{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ORFI2DG26TCUPCL6IEQHGRQUSM","short_pith_number":"pith:ORFI2DG2","schema_version":"1.0","canonical_sha256":"744a8d0cdaf4c547897e412073461493069418b563d3641c23e4966b1e63fce1","source":{"kind":"arxiv","id":"2507.18762","version":1},"attestation_state":"computed","paper":{"title":"The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdulhady Abas Abdullah, Amir H. Gandomi, Hadi Veisi, Laith Abualigah, Milena \\v{Z}ivkovi\\'c, Seyedali Mirjalili, Tarik A Rashid","submitted_at":"2025-07-24T19:28:33Z","abstract_excerpt":"In natural language processing, multilingual models like mBERT and XLM-RoBERTa promise broad coverage but often struggle with languages that share a script yet differ in orthographic norms and cultural context. This issue is especially notable in Arabic-script languages such as Kurdish Sorani, Arabic, Persian, and Urdu. We introduce the Arabic Script RoBERTa (AS-RoBERTa) family: four RoBERTa-based models, each pre-trained on a large corpus tailored to its specific language. By focusing pre-training on language-specific script features and statistics, our models capture patterns overlooked by g"},"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":"2507.18762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T19:28:33Z","cross_cats_sorted":[],"title_canon_sha256":"46b908a31d33ef45db3019147e67bf015f664a338c9ab2e824b096e18414e1a3","abstract_canon_sha256":"d85312f5a4251d843222fe7af9317302b03f2c4ea01e295860e21b5c5cafda58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:57.410044Z","signature_b64":"0gydiM3iCHtwijygtoQjnBJN6VxaTJSp7r7dIA9r0SvTmkaRUi/N9JGQQmAPSXn0GPSbn8MwnbCEdAw3R6g0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"744a8d0cdaf4c547897e412073461493069418b563d3641c23e4966b1e63fce1","last_reissued_at":"2026-07-05T11:42:57.409596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:57.409596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdulhady Abas Abdullah, Amir H. Gandomi, Hadi Veisi, Laith Abualigah, Milena \\v{Z}ivkovi\\'c, Seyedali Mirjalili, Tarik A Rashid","submitted_at":"2025-07-24T19:28:33Z","abstract_excerpt":"In natural language processing, multilingual models like mBERT and XLM-RoBERTa promise broad coverage but often struggle with languages that share a script yet differ in orthographic norms and cultural context. This issue is especially notable in Arabic-script languages such as Kurdish Sorani, Arabic, Persian, and Urdu. We introduce the Arabic Script RoBERTa (AS-RoBERTa) family: four RoBERTa-based models, each pre-trained on a large corpus tailored to its specific language. By focusing pre-training on language-specific script features and statistics, our models capture patterns overlooked by g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18762","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/2507.18762/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":"2507.18762","created_at":"2026-07-05T11:42:57.409654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18762v1","created_at":"2026-07-05T11:42:57.409654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18762","created_at":"2026-07-05T11:42:57.409654+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORFI2DG26TCU","created_at":"2026-07-05T11:42:57.409654+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORFI2DG26TCUPCL6","created_at":"2026-07-05T11:42:57.409654+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORFI2DG2","created_at":"2026-07-05T11:42:57.409654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM","json":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM.json","graph_json":"https://pith.science/api/pith-number/ORFI2DG26TCUPCL6IEQHGRQUSM/graph.json","events_json":"https://pith.science/api/pith-number/ORFI2DG26TCUPCL6IEQHGRQUSM/events.json","paper":"https://pith.science/paper/ORFI2DG2"},"agent_actions":{"view_html":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM","download_json":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM.json","view_paper":"https://pith.science/paper/ORFI2DG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18762&json=true","fetch_graph":"https://pith.science/api/pith-number/ORFI2DG26TCUPCL6IEQHGRQUSM/graph.json","fetch_events":"https://pith.science/api/pith-number/ORFI2DG26TCUPCL6IEQHGRQUSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM/action/storage_attestation","attest_author":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM/action/author_attestation","sign_citation":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM/action/citation_signature","submit_replication":"https://pith.science/pith/ORFI2DG26TCUPCL6IEQHGRQUSM/action/replication_record"}},"created_at":"2026-07-05T11:42:57.409654+00:00","updated_at":"2026-07-05T11:42:57.409654+00:00"}