{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZEPUNYPJZDO2UKJRASD66CQJIK","short_pith_number":"pith:ZEPUNYPJ","schema_version":"1.0","canonical_sha256":"c91f46e1e9c8ddaa29310487ef0a0942b0ba255f52de650f428ed443f8a346b9","source":{"kind":"arxiv","id":"2405.12163","version":1},"attestation_state":"computed","paper":{"title":"Fennec: Fine-grained Language Model Evaluation and Correction Extended through Branching and Bridging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoke Zhang, Helan hu, Juntao Li, Jun Xu, Min Zhang, Xiaobo Liang","submitted_at":"2024-05-20T16:47:22Z","abstract_excerpt":"The rapid advancement of large language models has given rise to a plethora of applications across a myriad of real-world tasks, mainly centered on aligning with human intent. However, the complexities inherent in human intent necessitate a dependence on labor-intensive and time-consuming human evaluation. To alleviate this constraint, we delve into the paradigm of employing open-source large language models as evaluators, aligning with the prevailing trend of utilizing GPT-4. Particularly, we present a step-by-step evaluation framework: \\textbf{Fennec}, capable of \\textbf{F}ine-grained \\textb"},"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":"2405.12163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T16:47:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58037e29e1812bff984b104a265384673e7d891bd6fd43db64101626d9367b0c","abstract_canon_sha256":"35de025148a28360ae21f13028aa06152909948f34d0974c942e66fbba2fc7bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:00.944434Z","signature_b64":"iJkVBkTFJY0C953K/KyMQDCX6WS2HzCEZQHpiXHssnQtMmf8y90GfNmFPTbjr6cMc5QGdUE6jxeCZmVet2NgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c91f46e1e9c8ddaa29310487ef0a0942b0ba255f52de650f428ed443f8a346b9","last_reissued_at":"2026-07-05T08:21:00.943921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:00.943921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fennec: Fine-grained Language Model Evaluation and Correction Extended through Branching and Bridging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoke Zhang, Helan hu, Juntao Li, Jun Xu, Min Zhang, Xiaobo Liang","submitted_at":"2024-05-20T16:47:22Z","abstract_excerpt":"The rapid advancement of large language models has given rise to a plethora of applications across a myriad of real-world tasks, mainly centered on aligning with human intent. However, the complexities inherent in human intent necessitate a dependence on labor-intensive and time-consuming human evaluation. To alleviate this constraint, we delve into the paradigm of employing open-source large language models as evaluators, aligning with the prevailing trend of utilizing GPT-4. Particularly, we present a step-by-step evaluation framework: \\textbf{Fennec}, capable of \\textbf{F}ine-grained \\textb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12163","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/2405.12163/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":"2405.12163","created_at":"2026-07-05T08:21:00.943987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12163v1","created_at":"2026-07-05T08:21:00.943987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12163","created_at":"2026-07-05T08:21:00.943987+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEPUNYPJZDO2","created_at":"2026-07-05T08:21:00.943987+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEPUNYPJZDO2UKJR","created_at":"2026-07-05T08:21:00.943987+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEPUNYPJ","created_at":"2026-07-05T08:21:00.943987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06009","citing_title":"Unlocking Recursive Thinking of LLMs: Alignment via Refinement","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK","json":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK.json","graph_json":"https://pith.science/api/pith-number/ZEPUNYPJZDO2UKJRASD66CQJIK/graph.json","events_json":"https://pith.science/api/pith-number/ZEPUNYPJZDO2UKJRASD66CQJIK/events.json","paper":"https://pith.science/paper/ZEPUNYPJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK","download_json":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK.json","view_paper":"https://pith.science/paper/ZEPUNYPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12163&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEPUNYPJZDO2UKJRASD66CQJIK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEPUNYPJZDO2UKJRASD66CQJIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK/action/storage_attestation","attest_author":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK/action/author_attestation","sign_citation":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK/action/citation_signature","submit_replication":"https://pith.science/pith/ZEPUNYPJZDO2UKJRASD66CQJIK/action/replication_record"}},"created_at":"2026-07-05T08:21:00.943987+00:00","updated_at":"2026-07-05T08:21:00.943987+00:00"}