{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JQAWCYGOS7J7KN6BTMD52IIOYG","short_pith_number":"pith:JQAWCYGO","schema_version":"1.0","canonical_sha256":"4c016160ce97d3f537c19b07dd210ec190322a0ab8280042ef8892e58ba5b5f4","source":{"kind":"arxiv","id":"2606.09435","version":1},"attestation_state":"computed","paper":{"title":"MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aso Mahmudi, David Setiawan, Ekaterina Vylomova, Milind Agarwal, Pagnarith Pit, Temuulen Khishigsuren","submitted_at":"2026-06-08T12:44:47Z","abstract_excerpt":"Multilingual dictionaries are among the most valuable documentary resources for low-resource and endangered languages, yet many remain available only as scans. For many decades, their digitization and conversion into a machine-readable format was nearly impossible due to language-specific scripts, complex multi-column layouts full of entries with abbreviations and cross-references. Recent vision-language models offer a promising solution, but it is unclear how well they preserve characters, markup, and process lexicographic structure. We introduce MUDIDI, a two-stage framework for multi-lingua"},"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":"2606.09435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:44:47Z","cross_cats_sorted":[],"title_canon_sha256":"3d9da880fed746628e9893ffa57a19d84a633709b01f7d1b41c6a2249f8161fa","abstract_canon_sha256":"cff1f64cb3677b9d5a87975d0fc6d8aeaceb3b8476af1659157a7c25dd9e78c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:48.392965Z","signature_b64":"alFtGEMGRJoWwkZKCS023XKJazkt8UrPJxBSToxOILP9fKzuZZ+VstrRDH9PyZeZcsS+XYk5D3golH9xszoKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c016160ce97d3f537c19b07dd210ec190322a0ab8280042ef8892e58ba5b5f4","last_reissued_at":"2026-06-09T02:08:48.392117Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:48.392117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aso Mahmudi, David Setiawan, Ekaterina Vylomova, Milind Agarwal, Pagnarith Pit, Temuulen Khishigsuren","submitted_at":"2026-06-08T12:44:47Z","abstract_excerpt":"Multilingual dictionaries are among the most valuable documentary resources for low-resource and endangered languages, yet many remain available only as scans. For many decades, their digitization and conversion into a machine-readable format was nearly impossible due to language-specific scripts, complex multi-column layouts full of entries with abbreviations and cross-references. Recent vision-language models offer a promising solution, but it is unclear how well they preserve characters, markup, and process lexicographic structure. We introduce MUDIDI, a two-stage framework for multi-lingua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09435","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/2606.09435/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":"2606.09435","created_at":"2026-06-09T02:08:48.392254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09435v1","created_at":"2026-06-09T02:08:48.392254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09435","created_at":"2026-06-09T02:08:48.392254+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQAWCYGOS7J7","created_at":"2026-06-09T02:08:48.392254+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQAWCYGOS7J7KN6B","created_at":"2026-06-09T02:08:48.392254+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQAWCYGO","created_at":"2026-06-09T02:08:48.392254+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/JQAWCYGOS7J7KN6BTMD52IIOYG","json":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG.json","graph_json":"https://pith.science/api/pith-number/JQAWCYGOS7J7KN6BTMD52IIOYG/graph.json","events_json":"https://pith.science/api/pith-number/JQAWCYGOS7J7KN6BTMD52IIOYG/events.json","paper":"https://pith.science/paper/JQAWCYGO"},"agent_actions":{"view_html":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG","download_json":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG.json","view_paper":"https://pith.science/paper/JQAWCYGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09435&json=true","fetch_graph":"https://pith.science/api/pith-number/JQAWCYGOS7J7KN6BTMD52IIOYG/graph.json","fetch_events":"https://pith.science/api/pith-number/JQAWCYGOS7J7KN6BTMD52IIOYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/action/storage_attestation","attest_author":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/action/author_attestation","sign_citation":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/action/citation_signature","submit_replication":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/action/replication_record"}},"created_at":"2026-06-09T02:08:48.392254+00:00","updated_at":"2026-06-09T02:08:48.392254+00:00"}