{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"da9869b3c850e07ed4ef89bde5d9a8650dddf2733b4588d16d322693b8c1f4e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T01:38:53Z","title_canon_sha256":"b3f6e4b76f73048dcfaf8c15574ceec4ab79da276bf7a896848e006cffc98701"},"schema_version":"1.0","source":{"id":"2306.10452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10452","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10452v1","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10452","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"JAQ4YHTPIEC4","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"pith_short_16","alias_value":"JAQ4YHTPIEC4ZOPV","created_at":"2026-07-05T06:21:38Z"},{"alias_kind":"pith_short_8","alias_value":"JAQ4YHTP","created_at":"2026-07-05T06:21:38Z"}],"graph_snapshots":[{"event_id":"sha256:83cdb41fcf087ea7779f69059b9dcfecbddcf660273490accdc28ffc827a0d0f","target":"graph","created_at":"2026-07-05T06:21:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.10452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T01:38:53Z","title":"MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10452","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:95c14089ac33e290896c933f5588f5582658bacb77ed55ab08a26b6952c88497","target":"record","created_at":"2026-07-05T06:21:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"da9869b3c850e07ed4ef89bde5d9a8650dddf2733b4588d16d322693b8c1f4e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T01:38:53Z","title_canon_sha256":"b3f6e4b76f73048dcfaf8c15574ceec4ab79da276bf7a896848e006cffc98701"},"schema_version":"1.0","source":{"id":"2306.10452","kind":"arxiv","version":1}},"canonical_sha256":"4821cc1e6f4105ccb9f56c362dc3c722471248615608cb45cfd685acf63b5aa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4821cc1e6f4105ccb9f56c362dc3c722471248615608cb45cfd685acf63b5aa1","first_computed_at":"2026-07-05T06:21:38.045951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:38.045951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cdyEG6dhqbyDMO4ZfAFmxdC6pa3M1IF0HwfGL6vHBLXvgGeGF7kKT8DgU8ZLMYqb2ioJ+HN0guk9OcD7YvnaAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:38.046361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95c14089ac33e290896c933f5588f5582658bacb77ed55ab08a26b6952c88497","sha256:83cdb41fcf087ea7779f69059b9dcfecbddcf660273490accdc28ffc827a0d0f"],"state_sha256":"bc64618c47588fe03b91d479f99dbee53ca3b8b68cdd7ddba5fcc7226151f313"}