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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
01a067a4731b69fc0996e89859a3f01e | 01a067a4731b69fc0996e89859a3f01e | 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 | "E" | sha256:6816a31bc63972607d5dcb26462fb736248ea3cddcc86e493cb4011f236ca993 | 88c2711e75bdd6922447e7e3 | e0bc9eda9058db50ce370db1 | 50f6f3c14cb7d7d7011f1797 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:3c162a2348196336 |
01a07a5c28244563ba3dd2bbba57a99a | 01a07a5c28244563ba3dd2bbba57a99a | 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 solve the problem, we can modify the provided code to iterate through all possible triples of numbers instead of pairs. We will add an additional loop that iterates through all possible third numbers.\n\nHere is the modified code:\n\n```python\ndef find_numbers(numbers, target_sum):\n complements = set()\n ma... | sha256:0e7438045970c7ce3a1ca439cc77cf48fcb17ea2022027218b94e6902f24674a | f9ecccdb15e9c97afecb2f84 | 92eff0218526ac9325d8fbdd | ed9c615a73455392635256e3 | 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:96f54fd254f507ed |
01a0f5d2843f92690eed64864822848a | 01a0f5d2843f92690eed64864822848a | 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 | "Lambda expressions in Python are anonymous functions that can take in arguments and return a value. They are commonly used for performing operations on collections of data, or for making code more concise." | sha256:315fa4f48daee76974af80b664a67ba9f4fca9ce7fe0bf4d25862e42a70c9f89 | 48aa52715d3cfac0539ab648 | ecc843071e6ed1d51b5c25d2 | ee60a5d864de4bcd84e2d188 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | test | curated:2bb62a21f36ab740 |
01a4e50b74c387dc58673c062b99996d | 01a4e50b74c387dc58673c062b99996d | 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 | "This is an infinite geometric series with first term 1 and common ratio $1/3$.\nThe sum of an infinite geometric series with first term $a$ and common ratio $r$ is $\\frac{a}{1-r}$.\nIn this case, the sum is $\\frac{1}{1-\\frac{1}{3}} = \\frac{1}{\\frac{2}{3}} = \\boxed{\\frac{3}{2}}$.\nThe answer is: \\frac{3}{2}" | sha256:661265cfb1f515cc751399b3a7488fd5a56e5c0de833525debcf0076aef18829 | 7c78bf0b24bdf7f20b913639 | 6dc718e15265a24c35df51fe | a800a8a7236d2bcef0d6aa1f | 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:567f37b415449914 |
01a56730d10665da42f86016eac650b3 | 01a56730d10665da42f86016eac650b3 | 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" | sha256:867e3b13ccf03457e58dc7c55b6891d120f9b960b5834ce100cbb256eb9c9f5b | 5c7a3dc64c7f00ebfa548964 | 5982880a204a0edf1ea8d9ab | 851d86acdad895f5cfa91621 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:5d61e65d35ce496f |
01a694eb5b2748db94ba3eb565135248 | 01a694eb5b2748db94ba3eb565135248 | 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 | "To find the value of A, we need to determine the three-digit number A7B that, when added to 32, results in 705.\n\nLet's first subtract 32 from 705 to find the value of A7B:\n\n705 - 32 = 673\n\nNow we have A7B = 673, where A, 7, and B are the digits of the three-digit number.\n\nFrom this, we can see that A is the hu... | sha256:d1b2ff51d7e6cdb20ac329651173921f458ea426908a8727cf455227dceee8a7 | 9bf51027cacb1efa25a18999 | 455aa49c618e312ff80f4d8e | 746dc54ec110be8eb128326d | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | train | curated:97320c48ac25d259 |
01a7d9174af14e074a08d26dfc43b333 | 01a7d9174af14e074a08d26dfc43b333 | 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 obtain fractions equivalent to $\\frac{5}{8}$ by multiplying the numerator and denominator by the same number.\n\nThe sum of the numerator and denominator of $\\frac{5}{8}$ is $13,$ so when we multiply the numerator and denominator by the same number, the sum of the numerator and denominator is also multiplied by t... | sha256:e98cdae7405eae296c9514160b72a6abf3b038d6f446ddf802f6d8daa0b51b75 | f98aee54863a3d90802182dd | 3ae5ef06c75c60365e926441 | 91e738f208ff9346e1117de2 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:7d73f111517b9991 |
01a8356b4d18cc78790b388ef5fb45c6 | 01a8356b4d18cc78790b388ef5fb45c6 | 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:ad259d8b8da7baf20865b5d6c3da10398c9bfb5d1ed8babef05aa66fd723df91 | ea51aef929f86ff217be629c | d78a6e385ea5672062c0cdd1 | f694e31370510c177083c2a7 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | test | curated:faa09b9bafee0f89 |
01a861252e54e17853b0ab2f533e5e97 | 01a861252e54e17853b0ab2f533e5e97 | 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 number of balls in the box is 5 white + 6 black = 11 balls.\nTo find the probability of drawing two white balls, we need to find the probability of drawing a white ball on the first draw and a white ball on the second draw.\nFor the first draw, there are 5 white balls out of 11 total balls, so the probabilit... | sha256:518b2e043e70800cd27e7ef86bd417291dfb2c21ef8a54424fa16ea0eaea8dd3 | 47dea99858801df9c26c86be | 1e662f8b807da1cf4c70646e | e989f171fc36cf96c5f9c89d | 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:26867561f54be76f |
01aca204dcbd14dc16253418cd7a6795 | 01aca204dcbd14dc16253418cd7a6795 | 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 | "We can group the factors in pairs:\n\\begin{align*}\nx(x + 1)(x + 2)(x + 3) &= x(x + 3) \\cdot (x + 1)(x + 2) \\\\\n&= (x^2 + 3x)(x^2 + 3x + 2).\n\\end{align*}Let $y = x^2 + 3x + 1.$ Then\n\\[(x^2 + 3x)(x^2 + 3x + 2) = (y - 1)(y + 1) = y^2 - 1 \\ge -1.\\]Equality occurs when $y = x^2 + 3x + 1 = 0,$ which has roots $x... | sha256:cde9d0bf2c126be797b1a25e61198b6cd792f6494d58eda60a497a5b21ade621 | d6ab69b3306a6e97e6e7d6be | 37b27ec33ed66179b93175ab | bb35ba5ead8748191e1dfd30 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:c30ed80c6e5ab8d4 |
01ad64a07cea8ab3ce1ca0ca94717197 | 01ad64a07cea8ab3ce1ca0ca94717197 | 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" | sha256:4e02f4f2db97599ad9059d08f35d297e97919a5c0620893ddc3b1643c7c961d8 | f6a9a20dd0635be18b6fb234 | 7aabd932da19ee66c8566fa5 | 7fbd9f36cf4c9f478a7afde7 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | train | curated:00807f89802f5948 |
01af0f965242fd01bb56b4164b47d6a7 | 01af0f965242fd01bb56b4164b47d6a7 | 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:a43dfad3aab53f1003ce9f95213ba7268b8811634c792d4c98afff746de04167 | c6298812c2dbc95c169b10ad | 05fe68125a9bdcc5373de906 | 533600c53729f3eab6bd24b7 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:b0a4d8ffd1f44458 |
01af2941e8d44cb53022144efcaec348 | 01af2941e8d44cb53022144efcaec348 | 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 | "D" | sha256:32988771a3ae9f6a1e242a754e35a677a00cbf5db28ae69ec763607050c06b40 | db99e7c080749f4615337739 | aa795ef72014074132a8104c | 9fe3f1957e1053e0f64b53ad | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:c7da7c68955485cd |
