parent_id stringlengths 16 32 | id stringlengths 16 32 | split stringclasses 1
value | messages_json stringlengths 630 244k ⌀ | tools_json stringclasses 204
values | task_type stringclasses 62
values | source stringclasses 32
values | domain stringclasses 16
values | subdomain stringclasses 62
values | teacher_model stringclasses 3
values | teacher_provider stringclasses 4
values | trace_kind stringclasses 3
values | disposition stringclasses 4
values | ground_truth_json stringlengths 1 26.1k ⌀ | source_record_hash stringlengths 71 71 ⌀ | prompt_cluster_id stringlengths 24 24 ⌀ | template_cluster_id stringlengths 24 24 ⌀ | dedup_cluster_id stringlengths 24 24 ⌀ | verifier_passed bool 1
class | family_oracle_passed bool 1
class | reference_agreement bool 1
class | format_score_raw float64 1 10 ⌀ | quality_flags listlengths 0 3 ⌀ | sampling_weight float64 0.4 4.21 | n_assistant_turns int32 1 12 ⌀ | n_tool_calls int32 0 13 ⌀ | schema_version stringclasses 3
values | source_repository stringclasses 20
values | source_revision stringclasses 21
values | source_license stringclasses 11
values | source_split stringclasses 4
values | source_item_id stringlengths 16 41 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
00027d004282ac60faef6d0985a483b3 | 00027d004282ac60faef6d0985a483b3 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | ARC-Easy | ARC-Easy | reasoning | ARC-Easy | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:85d5899bbfac3e0c6e9c4c259551819529e4e83f24c9831d56c2ba5f3fd9c492 | a8588fd102d83a0c264d56eb | 92d1408aa39293647f9953aa | 2d5e314f12be8cef143bca0f | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | validation | curated:aee4762772b12e5a |
0003b1c72f9d1cc94bbbd6f2fa360975 | 0003b1c72f9d1cc94bbbd6f2fa360975 | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:5663d0418e2754ae6c6b24c76706176dd0df95055ed4a4863f767d1dd06650e2 | b2106c9114db0bf749e8838e | 88d53ef1c8c245e26b43f212 | 772ca2f82e6fe16f0f3caee3 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:6c25a05a579c824b |
0006285035c8f96d854244e13595a369 | 0006285035c8f96d854244e13595a369 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "E" | sha256:c4e5cd2da11914b1e36165a995e122655c2671f7a80790f90dcf62c41dec528f | e1318ad8a77009233270ea28 | 98aa18dc710746b33a1e44d2 | d610b6f15bd166f41c6ab4a9 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:ed48e60216dfae10 |
000710d771ae7903c00ae72e6d5829e4 | 000710d771ae7903c00ae72e6d5829e4 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Let $r$ be the number of red balls and $y$ be the number of yellow balls.\nThe total number of balls is $r+y=10$.\nThe probability of drawing two red balls is $\\frac{r}{10}\\cdot \\frac{r-1}{9}=\\frac{r(r-1)}{90}$.\nWe are given that this probability is $\\frac{1}{15}$, so we have the equation $\\frac{r(r-1)}{90}=\\f... | sha256:a2b02b0e6b41822c7646c84d6fbf1cbd32fd06211570ab64ae155370e1f37c35 | 6ae35a71b0b9753f0f758685 | de7e5e4431f5da1a69b89f42 | 1475ab612982e42ad1d9bc8a | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:f10867b544fe4e2b |
00075a2060da00a97139e1a8c55a9072 | 00075a2060da00a97139e1a8c55a9072 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "A" | sha256:dc06198517e8cf47f062c68d16448cb264fa9355dfc848e36cc884026ab42e7c | 2e427d057cc2c630ec595c3b | 747ad8324bb2cf4ee4d1efa7 | 21e1693833212e85101b3073 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | validation | curated:479990ce5cc97294 |
000a72755abd88472961d104bedae058 | 000a72755abd88472961d104bedae058 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:a28f096c7450c60445f8e6b4d86ccd82eceba6435f75f5ce1cb461dd6cd231fc | 6a7cad8387929fc0dc264e8b | 3fa97b4a0cedf1ff0c76ec56 | 1d1624d5cfc9f0994a7fafe1 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | test | curated:e0eaf849de4f035e |
000b42533dfcdad910f05145c0764595 | 000b42533dfcdad910f05145c0764595 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | OrcaMath | OrcaMath | math | OrcaMath | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "If dividing a number by 4 gives you 12, then the original number is 4 times 12, which is 48.\n\nNow, if you want to divide this number by 3, you take the original number, 48, and divide it by 3:\n\n48 ÷ 3 = 16\n\nSo, the result of dividing the number by 3 is 16." | sha256:cbf141af7dfa394a35395dc131a09aadfa0bc1b2ec04523b94353210ecdf06e4 | 981251ee5220eb5ddbf8b3e4 | 1aa4d040ca6e456d1f9f495e | 34aa4398542bb84d01562305 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | train | curated:f4532c40489cb92b |
000c5ebfab11a439cc2b972d05b46495 | 000c5ebfab11a439cc2b972d05b46495 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Execute Python code in a sandboxed environment and return stdout/stderr.","name":"run_python","parameters":{"properties":{"code":{"description":"Python code to execute","type":"string"}},"required":["code"],"type":"object"}},"type":"function"},{"function":{"description":"Read the contents o... | code_debug | glm5.2-agent-tool-synthetic | agent_tool | code_debug | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"code_debug","expected_final":"The deterministic test must pass after correcting /tmp/agent_tool_workspace_11001366/src/totals.py so that compute([2, 4, 6]) returns 21; report the test output and the corrected behavior.","expected_tools":["run_python","read_file","patch_file","run_python"],"seed":11001366} | sha256:d95ec19bd6397bd6edad032d0b50fe977816fad5b47bc4b86dab709f16b0bec9 | dc38ef056d5783b8d6726595 | 8dab38b167e750e2a324c8ec | c545ab573c9eda34fdcf5659 | true | true | null | null | [] | 1.174049 | 4 | 5 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-code_debug-11001366 |
001161c894457e8291903acb18cfa067 | 001161c894457e8291903acb18cfa067 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "def sum_reverse(a: int, b: int) -> int:\n sum_of_integers = a + b\n return int(str(sum_of_integers)[::-1])" | sha256:2f95de969e60bf5c8ae78029bedd02bb5e4cdfa6de21ab384508253a2a0e8fb9 | 85eaa6dfd774c3946cec516b | 1414472db91cc5c0c7cf9b0f | 647277d4afb31474f8dc778d | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | validation | curated:7de1b857e7b31153 |
0013bd4d77e55d169f53707ace74a55e | 0013bd4d77e55d169f53707ace74a55e | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | OpenBookQA | OpenBookQA | reasoning | OpenBookQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "A" | sha256:c8ba8da2ab53d9c3f18191914fac5c599d13e9cfbca9217a3f77789ae2ecc2e4 | c58aa9d2b763653bdaca480f | e01da6285d95f78b6d3193f2 | 9a0b28a6095b8157c803699c | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/openbookqa | 388097ea7776314e93a529163e0fea805b8a6454 | unknown-see-provenance | train | curated:0b4609af6b73203f |
0014b9634d84248a49f3b3f200d7cd0e | 0014b9634d84248a49f3b3f200d7cd0e | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "In C++, the continue statement is used to skip the remaining code in the current iteration of a loop and move to the next iteration.\n\nHere's a C++ program that uses a continue statement within a nested while loop to find the first prime number greater than a given input number:\n\n```cpp\n#include <iostream>\n\nbool... | sha256:1694b6c85ce0947b12484ad19a5175c85bf5e853169d0234ad74e1bd86d8b144 | 0e56b08002fa9f65de99aa05 | 2bdaa0380c38c1db9f3d6b30 | 547a1b58f335ff862a3b3651 | null | null | null | 7 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:dac5634e7346de51 |
001578e6dbc00def788803e9c5f0b87a | 001578e6dbc00def788803e9c5f0b87a | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "To solve this problem, we need to determine the value of x, which represents the number of times Micah drank as much water in the afternoon as she did in the morning.\nLet's break down the information given:\nAmount of water Micah drank in the morning: 1.5 liters\nAmount of water Micah drank in the afternoon: x * 1.5 ... | sha256:a54166e4e91876f4b27d057eb488831108623875dc2bbd980a8e3afcd186f4dd | ad064eeeb9303ab24796742e | b20dd61a2fedc7de5baec282 | 2f71d12c61dc31293b8c32a1 | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | test | curated:cb0a42f5a8f89684 |
