    "Gather pieces",
    "Gather pieces into box",
    "Gather star beads",
    "Gathering colored beads",
    "Gathering items",
    "Gathering star beads",
    "Gesturing",
    "Grasp and retrieve item",
    "Grasp cardboard sheet",
    "Grasp cleaning bottle",
    "Grasp door handle",
    "Grasp electronic object",
    "Grasp item",
    "Grasp lantern",
    "Grasp lantern component",
    "Grasp next item",
    "Grasp origami stars",
    "Grasp package",
    "Grasp paper strip",
    "Grasp plastic bag on shelf",
    "Grasp product from box",
    "Grasp product from shelf",
    "Grasp retail item",
    "Grasp shopping bag",
    "Grasp snack package",
    "Grasping cleaning cloth",
    "Greeting/acknowledging participants",
    "Guide utility knife along ruler",
    "Handle paper lantern component",
    "Hold and align cardboard",
    "Hold and align newspaper",
    "Hold and align paper strip",
    "Hold and bend paper strip",
    "Hold and bend plastic strip",
    "Hold and crease purple paper",
    "Hold and examine item",
    "Hold and inspect can",
    "Hold and manipulate paper strip",
    "Hold and mark cardboard piece",
    "Hold and rotate paper strip",
    "Hold and view phone",
    "Hold and wipe product",
    "Hold beads",
    "Hold bin and move through aisle",
    "Hold blue product box",
    "Hold blue strip",
    "Hold canned food",
    "Hold cardboard",
    "Hold cardboard piece",
    "Hold cardboard pieces",
    "Hold cardboard strip",
    "Hold cardboard with ruler",
    "Hold charger",
    "Hold charger and cable",
    "Hold charging cable",
    "Hold cleaning cloth",
    "Hold container",
    "Hold container lid",
    "Hold container of canned food",
    "Hold craft tool",
    "Hold device and cable",
    "Hold earbud case",
    "Hold electronic accessory",
    "Hold electronic item",
    "Hold empty container",
    "Hold foam pieces",
    "Hold instructional sign",
    "Hold item",
    "Hold item and adjust posture",
    "Hold items",
    "Hold items and inspect shelf",
    "Hold items in hand",
    "Hold newspaper",
    "Hold paper lantern",
    "Hold paper strip",
    "Hold pen and paper",
    "Hold phone",
    "Hold pickle jar",
    "Hold portable charger",
    "Hold power adapter",
    "Hold power bank and cable",
    "Hold product",
    "Hold product labels",
    "Hold product package",
    "Hold quilled paper coil",
    "Hold quilled paper piece",
    "Hold quilling paper",
    "Hold recording sheet and pen",
    "Hold ruler",
    "Hold ruler and draw line",
    "Hold ruler and mark cardboard",
    "Hold ruler and marker",
    "Hold ruler and pen steady",
    "Hold ruler on cardboard",
    "Hold ruler steady",
    "Hold scissors",
    "Hold small cardboard pieces",
    "Hold small object",
    "Hold small piece of ribbon",
    "Hold small product bag",
    "Hold small white box",
    "Hold smartphone",
    "Hold smartphone box",
    "Hold snack package",
    "Hold snack packages",
    "Hold supplement bottle",
    "Hold tray of canned goods",
    "Hold utility knife",
    "Hold water bottle",
    "Holding marker",
    "Identify next cardboard piece",
    "Inflate paper star",
    "Initiate star folding",
    "Insert charging cable",
    "Insert charging cable into power bank",
    "Insert plug into power adapter",
    "Inspect Dior gift box",
    "Inspect almond package",
    "Inspect and place item on shelf",
    "Inspect bottle",
    "Inspect cardboard piece",
    "Inspect cardboard strip",
    "Inspect charging case",
    "Inspect electronic item",
    "Inspect jar",
    "Inspect product",
    "Inspect product lid",
    "Inspect shelf",
    "Inspect shelf and organize stock",
    "Inspect shelf condition",
    "Inspect smartphone box",
    "Inspect strip",
    "Inspect supplement bottle",
    "Interact with colleagues",
    "Interact with phone",
    "Interact with smartphone",
    "Interact with smartphone screen",
    "Interacting with phone screen",
    "Interaction with coworker",
    "Interlock paper strips",
    "Labeling cardboard piece",
    "Labeling cardboard square",
    "Labeling cardboard squares",
    "Lift blue strip",
    "Lift pen and shift ruler",
    "Lift pot lid",
    "Lift utility knife",
    "Lock phone",
    "Look around the table",
    "Look away",
    "Manipulate adhesive strip",
    "Manipulate and inspect colorful pieces",
    "Manipulate bead",
    "Manipulate beads",
    "Manipulate cardboard piece",
    "Manipulate cardboard shape",
    "Manipulate cardboard sheet",
    "Manipulate colorful pieces",
    "Manipulate component",
    "Manipulate component on strip",
    "Manipulate craft paper strips",
    "Manipulate craft piece",
    "Manipulate folded paper star",
    "Manipulate light blue strip",
    "Manipulate material",
    "Manipulate paper decoration",
    "Manipulate paper edge",
    "Manipulate paper piece",
    "Manipulate paper quilling piece",
    "Manipulate paper star",
    "Manipulate paper stars",
    "Manipulate paper strip",
    "Manipulate paper strips",
    "Manipulate plastic strip",
    "Manipulate plastic strips",
    "Manipulate power cable plug",
    "Manipulate puzzle piece",
    "Manipulate puzzle pieces",
    "Manipulate quilled paper",
    "Manipulate quilled paper shape",
    "Manipulate quilled paper strip",
    "Manipulate quilled paper strips",
    "Manipulate quilling paper",
    "Manipulate quilling strip",
    "Manipulate ribbon knot",
    "Manipulate ribbon piece",
    "Manipulate small component",
    "Manipulate small object",
    "Manipulate small paper segment",
    "Manipulate star",
    "Manipulate yellow strip",
    "Manipulating paper strips",
    "Mark cardboard",
    "Mark cardboard piece",
    "Mark cardboard strip with pen",
    "Mark cardboard with marker",
    "Mark cardboard with pen",
    "Mark cardboard with pen and ruler",
    "Mark cardboard with ruler",
    "Mark cardboard with ruler and pen",
    "Mark fabric",
    "Mark fabric with pen",
    "Mark fabric with pen and ruler",
    "Mark line on cardboard",
    "Mark lines on cardboard",
    "Mark lines with marker",
    "Mark lines with pen along ruler",
    "Mark list with pen",
    "Mark paper list",
    "Mark straight line",
    "Marking cardboard piece",
    "Marking cardboard with pen",
    "Marking lines on cardboard",
    "Measure and mark cardboard",
    "Measure cardboard with ruler",
    "Move Mahjong tile",
    "Move along shelf",
    "Move along the shelf",
    "Move along the shelves",
    "Move along the supermarket aisle",
    "Move and place black buttons",
    "Move away from collection box",
    "Move away from desk",
    "Move away from shelf",
    "Move away from table",
    "Move away from workstation",
    "Move bin",
    "Move bin to shelf area",
    "Move black button",
    "Move blue beads",
    "Move box to next position",
    "Move button to line",
    "Move camera over surface",
    "Move can towards shelf",
    "Move canned goods container",
    "Move cardboard",
    "Move cardboard box",
    "Move cardboard piece",
    "Move cardboard sheet",
    "Move cardboard to pile",
    "Move container toward shelf",
    "Move dustpan to side",
    "Move hand",
    "Move hand away",
    "Move hand away from shelf",
    "Move hand away from workspace",
    "Move hand back to box",
    "Move hand over button pile",
    "Move hand to paper stars",
    "Move hand toward craft materials",
    "Move item to bag",
    "Move marker and adjust hand",
    "Move marker and ruler",
    "Move marker away",
    "Move orange buttons",
    "Move origami stars",
    "Move pen",
    "Move pen aside",
    "Move pen away",
    "Move phone",
    "Move piece to pile",
    "Move pieces into box",
    "Move pineapple chips",
    "Move plastic storage bin",
    "Move plush toy",
    "Move pot",
    "Move product to box",
    "Move product to shelf",
    "Move product towards shelf",
    "Move puzzle piece",
    "Move ruler",
    "Move ruler and tools",
    "Move scissors away",
    "Move small blue foam piece towards the strip",
    "Move smartphone",
    "Move storage bin",
    "Move through aisle",
    "Move through the training room",
    "Move to box",
    "Move to desk",
    "Move to next section",
    "Move to shelf",
    "Move to shelf base",
    "Move to stock products",
    "Move towards aisle",
    "Move towards box",
    "Move towards kitchen area",
    "Move towards shelf",
    "Move towards table",
    "Move towards the stove",
    "Move tray towards packing area",
    "Move utility knife along ruler",
    "Move vacuum cleaner",
    "Move vacuum cleaner hose",
    "Moving cardboard square",
    "Moving hand",
    "Moving hand towards cardboard stack",
    "Moving ruler",
    "Observe and pause",
    "Observe and walk through store",
    "Observe colleague and workspace",
    "Observe craft layout",
    "Observe desktop layout",
    "Observe paper and count objects",
    "Observe paper quilling station",
    "Observe puzzle progress",
    "Observe room",
    "Observe shelf",
    "Observe shelf status",
    "Observe sorting progress",
    "Observe stocking",
    "Observe surroundings",
    "Observe workspace",
    "Open cardboard box",
    "Open door",
    "Open earbud case",
    "Open folded paper lantern",
    "Open paper lantern",
    "Open paper lantern component",
    "Open small case",
    "Open stove pot lid",
    "Open supplement bottle",
    "Operate smartphone",
    "Organize bag contents",
    "Organize cardboard pieces",
    "Organize item on shelf",
    "Organize products",
    "Organize snacks in box",
    "Organize tools and materials",
    "Pack beads into box",
    "Peel blue strip",
    "Peel foam strip",
    "Pick up Dior gift box",
    "Pick up Mahjong tile",
    "Pick up accessory",
    "Pick up and sort cardboard",
    "Pick up another bottle",
    "Pick up another canned item",
    "Pick up another item",
    "Pick up beads",
    "Pick up black button",
    "Pick up blue foam piece",
    "Pick up blue paper strip",
    "Pick up bottle",
    "Pick up bottled sauce",
    "Pick up button",
    "Pick up can",
    "Pick up canned food",
    "Pick up canned good",
    "Pick up canned goods",
    "Pick up canned item",
    "Pick up canned product",
    "Pick up cardboard",
    "Pick up cardboard cutout",
    "Pick up cardboard piece",
    "Pick up cardboard square",
    "Pick up cardboard stack",
    "Pick up cardboard strip",
    "Pick up cardboard tray",
    "Pick up cereal boxes",
    "Pick up charging cable",
    "Pick up charging case",
    "Pick up cleaning cloth",
    "Pick up colored tile",
    "Pick up container",
    "Pick up container from box",
    "Pick up craft material",
    "Pick up cut cardboard piece",
    "Pick up dustpan",
    "Pick up electronic accessory",
    "Pick up electronic accessory from box",
    "Pick up electronic device",
    "Pick up electronic item",
    "Pick up electronic product",
    "Pick up food item",
    "Pick up gift box",
    "Pick up grocery item",
    "Pick up item",
    "Pick up item from bin",
    "Pick up item from box",
    "Pick up item from shelf",
    "Pick up items from the shopping bag",
    "Pick up jar",
    "Pick up light blue strip",
    "Pick up marker",
    "Pick up metal ruler",
    "Pick up new cardboard piece",
    "Pick up new electronic product",
    "Pick up new product from box",
    "Pick up next gift box",
    "Pick up next item from bin",
    "Pick up next product from bin",
    "Pick up nut bar box",
    "Pick up object",
    "Pick up oil bottle",
    "Pick up orange button",
    "Pick up pack from shelf",
    "Pick up packaged paper lantern component",
    "Pick up paper star",
    "Pick up paper strip",
    "Pick up paper towel",
    "Pick up pasta box",
    "Pick up pen",
    "Pick up phone",
    "Pick up pickle jar",
    "Pick up pink water bottle",
    "Pick up plastic bin",
    "Pick up plastic container",
    "Pick up plush toy",
    "Pick up portable charger",
