{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RXVI3IA44RWKPNBXK6DYFCNUJK","short_pith_number":"pith:RXVI3IA4","schema_version":"1.0","canonical_sha256":"8dea8da01ce46ca7b43757878289b44aaf943d10d54374afddca82d3864cc848","source":{"kind":"arxiv","id":"2407.00934","version":2},"attestation_state":"computed","paper":{"title":"CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai-Tao Zheng, Hong-Gee Kim, Jingheng Ye, Linlin Song, Qingyu Zhou, Ruitong Liu, Wenhao Jiang, Xin Su, Yinghui Li, Ying Shen, Zifei Shan, Zishan Xu","submitted_at":"2024-07-01T03:35:58Z","abstract_excerpt":"The paper focuses on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, which received little attention in previous studies. To bridge the gap, we introduce **CLEME2.0**, a reference-based metric describing four fundamental aspects of GEC systems: hit-correction, wrong-correction, under-correction, and over-correction. They collectively contribute to exposing critical qualities and locating drawbacks of GEC systems. Evaluating systems by combining these aspects also leads to superior human consistency over other reference-based and reference-less metrics. Extensive "},"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":"2407.00934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T03:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"9cf1f8ae2f854c705d5ea16449e60ac789fe7c9d68d632da31dbd6220b887c3b","abstract_canon_sha256":"011345883f9364a804ca8d9f8c2de5bf1cc035c374605705eb4da4487505c3b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:33.130375Z","signature_b64":"XsqGLqFvUwmPCFVfBJTQCPVYht02/vFF8fgtD6cVUFwdLIJIY8poP90XVe8L2GC6GZtrqb6gvKOjqh/SrHACCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dea8da01ce46ca7b43757878289b44aaf943d10d54374afddca82d3864cc848","last_reissued_at":"2026-07-05T11:11:33.129806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:33.129806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai-Tao Zheng, Hong-Gee Kim, Jingheng Ye, Linlin Song, Qingyu Zhou, Ruitong Liu, Wenhao Jiang, Xin Su, Yinghui Li, Ying Shen, Zifei Shan, Zishan Xu","submitted_at":"2024-07-01T03:35:58Z","abstract_excerpt":"The paper focuses on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, which received little attention in previous studies. To bridge the gap, we introduce **CLEME2.0**, a reference-based metric describing four fundamental aspects of GEC systems: hit-correction, wrong-correction, under-correction, and over-correction. They collectively contribute to exposing critical qualities and locating drawbacks of GEC systems. Evaluating systems by combining these aspects also leads to superior human consistency over other reference-based and reference-less metrics. Extensive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00934","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/2407.00934/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":"2407.00934","created_at":"2026-07-05T11:11:33.129866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00934v2","created_at":"2026-07-05T11:11:33.129866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00934","created_at":"2026-07-05T11:11:33.129866+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXVI3IA44RWK","created_at":"2026-07-05T11:11:33.129866+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXVI3IA44RWKPNBX","created_at":"2026-07-05T11:11:33.129866+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXVI3IA4","created_at":"2026-07-05T11:11:33.129866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08459","citing_title":"Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK","json":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK.json","graph_json":"https://pith.science/api/pith-number/RXVI3IA44RWKPNBXK6DYFCNUJK/graph.json","events_json":"https://pith.science/api/pith-number/RXVI3IA44RWKPNBXK6DYFCNUJK/events.json","paper":"https://pith.science/paper/RXVI3IA4"},"agent_actions":{"view_html":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK","download_json":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK.json","view_paper":"https://pith.science/paper/RXVI3IA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00934&json=true","fetch_graph":"https://pith.science/api/pith-number/RXVI3IA44RWKPNBXK6DYFCNUJK/graph.json","fetch_events":"https://pith.science/api/pith-number/RXVI3IA44RWKPNBXK6DYFCNUJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK/action/storage_attestation","attest_author":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK/action/author_attestation","sign_citation":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK/action/citation_signature","submit_replication":"https://pith.science/pith/RXVI3IA44RWKPNBXK6DYFCNUJK/action/replication_record"}},"created_at":"2026-07-05T11:11:33.129866+00:00","updated_at":"2026-07-05T11:11:33.129866+00:00"}