{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VYGGL5PKXPXJOYLHNK7O3NT3RV","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":"ecbaafdf00b107dbfcdc2155f0ce045fdbaec41225457b283b2899f2fdb666c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T08:57:17Z","title_canon_sha256":"87ae05236550a2f0e81f402ac0b72348c2e00fe49e03952509a733d316112473"},"schema_version":"1.0","source":{"id":"2305.10819","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10819","created_at":"2026-07-05T07:01:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10819v2","created_at":"2026-07-05T07:01:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10819","created_at":"2026-07-05T07:01:41Z"},{"alias_kind":"pith_short_12","alias_value":"VYGGL5PKXPXJ","created_at":"2026-07-05T07:01:41Z"},{"alias_kind":"pith_short_16","alias_value":"VYGGL5PKXPXJOYLH","created_at":"2026-07-05T07:01:41Z"},{"alias_kind":"pith_short_8","alias_value":"VYGGL5PK","created_at":"2026-07-05T07:01:41Z"}],"graph_snapshots":[{"event_id":"sha256:a7076500e3d1fcbbc030f1505faf85f5f0d942f1ea70b4bf6eb11a52edb80a84","target":"graph","created_at":"2026-07-05T07:01:41Z","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/2305.10819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the performance of Grammatical Error Correction (GEC) systems is a challenging task due to its subjectivity. Designing an evaluation metric that is as objective as possible is crucial to the development of GEC task. However, mainstream evaluation metrics, i.e., reference-based metrics, introduce bias into the multi-reference evaluation by extracting edits without considering the presence of multiple references. To overcome this issue, we propose Chunk-LEvel Multi-reference Evaluation (CLEME), designed to evaluate GEC systems in the multi-reference evaluation setting. CLEME builds ch","authors_text":"Hai-Tao Zheng, Jingheng Ye, Qingyu Zhou, Shirong Ma, Yangning Li, Yinghui Li, Ying Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T08:57:17Z","title":"CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10819","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":"sha256:4b639bb38ceeb6aed4a18545ff2128b6971d047277f56a71af9f006c074c666e","target":"record","created_at":"2026-07-05T07:01:41Z","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":"ecbaafdf00b107dbfcdc2155f0ce045fdbaec41225457b283b2899f2fdb666c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T08:57:17Z","title_canon_sha256":"87ae05236550a2f0e81f402ac0b72348c2e00fe49e03952509a733d316112473"},"schema_version":"1.0","source":{"id":"2305.10819","kind":"arxiv","version":2}},"canonical_sha256":"ae0c65f5eabbee9761676abeedb67b8d64d70c672f870b035e77e4d72e06d9ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae0c65f5eabbee9761676abeedb67b8d64d70c672f870b035e77e4d72e06d9ff","first_computed_at":"2026-07-05T07:01:41.473689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:41.473689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QIhA8kb4re63iFBqN44mWL/S/64T+yOdSaxZEwi5RdE8eeV+1yF0vYiQ0argLbyxA5gva50xo0xBRHWDXhrvAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:41.474115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10819","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b639bb38ceeb6aed4a18545ff2128b6971d047277f56a71af9f006c074c666e","sha256:a7076500e3d1fcbbc030f1505faf85f5f0d942f1ea70b4bf6eb11a52edb80a84"],"state_sha256":"de83ea5758846ce28ad57c36d91bee369fd903491a60c31ae4af175022b9b3b2"}