{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","short_pith_number":"pith:JAQ4YHTP","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"},"canonical_sha256":"4821cc1e6f4105ccb9f56c362dc3c722471248615608cb45cfd685acf63b5aa1","source":{"kind":"arxiv","id":"2306.10452","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","target":"record","payload":{"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"},"canonical_sha256":"4821cc1e6f4105ccb9f56c362dc3c722471248615608cb45cfd685acf63b5aa1","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"},"source_kind":"arxiv","source_id":"2306.10452","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:21:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLtgp+HFKDUssKf08Bio4/Go/m0a4no+0h4n0u9OVIzAL/xCpit5YN2P2ebAkD6XhK3VyBoPVxS1a8j3GmdGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:49.654090Z"},"content_sha256":"95c14089ac33e290896c933f5588f5582658bacb77ed55ab08a26b6952c88497","schema_version":"1.0","event_id":"sha256:95c14089ac33e290896c933f5588f5582658bacb77ed55ab08a26b6952c88497"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:21:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yBR7xRal/SX13kZCGBw6DGH9eW6Hkf3Sng31IvkM5PNZpyoBqKPjquWvKsDg+egBs4/BIqyH/t21ORSTNQwrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:49.654481Z"},"content_sha256":"83cdb41fcf087ea7779f69059b9dcfecbddcf660273490accdc28ffc827a0d0f","schema_version":"1.0","event_id":"sha256:83cdb41fcf087ea7779f69059b9dcfecbddcf660273490accdc28ffc827a0d0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/bundle.json","state_url":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T20:50:49Z","links":{"resolver":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ","bundle":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/bundle.json","state":"https://pith.science/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAQ4YHTPIEC4ZOPVNQ3C3Q6HEJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/F1lKF3x547jO0zX1CV3VbhcUvm9Y518+IVHhfaY3WkBLx+qrCv+kv9Par17dYC5fHko9NR/UoiHL9Bb45kSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:50:49.656645Z","bundle_sha256":"30f98d12eed5d16b35cbaeb9dbb50c695fe07ef3931d282b8d5595e74cc97f18"}}