{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4BS74JXM7EZLRPNWVWEAIAEIDM","short_pith_number":"pith:4BS74JXM","schema_version":"1.0","canonical_sha256":"e065fe26ecf932b8bdb6ad880400881b3e5861728b559250d2dd4e38e663436c","source":{"kind":"arxiv","id":"2606.23144","version":1},"attestation_state":"computed","paper":{"title":"Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Faizan Iqbal, Haq Nawaz Malik, Nahfid Nissar","submitted_at":"2026-06-22T10:42:36Z","abstract_excerpt":"Optical Character Recognition (OCR) for low-resource languages is often constrained by the lack of annotated training data and the complexity of script-specific rendering. Kashmiri, written primarily in the Perso-Arabic Nastaliq script, presents additional challenges due to contextual glyph shaping, dense ligatures, and orthographic variability. We introduce Koshur Pixel, the first large-scale synthetic OCR dataset for Kashmiri, comprising 613,078 image-text pairs generated from the KS-PRET-5M corpus using the SynthOCR-Gen framework. The dataset spans multiple fonts and textual granularities, "},"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":"2606.23144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T10:42:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e9515767217b7b506f5bfb7b848046ee40294bf7ffeed4e77b1932ec5790dcb2","abstract_canon_sha256":"ef93f00f2e81d305ab73138b6c7ccb81c66fc5f417816f2ea78e9f30e6277d38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:11.166102Z","signature_b64":"B6GF4TIp5dHtnVbzb6efHrcGJh8+tPbnYSZ3vq/GdVwWSnZHDoMd7fxgW/gh+a337Z4FDO7rEG254CJPkih/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e065fe26ecf932b8bdb6ad880400881b3e5861728b559250d2dd4e38e663436c","last_reissued_at":"2026-06-23T03:14:11.165688Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:11.165688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Faizan Iqbal, Haq Nawaz Malik, Nahfid Nissar","submitted_at":"2026-06-22T10:42:36Z","abstract_excerpt":"Optical Character Recognition (OCR) for low-resource languages is often constrained by the lack of annotated training data and the complexity of script-specific rendering. Kashmiri, written primarily in the Perso-Arabic Nastaliq script, presents additional challenges due to contextual glyph shaping, dense ligatures, and orthographic variability. We introduce Koshur Pixel, the first large-scale synthetic OCR dataset for Kashmiri, comprising 613,078 image-text pairs generated from the KS-PRET-5M corpus using the SynthOCR-Gen framework. The dataset spans multiple fonts and textual granularities, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23144","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/2606.23144/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":"2606.23144","created_at":"2026-06-23T03:14:11.165752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23144v1","created_at":"2026-06-23T03:14:11.165752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23144","created_at":"2026-06-23T03:14:11.165752+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BS74JXM7EZL","created_at":"2026-06-23T03:14:11.165752+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BS74JXM7EZLRPNW","created_at":"2026-06-23T03:14:11.165752+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BS74JXM","created_at":"2026-06-23T03:14:11.165752+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/4BS74JXM7EZLRPNWVWEAIAEIDM","json":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM.json","graph_json":"https://pith.science/api/pith-number/4BS74JXM7EZLRPNWVWEAIAEIDM/graph.json","events_json":"https://pith.science/api/pith-number/4BS74JXM7EZLRPNWVWEAIAEIDM/events.json","paper":"https://pith.science/paper/4BS74JXM"},"agent_actions":{"view_html":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM","download_json":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM.json","view_paper":"https://pith.science/paper/4BS74JXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23144&json=true","fetch_graph":"https://pith.science/api/pith-number/4BS74JXM7EZLRPNWVWEAIAEIDM/graph.json","fetch_events":"https://pith.science/api/pith-number/4BS74JXM7EZLRPNWVWEAIAEIDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM/action/storage_attestation","attest_author":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM/action/author_attestation","sign_citation":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM/action/citation_signature","submit_replication":"https://pith.science/pith/4BS74JXM7EZLRPNWVWEAIAEIDM/action/replication_record"}},"created_at":"2026-06-23T03:14:11.165752+00:00","updated_at":"2026-06-23T03:14:11.165752+00:00"}