{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:M5P4B3JKTP4IUS7QNBBJ7EISSA","short_pith_number":"pith:M5P4B3JK","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"},"canonical_sha256":"675fc0ed2a9bf88a4bf068429f91129023497a8231e4279b0d2e8db8c5e84664","source":{"kind":"arxiv","id":"1802.10038","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10038","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10038v2","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10038","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"M5P4B3JKTP4I","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M5P4B3JKTP4IUS7Q","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M5P4B3JK","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:M5P4B3JKTP4IUS7QNBBJ7EISSA","target":"record","payload":{"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"},"canonical_sha256":"675fc0ed2a9bf88a4bf068429f91129023497a8231e4279b0d2e8db8c5e84664","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"},"source_kind":"arxiv","source_id":"1802.10038","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kKnhZirGj3hiXL7/LrWzVvgdgEBQOYtV4fY1wexkO/8HKbtaoAlO7DcmtXpmPZ4Ir4Vu/95dBQizsocHZRXoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:19:21.217029Z"},"content_sha256":"7c244a21195df22c8bfc7c6fe8f73be25d4431bd2233456e2c59857af3f502ce","schema_version":"1.0","event_id":"sha256:7c244a21195df22c8bfc7c6fe8f73be25d4431bd2233456e2c59857af3f502ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:M5P4B3JKTP4IUS7QNBBJ7EISSA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iil9YyDyuw6O2JDjz2PkFn//ZC1fxNKmf2+DHm6ZAZdcVNpdiN7rMMNR08Nc009s26UlXMeqF2BIaNccKyywCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:19:21.217389Z"},"content_sha256":"e3961ca44f3381391413b444487d3c1cac4a47b238669ce6780dea5dad164860","schema_version":"1.0","event_id":"sha256:e3961ca44f3381391413b444487d3c1cac4a47b238669ce6780dea5dad164860"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/bundle.json","state_url":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T22:19:21Z","links":{"resolver":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA","bundle":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/bundle.json","state":"https://pith.science/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5P4B3JKTP4IUS7QNBBJ7EISSA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:M5P4B3JKTP4IUS7QNBBJ7EISSA","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":"df40177698e777ed218c6da9a7eb2af254251e86c768340bd90a89e14c490bb8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T17:35:36Z","title_canon_sha256":"9d8fe9b41a57c18d1480a8a2b887656d9a31feb9dffc5804c13226ab84430916"},"schema_version":"1.0","source":{"id":"1802.10038","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10038","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10038v2","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10038","created_at":"2026-05-18T00:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"M5P4B3JKTP4I","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M5P4B3JKTP4IUS7Q","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M5P4B3JK","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:e3961ca44f3381391413b444487d3c1cac4a47b238669ce6780dea5dad164860","target":"graph","created_at":"2026-05-18T00:22:18Z","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":"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. (","authors_text":"Christian Reul, Christoph Wick, Frank Puppe, Uwe Springmann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T17:35:36Z","title":"Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10038","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":"sha256:7c244a21195df22c8bfc7c6fe8f73be25d4431bd2233456e2c59857af3f502ce","target":"record","created_at":"2026-05-18T00:22:18Z","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":"df40177698e777ed218c6da9a7eb2af254251e86c768340bd90a89e14c490bb8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T17:35:36Z","title_canon_sha256":"9d8fe9b41a57c18d1480a8a2b887656d9a31feb9dffc5804c13226ab84430916"},"schema_version":"1.0","source":{"id":"1802.10038","kind":"arxiv","version":2}},"canonical_sha256":"675fc0ed2a9bf88a4bf068429f91129023497a8231e4279b0d2e8db8c5e84664","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"675fc0ed2a9bf88a4bf068429f91129023497a8231e4279b0d2e8db8c5e84664","first_computed_at":"2026-05-18T00:22:18.149284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:18.149284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5R9hYAWYu18uaWdIU5eD+BN+V+sU0EzeJ89EOq3X0sxW5Tvw5k/DH7o6S6wUtKom3wFgsqbfO4Sqj6cJie0jDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:18.150015Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.10038","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c244a21195df22c8bfc7c6fe8f73be25d4431bd2233456e2c59857af3f502ce","sha256:e3961ca44f3381391413b444487d3c1cac4a47b238669ce6780dea5dad164860"],"state_sha256":"6600deaea086e34d93a1a84a809e37ccdd5fe9117af311cb3b51b5afc816c76b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jODXWVZZjJsQ1K7fF+QbCFU1m8RjnNbYRaymmylNJxt1U5a8unjhIzqlhgeOKbYtnhQC70vuf8E8IoVD0S9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T22:19:21.219329Z","bundle_sha256":"9693fcfe0f88c68702e6ec9e5da63549610b5ed8eb1ba5ccf3abd83b16a96138"}}