{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:X36WF5F44GP6YE6WOZQBONTB7K","short_pith_number":"pith:X36WF5F4","schema_version":"1.0","canonical_sha256":"befd62f4bce19fec13d67660173661fa80c92a7ddf5aeb7c71a5c530c643d387","source":{"kind":"arxiv","id":"1606.05157","version":2},"attestation_state":"computed","paper":{"title":"Automatic quality evaluation and (semi-) automatic improvement of OCR models for historical printings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"F. Fink, K. U. Schulz, U. Springmann","submitted_at":"2016-06-16T12:15:14Z","abstract_excerpt":"Good OCR results for historical printings rely on the availability of recognition models trained on diplomatic transcriptions as ground truth, which is both a scarce resource and time-consuming to generate. Instead of having to train a separate model for each historical typeface, we propose a strategy to start from models trained on a combined set of available transcriptions in a variety of fonts. These \\emph{mixed models} result in character accuracy rates over 90\\% on a test set of printings from the same period of time, but without any representation in the training data, demonstrating the "},"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":"1606.05157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2016-06-16T12:15:14Z","cross_cats_sorted":[],"title_canon_sha256":"c3abcbf5d679265fc66e2272aa3664bba6086b12b10cf4c5e65a7837727c33e5","abstract_canon_sha256":"900a8e522f42c21aad10587e4bcf04a6d14626db8f5406842f7289ff810f23d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:44.430016Z","signature_b64":"+hrQLC8ksMTfws7DrlqG3S8VI4UN10EGlzEjg0senGR0ivPi2vyZr1FtwomQUy+eX4fq2a+woV+Aeo8bJmk7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"befd62f4bce19fec13d67660173661fa80c92a7ddf5aeb7c71a5c530c643d387","last_reissued_at":"2026-05-18T01:01:44.429250Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:44.429250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic quality evaluation and (semi-) automatic improvement of OCR models for historical printings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"F. Fink, K. U. Schulz, U. Springmann","submitted_at":"2016-06-16T12:15:14Z","abstract_excerpt":"Good OCR results for historical printings rely on the availability of recognition models trained on diplomatic transcriptions as ground truth, which is both a scarce resource and time-consuming to generate. Instead of having to train a separate model for each historical typeface, we propose a strategy to start from models trained on a combined set of available transcriptions in a variety of fonts. These \\emph{mixed models} result in character accuracy rates over 90\\% on a test set of printings from the same period of time, but without any representation in the training data, demonstrating the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05157","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":"1606.05157","created_at":"2026-05-18T01:01:44.429389+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.05157v2","created_at":"2026-05-18T01:01:44.429389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05157","created_at":"2026-05-18T01:01:44.429389+00:00"},{"alias_kind":"pith_short_12","alias_value":"X36WF5F44GP6","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"X36WF5F44GP6YE6W","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"X36WF5F4","created_at":"2026-05-18T12:30:51.357362+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/X36WF5F44GP6YE6WOZQBONTB7K","json":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K.json","graph_json":"https://pith.science/api/pith-number/X36WF5F44GP6YE6WOZQBONTB7K/graph.json","events_json":"https://pith.science/api/pith-number/X36WF5F44GP6YE6WOZQBONTB7K/events.json","paper":"https://pith.science/paper/X36WF5F4"},"agent_actions":{"view_html":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K","download_json":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K.json","view_paper":"https://pith.science/paper/X36WF5F4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.05157&json=true","fetch_graph":"https://pith.science/api/pith-number/X36WF5F44GP6YE6WOZQBONTB7K/graph.json","fetch_events":"https://pith.science/api/pith-number/X36WF5F44GP6YE6WOZQBONTB7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K/action/storage_attestation","attest_author":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K/action/author_attestation","sign_citation":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K/action/citation_signature","submit_replication":"https://pith.science/pith/X36WF5F44GP6YE6WOZQBONTB7K/action/replication_record"}},"created_at":"2026-05-18T01:01:44.429389+00:00","updated_at":"2026-05-18T01:01:44.429389+00:00"}