{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:M5P4B3JKTP4IUS7QNBBJ7EISSA","short_pith_number":"pith:M5P4B3JK","schema_version":"1.0","canonical_sha256":"675fc0ed2a9bf88a4bf068429f91129023497a8231e4279b0d2e8db8c5e84664","source":{"kind":"arxiv","id":"1802.10038","version":2},"attestation_state":"computed","paper":{"title":"Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Reul, Christoph Wick, Frank Puppe, Uwe Springmann","submitted_at":"2018-02-27T17:35:36Z","abstract_excerpt":"We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in already existing models trained on a variety of typesets (mixed models) instead of starting the training from scratch. (2) Performing cross fold training on a single set of ground truth data (line images and their transcriptions) with a single OCR engine (OCRopus) produces a committee whose members then vote for the best outcome by also taking the top-N alternatives and their intrinsic confidence values into account. ("},"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":"1802.10038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T17:35:36Z","cross_cats_sorted":[],"title_canon_sha256":"9d8fe9b41a57c18d1480a8a2b887656d9a31feb9dffc5804c13226ab84430916","abstract_canon_sha256":"df40177698e777ed218c6da9a7eb2af254251e86c768340bd90a89e14c490bb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:18.150015Z","signature_b64":"5R9hYAWYu18uaWdIU5eD+BN+V+sU0EzeJ89EOq3X0sxW5Tvw5k/DH7o6S6wUtKom3wFgsqbfO4Sqj6cJie0jDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675fc0ed2a9bf88a4bf068429f91129023497a8231e4279b0d2e8db8c5e84664","last_reissued_at":"2026-05-18T00:22:18.149284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:18.149284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Reul, Christoph Wick, Frank Puppe, Uwe Springmann","submitted_at":"2018-02-27T17:35:36Z","abstract_excerpt":"We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in already existing models trained on a variety of typesets (mixed models) instead of starting the training from scratch. (2) Performing cross fold training on a single set of ground truth data (line images and their transcriptions) with a single OCR engine (OCRopus) produces a committee whose members then vote for the best outcome by also taking the top-N alternatives and their intrinsic confidence values into account. ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10038","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.10038","created_at":"2026-05-18T00:22:18.149415+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10038v2","created_at":"2026-05-18T00:22:18.149415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10038","created_at":"2026-05-18T00:22:18.149415+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5P4B3JKTP4I","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5P4B3JKTP4IUS7Q","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5P4B3JK","created_at":"2026-05-18T12:32:37.024351+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/M5P4B3JKTP4IUS7QNBBJ7EISSA","json":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA.json","graph_json":"https://pith.science/api/pith-number/M5P4B3JKTP4IUS7QNBBJ7EISSA/graph.json","events_json":"https://pith.science/api/pith-number/M5P4B3JKTP4IUS7QNBBJ7EISSA/events.json","paper":"https://pith.science/paper/M5P4B3JK"},"agent_actions":{"view_html":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA","download_json":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA.json","view_paper":"https://pith.science/paper/M5P4B3JK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10038&json=true","fetch_graph":"https://pith.science/api/pith-number/M5P4B3JKTP4IUS7QNBBJ7EISSA/graph.json","fetch_events":"https://pith.science/api/pith-number/M5P4B3JKTP4IUS7QNBBJ7EISSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/action/storage_attestation","attest_author":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/action/author_attestation","sign_citation":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/action/citation_signature","submit_replication":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/action/replication_record"}},"created_at":"2026-05-18T00:22:18.149415+00:00","updated_at":"2026-05-18T00:22:18.149415+00:00"}