01b11f99c725a5a77ed65ed91c15ec98 | 01b11f99c725a5a77ed65ed91c15ec98 | 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 recursive algorithm in Java to count the number of ones in a binary number string without using any bitwise operations or loops:\n\n```java\npublic class BinaryNumberOnesCounter {\n public static int countOnes(String binaryNumber) {\n // Base case: if the binary number is empty, return 0\n if... | sha256:29bdf8aeacd4bead348dfd5f5e5100957c5bfab91fb39e0b17d451b6c873fad1 | 16a73dbfaf99a366fb9f8c73 | bff285891a2875d6497a8141 | b2834d669ff0a185cd7ff478 | 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:0365c1c1329b7fac |
01b13317e817722e5bd95055754ccee4 | 01b13317e817722e5bd95055754ccee4 | 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:e44705eaf2c170bc31935783390ee6b81c9d683137dfc18da1ccbf23cf29ce75 | f72fc4ad62a2a2f4b19f3419 | 64b0eeea8c578f18c1606c74 | 3d7f0b60c0ceb2e9f28a0988 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:f46f425c611fc56b |
01b440671c46df58faec230d9f43060c | 01b440671c46df58faec230d9f43060c | 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:d8389f5df0e5f80cd729a7a6d09f97a0eed50eadfd41c1678b515210cf62692a | d1c361c569655bf2ea71b809 | 8179e4b6ad3333a96335d985 | 120b5621809ec31236069eab | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:abbea7e8c1c4eef6 |
01b5b5eeea70d0054eb295d726731d4d | 01b5b5eeea70d0054eb295d726731d4d | 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 C++ code that generates a random number in the range 0 - 1000, but the number generated must be divisible by both 7 and 11, and it should also have exactly 5 distinct prime factors:\n\n```cpp\n#include <iostream>\n#include <random>\n#include <vector>\n#include <algorithm>\n\n// Function to check if a number i... | sha256:64d34dd5a76aebd192b4db3adc24600bfc57c19a497bde78f61c039ed1e1d3ab | 42e6cb6150ce18d178ff0539 | f15e92c3cac1f5b266a49081 | 9a723f30e3bd5b195d5fd006 | 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:df635e422faee019 |
01b63af92a441eb28e1612a04ce58183 | 01b63af92a441eb28e1612a04ce58183 | 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" | sha256:68936e743bd23ee4e15cb559eccb849dbbe48c58b046b2c1bdacdecb7abdcef2 | 202c7034f9a64d9ec1104914 | ff889215fe0fd54f122dbee3 | 7c9bbbbd04ca6d138f07af45 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:afdcb93a4f4b6db1 |
01b8a2c922e1b07d94c7da0f5b718566 | 01b8a2c922e1b07d94c7da0f5b718566 | 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 pants that are purple in Teairra's closet.\nLet's break down the information given:\nNumber of shirts: 5\nNumber of pants: 24\nNumber of plaid shirts: 3\nNumber of shirts and pants which are neither plaid nor purple: 21\nWe can ... | sha256:9888b58480a3f86ce289397e3e09ae98fd4a1b8b6cb34b67a0434b1556340ec3 | b78cf6977f27d96c70296aa5 | 62a82b18fcc0aa805c260a47 | 6b6d988bf9045eb7d249f204 | 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:3016a6b475f15aac |
01bad74992d51db870da90e36ab2c83d | 01bad74992d51db870da90e36ab2c83d | 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 | "A" | sha256:f5a9c4e7476a425ee7c20b4564f1521a84ab139aca317f7ca5ca24587ec68df1 | a64db36f661aa2144b5082cf | dd47f5e5a0fbd8fb1d01a641 | ad0901c3d9f6ef61e71f51b2 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:83d6fd47c7797766 |
01bb5b8afe0e32897e060d521c9b718c | 01bb5b8afe0e32897e060d521c9b718c | 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 | "# Finds the middle node in a linked list \n# Input: head of the linked list \n# Return: the middle element of the linked list \ndef findMiddleNode(head): \n\t# If the linked list is empty \n\tif (head is None): \n\t\treturn None\n\n\t# Find the length of the linked list \n\tlength, node = 0, head \n\twhile (node is no... | sha256:d94edef6722744dbe04753ddb768301456f85f4a8252ef4dd5e497cd6836b057 | 41f07002d4ebd4e0f400feb1 | af95cdae54ef01c7fecf11d9 | 5bd09c05166a7010f75acb97 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:9ae00be27274b229 |
01bb5f98d9f5a687219e101378dcf732 | 01bb5f98d9f5a687219e101378dcf732 | 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" | sha256:8cbafb078e933b4106f100a61ca0ec40ba02ab3b61a3b0270d4485216ec5e2c3 | 41faed6a11004300de59dc2e | 4abd806562b266db9da2fb77 | f5657c327a97926435845a75 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:09828e68ed953029 |
01bc70ef77c1c72c3ba26be473be8483 | 01bc70ef77c1c72c3ba26be473be8483 | 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 | "A" | sha256:1aa9e01e748ee2999f27f2886ab1eefc992aac61495aac6b50b5cb917dd6eea6 | 1ed29f3912fa18858ed34007 | ddb37720187fd9ae4e08faf6 | 695197fce284a59aa9d5843c | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:5b30f859eaaa82a2 |
01bf81eb81f5ec40efa8aee4afe0ead3 | 01bf81eb81f5ec40efa8aee4afe0ead3 | 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 | "Since for any $x \\in \\mathbb{R}$, $f(x) = f(2-x)$ holds, \nit follows that the graph of the function $f(x)$ is symmetric about the line $x=1$. \nFurthermore, since $f(x)$ is an odd function defined on $\\mathbb{R}$, \nit implies that $f(x)$ is a periodic function \nwith a period $T=4$. \nTherefore, $f(2010) = f... | sha256:a19821958b7fa388d7e387e1409629443b03bfc09f81a085fb8c606dd5e28aa0 | d9cc23b9df825072f4dbe6ae | 5d7cbdff909c80061d20dbc9 | b7c8bc6c6d7fffe54f74ad17 | 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:7c14c4e79b7acdbd |
01c1c169c9353f4b5f1913e8ea2c3a26 | 01c1c169c9353f4b5f1913e8ea2c3a26 | 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 a SQL query against a SQLite database and return results.","name":"sqlite_query","parameters":{"properties":{"database":{"description":"Path to SQLite database file","type":"string"},"query":{"description":"SQL query to execute","type":"string"}},"required":["database","query"],"typ... | sqlite | glm5.2-agent-tool-synthetic | agent_tool | sqlite | glm-5.2 | z.ai-coding-paas-v4 | multi_turn_tool | traj_recovery | {"category":"sqlite","expected_final":"After the repair, the final query must verify quantity=18 and status=open for row 18 in orders.","expected_tools":["sqlite_query","sqlite_query","sqlite_query","sqlite_query","sqlite_query"],"seed":14000720} | sha256:41c8ebf8d9b7ce7f7282a3796b8cee0a8a3f66ea741fb442b0da2de81b8b94f8 | d8d2d732890ae26dc9cce447 | 33348ee935db66c92f2b773a | b1a1f3d2e8f45828cc16094b | 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-sqlite-14000720 |
01c2a924bd9db99396dce286b7ef4b01 | 01c2a924bd9db99396dce286b7ef4b01 | 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/counting_and_probability | MATH/counting_and_probability | math | MATH/counting_and_probability | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "We have to use a little bit of casework to solve this problem. If the first die shows a 1, the second die can be anything (6 cases). If the first die shows 2 or 4, the second die is limited to 1, 3, or 5 ($2\\cdot3 = 6$ cases). If the first die shows 3, the second die can be 1, 2, 4, or 5 (4 cases). If the first die s... | sha256:ec093e8bb5f6d078123ee02674959bbb96969b1759030041af031085db8c511d | 2715b655556c2e9a368c9700 | 2d996a0920217a3f89db979b | 305625335ea807e85514fa2b | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:bea7e9588db19fdd |