    "Pick up power bank",
    "Pick up product",
    "Pick up product box",
    "Pick up product from bin",
    "Pick up product from box",
    "Pick up product from shelf",
    "Pick up puzzle piece",
    "Pick up red button",
    "Pick up retail item",
    "Pick up sauce bottle",
    "Pick up scissors",
    "Pick up shopping bag",
    "Pick up small cardboard piece",
    "Pick up small item",
    "Pick up small object",
    "Pick up small piece of material",
    "Pick up smartphone",
    "Pick up snack package",
    "Pick up snack packages",
    "Pick up snack packs",
    "Pick up snack pouch",
    "Pick up spice jar",
    "Pick up stapler",
    "Pick up star",
    "Pick up star bead",
    "Pick up star-shaped bead",
    "Pick up storage container",
    "Pick up supplement bottle",
    "Pick up supplies from box",
    "Pick up tin can",
    "Pick up tool",
    "Pick up utility knife",
    "Pick up water bottle",
    "Pick up yellow item",
    "Pick up yellow paper strip",
    "Picking up bottle",
    "Picking up crafting material",
    "Picking up stock",
    "Place Mahjong tile on stack",
    "Place Mahjong tile on the stack",
    "Place accessory box",
    "Place accessory into box",
    "Place accessory on shelf",
    "Place and align button",
    "Place and count bead",
    "Place another canned food on shelf",
    "Place back Dior gift box",
    "Place bead on table",
    "Place bottle back on shelf",
    "Place box on shelf",
    "Place button",
    "Place button in group",
    "Place button in row",
    "Place can on shelf",
    "Place canned food in bin",
    "Place canned food in container",
    "Place canned food on shelf",
    "Place canned good on shelf",
    "Place canned goods in container",
    "Place canned product on shelf",
    "Place cans into box",
    "Place cardboard",
    "Place cardboard piece",
    "Place cardboard piece on stack",
    "Place cardboard square",
    "Place cardboard square on stack",
    "Place cardboard strip",
    "Place charger on table",
    "Place charging case down",
    "Place cloth on floor",
    "Place colored tile",
    "Place container in bin",
    "Place container on floor",
    "Place container on shelf",
    "Place controller on table",
    "Place crate on floor",
    "Place device on lap",
    "Place down paper pieces",
    "Place down paper segment",
    "Place down pen",
    "Place down pink water bottle",
    "Place down ruler and pen",
    "Place down scissors",
    "Place down strip",
    "Place finished star on table",
    "Place gift box into bin",
    "Place gift box on shelf",
    "Place hand on table",
    "Place item back",
    "Place item back on shelf",
    "Place item in bag",
    "Place item in container",
    "Place item in shopping bag",
    "Place item into bag",
    "Place item into shopping bag",
    "Place item on shelf",
    "Place item on table",
    "Place items on shelf",
    "Place items on table",
    "Place items on the shelf",
    "Place jar in box",
    "Place jar into shelf box",
    "Place jar on shelf",
    "Place ketchup bottle on shelf",
    "Place knife down",
    "Place lid back",
    "Place marked piece down",
    "Place marker down",
    "Place material",
    "Place oil in container",
    "Place paper star",
    "Place paper star in row",
    "Place pen on cardboard",
    "Place pen on table",
    "Place phone down",
    "Place phone on desk",
    "Place phone on shelf",
    "Place phone on table",
    "Place pickle jar in box",
    "Place piece into puzzle",
    "Place plush toy into bag",
    "Place plush toy on shelf",
    "Place product in box",
    "Place product on shelf",
    "Place puzzle piece",
    "Place quilled paper shape",
    "Place red button",
    "Place ribbon onto project",
    "Place ruler on cardboard",
    "Place sauce bottle on shelf",
    "Place sauce in container",
    "Place scissors aside",
    "Place scissors down",
    "Place scissors on table",
    "Place smartphone down",
    "Place smartphone on cardboard",
    "Place smartphone on desk",
    "Place smartphone on stand",
    "Place smartphone on table",
    "Place snack in box",
    "Place snack on shelf",
    "Place snack package in box",
    "Place snack package on shelf",
    "Place snack packages on shelf",
    "Place snack pouch in container",
    "Place snack pouch on shelf",
    "Place spice jar in container",
    "Place star",
    "Place star in row",
    "Place star on table",
    "Place stars in container",
    "Place stool on floor",
    "Place storage container on floor",
    "Place strip on table",
    "Place supplement bottle in container",
    "Place tool on table",
    "Place towel",
    "Place water bottle on table",
    "Place white box on table",
    "Placing labeled cardboard square",
    "Placing labeled square",
    "Placing paper strip",
    "Placing pen on table",
    "Placing phone down",
    "Placing piece on stack",
    "Placing stock on shelf",
    "Plug cable into portable charger",
    "Position cardboard for cutting",
    "Position cardboard piece",
    "Position cardboard strip",
    "Position cardboard tray",
    "Position cardboard tube",
    "Position container near shelf",
    "Position container on shelf",
    "Position hands for work",
    "Position ribbon piece",
    "Position ruler and mark cardboard",
    "Position ruler on cardboard",
    "Position scissors",
    "Position scissors for next cut",
    "Position scissors to cut cardboard",
    "Position shelving divider",
    "Position the ruler",
    "Position tray",
    "Position utility knife",
    "Position utility knife on cardboard",
    "Positioning cardboard on workspace",
    "Positioning paper strip",
    "Positioning puzzle piece",
    "Positioning ruler on cardboard",
    "Prepare paper strip",
    "Prepare to cut cardboard",
    "Prepare to draw lines",
    "Prepare to pick up item",
    "Prepare to place bottle on shelf",
    "Prepare to place cardboard",
    "Prepare to place item in bag",
    "Prepare to place product",
    "Prepare to resume cutting",
    "Prepare to sort beads",
    "Preparing to craft",
    "Press fold",
    "Pull back hand",
    "Pull paper strip",
    "Push vacuum cleaner",
    "Put down phone",
    "Put down scissors",
    "Put down smartphone",
    "Put down utility knife",
    "Put down water bottle",
    "Putting away smartphone",
    "Reach and sort buttons",
    "Reach for Mahjong tiles",
    "Reach for additional items",
    "Reach for and examine canned goods",
    "Reach for and pick up smartphone",
    "Reach for another container",
    "Reach for another item",
    "Reach for beads",
    "Reach for black button",
    "Reach for button",
    "Reach for can",
    "Reach for canned food",
    "Reach for canned goods",
    "Reach for cardboard box",
    "Reach for cardboard piece",
    "Reach for cleaning supplies",
    "Reach for container",
    "Reach for craft items",
    "Reach for empty shelf space",
    "Reach for item",
    "Reach for item in box",
    "Reach for item on shelf",
    "Reach for items",
    "Reach for items in box",
    "Reach for more pieces",
    "Reach for next can",
    "Reach for next canned food",
    "Reach for next canned food item",
    "Reach for next canned product",
    "Reach for next item",
    "Reach for next piece",
    "Reach for next product",
    "Reach for object",
    "Reach for paper strip",
    "Reach for paper strips",
    "Reach for phone",
    "Reach for product",
    "Reach for product labels",
    "Reach for product on shelf",
    "Reach for puzzle piece",
    "Reach for retail item",
    "Reach for shelf",
    "Reach for shelving divider",
    "Reach for snack package",
    "Reach for snack pouch",
    "Reach for star",
    "Reach for stars",
    "Reach for utility knife",
    "Reach for water bottle",
    "Reach for wire hangers",
    "Reach into bag",
    "Reach into box",
    "Reach towards shelf",
    "Reaching for beads",
    "Realign Mahjong tiles",
    "Rearrange Mahjong tile",
    "Rearrange Mahjong tiles",
    "Rearrange shelf item",
    "Record count",
    "Record count on notepad",
    "Record star count",
    "Record star count on paper",
    "Release and prepare new strip",
    "Release bottle",
    "Release cardboard",
    "Release cardboard piece",
    "Release cardboard piece and gesture",
    "Release cardboard shape",
    "Release container",
    "Release folded paper",
    "Release food item",
    "Release hook",
    "Release label",
    "Release lantern",
    "Release paper",
    "Release paper coil",
    "Release paper star",
    "Release paper strip",
    "Release pickle jar",
    "Release product on shelf",
    "Release puzzle piece",
    "Release quilling strip",
    "Release scissors",
    "Release smartphone",
    "Remove cardboard flap",
    "Remove cardboard pattern",
    "Remove cardboard pattern piece",
    "Remove cleaning bottle",
    "Remove item from bag",
    "Remove item from shelf",
    "Remove lid from container",
    "Remove paper lantern part from packaging",
    "Remove plastic container from shelf",
    "Remove plastic container from storage box",
    "Remove plastic packaging",
    "Remove ruler",
    "Remove ruler and marker",
    "Remove shelf label",
    "Remove storage bin from shelf",
    "Reorganize bin contents",
    "Reposition and cut",
    "Reposition cardboard for cutting",
    "Reposition hand",
    "Reposition hands",
    "Reposition hands and ruler",
    "Reposition marker",
    "Reposition newspaper",
    "Reposition pen and prepare for next line",
    "Reposition ruler",
    "Reposition ruler and pen",
    "Reposition scissors",
    "Reposition sign and organize beads",
    "Reposition tools",
    "Reposition utility knife",
    "Repositioning ruler",
    "Repositioning ruler and cardboard",
    "Resume counting stars",
    "Resume observation",
    "Resume sorting blue beads",
    "Resume writing on paper",
    "Retract camera/reposition view",
    "Retract hand",
    "Retract hand from bag",
    "Retrieve another container",
    "Retrieve canned food from box",
    "Retrieve hand to table",
    "Retrieve items from bag",
    "Retrieve next canned food item",
    "Retrieve paper strip",
    "Retrieve paper strips",
    "Retrieve snack from container",
    "Retrieve star",
    "Retrieving more beads",
    "Return to sorting",
    "Reviewing count record",
    "Rinse cloth in sink",
    "Roll quilling paper",
    "Rolling paper strip",
    "Rub hands together",
    "Scan for next piece",
    "Scan supermarket shelves",
    "Score cardboard",
    "Scroll on smartphone",
    "Scroll smartphone screen",
    "Scroll through photo gallery",
    "Scrolling and viewing content on phone",
    "Scrolling or navigating on phone",
    "Search for puzzle piece",
    "Secure paper edges with adhesive",
    "Secure ribbon with needle",
    "Securing paper structure",
    "Select a bottle",
    "Select and pick up a canned item",
    "Select another item",
    "Select paper strip",
    "Select product from box",
    "Selecting new paper strip",
    "Separate cardboard piece",
    "Set down scissors and pick up power bank",
    "Set down utility knife",
    "Slide utility knife along ruler",
    "Sort Mahjong tiles",
    "Sort and adjust button line",
    "Sort and arrange buttons",
    "Sort and arrange cardboard pieces",
    "Sort and count beads",
    "Sort and place buttons",
    "Sort and place paper star",
    "Sort and stack cardboard pieces",
    "Sort beads",
    "Sort beads and write count",
    "Sort beads by color",
    "Sort beads by hand",
    "Sort beads on table",
    "Sort beads on the table",
    "Sort blue beads",
    "Sort blue star-shaped pieces",
    "Sort button",
    "Sort button by color",
    "Sort buttons",
    "Sort buttons by color",
    "Sort canned goods in tray",
    "Sort colored tiles",
    "Sort colorful pieces",
    "Sort craft items",
    "Sort cut cardboard",