0016e51ad7645c9fd171e612d7889119 | 0016e51ad7645c9fd171e612d7889119 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Search for files matching a pattern or containing a text pattern.","name":"search_files","parameters":{"properties":{"path":{"default":".","description":"Directory to search in","type":"string"},"pattern":{"description":"Search pattern (glob or text)","type":"string"}},"required":["pattern"... | file_ops | glm5.2-agent-tool-synthetic | agent_tool | file_ops | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"file_ops","expected_final":"Search for the marker, verify the source, replace 'RETRY_LIMIT = 4' with 'RETRY_LIMIT = 6' in /tmp/agent_tool_workspace_10002411/src/parser.py, and read the file back to confirm the exact edit.","expected_tools":["search_files","read_file","patch_file","read_file"],"seed":100024... | sha256:2b0d66fce820abc94a0cd83212fb61d0622c5d449d64caf587ac522e7052de3b | bdb9d656b75681443461224a | 5b8a450ada3c9ddc96f151bf | 72da86036e0cb72202f15ee5 | true | true | null | null | [] | 1.611823 | 4 | 4 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-file_ops-10002411 |
001bfc0a2e7b486b046e3847de175320 | 001bfc0a2e7b486b046e3847de175320 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "The total ratio is 5+8 = 13\nBuzz's ratio is 5 out of 13, so he ate 5/13 * 78 = 30 slices of pizza\nThe waiter's ratio is 8 out of 13, so he ate 8/13 * 78 = 48 slices of pizza\nTwenty less than the number of slices the waiter ate is 48 - 20 = 28\n#### 28\nThe answer is: 28" | sha256:27f1f9ec078a9f871ce50b6fbd49f8f27bc7c3beb41890714d913a90bea09fe5 | 2ab461fa179f1951d05f5801 | 05ef2f507423a293cc752625 | d315c7f4b41611ff9fd1ade8 | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:21d51d3e225d0fa0 |
001e4b1b75ae256596d5d9e6558bfdc9 | 001e4b1b75ae256596d5d9e6558bfdc9 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "A" | sha256:f227ac70c32478aca9b227611f560f7b525ea89a7f1e4338f1311578f05cabeb | b1d6473b9ad08dcf3d969da1 | 729f6d43c9c7ab1e8ddc7789 | 0141ee0ca213de894168e3cc | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:d46febc305ff7afb |
001ecf012864e5edf330f2ae6731c2ba | 001ecf012864e5edf330f2ae6731c2ba | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Dave bought a total of 8 + 6 + 3 = 17 books.\nEach book cost $6, so Dave spent a total of 17 x $6 = $102 on the books.\n#### 102\nThe answer is: 102" | sha256:a484ff2a05ff5c980389ddc10c65342f1d1ca986a478b9b0e7d2223222f5e848 | 88a8a85507af54cf25433a2b | 1a0146c80bb1b5f561115784 | d468da82a3902815822bf9ef | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:7e7ddcb2acedbab1 |
001f0a24cbca61a5da82768d8344bcdd | 001f0a24cbca61a5da82768d8344bcdd | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here is a Python code that meets the requirements:\n\n```python\nnumbers = [1, 2, 3, 4, 5] # Sample list of numbers\n\n# Square and cube each number in the list\nsquared_cubed_numbers = [(num ** 2) ** 3 for num in numbers]\n\n# Print the squared, cubed numbers in reverse order\nfor num in reversed(squared_cubed_numbe... | sha256:71c57c0fd20c518c0f94d0c1df6a9d1124e89856854c262be31358196f480fb6 | d09e7b51065320ca0d308d32 | 8c10538e41959625b05f24a2 | fcd88524a515b32314de76fe | null | null | null | 8.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:e24b7212252505d1 |
001f85ef56d9238365791abce64d7b57 | 001f85ef56d9238365791abce64d7b57 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "#include <stdio.h>\n\nint main() {\n char str[] = \"Hello World\";\n char *ptr = str;\n char *end = ptr;\n \n while (*end != '\\0') {\n end++;\n }\n \n end--;\n \n while (end >= ptr) {\n printf(\"%c\\n\", *end);\n end--;\n }\n \n return 0;\n}" | sha256:e7df71d6269d25b7a71e07d87072d520edbb8f7abcb7ff4aa65533a563829179 | c57dc8e0b7b8033dc3f02ef0 | dc4b5e29c37552221e4cfd52 | a9ed0accff7b0b5b67a00284 | null | null | null | 8.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:1c5eff6425a2ec7f |
001fd1df5bfac8955be03c63a5dc8ed1 | 001fd1df5bfac8955be03c63a5dc8ed1 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:1c794a5098c9627d84f90c82346d474f990172b0b63bcd5773770147395c8d40 | eade235c3245069b489b7afc | 94cdc8f46d803525a5e734fe | f994e1d08c060dce706732aa | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:8c30a9271e00ba80 |
00208da0bd70e1d9a4a706a051f07c02 | 00208da0bd70e1d9a4a706a051f07c02 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:f8ac901824f2fa814bc26fb5fb0f9b1ba7fb285731d12d90776a05a7ede93172 | e0b85da215c6824c1383d9dd | b4047fa53c07e13c894642af | 04ef4eb1e32a0e46e48dfc35 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:23b363f6b1e65ce0 |
0022726714f83b06001ae853f8a77bce | 0022726714f83b06001ae853f8a77bce | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here's a Python program that creates a histogram for a given list of numbers by counting the occurrences of each unique pair of numbers:\n\n```python\ndef create_histogram(numbers):\n histogram = {}\n \n # Iterate through each pair of numbers in the list\n for i in range(len(numbers)):\n for j in ra... | sha256:f74e671a65d08baf71316c1f34e3314d879d18a22dbf8877eaf1c73c123a0100 | 3b3c056943832cb4ef6664cb | a71bbecb65dfc2072dac639f | 074a20d833373c45151d97a8 | null | null | null | 7 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:f7e1751cd78dc641 |
0022d4531e495ecdb14f54fbdbf5329d | 0022d4531e495ecdb14f54fbdbf5329d | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:13ab60ef3b1d4f9d31a26699687b47f4e0e759b4e1b180d0a1decdd97b5d0d59 | da2987a65c4e59aac8e8a4a8 | f13bc49228d74c28b8f6eba7 | 529ea81add74bb1def77182c | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:8e97e52e934923a1 |
0023e04b0cf0ca558b2e42927f4d38c6 | 0023e04b0cf0ca558b2e42927f4d38c6 | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:7fae2a57f4319ad0000e25f1cc819bb8edecf0e5b468583aa376096d33a68d71 | f83c27c7d9c592716c2144ad | c7be158f38c2128c3fab6d5b | 37e61beba88bd5e7c3e5e303 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:520d832407f8074e |
0024d4fbb5c8a867b91359d2861c2954 | 0024d4fbb5c8a867b91359d2861c2954 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Apply a transformation to JSON data (filter, map, reduce, restructure).","name":"json_transform","parameters":{"properties":{"input_path":{"description":"Path to input JSON file","type":"string"},"operation":{"description":"Operation: filter, map, reduce, restructure, merge","type":"string"... | json_csv | glm5.2-agent-tool-synthetic | agent_tool | json_csv | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_recovery | {"category":"json_csv","expected_final":"Transform /tmp/agent_tool_workspace_15001067/data/records.json by keeping records where active is true, write /tmp/agent_tool_workspace_15001067/out/active-records.json, and verify the JSON output.","expected_tools":["json_transform","json_transform","read_file"],"seed":15001067... | sha256:3a597129b35693f698b3ec9388ef12c4061a017d6ffb4b453a728f8cc432b552 | 2b70880185b034fa02d3a81c | 890e6513e7d4c1581ae4a16c | 15fa029634419f397d122338 | true | true | null | null | [] | 1.611823 | 4 | 4 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-json_csv-15001067 |
0024e78bbff47ae24020a9eb2310cbe2 | 0024e78bbff47ae24020a9eb2310cbe2 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "The bug in the provided code is that it replaces spaces in the search query with a plus sign (+), which is not the correct way to encode spaces in a URL. Instead, spaces should be encoded as \"%20\" in a URL.\n\nTo fix this bug, we can use the `urllib.parse.quote()` function in Python to properly encode the search que... | sha256:9c54e2456ffd0bef9edfb194e01ec624ad071b2383d91f2dce3cbd71f4059918 | fc66583eeea7cfec6f2cea88 | c8219644be10f791cd217feb | 8bf908e83544b8906089d7c2 | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:f6a50948fe0de037 |