01c2e39dfe47789027b3800f7d3f842c | 01c2e39dfe47789027b3800f7d3f842c | 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:c04db47b8db1df0753cf32dc5e687c65919b5983217885425e49c0f403174db7 | b60252fd84bb95156760bb46 | f14abc5878a0c66192e72d00 | 9a83f2e2e1fb36cd8f1ee85f | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:3cb07f16be32c478 |
01c552125ca6d8f13a2760e2bfd556d2 | 01c552125ca6d8f13a2760e2bfd556d2 | 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 | "To solve this problem, we can use the concept of relative speed. When two objects move in opposite directions, their relative speed is the sum of their individual speeds.\n\nSoyun's speed = 5 km/h\nJia's speed = 4 km/h\n\nRelative speed = Soyun's speed + Jia's speed\nRelative speed = 5 km/h + 4 km/h\nRelative speed = ... | sha256:ba98ed0b1c7f5e2276399846db11d7144b601ffadbcd3f9c2a584c7693304134 | 6d03639562401506744a82a5 | e865c3d0f897d05541e837b9 | 873d20b036cf91673c062cc9 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | train | curated:b19d253b4bc9d5e7 |
01c58e9c56f1d1b2f42cb6272585dc7b | 01c58e9c56f1d1b2f42cb6272585dc7b | 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:eeca87ea5d4476505ac680a937a3e3be7126c36170f7be0ba0d255aae373a6d1 | c36bfa8e2b93edbf6da5a4aa | 65d375916dfe70a6c844d459 | 54cd2ce3c478fda01c6bdd77 | 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:54b6f534f057b428 |
01c6658f87dbb14cce5c9f07b6120b03 | 01c6658f87dbb14cce5c9f07b6120b03 | 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 | "Let's denote the total number of problems in the workbook as P.\n\nOn the first day, you solved 1/2 of the problems, so you solved (1/2)P problems.\n\nOn the second day, you solved 1/4 of the problems, so you solved (1/4)P problems.\n\nOn the third day, you solved 1/6 of the problems, so you solved (1/6)P problems.\n\... | sha256:fc647e87504a076a95a78f7503cd3e9e391267c6c1ac549264093d7422b3ae3c | 593f04e2311e28daa46aa54c | f8e3f05568be9c088f65108d | c79ad11032e3c8b787ebb897 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | train | curated:235f695aac63cf90 |
01c6d0df275aef51af7bc91beee55bf8 | 01c6d0df275aef51af7bc91beee55bf8 | 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 | "static int[] intersect(int[] array1, int[] array2){\n \n int[] result = new int[array1.length];\n int k = 0;\n \n for (int i = 0; i < array1.length; i++) {\n for (int j = 0; j < array2.length; j++) {\n if(array1[i] == array2[j]){\n result[k] = array1[i];\n k++... | sha256:2ac44246c6703cd9378edf55db3e745cdd4c815b6c2bea06910880858487ad19 | 795262aacade498819aa8f4f | 9f31b7aa9d34a11a5c3f445a | 2a6d4bc5f7399679d528adf9 | null | null | null | 8.5 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:b7f11679711e4b2e |
01c83419b013ed0184286626ad8cfc3b | 01c83419b013ed0184286626ad8cfc3b | 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 | "Let's denote the certain number as \\( x \\).\n\nAccording to the problem, we have the following equation:\n\n\\[ \\frac{3x}{5} - 220 \\]\n\nThis result is then multiplied by 4 to get 320:\n\n\\[ 4 \\left( \\frac{3x}{5} - 220 \\right) = 320 \\]\n\nNow, let's solve for \\( x \\):\n\n\\[ 4 \\left( \\frac{3x}{5} \\right)... | sha256:3f75b0c16b35be4062b8c1722320bf2ef780f8bc47b6d51841fb44c385cdedab | 95a98fdcc753edba95fd05e5 | ebd4978d9dea80700202a782 | 0117ee4631b75f4dd541a1ed | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | train | curated:ddb035db634ed265 |
01ca968b3c7cdc47f0f1d9f2c246cd70 | 01ca968b3c7cdc47f0f1d9f2c246cd70 | 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" | sha256:8ba49951d4d63b0fb4b283fd2a8f9ba6b24c9572f6c3460f433c97abaaae71e9 | c39efe965c0d10c9507d9dd4 | 9697438293599351f0ba123e | 8dc4e8fb7a7afe5f54babc4d | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:f986b50a1fd21e72 |
01cacc92faf460dd20e11321a57e73d0 | 01cacc92faf460dd20e11321a57e73d0 | 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 | "To find the rise in water level when the cube is completely immersed, we need to calculate the volume of the cube and then determine how that volume affects the water level in the rectangular vessel.\n\nThe volume of the cube (V_cube) can be calculated using the formula for the volume of a cube, which is:\n\nV_cube = ... | sha256:0d054a794c2a2d54b12f34163687684934edddf9f4251d7d269619f3ab5ada0d | a71febd6a6df9bc804ef9bd4 | 32d4a8c8929716aed3447815 | afae44967cb41b7dcdb38774 | 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:5a9da596991d55ac |
01cb7004da125054cc16cdabf7d4bfd7 | 01cb7004da125054cc16cdabf7d4bfd7 | 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" | sha256:4c422417cc279656961d7b79863d886944cb663e610c7879458584b277a040e0 | 903d9dda854af89543be4d79 | fcd81bf067cb7316bed5ebfe | f6ae982bc2189493dce72442 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:3c190e6b9aadb39f |
01cba3f2f8727f79b1985f17f8c57fb7 | 01cba3f2f8727f79b1985f17f8c57fb7 | 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_11002712/src/totals.py so that compute([2, 4, 6]) returns 43; report the test output and the corrected behavior.","expected_tools":["read_file","patch_file","run_python"],"seed":11002712} | sha256:a67b4d358ff75ca396ff6b080d3847e0cf64b59f9cd8c5249f0323123fb9b712 | 8cd8952a46421b043096b58e | 74568478df9af8ff77715189 | 78b4687c9d4a9b029fbcfa3d | true | true | null | null | [] | 1.174049 | 4 | 3 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-code_debug-11002712 |
01cc8523b375d09ea0dd98361f86a4e2 | 01cc8523b375d09ea0dd98361f86a4e2 | 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":"",... | [] | IFEval | IFEval | instruction | IFEval | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "[\"keywords:forbidden_words\"]" | sha256:b31ea710778aeb479794e326b941048e6a1795e014081eb5c29f1a0066ae1bae | 5bad7842b8291f9cd507731e | 86f9812019589940276686f5 | 7bf93fe0b2abc97185e63b88 | true | null | true | 7.5 | [
"final_only_instruction"
] | 1 | 1 | 0 | 1.0.0 | google/IFEval | 966cd89545d6b6acfd7638bc708b98261ca58e84 | Apache-2.0 | train | curated:5e5af02c62dd51fd |
01cd7cb2ed53735e69c523271b1695dc | 01cd7cb2ed53735e69c523271b1695dc | 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 | "4" | sha256:9ee9f564917057929837d73a41faa3aed51abaeeacc3b197dc365bf884dc3c9e | 0948160ba98f46dc561ab71a | 1001949e524d73f90be2b563 | 3a283ea45fc5779ab3ec3c9b | true | null | true | 10 | [] | 1 | 1 | 0 | 1.0.0 | openai/gsm8k | 740312add88f781978c0658806c59bc2815b9866 | MIT | train | curated:e42a544032fe7005 |
