{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AMFRZWINRDLFHZO5MIRWATKMR3","short_pith_number":"pith:AMFRZWIN","schema_version":"1.0","canonical_sha256":"030b1cd90d88d653e5dd6223604d4c8ee5c9786dffa4d6f5cc49933dc984a86c","source":{"kind":"arxiv","id":"2505.24600","version":1},"attestation_state":"computed","paper":{"title":"SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adel Ammar, Omer Nacar, Serry Sibaee, Wadii Boulila, Yasser Al-Habashi","submitted_at":"2025-05-30T13:47:54Z","abstract_excerpt":"Arabic Optical Character Recognition (OCR) is essential for converting vast amounts of Arabic print media into digital formats. However, training modern OCR models, especially powerful vision-language models, is hampered by the lack of large, diverse, and well-structured datasets that mimic real-world book layouts. Existing Arabic OCR datasets often focus on isolated words or lines or are limited in scale, typographic variety, or structural complexity found in books. To address this significant gap, we introduce SARD (Large-Scale Synthetic Arabic OCR Dataset). SARD is a massive, synthetically "},"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":"2505.24600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T13:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"9ac6ba8bf1f0a9bc7bb67ff82e14fe97961e01f2e44d775eb911753b2cba2b2e","abstract_canon_sha256":"34451f75147252205f5f731c58a5401e65923e08f13eb2217f4a85879e4324dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:53.015803Z","signature_b64":"CKpmqGpSqyJNC4vCCg2J6ekY7RhlFW1SSm8VjmY/+L7XujKNjtW8XKkdrR2lS09+eFNqv0gBPkhjm3TTiu+mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"030b1cd90d88d653e5dd6223604d4c8ee5c9786dffa4d6f5cc49933dc984a86c","last_reissued_at":"2026-07-05T11:12:53.015029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:53.015029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adel Ammar, Omer Nacar, Serry Sibaee, Wadii Boulila, Yasser Al-Habashi","submitted_at":"2025-05-30T13:47:54Z","abstract_excerpt":"Arabic Optical Character Recognition (OCR) is essential for converting vast amounts of Arabic print media into digital formats. However, training modern OCR models, especially powerful vision-language models, is hampered by the lack of large, diverse, and well-structured datasets that mimic real-world book layouts. Existing Arabic OCR datasets often focus on isolated words or lines or are limited in scale, typographic variety, or structural complexity found in books. To address this significant gap, we introduce SARD (Large-Scale Synthetic Arabic OCR Dataset). SARD is a massive, synthetically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24600","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/2505.24600/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":"2505.24600","created_at":"2026-07-05T11:12:53.015137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24600v1","created_at":"2026-07-05T11:12:53.015137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24600","created_at":"2026-07-05T11:12:53.015137+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMFRZWINRDLF","created_at":"2026-07-05T11:12:53.015137+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMFRZWINRDLFHZO5","created_at":"2026-07-05T11:12:53.015137+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMFRZWIN","created_at":"2026-07-05T11:12:53.015137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02864","citing_title":"A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3","json":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3.json","graph_json":"https://pith.science/api/pith-number/AMFRZWINRDLFHZO5MIRWATKMR3/graph.json","events_json":"https://pith.science/api/pith-number/AMFRZWINRDLFHZO5MIRWATKMR3/events.json","paper":"https://pith.science/paper/AMFRZWIN"},"agent_actions":{"view_html":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3","download_json":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3.json","view_paper":"https://pith.science/paper/AMFRZWIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24600&json=true","fetch_graph":"https://pith.science/api/pith-number/AMFRZWINRDLFHZO5MIRWATKMR3/graph.json","fetch_events":"https://pith.science/api/pith-number/AMFRZWINRDLFHZO5MIRWATKMR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3/action/storage_attestation","attest_author":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3/action/author_attestation","sign_citation":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3/action/citation_signature","submit_replication":"https://pith.science/pith/AMFRZWINRDLFHZO5MIRWATKMR3/action/replication_record"}},"created_at":"2026-07-05T11:12:53.015137+00:00","updated_at":"2026-07-05T11:12:53.015137+00:00"}