{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5TUE2U7RFSCIASW45J5T5AF4FL","short_pith_number":"pith:5TUE2U7R","schema_version":"1.0","canonical_sha256":"ece84d53f12c84804adcea7b3e80bc2ac1246a5dff869522a07a8bbfb429cc18","source":{"kind":"arxiv","id":"2605.24310","version":1},"attestation_state":"computed","paper":{"title":"Discovering Lexical Gaps Using Embeddings from Multilingual LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron S. Cohen, Benjamin K. Bergen, Yoonwon Jung","submitted_at":"2026-05-23T00:36:53Z","abstract_excerpt":"Lexical gaps are words that do not exist in certain languages. They pose challenges for building multilingual lexical resources, for machine translation, and for cross-lingual transfer. Existing lexical gap detection relies on human judgments or fixed conceptual taxonomies. We propose a data-driven framework for identifying cross-lingual lexical gaps. We extracted contextualized embeddings from Korean-English bilingual LLMs for Korean-to-English and English-to-Korean translation pairs. Combinations of LLMs, embedding types, dimensionality, and orthogonal transformations across 100 train-test s"},"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":"2605.24310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T00:36:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"311095f561f1f0feca7a1bc2f02e7556faad6dd39844ba53376880dcc15eddbc","abstract_canon_sha256":"3ade18ddddac8fdf39eae75185a2303980bbec754334d17c9f33fe8af16786be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:59.118044Z","signature_b64":"N4rA1gKgCdRuz5bLcFnPvWXn3KIseJDqOvI+Diaoa4aXZebDFl2Dt6faQRIDt8+e9boYi1v/ZarxsYWSuvDCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ece84d53f12c84804adcea7b3e80bc2ac1246a5dff869522a07a8bbfb429cc18","last_reissued_at":"2026-05-26T01:02:59.117080Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:59.117080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Lexical Gaps Using Embeddings from Multilingual LLMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron S. Cohen, Benjamin K. Bergen, Yoonwon Jung","submitted_at":"2026-05-23T00:36:53Z","abstract_excerpt":"Lexical gaps are words that do not exist in certain languages. They pose challenges for building multilingual lexical resources, for machine translation, and for cross-lingual transfer. Existing lexical gap detection relies on human judgments or fixed conceptual taxonomies. We propose a data-driven framework for identifying cross-lingual lexical gaps. We extracted contextualized embeddings from Korean-English bilingual LLMs for Korean-to-English and English-to-Korean translation pairs. Combinations of LLMs, embedding types, dimensionality, and orthogonal transformations across 100 train-test s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24310","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/2605.24310/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":"2605.24310","created_at":"2026-05-26T01:02:59.117196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24310v1","created_at":"2026-05-26T01:02:59.117196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24310","created_at":"2026-05-26T01:02:59.117196+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TUE2U7RFSCI","created_at":"2026-05-26T01:02:59.117196+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TUE2U7RFSCIASW4","created_at":"2026-05-26T01:02:59.117196+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TUE2U7R","created_at":"2026-05-26T01:02:59.117196+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/5TUE2U7RFSCIASW45J5T5AF4FL","json":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL.json","graph_json":"https://pith.science/api/pith-number/5TUE2U7RFSCIASW45J5T5AF4FL/graph.json","events_json":"https://pith.science/api/pith-number/5TUE2U7RFSCIASW45J5T5AF4FL/events.json","paper":"https://pith.science/paper/5TUE2U7R"},"agent_actions":{"view_html":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL","download_json":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL.json","view_paper":"https://pith.science/paper/5TUE2U7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24310&json=true","fetch_graph":"https://pith.science/api/pith-number/5TUE2U7RFSCIASW45J5T5AF4FL/graph.json","fetch_events":"https://pith.science/api/pith-number/5TUE2U7RFSCIASW45J5T5AF4FL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/action/storage_attestation","attest_author":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/action/author_attestation","sign_citation":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/action/citation_signature","submit_replication":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/action/replication_record"}},"created_at":"2026-05-26T01:02:59.117196+00:00","updated_at":"2026-05-26T01:02:59.117196+00:00"}