01ce38dee772e1b10939e2a25a725972 | 01ce38dee772e1b10939e2a25a725972 | 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 | "If the larger number is 22 and it exceeds the smaller number by 10, then the smaller number is 22 - 10 = 12.\n\nThe sum of the two numbers is 22 + 12 = $\\boxed{34}$ ." | sha256:7d226ac5ef72a8ebdfcb0b1915b07d6cd7d0aa42bddf49f399cd32ed4b6427f4 | 9bd4bd0d59ca2839c3371723 | 0428ea411074995c70160daa | 0dbfb8a51d1da01da6479700 | 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:9fbdeea2e2a8d990 |
01cf66b5b920dd224e398532c29c49c6 | 01cf66b5b920dd224e398532c29c49c6 | 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:f00f346b5ffb4bc067b5d219bfab35663190f4c18464f1c9fadd0e35516c01ee | 2b8195d1808f561e90ff22b0 | 822bf67ab4b7bd867a513b20 | 968e1e9a5bd9d3610141f648 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:45cc64ddc29b73eb |
01cfdbee8e87432b1dc85cb7c51a5e7f | 01cfdbee8e87432b1dc85cb7c51a5e7f | 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 | "D" | sha256:f5ceafce0c1f246fe52c37a5358f19ee594d588c7d585938615b06afbdc3df95 | 37b6a51a38d7bdc6de622885 | 505048acb64ae71d915b6444 | 9ba67797bd36bb36e9ed136c | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/sciq | 2c94ad3e1aafab77146f384e23536f97a4849815 | CC-BY-NC-3.0 | train | curated:fbf995317673cfa5 |
01d15e961c165912dcbc2c88fdc46c8b | 01d15e961c165912dcbc2c88fdc46c8b | 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 | "It is hard to say what is the best swimming form as everyone's body may be more acclimated to a certain form. One of the most standard forms of swimming that works for most people is the breast stroke." | sha256:6ebca4e7fa621bad2355cfc3e199215309c9210c9280682b939dc000aefa1262 | 5b916ae48f9223bd619a82c3 | 0e845db842a7a10980c81bee | bb7be3c5d782d186da3523ff | 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:da0ece6668e2ecf5 |
01d259c602e8976c69c3733a8367b36c | 01d259c602e8976c69c3733a8367b36c | 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" | sha256:00e3d74a1aa9fee5f7619343b64cadb055c6202b8a9652505085d08efda8a5e7 | a18976750222b1731131507f | 2405befb2657443af304d078 | 4b3899b818a8990e2575f05a | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/qasc | a34ba204eb9a33b919c10cc08f4f1c8dae5ec070 | CC-BY-4.0 | validation | curated:e0f478f643d70438 |
01d4fd1b1ad201654fe2b58d48f90041 | 01d4fd1b1ad201654fe2b58d48f90041 | 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 | "#description{\n display: block;\n}" | sha256:e5cf152c333829566b265e166e1ec244f5a59cfc39ffa6b4fa5165bf1c4c687d | 6d5d7ef914a0286ecb4bd8b2 | b9258c36020840da3717a7a0 | ec8dbe58e16d52f7bfbe03b1 | null | null | null | 7 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:a49e5e5982a1f55b |
01d51db2b82cb97a135e5d16dda868e8 | 01d51db2b82cb97a135e5d16dda868e8 | 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 class that meets the requirements:\n\n```java\npublic class MyClass {\n private String field1;\n private int field2;\n private boolean field3;\n private double field4;\n\n public MyClass(String field1, int field2, boolean field3, double field4) {\n this.field1 = field1;\n this.... | sha256:dff222ccd317dd9374cc9d918896a558a5117104994938a4c5ca002a96b72081 | 69c30264e28a7df87f4c7959 | cf41d2bbe890b9f37e97072d | fab4e8d8b56d23ea745fa061 | 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:230387ed987005c1 |
01d60bf1cbd02e8c0202896f221835b3 | 01d60bf1cbd02e8c0202896f221835b3 | 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 = 2' with 'RETRY_LIMIT = 6' in /tmp/agent_tool_workspace_10001888/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"]... | sha256:18258a8d1e7429883a484bd0c603adb175fa61a41a3823d1f194fb4fcb3ba165 | f5801ea24879e2d99bc98910 | 2d79da33fc1e95aa9c525841 | a4618a3da4bb2cddf65686aa | 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-10001888 |
01d66813ca7d4b43a8ae0fb38dc03097 | 01d66813ca7d4b43a8ae0fb38dc03097 | 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 | "Tabitha started adding a new color to her hair when she was 15 years old, and she added her second hair color that year, so she was 15 years old.\nIn three years, Tabitha will have 8 different colors in her hair, which means she will have added 6 more colors.\nSince she added her second hair color when she was 15, she... | sha256:b066eaaa239456450003a6b74834497067e7813a95ef625fc95cd8a16ff5beaf | 7e26a8629c0834906f9b9be0 | 85398c07e0b542c3865244cf | 3d0c32cedd64ee5d160ef69c | 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:2162329e5dfc0c60 |
01d8cb3414c698d329cb74732e63d61b | 01d8cb3414c698d329cb74732e63d61b | 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_11001795/src/windows.py so that compute([2, 4, 6]) returns 34; report the test output and the corrected behavior.","expected_tools":["read_file","patch_file","run_python"],"seed":11001795} | sha256:8717e6c59179a51bdefc8771454ae55f56b54368cedb3241e263c818508372c3 | 2613f69a53ebd3fc08d24fa0 | 91ab7cee3925ce1a8ad554e7 | 6005afb9147cfd57d5dc9d27 | true | true | null | null | [] | 1.174049 | 4 | 3 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-code_debug-11001795 |
01d9c97fdde5c81dceb17c74edda557f | 01d9c97fdde5c81dceb17c74edda557f | 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 | "To solve for the distance from point $V$ to the plane $ABC$ in the triangular pyramid $V-ABC$ where $VA$, $VB$, and $VC$ are mutually perpendicular and equal to 1, we proceed as follows:\n\n1. **Calculate the Length of the Sides on the Base Triangle $ABC$**: Given $VA=VB=VC=1$ and that these edges are mutually perpend... | sha256:ef7b2204994c3d7ab9e1489f1ba5fb1d0a6b2107b74a2e3b78eefeab785f928b | eb3785d40351abb40a76113c | 73274378c3f39483e70ddb79 | e4d00f546d2526df3145d0f4 | 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:5d6f20ce7bb5cca2 |
01e08ac168394b50cca2d2aef2c1eee2 | 01e08ac168394b50cca2d2aef2c1eee2 | 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 = 2' with 'RETRY_LIMIT = 6' in /tmp/agent_tool_workspace_10000781/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"]... | sha256:53d8ce4c1495c5488a9a176385075b08eb16f2559f6f8c62ac3a687fcfbaf1b9 | 2668a6574ae2aa74091db3b7 | 6a433ff1beb4a37a4279b9ad | c939fde1a700d664d07684e5 | 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-10000781 |
01e375de7243dab7b653812ff283878f | 01e375de7243dab7b653812ff283878f | 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 | "Sure! Here's an example of how you can achieve this using HTML, CSS, and JavaScript:\n\nHTML:\n```html\n<!DOCTYPE html>\n<html>\n<head>\n <link rel=\"stylesheet\" type=\"text/css\" href=\"styles.css\">\n</head>\n<body>\n <div class=\"section\" id=\"section1\"></div>\n <div class=\"section\" id=\"section2\"></div>\n... | sha256:b79f592297292b2773a0dc73f0c7eef4fc8722cc2487e5fc66ca4b2618a36679 | d17c8d4de2d9e3a4063f588a | 0986f0f1ecf18b86a477cd44 | b798e81d8ba374098ee949c5 | 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:311d628937f76c09 |
