{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PFURVECBXTP3FCWMWG2MTOMMN5","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":"87eccd034930548884c74df58b19d2fd6fc41c7d92ff70fe860f8c300b582e10","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-26T08:28:51Z","title_canon_sha256":"ae01b48a60f3cd2a061ec639664287f12ff643557c8e549231e93f7eccb96cee"},"schema_version":"1.0","source":{"id":"1906.10907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10907","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10907v1","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10907","created_at":"2026-05-17T23:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"PFURVECBXTP3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PFURVECBXTP3FCWM","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PFURVECB","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:a69633c2312cb321766982326bf5775e3c0dc7b53d272bcf69df5bd06838a47d","target":"graph","created_at":"2026-05-17T23:42:10Z","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"},"paper":{"abstract_excerpt":"A common approach for improving OCR quality is a post-processing step based on models correcting misdetected characters and tokens. These models are typically trained on aligned pairs of OCR read text and their manually corrected counterparts. In this paper we show that the requirement of manually corrected training data can be alleviated by estimating the OCR errors from repeating text spans found in large OCR read text corpora and generating synthetic training examples following this error distribution. We use the generated data for training a character-level neural seq2seq model and evaluat","authors_text":"Aleksi Vesanto, Filip Ginter, Kai Hakala, Niko Miekka, Tapio Salakoski","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-26T08:28:51Z","title":"Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10907","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:a3c150f248e276348f8e54564c59e8940b09eb1f937294a22d3f21bb7b319f57","target":"record","created_at":"2026-05-17T23:42:10Z","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":"87eccd034930548884c74df58b19d2fd6fc41c7d92ff70fe860f8c300b582e10","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-26T08:28:51Z","title_canon_sha256":"ae01b48a60f3cd2a061ec639664287f12ff643557c8e549231e93f7eccb96cee"},"schema_version":"1.0","source":{"id":"1906.10907","kind":"arxiv","version":1}},"canonical_sha256":"79691a9041bcdfb28accb1b4c9b98c6f6ae1a4f0ad536f92344c3c7b93c1a809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79691a9041bcdfb28accb1b4c9b98c6f6ae1a4f0ad536f92344c3c7b93c1a809","first_computed_at":"2026-05-17T23:42:10.573599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:10.573599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DsfWWdrfkBqitNzp6nFgTmDqktd8FnKg8JSK8F7Ht4ksiEfAe8VuAHD1kAKK1kc6xPl3ljPh+lt7Ta4QIdfbDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:10.574458Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3c150f248e276348f8e54564c59e8940b09eb1f937294a22d3f21bb7b319f57","sha256:a69633c2312cb321766982326bf5775e3c0dc7b53d272bcf69df5bd06838a47d"],"state_sha256":"34eecd5c944cfac2ed7b706b367a15cf38a1b53bc7e996cbe98b8af8129e7a8e"}