{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K3HN47DEUP6UFC4BX6KTUQFCXF","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":"70f2f316b11f4bd28e2e21d56a0d05b101ac57114e10a5fd8acfc374f39beb8c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T21:17:32Z","title_canon_sha256":"18fb6bb45745c0aab93201cd72db3e289f26bcc6431cb7333a56c974fa2d1c24"},"schema_version":"1.0","source":{"id":"2509.09014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09014","created_at":"2026-07-05T12:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09014v1","created_at":"2026-07-05T12:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09014","created_at":"2026-07-05T12:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"K3HN47DEUP6U","created_at":"2026-07-05T12:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"K3HN47DEUP6UFC4B","created_at":"2026-07-05T12:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"K3HN47DE","created_at":"2026-07-05T12:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:583e47c15ff7c0091fbe24ccd9396c781f259cc150486a31e4931ed9a6349364","target":"graph","created_at":"2026-07-05T12:09:27Z","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/2509.09014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Umair Hassan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T21:17:32Z","title":"COCO-Urdu: A Large-Scale Urdu Image-Caption Dataset with Multimodal Quality Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09014","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:eaa668afe0565cfb2030f7ca9f740867e41465f885961fd757a4241c24158a60","target":"record","created_at":"2026-07-05T12:09:27Z","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":"70f2f316b11f4bd28e2e21d56a0d05b101ac57114e10a5fd8acfc374f39beb8c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T21:17:32Z","title_canon_sha256":"18fb6bb45745c0aab93201cd72db3e289f26bcc6431cb7333a56c974fa2d1c24"},"schema_version":"1.0","source":{"id":"2509.09014","kind":"arxiv","version":1}},"canonical_sha256":"56cede7c64a3fd428b81bf953a40a2b946dbed41b21902274eacc6b4c445d48a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56cede7c64a3fd428b81bf953a40a2b946dbed41b21902274eacc6b4c445d48a","first_computed_at":"2026-07-05T12:09:27.628691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:27.628691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4sKkSNhgJMa+eRP8MhR1a2Qm7Ginat6dXU787P7vJfJ4vJqn1M1XVnKFs7Kn3tBqZjPYKjZwHyemIs3e9s8GCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:27.629232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaa668afe0565cfb2030f7ca9f740867e41465f885961fd757a4241c24158a60","sha256:583e47c15ff7c0091fbe24ccd9396c781f259cc150486a31e4931ed9a6349364"],"state_sha256":"d1a52a97c647409c607068bb4fd46209e6e83fb051f359a40454ba5d7f1fa2da"}