{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CF26R2AQCERWWZNHQN3RBNPA5K","short_pith_number":"pith:CF26R2AQ","schema_version":"1.0","canonical_sha256":"1175e8e81011236b65a7837710b5e0ea9c986d9c3ef463bb6ce26c63e0b9c1a9","source":{"kind":"arxiv","id":"2410.03182","version":2},"attestation_state":"computed","paper":{"title":"Generating bilingual example sentences with large language models as lexicography assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ekaterina Vylomova, Kemal Kurniawan, Raphael Merx","submitted_at":"2024-10-04T06:45:48Z","abstract_excerpt":"We present a study of LLMs' performance in generating and rating example sentences for bilingual dictionaries across languages with varying resource levels: French (high-resource), Indonesian (mid-resource), and Tetun (low-resource), with English as the target language. We evaluate the quality of LLM-generated examples against the GDEX (Good Dictionary EXample) criteria: typicality, informativeness, and intelligibility. Our findings reveal that while LLMs can generate reasonably good dictionary examples, their performance degrades significantly for lower-resourced languages. We also observe hi"},"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":"2410.03182","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T06:45:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73555a96dc470f80bf9c594ab456cf9d3a4673db2f8f9edbd84ec088cfb01466","abstract_canon_sha256":"263865a44cc2224dad207650eb8046ce3b55637b3f56f2655dd36a0fb3918b2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:30.270980Z","signature_b64":"tumbMy/i2fZkgRZ1TXOoBDa5435p4y8HE8/nhkb7dRKhIrQkhM6oTWjt4A/XYjQqkeyEJn+hl7AUX5pZNZ5KCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1175e8e81011236b65a7837710b5e0ea9c986d9c3ef463bb6ce26c63e0b9c1a9","last_reissued_at":"2026-07-05T09:38:30.270484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:30.270484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating bilingual example sentences with large language models as lexicography assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ekaterina Vylomova, Kemal Kurniawan, Raphael Merx","submitted_at":"2024-10-04T06:45:48Z","abstract_excerpt":"We present a study of LLMs' performance in generating and rating example sentences for bilingual dictionaries across languages with varying resource levels: French (high-resource), Indonesian (mid-resource), and Tetun (low-resource), with English as the target language. We evaluate the quality of LLM-generated examples against the GDEX (Good Dictionary EXample) criteria: typicality, informativeness, and intelligibility. Our findings reveal that while LLMs can generate reasonably good dictionary examples, their performance degrades significantly for lower-resourced languages. We also observe hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03182","kind":"arxiv","version":2},"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/2410.03182/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":"2410.03182","created_at":"2026-07-05T09:38:30.270547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03182v2","created_at":"2026-07-05T09:38:30.270547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03182","created_at":"2026-07-05T09:38:30.270547+00:00"},{"alias_kind":"pith_short_12","alias_value":"CF26R2AQCERW","created_at":"2026-07-05T09:38:30.270547+00:00"},{"alias_kind":"pith_short_16","alias_value":"CF26R2AQCERWWZNH","created_at":"2026-07-05T09:38:30.270547+00:00"},{"alias_kind":"pith_short_8","alias_value":"CF26R2AQ","created_at":"2026-07-05T09:38:30.270547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23996","citing_title":"Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K","json":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K.json","graph_json":"https://pith.science/api/pith-number/CF26R2AQCERWWZNHQN3RBNPA5K/graph.json","events_json":"https://pith.science/api/pith-number/CF26R2AQCERWWZNHQN3RBNPA5K/events.json","paper":"https://pith.science/paper/CF26R2AQ"},"agent_actions":{"view_html":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K","download_json":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K.json","view_paper":"https://pith.science/paper/CF26R2AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03182&json=true","fetch_graph":"https://pith.science/api/pith-number/CF26R2AQCERWWZNHQN3RBNPA5K/graph.json","fetch_events":"https://pith.science/api/pith-number/CF26R2AQCERWWZNHQN3RBNPA5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K/action/storage_attestation","attest_author":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K/action/author_attestation","sign_citation":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K/action/citation_signature","submit_replication":"https://pith.science/pith/CF26R2AQCERWWZNHQN3RBNPA5K/action/replication_record"}},"created_at":"2026-07-05T09:38:30.270547+00:00","updated_at":"2026-07-05T09:38:30.270547+00:00"}