{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4BS74JXM7EZLRPNWVWEAIAEIDM","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":"ef93f00f2e81d305ab73138b6c7ccb81c66fc5f417816f2ea78e9f30e6277d38","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T10:42:36Z","title_canon_sha256":"e9515767217b7b506f5bfb7b848046ee40294bf7ffeed4e77b1932ec5790dcb2"},"schema_version":"1.0","source":{"id":"2606.23144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23144","created_at":"2026-06-23T03:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23144v1","created_at":"2026-06-23T03:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23144","created_at":"2026-06-23T03:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"4BS74JXM7EZL","created_at":"2026-06-23T03:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"4BS74JXM7EZLRPNW","created_at":"2026-06-23T03:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"4BS74JXM","created_at":"2026-06-23T03:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:af307e4cb559abf53a6bea2a626c808438cd22b9aaa39d550f1c581277812b3c","target":"graph","created_at":"2026-06-23T03:14:11Z","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/2606.23144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Faizan Iqbal, Haq Nawaz Malik, Nahfid Nissar","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T10:42:36Z","title":"Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23144","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":"sha256:043c06baf2b35938d8ad216d1c5feba675fbbaaf7629ecfc8b9ec1a8a7d92374","target":"record","created_at":"2026-06-23T03:14:11Z","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":"ef93f00f2e81d305ab73138b6c7ccb81c66fc5f417816f2ea78e9f30e6277d38","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T10:42:36Z","title_canon_sha256":"e9515767217b7b506f5bfb7b848046ee40294bf7ffeed4e77b1932ec5790dcb2"},"schema_version":"1.0","source":{"id":"2606.23144","kind":"arxiv","version":1}},"canonical_sha256":"e065fe26ecf932b8bdb6ad880400881b3e5861728b559250d2dd4e38e663436c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e065fe26ecf932b8bdb6ad880400881b3e5861728b559250d2dd4e38e663436c","first_computed_at":"2026-06-23T03:14:11.165688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:11.165688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B6GF4TIp5dHtnVbzb6efHrcGJh8+tPbnYSZ3vq/GdVwWSnZHDoMd7fxgW/gh+a337Z4FDO7rEG254CJPkih/AQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:11.166102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:043c06baf2b35938d8ad216d1c5feba675fbbaaf7629ecfc8b9ec1a8a7d92374","sha256:af307e4cb559abf53a6bea2a626c808438cd22b9aaa39d550f1c581277812b3c"],"state_sha256":"d3adbfb920545d0f421c5196b18b57fa6aa9869ebf709555cacd7b2293dfd30a"}