{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5TUE2U7RFSCIASW45J5T5AF4FL","short_pith_number":"pith:5TUE2U7R","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"},"canonical_sha256":"ece84d53f12c84804adcea7b3e80bc2ac1246a5dff869522a07a8bbfb429cc18","source":{"kind":"arxiv","id":"2605.24310","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24310","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24310v1","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24310","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"5TUE2U7RFSCI","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"5TUE2U7RFSCIASW4","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"5TUE2U7R","created_at":"2026-05-26T01:02:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5TUE2U7RFSCIASW45J5T5AF4FL","target":"record","payload":{"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"},"canonical_sha256":"ece84d53f12c84804adcea7b3e80bc2ac1246a5dff869522a07a8bbfb429cc18","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"},"source_kind":"arxiv","source_id":"2605.24310","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":"2026-05-26T01:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bV1ZVdbhWuC9TDB+lISZZjbYyjzn2LhHd38R9qspOOnrrqXwmJHNWnE6ZQWWU47wgxPHYJzBQJRVUAs97oYWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:11:46.628426Z"},"content_sha256":"c4f591d095ee7c98c21e96e083c26c9452d01b8285a48d8a0e3fd7393b47c0f4","schema_version":"1.0","event_id":"sha256:c4f591d095ee7c98c21e96e083c26c9452d01b8285a48d8a0e3fd7393b47c0f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5TUE2U7RFSCIASW45J5T5AF4FL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kkl38z9vHP4P2UZryvjSv6jccdmjt2fjj2ls5wIsvmvHrf01HayGjxgdhmSwkq3RhTUxHLq832HyowQhPSq5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:11:46.628817Z"},"content_sha256":"0ec7c8a2c4d1dce40c584fd836c65b0e429fb6ed9be552a4cb4d0359cc98f8ba","schema_version":"1.0","event_id":"sha256:0ec7c8a2c4d1dce40c584fd836c65b0e429fb6ed9be552a4cb4d0359cc98f8ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/bundle.json","state_url":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TUE2U7RFSCIASW45J5T5AF4FL/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":"2026-06-10T18:11:46Z","links":{"resolver":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL","bundle":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/bundle.json","state":"https://pith.science/pith/5TUE2U7RFSCIASW45J5T5AF4FL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TUE2U7RFSCIASW45J5T5AF4FL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5TUE2U7RFSCIASW45J5T5AF4FL","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":"3ade18ddddac8fdf39eae75185a2303980bbec754334d17c9f33fe8af16786be","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T00:36:53Z","title_canon_sha256":"311095f561f1f0feca7a1bc2f02e7556faad6dd39844ba53376880dcc15eddbc"},"schema_version":"1.0","source":{"id":"2605.24310","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24310","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24310v1","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24310","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"5TUE2U7RFSCI","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"5TUE2U7RFSCIASW4","created_at":"2026-05-26T01:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"5TUE2U7R","created_at":"2026-05-26T01:02:59Z"}],"graph_snapshots":[{"event_id":"sha256:0ec7c8a2c4d1dce40c584fd836c65b0e429fb6ed9be552a4cb4d0359cc98f8ba","target":"graph","created_at":"2026-05-26T01:02:59Z","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/2605.24310/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aaron S. Cohen, Benjamin K. Bergen, Yoonwon Jung","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T00:36:53Z","title":"Discovering Lexical Gaps Using Embeddings from Multilingual LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24310","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:c4f591d095ee7c98c21e96e083c26c9452d01b8285a48d8a0e3fd7393b47c0f4","target":"record","created_at":"2026-05-26T01:02:59Z","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":"3ade18ddddac8fdf39eae75185a2303980bbec754334d17c9f33fe8af16786be","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T00:36:53Z","title_canon_sha256":"311095f561f1f0feca7a1bc2f02e7556faad6dd39844ba53376880dcc15eddbc"},"schema_version":"1.0","source":{"id":"2605.24310","kind":"arxiv","version":1}},"canonical_sha256":"ece84d53f12c84804adcea7b3e80bc2ac1246a5dff869522a07a8bbfb429cc18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ece84d53f12c84804adcea7b3e80bc2ac1246a5dff869522a07a8bbfb429cc18","first_computed_at":"2026-05-26T01:02:59.117080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:59.117080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N4rA1gKgCdRuz5bLcFnPvWXn3KIseJDqOvI+Diaoa4aXZebDFl2Dt6faQRIDt8+e9boYi1v/ZarxsYWSuvDCCw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:59.118044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24310","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4f591d095ee7c98c21e96e083c26c9452d01b8285a48d8a0e3fd7393b47c0f4","sha256:0ec7c8a2c4d1dce40c584fd836c65b0e429fb6ed9be552a4cb4d0359cc98f8ba"],"state_sha256":"6a8cc5c5febeb5d92d5ac5f22c822698521fb1f2da99b4d5eccf5a04b617cc6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mahAX8YVJ5G+ud5Sk1nmccPvjoeOAK+U8vMAyfoe8tGxrmis1l07ponDVMx6poA67a2gwZjqALTNkzwfKcucDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T18:11:46.630899Z","bundle_sha256":"013879865d6a0b40bc17447de7c2fe1ac682924f5295db6ac56a068bb68f4424"}}