{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FUMZ5U2H4VDEMPT2DP3DWBRYJ6","short_pith_number":"pith:FUMZ5U2H","schema_version":"1.0","canonical_sha256":"2d199ed347e546463e7a1bf63b06384f86eb7eed634c0ad1ad7e7c1fba95fc3c","source":{"kind":"arxiv","id":"1809.05501","version":1},"attestation_state":"computed","paper":{"title":"Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Reul, Johannes Baiter, Stefanie Dipper, Uwe Springmann","submitted_at":"2018-09-14T16:52:12Z","abstract_excerpt":"In this paper we describe a dataset of German and Latin \\textit{ground truth} (GT) for historical OCR in the form of printed text line images paired with their transcription. This dataset, called \\textit{GT4HistOCR}, consists of 313,173 line pairs covering a wide period of printing dates from incunabula from the 15th century to 19th century books printed in Fraktur types and is openly available under a CC-BY 4.0 license. The special form of GT as line image/transcription pairs makes it directly usable to train state-of-the-art recognition models for OCR software employing recurring neural netw"},"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":"1809.05501","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-14T16:52:12Z","cross_cats_sorted":[],"title_canon_sha256":"e5d5983efa24f68e5f642d6a00c5c07d2c472d0e7537894fe5a1adf7c835ae45","abstract_canon_sha256":"2c522702f557cc8f5d120b31295a9ce4fbd0fe37c8fb5e731a5b9185f011b309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:41.263364Z","signature_b64":"Qn7GiaH+Iz65Fpv7YD6MqXbmn1VvTL10MgQPLoMgPpuQYG639agT1Iw3b/Sa9afQT1+yy4WoXZZ4WGp1rmlqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d199ed347e546463e7a1bf63b06384f86eb7eed634c0ad1ad7e7c1fba95fc3c","last_reissued_at":"2026-05-18T00:05:41.262833Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:41.262833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Reul, Johannes Baiter, Stefanie Dipper, Uwe Springmann","submitted_at":"2018-09-14T16:52:12Z","abstract_excerpt":"In this paper we describe a dataset of German and Latin \\textit{ground truth} (GT) for historical OCR in the form of printed text line images paired with their transcription. This dataset, called \\textit{GT4HistOCR}, consists of 313,173 line pairs covering a wide period of printing dates from incunabula from the 15th century to 19th century books printed in Fraktur types and is openly available under a CC-BY 4.0 license. The special form of GT as line image/transcription pairs makes it directly usable to train state-of-the-art recognition models for OCR software employing recurring neural netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05501","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.05501","created_at":"2026-05-18T00:05:41.262913+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05501v1","created_at":"2026-05-18T00:05:41.262913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05501","created_at":"2026-05-18T00:05:41.262913+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUMZ5U2H4VDE","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUMZ5U2H4VDEMPT2","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUMZ5U2H","created_at":"2026-05-18T12:32:25.280505+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/FUMZ5U2H4VDEMPT2DP3DWBRYJ6","json":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6.json","graph_json":"https://pith.science/api/pith-number/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/graph.json","events_json":"https://pith.science/api/pith-number/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/events.json","paper":"https://pith.science/paper/FUMZ5U2H"},"agent_actions":{"view_html":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6","download_json":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6.json","view_paper":"https://pith.science/paper/FUMZ5U2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05501&json=true","fetch_graph":"https://pith.science/api/pith-number/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/action/storage_attestation","attest_author":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/action/author_attestation","sign_citation":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/action/citation_signature","submit_replication":"https://pith.science/pith/FUMZ5U2H4VDEMPT2DP3DWBRYJ6/action/replication_record"}},"created_at":"2026-05-18T00:05:41.262913+00:00","updated_at":"2026-05-18T00:05:41.262913+00:00"}