{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OSGRG4IR3YK5MQIVV627ZCSHNQ","short_pith_number":"pith:OSGRG4IR","schema_version":"1.0","canonical_sha256":"748d137111de15d64115afb5fc8a476c3ed30dff83f8510fb6923ca02fa5108a","source":{"kind":"arxiv","id":"2501.14492","version":1},"attestation_state":"computed","paper":{"title":"RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Bowen Yu, Dayiheng Liu, Fei Huang, Junyang Lin, Ruoyu Sun, Tian Ding, Tianyu Liu, Zhengyang Tang, Zhenyang Xiao, Ziniu Li","submitted_at":"2025-01-24T13:48:10Z","abstract_excerpt":"Critiques are important for enhancing the performance of Large Language Models (LLMs), enabling both self-improvement and constructive feedback for others by identifying flaws and suggesting improvements. However, evaluating the critique capabilities of LLMs presents a significant challenge due to the open-ended nature of the task. In this work, we introduce a new benchmark designed to assess the critique capabilities of LLMs. Unlike existing benchmarks, which typically function in an open-loop fashion, our approach employs a closed-loop methodology that evaluates the quality of corrections ge"},"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":"2501.14492","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T13:48:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e1459cab254bccc337d95e9c784998461313063d1f7d3c589568df793519683","abstract_canon_sha256":"e741dca5001815f4824026b36078e2bd05784de026989909cf11ffda36a8987b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:01.628675Z","signature_b64":"DW4tY+0OjGwPzR6p2bS3lKvcO5EVcGdtGVS2yw81Dpt4VpmCa4Ob7DiVOdDQgYvxDtPNcBnNL6+cZ/6oj/SLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"748d137111de15d64115afb5fc8a476c3ed30dff83f8510fb6923ca02fa5108a","last_reissued_at":"2026-07-05T10:05:01.628235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:01.628235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Bowen Yu, Dayiheng Liu, Fei Huang, Junyang Lin, Ruoyu Sun, Tian Ding, Tianyu Liu, Zhengyang Tang, Zhenyang Xiao, Ziniu Li","submitted_at":"2025-01-24T13:48:10Z","abstract_excerpt":"Critiques are important for enhancing the performance of Large Language Models (LLMs), enabling both self-improvement and constructive feedback for others by identifying flaws and suggesting improvements. However, evaluating the critique capabilities of LLMs presents a significant challenge due to the open-ended nature of the task. In this work, we introduce a new benchmark designed to assess the critique capabilities of LLMs. Unlike existing benchmarks, which typically function in an open-loop fashion, our approach employs a closed-loop methodology that evaluates the quality of corrections ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14492","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/2501.14492/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":"2501.14492","created_at":"2026-07-05T10:05:01.628290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14492v1","created_at":"2026-07-05T10:05:01.628290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14492","created_at":"2026-07-05T10:05:01.628290+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSGRG4IR3YK5","created_at":"2026-07-05T10:05:01.628290+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSGRG4IR3YK5MQIV","created_at":"2026-07-05T10:05:01.628290+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSGRG4IR","created_at":"2026-07-05T10:05:01.628290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29425","citing_title":"Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ","json":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ.json","graph_json":"https://pith.science/api/pith-number/OSGRG4IR3YK5MQIVV627ZCSHNQ/graph.json","events_json":"https://pith.science/api/pith-number/OSGRG4IR3YK5MQIVV627ZCSHNQ/events.json","paper":"https://pith.science/paper/OSGRG4IR"},"agent_actions":{"view_html":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ","download_json":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ.json","view_paper":"https://pith.science/paper/OSGRG4IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14492&json=true","fetch_graph":"https://pith.science/api/pith-number/OSGRG4IR3YK5MQIVV627ZCSHNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OSGRG4IR3YK5MQIVV627ZCSHNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ/action/storage_attestation","attest_author":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ/action/author_attestation","sign_citation":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ/action/citation_signature","submit_replication":"https://pith.science/pith/OSGRG4IR3YK5MQIVV627ZCSHNQ/action/replication_record"}},"created_at":"2026-07-05T10:05:01.628290+00:00","updated_at":"2026-07-05T10:05:01.628290+00:00"}