01e3af43f0fcd4a8c8bbdcb965f2d200 | 01e3af43f0fcd4a8c8bbdcb965f2d200 | 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 | "Matt can make a dozen cookies using 2 pounds of flour, so each cookie requires 2/12 = 1/6 pound of flour.\nMatt has 4 bags of flour, each weighing 5 pounds, so he has a total of 4 * 5 = 20 pounds of flour.\nTherefore, Matt can make 20 / (1/6) = 120 cookies with the flour he has.\nAfter Jim eats 15 cookies, there are 1... | sha256:0f9d77f486a49ae66cbfa884158334bd7266e1ce19f1090e09db1be683427bbb | 219365502e0861f010187551 | eae541cf3a3eacab0822a0f7 | 05590163ec9956de80b8dc00 | 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:df5bfe277de0e7b3 |
01e4f8ef5fe728f5e51e3a4c6802dffe | 01e4f8ef5fe728f5e51e3a4c6802dffe | 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 | "First, we can move everything to one side, to get\n\\[a^2 + b^2 + c^2 - ab - ac - bc = 0.\\]Then\n\\[2a^2 + 2b^2 + 2c^2 - 2ab - 2ac - 2bc = 0.\\]We can write this as\n\\[(a - b)^2 + (a - c)^2 + (b - c)^2 = 0.\\]This forces $a = b = c.$ Thus, the triples that work are of the form $(a,b,c) = (k,k,k),$ where $1 \\le k \... | sha256:026ca36b72b600495be3fb0805fe472c2362657462b2f0d19f98ce27e5f188c5 | 0d6293a6c93f6a1ede82d092 | b45d3cd327e5e86be8897a7b | d225067823b985c54e6bed68 | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:6bb23b9708a6042f |
01e6856155a1b8c5c20c979feefc0341 | 01e6856155a1b8c5c20c979feefc0341 | 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":"",... | [] | IFEval | IFEval | instruction | IFEval | qwen3.8-max-preview | alibaba-model-studio | single_turn | sft | "[\"detectable_format:number_bullet_lists\", \"length_constraints:number_paragraphs\", \"change_case:capital_word_frequency\"]" | sha256:190f30793c1cb920bf2861805f25991c75e344241e4c43cc232630a2bb1b077a | 7810de5cf100e56e88fa5955 | bd8c8bfd662b07ee0fe5c437 | ce62d0d4aa3d4b564ef87790 | true | null | true | 7.5 | [
"final_only_instruction"
] | 1 | 1 | 0 | 1.0.0 | google/IFEval | 966cd89545d6b6acfd7638bc708b98261ca58e84 | Apache-2.0 | train | curated:a7b6620c6621c95c |
01e6ca41e9b05675a4a037485447e5b8 | 01e6ca41e9b05675a4a037485447e5b8 | 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 coefficient of the $m^4n^4$ term in the expansion of $(m+n)^8$ can be found using the binomial theorem.\nAccording to the binomial theorem, the coefficient can be calculated using the formula:\n$\\binom{8}{4} = \\frac{8!}{4!(8-4)!} = \\frac{8!}{4!4!} = \\frac{8 \\times 7 \\times 6 \\times 5}{4 \\times 3 \\times 2 ... | sha256:c0e8b7da9684994603335b514b555a105fbaf7734bcf22b374c557930fa36326 | 63e1667dbcdc463fa5c34005 | 7da62b06ad54f5a23359fbea | f6278015ddbd80381efed7ad | 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:2ee99afd859f6f3b |
01e9b65b3bac025bcc04fbaee3092e88 | 01e9b65b3bac025bcc04fbaee3092e88 | 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 | "Please revise the test to make it more challenging." | sha256:82f2e027bd723d3ec1971841318c4e547e5ea8ec53b7806efdf0a56ca68076eb | 05518b574433c358586b9185 | b790bf6969ed6a06b5f02b99 | 95138f3472ab2328c6322e4e | null | null | null | 6 | [
"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:e67684fc9da812f7 |
01ea01fe0ec0439bb2f64c5b42ee6087 | 01ea01fe0ec0439bb2f64c5b42ee6087 | 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 | "my_list.sort(key=lambda tup: tup[1], reverse=True)" | sha256:9c120515cabacbad3d19768c40cca7c4c5a142e9c2f0655972fcd027b843329e | f381105997bc28cbcdb7b0f9 | 0a38ea497899506fdb520a91 | 3efbead1cc712e3dfd714563 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:5ac704e37e3fff82 |
01ebb4df3819fd8ec24ca020ae852d06 | 01ebb4df3819fd8ec24ca020ae852d06 | 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 | "D" | sha256:5784d829d50efe7b095d0bcb382ff7edb487769c3b025abe790f19251b366deb | e6fd0c7347df5cb6bd9d34ac | 84b886978904134332493e44 | 37a1f63d94961515784cbe34 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:2af527d8f21b0aa1 |
01f3689851f07cd60f7f1c2693376931 | 01f3689851f07cd60f7f1c2693376931 | 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_15000460/data/records.json by keeping records where active is true, write /tmp/agent_tool_workspace_15000460/out/active-records.json, and verify the JSON output.","expected_tools":["json_transform","json_transform","read_file","read_file"],"se... | sha256:18b9a095395c0821bf830e57eb935de3b6c9bc1d9134cebf2d677285c8dc507e | d3ee13635d1051e673114a18 | 33cdffb03c2d36a720c8adca | 577f9f99aeb3542d61b0bd24 | 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-15000460 |
01f38ab4078e9a11a9918749813fc278 | 01f38ab4078e9a11a9918749813fc278 | 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 | "This is a simple Python function that takes two parameters, x and y, and returns the sum of them. The function can be called by passing the two inputs, and it will add them both, then return the result to the caller." | sha256:32aac3ec6b236c0c8d3acffca06b4c565c9a8f2ab5d70a639d1cd9ff5838d889 | 3a95fbfaeceb11ee3289e7f9 | b95485ecabfec6d96762cb3f | fb25d90b00954e499e8b29d5 | null | null | null | 6 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | validation | curated:d93c0c3a00f26f49 |
01f46791e33f77d3e36b496c9284cf89 | 01f46791e33f77d3e36b496c9284cf89 | 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 list of 1000 randomly generated strings that meet the given requirements:\n\n1. Q72nN!vw45YRx2N$0BC3Y1^*sJ@hZxJmGS^W5IQ%t\n2. xC@JKm6!%0nEVrLbmz&^vDoJ%N74iAf!slXHb1S\n3. y4K$5nlA3c%iJ8^ZU7R9qWt1BPd*&@2IjoVFSg#LbMx\n4. aJHKdFg6#Y!0%3p^$c5nsq92&4CrOLBX8VyWe^x7U\n5. E^b3Q#$yW8d%kpIz0Z&RcA91sS2QTYXLJ^MuH*oGnBf\n... | sha256:de7375c568cfb18177a52f7eae64b2ff4745b3af39a5cf72a8f97f2b0e867e1b | 761a641892cb1e1fac1b2926 | 3dc1a18440c72c3f84157978 | 5abaa57afcabae7a09def445 | 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:f781653e60795942 |
01f4e803ea6cd2a64e2be55b97861e31 | 01f4e803ea6cd2a64e2be55b97861e31 | 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 multiply_matrices(matrixA, matrixB): \n \"\"\"\n Matrix multiplication\n :param matrixA: 2D array\n :param matrixB: 2D array\n :return: product of matrixA and matrixB\n \"\"\"\n \n # Initialize matrix to store the result with size (m x n), where m and n are the rows and columns of matrixA a... | sha256:bef5234fec5ecd0d9ce85de7167f83643a53d0cac54c7b1f8dde62fc1f4add6b | a26b8b702228a6a3f02e6527 | 3acec834a5e34beb70e20d0f | 8d695e577466c2de6f2a5381 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:f1b02b8a51e770f9 |
01f5daa05bfd0ab6c367e496dbb76156 | 01f5daa05bfd0ab6c367e496dbb76156 | 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" | sha256:3b90254c18fe98d0008697b6963f714c3da0634bcee2fc48d9e3bc23afbd0f87 | bc1528de08b6ed98518f0015 | 2a609b7f97e7005cebe4b402 | 86c70c715f6fa979c953a294 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | validation | curated:2c50940af68c52a8 |