    "Sort light blue origami stars",
    "Sort orange button",
    "Sort orange buttons",
    "Sort origami stars",
    "Sort origami stars by color",
    "Sort paper star",
    "Sort paper stars",
    "Sort plastic pieces",
    "Sort purple beads",
    "Sort purple star-shaped objects",
    "Sort puzzle pieces",
    "Sort quilled paper pieces",
    "Sort small colorful pieces",
    "Sort small craft pieces",
    "Sort small objects",
    "Sort small plastic pieces",
    "Sort star-shaped beads",
    "Sort star-shaped objects",
    "Sort star-shaped objects by color",
    "Sort tiles",
    "Sort tiles by color",
    "Sort yellow star-shaped objects",
    "Sorting buttons",
    "Sorting colorful paper pieces",
    "Sorting paper stars",
    "Stabilize cardboard",
    "Stabilize ruler",
    "Stack cardboard pieces",
    "Stack cardboard square",
    "Stack cardboard squares",
    "Stacking cardboard pieces",
    "Stacking cardboard square",
    "Stacking cardboard squares",
    "Stand up and walk away",
    "Start cutting",
    "Start folding paper strip",
    "Starting to label next square",
    "Stir contents",
    "Stop measuring and put down tools",
    "Stop sorting stars",
    "Sweep debris",
    "Sweep floor debris",
    "Switch to scissors",
    "Switching marker",
    "Tap smartphone screen",
    "Tapping on smartphone screen",
    "Tapping smartphone screen",
    "Tear newspaper",
    "Tear off cardboard segment",
    "Touch canned goods",
    "Touch pieces in box",
    "Touch shelf edge",
    "Trace pattern on cardboard",
    "Transition to cutting",
    "Transition to standing position",
    "Trim cardboard",
    "Trim cardboard piece",
    "Type on smartphone",
    "Typing message on smartphone",
    "Typing on phone",
    "Typing on smartphone",
    "Update paper record",
    "Use phone",
    "Use phone to check instructions",
    "Use phone to check stock",
    "Use phone while crafting",
    "Use smartphone",
    "Vacuum edge of carpet",
    "Vacuum the carpet",
    "Vacuuming along the wall edge",
    "Vacuuming carpet corner",
    "Vacuuming carpet edge",
    "Vacuuming the carpet edge",
    "View content on smartphone",
    "View phone screen",
    "Viewing phone screen",
    "Walk across office",
    "Walk across room",
    "Walk across the room",
    "Walk away",
    "Walk in hallway",
    "Walk through corridor",
    "Walk through doorway",
    "Walk through hallway",
    "Walk through office",
    "Walk through store",
    "Walk through workspace",
    "Walk towards aisle",
    "Walk towards desk",
    "Walk towards next aisle",
    "Walk towards other aisles",
    "Walk towards room",
    "Walk towards shelf",
    "Walk towards shelves",
    "Walk towards storage area",
    "Walk towards table",
    "Walk towards workspace",
    "Walk with cardboard",
    "Walk with cardboard cutout",
    "Walk with marker",
    "Walk with shopping bag",
    "Walking across the room",
    "Walking along the aisle",
    "Walking in the hallway",
    "Walking in the workspace",
    "Walking through classroom",
    "Walking through office hallway",
    "Walking through the office",
    "Walking to sink",
    "Walking towards door",
    "Walking towards workstation",
    "Washing hands",
    "Washing hands in sink",
    "Wipe down shelf",
    "Wipe electronic item",
    "Wipe food product",
    "Wipe grocery shelf",
    "Wipe item",
    "Wipe jar",
    "Wipe ketchup bottle",
    "Wipe kitchen counter",
    "Wipe product",
    "Wipe retail item",
    "Wipe shelf",
    "Wipe shelf surface",
    "Wipe the plastic jar",
    "Wipe the product jar",
    "Wipe the shelf",
    "Wiping countertop",
    "Withdraw hand",
    "Write count on paper",
    "Write on notepad",
    "Write on paper",
    "Write on paper record",
    "Writing on notepad",
    "fold purple ribbon",
    "sort craft materials"
  ],
  "subtask_options": [
    "Adding items to shopping container",
    "Adjust Mahjong tiles",
    "Adjust and align Mahjong tiles",
    "Adjust and cut fabric",
    "Adjust fabric for cutting",
    "Adjust lantern string and handle components",
    "Adjust position and check phone",
    "Adjust tile alignment",
    "Adjust tiles on stack",
    "Adjust, move, and realign Mahjong tiles",
    "Adjusting a puzzle piece",
    "Adjusting and folding cardboard",
    "Adjusting and placing down paper pieces",
    "Adjusting and securing paper structure",
    "Adjusting canned goods on the shelf",
    "Adjusting cardboard divider",
    "Adjusting cardboard layout",
    "Adjusting container positions",
    "Adjusting cookware",
    "Adjusting edge and marking cardboard",
    "Adjusting items and reaching for stock",
    "Adjusting items on shelf",
    "Adjusting items on the shelf",
    "Adjusting marker and ruler",
    "Adjusting paper edge and placing strip",
    "Adjusting posture while holding item",
    "Adjusting puzzle piece",
    "Adjusting retail items on shelf",
    "Adjusting ruler position",
    "Adjusting snack package",
    "Adjusting stock and finishing placement",
    "Align and fold newspaper",
    "Align canned goods on shelf",
    "Align paper lantern edges",
    "Align ruler and draw line",
    "Aligning button rows",
    "Aligning canned goods on the shelf",
    "Aligning cardboard for cutting",
    "Aligning cardboard strip",
    "Aligning plastic containers on the shelf",
    "Aligning ruler for final measurements",
    "Approach inventory boxes",
    "Approaching restocking supplies",
    "Approaching the stove",
    "Approaching workstation",
    "Arrange Mahjong tiles",
    "Arrange buttons",
    "Arrange buttons in a line",
    "Arrange paper strips",
    "Arrange tiles into row",
    "Arranging and marking cardboard strips",
    "Arranging buttons",
    "Arranging buttons on the table",
    "Arranging cardboard squares",
    "Arranging items on shelf",
    "Arranging orange buttons",
    "Arranging paper stars",
    "Arranging products on shelf",
    "Arranging shelf display",
    "Arranging star-shaped beads",
    "Assembling cardboard base",
    "Assembling cardboard boxes",
    "Assembling material pieces",
    "Assembling small decorative components",
    "Assembling the foam base loop",
    "Assessing shelf arrangement",
    "Assessing shelf status and relocating",
    "Attaching and folding blue foam strips",
    "Bagging a held electronic item",
    "Beginning to roll the quilling strip",
    "Bend and shape paper strips",
    "Bending plastic strip",
    "Boxing pieces and picking up phone",
    "Browse and interact with phone interface",
    "Browse mobile phone",
    "Browse mobile phone and cut newspaper",
    "Browsing and selecting canned goods",
    "Browsing phone interface",
    "Browsing photo gallery",
    "Browsing smartphone",
    "Browsing smartphone content",
    "Bundle display hooks",
    "Cap marker and place down",
    "Capping marker and positioning ruler",
    "Carry cereal boxes to aisle",
    "Carry shopping bag",
    "Charging power bank",
    "Check instructions on phone",
    "Checking cooking pot",
    "Checking smartphone",
    "Checking smartwatch while reaching for product",
    "Checking stock information",
    "Clean and inspect shelf",
    "Clean shelf and stock product",
    "Clean shelf surface",
    "Cleaning and boxing jars",
    "Cleaning and organizing products in boxes",
    "Cleaning cloth maintenance",
    "Cleaning kitchen surfaces",
    "Cleaning products and retrieving items from boxes",
    "Cleaning shelves and handling pickle jars",
    "Cleaning shelves and rearranging products",
    "Cleaning shelves and relocating",
    "Cleaning up workspace and moving items",
    "Cleaning up workstation",
    "Cleaning workspace",
    "Cleaning, bagging, and selecting another item",
    "Cleaning, inspecting, and bagging an electronic item",
    "Clear workspace and pick up phone",
    "Clearing space on the shelf",
    "Collecting canned food into bin",
    "Collecting origami stars",
    "Comparing and replacing bottles",
    "Complete folding and place star on table",
    "Completing list and moving away from desk",
    "Completing marking and stepping away",
    "Connecting power cables to a portable charger",
    "Cooking at the stove",
    "Count beads and retrieve more",
    "Counting and recording paper stars",
    "Counting and recording stars",
    "Crafting with paper strips",
    "Cut along the marked line",
    "Cut along the newspaper edge",
    "Cut and fold cardboard",
    "Cut and release cardboard",
    "Cut and reposition utility knife",
    "Cut and tear off cardboard segment",
    "Cut cardboard",
    "Cut cardboard pattern",
    "Cut cardboard with utility knife",
    "Cut fabric with scissors",
    "Cut light green fabric",
    "Cut light green fabric and reposition scissors",
    "Cut newspaper and place scissors on table",
    "Cut out cardboard pattern",
    "Cut section from newspaper",
    "Cutting and adjusting cardboard",
    "Cutting and adjusting cardboard pieces",
    "Cutting and adjusting cardboard sheet",
    "Cutting and adjusting scissors",
    "Cutting and folding cardboard",
    "Cutting and folding cardboard shapes",
    "Cutting and gathering cardboard",
    "Cutting and measuring cardboard",
    "Cutting and organizing cardboard pieces",
    "Cutting and pausing",
    "Cutting and picking up new cardboard",
    "Cutting and placing cardboard",
    "Cutting and placing cardboard piece",
    "Cutting and placing cardboard squares",
    "Cutting and preparing cardboard pieces",
    "Cutting and releasing cardboard piece",
    "Cutting and releasing cardboard shapes",
    "Cutting and repositioning cardboard",
    "Cutting and separating cardboard pieces",
    "Cutting and sorting cardboard squares",
    "Cutting and stacking cardboard pieces",
    "Cutting cardboard",
    "Cutting cardboard and picking up smartphone",
    "Cutting cardboard and placing down scissors",
    "Cutting cardboard and placing knife down",
    "Cutting cardboard and putting down scissors",
    "Cutting cardboard and retrieving power bank",
    "Cutting cardboard into strips",
    "Cutting cardboard into triangles",
    "Cutting cardboard piece",
    "Cutting cardboard pieces",
    "Cutting cardboard pieces with scissors",
    "Cutting cardboard shapes",
    "Cutting cardboard sheet",
    "Cutting cardboard square",
    "Cutting cardboard strip",
    "Cutting cardboard strips",
    "Cutting cardboard strips with scissors",
    "Cutting cardboard triangles",
    "Cutting cardboard tube",
    "Cutting cardboard tube and setting aside scissors",
    "Cutting cardboard with a utility knife",
    "Cutting cardboard with scissors",
    "Cutting cardboard with scissors and checking phone",
    "Cutting cardboard with utility knife",
    "Cutting initial cardboard pieces",
    "Cutting newspaper",
    "Cutting triangular cardboard pieces",
    "Depositing cardboard squares",
    "Document bead counts",
    "Draw and reposition ruler",
    "Draw lines and patterns on cardboard",
    "Draw lines using a ruler",
    "Drawing grid lines",
    "Drawing grid lines and repositioning cardboard",
    "Drawing grid lines with a pen",
    "Drawing grid lines with a ruler",
    "Drawing grid lines with a ruler and pen",
    "Drawing guide lines on cardboard",
    "Drawing lines along ruler",
    "Drawing lines and checking smartphone",
    "Drawing lines on cardboard",
    "Entering the training area",
    "Examine yellow item",
    "Examining a product",
    "Expand and adjust lantern shape",
    "Expand paper lantern",
    "Extract wire hangers from inventory",
    "Fetching materials",
    "Final alignment and marking",
    "Final alignment of lantern edges",
    "Final button arrangement",
    "Final cardboard cutting",
    "Final component assembly",
    "Final trimming of cardboard",
    "Finalize wiping and placement of ketchup bottle",
