{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3OFY22UQV5KTBRH3D274ITFKBM","short_pith_number":"pith:3OFY22UQ","schema_version":"1.0","canonical_sha256":"db8b8d6a90af5530c4fb1ebfc44caa0b0843b2bea026ea6c1dc78099f83c0bc1","source":{"kind":"arxiv","id":"2310.04815","version":1},"attestation_state":"computed","paper":{"title":"Critique Ability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingbo Shang, Lei Meng, Lei Shu, Liangchen Luo, Yinxiao Liu, Yun Zhu, Zi Lin","submitted_at":"2023-10-07T14:12:15Z","abstract_excerpt":"Critical thinking is essential for rational decision-making and problem-solving. This skill hinges on the ability to provide precise and reasoned critiques and is a hallmark of human intelligence. In the era of large language models (LLMs), this study explores the ability of LLMs to deliver accurate critiques across various tasks. We are interested in this topic as a capable critic model could not only serve as a reliable evaluator, but also as a source of supervised signals for model tuning. Particularly, if a model can self-critique, it has the potential for autonomous self-improvement. To e"},"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":"2310.04815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-07T14:12:15Z","cross_cats_sorted":[],"title_canon_sha256":"d42ab7c4eedf47a768bd73122187405dec63e251d3c602d0b2ce6d615e573864","abstract_canon_sha256":"5c7eedf58f4c5990f195cf2c59246fd654ecdae38c793bca1d27441ea503e0a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:23.178407Z","signature_b64":"GcEyDdS0Yd2QP5KKUYfzb7OhGekUUWkcprR2UD9scjKMEbxZQtWmw/CBUFOm90Ntly5+K7jvqplQrgKDAemLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8b8d6a90af5530c4fb1ebfc44caa0b0843b2bea026ea6c1dc78099f83c0bc1","last_reissued_at":"2026-07-05T06:58:23.178037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:23.178037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Critique Ability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingbo Shang, Lei Meng, Lei Shu, Liangchen Luo, Yinxiao Liu, Yun Zhu, Zi Lin","submitted_at":"2023-10-07T14:12:15Z","abstract_excerpt":"Critical thinking is essential for rational decision-making and problem-solving. This skill hinges on the ability to provide precise and reasoned critiques and is a hallmark of human intelligence. In the era of large language models (LLMs), this study explores the ability of LLMs to deliver accurate critiques across various tasks. We are interested in this topic as a capable critic model could not only serve as a reliable evaluator, but also as a source of supervised signals for model tuning. Particularly, if a model can self-critique, it has the potential for autonomous self-improvement. To e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04815","kind":"arxiv","version":1},"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/2310.04815/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":"2310.04815","created_at":"2026-07-05T06:58:23.178096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04815v1","created_at":"2026-07-05T06:58:23.178096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04815","created_at":"2026-07-05T06:58:23.178096+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OFY22UQV5KT","created_at":"2026-07-05T06:58:23.178096+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OFY22UQV5KTBRH3","created_at":"2026-07-05T06:58:23.178096+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OFY22UQ","created_at":"2026-07-05T06:58:23.178096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.06592","citing_title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM","json":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM.json","graph_json":"https://pith.science/api/pith-number/3OFY22UQV5KTBRH3D274ITFKBM/graph.json","events_json":"https://pith.science/api/pith-number/3OFY22UQV5KTBRH3D274ITFKBM/events.json","paper":"https://pith.science/paper/3OFY22UQ"},"agent_actions":{"view_html":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM","download_json":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM.json","view_paper":"https://pith.science/paper/3OFY22UQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04815&json=true","fetch_graph":"https://pith.science/api/pith-number/3OFY22UQV5KTBRH3D274ITFKBM/graph.json","fetch_events":"https://pith.science/api/pith-number/3OFY22UQV5KTBRH3D274ITFKBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM/action/storage_attestation","attest_author":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM/action/author_attestation","sign_citation":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM/action/citation_signature","submit_replication":"https://pith.science/pith/3OFY22UQV5KTBRH3D274ITFKBM/action/replication_record"}},"created_at":"2026-07-05T06:58:23.178096+00:00","updated_at":"2026-07-05T06:58:23.178096+00:00"}