{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VW75VS3ILZZ5TONJPBQKAOMEL","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":"2bfd886050926b46ae1515a78ca53ad8f9a132420ae32d0ec3cc0db3ebb6818e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-14T16:06:32Z","title_canon_sha256":"98a023a4b3ee1787642f129dad1003ef4ea394dfd5de3b588c66ee33e65def5b"},"schema_version":"1.0","source":{"id":"2606.15883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.15883","created_at":"2026-06-19T16:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.15883v2","created_at":"2026-06-19T16:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.15883","created_at":"2026-06-19T16:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"3VW75VS3ILZZ","created_at":"2026-06-19T16:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"3VW75VS3ILZZ5TON","created_at":"2026-06-19T16:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"3VW75VS3","created_at":"2026-06-19T16:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:bdfcf7bc8e103095e1bab3a4ca055cee0dd1708299a91e7445e202c40e253012","target":"graph","created_at":"2026-06-19T16:10:01Z","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/2606.15883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Kashmiri, an Indo-Aryan language written in a modified Perso-Arabic script, frequently omits diacritic marks in digital text, creating ambiguity and challenging downstream NLP applications. We present Koshur Diacritizer, a ByT5-small byte-level sequence-to-sequence model for restoring diacritics in Kashmiri text. To support this task, we release a publicly available dataset of 23.7k aligned undiacritized diacritized Kashmiri sentence pairs. The proposed framework combines script-aware normalization, alignment validation, and skeleton-preserving inference to ensure reliable restoration while ma","authors_text":"Faizan Iqbal, Haq Nawaz Malik, Nahfid Nissar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-14T16:06:32Z","title":"Koshur Diacritizer: A Byte-Level Sequence-to-Sequence Model for Kashmiri Diacritic Restoration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.15883","kind":"arxiv","version":2},"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:ef33103897872a6597313b08d7a8f7d27f6318d4ea0a0f33aac6d9a60dcd9bb7","target":"record","created_at":"2026-06-19T16:10:01Z","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":"2bfd886050926b46ae1515a78ca53ad8f9a132420ae32d0ec3cc0db3ebb6818e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-14T16:06:32Z","title_canon_sha256":"98a023a4b3ee1787642f129dad1003ef4ea394dfd5de3b588c66ee33e65def5b"},"schema_version":"1.0","source":{"id":"2606.15883","kind":"arxiv","version":2}},"canonical_sha256":"dd6dfed65b42f39ecdcd4bc30501cc22e7e8110427210a711b60cb5a54ab7dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd6dfed65b42f39ecdcd4bc30501cc22e7e8110427210a711b60cb5a54ab7dc0","first_computed_at":"2026-06-19T16:10:01.528336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:01.528336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TuobEvN23J3WLyDGTu9uAspdb1q3r2yOb5HTFXetBynMhm62MeFuQ6xuDWNb0FJt9IBHWAGT1hVZGNOyAvXLCA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:01.528769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.15883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef33103897872a6597313b08d7a8f7d27f6318d4ea0a0f33aac6d9a60dcd9bb7","sha256:bdfcf7bc8e103095e1bab3a4ca055cee0dd1708299a91e7445e202c40e253012"],"state_sha256":"77f8259556cccdb917099a1a939117cbbbec2000a41a79b873f22c050b7917bd"}