00262645ccdee7c9d695b1846115bb4f | 00262645ccdee7c9d695b1846115bb4f | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | CodeAlpaca | CodeAlpaca | code | CodeAlpaca | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "#!/bin/bash\necho \"Welcome to the interactive calculator\"\nbc" | sha256:76c1821bf3510215460191ae7d6cdeed35b0884979f0f6abf1751f6c6ba5a5a8 | 6669203f28b8466ecc5fb65c | c196e4d14f95ebd4a6de5085 | 2794d45723b18b5dc9c34df3 | null | null | null | 8.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | validation | curated:b7a835b94fdc0f21 |
00275c52486af3f9e80b9bc3831664d1 | 00275c52486af3f9e80b9bc3831664d1 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here is a Python function that fulfills the given requirements:\n\n```python\ndef search_sorted_list(arr, target):\n if not isinstance(target, int):\n raise ValueError(\"Target element must be an integer.\")\n \n left = 0\n right = len(arr) - 1\n \n while left <= right:\n mid = (left + ... | sha256:02d552b57cf5cbb0a38890e0fcdc54bea67e6b0af4461be815bb9441b5cd9c92 | 07282ccb633dbe57f2321ec2 | c1e0bafdf2d7117e7b6e3622 | 6ca14d585ac52051d5751140 | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:f83d09bf5a0d6683 |
0028216a6c254000432af09df9496544 | 0028216a6c254000432af09df9496544 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Karl can choose 4 crayons out of the 12 in $\\binom{12}{4}=\\frac{12!}{4!8!}=\\boxed{495}$ ways.\nThe answer is: 495" | sha256:73060c078275a86f1dd69795fef8d9ebbbbf684e61db4d9059ac2127d847886b | 4d63b6d9d4681be3e13d943b | 1c125b8ec30b7b8b738bf218 | 31c059c732d2697bef71eaf9 | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:1829cdc895cbd582 |
00282bc41de80d0f8f4c76ec4864a713 | 00282bc41de80d0f8f4c76ec4864a713 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Jar A contains 28 marbles.\nJar B has 12 more marbles than Jar A, so it has 28 + 12 = 40 marbles.\nJar C has twice as many marbles as Jar B, so it has 40 * 2 = 80 marbles.\nThe total number of marbles in all three jars is 28 + 40 + 80 = 148.\n#### 148\nThe answer is: 148" | sha256:5f9feb1e55b0798e1485f3b12e614e0aeed1a03ce3b084a785ff9cf0ea81b93c | bf73b77397c9058d30d53d37 | 12bcf4d85ff312b7ded1bf0e | a636a39ac3f83f6bf7d9d96b | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:45360394c42cf560 |
00294962edad1acbbc60d86d93d947af | 00294962edad1acbbc60d86d93d947af | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:9fd65310fc02b324fd056f8e4547cdc322ae682ca75d1cc4cae79a8116c31b6c | 18ae37e60b36cd2482d69229 | d1e8d87f14c01fb88d0fb3a2 | 91e1e7998619f24c8ca918ea | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:6c1e67b372ce0cd8 |
002976e444f8ae6b253f1981baaed909 | 002976e444f8ae6b253f1981baaed909 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | CodeAlpaca | CodeAlpaca | code | CodeAlpaca | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "def is_even(n):\n return n % 2 == 0" | sha256:a483ac80fe73180d0b31f10c58fe32cb884feb2394e004cf2f78722057132398 | 8aafb2aca8b90644a6463560 | 519516bdb7020867fbb83251 | c1246001de12fc5d77a812b5 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:e313dfdbb427844f |
0029fd6270a92bd8291ebbf261331791 | 0029fd6270a92bd8291ebbf261331791 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "There are 12 choices for the first ball drawn, 11 choices for the second ball drawn, and 10 choices for the third ball drawn, for a total of $12 \\times 11 \\times 10 = \\boxed{1320}$ ways.\nThe answer is: 1320" | sha256:29c686c461d157e98cd24a0a8ca14f781e5d4e3633640a9d5e625ca02976004a | 073327e1ec70ee98aea88625 | 862e68d2163d00ae359713c7 | 8101b09c9a5b5520511f1cdd | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:56ac32831e2715c0 |
002b6bc0b6b859db1d9381d495419eed | 002b6bc0b6b859db1d9381d495419eed | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | ARC-Easy | ARC-Easy | reasoning | ARC-Easy | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:2a9b2dc1accfac18470c0703ff5e455cb3ab281d45ae3f957d51e9b031832552 | 14df383d865b4f825189efc4 | fbc71d56c504c8d4cb8e3c59 | 8281d7d79cf4529e6a0a7c3f | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:d4d8c91b32eb5b81 |
002bf28a9f06354b871844a9d729716e | 002bf28a9f06354b871844a9d729716e | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "def calculate(x, y): \n if isinstance(x, int) and isinstance(y, int): \n return x + y \n elif isinstance(x, float) and isinstance(y, float):\n return round(x + y, 15)\n elif isinstance(x, str) and isinstance(y, str):\n try:\n x = float(x)\n y = float(y)\n ... | sha256:fa27556d1500c342518fb2e3733ed0ab46ed4d734d2a3a94b7a94718a1bbccce | d5c5141001c27d3c924b90c0 | 8de99938c7e40ebb70d7980f | 3da002747ad4c2c5dbc89e99 | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:442da87d08e386e3 |
002bff538dc0eab6aec47e59b8144975 | 002bff538dc0eab6aec47e59b8144975 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "The cost of the 5 pansies is 5 x $2.50 = $<<5*2.50=12.50>>12.50.\nThe cost of the 5 petunias is 5 x $1.00 = $<<5*1=5.00>>5.00.\nThe total cost of the pansies, hydrangea, and petunias is $12.50 + $12.50 + $5.00 = $<<12.50+12.50+5.00=30.00>>30.00.\nThe discount on the purchase is 10% of $30.00, which is $30.00 x 10/100 ... | sha256:948b1af1a16e92c88cfa3152f376f75fd5256144a4badf07389a4f5414c7da1c | 187ffa97d383ef0f4a971a48 | 26116f06549457497b1c417f | 49e9ec643f5c4fff99f8c7ad | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:0ea98dd2911dcfa0 |
002eb74ef7908233dcca783bf71827a5 | 002eb74ef7908233dcca783bf71827a5 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Mary starts with 5 green crayons and gives out 3 green crayons, so she has 5 - 3 = 2 green crayons left.\nMary also starts with 8 blue crayons and gives out 1 blue crayon, so she has 8 - 1 = 7 blue crayons left.\nIn total, Mary has 2 green crayons + 7 blue crayons = 9 crayons left.\n#### 9\nThe answer is: 9" | sha256:b2dea9068c3cb007004fd1e7177ef3afa2aa67a672f52fed19f897ab6a73b82e | e29e5b9cbc7f52d444d4dcc4 | fbc7d598a87a5e6400aaac36 | 38f5f7b9ef139c87e7b77fc8 | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:59b46b76d74da4f8 |
0031cd8b0381ea25d0de02b5397ee08a | 0031cd8b0381ea25d0de02b5397ee08a | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "# Prompt the user to enter their age and store the value in a variable called \"age\"\nage = int(input(\"Enter your age: \"))\n\n# Initialize the factorial variable as 1\nfactorial = 1\n\n# Calculate the factorial using a loop\nfor i in range(1, age + 1):\n factorial *= i\n\n# Print the factorial\nprint(f\"The fact... | sha256:780f566d39bdcf3e9ca7c1e6ead5d6397b17e87f992858e9c858eb26cdeb5130 | 56f459af21151d7086163bb4 | b61edcaaee00bca105080d22 | 91d502a8aaea4506a7670ecd | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:e327b5265df32f6a |
003252f80d6c584344d2af727c6b8a3e | 003252f80d6c584344d2af727c6b8a3e | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | OrcaMath | OrcaMath | math | OrcaMath | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "A regular octahedron has 8 faces. Each face is an equilateral triangle, and the octahedron is one of the five Platonic solids." | sha256:07b7d10d456606471aabf94dad8576f0dd1f46ee9710318264a770dd22390fa9 | cc3c0648d82b067280d8c512 | 6ef12d26e40a3229e557baa7 | 5429b06e25ddbb22856ba6e0 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | train | curated:80541dfd6ff3d1f2 |
0032ab30a6e16cc6fbd7eceddb168c32 | 0032ab30a6e16cc6fbd7eceddb168c32 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:cc2a875fb3b6ac1d143271a2d077f2475e82f8e5f9f0a1febfc77de77e40c333 | 559bea5036624cc099f9e07c | 3de9f1caab6422fc3755fd37 | 83020951cf3aca4d9c1cf2f9 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:01df096d1ebac0a1 |
