{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LCMXITNSPJDTJFIKSNSF4RGBBN","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":"265235409df6c266281f46a093f86fa334fb7a6d48fa3acb945aaf534372e60f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T20:28:37Z","title_canon_sha256":"4492f27607cbd4f7380e5414435eaad9b9ab611b1680ab83273e6fcb153ba0e3"},"schema_version":"1.0","source":{"id":"2502.05312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05312","created_at":"2026-07-05T10:11:35Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05312v1","created_at":"2026-07-05T10:11:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05312","created_at":"2026-07-05T10:11:35Z"},{"alias_kind":"pith_short_12","alias_value":"LCMXITNSPJDT","created_at":"2026-07-05T10:11:35Z"},{"alias_kind":"pith_short_16","alias_value":"LCMXITNSPJDTJFIK","created_at":"2026-07-05T10:11:35Z"},{"alias_kind":"pith_short_8","alias_value":"LCMXITNS","created_at":"2026-07-05T10:11:35Z"}],"graph_snapshots":[{"event_id":"sha256:193a015ff47abe7fc8a25706bd643511b523a9ff5d2e4c20cff6c00dea8481b7","target":"graph","created_at":"2026-07-05T10:11:35Z","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/2502.05312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic data generation is widely recognized as a way to enhance the quality of neural grammatical error correction (GEC) systems. However, current approaches often lack diversity or are too simplistic to generate the wide range of grammatical errors made by humans, especially for low-resource languages such as Arabic. In this paper, we will develop the error tagging model and the synthetic data generation model to create a large synthetic dataset in Arabic for grammatical error correction. In the error tagging model, the correct sentence is categorized into multiple error types by using the","authors_text":"Ahlam Alrehili, Areej Alhothali","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T20:28:37Z","title":"Towards the Development of Balanced Synthetic Data for Correcting Grammatical Errors in Arabic: An Approach Based on Error Tagging Model and Synthetic Data Generating Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05312","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:e64de1aea2c5a6acbd60e92f131101385d002dfd09d7013ed433c45759eda1d2","target":"record","created_at":"2026-07-05T10:11:35Z","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":"265235409df6c266281f46a093f86fa334fb7a6d48fa3acb945aaf534372e60f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T20:28:37Z","title_canon_sha256":"4492f27607cbd4f7380e5414435eaad9b9ab611b1680ab83273e6fcb153ba0e3"},"schema_version":"1.0","source":{"id":"2502.05312","kind":"arxiv","version":1}},"canonical_sha256":"5899744db27a4734950a93645e44c10b4debe98e2cd6e02d15dc2b54d4d1d7df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5899744db27a4734950a93645e44c10b4debe98e2cd6e02d15dc2b54d4d1d7df","first_computed_at":"2026-07-05T10:11:35.827169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:35.827169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a5XMAuLXHBPtL5Vjw79UKeJ/4Gkja2A1rBaHPhTwG/1l4f1QzwKxViBFdTx+gnjpGwhd2xqfdIxi7RusC6PeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:35.827612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e64de1aea2c5a6acbd60e92f131101385d002dfd09d7013ed433c45759eda1d2","sha256:193a015ff47abe7fc8a25706bd643511b523a9ff5d2e4c20cff6c00dea8481b7"],"state_sha256":"75b9f228ff8f81fe0abf9147c37dd11405d5183a7369b04371efbd1f903ea7ac"}