01f61f77a0eab2e7a34ceb60904af264 | 01f61f77a0eab2e7a34ceb60904af264 | 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:d11901e4e4a4f180e78546c0e8898e2c589d7b2c154bec206fda9e85ac9d203a | bb21f175355db46a92677694 | f6a4a27ec8b59b34104c3415 | 453a7b5c3ad22db7ec9fc41c | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:553e0b17675600c0 |
01f7439ea71fcf081dce83becf9a12ee | 01f7439ea71fcf081dce83becf9a12ee | 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 | "Theon's ship can move 15 nautical miles per hour, so it will take him 90/15 = 6 hours to reach the destination.\nYara's ship can move 30 nautical miles per hour, so it will take her 90/30 = 3 hours to reach the destination.\nYara will be ahead of Theon by 6 - 3 = 3 hours.\n#### 3\nThe answer is: 3" | sha256:8eb6cca5a9b9457b5f41127d4150b53600e42bf985dd1423963874e67038d2c7 | 5c2469a8244a69e570e6e155 | d2add90fca28dc65ff755702 | c21828b6e2a64dda217b6e4f | true | null | true | 10 | [
"difficulty_untrusted",
"ground_truth_restored_from_pinned_upstream"
] | 1 | 1 | 0 | 1.0.0 | meta-math/MetaMathQA | aa4f34d3d2d3231299b5b03d9b3e5a20da45aa18 | MIT | validation | curated:6a391d86c0202fca |
01f907b326a1de33eaa120f292e4c7a2 | 01f907b326a1de33eaa120f292e4c7a2 | 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 | "We can expand the dot product as follows:\n\\begin{align*}\n(\\mathbf{a} + \\mathbf{b}) \\cdot (\\mathbf{a} - \\mathbf{b}) &= \\mathbf{a} \\cdot \\mathbf{a} - \\mathbf{a} \\cdot \\mathbf{b} + \\mathbf{b} \\cdot \\mathbf{a} - \\mathbf{b} \\cdot \\mathbf{b} \\\\\n&= \\|\\mathbf{a}\\|^2 - \\|\\mathbf{b}\\|^2 \\\\\n&= 3^2... | sha256:7ac599baff3a7403946bd06645aa77c2504017ea87130ffbae4c332808c353f4 | 2dca7327dcd4e9130b809059 | e53de3332375402ab8e07df9 | 9387c9b29ec36fd619cac861 | 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:71fc8501ab95b3e9 |
0202f1bcc888b531165988147ca0fb05 | 0202f1bcc888b531165988147ca0fb05 | 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:b5159679706eed87285bd0ab6297f55f54d82e52b3251417345d5299c63f24b0 | 7fea44e7a27c9db078ed9f53 | af4e7cfb5f6febe91caf59cc | d687be21977a4d0abb92a1e6 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | tau/commonsense_qa | 94630fe30dad47192a8546eb75f094926d47e155 | unknown-see-provenance | train | curated:74ca593d608055bf |
0202f836eaea84d9d47c72764c34b789 | 0202f836eaea84d9d47c72764c34b789 | 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 code to generate a 5x4 matrix of random numbers between -5 and 15 rounded to the nearest hundredth decimal place, and then find the sum of all the numbers in the matrix:\n\n```python\nimport random\n\ndef generate_matrix():\n matrix = []\n for i in range(5):\n row = []\n for j in range(4... | sha256:b896ae7668f05a9cca5413846d95b0a1104a29cc2c0a44e56a1eb80ed003ab16 | 2a49ad310900e19539a856e8 | 44c41dd6b8ef0065cb179f0e | ee5503d85bb4a5834dc581a7 | 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:59328d7b968dfdec |
0209295a1ece3ccd2049c5849029d4d5 | 0209295a1ece3ccd2049c5849029d4d5 | 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","corpus_search","calculator"],"seed":13000220} | sha256:9055b12723b3614d8d1878592802551b8805f4dd8280f8477a461527b27ea561 | e066db30c7dc76baeb04abd4 | 394e3cdff2cd11ca0836ac4e | 61b01eb9411d64618339fa9b | 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-13000220 |
020941c6092c3a1a432d71aa3fab8383 | 020941c6092c3a1a432d71aa3fab8383 | 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_11002448/src/totals.py so that compute([2, 4, 6]) returns 46; report the test output and the corrected behavior.","expected_tools":["run_python","read_file","patch_file","run_python"],"seed":11002448} | sha256:25ba0f5ca6cfe1c218e76fe12be643c819566abf1e82d9d458971557475e292d | f908e80892a4f3034c7ce480 | 8dab38b167e750e2a324c8ec | b7929ad3520837ad35dd7fad | true | true | null | null | [] | 1.174049 | 6 | 7 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-code_debug-11002448 |
020b4093ea98eeab411194063173ec7d | 020b4093ea98eeab411194063173ec7d | 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:eb88d4398b8f11b9fc59e372babfed8e063511fc239f75325830c50d4f31f943 | 6c6411fbc3bcbc407ca967a2 | abe1f683cea1fdfdaa73d346 | adbbcf8deb7731060dc09dc4 | null | null | null | 6.5 | [
"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:6dc654ff1f2cda69 |
020f573a029b3b306696bd6d0a9fb4f3 | 020f573a029b3b306696bd6d0a9fb4f3 | 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 | "SELECT name, date_of_birth \nFROM people \nWHERE YEAR(date_of_birth) = '1975';" | sha256:aaf698d06876df7f829f4bc38153d458c8cb85785925e15dd5037e6480c3fe36 | 9fce835421a82f43d80815d7 | 7ee65416151ef463b08b278b | 7646e76ab85b5e0329827d63 | null | null | null | 7 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:fed0e0d895768708 |
02113877d913d81f07f7794b7c91f7d6 | 02113877d913d81f07f7794b7c91f7d6 | 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 | "" | sha256:3f2bbfe198ac2f31dc841b1804071fd81d99b00ed97dc650ebf328bcd2710a93 | abd8331edd208a25cc809020 | 074ddb5ce8377e213581338b | 921bf2ec8afae4568fe6ea29 | 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:d50095471fd52a8a |
0211af914752a2ede06f60dca961ed14 | 0211af914752a2ede06f60dca961ed14 | 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 | "A" | sha256:a9e9197ca3255e56ad0fbd41f2f89feca63650bc2a9646f1aae5d4f424ba39d0 | 71a6faff53fe767ba950e866 | 2cbbe78d9be582d20a9cf4da | 6da84c8ee160c267d2232f43 | true | null | true | 9.5 | [] | 1 | 1 | 0 | 1.0.0 | allenai/ai2_arc | 210d026faf9955653af8916fad021475a3f00453 | unknown-see-provenance | train | curated:66e7423717575b5f |
02122b3c23967f9bd0c856a648f561bf | 02122b3c23967f9bd0c856a648f561bf | 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 | "" | sha256:42a1b6d8b944c6a60b999135060573ee8bb5f7519e14c15f9fbc78f6f224c619 | 36861c40db34d079acd750cd | 86a1e7e12dfe71899863c54d | 794cd0f847fc2b78d3645e7f | 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 | test | curated:2c3b4da67c98bf7d |
021255447d64a3734b49fcb364e86202 | 021255447d64a3734b49fcb364e86202 | 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 days Joy will need 57 cups of food for.\nLet's break down the information given:\nAmount of food eaten by the mom foster dog per day: 1.5 cups * 3 times = 4.5 cups\nAmount of food eaten by each puppy per day: 1/2 cup * 2 times =... | sha256:e51a2cb69f11a1f7d4f6e5d07ccc41390c082ac75a4b506294f173565a46d3de | 034c16ae4e61d3b0d18b7f57 | b43ea9b65a4741aa76f104d5 | 8a0a35c1e72e11e4dab2be2e | 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:3422059629e5288b |
021328b82a51037ec72ef55d975b9b58 | 021328b82a51037ec72ef55d975b9b58 | 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_11001068/src/windows.py so that window([2, 4, 6]) returns 47; report the test output and the corrected behavior.","expected_tools":["run_python","read_file","patch_file","run_python"],"seed":11001068} | sha256:5a03b49d49aedcceab1fb99efd05b215354cdd301e237938cfc9808943620f66 | bb4af7107e6662158e4e3012 | 8abd134628ff8ccdc26e1f12 | 997b9326f46582384a84a67a | true | true | null | null | [] | 1.174049 | 7 | 8 | 1.0.0 | local:distillation-glm52 | run:full-20260724-175443@sha256:71f34bba1cb29a831fd1f26b51f0b787d9d4ad2bc51c93cb1af5084759e128e1 | other; synthetic research corpus; see provenance | train | agent-code_debug-11001068 |
