{ "title": "Ropedia Xperience-10M Figure Index", "status": "pass", "generated_at_utc": "2026-06-18T18:18:13+00:00", "scope": "Public figures, diagrams, charts, and derived modality thumbnails. Raw Xperience-10M videos, annotations, RRD files, and Qwen weights are excluded.", "figure_count": 29, "figures": [ { "id": "brand_logo_mark", "title": "Project logo mark", "path": "docs/assets/brand/xperience10m-logo-mark-512.png", "role": "Primary X-shaped multimodal camera mark used for the website header, README, HF cards, and brand identity.", "source_script": "scripts/build_brand_assets.py", "surface": "README, website, HF Space, artifact dataset, model card, favicon variants", "exists": true, "bytes": 234569, "sha256": "c1a2a0a62347c5abae909d12441f440dba979497d4b2f055459e2cf5ad9dd50a", "dimensions": { "format": "PNG", "width": 512, "height": 512 }, "source_script_exists": true }, { "id": "brand_social_card", "title": "Project logo social card", "path": "docs/assets/brand/xperience10m-logo-social-card.png", "role": "Large preview image for README, Hugging Face cards, and Open Graph/Twitter social sharing.", "source_script": "scripts/build_brand_assets.py", "surface": "README, website metadata, HF Space, artifact dataset, model card", "exists": true, "bytes": 173180, "sha256": "623bd7d8fb42b4d742a7c9d441fee5c829c4f9af4fe0db456cd52dd330cc1610", "dimensions": { "format": "PNG", "width": 1200, "height": 630 }, "source_script_exists": true }, { "id": "brand_favicon", "title": "Project favicon", "path": "docs/assets/brand/xperience10m-logo-favicon-64.png", "role": "Small dark-tile logo for browser tabs and compact navigation.", "source_script": "scripts/build_brand_assets.py", "surface": "website favicon and header", "exists": true, "bytes": 3471, "sha256": "187f801a47d4cb0ff308568763a3baa83bd63e263308895a36c4339b4e8fec57", "dimensions": { "format": "PNG", "width": 64, "height": 64 }, "source_script_exists": true }, { "id": "task_suite_infographic", "title": "Original task-suite infographic", "path": "docs/assets/task_suite_infographic.png", "role": "Primary visual map of the original task families, verified metrics, and sample modalities; the unified public suite is now documented as 20 tasks.", "source_script": "scripts/render_task_suite_infographic.py", "surface": "README, website, HF Space, artifact dataset, model card", "exists": true, "bytes": 1591194, "sha256": "95ab73e01cfba86538b63247869fae4091934ddedf9e22523ab4cead9c59086d", "dimensions": { "format": "PNG", "width": 1800, "height": 6600 }, "source_script_exists": true }, { "id": "pipeline_diagram", "title": "Episode-to-task pipeline diagram", "path": "docs/assets/pipeline_diagram.png", "role": "End-to-end data processing and evaluation pipeline overview.", "source_script": "scripts/generate_visualizations.py", "surface": "README, website, HF artifact dataset", "exists": true, "bytes": 704575, "sha256": "c90723cc4b1bf5490269af2df594849030ae8d4cc8176e1d1eab96fabf9412f9", "dimensions": { "format": "PNG", "width": 1800, "height": 1120 }, "source_script_exists": true }, { "id": "qwen3_omni_lora_pipeline", "title": "Qwen3-Omni LoRA training pipeline", "path": "docs/assets/qwen3_omni_lora_pipeline.png", "role": "Detailed raw-data-to-adapter flow for staged Xperience-10M Qwen3-Omni LoRA training.", "source_script": "docs/assets/qwen3_omni_lora_pipeline.prompt.md", "surface": "README, website, HF Space, artifact dataset, model card", "exists": true, "bytes": 1879166, "sha256": "41cc0ca137ae453834a98f5496ff5fab44654900154ccbfdb235767e604cd644", "dimensions": { "format": "PNG", "width": 1536, "height": 1024 }, "source_script_exists": true }, { "id": "spatial_intelligence_presentation_photo", "title": "Spatial intelligence slide diagram", "path": "docs/assets/foundation-pipelines/spatial-intelligence-pipeline.png", "role": "High-resolution slide diagram for the spatial intelligence pipeline