0033c30531600ce21ba91bfbb706bc8c | 0033c30531600ce21ba91bfbb706bc8c | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | CodeAlpaca | CodeAlpaca | code | CodeAlpaca | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Maximum Number = 11\nMinimum Number = -2" | sha256:9bf104fbe6d3a8246554d4afeef891dfec6df2553af801b03066af9ac7c892bc | 1e540af49b8b74257099cff5 | 6f94daf49746f2c08c5b4cde | aed949d3f7d571b23b5ba446 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:4a5b70a9d4cc6046 |
00343d4aa1a781f418454cc064dbffef | 00343d4aa1a781f418454cc064dbffef | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Read the contents of a file at the given path. Returns the file content as a string.","name":"read_file","parameters":{"properties":{"path":{"description":"Absolute or relative file path","type":"string"}},"required":["path"],"type":"object"}},"type":"function"},{"function":{"description":"... | recovery | glm5.2-agent-tool-synthetic | agent_tool | recovery | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_recovery | {"category":"recovery","expected_final":"Recover from the missing path, patch /tmp/agent_tool_workspace_12001260/config/worker.conf from timeout=8 to timeout=16, read it back, and report the verified final line.","expected_tools":["read_file","search_files","search_files","read_file","patch_file","read_file"],"seed":12... | sha256:917f70c320fd7fdd874898e8c83ce34ea6fe1e3812c88d6bc8f01487659745d2 | fbb98118d01b5a15d75bbdd2 | 27ecbfbb6a1cf98727e4919d | 329cf92b81fd33f524653e04 | true | true | null | null | [] | 1.611823 | 5 | 6 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-recovery-12001260 |
0034f1f8cbfd917365d3a3ed979c6315 | 0034f1f8cbfd917365d3a3ed979c6315 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "H" | sha256:16f7ffe6afed6eb9f2b7884490b6e540fb92cf2ff1731d35f7f275525767248a | 058e05d1192f9a76fd6f6152 | 9042bbefacab3bf56051984a | 2643dac9263dfa7d2f1592c1 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:59640fad82fae6ab |
0035a1f17bca61828450dae15019bcdc | 0035a1f17bca61828450dae15019bcdc | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Elyse had 100 pieces of gum.\nShe gave half, which is 100/2 = 50 pieces, to her brother Rick.\nRick then gave half of his, which is 50/2 = 25 pieces, to his friend Shane.\nShane received 25 pieces of gum from Rick.\nIf Shane chewed 11 pieces, then he has 25 - 11 = 14 pieces left.\n#### 14\nThe answer is: 14" | sha256:99d6e6002f75501785e2d496df157012e0291250527597900ea0a0283e469bb9 | b179dfd32c6ebd737d2b4650 | ed3e8c758b8af0423c53b81f | 436e7a0150b1e6ad384b73dc | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:8c03683cd1382a53 |
003845ae689566ee581132534764a73f | 003845ae689566ee581132534764a73f | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MATH/prealgebra | MATH/prealgebra | math | MATH/prealgebra | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "We will locate the numbers on the number line. $4.5$ goes half way between $4$ and $5$ because $0.5=\\frac{5}{10}=\\frac{1}{2}.$.\n\nNote that $4.45$ goes half way between $4.4$ and $4.5$ because $$0.4=\\frac{4}{10}=\\frac{8}{20}, \\ \\ 0.5=\\frac{5}{10}=\\frac{10}{20}, \\ \\ \\text{and} \\ \\ 0.45=\\frac{9}{20}.$$Li... | sha256:9261aae76d429c87770bba61be25c59e840b898f0c3390ecca911f3a59b07f26 | 4fd1f0769f605b8b55783e3f | a73e906b254f6b7230e27572 | e4e4622b0ba933cbaeb58daa | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:1681155f50ba6288 |
003a813c8c1819fb4992bbe874c5af40 | 003a813c8c1819fb4992bbe874c5af40 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "The variable x is a private integer that can only hold integers and must be initialized with a value greater than or equal to 100. Additionally, it must have a custom validation method that checks if the value is divisible by 5. The variable should have a setter method that throws an exception if the value is less tha... | sha256:489bae028155b804fdfc61f8a683d214de85add7c479b447ffc99627cb6d7349 | 0dbd5e3ffaaeb3836489a66c | a50b36e2b28d21331b4cf0a2 | 568178d6df9ab82487b0d99c | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:41b2d4e939191890 |
003b7533612e3fd36ac8c25aab9c1c53 | 003b7533612e3fd36ac8c25aab9c1c53 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | CodeAlpaca | CodeAlpaca | code | CodeAlpaca | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "INSERT INTO products (product_id, product_name, product_price)\nVALUES (5373, 'Disc', 15.99)" | sha256:5942e82df2200630a5cf16bf8946bc0619d9afde40a216f5aa4d138f8a051bb1 | ae349f6a5c5a8c84c5e8b961 | 29feebda9d32a2241190e8bc | 7626ff0cef8dd8561d1714f8 | null | null | null | 10 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:eaab9c9db5b2c603 |
003f3a2d56d0071b3b584315aa860ee6 | 003f3a2d56d0071b3b584315aa860ee6 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "for (let i = 1; i <= 100; i++) {\n let output = '';\n\n if (i % 3 === 0) {\n output += 'Fizz';\n }\n\n if (i % 5 === 0) {\n output += 'Buzz';\n }\n\n console.log(output || i);\n}" | sha256:981d8779c2057cae7e5ddecd9bde656c5c575fc4007b5927595f72af1775415a | 5254185a36ab4708bb3394a2 | e9fb250904e72e32d538e53e | 4f9296d08f7c7d11a59f92de | null | null | null | 8.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:3f0a19482ccddd62 |
004267792b470382c847718bc309d5ff | 004267792b470382c847718bc309d5ff | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MATH/algebra | MATH/algebra | math | MATH/algebra | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "We use the distance formula: \\begin{align*}\n\\sqrt{(2 - (-4))^2 + ((-6) - 3)^2} &= \\sqrt{6^2 + (-9)^2}\\\\\n& = \\sqrt{36 + 81}\\\\\n& = \\sqrt{117} = \\boxed{3\\sqrt{13}}.\n\\end{align*}" | sha256:c31e2efe82e6fb692f5a79413f7e45625e327cb443c07a634b165687a60678ca | f5611303810b24a062dd37c7 | 48ad61408b256f123327004e | b026a5656c86a49b7961eec8 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:8ea54cac2ed8b5ee |
00435c20dc1c69c6dd67bf1ab805668f | 00435c20dc1c69c6dd67bf1ab805668f | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Search for files matching a pattern or containing a text pattern.","name":"search_files","parameters":{"properties":{"path":{"default":".","description":"Directory to search in","type":"string"},"pattern":{"description":"Search pattern (glob or text)","type":"string"}},"required":["pattern"... | file_ops | glm5.2-agent-tool-synthetic | agent_tool | file_ops | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"file_ops","expected_final":"Search for the marker, verify the source, replace 'RETRY_LIMIT = 3' with 'RETRY_LIMIT = 7' in /tmp/agent_tool_workspace_10002212/src/settings.py, and read the file back to confirm the exact edit.","expected_tools":["search_files","read_file","patch_file","read_file"],"seed":1000... | sha256:1d39e49857cd423963350047a52fe0cc5361005594abea1cf10631b4522cff55 | 50017aa867d802b35808d21b | 01b8bb5acf854ae7970595fc | 8bb81874a0242541e234d2e1 | true | true | null | null | [] | 1.611823 | 4 | 4 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-file_ops-10002212 |
0043d68d20f4a595fc689e6908d85236 | 0043d68d20f4a595fc689e6908d85236 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "To convert a variable into a string using only bitwise operations, we can extract each individual digit from the variable and convert it to its ASCII representation.\n\nHere's a solution that converts a variable `a_variable` into a string using bitwise operations:\n\n```python\na_variable = 8\nstring_variable = \"\"\n... | sha256:ca61b1c509e9146685a1aecf98cffa1b63dfe506d27d1dac644ad2e1ad5d7222 | 3b8b79d27f0674074d03fd61 | 142bc1e79756f26e65e70205 | d9d42fb61e4bef982d3acd4a | null | null | null | 7.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:3bdc01ea571b9c08 |