    "Finalizing and releasing folded paper",
    "Finalizing cuts and storing tools",
    "Finalizing item placement into shopping bag",
    "Finalizing marks on cardboard",
    "Finalizing paper star",
    "Finalizing shelf organization",
    "Finalizing shelf placement",
    "Finalizing shelf placement and moving bin",
    "Finalizing the craft assembly",
    "Fine-tuning bead placement",
    "Finish and place origami star",
    "Finish cutting along the marked line and reposition",
    "Finishing coil and selecting new strip",
    "Finishing cut and placing scissors down",
    "Finishing cutting and switching to phone",
    "Finishing segment and placing scissors",
    "Fold and grasp lantern",
    "Fold paper star",
    "Fold paper strip",
    "Fold paper strip into knot",
    "Fold paper strip into lucky star",
    "Fold paper strip into star",
    "Folding and organizing paper strips",
    "Folding and positioning cardboard",
    "Folding and shaping ribbon",
    "Folding and sorting paper stars",
    "Folding and sorting paper stars while handling a water bottle",
    "Folding cardboard",
    "Folding cardboard and checking phone",
    "Folding cardboard and handling utility knife",
    "Folding cardboard and preparing marker",
    "Folding cardboard edge",
    "Folding lucky star",
    "Folding paper strip",
    "Folding paper strip into lucky star",
    "Folding paper strips",
    "Folding paper strips while using phone",
    "Folding plastic strip",
    "Folding purple paper strip",
    "Folding purple ribbon",
    "Form paper strip into a star",
    "Forming quilled paper shapes",
    "Forming ribbon knot",
    "Gather and hold beads",
    "Gathering and boxing inventory",
    "Gathering and boxing plastic pieces",
    "Gathering cardboard pieces",
    "Gathering colored beads",
    "Gathering items",
    "Gathering materials and walking",
    "Gathering star beads",
    "Grasp lantern component",
    "Grasp paper strip",
    "Grasping and placing products on shelf",
    "Greeting participants",
    "Guiding utility knife along ruler",
    "Handle and prepare paper coil",
    "Handle container from box",
    "Handle crate of cans",
    "Handle paper lantern component",
    "Handle power bank and cable",
    "Handling and organizing containers",
    "Handling charging cables",
    "Handling container lid",
    "Handling earbud case",
    "Handling electronic device",
    "Handling miscellaneous items",
    "Handling plastic strip",
    "Handling shipping box",
    "Handling snack packages",
    "Hang shopping bag and exit area",
    "Hold and carry tray of canned goods",
    "Hold and cut newspaper with scissors",
    "Hold and mark cardboard piece",
    "Hold blue product box",
    "Hold instructional sign",
    "Hold newspaper",
    "Hold paper strip",
    "Hold quilling paper",
    "Hold small object",
    "Hold small white box",
    "Holding a smartphone",
    "Holding and adjusting cardboard",
    "Holding and aligning paper strip",
    "Holding and bagging a smartphone box",
    "Holding and creasing purple paper",
    "Holding and grasping product bags",
    "Holding and inspecting product",
    "Holding and organizing product packages",
    "Holding and retrieving paper strips",
    "Holding and rotating paper strip",
    "Holding cardboard pieces",
    "Holding cardboard with ruler",
    "Holding container of canned food",
    "Holding pen and paper",
    "Holding smartphone",
    "Holding writing materials",
    "Inflate paper star",
    "Initiating assembly",
    "Inspect product",
    "Inspect shelf condition",
    "Inspect shelf condition and observe surroundings",
    "Inspecting Dior gift box",
    "Inspecting almond package and scanning shelves",
    "Inspecting and approaching shelf",
    "Inspecting and bagging a smartphone box",
    "Inspecting and folding cardboard pieces",
    "Inspecting and packing supplement bottle",
    "Inspecting and placing cans on shelf",
    "Inspecting and placing cardboard strips",
    "Inspecting and stocking shelf items",
    "Inspecting bottle",
    "Inspecting cardboard",
    "Inspecting pieces and switching to scissors",
    "Inspecting shelf contents",
    "Inspecting supplement bottle",
    "Inspecting the cleaned plastic jar",
    "Install display hooks",
    "Interacting with coworker",
    "Interacting with phone",
    "Interlocking the craft strips",
    "Interruption: handling charging case",
    "Labeling and organizing cardboard squares",
    "Labeling and placing cardboard square",
    "Labeling and placing cardboard squares",
    "Labeling and retrieving cardboard pieces",
    "Labeling and switching markers",
    "Labeling cardboard pieces",
    "Labeling cardboard square",
    "Labeling cardboard squares",
    "Leaving the room and retrieving object",
    "Managing shopping container",
    "Manipulate adhesive strip",
    "Manipulate and inspect colorful pieces",
    "Manipulate and release paper strips",
    "Manipulate colorful pieces",
    "Manipulate craft pieces",
    "Manipulate light blue strip",
    "Manipulate paper decoration",
    "Manipulate paper edge",
    "Manipulate paper piece",
    "Manipulate paper strip",
    "Manipulate paper strips",
    "Manipulate puzzle piece",
    "Manipulate puzzle pieces",
    "Manipulate quilled paper strip",
    "Manipulate small paper segment",
    "Manipulate star and prepare next strip",
    "Manipulating and placing paper shapes",
    "Manipulating and placing strip components",
    "Manipulating and releasing paper strips",
    "Manipulating and releasing quilling strips",
    "Manipulating beads",
    "Manipulating cardboard and picking up scissors",
    "Manipulating cardboard piece",
    "Manipulating cardboard shapes",
    "Manipulating components on a strip",
    "Manipulating paper quilling piece",
    "Manipulating paper star",
    "Manipulating paper stars",
    "Manipulating paper strip",
    "Manipulating paper strips",
    "Manipulating plastic strip",
    "Manipulating puzzle pieces",
    "Manipulating quilled paper",
    "Manipulating ribbon piece",
    "Manipulating small object",
    "Manipulating tools and quilling materials",
    "Manipulating yellow strips",
    "Mark cardboard for cutting",
    "Mark cardboard with marker",
    "Mark fabric",
    "Mark fabric and reposition ruler",
    "Mark fabric with pen and remove ruler",
    "Mark fabric with pen and ruler",
    "Mark lines on cardboard",
    "Marking and cutting cardboard",
    "Marking and positioning cardboard",
    "Marking cardboard",
    "Marking cardboard and preparing to cut",
    "Marking cardboard measurements",
    "Marking cardboard piece",
    "Marking cardboard piece and preparing workspace",
    "Marking cardboard pieces",
    "Marking cardboard squares",
    "Marking cardboard with pen",
    "Marking dimensions on cardboard",
    "Marking grid lines",
    "Marking guidelines on cardboard",
    "Marking lines and repositioning ruler",
    "Marking lines on cardboard",
    "Marking lines with pen",
    "Marking list and moving blue beads",
    "Marking list and sorting beads",
    "Marking paper and adjusting piles",
    "Measure and mark cardboard with ruler",
    "Measuring and adjusting workspace",
    "Measuring and marking cardboard",
    "Measuring and marking cardboard for crafting",
    "Measuring and marking cardboard for cutting",
    "Measuring and marking cardboard with ruler",
    "Monitoring task progress via smartwatch",
    "Move product towards shelf",
    "Move to stocking area",
    "Move towards shelf and position tray",
    "Moving along the aisle",
    "Moving along the aisle to assess stock",
    "Moving along the shelves",
    "Moving and adjusting the vacuum cleaner",
    "Moving around the kitchen",
    "Moving away from and returning to the table",
    "Moving away from workstation",
    "Moving cardboard cutouts",
    "Moving cardboard pieces across the workspace",
    "Moving container and stocking items",
    "Moving hand over pile and sorting orange buttons",
    "Moving orange buttons",
    "Moving orange buttons and interacting with smartphone",
    "Moving origami stars",
    "Moving plastic storage bin",
    "Moving the vacuum cleaner",
    "Moving through the room",
    "Moving through workspace",
    "Moving to workspace",
    "Moving towards aisle",
    "Moving utility knife along ruler",
    "Moving, placing, and adjusting puzzle pieces",
    "Navigating store and browsing shelves",
    "Observe puzzle progress",
    "Observe workspace",
    "Observe workspace and reach for beads",
    "Observing and pausing",
    "Observing restocking needs",
    "Observing shelf and relocating to next aisle",
    "Observing workspace",
    "Opening cardboard box",
    "Operate and release smartphone",
    "Organize and count beads",
    "Organize inventory and reach for products",
    "Organizing buttons into patterns",
    "Organizing canned goods in container",
    "Organizing cans into a storage box",
    "Organizing cardboard pieces",
    "Organizing container contents",
    "Organizing paper pieces into piles",
    "Organizing paper strips",
    "Organizing pickle jars and maintaining cleaning tools",
    "Organizing products into box",
    "Organizing products on shelf",
    "Organizing shelf and placing plush toy into bag",
    "Organizing shelf display",
    "Organizing shelf products",
    "Organizing shelf workspace",
    "Organizing snack packages in box",
    "Organizing snack pouches into containers",
    "Organizing snacks in box",
    "Organizing stars into a row",
    "Organizing tools and materials",
    "Pack beads into box",
    "Paper quilling craft",
    "Peeling and disposing of shelf labels",
    "Performing precision cuts on cardboard",
    "Pick up and begin folding paper strip",
    "Pick up and deposit beads into box",
    "Pick up and inspect light blue strip",
    "Pick up and place accessory on shelf",
    "Pick up and place buttons",
    "Pick up and place canned goods on shelf",
    "Pick up and place product on shelf",
    "Pick up and place puzzle piece",
    "Pick up and place star-shaped beads",
    "Pick up and place tiles on stack",
    "Pick up cereal boxes",
    "Pick up electronic accessory from box",
    "Pick up grocery item",
    "Pick up product from box",
    "Pick, place, and count beads",
    "Picking and moving items to shelf",
    "Picking and placing items from bin onto shelves",
    "Picking and stocking items from container",
    "Picking up and bagging a charging cable",
    "Picking up and bagging an electronic item",
    "Picking up and packing products",
    "Picking up and placing canned goods",
    "Picking up and placing tiles",
    "Picking up canned goods",
    "Picking up knife and cutting cardboard",
    "Place accessory on shelf",
    "Place and adjust items on shelf",
    "Place and retrieve items for stocking",
    "Place canned food on shelf",
    "Place down paper segment and reach for supplies",
    "Place down paper strip",
    "Place grocery item on shelf",
    "Place product on shelf",
    "Place puzzle piece",
    "Place white box, adjust smartphone, and resume sorting",
    "Placing and adjusting plush toys",
    "Placing and arranging cans on the shelf",
    "Placing and retrieving canned goods",
    "Placing and scanning for puzzle pieces",
    "Placing and searching for puzzle pieces",
    "Placing canned food onto shelf",
    "Placing canned goods on the shelf",
    "Placing canned goods onto the shelf",
    "Placing canned goods onto the shelf and retrieving container",
    "Placing cans onto the shelf",
    "Placing cardboard piece",
    "Placing container on floor",
    "Placing containers on the shelf",
    "Placing down scissors",
    "Placing held items on shelf",
    "Placing items and checking phone",
    "Placing items and returning to box",
    "Placing items and transitioning",
    "Placing items into and organizing shopping bag",
