{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FUMZ5U2H4VDEMPT2DP3DWBRYJ6","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":"2c522702f557cc8f5d120b31295a9ce4fbd0fe37c8fb5e731a5b9185f011b309","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-14T16:52:12Z","title_canon_sha256":"e5d5983efa24f68e5f642d6a00c5c07d2c472d0e7537894fe5a1adf7c835ae45"},"schema_version":"1.0","source":{"id":"1809.05501","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05501","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05501v1","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05501","created_at":"2026-05-18T00:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"FUMZ5U2H4VDE","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FUMZ5U2H4VDEMPT2","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FUMZ5U2H","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:c01d146930cabc272361923f544f22196c594d56531d55485066ff1afaf1c4d4","target":"graph","created_at":"2026-05-18T00:05:41Z","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 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","authors_text":"Christian Reul, Johannes Baiter, Stefanie Dipper, Uwe Springmann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-14T16:52:12Z","title":"Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05501","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:eb4b0ed13e83d06db579f40ef6865640520e0c076898c157e8e7ce88bdf04add","target":"record","created_at":"2026-05-18T00:05:41Z","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":"2c522702f557cc8f5d120b31295a9ce4fbd0fe37c8fb5e731a5b9185f011b309","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-14T16:52:12Z","title_canon_sha256":"e5d5983efa24f68e5f642d6a00c5c07d2c472d0e7537894fe5a1adf7c835ae45"},"schema_version":"1.0","source":{"id":"1809.05501","kind":"arxiv","version":1}},"canonical_sha256":"2d199ed347e546463e7a1bf63b06384f86eb7eed634c0ad1ad7e7c1fba95fc3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d199ed347e546463e7a1bf63b06384f86eb7eed634c0ad1ad7e7c1fba95fc3c","first_computed_at":"2026-05-18T00:05:41.262833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:41.262833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qn7GiaH+Iz65Fpv7YD6MqXbmn1VvTL10MgQPLoMgPpuQYG639agT1Iw3b/Sa9afQT1+yy4WoXZZ4WGp1rmlqDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:41.263364Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.05501","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb4b0ed13e83d06db579f40ef6865640520e0c076898c157e8e7ce88bdf04add","sha256:c01d146930cabc272361923f544f22196c594d56531d55485066ff1afaf1c4d4"],"state_sha256":"7ab0c278877c36998966924a422a74d27ad3cbe848a962a6efb3d2d5133f7051"}