{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PHAPVHPAAVOJC6INA3ZGPTCIOT","short_pith_number":"pith:PHAPVHPA","canonical_record":{"source":{"id":"1711.09670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T13:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"f3c8e528e9e21720966283b6313efe813d62d50863a8e7fd210c5f21cde72c77","abstract_canon_sha256":"c025d0bbbab90384f3ae82beb21d207fd61bbca462ef3704930d3e97aa19dcaa"},"schema_version":"1.0"},"canonical_sha256":"79c0fa9de0055c91790d06f267cc4874c6abce5cc9934bb512ca6cde36f209e8","source":{"kind":"arxiv","id":"1711.09670","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.09670","created_at":"2026-05-18T00:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"1711.09670v1","created_at":"2026-05-18T00:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09670","created_at":"2026-05-18T00:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"PHAPVHPAAVOJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PHAPVHPAAVOJC6IN","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PHAPVHPA","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PHAPVHPAAVOJC6INA3ZGPTCIOT","target":"record","payload":{"canonical_record":{"source":{"id":"1711.09670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T13:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"f3c8e528e9e21720966283b6313efe813d62d50863a8e7fd210c5f21cde72c77","abstract_canon_sha256":"c025d0bbbab90384f3ae82beb21d207fd61bbca462ef3704930d3e97aa19dcaa"},"schema_version":"1.0"},"canonical_sha256":"79c0fa9de0055c91790d06f267cc4874c6abce5cc9934bb512ca6cde36f209e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:03.585188Z","signature_b64":"rjA+IsDylresduuUI9R+ZlORuM6Y2sfSjN/U8+9XfXhYKYsklvgZNcRurUbp0rsVi92bA1v/q8VIXfMRKtxrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79c0fa9de0055c91790d06f267cc4874c6abce5cc9934bb512ca6cde36f209e8","last_reissued_at":"2026-05-18T00:10:03.584522Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:03.584522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.09670","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HLcCMrQ0959PrVNvQyVsgepDo66uhLPVPAPa6G9yIereKYXwq5A3tTOdqR+9+TYyYtnPEvqLSClY3s2s4vOjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:34:43.315233Z"},"content_sha256":"cd130e50fef5a7d5c61569caf735cfa50b60d4dbb018d9f6fb2110e6d70f13a3","schema_version":"1.0","event_id":"sha256:cd130e50fef5a7d5c61569caf735cfa50b60d4dbb018d9f6fb2110e6d70f13a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PHAPVHPAAVOJC6INA3ZGPTCIOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Reul, Christoph Wick, Frank Puppe, Uwe Springmann","submitted_at":"2017-11-27T13:15:52Z","abstract_excerpt":"In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consider"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09670","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":""},"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":"2026-05-18T00:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cstV0+T4nuLZnfFkWC8NRo42L6cBHwmMMHY/bG9DuSlB3OyI9m3G5GLf71zOGbgzccsGy1HIAurAeKW/HoYlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T03:34:43.315602Z"},"content_sha256":"19be459a9c0fffdb6eadd851b02347e84f0ce0c6e57ded66c307d624a6305b2f","schema_version":"1.0","event_id":"sha256:19be459a9c0fffdb6eadd851b02347e84f0ce0c6e57ded66c307d624a6305b2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT/bundle.json","state_url":"https://pith.science/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT/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":"2026-06-02T03:34:43Z","links":{"resolver":"https://pith.science/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT","bundle":"https://pith.science/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT/bundle.json","state":"https://pith.science/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHAPVHPAAVOJC6INA3ZGPTCIOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PHAPVHPAAVOJC6INA3ZGPTCIOT","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":"c025d0bbbab90384f3ae82beb21d207fd61bbca462ef3704930d3e97aa19dcaa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T13:15:52Z","title_canon_sha256":"f3c8e528e9e21720966283b6313efe813d62d50863a8e7fd210c5f21cde72c77"},"schema_version":"1.0","source":{"id":"1711.09670","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.09670","created_at":"2026-05-18T00:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"1711.09670v1","created_at":"2026-05-18T00:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09670","created_at":"2026-05-18T00:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"PHAPVHPAAVOJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PHAPVHPAAVOJC6IN","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PHAPVHPA","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:19be459a9c0fffdb6eadd851b02347e84f0ce0c6e57ded66c307d624a6305b2f","target":"graph","created_at":"2026-05-18T00:10:03Z","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":"In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consider","authors_text":"Christian Reul, Christoph Wick, Frank Puppe, Uwe Springmann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T13:15:52Z","title":"Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09670","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:cd130e50fef5a7d5c61569caf735cfa50b60d4dbb018d9f6fb2110e6d70f13a3","target":"record","created_at":"2026-05-18T00:10:03Z","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":"c025d0bbbab90384f3ae82beb21d207fd61bbca462ef3704930d3e97aa19dcaa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-27T13:15:52Z","title_canon_sha256":"f3c8e528e9e21720966283b6313efe813d62d50863a8e7fd210c5f21cde72c77"},"schema_version":"1.0","source":{"id":"1711.09670","kind":"arxiv","version":1}},"canonical_sha256":"79c0fa9de0055c91790d06f267cc4874c6abce5cc9934bb512ca6cde36f209e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79c0fa9de0055c91790d06f267cc4874c6abce5cc9934bb512ca6cde36f209e8","first_computed_at":"2026-05-18T00:10:03.584522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:03.584522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rjA+IsDylresduuUI9R+ZlORuM6Y2sfSjN/U8+9XfXhYKYsklvgZNcRurUbp0rsVi92bA1v/q8VIXfMRKtxrCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:03.585188Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.09670","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd130e50fef5a7d5c61569caf735cfa50b60d4dbb018d9f6fb2110e6d70f13a3","sha256:19be459a9c0fffdb6eadd851b02347e84f0ce0c6e57ded66c307d624a6305b2f"],"state_sha256":"10ea78a02a343eca63eadf6c549140ac4631b63f936c237c536fbbd65c34a7ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bKIY/15iiog98jYJWERJbUnsSWGyn9K1WZu0qNX+6jIKIsz4kVQtxtSlsYWcW4wIm9Bx/znlbGgbAmDAdHavCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T03:34:43.317651Z","bundle_sha256":"956426d414b679df35b9791a96fabf8c697bba6d199fba2f3a6464f5735971a7"}}