    "Placing items into the bin",
    "Placing items on shelf",
    "Placing items on shelf and moving box",
    "Placing items on shelf and retrieving new items",
    "Placing items on the shelf",
    "Placing jar on shelf",
    "Placing product bags on shelf",
    "Placing products on shelf",
    "Placing ribbon onto project",
    "Placing snack packages in box",
    "Placing snack packages on shelf",
    "Placing, rearranging, and cleaning shelf items",
    "Position ruler and draw initial lines",
    "Position tray and reach for beads",
    "Position utility knife and begin cutting",
    "Positioning and cutting cardboard",
    "Positioning and cutting cardboard piece",
    "Positioning cardboard piece",
    "Positioning cardboard pieces",
    "Positioning container near the shelf",
    "Positioning newspaper and scissors",
    "Positioning paper strip",
    "Positioning puzzle piece",
    "Positioning ribbon piece",
    "Positioning ruler and drawing lines",
    "Positioning ruler for cutting",
    "Positioning ruler for measurement",
    "Positioning scissors to cut cardboard",
    "Positioning shelving dividers",
    "Positioning the container on the floor",
    "Positioning utility knife",
    "Preparation and initial cutting with utility knife",
    "Prepare for further marking",
    "Prepare shelf for stocking",
    "Prepare to cut cardboard",
    "Prepare tools for marking",
    "Prepare workspace and tools",
    "Preparing and folding cardboard",
    "Preparing container on shelf",
    "Preparing craft area",
    "Preparing for further sorting",
    "Preparing materials",
    "Preparing materials and positioning hands for quilling",
    "Preparing shopping bag",
    "Preparing to organize container bin",
    "Preparing tools and materials",
    "Preparing workspace",
    "Preparing workspace for craft activity",
    "Preparing workstation",
    "Pushing the vacuum cleaner",
    "Reach for and adjust Mahjong tiles",
    "Reach for items in box",
    "Reach for, pick up, and attempt to fit puzzle piece",
    "Reaching for and adjusting shelf containers",
    "Reaching for and picking up stars",
    "Reaching for products",
    "Reaching for products and preparing the shelf",
    "Reaching for utility knife",
    "Reaching into the box for more stock",
    "Rearrange Mahjong tile",
    "Rearrange Mahjong tiles",
    "Rearranging containers on the shelf",
    "Rearranging items from shelf back to box",
    "Recording star count",
    "Refining bead arrangement with marker",
    "Refining button layout",
    "Refining cardboard cuts",
    "Release and adjust puzzle piece",
    "Release and prepare new strip",
    "Release paper strip",
    "Release scissors and operate smartphone",
    "Releasing paper and reaching for phone",
    "Releasing scissors",
    "Relocating storage bins along the aisle",
    "Remove packaging and prepare component",
    "Remove tools after marking",
    "Removing and discarding damaged items",
    "Removing items from bag and stocking them",
    "Removing labels and moving along the shelf",
    "Removing old shelf labels",
    "Reorganize items in box",
    "Reorganizing stock on shelf",
    "Replenishing shelf stock",
    "Reposition and cut cardboard",
    "Reposition and cut newspaper",
    "Reposition ruler and draw lines",
    "Reposition sign and organize beads",
    "Repositioning and cutting cardboard pieces",
    "Repositioning stool for the next section",
    "Restocking pineapple chips",
    "Resuming cardboard cutting",
    "Resuming cutting",
    "Resuming cutting cardboard",
    "Resuming recording star count",
    "Resuming sorting paper stars",
    "Retrieve and move cardboard tray",
    "Retrieve and transport cereal",
    "Retrieve food items from boxes",
    "Retrieve product from box",
    "Retrieve snack packs",
    "Retrieving additional supplies",
    "Retrieving and carrying containers",
    "Retrieving and examining items from bag",
    "Retrieving and placing canned goods",
    "Retrieving and shelving container",
    "Retrieving cleaning supplies",
    "Retrieving items for bag placement",
    "Retrieving items from bag",
    "Retrieving items from boxes",
    "Retrieving items from shelf",
    "Retrieving materials",
    "Retrieving next product",
    "Retrieving plastic container and moving to aisle",
    "Retrieving smartphone",
    "Retrieving tools from bag",
    "Returning Dior gift box to shelf",
    "Returning canned goods to shelf",
    "Returning to desk",
    "Returning to desk and setting up smartphone",
    "Returning to table and placing controller",
    "Returning to the workspace",
    "Returning to work table",
    "Returning to workspace",
    "Returning to workstation",
    "Reviewing and organizing records",
    "Reviewing craft instructions",
    "Reviewing new product labels",
    "Roll quilling paper",
    "Rolling paper strips into coils",
    "Scanning workspace",
    "Scoring and cutting cardboard",
    "Scrolling and placing smartphone down",
    "Scrolling and setting down smartphone",
    "Scrolling and tapping on smartphone",
    "Scrolling and viewing content on phone",
    "Scrolling on smartphone",
    "Scrolling smartphone screen",
    "Search for and pick up puzzle piece",
    "Secure lantern with adhesive",
    "Secure paper edges with adhesive",
    "Securing ribbon with needle",
    "Select and handle paper strips",
    "Selecting a bottle",
    "Selecting and bagging electronic accessories",
    "Selecting and collecting bottled goods",
    "Selecting and collecting oil bottles",
    "Selecting and evaluating items",
    "Selecting and manipulating paper strips",
    "Selecting and packing spice jars",
    "Selecting and picking up canned goods",
    "Setting down water and picking up phone",
    "Setting up smartphone",
    "Sliding utility knife along ruler",
    "Sort Mahjong tiles",
    "Sort and adjust button line",
    "Sort and arrange buttons",
    "Sort and combine bead piles",
    "Sort and group beads",
    "Sort and place buttons",
    "Sort and record bead counts",
    "Sort beads",
    "Sort beads and adjust phone",
    "Sort beads and adjust tray position",
    "Sort beads and record count",
    "Sort beads by color",
    "Sort beads by hand",
    "Sort beads on table",
    "Sort beads on the table",
    "Sort buttons",
    "Sort buttons by color",
    "Sort canned goods in tray",
    "Sort colorful paper pieces",
    "Sort colorful pieces",
    "Sort craft materials into piles",
    "Sort purple beads",
    "Sort puzzle pieces",
    "Sort small colorful pieces",
    "Sort small craft pieces",
    "Sort star-shaped beads",
    "Sorting and collecting cardboard squares",
    "Sorting and counting beads",
    "Sorting and grouping buttons",
    "Sorting and processing cardboard strips",
    "Sorting and reaching for pieces",
    "Sorting and reaching for plastic pieces",
    "Sorting and stacking cardboard pieces",
    "Sorting beads by color",
    "Sorting blue beads and marking list",
    "Sorting blue beads and writing on paper",
    "Sorting buttons",
    "Sorting buttons by color",
    "Sorting cardboard pieces",
    "Sorting cardboard shapes and holding marker",
    "Sorting colorful paper stars",
    "Sorting gift boxes into a bin",
    "Sorting light blue origami stars",
    "Sorting orange button",
    "Sorting orange buttons",
    "Sorting origami stars",
    "Sorting origami stars by color",
    "Sorting pieces and retrieving smartphone",
    "Sorting pieces and writing on paper",
    "Sorting purple star-shaped objects",
    "Sorting quilled paper pieces",
    "Sorting small colored tiles",
    "Sorting small star-shaped plastic pieces",
    "Sorting squares and preparing for next cut",
    "Sorting star-shaped objects",
    "Sorting star-shaped objects by color",
    "Sorting tiles by color",
    "Sorting yellow star-shaped objects",
    "Stabilizing cardboard for cutting",
    "Stacking and organizing cardboard",
    "Stacking cardboard pieces",
    "Stacking cardboard squares",
    "Steadying the ruler and pen",
    "Stock multiple products on shelf",
    "Stocking and repositioning box",
    "Stocking canned goods",
    "Stocking canned goods onto the shelf",
    "Stocking containers on the shelf",
    "Stocking gift boxes on the shelf",
    "Stocking items and carrying container",
    "Stocking items and reaching for container",
    "Stocking jars on shelf",
    "Stocking miscellaneous products on shelf",
    "Stocking multiple cans on the shelf",
    "Stocking product boxes",
    "Stocking products and reorganizing bin",
    "Stocking products from bin onto shelf",
    "Stocking products on shelf",
    "Stocking sauce bottles on shelf",
    "Stocking snack packets on the shelf",
    "Stocking snack pouches on the shelf",
    "Stop measuring and transition to smartphone usage",
    "Stopping sorting activity",
    "Sweeping floor debris",
    "Taking a break to drink water and check phone",
    "Tapping and putting away smartphone",
    "Tear newspaper",
    "Tearing and preparing blue foam pieces",
    "Tidying workspace",
    "Touch pieces in box and interact with colleagues",
    "Touching canned goods",
    "Trace and remove pattern",
    "Trace and remove pattern piece",
    "Transferring items from shelf to shopping bag",
    "Transferring products from box to shelf",
    "Transition to new product selection",
    "Transitioning and observing workspace",
    "Transitioning from jar to tin can",
    "Transitioning from utility knife to scissors",
    "Transitioning to cutting",
    "Transitioning to new workstation",
    "Transitioning to smartphone usage",
    "Transport cereal to shelf",
    "Transport pasta to shelf",
    "Transporting cardboard to collection area",
    "Transporting snack packages to shelf",
    "Trimming and placing cardboard pieces",
    "Trimming and stacking cardboard pieces",
    "Trimming cardboard piece",
    "Typing and navigating on phone",
    "Typing message on smartphone",
    "Typing on smartphone",
    "Typing on smartphone while working with paper",
    "Unfold paper lantern",
    "Unpack additional lantern component",
    "Unpack and place items on shelf",
    "Use smartphone",
    "Using a smartphone",
    "Using and placing phone",
    "Using phone",
    "Using phone and drinking water",
    "Using phone and resuming work",
    "Using smartphone",
    "Using smartphone as a guide on cardboard",
    "Vacuuming along the wall edge",
    "Vacuuming the carpet",
    "Vacuuming the carpet corner",
    "Vacuuming the carpet edge",
    "Walk to and approach packing area",
    "Walk to shelf location",
    "Walking along the aisle",
    "Walking in workspace",
    "Walking through office",
    "Walking through the room",
    "Walking through workspace",
    "Walking to and approaching workspace",
    "Walking to storage area",
    "Walking to the crafting area",
    "Walking to workspace",
    "Walking to workstation",
    "Walking towards the desk",
    "Walking towards workstation",
    "Washing hands",
    "Wipe and place ketchup bottle on shelf",
    "Wipe and select ketchup bottle",
    "Wipe and transport product to shelf",
    "Wipe shelf and pick up product",
    "Wipe shelf and retrieve canned food",
    "Wiping and cleaning retail items",
    "Wiping and organizing grocery products",
    "Wiping counter",
    "Wiping product jars and shelf stocking",
    "Wiping shelves",
    "Wiping shelves and cleaning product items",
    "Wiping shelves and picking up products",
    "Wiping the plastic jar",
    "Working with paper strips",
    "Working with paper strips and using phone",
    "Write on paper",
    "Writing on paper and reaching for beads",
    "folding paper star",
    "folding paper stars and typing on smartphone",
    "folding paper strip",
    "folding paper strips and retrieving stapler",