track.", "source_script": "scripts/render_foundation_pipeline_diagrams.py", "surface": "README, website, HF Space, artifact dataset, model card", "exists": true, "bytes": 1808109, "sha256": "9bffa9c8e690f64f2c08b5bcfffd6d151b125dfe541bc059a199de797f6ca697", "dimensions": { "format": "PNG", "width": 2560, "height": 1920 }, "source_script_exists": true }, { "id": "human_video_world_model_presentation_photo", "title": "Human-video world model slide diagram", "path": "docs/assets/foundation-pipelines/human-video-world-model-pipeline.png", "role": "High-resolution slide diagram for the human-video world-model pipeline track.", "source_script": "scripts/render_foundation_pipeline_diagrams.py", "surface": "README, website, HF Space, artifact dataset, model card", "exists": true, "bytes": 1724429, "sha256": "9e9828dea816a2e67cabbe5cd19237113df2edc8b5f1c038cb843f77b45cd818", "dimensions": { "format": "PNG", "width": 2560, "height": 1920 }, "source_script_exists": true }, { "id": "vision_language_action_presentation_photo", "title": "Vision-language-action slide diagram", "path": "docs/assets/foundation-pipelines/vision-language-action-pipeline.png", "role": "High-resolution slide diagram for the VLA/action-policy pipeline track.", "source_script": "scripts/render_foundation_pipeline_diagrams.py", "surface": "README, website, HF Space, artifact dataset, model card", "exists": true, "bytes": 1553916, "sha256": "6d502580c9f11b170036843690dff0ef99e146890d9914046b5d4b165bd1f89b", "dimensions": { "format": "PNG", "width": 2560, "height": 1920 }, "source_script_exists": true }, { "id": "task_architectures", "title": "Minimal and neural task architecture map", "path": "docs/assets/task_architectures.png", "role": "Minimal and neural heads for the original task contracts and shared feature contracts.", "source_script": "scripts/render_overview_figures.py", "surface": "README, website, HF artifact dataset, model card", "exists": true, "bytes": 774391, "sha256": "f08b03bc21e194efe382347d74cf89cd6ac65dede51889971dbfc2fb9d1de3c2", "dimensions": { "format": "PNG", "width": 1800, "height": 2450 }, "source_script_exists": true }, { "id": "video_modality", "title": "Video modality thumbnail", "path": "docs/assets/modalities/video.jpg", "role": "Derived thumbnail for synchronized camera streams.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 82323, "sha256": "411a125e7b364a3f50d9f34ff5372b7a5f980239f0b393085a405ba839d39631", "dimensions": { "format": "JPEG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "audio_modality", "title": "Audio modality thumbnail", "path": "docs/assets/modalities/audio.png", "role": "Derived waveform thumbnail for the MP4 AAC stream.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 7075, "sha256": "50dfc7611bb3589ebe2965d44eb9dc641a3666e638968200ec63a0edc447e11a", "dimensions": { "format": "PNG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "depth_modality", "title": "Depth modality thumbnail", "path": "docs/assets/modalities/depth.jpg", "role": "Derived depth and confidence thumbnail.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 45018, "sha256": "155ba0181a1131864ebfd3492d3db38086645541d1892ba6a430d7f1387c0cf4", "dimensions": { "format": "JPEG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "pose_slam_modality", "title": "Pose / SLAM modality thumbnail", "path": "docs/assets/modalities/pose_slam.png", "role": "Derived camera trajectory and sparse map thumbnail.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 68057, "sha256": "5c3f59b6aa809c41c74be3cd8765a6f01f4c93306ce8fcb7fa9b79914666efd2", "dimensions": { "format": "PNG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "motion_capture_modality", "title": "Motion capture modality thumbnail", "path": "docs/assets/modalities/motion_capture.png", "role": "Derived body and hand motion-capture thumbnail.