{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F3A36Y6MKAWKLSPWYSXI3JKWKG","short_pith_number":"pith:F3A36Y6M","schema_version":"1.0","canonical_sha256":"2ec1bf63cc502ca5c9f6c4ae8da55651bd218cd6f55c30b2fa3c6899ab017c74","source":{"kind":"arxiv","id":"2605.30529","version":1},"attestation_state":"computed","paper":{"title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Rey-Blanco, Roberto Cruz","submitted_at":"2026-05-28T20:06:43Z","abstract_excerpt":"Sentence-embedding models for semantic search are overwhelmingly developed and evaluated on English corpora. When applied to clinical retrieval in other languages -- particularly retrieval of ICD-10-CM / CIE-10 codes -- recall degrades in ways often masked by aggregate benchmarks. We study whether large generative language models can serve as data factories to close this gap. We build a two-stage retriever (bi-encoder followed by cross-encoder reranker), fine-tuned from a Spanish biomedical encoder (PlanTL-GOB-ES/bsc-bio-ehr-es) on Gemini-generated synthetic data covering English, Spanish, Cat"},"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":"2605.30529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T20:06:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"834b4d8f40250e8610c42c714482a39a1df8e4d8ab7154af1b2339c11a85dbc6","abstract_canon_sha256":"196b9969649ad56e4d746911a5fa96b783a2b22a61d7d49e428e875f2167d53f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:59.350908Z","signature_b64":"bUdoRFyP/v9tnheeQ3u5cBDZ1SLtgz3j2CvKyp3ZLjT5JNIiYKvYmt2bn4fAWi6JDuOJV966X5caxizIRtqpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec1bf63cc502ca5c9f6c4ae8da55651bd218cd6f55c30b2fa3c6899ab017c74","last_reissued_at":"2026-06-01T01:02:59.350028Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:59.350028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Rey-Blanco, Roberto Cruz","submitted_at":"2026-05-28T20:06:43Z","abstract_excerpt":"Sentence-embedding models for semantic search are overwhelmingly developed and evaluated on English corpora. When applied to clinical retrieval in other languages -- particularly retrieval of ICD-10-CM / CIE-10 codes -- recall degrades in ways often masked by aggregate benchmarks. We study whether large generative language models can serve as data factories to close this gap. We build a two-stage retriever (bi-encoder followed by cross-encoder reranker), fine-tuned from a Spanish biomedical encoder (PlanTL-GOB-ES/bsc-bio-ehr-es) on Gemini-generated synthetic data covering English, Spanish, Cat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30529","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/2605.30529/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":"2605.30529","created_at":"2026-06-01T01:02:59.350181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30529v1","created_at":"2026-06-01T01:02:59.350181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30529","created_at":"2026-06-01T01:02:59.350181+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3A36Y6MKAWK","created_at":"2026-06-01T01:02:59.350181+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3A36Y6MKAWKLSPW","created_at":"2026-06-01T01:02:59.350181+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3A36Y6M","created_at":"2026-06-01T01:02:59.350181+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/F3A36Y6MKAWKLSPWYSXI3JKWKG","json":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG.json","graph_json":"https://pith.science/api/pith-number/F3A36Y6MKAWKLSPWYSXI3JKWKG/graph.json","events_json":"https://pith.science/api/pith-number/F3A36Y6MKAWKLSPWYSXI3JKWKG/events.json","paper":"https://pith.science/paper/F3A36Y6M"},"agent_actions":{"view_html":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG","download_json":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG.json","view_paper":"https://pith.science/paper/F3A36Y6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30529&json=true","fetch_graph":"https://pith.science/api/pith-number/F3A36Y6MKAWKLSPWYSXI3JKWKG/graph.json","fetch_events":"https://pith.science/api/pith-number/F3A36Y6MKAWKLSPWYSXI3JKWKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG/action/storage_attestation","attest_author":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG/action/author_attestation","sign_citation":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG/action/citation_signature","submit_replication":"https://pith.science/pith/F3A36Y6MKAWKLSPWYSXI3JKWKG/action/replication_record"}},"created_at":"2026-06-01T01:02:59.350181+00:00","updated_at":"2026-06-01T01:02:59.350181+00:00"}