{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JQAWCYGOS7J7KN6BTMD52IIOYG","short_pith_number":"pith:JQAWCYGO","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"},"canonical_sha256":"4c016160ce97d3f537c19b07dd210ec190322a0ab8280042ef8892e58ba5b5f4","source":{"kind":"arxiv","id":"2606.09435","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09435","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09435v1","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09435","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"JQAWCYGOS7J7","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"JQAWCYGOS7J7KN6B","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"JQAWCYGO","created_at":"2026-06-09T02:08:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JQAWCYGOS7J7KN6BTMD52IIOYG","target":"record","payload":{"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"},"canonical_sha256":"4c016160ce97d3f537c19b07dd210ec190322a0ab8280042ef8892e58ba5b5f4","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"},"source_kind":"arxiv","source_id":"2606.09435","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nk/XNTGCGAYIGUDowiNgiOCF+xrl0sUkr3H5Lpy/NObbok9MRoj/hCqKhkUQgIdTNHSSQzmi3/5KYYstWcPUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:55:22.510351Z"},"content_sha256":"bbd985cc5b495a16dfed2010ba9163ed6da189cb70e214b27fa1be4c9bc3a6d4","schema_version":"1.0","event_id":"sha256:bbd985cc5b495a16dfed2010ba9163ed6da189cb70e214b27fa1be4c9bc3a6d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JQAWCYGOS7J7KN6BTMD52IIOYG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yikWmMjUP/x0MJWq0xtDsB5jrZXLSJOTNVyeSxXa+RF3zZfjPwk3x77uS/39F/QaDrGrNW3tgik4+JEjH2jVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:55:22.510723Z"},"content_sha256":"d0043c8d2b352fd02d1ea6c3f3a52808c69886ae9d47a90a2035b2a639ff8268","schema_version":"1.0","event_id":"sha256:d0043c8d2b352fd02d1ea6c3f3a52808c69886ae9d47a90a2035b2a639ff8268"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/bundle.json","state_url":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T04:55:22Z","links":{"resolver":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG","bundle":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/bundle.json","state":"https://pith.science/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQAWCYGOS7J7KN6BTMD52IIOYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JQAWCYGOS7J7KN6BTMD52IIOYG","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":"cff1f64cb3677b9d5a87975d0fc6d8aeaceb3b8476af1659157a7c25dd9e78c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:44:47Z","title_canon_sha256":"3d9da880fed746628e9893ffa57a19d84a633709b01f7d1b41c6a2249f8161fa"},"schema_version":"1.0","source":{"id":"2606.09435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09435","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09435v1","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09435","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"JQAWCYGOS7J7","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"JQAWCYGOS7J7KN6B","created_at":"2026-06-09T02:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"JQAWCYGO","created_at":"2026-06-09T02:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:d0043c8d2b352fd02d1ea6c3f3a52808c69886ae9d47a90a2035b2a639ff8268","target":"graph","created_at":"2026-06-09T02:08:48Z","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/2606.09435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aso Mahmudi, David Setiawan, Ekaterina Vylomova, Milind Agarwal, Pagnarith Pit, Temuulen Khishigsuren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:44:47Z","title":"MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09435","kind":"arxiv","version":1},"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:bbd985cc5b495a16dfed2010ba9163ed6da189cb70e214b27fa1be4c9bc3a6d4","target":"record","created_at":"2026-06-09T02:08:48Z","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":"cff1f64cb3677b9d5a87975d0fc6d8aeaceb3b8476af1659157a7c25dd9e78c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:44:47Z","title_canon_sha256":"3d9da880fed746628e9893ffa57a19d84a633709b01f7d1b41c6a2249f8161fa"},"schema_version":"1.0","source":{"id":"2606.09435","kind":"arxiv","version":1}},"canonical_sha256":"4c016160ce97d3f537c19b07dd210ec190322a0ab8280042ef8892e58ba5b5f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c016160ce97d3f537c19b07dd210ec190322a0ab8280042ef8892e58ba5b5f4","first_computed_at":"2026-06-09T02:08:48.392117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:48.392117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"alFtGEMGRJoWwkZKCS023XKJazkt8UrPJxBSToxOILP9fKzuZZ+VstrRDH9PyZeZcsS+XYk5D3golH9xszoKDw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:48.392965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd985cc5b495a16dfed2010ba9163ed6da189cb70e214b27fa1be4c9bc3a6d4","sha256:d0043c8d2b352fd02d1ea6c3f3a52808c69886ae9d47a90a2035b2a639ff8268"],"state_sha256":"e1a996754602e338c8dc790a543b7c187977faaac3b009954ee82de8313f59d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fpztYZfATa7tWsMrk0DP0pd9cGNBTE66Kg6M9LzKH4cPQuOJJiB38NcSFZbQWqjg6vM50O2mFm13rA75awV4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T04:55:22.512692Z","bundle_sha256":"5c5b4badc5a310e9eb58f58cd188ab074af62fee8ff755f24b6743bdb48fe5d7"}}