{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PKBOEBASDB2476KA2SVQDKASIA","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":"e8edabad2e522b6afd616b3a15e9267849e06cc0e2f6482119c7bb0c720827d9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T10:52:52Z","title_canon_sha256":"8cc0bb13e0db60e6b28198a90177563f155f8bc619bb90ee1f1dc7e14633f048"},"schema_version":"1.0","source":{"id":"2506.01535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01535","created_at":"2026-07-05T11:14:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01535v1","created_at":"2026-07-05T11:14:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01535","created_at":"2026-07-05T11:14:15Z"},{"alias_kind":"pith_short_12","alias_value":"PKBOEBASDB24","created_at":"2026-07-05T11:14:15Z"},{"alias_kind":"pith_short_16","alias_value":"PKBOEBASDB2476KA","created_at":"2026-07-05T11:14:15Z"},{"alias_kind":"pith_short_8","alias_value":"PKBOEBAS","created_at":"2026-07-05T11:14:15Z"}],"graph_snapshots":[{"event_id":"sha256:9c28ff58d13da7013c7c481fd42c120d665974d68547a8168c21d8e7a421de88","target":"graph","created_at":"2026-07-05T11:14:15Z","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/2506.01535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual vocabulary transfer plays a promising role in adapting pre-trained language models to new languages, including low-resource languages. Existing approaches that utilize monolingual or parallel corpora face challenges when applied to languages with limited resources. In this work, we propose a simple yet effective vocabulary transfer method that utilizes bilingual dictionaries, which are available for many languages, thanks to descriptive linguists. Our proposed method leverages a property of BPE tokenizers where removing a subword from the vocabulary causes a fallback to shorter s","authors_text":"Haruki Sakajo, Hidetaka Kamigaito, Justin Vasselli, Taro Watanabe, Yingtao Tian, Yusuke Ide, Yusuke Sakai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T10:52:52Z","title":"Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01535","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:a171f9f7ea2c98d03c78d6f2a9e0d539c9e012f6b6520f759253a9dbd9c0bfa3","target":"record","created_at":"2026-07-05T11:14:15Z","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":"e8edabad2e522b6afd616b3a15e9267849e06cc0e2f6482119c7bb0c720827d9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T10:52:52Z","title_canon_sha256":"8cc0bb13e0db60e6b28198a90177563f155f8bc619bb90ee1f1dc7e14633f048"},"schema_version":"1.0","source":{"id":"2506.01535","kind":"arxiv","version":1}},"canonical_sha256":"7a82e204121875cff940d4ab01a8124022226b924cc1424b5adf2cf143f6ec7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a82e204121875cff940d4ab01a8124022226b924cc1424b5adf2cf143f6ec7a","first_computed_at":"2026-07-05T11:14:15.289490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:15.289490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"byXa3Llrwc/NNCXUSAxno6xVkfqCrZSre2qxPHdylW1Hgyp5mmb/H1c2Rg8yUi+iTW74vf2fsNBYo+Elv+z5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:15.289936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a171f9f7ea2c98d03c78d6f2a9e0d539c9e012f6b6520f759253a9dbd9c0bfa3","sha256:9c28ff58d13da7013c7c481fd42c120d665974d68547a8168c21d8e7a421de88"],"state_sha256":"4548fdac282a35e36eb13ef3a76a658e1ac5acff81990c349d789ba4ce0e0f01"}