0044ccc356f3984e1cc017537c79f903 | 0044ccc356f3984e1cc017537c79f903 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Read the contents of a file at the given path. Returns the file content as a string.","name":"read_file","parameters":{"properties":{"path":{"description":"Absolute or relative file path","type":"string"}},"required":["path"],"type":"object"}},"type":"function"},{"function":{"description":"... | file_ops | glm5.2-agent-tool-synthetic | agent_tool | file_ops | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_recovery | {"category":"file_ops","expected_final":"Search for the marker, verify the source, replace 'RETRY_LIMIT = 4' with 'RETRY_LIMIT = 5' in /tmp/agent_tool_workspace_10001247/src/settings.py, and read the file back to confirm the exact edit.","expected_tools":["read_file","search_files","read_file","patch_file","read_file"]... | sha256:d1bfc810a623fb0ad3e319947576aaf33ca47e681782ebdab62d4ee5cc671370 | 8e889bd35e25b6513d7c59a1 | e76c48fa9c7c7419c1c4fc5f | 472edbe78fe7c0111e8d3bd8 | true | true | null | null | [] | 1.611823 | 4 | 5 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-file_ops-10001247 |
0048a43afac118b95233f9dafbe02e37 | 0048a43afac118b95233f9dafbe02e37 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "D" | sha256:9554502dc758bd6bd8965630a54e6e9e5e66345c80ca1bb12efbd6b57b827ceb | f95879d596e7cacecf6666e0 | 711c74cdabce83ecd6395177 | aede989b09eda46ec9f3b097 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:0d48cb7bc19bf95b |
004b771e18c318296194b83aac649afb | 004b771e18c318296194b83aac649afb | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:9e7f3b0291901b3b99ad99e7adc817c31f1afff56b67615028c91f62ae1dfda5 | ff0b89820f1a27ec20ee7ae0 | 96927f69f45d9c6a93fb3492 | c8253d249cff7cf359568541 | true | null | true | 8.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:6e9372a451d946a0 |
004b8a05dbdc947097b66227870810f6 | 004b8a05dbdc947097b66227870810f6 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Search a fixed local document corpus and return matching passages.","name":"corpus_search","parameters":{"properties":{"query":{"description":"Search query","type":"string"},"top_k":{"default":5,"description":"Number of results to return","type":"integer"}},"required":["query"],"type":"obje... | multi_research | glm5.2-agent-tool-synthetic | agent_tool | multi_research | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"multi_research","expected_final":"Cite the retrieved passages for error rate=48 and throughput=120, then report the calculator result for 120 / 48 as 2.5000.","expected_tools":["corpus_search","corpus_search","calculator"],"seed":13000935} | sha256:0644cb0bf433027bfebd6c198b5c9f79011da99a09956cd737135af7d974bfb2 | 3a1ab48d838e488a46d97e65 | 46400b74650b0337ed857e98 | 82ae9a09ab39e597382e0593 | true | true | null | null | [] | 1.611823 | 3 | 3 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-multi_research-13000935 |
004c7ad6cd651395fac6c628db83f0ad | 004c7ad6cd651395fac6c628db83f0ad | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | Dolly | Dolly | instruction | Dolly | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "blue-grey" | sha256:c370e84d7370f80780bea65980f8ef6dc6fa5520543547225d8245500a1793df | 35a237655c0ef247cafb427d | 7295726b1a457f183944735e | f10660b770368c66654414f4 | null | null | null | 6.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | databricks/databricks-dolly-15k | bdd27f4d94b9c1f951818a7da7fd7aeea5dbff1a | CC-BY-SA-3.0 | validation | curated:b193711b42468725 |
004ecdfc3920f43541211657431aed12 | 004ecdfc3920f43541211657431aed12 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "If Cori is currently 3 years old, then in 5 years she will be 3 + 5 = 8 years old.\nIn 5 years, Cori will be one-third the age of her aunt, so her aunt will be 8 x 3 = 24 years old.\nTherefore, the current age of Cori's aunt is 24 - 5 = 19 years old.\n#### 19\nThe answer is: 19" | sha256:9760b8d9975b81df8f5a375d09f47e1c9c364b832640a86528a1f1cfe9228232 | 9a81a28147b6fc748da22ca6 | d12fffaf592d8cfb1fdbfa0a | b840711237adebebba38dd44 | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:0275c21c3e513d43 |
004f8aab3dc0a24bc578ed29579648cc | 004f8aab3dc0a24bc578ed29579648cc | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | Dolly | Dolly | instruction | Dolly | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Elon Musk" | sha256:abe954b6e3fb26f8afaa274530d958b77ec2e3c633c2e0952f85d012677ac9d9 | 0ebe12c8cb08891f245bf805 | 036a997006f66ea0897f8565 | ee0fa410c2e6156151a31786 | null | null | null | 7.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | databricks/databricks-dolly-15k | bdd27f4d94b9c1f951818a7da7fd7aeea5dbff1a | CC-BY-SA-3.0 | train | curated:4928737450c2e6e5 |
004fdf47b307005d717695b43ee29b3b | 004fdf47b307005d717695b43ee29b3b | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "H" | sha256:d0e89103ccf067b18a9953655277242d843137bf7ecf90ea4c22a11f7a8a71ef | fbfdb5bcaec3b0f1aa3051ea | 23a743f71eba0d134b37f970 | bba02224ca8cb74f05c7cd7e | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:1ebd8845c768c932 |
00502024a1c4c43c0c9b42796849395e | 00502024a1c4c43c0c9b42796849395e | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Read the contents of a file at the given path. Returns the file content as a string.","name":"read_file","parameters":{"properties":{"path":{"description":"Absolute or relative file path","type":"string"}},"required":["path"],"type":"object"}},"type":"function"},{"function":{"description":"... | code_debug | glm5.2-agent-tool-synthetic | agent_tool | code_debug | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"code_debug","expected_final":"The deterministic test must pass after correcting /tmp/agent_tool_workspace_11000470/src/windows.py so that group([2, 4, 6]) returns 46; report the test output and the corrected behavior.","expected_tools":["read_file","run_python","patch_file","run_python"],"seed":11000470} | sha256:eb8373d2ccf609519552ef6d5209e5a3916c1cd106d8aba478281de2cd21992a | 4424ad5f7dbcb4be9d6c4ace | 35fc792ad451854211cf5f1c | f9f5eb4b26d665dbe029ff96 | true | true | null | null | [] | 1.174049 | 5 | 7 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-code_debug-11000470 |
00507cd6839fcd90c76f401f33c17656 | 00507cd6839fcd90c76f401f33c17656 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:ebbe37f09dd3e56620761ca4bb02ac964c136b4f1382230688f47602d0eb4bd8 | 1b06a0a1a4896de907688f41 | 005119bda63ad1bac11fb1b8 | 415b2c9c59678e6147058b62 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:24b4c26162c348c8 |
00525d577c428cb8230d27714bef028b | 00525d577c428cb8230d27714bef028b | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | HumanEval | HumanEval | code | HumanEval | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | " return [x for x in values if isinstance(x, int)]\n" | sha256:662ee752adb5b26291c1cafb6351dc323e3c4c4737107d07b9d059f4b14bd4ef | fdba2302eba7c9c83715d5d8 | d332ec6fcd001eadcc0f846c | d65abeb6c35bd88ee9c8f7cc | null | null | null | 10 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | openai/openai_humaneval | 7dce6050a7d6d172f3cc5c32aa97f52fa1a2e544 | unknown-see-provenance | train | curated:67bce27c0d804b60 |
005415a167d4f63d014d3b3b87ed03c5 | 005415a167d4f63d014d3b3b87ed03c5 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:224269e91532d6c29fe749ccd9ae6b5fd70e6a9757bc2ea1d7dd98f2170912ce | e2ded9a71aa989a910d6ad1e | bcb0e43bd89a4c9c64ccd079 | e38343bb6897b9c395b03f33 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:b7d5dced9b32ecef |
00564af9a8ad724153bd7961f43318ef | 00564af9a8ad724153bd7961f43318ef | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | Dolly | Dolly | instruction | Dolly | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "French Bulldogs are a type of dog.\nRagdoll is a type of cat.\nBritish Shorthair is a type of cat.\nLabrador Retrievers are a type of dog.\nGolden Retrievers are a type of dog.\nGerman Shepherds are a type of dog.\nMaine Coon is a type of cat.\nPoodles are a type of dog.\nBulldogs are a type of dog.\nPersian is a type... | sha256:3b8b1bbd53d4c767d3afe94413a5cbe5676a47b0419ed2d44d4ef7ffdb93f5a8 | 34e944016c82fe8ad65c78c7 | 566ffb11685624f6bdad867d | d32f5a4821999c7debbd1d15 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | databricks/databricks-dolly-15k | bdd27f4d94b9c1f951818a7da7fd7aeea5dbff1a | CC-BY-SA-3.0 | train | curated:5d1101230234fdfb |
