{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLX5NIB4KJCJN4WT6DG6A6DAZD","short_pith_number":"pith:WLX5NIB4","schema_version":"1.0","canonical_sha256":"b2efd6a03c524496f2d3f0cde07860c8c52e15335d03b41cf2a68dd51052fcd5","source":{"kind":"arxiv","id":"2502.18874","version":3},"attestation_state":"computed","paper":{"title":"Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaishuai Xu, Liangyou Li, Lifeng Shang, Qun Liu, Tiezheng Yu, Wenjie Li, Wenjun Hou, Xin Jiang, Yi Cheng","submitted_at":"2025-02-26T06:31:45Z","abstract_excerpt":"Large Language Models (LLMs) are being used more and more extensively for automated evaluation in various scenarios. Previous studies have attempted to fine-tune open-source LLMs to replicate the evaluation explanations and judgments of powerful proprietary models, such as GPT-4. However, these methods are largely limited to text-based analyses under predefined general criteria, resulting in reduced adaptability for unseen instructions and demonstrating instability in evaluating adherence to quantitative and structural constraints. To address these limitations, we propose a novel evaluation fr"},"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":"2502.18874","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T06:31:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd3eb0a9137bb4ce38f8792c3f0a096d7eef24663c647a38c65b3426a32a8389","abstract_canon_sha256":"6f0dbede8abc707fcad6823c63b19be77528602e739f74a696f4ffa110c3a9e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:05.796676Z","signature_b64":"7CfAZtT/yZgUjZQkOyI+AqEv45H1oSjGyILHLuR96ZwcdYkIUI9u/UBVhq3kDSSyRGiHBoA9WNyXXn6G38b0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2efd6a03c524496f2d3f0cde07860c8c52e15335d03b41cf2a68dd51052fcd5","last_reissued_at":"2026-07-05T11:10:05.796158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:05.796158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kaishuai Xu, Liangyou Li, Lifeng Shang, Qun Liu, Tiezheng Yu, Wenjie Li, Wenjun Hou, Xin Jiang, Yi Cheng","submitted_at":"2025-02-26T06:31:45Z","abstract_excerpt":"Large Language Models (LLMs) are being used more and more extensively for automated evaluation in various scenarios. Previous studies have attempted to fine-tune open-source LLMs to replicate the evaluation explanations and judgments of powerful proprietary models, such as GPT-4. However, these methods are largely limited to text-based analyses under predefined general criteria, resulting in reduced adaptability for unseen instructions and demonstrating instability in evaluating adherence to quantitative and structural constraints. To address these limitations, we propose a novel evaluation fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18874","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/2502.18874/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":"2502.18874","created_at":"2026-07-05T11:10:05.796218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18874v3","created_at":"2026-07-05T11:10:05.796218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18874","created_at":"2026-07-05T11:10:05.796218+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLX5NIB4KJCJ","created_at":"2026-07-05T11:10:05.796218+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLX5NIB4KJCJN4WT","created_at":"2026-07-05T11:10:05.796218+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLX5NIB4","created_at":"2026-07-05T11:10:05.796218+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/WLX5NIB4KJCJN4WT6DG6A6DAZD","json":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD.json","graph_json":"https://pith.science/api/pith-number/WLX5NIB4KJCJN4WT6DG6A6DAZD/graph.json","events_json":"https://pith.science/api/pith-number/WLX5NIB4KJCJN4WT6DG6A6DAZD/events.json","paper":"https://pith.science/paper/WLX5NIB4"},"agent_actions":{"view_html":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD","download_json":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD.json","view_paper":"https://pith.science/paper/WLX5NIB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18874&json=true","fetch_graph":"https://pith.science/api/pith-number/WLX5NIB4KJCJN4WT6DG6A6DAZD/graph.json","fetch_events":"https://pith.science/api/pith-number/WLX5NIB4KJCJN4WT6DG6A6DAZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD/action/storage_attestation","attest_author":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD/action/author_attestation","sign_citation":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD/action/citation_signature","submit_replication":"https://pith.science/pith/WLX5NIB4KJCJN4WT6DG6A6DAZD/action/replication_record"}},"created_at":"2026-07-05T11:10:05.796218+00:00","updated_at":"2026-07-05T11:10:05.796218+00:00"}