{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LP3JHS4FHL6AJ4BCQN6XO2IO7O","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":"874d263a19a409d1f1f91db04e3df6f8b69f130cb2b49bedbe99abccd9a4749b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T10:49:56Z","title_canon_sha256":"369dd9490b53e849b5aeae1b4449b22595c5510c0882cb75fde4e3c6ca6ac2b0"},"schema_version":"1.0","source":{"id":"2406.17456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17456","created_at":"2026-07-05T08:36:35Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17456v1","created_at":"2026-07-05T08:36:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17456","created_at":"2026-07-05T08:36:35Z"},{"alias_kind":"pith_short_12","alias_value":"LP3JHS4FHL6A","created_at":"2026-07-05T08:36:35Z"},{"alias_kind":"pith_short_16","alias_value":"LP3JHS4FHL6AJ4BC","created_at":"2026-07-05T08:36:35Z"},{"alias_kind":"pith_short_8","alias_value":"LP3JHS4F","created_at":"2026-07-05T08:36:35Z"}],"graph_snapshots":[{"event_id":"sha256:7e26df1f88e85ee41a8c06d603e55de34d48b1cc372dc152021b84c15b6c7eec","target":"graph","created_at":"2026-07-05T08:36:35Z","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/2406.17456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nowadays, data augmentation through synthetic data has been widely used in the field of Grammatical Error Correction (GEC) to alleviate the problem of data scarcity. However, these synthetic data are mainly used in the pre-training phase rather than the data-limited fine-tuning phase due to inconsistent error distribution and noisy labels. In this paper, we propose a synthetic data construction method based on contextual augmentation, which can ensure an efficient augmentation of the original data with a more consistent error distribution. Specifically, we combine rule-based substitution with ","authors_text":"Baoxin Wang, Dayong Wu, Qingfu Zhu, Wanxiang Che, Yijun Liu, Yixuan Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T10:49:56Z","title":"Improving Grammatical Error Correction via Contextual Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17456","kind":"arxiv","version":1},"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":"sha256:37eb40ee36fc79a9cbd221c50448e5c650bcd450b1d83594a82ebaca12c9da02","target":"record","created_at":"2026-07-05T08:36:35Z","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":"874d263a19a409d1f1f91db04e3df6f8b69f130cb2b49bedbe99abccd9a4749b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T10:49:56Z","title_canon_sha256":"369dd9490b53e849b5aeae1b4449b22595c5510c0882cb75fde4e3c6ca6ac2b0"},"schema_version":"1.0","source":{"id":"2406.17456","kind":"arxiv","version":1}},"canonical_sha256":"5bf693cb853afc04f022837d77690efb9ceca9dc40e7ee896625203f425defe1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bf693cb853afc04f022837d77690efb9ceca9dc40e7ee896625203f425defe1","first_computed_at":"2026-07-05T08:36:35.220006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:35.220006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dknJpt9/SMQiG8lG5sEguJOQxdNjSZ4LXXEm3F2eJLiK8VbDBjrNUK8LALZIMeeK/I1OfL1aT+EvRupj7LT/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:35.220496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37eb40ee36fc79a9cbd221c50448e5c650bcd450b1d83594a82ebaca12c9da02","sha256:7e26df1f88e85ee41a8c06d603e55de34d48b1cc372dc152021b84c15b6c7eec"],"state_sha256":"d651cee8eba5e3abc862c93731693f8cacc8f7727eb85c74f45968cb10d04143"}