0058d44a0c6bd83d9fd45af46f8ff970 | 0058d44a0c6bd83d9fd45af46f8ff970 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "From the first equation, we have $x = y + 4$.\nSubstituting this into the second equation, we get $(y + 4)^3 - y^3 = 28$.\nExpanding and simplifying, we have $y^3 + 12y^2 + 48y + 64 - y^3 = 28$.\nThis simplifies to $12y^2 + 48y + 36 = 0$.\nDividing by 12, we get $y^2 + 4y + 3 = 0$.\nFactoring, we have $(y + 1)(y + 3) ... | sha256:cdfd6e4e3ecf0625f11b6c9547d54bf62290783bd816e84d7ddab291ead6511f | 8ea42eb516fa474a081694b4 | def53ad58ff9f6e5e2586e1f | 0f7bd6cb4cbe2f5b2eda5b6b | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:fe41a9e81b3ac6b7 |
005ba9ec726e1736e52f4a52ed2d5eed | 005ba9ec726e1736e52f4a52ed2d5eed | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MATH/intermediate_algebra | MATH/intermediate_algebra | math | MATH/intermediate_algebra | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "By Vieta's formulas, $pqr + pqs + prs + qrs = \\boxed{\\frac{1}{3}}.$" | sha256:a59e4a9f1584d096d330c3f2524d9978e8e7cd009da5d4b4f3b584c36aadc764 | 2c159d652ed189ea6f37ffe4 | 9bf8ec8455ca3fe408ba84b7 | c0f008ca35f614cf61529ba7 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | test | curated:bb0afd6f49c967e6 |
005cf4e66f76789db478b7c9a5dc0151 | 005cf4e66f76789db478b7c9a5dc0151 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | NuminaMath-CoT | NuminaMath-CoT | math | NuminaMath-CoT | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Let's calculate the number of occupied seats in each section and then the number of vacant seats.\n\n1. Awardees' row: 15 seats, all occupied, so 0 vacant seats.\n\n2. Administrators and teachers' rows: 45 seats, 9/10 occupied.\nOccupied seats = 45 * (9/10) = 40.5, which we can round down to 40 since we can't have hal... | sha256:dafa882e01bdac84bb0b48c63bbe0447264500e1b00bc0ca7d761c1dd84a76da | 551b995224bafd4d76202be2 | c7efb78229f18b0b33dc5c61 | 432268cb9b72dc7fe02dc258 | true | null | true | 9 | [
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | AI-MO/NuminaMath-CoT | 9d8d210c9f6a36c8f3cd84045668c9b7800ef517 | Apache-2.0 | train | curated:eff30f320ff83e98 |
005dbbb17229adafb1c613eb46599100 | 005dbbb17229adafb1c613eb46599100 | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:610fb2084422046cde177c661f34057eefc0c1daf39ce368a77592482435e436 | 0a7c275d2498c7773bc5ebad | e005ce255ce59b5bdcd3e36e | 529c8df9790c2426b3c23c7e | null | null | null | 7.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:1ad35e59b04fb54d |
005ef634df788ce523f1c2f39693300a | 005ef634df788ce523f1c2f39693300a | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Read the contents of a file at the given path. Returns the file content as a string.","name":"read_file","parameters":{"properties":{"path":{"description":"Absolute or relative file path","type":"string"}},"required":["path"],"type":"object"}},"type":"function"},{"function":{"description":"... | file_ops | glm5.2-agent-tool-synthetic | agent_tool | file_ops | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_recovery | {"category":"file_ops","expected_final":"Search for the marker, verify the source, replace 'RETRY_LIMIT = 4' with 'RETRY_LIMIT = 7' in /tmp/agent_tool_workspace_10001166/src/parser.py, and read the file back to confirm the exact edit.","expected_tools":["read_file","search_files","read_file","patch_file","read_file"],"... | sha256:66946115073bce3a7aadb51d7cc5443b862ec0e69b6fb40b5500af029e06a074 | b2fe2a02f835c165714bff3d | e622d68665aed7ce408ced91 | f1d9cccf6d610cb94e9d48cc | true | true | null | null | [] | 1.611823 | 4 | 5 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-file_ops-10001166 |
0060bbd8b43e4235817353dcf266f291 | 0060bbd8b43e4235817353dcf266f291 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here's one way to design a function that returns the maximum of three inputs without using comparison operators or mathematical functions:\n\n```python\ndef find_maximum(a, b, c):\n diff1 = a - b # difference between a and b\n diff2 = a - c # difference between a and c\n\n mask1 = (diff1 >> 31) & 1 # mask ... | sha256:1da2b534cc9a148062de5036ace5e1b3c982be94934e5c46915547c57c2198f6 | a8b7792de03734017d4f8f9f | 45d57efa92464c6239081de0 | dc37b18b382cba3d6893ea85 | null | null | null | 7.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | validation | curated:9f40d7e6d5b672e6 |
006114d539cb95e1d64b204ca5266f2e | 006114d539cb95e1d64b204ca5266f2e | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | ARC-Challenge | ARC-Challenge | reasoning | ARC-Challenge | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "D" | sha256:f95cbe306631906b9aca5fbef4aa90f5101d6e00344e46b6a0772667c2a5a179 | b2e98c1aa46443d2070a81c0 | 7a523786711b737bcf485233 | 4406aa22df6c91a68bea0c37 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:8a9772682946fe06 |
00611df8f852d6007f24b9c6c3117958 | 00611df8f852d6007f24b9c6c3117958 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "G" | sha256:8847833f9f891e523ff26d515b7299a0aa1840c5fc9591e9bf3791b2224f80e1 | 990197ae82d791c93c9c6eaa | abe4a2994c4606e8ccc0d683 | 40275c41e61e243e689db64d | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:63cb2b567654529c |
0061ba8aa665008dd977c1be7e9c3c44 | 0061ba8aa665008dd977c1be7e9c3c44 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Search a fixed local document corpus and return matching passages.","name":"corpus_search","parameters":{"properties":{"query":{"description":"Search query","type":"string"},"top_k":{"default":5,"description":"Number of results to return","type":"integer"}},"required":["query"],"type":"obje... | multi_research | glm5.2-agent-tool-synthetic | agent_tool | multi_research | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"multi_research","expected_final":"Cite the retrieved passages for error rate=48 and batch size=120, then report the calculator result for 120 / 48 as 2.5000.","expected_tools":["corpus_search","corpus_search","calculator"],"seed":13000474} | sha256:0cb5a6113eee9f2918e333a9309511417ab609aed96128550308618a805d1cc8 | 2d2fe488c671b5f53aa50e24 | b9c0d37585bd0df447d34632 | d69d5339f285d55b85456288 | true | true | null | null | [] | 1.611823 | 3 | 3 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-multi_research-13000474 |
0065d7c4c702da6eeb138fcafe8f519b | 0065d7c4c702da6eeb138fcafe8f519b | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "SELECT customer.name, customer.age, income.income, customer.address\nFROM customer\nJOIN income ON customer.customer_id = income.customer_id\nWHERE income.income > 50000 AND customer.age > 30\nORDER BY income.income DESC" | sha256:62a4366c4e97134c49d4d0405725425028563453af16a1e5b2657310c5fdab73 | 0d93105ea4478e53b3be07ed | 74ade4c6fefd127c78f19753 | 004d666c5dc6b04ce2cd4063 | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:0a951af13c9bcc5a |
006c85deec8679bd47b3e71a81661dec | 006c85deec8679bd47b3e71a81661dec | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | Dolly | Dolly | instruction | Dolly | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Quinoa: Grain\nMillet: Grain\nCouscous: Grain\nRibeye Steak: Animal\nPork Belly: Animal\nChicken Wing: Animal" | sha256:d1e5e541a67372dbc6f462b4fe89a2b9ad386bca1b7c7d87d6295b153dafa3fb | a5b411bc1d3fd05b43097974 | 7365e7490ee25600c860cf60 | 30c6630ec258d6da58a059f4 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | databricks/databricks-dolly-15k | bdd27f4d94b9c1f951818a7da7fd7aeea5dbff1a | CC-BY-SA-3.0 | train | curated:0525c319252abf4f |
006d50415ec39e8781c077fd5269289e | 006d50415ec39e8781c077fd5269289e | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:5701f23407fbb7ae949c0eca5d3e32712b7409ef3bfaccbaffd90e17ee1fd5d0 | 7c22fe35c9914e8641d3ac39 | 03afe6f4765a2ae463a62409 | 51cb901c73f11a30bd5a0f35 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:d240c03508303c01 |
