{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","short_pith_number":"pith:JAQ4YHTP","schema_version":"1.0","canonical_sha256":"4821cc1e6f4105ccb9f56c362dc3c722471248615608cb45cfd685acf63b5aa1","source":{"kind":"arxiv","id":"2306.10452","version":1},"attestation_state":"computed","paper":{"title":"MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achille Fokoue, Alexander Gray, Chulaka Gunasekara, Diwakar Mahajan, Ibrahim Abdelaziz, Keerthiram Murugesan, Maxwell Crouse, Pavan Kapanipathi, Salim Roukos, Sarathkrishna Swaminathan, Soham Dan, Subhajit Chaudhury","submitted_at":"2023-06-18T01:38:53Z","abstract_excerpt":"With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal attention. Most recent works focus either on task-specific evaluation metrics or study the properties of machine-generated text captured by the existing metrics. In this work, we propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mism"},"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":"2306.10452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T01:38:53Z","cross_cats_sorted":[],"title_canon_sha256":"b3f6e4b76f73048dcfaf8c15574ceec4ab79da276bf7a896848e006cffc98701","abstract_canon_sha256":"da9869b3c850e07ed4ef89bde5d9a8650dddf2733b4588d16d322693b8c1f4e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:38.046361Z","signature_b64":"cdyEG6dhqbyDMO4ZfAFmxdC6pa3M1IF0HwfGL6vHBLXvgGeGF7kKT8DgU8ZLMYqb2ioJ+HN0guk9OcD7YvnaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4821cc1e6f4105ccb9f56c362dc3c722471248615608cb45cfd685acf63b5aa1","last_reissued_at":"2026-07-05T06:21:38.045951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:38.045951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achille Fokoue, Alexander Gray, Chulaka Gunasekara, Diwakar Mahajan, Ibrahim Abdelaziz, Keerthiram Murugesan, Maxwell Crouse, Pavan Kapanipathi, Salim Roukos, Sarathkrishna Swaminathan, Soham Dan, Subhajit Chaudhury","submitted_at":"2023-06-18T01:38:53Z","abstract_excerpt":"With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal attention. Most recent works focus either on task-specific evaluation metrics or study the properties of machine-generated text captured by the existing metrics. In this work, we propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mism"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10452","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/2306.10452/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":"2306.10452","created_at":"2026-07-05T06:21:38.046008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10452v1","created_at":"2026-07-05T06:21:38.046008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10452","created_at":"2026-07-05T06:21:38.046008+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAQ4YHTPIEC4","created_at":"2026-07-05T06:21:38.046008+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAQ4YHTPIEC4ZOPV","created_at":"2026-07-05T06:21:38.046008+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAQ4YHTP","created_at":"2026-07-05T06:21:38.046008+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/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","json":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ.json","graph_json":"https://pith.science/api/pith-number/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/graph.json","events_json":"https://pith.science/api/pith-number/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/events.json","paper":"https://pith.science/paper/JAQ4YHTP"},"agent_actions":{"view_html":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","download_json":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ.json","view_paper":"https://pith.science/paper/JAQ4YHTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10452&json=true","fetch_graph":"https://pith.science/api/pith-number/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/action/storage_attestation","attest_author":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/action/author_attestation","sign_citation":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/action/citation_signature","submit_replication":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/action/replication_record"}},"created_at":"2026-07-05T06:21:38.046008+00:00","updated_at":"2026-07-05T06:21:38.046008+00:00"}