{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F3A36Y6MKAWKLSPWYSXI3JKWKG","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":"196b9969649ad56e4d746911a5fa96b783a2b22a61d7d49e428e875f2167d53f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T20:06:43Z","title_canon_sha256":"834b4d8f40250e8610c42c714482a39a1df8e4d8ab7154af1b2339c11a85dbc6"},"schema_version":"1.0","source":{"id":"2605.30529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30529","created_at":"2026-06-01T01:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30529v1","created_at":"2026-06-01T01:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30529","created_at":"2026-06-01T01:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"F3A36Y6MKAWK","created_at":"2026-06-01T01:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"F3A36Y6MKAWKLSPW","created_at":"2026-06-01T01:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"F3A36Y6M","created_at":"2026-06-01T01:02:59Z"}],"graph_snapshots":[{"event_id":"sha256:535e0a0962a809ffdca0c37ccf3f616bbdd474d0929329710bda675117ff4745","target":"graph","created_at":"2026-06-01T01:02:59Z","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/2605.30529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Rey-Blanco, Roberto Cruz","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T20:06:43Z","title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30529","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":"sha256:02904cd05c9c1b7f4ebbdee3f233148066bae5e70240ff478ff9c14ceebe21de","target":"record","created_at":"2026-06-01T01:02:59Z","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":"196b9969649ad56e4d746911a5fa96b783a2b22a61d7d49e428e875f2167d53f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T20:06:43Z","title_canon_sha256":"834b4d8f40250e8610c42c714482a39a1df8e4d8ab7154af1b2339c11a85dbc6"},"schema_version":"1.0","source":{"id":"2605.30529","kind":"arxiv","version":1}},"canonical_sha256":"2ec1bf63cc502ca5c9f6c4ae8da55651bd218cd6f55c30b2fa3c6899ab017c74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ec1bf63cc502ca5c9f6c4ae8da55651bd218cd6f55c30b2fa3c6899ab017c74","first_computed_at":"2026-06-01T01:02:59.350028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:59.350028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bUdoRFyP/v9tnheeQ3u5cBDZ1SLtgz3j2CvKyp3ZLjT5JNIiYKvYmt2bn4fAWi6JDuOJV966X5caxizIRtqpDA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:59.350908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02904cd05c9c1b7f4ebbdee3f233148066bae5e70240ff478ff9c14ceebe21de","sha256:535e0a0962a809ffdca0c37ccf3f616bbdd474d0929329710bda675117ff4745"],"state_sha256":"ff840b25f8d7bfdb981807632836c13b65431fd5a7586685d72fde237973bd9e"}