{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_49404e187ff60e6aa43677036f03b70408144ed4e3bae765c9c64e3dcfe2a3cc","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_49404e187ff60e6aa43677036f03b70408144ed4e3bae765c9c64e3dcfe2a3cc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ee89848c383b7fb77cdb9f2020f1204d03a5dfbdfca34ff44eb4549a239ebf68","published":"Mon, 01 Jun 2026 00:00:00 -0400","receipt_hash":"ee89848c383b7fb77cdb9f2020f1204d03a5dfbdfca34ff44eb4549a239ebf68","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"ee89848c383b7fb77cdb9f2020f1204d03a5dfbdfca34ff44eb4549a239ebf68","observed_at":"2026-06-01T04:43:13.859018Z","parent_run_hash":"8993bbc535dae8c9669e099af3624cb39166b8d9bbfd66f26ae5c338cbb21be2","published":"Mon, 01 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.30529v1 Announce Type: cross \nAbstract: 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, Catalan, Italian, Portuguese and French, and evaluate against BioBERT-ST and the un-tuned Spanish encoder. The bi-encoder alone matches BioBERT-ST on MRR (0.876 vs. 0.866) and overtakes it on R@3 (0.650 vs. 0.626) and R@5 (0.804 vs. 0.790) without English biomedical pretraining. Adding a cross-encoder reranker lifts aggregate R@5 to 0.822 and dominat","title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","url":"https://arxiv.org/abs/2605.30529","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.30529v1 Announce Type: cross \nAbstract: 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, Catalan, Italian, Portuguese and French, and evaluate against BioBERT-ST and the un-tuned Spanish encoder. The bi-encoder alone matches BioBERT-ST on MRR (0.876 vs. 0.866) and overtakes it on R@3 (0.650 vs. 0.626) and R@5 (0.804 vs. 0.790) without English biomedical pretraining. Adding a cross-encoder reranker lifts aggregate R@5 to 0.822 and dominat","title":"Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-01T04:43:13Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.30529"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:0bbc5507f9d60099495bed28ef18bddfcff3bebd97db65c1f71235766de75999ff655f1c6c265a16f3f520905d0754380273d12c18ffc82ff5a6652c59969508","signer":"crovia.substrate","subject":{"observed_at":"2026-06-01T04:43:13Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.30529"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"0b3e3d2d3f340e8ff76c75ff2689ef9392b4f781ee2f2cd8aa5d8861f5434084","leaf_index":163834,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"96d51455aba8fb81918d0b75c84169ba608e3e0d59da2e33a99e5907b69f949c","side":"right"},{"sibling":"f52aa09224c44056dccc340c319bedda3c26a18468f5a63e748bedde6420c316","side":"left"},{"sibling":"a8d133c018ff56286d62032801c18d875e519df7e53f7f68f0bd67ca98ac2162","side":"right"},{"sibling":"3768a10bc566886e5d4e900a7bdb7aa03041e2fdbf823ddcd6029c3d1aa2752a","side":"left"},{"sibling":"4d05c1d10ce177e734550afbe0158142b54cf93075855777c739ec460dad2756","side":"left"},{"sibling":"a8f314233e57d9b2e1f73a238db7bf336c4b3b1673499ca02aeae9337c8cb49b","side":"left"},{"sibling":"6f506d4e4c7fb170ea5ab20efffbcbb69464bf6db4cde5e90925fede53e31584","side":"left"},{"sibling":"764e4312cdb701ef8613acdc2311e1724d6a379f21c70c30ed832e7ede3d2d33","side":"left"},{"sibling":"5a0517e6c348bc5a70f1aef04c1415d23980c712e375838fff54dfa281f98760","side":"left"},{"sibling":"d6986f4b6a5bd07cba1de43f660d527af780ad1465d0f4af5f137bd514e95f7e","side":"left"},{"sibling":"aff54f89d4445cf32bb05b2ece532d190200cb92524489ddfa648b5cc36e21a4","side":"left"},{"sibling":"f028fad1771bff7dceff3a83baf90249f4eb410ebedfe92dda1bb2b89d7093c8","side":"left"},{"sibling":"59c6490072e8a1d357ece10bb08d7f449a3acbae58e130e3e7469cbea0314c65","side":"left"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"c9ac00eed8c475f1e525869bb329af03d052181b19ff8234edefe12f6ecec154","side":"right"},{"sibling":"ce41d9b82f34b16efd653dfb3552acc4e2512939e47903e5fc979fbed00c5764","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":164217,"merkle_root":"a1098816aea1b60b8fe37b62410469bc5024a2c335bbec4f6ef2add7875dbdf2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260601T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-01T05:37:41Z","sig_algorithm":"ed25519","signature":"d7f91db1d54b9495c499440c2828f4bd53360555391ce6e25adea5183bc1fa0f697d80708a099d0b0429e6f8cb6c71e7fccf82acb3c84481149974fb26074708","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_49404e187ff60e6aa43677036f03b70408144ed4e3bae765c9c64e3dcfe2a3cc"}}