{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4E7XVPTLXRT6UY3BT2ZE4RMFU4","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":"82410e7be0a37f6c3e9dfe03afad4415efb506b92250272da14d59727933673b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-27T08:09:11Z","title_canon_sha256":"66c14bb212a80dd1fb3417963a7fd4275c9b4ea01481d5ff0a89fb1d4f548751"},"schema_version":"1.0","source":{"id":"2412.19513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19513","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19513v1","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19513","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"4E7XVPTLXRT6","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"4E7XVPTLXRT6UY3B","created_at":"2026-07-05T09:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"4E7XVPTL","created_at":"2026-07-05T09:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:cb7b984e78155ce5b52f29d72ecdb9e6605ada8165fbf3818ab36a1d3e4c9cd4","target":"graph","created_at":"2026-07-05T09:54:37Z","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/2412.19513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) can correct their self-generated responses, but a decline in accuracy after self-correction is also witnessed. To have a deeper understanding of self-correction, we endeavor to decompose, evaluate, and analyze the self-correction behaviors of LLMs. By enumerating and analyzing answer correctness before and after self-correction, we decompose the self-correction capability into confidence (being confident to correct answers) and critique (turning wrong answers to correct) capabilities, and propose two metrics from a probabilistic perspective to measure these 2 capab","authors_text":"Junyang Lin, Yichang Zhang, Yudong Wang, Zhe Yang, Zhifang Sui, Ziyao Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-27T08:09:11Z","title":"Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19513","kind":"arxiv","version":1},"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":"sha256:774246d78b1dec7b67dddd572c45d79d928a30bfa5310746a6c432f9629d9014","target":"record","created_at":"2026-07-05T09:54:37Z","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":"82410e7be0a37f6c3e9dfe03afad4415efb506b92250272da14d59727933673b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-27T08:09:11Z","title_canon_sha256":"66c14bb212a80dd1fb3417963a7fd4275c9b4ea01481d5ff0a89fb1d4f548751"},"schema_version":"1.0","source":{"id":"2412.19513","kind":"arxiv","version":1}},"canonical_sha256":"e13f7abe6bbc67ea63619eb24e4585a700c716acae27ce1404f19c3539002d5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e13f7abe6bbc67ea63619eb24e4585a700c716acae27ce1404f19c3539002d5f","first_computed_at":"2026-07-05T09:54:37.066452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:37.066452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMiK3ou9JcY/0+IzIqFtwZMb8kpLT2fyCbutrJ642Ff9DOLAd0a52pi5f9+S3gFM1zbr8P4dFUsNTfIARkGOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:37.066949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:774246d78b1dec7b67dddd572c45d79d928a30bfa5310746a6c432f9629d9014","sha256:cb7b984e78155ce5b52f29d72ecdb9e6605ada8165fbf3818ab36a1d3e4c9cd4"],"state_sha256":"29f609e0c69879733eda7ce384b2f09bb821b2f3ddb7900d83a1d02fa3e0ed47"}