    "folding paper strips into stars",
    "manipulating paper star and using smartphone",
    "manipulating paper strip",
    "typing on smartphone and picking up paper strip"
  ],
  "parallel_export": {
    "num_workers": 8,
    "shards": [
      {
        "shard_index": 5,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_05.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_05",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_05/dataset.jsonl",
        "seconds": 3015.303
      },
      {
        "shard_index": 3,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_03.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_03",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_03/dataset.jsonl",
        "seconds": 3091.636
      },
      {
        "shard_index": 4,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_04.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_04",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_04/dataset.jsonl",
        "seconds": 3128.09
      },
      {
        "shard_index": 6,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_06.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_06",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_06/dataset.jsonl",
        "seconds": 3340.064
      },
      {
        "shard_index": 2,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_02.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_02",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_02/dataset.jsonl",
        "seconds": 3375.476
      },
      {
        "shard_index": 7,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_07.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_07",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_07/dataset.jsonl",
        "seconds": 3461.252
      },
      {
        "shard_index": 1,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_01.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_01",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_01/dataset.jsonl",
        "seconds": 3534.427
      },
      {
        "shard_index": 0,
        "manifest": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/manifest_shard_00.json",
        "output_dir": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_00",
        "dataset_jsonl": "<project>/results/omni_finetune/xperience10m_qwen3_omni_128ep_96train_16val_16test_valmon_20260605_dataset/shards/shard_00/dataset.jsonl",
        "seconds": 3564.839
      }
    ],
    "seconds": 3569.987
  },
  "clip_policy": {
    "max_windows_per_episode": 32,
    "max_video_frames": 16,
    "audio_span": "same_as_video_context",
    "mosaic": "2x3 multi-camera grid"
  },
  "feature_manifest": [
    {
      "shard_index": 0,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 1,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 2,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 3,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 4,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 5,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 6,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    },
    {
      "shard_index": 7,
      "feature_manifest": [
        {
          "name": "hand_left_joints",
          "start": 0,
          "end": 441,
          "dim": 441
        },
        {
          "name": "hand_right_joints",
          "start": 441,
          "end": 882,
          "dim": 441
        },
        {
          "name": "body_joints",
          "start": 882,
          "end": 1974,
          "dim": 1092
        },
        {
          "name": "body_contacts",
          "start": 1974,
          "end": 2121,
          "dim": 147
        },
        {
          "name": "camera_translation",
          "start": 2121,
          "end": 2142,
          "dim": 21
        },
        {
          "name": "camera_rotation_matrix",
          "start": 2142,
          "end": 2205,
          "dim": 63
        },
        {
          "name": "imu_accel_gyro",
          "start": 2205,
          "end": 2247,
          "dim": 42
        },
        {
          "name": "depth_confidence",
          "start": 2247,
          "end": 3227,
          "dim": 980
        },
        {
          "name": "audio_fisheye_cam0_aac",
          "start": 3227,
          "end": 3395,
          "dim": 168
        },
        {
          "name": "caption_objects_interaction_text",
          "start": 3395,
          "end": 4291,
          "dim": 896
        },
        {
          "name": "slam_point_cloud",
          "start": 4291,
          "end": 4313,
          "dim": 22
        },
        {
          "name": "calibration",
          "start": 4313,
          "end": 4430,
          "dim": 117
        }
      ]
    }
  ],
  "available_modalities": [
    {
      "episode_id": "27c9fc42-2bb4-4737-b09c-08d2dd88aed4__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5100,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5100,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99764779676964,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5100,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "6dc018a4-0614-478c-9332-86bd6c4af9e8__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5139,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5139,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5139,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "17eea990-0d39-4cc8-a7c8-03fd56b4bf04__ep10",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5085,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5085,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00157306905773,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5085,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "994e4c6c-660a-49f2-90a7-3ebbbb55eb9b__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5855,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5855,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.810554803788904,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5855,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "6fbdecec-d4d5-477a-b94b-2486adb0dbd8__ep6",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5851,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5851,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5851,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "82c95b73-ba14-4083-8929-ddeb85d22e9f__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5855,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5855,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002732613745046,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5855,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "41e90813-8fff-4053-94f0-9537b1393bc2__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002018027714247,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "2aee3428-f462-49e6-95c4-b803c1803e0b__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5945,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5945,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.993275050437123,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5945,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "17901b9e-7d5d-475a-86f8-b4a9bc9a5709__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.000672404518557,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "13ca0290-713b-43a8-a06c-305bde0cbf6c__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "7258c332-1061-4c43-8242-f438d951db1f__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "1a76d123-ed27-4c4a-a8d4-06f3aaeda454__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "2f579b88-12fb-41c2-aa2a-9b8f5ae8f918__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5123,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5123,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003123048094942,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5123,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "4e3da960-c06f-4b2c-996d-fe6f04fa4e36__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.997310381925768,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "8a8e1b3c-607e-4ada-b3fd-fa639727e92c__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5102,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5102,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002351834430858,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5102,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a1012a57-385e-45a9-8a59-694a26fe92a5__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99193331540737,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "363abff7-e5ce-425e-a85c-5397186aefd2__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5093,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5093,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99215070643642,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5093,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "c09b25c6-218c-4e06-95ff-d63eccf20f2b__ep8",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5126,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5126,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002340823970037,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5126,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "81d4c5c5-b164-419c-86e0-c26347284f83__ep9",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5127,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5127,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003120611639883,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5127,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "53ccaadb-44df-4ddf-bc40-c1bcedb92faa__ep7",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5852,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5852,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003417634996584,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5852,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "c5e5183a-9eca-448a-9ec1-a0a40682b81a__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5863,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5863,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.559706470980654,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5863,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "8533707e-d7e0-4d1a-99d1-fa154a8e62ad__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5853,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5853,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.995901079382428,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5853,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "bc53027e-d29a-473f-8f18-7b524b801e40__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002018027714247,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "40611d4c-a36d-4ae3-8a71-da94b81cdce4__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99529443398763,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "960e7265-e8f2-4bca-9c21-501e2c250ce8__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5949,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5949,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0013446282103,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5949,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "0a5009c4-292b-40c6-b9ec-7c75cf54a112__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "22af1ff1-eaa9-4268-b96a-81a9fa35fe93__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "0073a4be-ec41-47f3-92d6-f63cf89aec9b__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "7f443115-54a4-4d50-acfb-e05fe506c270__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5129,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5129,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.001559575795383,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5129,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "628d6ea4-0a63-4d8f-9725-1e41d2a56b8c__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