{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3K3TGMPZ5KOSVQGZTHG65MJRST","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":"0f8b82822020383126106a95fe2a43ea0771dcc569e94dfc85e739765569d3f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T15:20:37Z","title_canon_sha256":"9b9ec1b273fe48c64cf5ffdad92a031e8e583426f116fb5d3d1b50ddaa26ec21"},"schema_version":"1.0","source":{"id":"2409.19735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19735","created_at":"2026-07-05T09:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19735v1","created_at":"2026-07-05T09:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19735","created_at":"2026-07-05T09:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"3K3TGMPZ5KOS","created_at":"2026-07-05T09:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"3K3TGMPZ5KOSVQGZ","created_at":"2026-07-05T09:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"3K3TGMPZ","created_at":"2026-07-05T09:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:19005b75e5966e05f5c2afae457c962e2c067215f0f725a033d5d301fd0da37c","target":"graph","created_at":"2026-07-05T09:13:21Z","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/2409.19735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"OCR errors are common in digitised historical archives significantly affecting their usability and value. Generative Language Models (LMs) have shown potential for correcting these errors using the context provided by the corrupted text and the broader socio-cultural context, a process called Context Leveraging OCR Correction (CLOCR-C). However, getting sufficient training data for fine-tuning such models can prove challenging. This paper shows that fine-tuning a language model on synthetic data using an LM and using a character level Markov corruption process can significantly improve the abi","authors_text":"Jonathan Bourne","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T15:20:37Z","title":"Scrambled text: training Language Models to correct OCR errors using synthetic data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19735","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:d6fedee7ab49d0644ae179976c0391a71b9a9133ef14bd5f289a8c016db886d3","target":"record","created_at":"2026-07-05T09:13:21Z","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":"0f8b82822020383126106a95fe2a43ea0771dcc569e94dfc85e739765569d3f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T15:20:37Z","title_canon_sha256":"9b9ec1b273fe48c64cf5ffdad92a031e8e583426f116fb5d3d1b50ddaa26ec21"},"schema_version":"1.0","source":{"id":"2409.19735","kind":"arxiv","version":1}},"canonical_sha256":"dab73331f9ea9d2ac0d999cdeeb13194c31d256f5382cf782d271b7465d98470","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dab73331f9ea9d2ac0d999cdeeb13194c31d256f5382cf782d271b7465d98470","first_computed_at":"2026-07-05T09:13:21.684359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:21.684359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lPZqq8MpxsJiRkl6e0K/G1TtXICtQ2dMvOeQGkvs7Ouzo7hPP2qBiX4e4ZUCRbWoXTj6GDN941T+mAT9D6LQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:21.687377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6fedee7ab49d0644ae179976c0391a71b9a9133ef14bd5f289a8c016db886d3","sha256:19005b75e5966e05f5c2afae457c962e2c067215f0f725a033d5d301fd0da37c"],"state_sha256":"257e5430afc38a39550dfd5e2ab849f28b9c8e65caa52fc54adb99c4f298e682"}