{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YTZ5CRQDDOF2J2FQHL6BKUYULU","short_pith_number":"pith:YTZ5CRQD","schema_version":"1.0","canonical_sha256":"c4f3d146031b8ba4e8b03afc1553145d1612c53a8a0be791f1f16b33e3cfe19f","source":{"kind":"arxiv","id":"1601.07252","version":1},"attestation_state":"computed","paper":{"title":"Font Identification in Historical Documents Using Active Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","stat.AP","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anshul Gupta, Laura Mandell, Matthew Christy, Ricardo Gutierrez-Osuna, Richard Furuta","submitted_at":"2016-01-27T03:24:05Z","abstract_excerpt":"Identifying the type of font (e.g., Roman, Blackletter) used in historical documents can help optical character recognition (OCR) systems produce more accurate text transcriptions. Towards this end, we present an active-learning strategy that can significantly reduce the number of labeled samples needed to train a font classifier. Our approach extracts image-based features that exploit geometric differences between fonts at the word level, and combines them into a bag-of-word representation for each page in a document. We evaluate six sampling strategies based on uncertainty, dissimilarity and"},"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":"1601.07252","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-01-27T03:24:05Z","cross_cats_sorted":["cs.AI","cs.DL","stat.AP","stat.ML"],"title_canon_sha256":"fcf0e1ddccc683ad36565fead98c9cabd8c0dccd3313d0d588ccf6b7807431e1","abstract_canon_sha256":"b6d480c6010577b77e2f97ec4e126daec8079c32b7d5ece14592ae7f6f080304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:46.377665Z","signature_b64":"1E2U/P/rth3AbH0uguqOWhOmww5sobC6zynZ7J6L6hE8c/owWOwthjJwOZr5r1UEKzbmZn4dvYR1ALsle5E2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f3d146031b8ba4e8b03afc1553145d1612c53a8a0be791f1f16b33e3cfe19f","last_reissued_at":"2026-05-18T01:21:46.376963Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:46.376963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Font Identification in Historical Documents Using Active Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","stat.AP","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anshul Gupta, Laura Mandell, Matthew Christy, Ricardo Gutierrez-Osuna, Richard Furuta","submitted_at":"2016-01-27T03:24:05Z","abstract_excerpt":"Identifying the type of font (e.g., Roman, Blackletter) used in historical documents can help optical character recognition (OCR) systems produce more accurate text transcriptions. Towards this end, we present an active-learning strategy that can significantly reduce the number of labeled samples needed to train a font classifier. Our approach extracts image-based features that exploit geometric differences between fonts at the word level, and combines them into a bag-of-word representation for each page in a document. We evaluate six sampling strategies based on uncertainty, dissimilarity and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.07252","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":""},"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":"1601.07252","created_at":"2026-05-18T01:21:46.377070+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.07252v1","created_at":"2026-05-18T01:21:46.377070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.07252","created_at":"2026-05-18T01:21:46.377070+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTZ5CRQDDOF2","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTZ5CRQDDOF2J2FQ","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTZ5CRQD","created_at":"2026-05-18T12:30:53.716459+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/YTZ5CRQDDOF2J2FQHL6BKUYULU","json":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU.json","graph_json":"https://pith.science/api/pith-number/YTZ5CRQDDOF2J2FQHL6BKUYULU/graph.json","events_json":"https://pith.science/api/pith-number/YTZ5CRQDDOF2J2FQHL6BKUYULU/events.json","paper":"https://pith.science/paper/YTZ5CRQD"},"agent_actions":{"view_html":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU","download_json":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU.json","view_paper":"https://pith.science/paper/YTZ5CRQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.07252&json=true","fetch_graph":"https://pith.science/api/pith-number/YTZ5CRQDDOF2J2FQHL6BKUYULU/graph.json","fetch_events":"https://pith.science/api/pith-number/YTZ5CRQDDOF2J2FQHL6BKUYULU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU/action/storage_attestation","attest_author":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU/action/author_attestation","sign_citation":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU/action/citation_signature","submit_replication":"https://pith.science/pith/YTZ5CRQDDOF2J2FQHL6BKUYULU/action/replication_record"}},"created_at":"2026-05-18T01:21:46.377070+00:00","updated_at":"2026-05-18T01:21:46.377070+00:00"}