{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2AYQ7DFE5LQI32HGVOIYY7CVQH","short_pith_number":"pith:2AYQ7DFE","schema_version":"1.0","canonical_sha256":"d0310f8ca4eae08de8e6ab918c7c5581fa4a0b0eddeb8d805e34fb32c4b08f80","source":{"kind":"arxiv","id":"2411.03340","version":1},"attestation_state":"computed","paper":{"title":"Unlocking the Archives: Using Large Language Models to Transcribe Handwritten Historical Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Elizabeth Spence, Isabella Murray, John McConnell, Lianne C. Leddy, Mark Humphries, Meredith Legace, Quinn Downton","submitted_at":"2024-11-02T00:16:29Z","abstract_excerpt":"This study demonstrates that Large Language Models (LLMs) can transcribe historical handwritten documents with significantly higher accuracy than specialized Handwritten Text Recognition (HTR) software, while being faster and more cost-effective. We introduce an open-source software tool called Transcription Pearl that leverages these capabilities to automatically transcribe and correct batches of handwritten documents using commercially available multimodal LLMs from OpenAI, Anthropic, and Google. In tests on a diverse corpus of 18th/19th century English language handwritten documents, LLMs a"},"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":"2411.03340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-02T00:16:29Z","cross_cats_sorted":["cs.CL","cs.DL","cs.LG"],"title_canon_sha256":"0a9c85a9359a33a3efcdd4a221a68f9f85575e480111ddb6d72db9c25d20c447","abstract_canon_sha256":"ae24edaf5c9e12eb8ec5fc93f737fbdb3c2f6614d02d968c439a37e603ca2a3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:52.134065Z","signature_b64":"qNEPcXyA/afiBvygSysqHLq28UedZHZH2iFI7RklYmWUfSbVtKzPUg+SAyfnTN1KwbtF+u3dSfyVdhRmJ0KZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0310f8ca4eae08de8e6ab918c7c5581fa4a0b0eddeb8d805e34fb32c4b08f80","last_reissued_at":"2026-07-05T09:31:52.133661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:52.133661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking the Archives: Using Large Language Models to Transcribe Handwritten Historical Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Elizabeth Spence, Isabella Murray, John McConnell, Lianne C. Leddy, Mark Humphries, Meredith Legace, Quinn Downton","submitted_at":"2024-11-02T00:16:29Z","abstract_excerpt":"This study demonstrates that Large Language Models (LLMs) can transcribe historical handwritten documents with significantly higher accuracy than specialized Handwritten Text Recognition (HTR) software, while being faster and more cost-effective. We introduce an open-source software tool called Transcription Pearl that leverages these capabilities to automatically transcribe and correct batches of handwritten documents using commercially available multimodal LLMs from OpenAI, Anthropic, and Google. In tests on a diverse corpus of 18th/19th century English language handwritten documents, LLMs a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03340","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.03340/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":"2411.03340","created_at":"2026-07-05T09:31:52.133716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03340v1","created_at":"2026-07-05T09:31:52.133716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03340","created_at":"2026-07-05T09:31:52.133716+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AYQ7DFE5LQI","created_at":"2026-07-05T09:31:52.133716+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AYQ7DFE5LQI32HG","created_at":"2026-07-05T09:31:52.133716+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AYQ7DFE","created_at":"2026-07-05T09:31:52.133716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04132","citing_title":"An HTR-LLM Workflow for High-Accuracy Transcription and Analysis of Abbreviated Latin Court Hand","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH","json":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH.json","graph_json":"https://pith.science/api/pith-number/2AYQ7DFE5LQI32HGVOIYY7CVQH/graph.json","events_json":"https://pith.science/api/pith-number/2AYQ7DFE5LQI32HGVOIYY7CVQH/events.json","paper":"https://pith.science/paper/2AYQ7DFE"},"agent_actions":{"view_html":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH","download_json":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH.json","view_paper":"https://pith.science/paper/2AYQ7DFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03340&json=true","fetch_graph":"https://pith.science/api/pith-number/2AYQ7DFE5LQI32HGVOIYY7CVQH/graph.json","fetch_events":"https://pith.science/api/pith-number/2AYQ7DFE5LQI32HGVOIYY7CVQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH/action/storage_attestation","attest_author":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH/action/author_attestation","sign_citation":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH/action/citation_signature","submit_replication":"https://pith.science/pith/2AYQ7DFE5LQI32HGVOIYY7CVQH/action/replication_record"}},"created_at":"2026-07-05T09:31:52.133716+00:00","updated_at":"2026-07-05T09:31:52.133716+00:00"}