{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VDVSH2EN7CXKA7OXE5GCOW7UIT","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":"a5911a769916395f3a74ea073e0154b2e0d0a7eab69bd7162981e751c38ccc5d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T05:51:26Z","title_canon_sha256":"747f9f27988ee0734a08a8eac76b0a5c877babd1bad2d243c60b20a914f03c74"},"schema_version":"1.0","source":{"id":"2410.02229","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02229","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02229v2","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02229","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"VDVSH2EN7CXK","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"VDVSH2EN7CXKA7OX","created_at":"2026-07-05T11:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"VDVSH2EN","created_at":"2026-07-05T11:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:a28654d6176e3e009bf40fdb6262b21fef6e9d0381e9095baf037a871c4cb53b","target":"graph","created_at":"2026-07-05T11:11:35Z","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/2410.02229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made significant progress in natural language understanding and generation, driven by scalable pretraining and advanced finetuning. However, enhancing reasoning abilities in LLMs, particularly via reinforcement learning from human feedback (RLHF), remains challenging due to the scarcity of high-quality preference data, which is labor-intensive to annotate and crucial for reward model (RM) finetuning. To alleviate this issue, we introduce CodePMP, a scalable preference model pretraining (PMP) pipeline that utilizes a large corpus of synthesized code-preference ","authors_text":"Debing Zhang, Haotian Xu, Huimu Yu, Songlin Hu, Xing Wu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T05:51:26Z","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02229","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:e16e85422632ebf530bd0158c8ddc5b9520a06274eaa46ce80c4251a97b03095","target":"record","created_at":"2026-07-05T11:11:35Z","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":"a5911a769916395f3a74ea073e0154b2e0d0a7eab69bd7162981e751c38ccc5d","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T05:51:26Z","title_canon_sha256":"747f9f27988ee0734a08a8eac76b0a5c877babd1bad2d243c60b20a914f03c74"},"schema_version":"1.0","source":{"id":"2410.02229","kind":"arxiv","version":2}},"canonical_sha256":"a8eb23e88df8aea07dd7274c275bf444c6a6ef2bbb09b5821a76d0ca42a9d05c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8eb23e88df8aea07dd7274c275bf444c6a6ef2bbb09b5821a76d0ca42a9d05c","first_computed_at":"2026-07-05T11:11:35.164957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:35.164957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"swafNUjIlF56rldN8W3Gi/ofcIsTx3X0QU+Otg9oi9t3dtbiQbDxWZu1Ojbdxvb9diQ4VtHt/bFFDHO54OoPBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:35.165582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02229","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e16e85422632ebf530bd0158c8ddc5b9520a06274eaa46ce80c4251a97b03095","sha256:a28654d6176e3e009bf40fdb6262b21fef6e9d0381e9095baf037a871c4cb53b"],"state_sha256":"7fe23dad47e75d76fa35fb3d1da2fb62c348ee731a4ab175df09a221478e52cc"}