{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F7FPRQIY6G7FXOPBIRHVU5UGKC","short_pith_number":"pith:F7FPRQIY","schema_version":"1.0","canonical_sha256":"2fcaf8c118f1be5bb9e1444f5a768650bf120e4c0bf7c95ad313ad268be30d0e","source":{"kind":"arxiv","id":"2310.11671","version":1},"attestation_state":"computed","paper":{"title":"MixEdit: Revisiting Data Augmentation and Beyond 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, Yangning Li, Yinghui Li","submitted_at":"2023-10-18T02:45:51Z","abstract_excerpt":"Data Augmentation through generating pseudo data has been proven effective in mitigating the challenge of data scarcity in the field of Grammatical Error Correction (GEC). Various augmentation strategies have been widely explored, most of which are motivated by two heuristics, i.e., increasing the distribution similarity and diversity of pseudo data. However, the underlying mechanism responsible for the effectiveness of these strategies remains poorly understood. In this paper, we aim to clarify how data augmentation improves GEC models. To this end, we introduce two interpretable and computat"},"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":"2310.11671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T02:45:51Z","cross_cats_sorted":[],"title_canon_sha256":"4d75162b86fdc80791d79adcc8932c0455058a4d0c388df0ec6c7d1d36a03349","abstract_canon_sha256":"a350ae34c4c02dd6ef35dd6320c29f09c3d76b8a8af48d5e976d07960f3dbfe6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:10.843104Z","signature_b64":"tm4embjZOpzL3yxoTs4W8nX+gXE2gq1w/DghhzD25bI+0wh+enS33Ft2md1ndVB7v0Jah41Kgw2OzUk5wPM8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fcaf8c118f1be5bb9e1444f5a768650bf120e4c0bf7c95ad313ad268be30d0e","last_reissued_at":"2026-07-05T07:02:10.842649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:10.842649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixEdit: Revisiting Data Augmentation and Beyond 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, Yangning Li, Yinghui Li","submitted_at":"2023-10-18T02:45:51Z","abstract_excerpt":"Data Augmentation through generating pseudo data has been proven effective in mitigating the challenge of data scarcity in the field of Grammatical Error Correction (GEC). Various augmentation strategies have been widely explored, most of which are motivated by two heuristics, i.e., increasing the distribution similarity and diversity of pseudo data. However, the underlying mechanism responsible for the effectiveness of these strategies remains poorly understood. In this paper, we aim to clarify how data augmentation improves GEC models. To this end, we introduce two interpretable and computat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11671","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/2310.11671/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":"2310.11671","created_at":"2026-07-05T07:02:10.842716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11671v1","created_at":"2026-07-05T07:02:10.842716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11671","created_at":"2026-07-05T07:02:10.842716+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7FPRQIY6G7F","created_at":"2026-07-05T07:02:10.842716+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7FPRQIY6G7FXOPB","created_at":"2026-07-05T07:02:10.842716+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7FPRQIY","created_at":"2026-07-05T07:02:10.842716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04507","citing_title":"Detecting Spelling and Grammatical Anomalies in Russian Poetry Texts","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC","json":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC.json","graph_json":"https://pith.science/api/pith-number/F7FPRQIY6G7FXOPBIRHVU5UGKC/graph.json","events_json":"https://pith.science/api/pith-number/F7FPRQIY6G7FXOPBIRHVU5UGKC/events.json","paper":"https://pith.science/paper/F7FPRQIY"},"agent_actions":{"view_html":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC","download_json":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC.json","view_paper":"https://pith.science/paper/F7FPRQIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11671&json=true","fetch_graph":"https://pith.science/api/pith-number/F7FPRQIY6G7FXOPBIRHVU5UGKC/graph.json","fetch_events":"https://pith.science/api/pith-number/F7FPRQIY6G7FXOPBIRHVU5UGKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC/action/storage_attestation","attest_author":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC/action/author_attestation","sign_citation":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC/action/citation_signature","submit_replication":"https://pith.science/pith/F7FPRQIY6G7FXOPBIRHVU5UGKC/action/replication_record"}},"created_at":"2026-07-05T07:02:10.842716+00:00","updated_at":"2026-07-05T07:02:10.842716+00:00"}