{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C2OUHYVCYFFCQWVKKTYOSRBBP7","short_pith_number":"pith:C2OUHYVC","schema_version":"1.0","canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","source":{"kind":"arxiv","id":"2407.14467","version":2},"attestation_state":"computed","paper":{"title":"Check-Eval: A Checklist-based Approach for Evaluating Text Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andre Assumpcao, Jayr Pereira, Roberto Lotufo","submitted_at":"2024-07-19T17:14:16Z","abstract_excerpt":"Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this paper, we propose \\textsc{Check-Eval}, a novel evaluation framework leveraging LLMs to assess the quality of generated text through a checklist-based approach. \\textsc{Check-Eval} can be employed as both a reference-free and reference-dependent evaluation method, providing a structured and interpretable assessment of text quality. The framework consists of two m"},"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":"2407.14467","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-19T17:14:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd72144e1eb53f6e76614a98650f4e7f1484b459f3d9c8496679e908c9d77938","abstract_canon_sha256":"d00419b44735045a84638dfa9abdfdc8546c6bce8a074270408a4149164e0e0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:18.039394Z","signature_b64":"0FnXhFGYUV+BqKxP1sHGF69A+iR+M14dOniHOcyRimfRy09w+ou5jncRe+KFWr/wod8Vyv9lant5KP5dbYIdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"169d43e2a2c14a285aaa54f0e944217fddad2ababca8e39af4ecedd24c2004f8","last_reissued_at":"2026-07-05T09:05:18.038938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:18.038938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Check-Eval: A Checklist-based Approach for Evaluating Text Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andre Assumpcao, Jayr Pereira, Roberto Lotufo","submitted_at":"2024-07-19T17:14:16Z","abstract_excerpt":"Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this paper, we propose \\textsc{Check-Eval}, a novel evaluation framework leveraging LLMs to assess the quality of generated text through a checklist-based approach. \\textsc{Check-Eval} can be employed as both a reference-free and reference-dependent evaluation method, providing a structured and interpretable assessment of text quality. The framework consists of two m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14467","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/2407.14467/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":"2407.14467","created_at":"2026-07-05T09:05:18.038993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14467v2","created_at":"2026-07-05T09:05:18.038993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14467","created_at":"2026-07-05T09:05:18.038993+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2OUHYVCYFFC","created_at":"2026-07-05T09:05:18.038993+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2OUHYVCYFFCQWVK","created_at":"2026-07-05T09:05:18.038993+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2OUHYVC","created_at":"2026-07-05T09:05:18.038993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04295","citing_title":"Adaptive Cost-Efficient Evaluation for Reliable Patent Claim Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11655","citing_title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7","json":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7.json","graph_json":"https://pith.science/api/pith-number/C2OUHYVCYFFCQWVKKTYOSRBBP7/graph.json","events_json":"https://pith.science/api/pith-number/C2OUHYVCYFFCQWVKKTYOSRBBP7/events.json","paper":"https://pith.science/paper/C2OUHYVC"},"agent_actions":{"view_html":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7","download_json":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7.json","view_paper":"https://pith.science/paper/C2OUHYVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14467&json=true","fetch_graph":"https://pith.science/api/pith-number/C2OUHYVCYFFCQWVKKTYOSRBBP7/graph.json","fetch_events":"https://pith.science/api/pith-number/C2OUHYVCYFFCQWVKKTYOSRBBP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/action/storage_attestation","attest_author":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/action/author_attestation","sign_citation":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/action/citation_signature","submit_replication":"https://pith.science/pith/C2OUHYVCYFFCQWVKKTYOSRBBP7/action/replication_record"}},"created_at":"2026-07-05T09:05:18.038993+00:00","updated_at":"2026-07-05T09:05:18.038993+00:00"}