{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HQXRZYBQ6CWGCGMUPB7TXBBVOM","short_pith_number":"pith:HQXRZYBQ","schema_version":"1.0","canonical_sha256":"3c2f1ce030f0ac611994787f3b8435731e9ee3d66459b60baf7bb5cc08ba658d","source":{"kind":"arxiv","id":"1807.02004","version":3},"attestation_state":"computed","paper":{"title":"Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Reul, Christoph Wick, Frank Puppe","submitted_at":"2018-07-05T13:46:37Z","abstract_excerpt":"Optical Character Recognition (OCR) on contemporary and historical data is still in the focus of many researchers. Especially historical prints require book specific trained OCR models to achieve applicable results (Springmann and L\\\"udeling, 2016, Reul et al., 2017a). To reduce the human effort for manually annotating ground truth (GT) various techniques such as voting and pretraining have shown to be very efficient (Reul et al., 2018a, Reul et al., 2018b). Calamari is a new open source OCR line recognition software that both uses state-of-the art Deep Neural Networks (DNNs) implemented in Te"},"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":"1807.02004","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-05T13:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"9b26b5a0f5d930e18cc829aa820dfb9f62bf56e1b4a1d9dc1045f075d2a1eeae","abstract_canon_sha256":"385f3587841f7bd0f8accf1a467dc195a41a09f09b82af2473198c0d214f9edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:46.838368Z","signature_b64":"1khgC8XC6L1SywbaIqUvwzSThrFXsBqoZJwx1/e73kxYOWBskaEcrakgTpR98Z2yiHZsxzy734Db59kErQQ6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c2f1ce030f0ac611994787f3b8435731e9ee3d66459b60baf7bb5cc08ba658d","last_reissued_at":"2026-07-05T02:06:46.837972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:46.837972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Reul, Christoph Wick, Frank Puppe","submitted_at":"2018-07-05T13:46:37Z","abstract_excerpt":"Optical Character Recognition (OCR) on contemporary and historical data is still in the focus of many researchers. Especially historical prints require book specific trained OCR models to achieve applicable results (Springmann and L\\\"udeling, 2016, Reul et al., 2017a). To reduce the human effort for manually annotating ground truth (GT) various techniques such as voting and pretraining have shown to be very efficient (Reul et al., 2018a, Reul et al., 2018b). Calamari is a new open source OCR line recognition software that both uses state-of-the art Deep Neural Networks (DNNs) implemented in Te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02004","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1807.02004/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1807.02004","created_at":"2026-07-05T02:06:46.838020+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02004v3","created_at":"2026-07-05T02:06:46.838020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02004","created_at":"2026-07-05T02:06:46.838020+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQXRZYBQ6CWG","created_at":"2026-07-05T02:06:46.838020+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQXRZYBQ6CWGCGMU","created_at":"2026-07-05T02:06:46.838020+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQXRZYBQ","created_at":"2026-07-05T02:06:46.838020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22880","citing_title":"TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM","json":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM.json","graph_json":"https://pith.science/api/pith-number/HQXRZYBQ6CWGCGMUPB7TXBBVOM/graph.json","events_json":"https://pith.science/api/pith-number/HQXRZYBQ6CWGCGMUPB7TXBBVOM/events.json","paper":"https://pith.science/paper/HQXRZYBQ"},"agent_actions":{"view_html":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM","download_json":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM.json","view_paper":"https://pith.science/paper/HQXRZYBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02004&json=true","fetch_graph":"https://pith.science/api/pith-number/HQXRZYBQ6CWGCGMUPB7TXBBVOM/graph.json","fetch_events":"https://pith.science/api/pith-number/HQXRZYBQ6CWGCGMUPB7TXBBVOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM/action/storage_attestation","attest_author":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM/action/author_attestation","sign_citation":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM/action/citation_signature","submit_replication":"https://pith.science/pith/HQXRZYBQ6CWGCGMUPB7TXBBVOM/action/replication_record"}},"created_at":"2026-07-05T02:06:46.838020+00:00","updated_at":"2026-07-05T02:06:46.838020+00:00"}