{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.17339", "kind": "paper", "url": "https://arxiv.org/abs/2606.17339"}], "authors": ["Sejal Bhalla", "Larry Kieu", "Aina Merchant", "Eyal de Lara", "Alex Mariakakis"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.17339", "source_url": "https://arxiv.org/abs/2606.17339"}, "categories": ["Biology & Drug Discovery", "Speech & Audio", "cs.AI"], "description": {"en": "SpeechDx evaluates clinical speech AI across 12 datasets and 27 tasks covering various conditions, structured by speech production stages. Scoring includes classification accuracy and zero-shot transfer performance."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.17339", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.17339", "title": "SpeechDx"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Toronto"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.17339", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.17339", "source_url": "https://openalex.org/W7165016879"}, "key": "claire-radar:2606.17339", "modality": null, "name": "SpeechDx", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_speechdx_58f3f420", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b315f0cbfd10b1527843fe0c59de2b5374476f0304585a2bfc43362930072208", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.17339"}, "publisher": null, "released": "2026-06-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.17339", "source_url": "https://arxiv.org/abs/2606.17339"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-17339", "source": "claire_radar", "source_benchmark_id": "2606.17339", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Speech & Audio", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.17339", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "30c3333abd92784b111d6a5e52d7e8d60f57e64abe28e8e7f357519f7fb90be4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SpeechDx evaluates clinical speech AI across 12 datasets and 27 tasks covering various conditions, structured by speech production stages. Scoring includes classification accuracy and zero-shot transfer performance.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions."}, "familyId": "bmf_89f2b89c21d5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_speechdx_58f3f420", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.17339", "paper": "https://arxiv.org/abs/2606.17339", "pdf": "https://arxiv.org/pdf/2606.17339", "project": null, "report": "https://arxiv.org/abs/2606.17339"}, "metrics": [], "motivation": "Speech offers a uniquely informative window into health by simultaneously engaging neurological, motor, respiratory, and vocal systems.", "name": "SpeechDx", "oneLine": "SpeechDx evaluates clinical speech AI across 12 datasets and 27 tasks covering various conditions, structured by speech production stages. Scoring includes classification accuracy and zero-shot transfer performance.", "paperTitle": "SpeechDx: A Multi-Task Benchmark for Clinical Speech AI", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.17339", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.17339"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-15", "source": {"authors": ["Sejal Bhalla", "Larry Kieu", "Aina Merchant", "Eyal de Lara", "Alex Mariakakis"], "categories": ["cs.AI", "cs.CL", "cs.SD"], "id": "2606.17339", "title": "SpeechDx: A Multi-Task Benchmark for Clinical Speech AI", "type": "arxiv", "url": "https://arxiv.org/abs/2606.17339"}, "sourceUpdatedAt": "2026-06-15T22:38:36Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Clinical speech AI lacks comparable evaluation across conditions. SpeechDx provides a shared framework to assess generalization and representation quality, guiding progress toward general-purpose models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
