{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RGSHT52KQ2WM5YLV4NU6CVZTX6","short_pith_number":"pith:RGSHT52K","schema_version":"1.0","canonical_sha256":"89a479f74a86accee175e369e15733bf9cad63eb1b1ab39ab3e0279b4c1b7332","source":{"kind":"arxiv","id":"2411.02448","version":3},"attestation_state":"computed","paper":{"title":"Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aliyah R. Hsu, Bin Bi, Bin Yu, Claire Na Cheng, James Zhu, Katherine Tan, Regunathan Radhakrishnan, Roshanak Omrani, Shiva K. Pentyala, Shubham Mehrotra, Sitaram Asur, Sougata Chaudhuri, Xiang-Bo Mao, Zhichao Wang","submitted_at":"2024-11-03T02:36:33Z","abstract_excerpt":"LLMs have demonstrated impressive proficiency in generating coherent and high-quality text, making them valuable across a range of text-generation tasks. However, rigorous evaluation of this generated content is crucial, as ensuring its quality remains a significant challenge due to persistent issues such as factual inaccuracies and hallucination. This paper introduces three fine-tuned general-purpose LLM autoevaluators, REC-8B, REC-12B and REC-70B, specifically designed to evaluate generated text across several dimensions: faithfulness, instruction following, coherence, and completeness. Thes"},"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":"2411.02448","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-03T02:36:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"acbc50cc05dd6a659df8a18821ce13b8505470289b87770b6a76432e9ac66898","abstract_canon_sha256":"86598efc0db9e300cb7c730c59fccb5538ccb4e4f9ced1be1ccf74bd697642f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:36.072829Z","signature_b64":"FLgMZg55gKuHaQSSloeLxsHqFCu9nqnWZEjZuPm4l8eN+2Y9epbbnrWVKB8n47yNxffaK2coO4cunodwm0IrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a479f74a86accee175e369e15733bf9cad63eb1b1ab39ab3e0279b4c1b7332","last_reissued_at":"2026-07-05T11:05:36.072336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:36.072336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rate, Explain and Cite (REC): Enhanced Explanation and Attribution in Automatic Evaluation by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aliyah R. Hsu, Bin Bi, Bin Yu, Claire Na Cheng, James Zhu, Katherine Tan, Regunathan Radhakrishnan, Roshanak Omrani, Shiva K. Pentyala, Shubham Mehrotra, Sitaram Asur, Sougata Chaudhuri, Xiang-Bo Mao, Zhichao Wang","submitted_at":"2024-11-03T02:36:33Z","abstract_excerpt":"LLMs have demonstrated impressive proficiency in generating coherent and high-quality text, making them valuable across a range of text-generation tasks. However, rigorous evaluation of this generated content is crucial, as ensuring its quality remains a significant challenge due to persistent issues such as factual inaccuracies and hallucination. This paper introduces three fine-tuned general-purpose LLM autoevaluators, REC-8B, REC-12B and REC-70B, specifically designed to evaluate generated text across several dimensions: faithfulness, instruction following, coherence, and completeness. Thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02448","kind":"arxiv","version":3},"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/2411.02448/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":"2411.02448","created_at":"2026-07-05T11:05:36.072401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02448v3","created_at":"2026-07-05T11:05:36.072401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02448","created_at":"2026-07-05T11:05:36.072401+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGSHT52KQ2WM","created_at":"2026-07-05T11:05:36.072401+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGSHT52KQ2WM5YLV","created_at":"2026-07-05T11:05:36.072401+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGSHT52K","created_at":"2026-07-05T11:05:36.072401+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/RGSHT52KQ2WM5YLV4NU6CVZTX6","json":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6.json","graph_json":"https://pith.science/api/pith-number/RGSHT52KQ2WM5YLV4NU6CVZTX6/graph.json","events_json":"https://pith.science/api/pith-number/RGSHT52KQ2WM5YLV4NU6CVZTX6/events.json","paper":"https://pith.science/paper/RGSHT52K"},"agent_actions":{"view_html":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6","download_json":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6.json","view_paper":"https://pith.science/paper/RGSHT52K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02448&json=true","fetch_graph":"https://pith.science/api/pith-number/RGSHT52KQ2WM5YLV4NU6CVZTX6/graph.json","fetch_events":"https://pith.science/api/pith-number/RGSHT52KQ2WM5YLV4NU6CVZTX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6/action/storage_attestation","attest_author":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6/action/author_attestation","sign_citation":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6/action/citation_signature","submit_replication":"https://pith.science/pith/RGSHT52KQ2WM5YLV4NU6CVZTX6/action/replication_record"}},"created_at":"2026-07-05T11:05:36.072401+00:00","updated_at":"2026-07-05T11:05:36.072401+00:00"}