{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JMEVCRTFVWJAMZAJLZS3DQM54R","short_pith_number":"pith:JMEVCRTF","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"},"canonical_sha256":"4b09514665ad920664095e65b1c19de47e0a8a0d609d0a253768bf046e50dc68","source":{"kind":"arxiv","id":"2402.10176","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10176","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10176v2","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10176","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"JMEVCRTFVWJA","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"JMEVCRTFVWJAMZAJ","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"JMEVCRTF","created_at":"2026-07-05T09:30:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JMEVCRTFVWJAMZAJLZS3DQM54R","target":"record","payload":{"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"},"canonical_sha256":"4b09514665ad920664095e65b1c19de47e0a8a0d609d0a253768bf046e50dc68","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"},"source_kind":"arxiv","source_id":"2402.10176","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"83WAxW367LjDRiwo16TUi5AxyeL+Gc3dycTazZoT7fDskYS43pGnny4dzGO/yG+aeFaa5+BXrYMw1GVuzH+jAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:14:29.910341Z"},"content_sha256":"d109fcdc1cd783d4ef2c8a2799aa9e75eba389b4c3c1a7ccb559e67ce114f69d","schema_version":"1.0","event_id":"sha256:d109fcdc1cd783d4ef2c8a2799aa9e75eba389b4c3c1a7ccb559e67ce114f69d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JMEVCRTFVWJAMZAJLZS3DQM54R","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KlOF8ZkcyJFsEYmL1jVcTq5PjBsMjwjKYN6ylQFsOtcxSv8yHAPm9kWeshF/xfk7fIOWQP5iECh9iia7MdujDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:14:29.911377Z"},"content_sha256":"c8dfdf2d57e8c5f272c70ad2b4588afdc145b8e1c6b12946fc8ad24345c11206","schema_version":"1.0","event_id":"sha256:c8dfdf2d57e8c5f272c70ad2b4588afdc145b8e1c6b12946fc8ad24345c11206"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/bundle.json","state_url":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T17:14:29Z","links":{"resolver":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R","bundle":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/bundle.json","state":"https://pith.science/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMEVCRTFVWJAMZAJLZS3DQM54R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JMEVCRTFVWJAMZAJLZS3DQM54R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c68e2edf3ba1e6725b768351dee649e2679f4e3f67c66cbbf42ba9e3042f6a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:26:11Z","title_canon_sha256":"305c1486ab8449e92f69966045567ace97f3163db3be495a490b23044c398a45"},"schema_version":"1.0","source":{"id":"2402.10176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10176","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10176v2","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10176","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"JMEVCRTFVWJA","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"JMEVCRTFVWJAMZAJ","created_at":"2026-07-05T09:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"JMEVCRTF","created_at":"2026-07-05T09:30:08Z"}],"graph_snapshots":[{"event_id":"sha256:c8dfdf2d57e8c5f272c70ad2b4588afdc145b8e1c6b12946fc8ad24345c11206","target":"graph","created_at":"2026-07-05T09:30:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.10176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daria Gitman, Fei Jia, Igor Gitman, Ivan Moshkov, Sean Narenthiran, Shubham Toshniwal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:26:11Z","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10176","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d109fcdc1cd783d4ef2c8a2799aa9e75eba389b4c3c1a7ccb559e67ce114f69d","target":"record","created_at":"2026-07-05T09:30:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4c68e2edf3ba1e6725b768351dee649e2679f4e3f67c66cbbf42ba9e3042f6a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T18:26:11Z","title_canon_sha256":"305c1486ab8449e92f69966045567ace97f3163db3be495a490b23044c398a45"},"schema_version":"1.0","source":{"id":"2402.10176","kind":"arxiv","version":2}},"canonical_sha256":"4b09514665ad920664095e65b1c19de47e0a8a0d609d0a253768bf046e50dc68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b09514665ad920664095e65b1c19de47e0a8a0d609d0a253768bf046e50dc68","first_computed_at":"2026-07-05T09:30:08.106414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:08.106414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ywB6f/EViHi95qkZp2bN2PxfAUvQ/FrcqS0Q2nwYjkB+MtrUkQarMmXkOMRa2/x0py9AQXaJ9Xm6t0JdeRgvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:08.106904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d109fcdc1cd783d4ef2c8a2799aa9e75eba389b4c3c1a7ccb559e67ce114f69d","sha256:c8dfdf2d57e8c5f272c70ad2b4588afdc145b8e1c6b12946fc8ad24345c11206"],"state_sha256":"5d6a53ea2473044ded47c07ad6be642d2f4f6d01813b09b7edb71d1189d73084"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uqmy1cr7VVjayur2mDec4thpU5WU8SZ2OT8PbR0mw3Ma5suyZYzzPeCef7htEUpVwgXScdCeD4a4nxiqCFX8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:14:29.919203Z","bundle_sha256":"cf163c4716fa190008bd59361f642f5af19969943524d3a8100174486bdb7e7b"}}