{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MPAELKDIAUAURJ2AU6VXPYECFQ","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":"e5237d915eecc3cd88507c178763ea81bc3b241b86bf78a722a2ee67466f7d80","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-10T08:11:05Z","title_canon_sha256":"88d0a2f75aed19c6186437e01eb6a4629fe56dc414f4865a8e1a0d7f48e7298e"},"schema_version":"1.0","source":{"id":"2411.06387","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06387","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06387v4","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06387","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"pith_short_12","alias_value":"MPAELKDIAUAU","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"pith_short_16","alias_value":"MPAELKDIAUAURJ2A","created_at":"2026-07-05T10:10:09Z"},{"alias_kind":"pith_short_8","alias_value":"MPAELKDI","created_at":"2026-07-05T10:10:09Z"}],"graph_snapshots":[{"event_id":"sha256:1576aa1ecfa324c1654a31585853ecc6e95126e22ac65e872ea5a4d9673448c3","target":"graph","created_at":"2026-07-05T10:10:09Z","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/2411.06387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as appropriate for training. However, a single measure risks misjudging rationale quality, leading the models to learn flawed reasoning patterns. To address this issue, we propose CREST (Consistency-driven Rationale Evaluation for Self-Training), a self-training framework that further evaluates each rationale through follow-up questions and leverages this eval","authors_text":"Jaehyeok Lee, JinYeong Bak, Keisuke Sakaguchi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-10T08:11:05Z","title":"Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06387","kind":"arxiv","version":4},"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":"sha256:4d3292c799c46c01ca6e119f9e50fcd67703e3a0d284cc280c5a6fd072870f20","target":"record","created_at":"2026-07-05T10:10:09Z","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":"e5237d915eecc3cd88507c178763ea81bc3b241b86bf78a722a2ee67466f7d80","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-10T08:11:05Z","title_canon_sha256":"88d0a2f75aed19c6186437e01eb6a4629fe56dc414f4865a8e1a0d7f48e7298e"},"schema_version":"1.0","source":{"id":"2411.06387","kind":"arxiv","version":4}},"canonical_sha256":"63c045a868050148a740a7ab77e0822c38d4feafb6e38b761458dac2b4020480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63c045a868050148a740a7ab77e0822c38d4feafb6e38b761458dac2b4020480","first_computed_at":"2026-07-05T10:10:09.707346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:09.707346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ftXK/0HWc7Q03mV0h2omel18lOljzehFPXruRiZKrTwbJ/5O2Psq7Ufkyv0yb1mAI7AcT+rM6sRAkROxFf/YDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:09.707778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06387","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d3292c799c46c01ca6e119f9e50fcd67703e3a0d284cc280c5a6fd072870f20","sha256:1576aa1ecfa324c1654a31585853ecc6e95126e22ac65e872ea5a4d9673448c3"],"state_sha256":"21623bb8b945cfa330a6f8c62155d443d449311b7111beb7f8a007957b71b1d3"}