{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3BV4KIAFU43CA4ZMMK5Z2OAAL5","short_pith_number":"pith:3BV4KIAF","schema_version":"1.0","canonical_sha256":"d86bc52005a73620732c62bb9d38005f579ebd800e6abc7bfc6eded4b60e3183","source":{"kind":"arxiv","id":"2304.02737","version":2},"attestation_state":"computed","paper":{"title":"Efficient OCR for Building a Diverse Digital History","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","econ.GN","q-fin.EC"],"primary_cat":"cs.CV","authors_text":"Jacob Carlson, Melissa Dell, Tom Bryan","submitted_at":"2023-04-05T20:36:04Z","abstract_excerpt":"Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence architecture typically used for optical character recognition (OCR) - which jointly learns a vision and language model - is poorly extensible to low-resource document collections, as learning a language-vision model requires extensive labeled sequences and compute. This study models OCR as a character level image retrieval problem, using a contrastively trained vision encoder. Because the model only learns characters' visua"},"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":"2304.02737","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T20:36:04Z","cross_cats_sorted":["cs.DL","econ.GN","q-fin.EC"],"title_canon_sha256":"7ae60ceae6c549c710562f35842546e14aa1ee4c231b6eef1c1e2ca50dea4d30","abstract_canon_sha256":"bc0b5223b54992975d23191bced18d49d9eebb6630c3cf1d88722d61896ec704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:38.362889Z","signature_b64":"qZDIEt8gYyBN0th+vxXua5iP3OwNwv/By4O2mW5Vpmus37LixnOWeXRLQ3NQvysJl8olsctTdJhjerxcPNsTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d86bc52005a73620732c62bb9d38005f579ebd800e6abc7bfc6eded4b60e3183","last_reissued_at":"2026-07-05T08:48:38.362396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:38.362396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient OCR for Building a Diverse Digital History","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","econ.GN","q-fin.EC"],"primary_cat":"cs.CV","authors_text":"Jacob Carlson, Melissa Dell, Tom Bryan","submitted_at":"2023-04-05T20:36:04Z","abstract_excerpt":"Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence architecture typically used for optical character recognition (OCR) - which jointly learns a vision and language model - is poorly extensible to low-resource document collections, as learning a language-vision model requires extensive labeled sequences and compute. This study models OCR as a character level image retrieval problem, using a contrastively trained vision encoder. Because the model only learns characters' visua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02737","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.02737/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":"2304.02737","created_at":"2026-07-05T08:48:38.362458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02737v2","created_at":"2026-07-05T08:48:38.362458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02737","created_at":"2026-07-05T08:48:38.362458+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BV4KIAFU43C","created_at":"2026-07-05T08:48:38.362458+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BV4KIAFU43CA4ZM","created_at":"2026-07-05T08:48:38.362458+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BV4KIAF","created_at":"2026-07-05T08:48:38.362458+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/3BV4KIAFU43CA4ZMMK5Z2OAAL5","json":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5.json","graph_json":"https://pith.science/api/pith-number/3BV4KIAFU43CA4ZMMK5Z2OAAL5/graph.json","events_json":"https://pith.science/api/pith-number/3BV4KIAFU43CA4ZMMK5Z2OAAL5/events.json","paper":"https://pith.science/paper/3BV4KIAF"},"agent_actions":{"view_html":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5","download_json":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5.json","view_paper":"https://pith.science/paper/3BV4KIAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02737&json=true","fetch_graph":"https://pith.science/api/pith-number/3BV4KIAFU43CA4ZMMK5Z2OAAL5/graph.json","fetch_events":"https://pith.science/api/pith-number/3BV4KIAFU43CA4ZMMK5Z2OAAL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5/action/storage_attestation","attest_author":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5/action/author_attestation","sign_citation":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5/action/citation_signature","submit_replication":"https://pith.science/pith/3BV4KIAFU43CA4ZMMK5Z2OAAL5/action/replication_record"}},"created_at":"2026-07-05T08:48:38.362458+00:00","updated_at":"2026-07-05T08:48:38.362458+00:00"}