{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R3HVR7OP43NFIF4AKYSFO76K5I","short_pith_number":"pith:R3HVR7OP","schema_version":"1.0","canonical_sha256":"8ecf58fdcfe6da5417805624577fcaea16761b89b578cebfb6776e98b43cef28","source":{"kind":"arxiv","id":"2401.04518","version":2},"attestation_state":"computed","paper":{"title":"The Critique of Critique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junlong Li, Pengfei Liu, Ruifeng Yuan, Shichao Sun, Weizhe Yuan, Wenjie Li","submitted_at":"2024-01-09T12:20:41Z","abstract_excerpt":"Critique, as a natural language description for assessing the quality of model-generated content, has played a vital role in the training, evaluation, and refinement of LLMs. However, a systematic method to evaluate the quality of critique is lacking. In this paper, we pioneer the critique of critique, termed MetaCritique, which builds specific quantification criteria. To achieve a reliable evaluation outcome, we propose Atomic Information Units (AIUs), which describe the critique in a more fine-grained manner. MetaCritique aggregates each AIU's judgment for the overall score. Moreover, MetaCr"},"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":"2401.04518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-09T12:20:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3fe4418a99c27633fcdde57989d6ee7cf9fd29e64f49fc29643f8579faa0375","abstract_canon_sha256":"ddcdcf5ed8cc7515c3b30754df8c93d9d001d1e4de3adec7ef2daeb1fb9f1662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:51.643696Z","signature_b64":"BVdhdoqajT7CIzvC+LSl/wMgeeqKaQ7XohiEgLZwlFF9cGmbWjAkLwPFUkC6PC2EdckQtmraQc/+/tPfHsieAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ecf58fdcfe6da5417805624577fcaea16761b89b578cebfb6776e98b43cef28","last_reissued_at":"2026-07-05T08:25:51.643239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:51.643239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Critique of Critique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junlong Li, Pengfei Liu, Ruifeng Yuan, Shichao Sun, Weizhe Yuan, Wenjie Li","submitted_at":"2024-01-09T12:20:41Z","abstract_excerpt":"Critique, as a natural language description for assessing the quality of model-generated content, has played a vital role in the training, evaluation, and refinement of LLMs. However, a systematic method to evaluate the quality of critique is lacking. In this paper, we pioneer the critique of critique, termed MetaCritique, which builds specific quantification criteria. To achieve a reliable evaluation outcome, we propose Atomic Information Units (AIUs), which describe the critique in a more fine-grained manner. MetaCritique aggregates each AIU's judgment for the overall score. Moreover, MetaCr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04518","kind":"arxiv","version":2},"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/2401.04518/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":"2401.04518","created_at":"2026-07-05T08:25:51.643300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04518v2","created_at":"2026-07-05T08:25:51.643300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04518","created_at":"2026-07-05T08:25:51.643300+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3HVR7OP43NF","created_at":"2026-07-05T08:25:51.643300+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3HVR7OP43NFIF4A","created_at":"2026-07-05T08:25:51.643300+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3HVR7OP","created_at":"2026-07-05T08:25:51.643300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I","json":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I.json","graph_json":"https://pith.science/api/pith-number/R3HVR7OP43NFIF4AKYSFO76K5I/graph.json","events_json":"https://pith.science/api/pith-number/R3HVR7OP43NFIF4AKYSFO76K5I/events.json","paper":"https://pith.science/paper/R3HVR7OP"},"agent_actions":{"view_html":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I","download_json":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I.json","view_paper":"https://pith.science/paper/R3HVR7OP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04518&json=true","fetch_graph":"https://pith.science/api/pith-number/R3HVR7OP43NFIF4AKYSFO76K5I/graph.json","fetch_events":"https://pith.science/api/pith-number/R3HVR7OP43NFIF4AKYSFO76K5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I/action/storage_attestation","attest_author":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I/action/author_attestation","sign_citation":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I/action/citation_signature","submit_replication":"https://pith.science/pith/R3HVR7OP43NFIF4AKYSFO76K5I/action/replication_record"}},"created_at":"2026-07-05T08:25:51.643300+00:00","updated_at":"2026-07-05T08:25:51.643300+00:00"}