006e72c00e8639923ebc1072330675d6 | 006e72c00e8639923ebc1072330675d6 | train | [{"content":"You are a careful deterministic workspace assistant. The workspace and local corpus described by the user are synthetic ephemeral fixtures, not the user's live files or live services. Solve the task by using the provided tools through native OpenAI function calling (the assistant message must contain a too... | [{"function":{"description":"Search a fixed local document corpus and return matching passages.","name":"corpus_search","parameters":{"properties":{"query":{"description":"Search query","type":"string"},"top_k":{"default":5,"description":"Number of results to return","type":"integer"}},"required":["query"],"type":"obje... | multi_research | glm5.2-agent-tool-synthetic | agent_tool | multi_research | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_success | {"category":"multi_research","expected_final":"Cite the retrieved passages for throughput=24 and batch size=240, then report the calculator result for 240 / 24 as 10.0000.","expected_tools":["corpus_search","corpus_search","corpus_search","calculator"],"seed":13001126} | sha256:1a59e7bd7bf0dc0af43b0fc1a9536d80cae47bf8f310a3de07c444df7bc7da60 | 4af5bdf15a8b34a7a2a3fed4 | 2b30a4248b06d9721a42d581 | ed8424fe069dbbfe58b337c3 | true | true | null | null | [] | 1.611823 | 4 | 4 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-multi_research-13001126 |
006e9f2ca9ac6393cf34c1e545c57195 | 006e9f2ca9ac6393cf34c1e545c57195 | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:dfd408e9b70d984e58663f93d4392dc2302e687d260edaeb07e63a9d3a1942df | 3284b041b46e716341bcea0c | be3b465a295f3c51c17fe53d | 4f1ab422391e9fffd8f4fc40 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:a6ac0e685a832938 |
006f6e2a461268829a43a9808302d253 | 006f6e2a461268829a43a9808302d253 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "D" | sha256:c7d8a3f0ea066e19e7b50732c1a762c12293439ec2c6e2bc8921c616e68f0372 | 30f688a0d404cd390ebe3893 | 508a060d8a5194a7cf1b370f | ca2f2219f3788ee55b66c830 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:4eef1f8869e1e6fd |
007155360c95a0d7f507c499ea69e9db | 007155360c95a0d7f507c499ea69e9db | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | OpenBookQA | OpenBookQA | reasoning | OpenBookQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "A" | sha256:1bc08cecffd3207bf9887c92092cd336372a5c8e756ac7f7e4598411f87beeb3 | d057ff7a68cebc1ac8fc18ff | 035687b3fbbbaa2e891683dd | 7ed35332d8d65535270afc68 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/openbookqa | 388097ea7776314e93a529163e0fea805b8a6454 | unknown-see-provenance | train | curated:bd62816194121c14 |
00715a0d91eff0890231e7d5e660464f | 00715a0d91eff0890231e7d5e660464f | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here's an implementation of a class in Python that sorts an array of numbers in increasing order without using any built-in sorting function and with a space complexity of O(1):\n\n```python\nclass Sorter:\n def sort_array(self, nums):\n n = len(nums)\n for i in range(n):\n min_idx = i\n ... | sha256:e44bcfd65b04ab802191e86c6942007ae953c9460b873e6e147bcba715c8b257 | 0b83afdc151e5d097c619f64 | a7e6f12e0ab1639cfff87cfd | ead71d1a645936bd1cb5bd57 | null | null | null | 9 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:b889b647dcd4243f |
0072637b22b66d8d1c96514ffe00d417 | 0072637b22b66d8d1c96514ffe00d417 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | MBPP | MBPP | code | MBPP | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "def long_words(n, str):\n word_len = []\n txt = str.split(\" \")\n for x in txt:\n if len(x) > n:\n word_len.append(x)\n return word_len\t" | sha256:197d50d5d4cc24a1f30863cf9536b12698e3febd5df3e476984b44274478d60b | db4de3fa2427d66144886f4a | 8a0d0e69018b5f0138449b32 | 3349015c5d50d3a57f4b5e89 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | google-research-datasets/mbpp | 4bb6404fdc6cacfda99d4ac4205087b89d32030c | CC-BY-4.0 | train | curated:0a325e7b0e29fbd5 |
0073202c6fde928c53f8d937bb73702c | 0073202c6fde928c53f8d937bb73702c | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here's a Python code that sorts the given list of strings in ascending order based on the length of each string, while ignoring any strings that contain the letter \"e\". The time complexity of this code is O(n log n), where n is the length of the list, and the space complexity is O(n).\n\n```python\ndef sort_strings(... | sha256:91ab60bb222f80d2090d4e08f7ae56ef9b785e91415e767c26c2ff1e171fb706 | 9c53f63dfb9217339534fe46 | 9d1fa57e20eaedd10457ba9b | 65594c6c947545882d297759 | null | null | null | 7.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:b903488f6dc817b0 |
0074af740c8af891f556e5cc62d9f795 | 0074af740c8af891f556e5cc62d9f795 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "D" | sha256:efa25caf799242f9ddf55cd357806bc161eb67c08c1c2ec3770bb6806a1f1a49 | de0fa4045f79bae34e1c700e | 4dc08fe3bd425c9f5b03074a | 737b0227e6ce79ccb33c10ec | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:c7417af1e1679f2c |
0076da686b8b654ff0e9426f3a7e7bf7 | 0076da686b8b654ff0e9426f3a7e7bf7 | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | gsm8k | gsm8k | math | gsm8k | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "40" | sha256:b817dd7058d846606361cceb6d62009043540eb16b1b71a31a09c917a0d34804 | 48bdbd97f7a1a98c06ed451a | 84302546b25c204a55d6370c | 83ea4e776e3f0ef841b1ba1a | true | null | true | 10 | [] | 1 | 1 | 0 | 1.0.0 | openai/gsm8k | 740312add88f781978c0658806c59bc2815b9866 | MIT | train | curated:0f0a1d9ffdc1e11c |
00785d91d626fa41f11eb8e6b0684734 | 00785d91d626fa41f11eb8e6b0684734 | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | CodeAlpaca | CodeAlpaca | code | CodeAlpaca | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "An example of a memoization technique in programming is to store the result of a function call in a lookup table. When the function is called for the same input in the future, the stored result can be accessed quickly from the lookup table instead of needing to calculate it again, resulting in improved performance." | sha256:20f5fb53275ad13b3e6bb09819f9a1583ff8075fa6146bb2bf1f403fc628d90d | 19357f50a04f5b4bc770e9a6 | c04c0b1e88a9ea042ddc1bb5 | 358ae5f40917812b72a08e8d | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:3019b60380f144b9 |
0079535aafcb39e7a1ce7e8801e99a12 | 0079535aafcb39e7a1ce7e8801e99a12 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "D" | sha256:a566e14f23d28bc193fe6f045e72b5166237de788caa02ed56e178138f286a13 | 7a7cd295bf5feb32af9cbf9f | acaf52e65e66598393f6b65e | 93763b66a86ac9d210b6ace0 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:f724f69a0775a7fa |
007e14080ff86067382284107c5432df | 007e14080ff86067382284107c5432df | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:e61f7ffda6fcf67359d20f712de1bd4abc0f9e8d1d4057fc3157bc78a8a2b555 | 5bc2aa113786e883557853ce | 8453a9a2993a79ee3e3403b9 | 3c64e498af897c79341bb403 | null | null | null | 7.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:0d889b19d66ab083 |
00810a986a99b3ada536518bf5f0e3ca | 00810a986a99b3ada536518bf5f0e3ca | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "To solve this problem, we need to determine the value of x, which represents the amount of money Johannes earned last Friday.\nWe know that Johannes sells cabbage for $2 per kilogram.\nLet's break down the information given:\nAmount earned last Wednesday: $30\nAmount earned last Friday: $x\nAmount earned today: $42\nT... | sha256:9538160002bb9c94e98da5990f9b04398c7787888a858b01909ecbec101ccc83 | a4199f9ad3c8a01684b3190c | 95573f174d783a68917b74fa | aebcfc347fa204e51149d35f | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | test | curated:138386991f8f2f7d |
