{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VYGGL5PKXPXJOYLHNK7O3NT3RV","short_pith_number":"pith:VYGGL5PK","schema_version":"1.0","canonical_sha256":"ae0c65f5eabbee9761676abeedb67b8d64d70c672f870b035e77e4d72e06d9ff","source":{"kind":"arxiv","id":"2305.10819","version":2},"attestation_state":"computed","paper":{"title":"CLEME: Debiasing Multi-reference Evaluation 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, Jingheng Ye, Qingyu Zhou, Shirong Ma, Yangning Li, Yinghui Li, Ying Shen","submitted_at":"2023-05-18T08:57:17Z","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"},"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":"2305.10819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T08:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"87ae05236550a2f0e81f402ac0b72348c2e00fe49e03952509a733d316112473","abstract_canon_sha256":"ecbaafdf00b107dbfcdc2155f0ce045fdbaec41225457b283b2899f2fdb666c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:41.474115Z","signature_b64":"QIhA8kb4re63iFBqN44mWL/S/64T+yOdSaxZEwi5RdE8eeV+1yF0vYiQ0argLbyxA5gva50xo0xBRHWDXhrvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae0c65f5eabbee9761676abeedb67b8d64d70c672f870b035e77e4d72e06d9ff","last_reissued_at":"2026-07-05T07:01:41.473689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:41.473689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLEME: Debiasing Multi-reference Evaluation 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, Jingheng Ye, Qingyu Zhou, Shirong Ma, Yangning Li, Yinghui Li, Ying Shen","submitted_at":"2023-05-18T08:57:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10819","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/2305.10819/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":"2305.10819","created_at":"2026-07-05T07:01:41.473752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10819v2","created_at":"2026-07-05T07:01:41.473752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10819","created_at":"2026-07-05T07:01:41.473752+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYGGL5PKXPXJ","created_at":"2026-07-05T07:01:41.473752+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYGGL5PKXPXJOYLH","created_at":"2026-07-05T07:01:41.473752+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYGGL5PK","created_at":"2026-07-05T07:01:41.473752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00330","citing_title":"Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV","json":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV.json","graph_json":"https://pith.science/api/pith-number/VYGGL5PKXPXJOYLHNK7O3NT3RV/graph.json","events_json":"https://pith.science/api/pith-number/VYGGL5PKXPXJOYLHNK7O3NT3RV/events.json","paper":"https://pith.science/paper/VYGGL5PK"},"agent_actions":{"view_html":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV","download_json":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV.json","view_paper":"https://pith.science/paper/VYGGL5PK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10819&json=true","fetch_graph":"https://pith.science/api/pith-number/VYGGL5PKXPXJOYLHNK7O3NT3RV/graph.json","fetch_events":"https://pith.science/api/pith-number/VYGGL5PKXPXJOYLHNK7O3NT3RV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV/action/storage_attestation","attest_author":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV/action/author_attestation","sign_citation":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV/action/citation_signature","submit_replication":"https://pith.science/pith/VYGGL5PKXPXJOYLHNK7O3NT3RV/action/replication_record"}},"created_at":"2026-07-05T07:01:41.473752+00:00","updated_at":"2026-07-05T07:01:41.473752+00:00"}