{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PR335IM4KMONM3S6X6KHJE7WJX","short_pith_number":"pith:PR335IM4","schema_version":"1.0","canonical_sha256":"7c77bea19c531cd66e5ebf947493f64dc707ed69105b05137e92ada8a0f01e64","source":{"kind":"arxiv","id":"2105.04443","version":1},"attestation_state":"computed","paper":{"title":"Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liner Yang, Maosong Sun, Tat-Seng Chua, Xiaoyuan Yi, Zhenghao Liu","submitted_at":"2021-05-10T15:04:25Z","abstract_excerpt":"Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC ev"},"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":"2105.04443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T15:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"70b3279f285699ceb6bffb2cce24c5c6b3a8862fdbff020bcce42c367bf8eaa1","abstract_canon_sha256":"34a66742f93a1510ec5acc84b679f73f920cc9aee9863e4f0c5278fef06eb789"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:57.309852Z","signature_b64":"9CBeQl6v5dWrE6I5xgdo75Bupewec4HzFvoCmfEbYh3nI/jj6dCiUNZSLmuOMvHqHqPmFzqwppXG/B7HoTMEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c77bea19c531cd66e5ebf947493f64dc707ed69105b05137e92ada8a0f01e64","last_reissued_at":"2026-07-05T02:38:57.309482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:57.309482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liner Yang, Maosong Sun, Tat-Seng Chua, Xiaoyuan Yi, Zhenghao Liu","submitted_at":"2021-05-10T15:04:25Z","abstract_excerpt":"Grammatical Error Correction (GEC) aims to correct writing errors and help language learners improve their writing skills. However, existing GEC models tend to produce spurious corrections or fail to detect lots of errors. The quality estimation model is necessary to ensure learners get accurate GEC results and avoid misleading from poorly corrected sentences. Well-trained GEC models can generate several high-quality hypotheses through decoding, such as beam search, which provide valuable GEC evidence and can be used to evaluate GEC quality. However, existing models neglect the possible GEC ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04443","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/2105.04443/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":"2105.04443","created_at":"2026-07-05T02:38:57.309543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04443v1","created_at":"2026-07-05T02:38:57.309543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04443","created_at":"2026-07-05T02:38:57.309543+00:00"},{"alias_kind":"pith_short_12","alias_value":"PR335IM4KMON","created_at":"2026-07-05T02:38:57.309543+00:00"},{"alias_kind":"pith_short_16","alias_value":"PR335IM4KMONM3S6","created_at":"2026-07-05T02:38:57.309543+00:00"},{"alias_kind":"pith_short_8","alias_value":"PR335IM4","created_at":"2026-07-05T02:38:57.309543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15523","citing_title":"Enhancing Grammatical Error Detection using BERT with Cleaned Lang-8 Dataset","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX","json":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX.json","graph_json":"https://pith.science/api/pith-number/PR335IM4KMONM3S6X6KHJE7WJX/graph.json","events_json":"https://pith.science/api/pith-number/PR335IM4KMONM3S6X6KHJE7WJX/events.json","paper":"https://pith.science/paper/PR335IM4"},"agent_actions":{"view_html":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX","download_json":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX.json","view_paper":"https://pith.science/paper/PR335IM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04443&json=true","fetch_graph":"https://pith.science/api/pith-number/PR335IM4KMONM3S6X6KHJE7WJX/graph.json","fetch_events":"https://pith.science/api/pith-number/PR335IM4KMONM3S6X6KHJE7WJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX/action/storage_attestation","attest_author":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX/action/author_attestation","sign_citation":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX/action/citation_signature","submit_replication":"https://pith.science/pith/PR335IM4KMONM3S6X6KHJE7WJX/action/replication_record"}},"created_at":"2026-07-05T02:38:57.309543+00:00","updated_at":"2026-07-05T02:38:57.309543+00:00"}