0081eb86eb8603b2a5ddf3c5e44b713d | 0081eb86eb8603b2a5ddf3c5e44b713d | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | CommonsenseQA | CommonsenseQA | reasoning | CommonsenseQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:81ba27646da28f86d27018d293eba2036cbad30d3fb92216a6c04129b5cad71c | b36b96dd32896f8f31276f51 | f3cbd7fa60e681842387f18b | 424bc2f8adec34a1aef4171a | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:56bc3a0ab6da3dac |
0082721b748bb599876907b7e174ae0b | 0082721b748bb599876907b7e174ae0b | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:dbf60605f4ef7c5d95010bff667568fb4d519e2ccf0d52c9d7db1f82ef7e31b7 | 458ae5405444638fc857a3d0 | 3afeb3163ac25f49719d29e0 | 33049fbd2771417159effd6d | null | null | null | 7.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:78701c8f9a51af1f |
0082c5a5bc4dd5f4521cf7b8f644371d | 0082c5a5bc4dd5f4521cf7b8f644371d | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here is the code for the requested function and array:\n\n```python\ndef modify_string(string):\n vowels = ['a', 'e', 'i', 'o', 'u']\n modified_string = ''\n \n for char in string[::-1]:\n if char.lower() in vowels:\n modified_string += char.upper()\n else:\n modified_st... | sha256:b999a8e172a53e4fabb12a5b955d32aa8cef414d6bb1c9cca2247f0dde769d00 | 64bcce7f55b8c12eccc27f17 | d828f6e776228eaae93d643e | 9363a0d9d2437959429acc4e | null | null | null | 7.5 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:83969082484a000f |
008411c65bb205eaa634461bb710db5b | 008411c65bb205eaa634461bb710db5b | train | [{"content":"You are an expert software engineer. Write complete, correct, runnable code in the language requested by the user. Follow the requested language, interface, and constraints. Explain the approach briefly when requested.","name":"","reasoning_content":"","role":"system","tool_call_id":"","tool_calls":[],"tra... | [] | Evol-Code | Evol-Code | code | Evol-Code | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "Here's the Python code for the required function:\n\n```python\ndef generate_fibonacci(n):\n fibonacci_series = []\n a, b = 0, 1\n\n while len(fibonacci_series) < n:\n fibonacci_series.append(a)\n a, b = b, a + b\n\n prime_fibonacci_sum = 0\n smallest_prime_palindrome = None\n\n def is_... | sha256:ea955167adf73a8112ec692e9153d0e298f637c53626c4399399086dbb89175a | 45600241488e8a964622f7a0 | db3c6ea680ec635c587972b5 | 9aff3afabd600220e3820736 | null | null | null | 8 | [
"difficulty_untrusted",
"reference_status_unknown",
"reference_unknown"
] | 0.395189 | 1 | 0 | 1.0.0 | nickrosh/Evol-Instruct-Code-80k-v1 | 3ae930c20d5496e2c8386872d5628c45f6957db4 | CC-BY-NC-SA-4.0 | train | curated:0e2bfa01c124d17e |
00847d2d73d60e97aaf81be1828e10dd | 00847d2d73d60e97aaf81be1828e10dd | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "To solve this problem, we need to determine the value of x, which represents the total amount of wages Mike earned this week.\nWe know that Mike received $52 from his first job.\nFor his second job, he works 12 hours per week and earns $9 per hour.\nLet's calculate how much money Mike earned from his second job:\n12 h... | sha256:f5f75b35ad1f8dc536def1359970b72eac805ba5188b5c34a43cdca1ab399bb7 | c86523dd897a462811420299 | 2931d8a0562775a585d1b8be | 3d768ace97a79f2a4c083ee6 | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:1c28bdcb61a3bfbe |
00856396241e0e31c62d6dfefc514625 | 00856396241e0e31c62d6dfefc514625 | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | Dolly | Dolly | instruction | Dolly | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "China's 1st Mars Exploration Mission" | sha256:fc7c0221d924e549f4daca546eefdbd6c866124302fdf095cc48a54fa0649cd2 | 89a96a5a295bacd9a6438a20 | b0de89f188c40adcab8ad439 | 5073591825ba3b04e7a295e9 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | databricks/databricks-dolly-15k | bdd27f4d94b9c1f951818a7da7fd7aeea5dbff1a | CC-BY-SA-3.0 | train | curated:fe5b580e70ad255e |
00868933c2ec88499750f15abf345b4b | 00868933c2ec88499750f15abf345b4b | train | [{"content":"You are a helpful, precise assistant. Follow instructions exactly.\n\nFormat your response as:\n<think>\n[Understand what is being asked. Identify constraints and requirements.\nPlan your response structure.]\n</think>\n\n[Your complete, well-structured response following all given constraints]","name":"",... | [] | tulu-3 | tulu-3 | instruction | tulu-3 | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "" | sha256:bc75a8560571c0cc99b1e67b10f321330856ab4b0bf813254cbf0e7118b9dd9d | 855cc23e335eb20811dcde6b | f08cf064b22f8b55de5019d0 | 5aac01d1843bb88d403cb3c9 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | allenai/tulu-3-sft-mixture | b14afda60f1bbebe55d5d2fa1e4df5042f97f8be | ODC-BY-1.0; mixture terms vary | train | curated:0b8aab9cfc8337ff |
0086ce96cd3252b2208f8dc812667edd | 0086ce96cd3252b2208f8dc812667edd | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:eab37876e42b54b36afe2073ed45001bea09bbe8fe85beed2bb975e53470d754 | f5d9675e1e6e2ff3980a81f6 | 9aa05c4a1f5c3d0affbc08b7 | 279f36c8a7e6b297ca43a78e | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:5df45a3bf7556c7c |
00871720f41da1b5581bf4aecde44019 | 00871720f41da1b5581bf4aecde44019 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | ARC-Easy | ARC-Easy | reasoning | ARC-Easy | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:7c374aba6f2b0a1c462bc8a88329f25373e453bf12eb4c889b6cc48779072347 | 0ac94f1a57ed8630fb6dda5a | 837a5ce56d4f2995de2c99a7 | 28f17d80dae5319e54cd0725 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:49614d5092d0f463 |
0087fb0b63c511344dc62315b8f7c87f | 0087fb0b63c511344dc62315b8f7c87f | train | [{"content":"You are an expert mathematician. Solve the given problem with complete rigor.\n\nFormat your response EXACTLY as:\n<think>\n[Your complete step-by-step reasoning. Show all intermediate calculations.\nIf you make an error and catch it, show the correction.\nEnd with a clear statement of the final answer.]\n... | [] | MetaMathQA | MetaMathQA | math | MetaMathQA | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "The second student guesses 8 times the amount of the first student, so their guess is 8 * 100 = 800 jellybeans.\nThe third student guesses 200 less than the second student, so their guess is 800 - 200 = 600 jellybeans.\nThe average of the first three guesses is (100 + 800 + 600) / 3 = 1500 / 3 = 500 jellybeans.\nThe f... | sha256:bdf9900f3ef38662e882bb4c5149e8575bbedf7cae27016cc0a46f7e535f3379 | 47cd6235abd9ab3bfd318ba6 | 84dac86af1f0ecc6b62797ee | 875754f3c554940154e692ff | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | train | curated:006e7186aaa18a4c |
00888afe2c4924def6c7018e2c2d48f4 | 00888afe2c4924def6c7018e2c2d48f4 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | QASC | QASC | reasoning | QASC | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "C" | sha256:e71214467c885f3fdaae58418b344fe4a5ef8751b72c9a08ced0aaa0680e8bb8 | d307c447b16af99a209f1a4c | d8f58edf48ffb723cb83ca49 | 3a733e2a686da0ad17ec29d3 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:85fd4ccdef7fc0d5 |
008946121d15b8fbc2f654f23fd63fb0 | 008946121d15b8fbc2f654f23fd63fb0 | train | [{"content":"You are an expert logical reasoner. Think through the problem carefully.\n\nFormat your response EXACTLY as:\n<think>\n[Break down the problem into components.\nConsider multiple hypotheses if applicable.\nEliminate incorrect paths explicitly.\nBuild toward the conclusion step by step.]\n</think>\n\n[Clear... | [] | SciQ | SciQ | reasoning | SciQ | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "B" | sha256:00f1c666b724bd61defc9477b2d994f9535dce4fc68d26511d7a3803e091e323 | fdd4028d97957340d0788845 | c810694fc5a6e5b527b7b127 | 37bf892fb6997b722eb84a89 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:e8e74bb66e27fb6f |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.