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 15078, "sha256": "fcd5564cd1dd49e01125c24e368fb64d9cc4631db65d6daa93885dbd065b344c", "dimensions": { "format": "PNG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "inertial_modality", "title": "Inertial modality thumbnail", "path": "docs/assets/modalities/inertial.png", "role": "Derived accelerometer and gyroscope trace thumbnail.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 46655, "sha256": "10eff24ca245b5d06a6f533ff53b584962baa00b83638b3ee4ac871fef4c7569", "dimensions": { "format": "PNG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "language_modality", "title": "Language modality thumbnail", "path": "docs/assets/modalities/language.png", "role": "Derived object-tag and caption thumbnail.", "source_script": "scripts/export_modality_atlas_assets.py", "surface": "website modality atlas, HF mirrors", "exists": true, "bytes": 15428, "sha256": "932895f67d58e98128b707c6c9e6ee320065e4a5945145d0fdec754ee8763392", "dimensions": { "format": "PNG", "width": 880, "height": 520 }, "source_script_exists": true }, { "id": "model_macro_f1_chart", "title": "Model macro-F1 comparison chart", "path": "docs/assets/charts/model_macro_f1.svg", "role": "Minimal-vs-neural classification score comparison.", "source_script": "scripts/generate_visualizations.py", "surface": "website diagnostics", "exists": true, "bytes": 3321, "sha256": "2984c0cde631cf891fe86c1b24248ce07595fa55efbf44391858d67f07a86386", "dimensions": { "format": "SVG", "width": 1100, "height": 284, "view_box": "0 0 1100 284" }, "source_script_exists": true }, { "id": "neural_score_chart", "title": "Neural MLP task score chart", "path": "docs/assets/charts/episode_task_scores_neural_mlp.svg", "role": "Neural MLP metric snapshot across the task suite.", "source_script": "scripts/generate_visualizations.py", "surface": "website diagnostics", "exists": true, "bytes": 5997, "sha256": "30b69843b06bddf7b05bcf527efd9d327728376e2f0cb27fd65c4febd425f2c4", "dimensions": { "format": "SVG", "width": 1100, "height": 556, "view_box": "0 0 1100 556" }, "source_script_exists": true }, { "id": "minimal_vs_neural_score_chart", "title": "Minimal-vs-neural task score chart", "path": "docs/assets/charts/episode_task_scores_minimal_vs_neural.svg", "role": "Side-by-side baseline comparison over the same window contracts.", "source_script": "scripts/generate_visualizations.py", "surface": "website diagnostics", "exists": true, "bytes": 10200, "sha256": "934ba7c1aa03985ebaaa38607ac83e7cbea9d7fb6093af5ad7d79bf59d26ed78", "dimensions": { "format": "SVG", "width": 1100, "height": 964, "view_box": "0 0 1100 964" }, "source_script_exists": true }, { "id": "research_direction_coverage_chart", "title": "Research direction coverage chart", "path": "docs/assets/charts/research_direction_coverage.svg", "role": "Four-track coverage map for Ropedia research directions.", "source_script": "scripts/generate_visualizations.py", "surface": "website directions", "exists": true, "bytes": 5078, "sha256": "fd4ba0a9d6d525bdfa8677c66e1a751efc83936dc032ce229bfca1ea106acb40", "dimensions": { "format": "SVG", "width": 1180, "height": 700, "view_box": "0 0 1180 700" }, "source_script_exists": true }, { "id": "research_direction_extension_chart", "title": "Research direction extension chart", "path": "docs/assets/charts/research_direction_extension_tasks.svg", "role": "Four coded extension probes, one per Ropedia research direction.", "source_script": "scripts/generate_visualizations.py", "surface": "website directions", "exists": true, "bytes": 6685, "sha256": "ab11b70fd8aac5f81779eb0f4b183fcee7f131eadea0d10a91ff45ccb09ca095", "dimensions": { "format": "SVG", "width": 1420, "height": 920, "view_box": "0 0 1420 920" }, "source_script_exists": true }, { "id": "tier2_task_suite_chart", "title": "Tasks 13-20 baseline chart", "path": "docs/assets/charts/tier2_task_suite.svg", "role": "Eight additional sample-supported tasks in the unified 20-task suite with aligned minimal and