021330589103dc6e5bcd2b6ddd657992 | 021330589103dc6e5bcd2b6ddd657992 | 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 | "" | sha256:1c44e2f582f09be22ba08f01390d501ede58e81ee3bab73329942b9661d30c1d | 9a4ea38ffafec7558ca202d4 | a7b4c8cd5659eec805473f49 | 5528c739235e290db9a1f31f | 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:afa92b2fbadaa6bc |
0214127c37a72d33601db7edae56b2e5 | 0214127c37a72d33601db7edae56b2e5 | 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 an Objective-C program that finds all prime numbers within a given range of integers and prints them in descending order:\n\n```objective-c\n#import <Foundation/Foundation.h>\n\nBOOL isPrime(int num) {\n if (num <= 1) {\n return NO;\n }\n for (int i = 2; i <= sqrt(num); i++) {\n if (num ... | sha256:ad3953fc7e1cf44e6d8ac9911184dd3b2b4e52247a6a85050faae9c384062e21 | d8a13e4a355c4fe613d57ad0 | 5dd4f09bfa844eaab1b02668 | 6bbdf1958fd102fa6043882b | 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:d50ba4bd129f8a3a |
02147fef87af718553cd930a9ce4e727 | 02147fef87af718553cd930a9ce4e727 | 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 possible implementation that checks if a given string is a palindrome using recursion:\n\n```python\ndef is_palindrome(string):\n # Base case: an empty string or a string with only one character is always a palindrome\n if len(string) <= 1:\n return True\n\n # Recursive case: check if the fir... | sha256:5cd905347e17e83b13e3d618afa5d5c1a93a49f3257cc7e19d7ea91f7baff120 | a454dbdd0c133e9ef637a4a1 | 1acf8ec106590b04534f717e | 03907638f8c64d05ed5b9477 | 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:e81f15886b880d41 |
0215856f4285bc78c33c8e7f2998e05e | 0215856f4285bc78c33c8e7f2998e05e | 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 | "```python\nfrom typing import List\n\ndef capitalize_names(names: List[str]) -> List[str]:\n modified_names = []\n for name in names:\n words = name.split(\" \")\n capitalized_words = []\n for word in words:\n capitalized_word = word.lower().capitalize()\n capitalized_w... | sha256:58b85240335c4c11fd5b0b61dacd91ceb674d3011fd07d2f025ec57609b5fcf6 | 59d69673448c854c9102d7c8 | bc2ab1e5427a0e7087adb2b0 | 2ba4bee503bca3e3403e4fb9 | 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:a9e97f2e757def41 |
021698427057046be06ee54ce4674c26 | 021698427057046be06ee54ce4674c26 | 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 = 2' with 'RETRY_LIMIT = 5' in /tmp/agent_tool_workspace_10000890/src/parser.py, and read the file back to confirm the exact edit.","expected_tools":["search_files","search_files","read_file","patch_file","read_file"... | sha256:ae132a9ea84b7708d9bc8cb9ea2e9a57a5332d2a487d7a65c52252de9e199058 | 990fa14875520b3520b96bf6 | dbc815aabfaeccc7eb028c6c | 37cf77ca265f4acee1fc5004 | 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-10000890 |
0216f3380244f5708588fd48c9fd22fa | 0216f3380244f5708588fd48c9fd22fa | 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 solve this problem recursively, we can define a helper function that takes the text and the current count of vowels as input parameters. In each recursive call, we will check if the word \"the\" exists in the text. If it does, we will remove it and make a recursive call with the updated text. If it doesn't, we will... | sha256:24d1c724057b0f15d52f930c5743a3f910e608bf537925e26c06ef2138c6e4c9 | eb754e63a80997165f98825a | f5b1d53f69349758eea0d79d | 17532d770b50a1ae5f8c00a8 | 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:5356c5f63bff1b7b |
0217d9bba2c1429844f7884ae033f6ad | 0217d9bba2c1429844f7884ae033f6ad | 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 there are 9 people behind Yuna, then Yuna is the 10th person from the end of the line. Since there are 25 students in total, we can subtract the 10 students (including Yuna) from the end of the line from the total number of students to find out how many are in front of her.\n\n25 students (total) - 10 students (Yun... | sha256:11a2ea53d4aed46f5170e303b3f9306fc983ea8a09c1e7a27d3cd54856df2141 | 8e0f151213bc3de64ef55626 | 13a0e22929f8c692ef0cdd40 | 3e622f032f68371839bdb06f | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | microsoft/orca-math-word-problems-200k | 29255d1770cc4eac66e5e7fa378cba542c026350 | unknown-see-provenance | validation | curated:7eee165d38d21836 |
0217efd2874a5c8db180215413f34d7e | 0217efd2874a5c8db180215413f34d7e | 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:b91d670f23c59029a6cea4ddf175f900107fbda287394e85fb86ca64b7032b3e | 122bb693ede9eee3a668f77b | d55340f9f0cf3e2f1589b593 | d5d1215b407aa538dfa61b06 | 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:c5d5aac0f11ecc81 |
0219ba9b54d2626288d89283c15f1ce3 | 0219ba9b54d2626288d89283c15f1ce3 | 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=60 and batch size=320, then report the calculator result for 320 / 60 as 5.3333.","expected_tools":["corpus_search","corpus_search","calculator"],"seed":13000970} | sha256:c75a45301b7003ecb87e9097bd9f4ea56a07faef5c36e11422efb08dd3e73fb2 | 85ba2f02de7283c8c54c9e0f | 17b0da5f67a7d7e263982126 | a3351ae6a0b8ac86c56da448 | 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-13000970 |
021bb39e32ac8aacafebf42ca4d435b4 | 021bb39e32ac8aacafebf42ca4d435b4 | 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 | "# create a matrix of 5 x 4\nmatrix = [[0 for x in range(4)] for y in range(5)]" | sha256:0b89a9707a3e4d0ef994596ea23dc571cfed6413a5837a9cbd6df78f537c82d4 | af15fa7af271fc06e4cd173d | b289e30346722753d66e7b9e | e7e59a6c0512cdb69bc45f4d | null | null | null | 7 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:1514bceae27023f3 |
021c169f74cf7c8480547af19d3039fc | 021c169f74cf7c8480547af19d3039fc | 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 consider a hand at the 12 to be $0^\\circ$. Now we convert the hour and minute hands to a degree measure from $0^\\circ$ to $360^\\circ$. If we divide $360^\\circ$ evenly among 60 minutes, we get that each minute, the minute hand moves $\\frac{360^\\circ}{60}=6^\\circ$. So if the minute hand is at 48 minutes, it is... | sha256:0d2f8f1b40b8324d9560c38e2f579468e880e5d33604f4a2895b07a7036d9b5a | 10d3d7fae5f3f269dd6cf103 | f07fcdccbbeecf017d8699a9 | e39ce82c904da7975c12928f | true | null | true | 9 | [] | 1 | 1 | 0 | 1.0.0 | EleutherAI/hendrycks_math | 21a5633873b6a120296cce3e2df9d5550074f4a3 | unknown-see-provenance | train | curated:f57c3c1009291d97 |
