{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JQS5FKPLQULYFIFXA676XO3E2D","short_pith_number":"pith:JQS5FKPL","schema_version":"1.0","canonical_sha256":"4c25d2a9eb851782a0b707bfebbb64d0e8cd00809bd12d71a3df14a518a43cdd","source":{"kind":"arxiv","id":"2606.29378","version":1},"attestation_state":"computed","paper":{"title":"Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avisha Dilhara, Nevidu Jayatilleke","submitted_at":"2026-06-28T13:01:54Z","abstract_excerpt":"Sinhala is a morphologically rich abugida spoken by roughly 16 million people in Sri Lanka, and to date, there are no publicly available real-world datasets for page-level Sinhala OCR. All previous studies for assessing Sinhala OCR models have used artificially generated data. To bridge the gap, we introduce sinhala-ocr-lk-acts-1010, an annotated dataset of 1,010 page-level images and their transcriptions collected from Sri Lankan Legislative Acts published between 1981-1989 and 2000-2019, split into 707 training examples, 101 validation examples, and 202 testing examples. Three models based o"},"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":"2606.29378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T13:01:54Z","cross_cats_sorted":[],"title_canon_sha256":"59011cbf375784b0386b1cf2a2798905e988187552a81f895513205cd9993acc","abstract_canon_sha256":"4e12eed62f31203fd1ceb60c3749d2493cce95bd22db804f716433b2c9e59e8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:03.519698Z","signature_b64":"gsYVCnbv0obT4iSnLTa7rpOa2ALDkf7LqB7wHBpmKUXZt2rjrSjFv7u7dlLVgc20QQzTfzaQ48SfxkzY318GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c25d2a9eb851782a0b707bfebbb64d0e8cd00809bd12d71a3df14a518a43cdd","last_reissued_at":"2026-06-30T01:18:03.519191Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:03.519191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avisha Dilhara, Nevidu Jayatilleke","submitted_at":"2026-06-28T13:01:54Z","abstract_excerpt":"Sinhala is a morphologically rich abugida spoken by roughly 16 million people in Sri Lanka, and to date, there are no publicly available real-world datasets for page-level Sinhala OCR. All previous studies for assessing Sinhala OCR models have used artificially generated data. To bridge the gap, we introduce sinhala-ocr-lk-acts-1010, an annotated dataset of 1,010 page-level images and their transcriptions collected from Sri Lankan Legislative Acts published between 1981-1989 and 2000-2019, split into 707 training examples, 101 validation examples, and 202 testing examples. Three models based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29378","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/2606.29378/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":"2606.29378","created_at":"2026-06-30T01:18:03.519248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29378v1","created_at":"2026-06-30T01:18:03.519248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29378","created_at":"2026-06-30T01:18:03.519248+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQS5FKPLQULY","created_at":"2026-06-30T01:18:03.519248+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQS5FKPLQULYFIFX","created_at":"2026-06-30T01:18:03.519248+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQS5FKPL","created_at":"2026-06-30T01:18:03.519248+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/JQS5FKPLQULYFIFXA676XO3E2D","json":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D.json","graph_json":"https://pith.science/api/pith-number/JQS5FKPLQULYFIFXA676XO3E2D/graph.json","events_json":"https://pith.science/api/pith-number/JQS5FKPLQULYFIFXA676XO3E2D/events.json","paper":"https://pith.science/paper/JQS5FKPL"},"agent_actions":{"view_html":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D","download_json":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D.json","view_paper":"https://pith.science/paper/JQS5FKPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29378&json=true","fetch_graph":"https://pith.science/api/pith-number/JQS5FKPLQULYFIFXA676XO3E2D/graph.json","fetch_events":"https://pith.science/api/pith-number/JQS5FKPLQULYFIFXA676XO3E2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D/action/storage_attestation","attest_author":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D/action/author_attestation","sign_citation":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D/action/citation_signature","submit_replication":"https://pith.science/pith/JQS5FKPLQULYFIFXA676XO3E2D/action/replication_record"}},"created_at":"2026-06-30T01:18:03.519248+00:00","updated_at":"2026-06-30T01:18:03.519248+00:00"}