{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMCYFB65LDMSDXMYDT3SRFIIGW","short_pith_number":"pith:TMCYFB65","schema_version":"1.0","canonical_sha256":"9b058287dd58d921dd981cf7289508359bce355c722c3d0480efdd74eb97917e","source":{"kind":"arxiv","id":"2402.14809","version":4},"attestation_state":"computed","paper":{"title":"CriticBench: Benchmarking LLMs for Critique-Correct Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haowei Liu, Ruilin Luo, Tian Liang, Yujiu Yang, Zhibin Gou, Zicheng Lin","submitted_at":"2024-02-22T18:59:02Z","abstract_excerpt":"The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark designed to assess LLMs' abilities to critique and rectify their reasoning across a variety of tasks. CriticBench encompasses five reasoning domains: mathematical, commonsense, symbolic, coding, and algorithmic. It compiles 15 datasets and incorporates responses from three LLM families. Utilizing CriticBench, we evaluate and dissect the performance of 17 LLMs in g"},"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":"2402.14809","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dee9436fef3543698ae35b8fc74dc501e5da1ab3c61ae95b67a8b2e2a58814ef","abstract_canon_sha256":"0195e5fb524c961442bee02fd55d4e90e43c454eb32755b46d56bdf7a0ab0e0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:52.734223Z","signature_b64":"DbjCagQynEC3YZHMbP+FtNhiOPWK6PZiuY7vmdt4K0T+0inY2BnKBl4qyfSAOAfbgAZVlJu1lSJuCEONSiSgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b058287dd58d921dd981cf7289508359bce355c722c3d0480efdd74eb97917e","last_reissued_at":"2026-07-05T08:25:52.733767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:52.733767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CriticBench: Benchmarking LLMs for Critique-Correct Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haowei Liu, Ruilin Luo, Tian Liang, Yujiu Yang, Zhibin Gou, Zicheng Lin","submitted_at":"2024-02-22T18:59:02Z","abstract_excerpt":"The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark designed to assess LLMs' abilities to critique and rectify their reasoning across a variety of tasks. CriticBench encompasses five reasoning domains: mathematical, commonsense, symbolic, coding, and algorithmic. It compiles 15 datasets and incorporates responses from three LLM families. Utilizing CriticBench, we evaluate and dissect the performance of 17 LLMs in g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14809","kind":"arxiv","version":4},"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/2402.14809/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":"2402.14809","created_at":"2026-07-05T08:25:52.733833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14809v4","created_at":"2026-07-05T08:25:52.733833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14809","created_at":"2026-07-05T08:25:52.733833+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMCYFB65LDMS","created_at":"2026-07-05T08:25:52.733833+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMCYFB65LDMSDXMY","created_at":"2026-07-05T08:25:52.733833+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMCYFB65","created_at":"2026-07-05T08:25:52.733833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32034","citing_title":"QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13918","citing_title":"Improving Video Generation with Human Feedback","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19264","citing_title":"DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW","json":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW.json","graph_json":"https://pith.science/api/pith-number/TMCYFB65LDMSDXMYDT3SRFIIGW/graph.json","events_json":"https://pith.science/api/pith-number/TMCYFB65LDMSDXMYDT3SRFIIGW/events.json","paper":"https://pith.science/paper/TMCYFB65"},"agent_actions":{"view_html":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW","download_json":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW.json","view_paper":"https://pith.science/paper/TMCYFB65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14809&json=true","fetch_graph":"https://pith.science/api/pith-number/TMCYFB65LDMSDXMYDT3SRFIIGW/graph.json","fetch_events":"https://pith.science/api/pith-number/TMCYFB65LDMSDXMYDT3SRFIIGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW/action/storage_attestation","attest_author":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW/action/author_attestation","sign_citation":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW/action/citation_signature","submit_replication":"https://pith.science/pith/TMCYFB65LDMSDXMYDT3SRFIIGW/action/replication_record"}},"created_at":"2026-07-05T08:25:52.733833+00:00","updated_at":"2026-07-05T08:25:52.733833+00:00"}