{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GXQZ6LZSPNWMXXDTZCUTIJDNPR","short_pith_number":"pith:GXQZ6LZS","schema_version":"1.0","canonical_sha256":"35e19f2f327b6ccbdc73c8a934246d7c766e4b2a49d080ca6442f6061e8fa0be","source":{"kind":"arxiv","id":"2402.13764","version":5},"attestation_state":"computed","paper":{"title":"CriticEval: Evaluating Large Language Model as Critic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Dahua Lin, Heyan Huang, Kai Chen, Tian Lan, Wenwei Zhang, Xian-Ling Mao","submitted_at":"2024-02-21T12:38:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.13764","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T12:38:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c0ea497bfd697db893846d8e51a3c530ed0367939228a6d00b3599f50f71106","abstract_canon_sha256":"5df84f949b63bcad43182656ddf8b1d19cd326c85041456b0c725bc14272f87e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:03.502135Z","signature_b64":"Ur03iCJrpXSOQ0QaI0hOBGn504oZphqtXLrp3ESXiNrLj4DL6QpVisoLZTuSLLbJLldv6b1lAxBHN5iNGn5SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35e19f2f327b6ccbdc73c8a934246d7c766e4b2a49d080ca6442f6061e8fa0be","last_reissued_at":"2026-07-05T09:23:03.501653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:03.501653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CriticEval: Evaluating Large Language Model as Critic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Dahua Lin, Heyan Huang, Kai Chen, Tian Lan, Wenwei Zhang, Xian-Ling Mao","submitted_at":"2024-02-21T12:38:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13764","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.13764/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.13764","created_at":"2026-07-05T09:23:03.501711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13764v5","created_at":"2026-07-05T09:23:03.501711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13764","created_at":"2026-07-05T09:23:03.501711+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXQZ6LZSPNWM","created_at":"2026-07-05T09:23:03.501711+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXQZ6LZSPNWMXXDT","created_at":"2026-07-05T09:23:03.501711+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXQZ6LZS","created_at":"2026-07-05T09:23:03.501711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30448","citing_title":"Bounded Behavioral Indistinguishability for Black-Box LLM Distillation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18864","citing_title":"Towards an AI co-scientist","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR","json":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR.json","graph_json":"https://pith.science/api/pith-number/GXQZ6LZSPNWMXXDTZCUTIJDNPR/graph.json","events_json":"https://pith.science/api/pith-number/GXQZ6LZSPNWMXXDTZCUTIJDNPR/events.json","paper":"https://pith.science/paper/GXQZ6LZS"},"agent_actions":{"view_html":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR","download_json":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR.json","view_paper":"https://pith.science/paper/GXQZ6LZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13764&json=true","fetch_graph":"https://pith.science/api/pith-number/GXQZ6LZSPNWMXXDTZCUTIJDNPR/graph.json","fetch_events":"https://pith.science/api/pith-number/GXQZ6LZSPNWMXXDTZCUTIJDNPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR/action/storage_attestation","attest_author":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR/action/author_attestation","sign_citation":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR/action/citation_signature","submit_replication":"https://pith.science/pith/GXQZ6LZSPNWMXXDTZCUTIJDNPR/action/replication_record"}},"created_at":"2026-07-05T09:23:03.501711+00:00","updated_at":"2026-07-05T09:23:03.501711+00:00"}