{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KOYCU3BPSZEE2HY5T43ILXI5DD","short_pith_number":"pith:KOYCU3BP","schema_version":"1.0","canonical_sha256":"53b02a6c2f96484d1f1d9f3685dd1d18e8d7f1ef73ea2bc809adc6d6de8256f8","source":{"kind":"arxiv","id":"2502.14949","version":2},"attestation_state":"computed","paper":{"title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abdullah Sohail, Ahmed Heakl, Fahad Khan, Ghazi Shazan Ahmad, Mohamed El-Geish, Mukul Ranjan, Omar Maher, Rania Hossam, Salman Khan, Zhiqiang Shen","submitted_at":"2025-02-20T18:41:23Z","abstract_excerpt":"With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples acr"},"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":"2502.14949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:41:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"title_canon_sha256":"6ccafab28c85188b40cd58c73f2df9434eafe9ea3f361856c11c1489bff0b12a","abstract_canon_sha256":"5e75931040ccef27733763a958edfb4a71134422fa732211173c1c6922a7f66a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:14.491138Z","signature_b64":"DmAW5Z3UfiF6fiCM1wip6Hi4m1DH+RpJcB6jSzvaezERvLdNbRSNxQONCKhcaqLh6hfi5CLMAYODCVzqmtZTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53b02a6c2f96484d1f1d9f3685dd1d18e8d7f1ef73ea2bc809adc6d6de8256f8","last_reissued_at":"2026-07-05T11:28:14.490655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:14.490655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abdullah Sohail, Ahmed Heakl, Fahad Khan, Ghazi Shazan Ahmad, Mohamed El-Geish, Mukul Ranjan, Omar Maher, Rania Hossam, Salman Khan, Zhiqiang Shen","submitted_at":"2025-02-20T18:41:23Z","abstract_excerpt":"With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14949","kind":"arxiv","version":2},"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/2502.14949/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":"2502.14949","created_at":"2026-07-05T11:28:14.490712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14949v2","created_at":"2026-07-05T11:28:14.490712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14949","created_at":"2026-07-05T11:28:14.490712+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOYCU3BPSZEE","created_at":"2026-07-05T11:28:14.490712+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOYCU3BPSZEE2HY5","created_at":"2026-07-05T11:28:14.490712+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOYCU3BP","created_at":"2026-07-05T11:28:14.490712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD","json":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD.json","graph_json":"https://pith.science/api/pith-number/KOYCU3BPSZEE2HY5T43ILXI5DD/graph.json","events_json":"https://pith.science/api/pith-number/KOYCU3BPSZEE2HY5T43ILXI5DD/events.json","paper":"https://pith.science/paper/KOYCU3BP"},"agent_actions":{"view_html":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD","download_json":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD.json","view_paper":"https://pith.science/paper/KOYCU3BP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14949&json=true","fetch_graph":"https://pith.science/api/pith-number/KOYCU3BPSZEE2HY5T43ILXI5DD/graph.json","fetch_events":"https://pith.science/api/pith-number/KOYCU3BPSZEE2HY5T43ILXI5DD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD/action/storage_attestation","attest_author":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD/action/author_attestation","sign_citation":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD/action/citation_signature","submit_replication":"https://pith.science/pith/KOYCU3BPSZEE2HY5T43ILXI5DD/action/replication_record"}},"created_at":"2026-07-05T11:28:14.490712+00:00","updated_at":"2026-07-05T11:28:14.490712+00:00"}