neural baseline metrics.", "source_script": "scripts/tier2_task_suite.py", "surface": "website unified task section, README, HF mirrors", "exists": true, "bytes": 5437, "sha256": "3e35e476f559cd6188e5417e4d28c25efc130abafc9cab2d941bc77d559177a1", "dimensions": { "format": "SVG", "width": 1440, "height": 832, "view_box": "0 0 1440 832" }, "source_script_exists": true }, { "id": "unified_task_model_radar", "title": "Unified 20-task model radar", "path": "docs/assets/charts/unified_task_model_radar.svg", "role": "Twenty-axis direction-aware comparison of minimal and neural MLP baselines, with 128-episode metadata, Qwen3, and Cosmos task-aligned overlay points and branch notes.", "source_script": "scripts/build_unified_task_model_radar.py", "surface": "website unified task section, README, HF mirrors", "exists": true, "bytes": 54276, "sha256": "66b3f285ecb9a3bf7d1125495fc3b6d4400edacb59700e06e9b504c9767d434e", "dimensions": { "format": "SVG", "width": 2400, "height": 1840, "view_box": "0 0 2400 1840" }, "source_script_exists": true }, { "id": "single_episode_task_model_radar", "title": "Single-episode 20-task model radar", "path": "docs/assets/charts/single_episode_task_model_radar.svg", "role": "Twenty-axis split radar for the one public-sample episode, comparing Minimal and Neural MLP as two complete 20/20 scored polygons.", "source_script": "scripts/build_unified_task_model_radar.py", "surface": "website unified task section, README, HF mirrors", "exists": true, "bytes": 35229, "sha256": "eae52facf93c6c674a82178e4ec1592f9d77fd5d5fcf8b11845deff7dbca3f6c", "dimensions": { "format": "SVG", "width": 2400, "height": 1840, "view_box": "0 0 2400 1840" }, "source_script_exists": true }, { "id": "episode128_task_model_radar", "title": "128-episode 20-task model radar", "path": "docs/assets/charts/episode128_task_model_radar.svg", "role": "Twenty-axis split radar for selected 128-episode methods: raw-feature simple/NN as complete scored polygons and metadata/Qwen/Cosmos as task-aligned overlays.", "source_script": "scripts/build_unified_task_model_radar.py", "surface": "website unified task section, README, HF mirrors", "exists": true, "bytes": 48263, "sha256": "9538bfb512f16bbd280151923adf8a23377bfaed2a8be5961a25eaf0a11d1404", "dimensions": { "format": "SVG", "width": 2400, "height": 1840, "view_box": "0 0 2400 1840" }, "source_script_exists": true }, { "id": "feature_blocks_chart", "title": "Feature block chart", "path": "docs/assets/charts/feature_blocks.svg", "role": "Feature allocation by modality block.", "source_script": "scripts/generate_visualizations.py", "surface": "website features", "exists": true, "bytes": 7889, "sha256": "c6589dff757ef4ca6e949cd346b0c54ab03e3120e20317ba0ad9d02f47377df8", "dimensions": { "format": "SVG", "width": 1100, "height": 760, "view_box": "0 0 1100 760" }, "source_script_exists": true }, { "id": "episode_task_scores_chart", "title": "Minimal task score chart", "path": "docs/assets/charts/episode_task_scores.svg", "role": "Minimal baseline metric snapshot across the task suite.", "source_script": "scripts/generate_visualizations.py", "surface": "website diagnostics", "exists": true, "bytes": 5983, "sha256": "5eb84b773b52663cb9a17769039f9bd29cf3f575bec5e9de0a887a6180977afa", "dimensions": { "format": "SVG", "width": 1100, "height": 556, "view_box": "0 0 1100 556" }, "source_script_exists": true }, { "id": "cross_modal_retrieval_chart", "title": "Cross-modal retrieval chart", "path": "docs/assets/charts/cross_modal_retrieval.svg", "role": "Retrieval behavior chart for the cross-modal task.", "source_script": "scripts/generate_visualizations.py", "surface": "website diagnostics", "exists": true, "bytes": 3196, "sha256": "869f4453b12efd99d13ad60d407cbff75666e41051cb7457d8ac662fcb4d8553", "dimensions": { "format": "SVG", "width": 1100, "height": 284, "view_box": "0 0 1100 284" }, "source_script_exists": true } ], "failures": [] }