{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PQL7XZF5EG4KDHH7ANEXISGLNR","short_pith_number":"pith:PQL7XZF5","schema_version":"1.0","canonical_sha256":"7c17fbe4bd21b8a19cff03497448cb6c77bfd23620b08b978c11589943bbd486","source":{"kind":"arxiv","id":"2306.17059","version":2},"attestation_state":"computed","paper":{"title":"The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Jina Kim, Leeje Jang, Min Namgung, Yao-Yi Chiang, Yijun Lin, Zekun Li","submitted_at":"2023-06-29T16:05:40Z","abstract_excerpt":"Scanned historical maps in libraries and archives are valuable repositories of geographic data that often do not exist elsewhere. Despite the potential of machine learning tools like the Google Vision APIs for automatically transcribing text from these maps into machine-readable formats, they do not work well with large-sized images (e.g., high-resolution scanned documents), cannot infer the relation between the recognized text and other datasets, and are challenging to integrate with post-processing tools. This paper introduces the mapKurator system, an end-to-end system integrating machine l"},"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":"2306.17059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-29T16:05:40Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"213f4100da7c3a29750f79095fa1eaf9f808c5fecd816c1a2447dae1a8725fba","abstract_canon_sha256":"333f1b4a5a5e5748517bebd77b6341193809cd0e9bd184cb622e67945617f7dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:52.126779Z","signature_b64":"z4leVj5Hiv4Alz9csx0GmxrKPVRcWwNjWrF8g3bEcFJ7qfBgRFWCMLV1YEBcKUJUaJgSsI74KGFGORn5oASYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c17fbe4bd21b8a19cff03497448cb6c77bfd23620b08b978c11589943bbd486","last_reissued_at":"2026-07-05T06:27:52.126342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:52.126342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Jina Kim, Leeje Jang, Min Namgung, Yao-Yi Chiang, Yijun Lin, Zekun Li","submitted_at":"2023-06-29T16:05:40Z","abstract_excerpt":"Scanned historical maps in libraries and archives are valuable repositories of geographic data that often do not exist elsewhere. Despite the potential of machine learning tools like the Google Vision APIs for automatically transcribing text from these maps into machine-readable formats, they do not work well with large-sized images (e.g., high-resolution scanned documents), cannot infer the relation between the recognized text and other datasets, and are challenging to integrate with post-processing tools. This paper introduces the mapKurator system, an end-to-end system integrating machine l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17059","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/2306.17059/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":"2306.17059","created_at":"2026-07-05T06:27:52.126393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17059v2","created_at":"2026-07-05T06:27:52.126393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17059","created_at":"2026-07-05T06:27:52.126393+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQL7XZF5EG4K","created_at":"2026-07-05T06:27:52.126393+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQL7XZF5EG4KDHH7","created_at":"2026-07-05T06:27:52.126393+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQL7XZF5","created_at":"2026-07-05T06:27:52.126393+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/PQL7XZF5EG4KDHH7ANEXISGLNR","json":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR.json","graph_json":"https://pith.science/api/pith-number/PQL7XZF5EG4KDHH7ANEXISGLNR/graph.json","events_json":"https://pith.science/api/pith-number/PQL7XZF5EG4KDHH7ANEXISGLNR/events.json","paper":"https://pith.science/paper/PQL7XZF5"},"agent_actions":{"view_html":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR","download_json":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR.json","view_paper":"https://pith.science/paper/PQL7XZF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17059&json=true","fetch_graph":"https://pith.science/api/pith-number/PQL7XZF5EG4KDHH7ANEXISGLNR/graph.json","fetch_events":"https://pith.science/api/pith-number/PQL7XZF5EG4KDHH7ANEXISGLNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR/action/storage_attestation","attest_author":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR/action/author_attestation","sign_citation":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR/action/citation_signature","submit_replication":"https://pith.science/pith/PQL7XZF5EG4KDHH7ANEXISGLNR/action/replication_record"}},"created_at":"2026-07-05T06:27:52.126393+00:00","updated_at":"2026-07-05T06:27:52.126393+00:00"}