99663752521856,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "33f7ae08-ac1d-4321-9cb9-eca79016b359__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5109,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5109,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.998434564809017,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5109,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "9c553886-83c5-4dc4-be5c-dcb269b3a771__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002690341673393,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "0d330006-684f-4e93-bf38-06d53be3fe5f__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5124,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5124,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.35130644917686,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5124,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "85a956ae-65c6-4d11-9e7f-720d6d71ae5b__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5125,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5125,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.998439450686643,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5125,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "d5520c73-fa72-4e92-ad2a-4c3e48d8ad7c__ep6",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5853,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5853,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003417634996584,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5853,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "003dcaf0-edba-4787-ada0-187d2748f684__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5858,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5858,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002048340843917,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5858,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "81e9362f-fd63-4aec-92fa-1f489d6ac025__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5843,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5843,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.492995330220147,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5843,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "727f582a-fe2a-45c3-b506-216133a28c35__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002690341673393,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "832369c5-8fca-4591-940a-7a7a28206de2__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002018027714247,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "833144f1-bd03-4b93-bdc7-3d2e46aedcf1__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5949,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5949,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.998655552567893,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5949,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a39eaab1-ac8c-4c2d-9764-a566b773136e__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "2680606b-f296-4daa-baf9-7d58c90444bc__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "4a12e289-e4ed-405c-b198-96f704e94276__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "3ebbfff2-3a60-4cf4-af98-9db074a46e73__ep11",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5089,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5089,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.995285983658075,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5089,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "70a56200-9f80-4f13-8adb-33c0f931e1de__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.999327414581654,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "34f07a04-eb37-45a3-95ec-189ed5f4a85b__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5116,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5116,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003909304143864,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5116,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "b9dd769b-e31a-4fdb-945e-5a60db6487b0__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5945,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5945,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.998654648190502,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5945,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "705435da-879d-456e-a28e-f15f86e75027__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5106,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5106,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.996084573218482,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5106,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "322958e6-2d26-40d7-af3d-cb16362c78f7__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5163,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5163,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5163,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "4b7cc33d-56cf-4029-bda8-f154bd146447__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5180,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5180,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99459709786971,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5180,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a00c1d99-de08-42bc-8623-712b9dde7fde__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5849,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5849,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99863257213182,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5849,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "55f345d5-aa45-4d75-829b-a6ec41dca2ed__ep7",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5856,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5856,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003415300546447,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5856,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "cd364707-88fc-43bd-a95b-61aee9f8bd20__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5856,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5856,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.997951379404533,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5856,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "34353740-0ce5-4b2f-9394-f9fd9a19b8fe__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.992606533136176,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "c304368b-3b2c-46fc-8a19-c1de1e13dc75__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.999327414581654,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "53e64c93-8947-403e-ab35-3428c431aee8__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "21d33146-cd1f-40bd-b26b-0c64fd1d603f__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a93a840b-2d22-4231-9504-87ec4d930aad__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "5d994eb3-bc12-46dd-8984-da2d5f1a7055__ep9",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5089,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5089,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.992144540455616,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5089,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "573a5795-03bf-4f16-b4ce-bc09c2c56476__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "ba045ed4-ef25-404d-b756-8dcbd45b18fa__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99663752521856,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "65adf646-cb23-430e-9583-12482dd451a1__ep8",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5102,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5102,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99921617808434,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5102,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "af8e9345-011f-4c97-a78e-ecb4a268220f__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5084,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5084,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99449512425291,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5084,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "adb1bb6f-6df3-4f46-b895-f045ac3e0772__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5857,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5857,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.001365747063645,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5857,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "5e221284-f4af-4408-9177-25200282b6de__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5852,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5852,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003417634996584,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5852,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "999100c1-b488-4ed1-a580-c0487f308e5d__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5854,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5854,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00204974036622,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5854,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "b49d8a3c-7a1e-4ca3-8ce8-ae1cce0df001__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002690341673393,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "2a433534-63d5-48ad-b75e-a5607087b5df__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.000672404518557,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "2651c600-a427-42a5-bdc9-6e8ab74356eb__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.000672404518557,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "7ba21b77-14c9-47c5-8942-ef2ef5e02784__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.996666666666666,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "48b299c1-6c08-40a5-9b9d-9d170647a15a__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "b2bd37ae-1261-4a9c-82ee-6d50fec3550b__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "53f2c164-09dd-48ca-ae69-4f5955a902ed__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5851,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5851,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.714324215065353,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5851,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "9c7b2c19-5370-4a81-af68-6b76723f3c67__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "4b02bb38-384a-438a-b5f9-6131d85c34b0__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.996666666666666,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "0474d134-f983-4590-9cf9-29bd1c6e33cb__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5070,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5070,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99921123205553,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5070,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "59d0d93f-55c9-4a55-8cd4-e570cc0499d6__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5138,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5138,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.996108949416342,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5138,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "676c3db3-464e-406a-be9f-8283518e8181__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5865,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5865,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003410641200546,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5865,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "bf622eaf-363e-40c4-8a04-1dfedd85a718__ep10",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5849,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5849,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99863257213182,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5849,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "8692d5eb-19b2-4c49-9f88-da2ec373796e__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.999327414581654,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "dab5e5d1-9d11-43ad-ac6f-205500ff5ad4__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.999327414581654,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "d377bbb4-1bce-43ae-a41f-cefd23b8a8a2__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "4ab31463-5a47-4904-82c4-d859a0506e04__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "4318ba68-cc33-455d-bac1-6f8b66558708__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "d342e6e2-c381-4a1c-b0ac-e62a5c80624f__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5853,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5853,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00136668033347,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5853,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "34e4d6f3-f2b4-4de1-b837-15a372512a90__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "5399ef86-4df9-49bc-809f-8f4f92f9e659__ep6",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5851,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5851,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5851,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "b750fab3-7fbb-43a0-b451-c64c4d4a64da__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "0ffa6540-b99f-4909-9f80-c1b3e4c14a85__ep6",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5088,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5088,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003930817610062,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5088,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "90fe845b-df65-4297-838c-7924d4c3b6ad__ep9",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5095,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5095,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003140210394097,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5095,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "9f84a0a7-8964-48c5-b7e1-8a1d28094c86__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5849,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5849,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99863257213182,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5849,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "46b507a1-b1cb-4851-8558-9435de4abf68__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5870,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5870,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.988424349720823,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5870,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a3e06450-50f8-4894-a22f-1f891fad3809__ep7",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5854,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5854,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00204974036622,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5854,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "54bf2b92-a5f8-440c-81fe-8f820bb90aab__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "613e0f29-cc10-4d0c-b0ce-e39fe9c8a6b9__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99529443398763,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a2f2e433-d2c6-4ae1-80b9-c775a8428aa8__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5946,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5946,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99663752521856,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5946,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "c221c115-7b98-4d08-b5ab-653b5956c811__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "175a573b-7294-43b4-9c14-09c29ab3fef0__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "373850be-6393-4d15-985d-283da6cbe3e7__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "3cd70c8e-4ef5-481c-aa61-88b0dd4dec1f__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5843,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5843,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00273822562979,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5843,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "aed79382-cf3f-4b5c-89bb-46c322c19350__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "877779cd-25f3-4293-a3c4-39067dd9558c__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5844,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5844,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00273822562979,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5844,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "1796b943-caad-43c6-b9bd-80b8d601f37d__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "c5e31792-0961-463c-bfb4-ff89030c2ac8__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5157,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5157,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.992248062015506,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5157,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "638630bb-caf0-4367-a990-7a3d02dd395a__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5072,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5072,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99763481551561,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5072,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "0da1f6d2-6564-4f28-b248-1d1b71f9521b__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5061,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5061,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.001580527896316,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5061,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "84106bb9-1cf8-47b6-8d11-fddbfe381e4f__ep5",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5847,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5847,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5847,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "aa3ca3ec-56fd-4bbd-ad15-055eabc1838a__ep7",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5857,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5857,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.001365747063645,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5857,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "04d9f378-2812-4c7f-a269-1ad0bc43445f__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5844,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5844,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.003422313483917,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5844,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "3eb8ef88-902d-4e84-8a72-a361c9d18647__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5948,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5948,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002690341673393,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5948,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "3efd6a52-1457-4437-a3bf-9d5894614fe6__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5945,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5945,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.00336473755047,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5945,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "2f918260-6ba7-4132-8069-7972afedc1cf__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5947,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5947,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.997310381925768,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5947,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "a90b8b61-cbba-40fa-948c-b3da79fec1cb__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "bdfae17b-1e56-4cc5-a4dc-f4fad8369aed__ep1",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.996666666666666,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "37ee5802-66fb-4893-9173-fe97fe0e2000__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.002000533475595,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "c038defe-faa6-4fe9-aef6-84bd93726d1c__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5855,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5855,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 20.0,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5855,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "b5d76a3d-f4a3-4950-ab9d-344caa247059__ep4",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "ba18b7c1-21ff-45da-8452-41acce7fc8de__ep2",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5866,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5866,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99659168370825,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5866,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    },
    {
      "episode_id": "b6579cb5-0a71-4ca6-8808-1e2700be05c7__ep3",
      "modalities": [
        {
          "modality": "depth_confidence",
          "shape": [
            5998,
            140
          ]
        },
        {
          "modality": "audio/fisheye_cam0",
          "path": "fisheye_cam0.mp4",
          "shape": [
            5998,
            24
          ],
          "band_count": 16,
          "exists": true,
          "fps": 19.99933324443259,
          "has_audio": false,
          "num_samples": 0,
          "per_frame_dim": 24,
          "sample_rate": 16000,
          "source": "fisheye_cam0.mp4"
        },
        {
          "modality": "caption_text",
          "shape": [
            5998,
            128
          ],
          "fields": "objects,interaction"
        },
        {
          "modality": "slam_point_cloud_static",
          "shape": [
            22
          ]
        },
        {
          "modality": "calibration_static",
          "shape": [
            117
          ]
        }
      ]
    }
  ],
  "skipped_episodes": [
    {
      "shard_index": 2,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/0e4f59cc-c232-4ad0-9d0c-fed6e026422a/ep3",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 3,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/b1292f20-bfca-497b-a41a-e7fd62bbf913/ep2",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 3,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/cba9c19e-a55f-46e8-bda8-423cdcc2de5f/ep1",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 4,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/9dc8fc7c-977f-444a-9331-06d2dd7bf120/ep2",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 4,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/46f7dea3-76bd-4de4-a0fe-56c0c1e1a276/ep3",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 5,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/7f723cf6-13a4-451d-96bf-d37cbb3f84f3/ep9",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 5,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/5aeb0920-ab9f-4dc2-a261-747a678bf9cb/ep2",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    },
    {
      "shard_index": 5,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/480cb308-6ad0-4791-8bb6-f029f439548a/ep5",
      "reason": "No caption_frame_info_map found in annotation."
    },
    {
      "shard_index": 6,
      "episode_path": "<workspace-parent>/modelscope_data/xperience10m_128/acb1b145-804e-41fe-915e-16ff7f59433a/ep7",
      "reason": "No labeled windows were created. Try lowering --min-label-fraction."
    }
  ],
  "notes": [
    "Shard media and sensor-feature paths remain in shard output directories.",
    "Assistant answers are strict JSON for episode understanding, not robot-control policies.",
    "Merged label options are recomputed globally across all shards.",
    "Episodes with no labeled windows under the configured label rule are skipped and reported."
  ]
}