{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ORFI2DG26TCUPCL6IEQHGRQUSM","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":"d85312f5a4251d843222fe7af9317302b03f2c4ea01e295860e21b5c5cafda58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T19:28:33Z","title_canon_sha256":"46b908a31d33ef45db3019147e67bf015f664a338c9ab2e824b096e18414e1a3"},"schema_version":"1.0","source":{"id":"2507.18762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18762","created_at":"2026-07-05T11:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18762v1","created_at":"2026-07-05T11:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18762","created_at":"2026-07-05T11:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"ORFI2DG26TCU","created_at":"2026-07-05T11:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"ORFI2DG26TCUPCL6","created_at":"2026-07-05T11:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"ORFI2DG2","created_at":"2026-07-05T11:42:57Z"}],"graph_snapshots":[{"event_id":"sha256:2a41177b1ca3326de273aa05d30b2da306897fb0489ccf1114135fc1fe6c13e9","target":"graph","created_at":"2026-07-05T11:42:57Z","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/2507.18762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdulhady Abas Abdullah, Amir H. Gandomi, Hadi Veisi, Laith Abualigah, Milena \\v{Z}ivkovi\\'c, Seyedali Mirjalili, Tarik A Rashid","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T19:28:33Z","title":"The Role of Orthographic Consistency in Multilingual Embedding Models for Text Classification in Arabic-Script Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18762","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":"sha256:205ccad5c0b28e5a69b6c9c8b94762e12e9a01153aec95ada1d437c861acc9a2","target":"record","created_at":"2026-07-05T11:42:57Z","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":"d85312f5a4251d843222fe7af9317302b03f2c4ea01e295860e21b5c5cafda58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T19:28:33Z","title_canon_sha256":"46b908a31d33ef45db3019147e67bf015f664a338c9ab2e824b096e18414e1a3"},"schema_version":"1.0","source":{"id":"2507.18762","kind":"arxiv","version":1}},"canonical_sha256":"744a8d0cdaf4c547897e412073461493069418b563d3641c23e4966b1e63fce1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"744a8d0cdaf4c547897e412073461493069418b563d3641c23e4966b1e63fce1","first_computed_at":"2026-07-05T11:42:57.409596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:57.409596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0gydiM3iCHtwijygtoQjnBJN6VxaTJSp7r7dIA9r0SvTmkaRUi/N9JGQQmAPSXn0GPSbn8MwnbCEdAw3R6g0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:57.410044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:205ccad5c0b28e5a69b6c9c8b94762e12e9a01153aec95ada1d437c861acc9a2","sha256:2a41177b1ca3326de273aa05d30b2da306897fb0489ccf1114135fc1fe6c13e9"],"state_sha256":"f2dab754002334693bd3e0cd97d0d45eb8f2de111fc51e1d41af4c73b27a9f8f"}