{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GXQZ6LZSPNWMXXDTZCUTIJDNPR","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":"5df84f949b63bcad43182656ddf8b1d19cd326c85041456b0c725bc14272f87e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T12:38:59Z","title_canon_sha256":"6c0ea497bfd697db893846d8e51a3c530ed0367939228a6d00b3599f50f71106"},"schema_version":"1.0","source":{"id":"2402.13764","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13764","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13764v5","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13764","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"GXQZ6LZSPNWM","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"GXQZ6LZSPNWMXXDT","created_at":"2026-07-05T09:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"GXQZ6LZS","created_at":"2026-07-05T09:23:03Z"}],"graph_snapshots":[{"event_id":"sha256:6aa3c652320210472fbcbe2c00aceaf3b15346744d814114d6207131a9c700c7","target":"graph","created_at":"2026-07-05T09:23:03Z","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/2402.13764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Critique ability, i.e., the capability of Large Language Models (LLMs) to identify and rectify flaws in responses, is crucial for their applications in self-improvement and scalable oversight. While numerous studies have been proposed to evaluate critique ability of LLMs, their comprehensiveness and reliability are still limited. To overcome this problem, we introduce CriticEval, a novel benchmark designed to comprehensively and reliably evaluate critique ability of LLMs. Specifically, to ensure the comprehensiveness, CriticEval evaluates critique ability from four dimensions across nine diver","authors_text":"Chen Xu, Dahua Lin, Heyan Huang, Kai Chen, Tian Lan, Wenwei Zhang, Xian-Ling Mao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T12:38:59Z","title":"CriticEval: Evaluating Large Language Model as Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13764","kind":"arxiv","version":5},"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:a24cc6db98e89dc885492a719946f3dcc679155b3a5c8c0505a2973577b73be9","target":"record","created_at":"2026-07-05T09:23:03Z","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":"5df84f949b63bcad43182656ddf8b1d19cd326c85041456b0c725bc14272f87e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T12:38:59Z","title_canon_sha256":"6c0ea497bfd697db893846d8e51a3c530ed0367939228a6d00b3599f50f71106"},"schema_version":"1.0","source":{"id":"2402.13764","kind":"arxiv","version":5}},"canonical_sha256":"35e19f2f327b6ccbdc73c8a934246d7c766e4b2a49d080ca6442f6061e8fa0be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35e19f2f327b6ccbdc73c8a934246d7c766e4b2a49d080ca6442f6061e8fa0be","first_computed_at":"2026-07-05T09:23:03.501653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:03.501653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ur03iCJrpXSOQ0QaI0hOBGn504oZphqtXLrp3ESXiNrLj4DL6QpVisoLZTuSLLbJLldv6b1lAxBHN5iNGn5SAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:03.502135Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13764","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a24cc6db98e89dc885492a719946f3dcc679155b3a5c8c0505a2973577b73be9","sha256:6aa3c652320210472fbcbe2c00aceaf3b15346744d814114d6207131a9c700c7"],"state_sha256":"10a0dba6b80f32d3d58bd21ac4aa16047f410653b378d48f4112dd2d50ec7720"}