{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FKVGHVNPHFFYG4EVAV4LW7UOQV","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":"f296fada3e3a6d665216768ee1a3b04c3855ed99dd6687b2d850d97785b27f45","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:38:02Z","title_canon_sha256":"f69fba9dced1c47948d61ad4ac00693c95ed112065cdc66762ead7a08904e02c"},"schema_version":"1.0","source":{"id":"2402.12563","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12563","created_at":"2026-07-05T08:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12563v3","created_at":"2026-07-05T08:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12563","created_at":"2026-07-05T08:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"FKVGHVNPHFFY","created_at":"2026-07-05T08:18:05Z"},{"alias_kind":"pith_short_16","alias_value":"FKVGHVNPHFFYG4EV","created_at":"2026-07-05T08:18:05Z"},{"alias_kind":"pith_short_8","alias_value":"FKVGHVNP","created_at":"2026-07-05T08:18:05Z"}],"graph_snapshots":[{"event_id":"sha256:74e364c97fcbe75c74301c5f26f11c50111ecc1314d30e7d10a055ea080e2acf","target":"graph","created_at":"2026-07-05T08:18:05Z","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/2402.12563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of Large Language Models (LLMs) has catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs, attempting to address the ongoing debate about its feasibility. Our research has identified an important latent factor - the \"confidence\" of LLMs - during the self-correction process. Overlooking this factor may cause the models to over-criticize themselves, resulting in unreliable conclusions regarding the efficacy of self-correction. We have experimentally observed that LLMs","authors_text":"Eric Xing, Guangyi Chen, Kun Zhang, Loka Li, Yixuan Zhang, Yusheng Su, Zhenhao Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:38:02Z","title":"Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12563","kind":"arxiv","version":3},"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":"sha256:326f5af32e18e654fe9c53c7a3a5db2ee5d5c62b69956d78d4632206f07bddb8","target":"record","created_at":"2026-07-05T08:18:05Z","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":"f296fada3e3a6d665216768ee1a3b04c3855ed99dd6687b2d850d97785b27f45","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T21:38:02Z","title_canon_sha256":"f69fba9dced1c47948d61ad4ac00693c95ed112065cdc66762ead7a08904e02c"},"schema_version":"1.0","source":{"id":"2402.12563","kind":"arxiv","version":3}},"canonical_sha256":"2aaa63d5af394b8370950578bb7e8e8543e5ca91f2a4fcc63adf0cd02ee9c1a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2aaa63d5af394b8370950578bb7e8e8543e5ca91f2a4fcc63adf0cd02ee9c1a6","first_computed_at":"2026-07-05T08:18:05.506941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:05.506941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2KjmxdB2bhtIy4t6CSwWa1symTvGVK74040IA5bRl8dm06Z7yr5DQAqcecS5408eBXyD75qkoZFEgXz6ZoAZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:05.507529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12563","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:326f5af32e18e654fe9c53c7a3a5db2ee5d5c62b69956d78d4632206f07bddb8","sha256:74e364c97fcbe75c74301c5f26f11c50111ecc1314d30e7d10a055ea080e2acf"],"state_sha256":"6c00338027e59a72ac4ceb7a4fcd1c75c24caea8da44326026d5b976640da28c"}