{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K3HN47DEUP6UFC4BX6KTUQFCXF","short_pith_number":"pith:K3HN47DE","schema_version":"1.0","canonical_sha256":"56cede7c64a3fd428b81bf953a40a2b946dbed41b21902274eacc6b4c445d48a","source":{"kind":"arxiv","id":"2509.09014","version":1},"attestation_state":"computed","paper":{"title":"COCO-Urdu: A Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Umair Hassan","submitted_at":"2025-09-10T21:17:32Z","abstract_excerpt":"Urdu, spoken by over 250 million people, remains critically under-served in multimodal and vision-language research. The absence of large-scale, high-quality datasets has limited the development of Urdu-capable systems and reinforced biases in multilingual vision-language models trained primarily on high-resource languages. To address this gap, we present COCO-Urdu, a large-scale image-caption dataset derived from MS COCO, containing 59,000 images and 319,000 Urdu captions selected through stratified sampling to preserve the original distribution. Captions were translated using SeamlessM4T v2 "},"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":"2509.09014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T21:17:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"18fb6bb45745c0aab93201cd72db3e289f26bcc6431cb7333a56c974fa2d1c24","abstract_canon_sha256":"70f2f316b11f4bd28e2e21d56a0d05b101ac57114e10a5fd8acfc374f39beb8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:27.629232Z","signature_b64":"4sKkSNhgJMa+eRP8MhR1a2Qm7Ginat6dXU787P7vJfJ4vJqn1M1XVnKFs7Kn3tBqZjPYKjZwHyemIs3e9s8GCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56cede7c64a3fd428b81bf953a40a2b946dbed41b21902274eacc6b4c445d48a","last_reissued_at":"2026-07-05T12:09:27.628691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:27.628691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COCO-Urdu: A Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Umair Hassan","submitted_at":"2025-09-10T21:17:32Z","abstract_excerpt":"Urdu, spoken by over 250 million people, remains critically under-served in multimodal and vision-language research. The absence of large-scale, high-quality datasets has limited the development of Urdu-capable systems and reinforced biases in multilingual vision-language models trained primarily on high-resource languages. To address this gap, we present COCO-Urdu, a large-scale image-caption dataset derived from MS COCO, containing 59,000 images and 319,000 Urdu captions selected through stratified sampling to preserve the original distribution. Captions were translated using SeamlessM4T v2 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09014","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/2509.09014/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":"2509.09014","created_at":"2026-07-05T12:09:27.628761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09014v1","created_at":"2026-07-05T12:09:27.628761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09014","created_at":"2026-07-05T12:09:27.628761+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3HN47DEUP6U","created_at":"2026-07-05T12:09:27.628761+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3HN47DEUP6UFC4B","created_at":"2026-07-05T12:09:27.628761+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3HN47DE","created_at":"2026-07-05T12:09:27.628761+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/K3HN47DEUP6UFC4BX6KTUQFCXF","json":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF.json","graph_json":"https://pith.science/api/pith-number/K3HN47DEUP6UFC4BX6KTUQFCXF/graph.json","events_json":"https://pith.science/api/pith-number/K3HN47DEUP6UFC4BX6KTUQFCXF/events.json","paper":"https://pith.science/paper/K3HN47DE"},"agent_actions":{"view_html":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF","download_json":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF.json","view_paper":"https://pith.science/paper/K3HN47DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09014&json=true","fetch_graph":"https://pith.science/api/pith-number/K3HN47DEUP6UFC4BX6KTUQFCXF/graph.json","fetch_events":"https://pith.science/api/pith-number/K3HN47DEUP6UFC4BX6KTUQFCXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF/action/storage_attestation","attest_author":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF/action/author_attestation","sign_citation":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF/action/citation_signature","submit_replication":"https://pith.science/pith/K3HN47DEUP6UFC4BX6KTUQFCXF/action/replication_record"}},"created_at":"2026-07-05T12:09:27.628761+00:00","updated_at":"2026-07-05T12:09:27.628761+00:00"}