{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QQZQBB4WE62ZOZQLQRTHPOH6CD","short_pith_number":"pith:QQZQBB4W","canonical_record":{"source":{"id":"2403.17540","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"96ba77549aefb5be913629fc244b815a8b08829fc403d5f8399333e5359b0b03","abstract_canon_sha256":"36ac0cf73809bab069a5901fe4e9c98d858c0fe8905baa28fa3b0b9080770d82"},"schema_version":"1.0"},"canonical_sha256":"843300879627b597660b846677b8fe10f911ffdebc12769d775b0f6d269cc296","source":{"kind":"arxiv","id":"2403.17540","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17540","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17540v2","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17540","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"QQZQBB4WE62Z","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"QQZQBB4WE62ZOZQL","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"QQZQBB4W","created_at":"2026-07-05T08:23:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QQZQBB4WE62ZOZQLQRTHPOH6CD","target":"record","payload":{"canonical_record":{"source":{"id":"2403.17540","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"96ba77549aefb5be913629fc244b815a8b08829fc403d5f8399333e5359b0b03","abstract_canon_sha256":"36ac0cf73809bab069a5901fe4e9c98d858c0fe8905baa28fa3b0b9080770d82"},"schema_version":"1.0"},"canonical_sha256":"843300879627b597660b846677b8fe10f911ffdebc12769d775b0f6d269cc296","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:20.374439Z","signature_b64":"1MhGZ0NW2heekW4xuJgmXUy6TulF7gwLrWpOtPL0/vTX+YRxrEIJfJJ5CKzGYAThNL8c1p6xkY23z3C5IUsNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"843300879627b597660b846677b8fe10f911ffdebc12769d775b0f6d269cc296","last_reissued_at":"2026-07-05T08:23:20.373970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:20.373970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.17540","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CKrtAZTpVfAeqYIlqlD2FRsF4P1L6Le8iaKosfxW6ni0knySCL34xKFrFAwcfl3UzYWAPxisU2CatjeLmwYqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:41:57.608188Z"},"content_sha256":"0ca05edebc9b42bdb1134ce7c77bc8f8ad6c371224e34eef39f4ce985c53b8d4","schema_version":"1.0","event_id":"sha256:0ca05edebc9b42bdb1134ce7c77bc8f8ad6c371224e34eef39f4ce985c53b8d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QQZQBB4WE62ZOZQLQRTHPOH6CD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mamoru Komachi, Masamune Kobayashi, Masato Mita","submitted_at":"2024-03-26T09:43:15Z","abstract_excerpt":"Large Language Models (LLMs) have been reported to outperform existing automatic evaluation metrics in some tasks, such as text summarization and machine translation. However, there has been a lack of research on LLMs as evaluators in grammatical error correction (GEC). In this study, we investigate the performance of LLMs in GEC evaluation by employing prompts designed to incorporate various evaluation criteria inspired by previous research. Our extensive experimental results demonstrate that GPT-4 achieved Kendall's rank correlation of 0.662 with human judgments, surpassing all existing meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17540","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/2403.17540/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":"2026-07-05T08:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/OoNpPCWt8L2wyPQjNnmnXX3bqwFEJGOdBgH1TcRTlLrfYCaTR96rK76g9Mf/dZcirOzP3OTJysSgI9GZKXRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:41:57.609295Z"},"content_sha256":"9981269328f8acca181fdbcc7139ea803b13460dbf491d91e0bc7da03b893e50","schema_version":"1.0","event_id":"sha256:9981269328f8acca181fdbcc7139ea803b13460dbf491d91e0bc7da03b893e50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD/bundle.json","state_url":"https://pith.science/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD/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":"2026-08-16T22:41:57Z","links":{"resolver":"https://pith.science/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD","bundle":"https://pith.science/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD/bundle.json","state":"https://pith.science/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQZQBB4WE62ZOZQLQRTHPOH6CD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QQZQBB4WE62ZOZQLQRTHPOH6CD","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":"36ac0cf73809bab069a5901fe4e9c98d858c0fe8905baa28fa3b0b9080770d82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:43:15Z","title_canon_sha256":"96ba77549aefb5be913629fc244b815a8b08829fc403d5f8399333e5359b0b03"},"schema_version":"1.0","source":{"id":"2403.17540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17540","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17540v2","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17540","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"QQZQBB4WE62Z","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"QQZQBB4WE62ZOZQL","created_at":"2026-07-05T08:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"QQZQBB4W","created_at":"2026-07-05T08:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:9981269328f8acca181fdbcc7139ea803b13460dbf491d91e0bc7da03b893e50","target":"graph","created_at":"2026-07-05T08:23:20Z","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/2403.17540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been reported to outperform existing automatic evaluation metrics in some tasks, such as text summarization and machine translation. However, there has been a lack of research on LLMs as evaluators in grammatical error correction (GEC). In this study, we investigate the performance of LLMs in GEC evaluation by employing prompts designed to incorporate various evaluation criteria inspired by previous research. Our extensive experimental results demonstrate that GPT-4 achieved Kendall's rank correlation of 0.662 with human judgments, surpassing all existing meth","authors_text":"Mamoru Komachi, Masamune Kobayashi, Masato Mita","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:43:15Z","title":"Large Language Models Are State-of-the-Art Evaluator for Grammatical Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17540","kind":"arxiv","version":2},"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":"sha256:0ca05edebc9b42bdb1134ce7c77bc8f8ad6c371224e34eef39f4ce985c53b8d4","target":"record","created_at":"2026-07-05T08:23:20Z","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":"36ac0cf73809bab069a5901fe4e9c98d858c0fe8905baa28fa3b0b9080770d82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-26T09:43:15Z","title_canon_sha256":"96ba77549aefb5be913629fc244b815a8b08829fc403d5f8399333e5359b0b03"},"schema_version":"1.0","source":{"id":"2403.17540","kind":"arxiv","version":2}},"canonical_sha256":"843300879627b597660b846677b8fe10f911ffdebc12769d775b0f6d269cc296","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"843300879627b597660b846677b8fe10f911ffdebc12769d775b0f6d269cc296","first_computed_at":"2026-07-05T08:23:20.373970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:20.373970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1MhGZ0NW2heekW4xuJgmXUy6TulF7gwLrWpOtPL0/vTX+YRxrEIJfJJ5CKzGYAThNL8c1p6xkY23z3C5IUsNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:20.374439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ca05edebc9b42bdb1134ce7c77bc8f8ad6c371224e34eef39f4ce985c53b8d4","sha256:9981269328f8acca181fdbcc7139ea803b13460dbf491d91e0bc7da03b893e50"],"state_sha256":"4e5a29c0f491b58b5082c0bf4913430de31dfaba5123e1833c21c04da88590c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZO5+MCcTxkGn3i3fvikjW1Cpv7davYVQyOIGQ70NKzuC0EBW1fz7XRnJQpJ/kxquKTITp4MXPxNLfVds4HIKBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:41:57.624491Z","bundle_sha256":"3fcc753d594b52b2b2ca84934c60be5f8a15ab69b58f07400c7d0de7582761b4"}}