{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMEVCRTFVWJAMZAJLZS3DQM54R","short_pith_number":"pith:JMEVCRTF","schema_version":"1.0","canonical_sha256":"4b09514665ad920664095e65b1c19de47e0a8a0d609d0a253768bf046e50dc68","source":{"kind":"arxiv","id":"2402.10176","version":2},"attestation_state":"computed","paper":{"title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daria Gitman, Fei Jia, Igor Gitman, Ivan Moshkov, Sean Narenthiran, Shubham Toshniwal","submitted_at":"2024-02-15T18:26:11Z","abstract_excerpt":"Recent work has shown the immense potential of synthetically generated datasets for training large language models (LLMs), especially for acquiring targeted skills. Current large-scale math instruction tuning datasets such as MetaMathQA (Yu et al., 2024) and MAmmoTH (Yue et al., 2024) are constructed using outputs from closed-source LLMs with commercially restrictive licenses. A key reason limiting the use of open-source LLMs in these data generation pipelines has been the wide gap between the mathematical skills of the best closed-source LLMs, such as GPT-4, and the best open-source LLMs. Bui"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.10176","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:26:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"305c1486ab8449e92f69966045567ace97f3163db3be495a490b23044c398a45","abstract_canon_sha256":"4c68e2edf3ba1e6725b768351dee649e2679f4e3f67c66cbbf42ba9e3042f6a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:08.106904Z","signature_b64":"ywB6f/EViHi95qkZp2bN2PxfAUvQ/FrcqS0Q2nwYjkB+MtrUkQarMmXkOMRa2/x0py9AQXaJ9Xm6t0JdeRgvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b09514665ad920664095e65b1c19de47e0a8a0d609d0a253768bf046e50dc68","last_reissued_at":"2026-07-05T09:30:08.106414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:08.106414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daria Gitman, Fei Jia, Igor Gitman, Ivan Moshkov, Sean Narenthiran, Shubham Toshniwal","submitted_at":"2024-02-15T18:26:11Z","abstract_excerpt":"Recent work has shown the immense potential of synthetically generated datasets for training large language models (LLMs), especially for acquiring targeted skills. Current large-scale math instruction tuning datasets such as MetaMathQA (Yu et al., 2024) and MAmmoTH (Yue et al., 2024) are constructed using outputs from closed-source LLMs with commercially restrictive licenses. A key reason limiting the use of open-source LLMs in these data generation pipelines has been the wide gap between the mathematical skills of the best closed-source LLMs, such as GPT-4, and the best open-source LLMs. Bui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10176","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.10176/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.10176","created_at":"2026-07-05T09:30:08.106476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10176v2","created_at":"2026-07-05T09:30:08.106476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10176","created_at":"2026-07-05T09:30:08.106476+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMEVCRTFVWJA","created_at":"2026-07-05T09:30:08.106476+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMEVCRTFVWJAMZAJ","created_at":"2026-07-05T09:30:08.106476+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMEVCRTF","created_at":"2026-07-05T09:30:08.106476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07779","citing_title":"From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier","ref_index":225,"is_internal_anchor":true},{"citing_arxiv_id":"2505.07527","citing_title":"Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07711","citing_title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2406.18629","citing_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07711","citing_title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R","json":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R.json","graph_json":"https://pith.science/api/pith-number/JMEVCRTFVWJAMZAJLZS3DQM54R/graph.json","events_json":"https://pith.science/api/pith-number/JMEVCRTFVWJAMZAJLZS3DQM54R/events.json","paper":"https://pith.science/paper/JMEVCRTF"},"agent_actions":{"view_html":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R","download_json":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R.json","view_paper":"https://pith.science/paper/JMEVCRTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10176&json=true","fetch_graph":"https://pith.science/api/pith-number/JMEVCRTFVWJAMZAJLZS3DQM54R/graph.json","fetch_events":"https://pith.science/api/pith-number/JMEVCRTFVWJAMZAJLZS3DQM54R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/action/storage_attestation","attest_author":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/action/author_attestation","sign_citation":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/action/citation_signature","submit_replication":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/action/replication_record"}},"created_at":"2026-07-05T09:30:08.106476+00:00","updated_at":"2026-07-05T09:30:08.106476+00:00"}