{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3BV4KIAFU43CA4ZMMK5Z2OAAL5","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":"bc0b5223b54992975d23191bced18d49d9eebb6630c3cf1d88722d61896ec704","cross_cats_sorted":["cs.DL","econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T20:36:04Z","title_canon_sha256":"7ae60ceae6c549c710562f35842546e14aa1ee4c231b6eef1c1e2ca50dea4d30"},"schema_version":"1.0","source":{"id":"2304.02737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02737","created_at":"2026-07-05T08:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02737v2","created_at":"2026-07-05T08:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02737","created_at":"2026-07-05T08:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"3BV4KIAFU43C","created_at":"2026-07-05T08:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"3BV4KIAFU43CA4ZM","created_at":"2026-07-05T08:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"3BV4KIAF","created_at":"2026-07-05T08:48:38Z"}],"graph_snapshots":[{"event_id":"sha256:9b2dfa1035d481fe3eff5ea5b55b963da55326e503fbbf79f3cfc86e214c9dbf","target":"graph","created_at":"2026-07-05T08:48:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.02737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jacob Carlson, Melissa Dell, Tom Bryan","cross_cats":["cs.DL","econ.GN","q-fin.EC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T20:36:04Z","title":"Efficient OCR for Building a Diverse Digital History"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02737","kind":"arxiv","version":2},"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:d5262e13972b22d6838eb7bba7b9e2eeee071e741bbe19c046a78af66cc1a849","target":"record","created_at":"2026-07-05T08:48:38Z","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":"bc0b5223b54992975d23191bced18d49d9eebb6630c3cf1d88722d61896ec704","cross_cats_sorted":["cs.DL","econ.GN","q-fin.EC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T20:36:04Z","title_canon_sha256":"7ae60ceae6c549c710562f35842546e14aa1ee4c231b6eef1c1e2ca50dea4d30"},"schema_version":"1.0","source":{"id":"2304.02737","kind":"arxiv","version":2}},"canonical_sha256":"d86bc52005a73620732c62bb9d38005f579ebd800e6abc7bfc6eded4b60e3183","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d86bc52005a73620732c62bb9d38005f579ebd800e6abc7bfc6eded4b60e3183","first_computed_at":"2026-07-05T08:48:38.362396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:38.362396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qZDIEt8gYyBN0th+vxXua5iP3OwNwv/By4O2mW5Vpmus37LixnOWeXRLQ3NQvysJl8olsctTdJhjerxcPNsTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:38.362889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5262e13972b22d6838eb7bba7b9e2eeee071e741bbe19c046a78af66cc1a849","sha256:9b2dfa1035d481fe3eff5ea5b55b963da55326e503fbbf79f3cfc86e214c9dbf"],"state_sha256":"17c9626ddbcfdc60c95e862e3e87d5bf7c4c122f3f96d2bab88f0d36fdd2b1ff"}