{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WFBJU6FZBU3BHAQLTI4IF577G2","short_pith_number":"pith:WFBJU6FZ","schema_version":"1.0","canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","source":{"kind":"arxiv","id":"1608.02153","version":2},"attestation_state":"computed","paper":{"title":"OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"A. L\\\"udeling, U. Springmann","submitted_at":"2016-08-06T20:51:53Z","abstract_excerpt":"This article describes the results of a case study that applies Neural Network-based Optical Character Recognition (OCR) to scanned images of books printed between 1487 and 1870 by training the OCR engine OCRopus [@breuel2013high] on the RIDGES herbal text corpus [@OdebrechtEtAlSubmitted]. Training specific OCR models was possible because the necessary *ground truth* is available as error-corrected diplomatic transcriptions. The OCR results have been evaluated for accuracy against the ground truth of unseen test sets. Character and word accuracies (percentage of correctly recognized items) for"},"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":"1608.02153","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-06T20:51:53Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"deffc7c3059621d1ffd2011b3900ada4f6a5a2bc580d80923206223e4fb6214d","abstract_canon_sha256":"b9770366d101260c9246fb8516acdfd3ebc763f9e33e82856589dda43b30fd52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:49.217618Z","signature_b64":"rhMxKBtIZIRIHpgUZfY/3KqY94rJ1zmCIqM7DPXES5Yd34PEht6+TOIZdfQJJByMkQSiczx8fR9Fh305w+RKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1429a78b90d3613820b9a3882f7ff369130104df20f6246677fb34f294c81b3","last_reissued_at":"2026-05-18T00:46:49.216881Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:49.216881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"A. L\\\"udeling, U. Springmann","submitted_at":"2016-08-06T20:51:53Z","abstract_excerpt":"This article describes the results of a case study that applies Neural Network-based Optical Character Recognition (OCR) to scanned images of books printed between 1487 and 1870 by training the OCR engine OCRopus [@breuel2013high] on the RIDGES herbal text corpus [@OdebrechtEtAlSubmitted]. Training specific OCR models was possible because the necessary *ground truth* is available as error-corrected diplomatic transcriptions. The OCR results have been evaluated for accuracy against the ground truth of unseen test sets. Character and word accuracies (percentage of correctly recognized items) for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02153","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":"1608.02153","created_at":"2026-05-18T00:46:49.217008+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.02153v2","created_at":"2026-05-18T00:46:49.217008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02153","created_at":"2026-05-18T00:46:49.217008+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFBJU6FZBU3B","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFBJU6FZBU3BHAQL","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFBJU6FZ","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.29378","citing_title":"Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2","json":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2.json","graph_json":"https://pith.science/api/pith-number/WFBJU6FZBU3BHAQLTI4IF577G2/graph.json","events_json":"https://pith.science/api/pith-number/WFBJU6FZBU3BHAQLTI4IF577G2/events.json","paper":"https://pith.science/paper/WFBJU6FZ"},"agent_actions":{"view_html":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2","download_json":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2.json","view_paper":"https://pith.science/paper/WFBJU6FZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.02153&json=true","fetch_graph":"https://pith.science/api/pith-number/WFBJU6FZBU3BHAQLTI4IF577G2/graph.json","fetch_events":"https://pith.science/api/pith-number/WFBJU6FZBU3BHAQLTI4IF577G2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/action/storage_attestation","attest_author":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/action/author_attestation","sign_citation":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/action/citation_signature","submit_replication":"https://pith.science/pith/WFBJU6FZBU3BHAQLTI4IF577G2/action/replication_record"}},"created_at":"2026-05-18T00:46:49.217008+00:00","updated_at":"2026-05-18T00:46:49.217008+00:00"}