021c6a35550755a55dc0c6e4800a5453 | 021c6a35550755a55dc0c6e4800a5453 | 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 | "import random\nimport string\n\ndef generate_string():\n chars = string.ascii_letters + string.digits \n return ''.join(random.choice(chars) for _ in range(16))\n\nif __name__ == '__main__':\n print(generate_string()) \n # Output: 5A5l7p9XohHmFWhh" | sha256:cdf32c5abfe9ca2d1aea1d3a94bc00565824ebbde0f034612b921f9a233f2aef | 59ceb3e50e805803c447929d | ba5e67aca1ddff18d9c8ba7c | b6bf9b71718e29cc1248f506 | null | null | null | 9 | [
"reference_status_unknown",
"reference_unknown"
] | 1 | 1 | 0 | 1.0.0 | sahil2801/CodeAlpaca-20k | 152bb5e9a29651266b018106053980070a0521a1 | unknown-see-provenance | train | curated:4720a57c4c3c10a9 |
021ccf45054487bdd62730b4d2699ab8 | 021ccf45054487bdd62730b4d2699ab8 | 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 | "To find the condition under which the line \\\\(ax+by+3=0\\\\) intersects with the circle \\\\(x^{2}+y^{2}=1\\\\), we need the distance from the center of the circle to the line to be less than or equal to the radius of the circle. This is expressed as \\\\( \\dfrac {|0+0+3|}{ \\sqrt {a^{2}+b^{2}}} \\leqslant 1\\\\), ... | sha256:fcbec1c9fcdfd4be34b8a29e9bb5ff8784eb7b8df8d26f63db1b7309ac351271 | 7f2d2cf7cbec277132b9b30d | 7809d29bde09f92cbbb91a45 | 6aae58b3b1f314d4992c5838 | 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:d358d7a7c60696d3 |
021ce0e1bce4ed07cfd9fff4a35641bb | 021ce0e1bce4ed07cfd9fff4a35641bb | 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 | "To convert the decimal number $134$ into its equivalent in base $5$, we follow these steps:\n\n1. **Find the largest power of $5$ less than $134$:**\n - $5^1 = 5$\n - $5^2 = 25$\n - $5^3 = 125$\n - $5^4 = 625$ (which is greater than $134$)\n\n Thus, the largest power of $5$ that is less than $134$ is $5^3 = ... | sha256:4aa2aceea0b7f42bcb9f4697d09fbfc614c079f90e510784eddf8d400d9aa9d7 | c2218b6a2fb61bb7c8c97773 | 84df5861d5d591b5f635622c | b1ba29612736bb87bc6cc94c | 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:2a5c2d7baee6fb30 |
021d6efbda28ac42cab84578daf28955 | 021d6efbda28ac42cab84578daf28955 | 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 | "" | sha256:6ab62ab845f4928d46c414ea606c360bed389b6f0caa1e0d0f815b11d7e4beb5 | 380727630c07cae52fa815c9 | 5883dee907c566c824f39c7f | db99a0710a92e488ee892760 | 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:182ed11a76ba6779 |
021e9928f38b785a614ea7756c7676a5 | 021e9928f38b785a614ea7756c7676a5 | 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 | "" | sha256:018abd38f801d0e3d3bebcbf48c6b0656ce9dab6fe9a64c59ae44e9e7ddcf567 | 73ab68e25b7aefd4cb2e63e4 | 318762e359c23abe850e7fe9 | f7b157dad1ea1887e828147d | 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 | test | curated:7ae9846efdfdaf7e |
021efa2e36e737a2e0cb16334de2b100 | 021efa2e36e737a2e0cb16334de2b100 | 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 Tina gets for each postcard sold.\nLet's break down the information given:\nNumber of postcards made in a day: 30\nNumber of days: 6\nTotal earnings: $900\nWe can set up the equation as follows:\nNumber of postcards made i... | sha256:306330145944ad865627716dcfe7582ac2b07b47eeec02347b3f9daf72eb6fc7 | a556892c74fcc551360d0782 | 345221768c0ce8238f350a64 | 5ded58b47afcc2bc0f21a631 | 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:444129b284d0b767 |
02215b6e44a505813d171fbcb892b926 | 02215b6e44a505813d171fbcb892b926 | 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 create a dictionary in JavaScript that meets the given requirements, we can implement a combination of a Map and a Doubly Linked List. Here's a step-by-step guide:\n\nStep 1: Implement a Doubly Linked List\n- Create a Node class with properties: key, value, next, and previous.\n- Create a DoublyLinkedList class wit... | sha256:79291ba1e7a83febfc82e4e2e5e9be4de8b35ecf957f51501e8d6c7574d731c2 | ff2a233e7e07b59f12d32c0f | 4bbbcbc229f2d5e43456592f | 941c861427cfb4fba057bd9f | 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:1a6420c182ada953 |
0226b96b5a686de555f63182c35e6733 | 0226b96b5a686de555f63182c35e6733 | 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 | "" | sha256:8fb916a150b76fbb950d927601ea8c8471554c0909d5a53540db0f11675ef73d | f458b654149b289fe5d27b77 | 52636f7134d69368d63f9d88 | 9bad2463f011bd2f114a623c | 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:4dccbc0df44ce7f9 |
02271952a7974c3953559bcac0c08d54 | 02271952a7974c3953559bcac0c08d54 | 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=48 and batch size=480, then report the calculator result for 480 / 48 as 10.0000.","expected_tools":["corpus_search","corpus_search","corpus_search","calculator"],"seed":13000821} | sha256:8384d230b19d06b09a9879da9d6238b4bae3a6ea320ca2c05bd31718b66c6e2c | 500f50cac0a7a35be16ad0b7 | 2b30a4248b06d9721a42d581 | 43364a1e36c028e5f1013a71 | 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-13000821 |
0228b161e4d6ce410b1bc1dc0c2f4d9d | 0228b161e4d6ce410b1bc1dc0c2f4d9d | 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 Hugo spent on an online game.\nLet's break down the information given:\nAmount of money saved in September: $29\nAmount of money saved in October: $25\nAmount of money saved in November: $31\nAmount of money left: $10\nWe ... | sha256:e667b023f40ff2dd970e3e26fdcd6755066986ee7f2caf2ad8916f524e96cff4 | 4cf8560c6b8c4de44d52a3ef | cf765ef61344ccf714277a68 | e06662616dfc03bae771a6db | 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:8c96f7a53415126c |
022b234e496f1e46a1a30188d0f8366e | 022b234e496f1e46a1a30188d0f8366e | 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 denote the average monthly sales total for January through November as A. Therefore, the total sales for these 11 months would be 11A.\n\nThe sales total for December is given as 7 times the average monthly sales, so the sales for December would be 7A.\n\nThe total sales for the year would be the sum of the sale... | sha256:525c65123ff876d76cd3de9c99bf4a76dcd309c578505f33856536923c5972f2 | 46285096c3a8d6d0f8aa64bf | 4dd4a127ebb1633189e85310 | 7c0dbab6d673bc846ac95028 | 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:8729d7e7d18095b9 |
022bbdffa84bd0f5b169533951c5a8f5 | 022bbdffa84bd0f5b169533951c5a8f5 | 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 | "Playstation and Xbox are two competing game consoles, where which is \"best\" will depend on the preferences of the gamer. From a graphics and performance perspective they are comparable, with Sony's Playstation technically leading, though most gamers would be unlikely to notice a significant difference. From a game... | sha256:187177a35969813b2d394d4955949d5bd7ff1456c64035a3baa29ad8ebd2b1f0 | b716f83aeede9ab639045bc4 | 8edd1e1761c1fafe5ec39c7f | cc341be177fc927bf764b9c0 | 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:adafb0b7e780f86c |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.