{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.19201", "kind": "paper", "url": "https://arxiv.org/abs/2607.19201"}], "authors": ["Iker De la Iglesia", "Johanna Ramirez-Romero", "Jose Maria Villa-Gonzalez", "Irune Urroz García", "Ander Barrena", "Aitziber Atutxa"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.19201", "source_url": "https://arxiv.org/abs/2607.19201"}, "categories": ["Biology & Drug Discovery", "Reasoning", "Vision & 3D"], "description": {"en": "MIRA-Ev evaluates clinical NLP on evidence detection and relational reasoning in Spanish MIR exam cases, with three tasks: evidence sentence retrieval, argumentative component extraction, and relation classification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.19201", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.19201", "title": "MIRA-Ev"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of the Basque Country", "Hospital de Cruces"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.19201", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.19201", "source_url": "https://openalex.org/W7170054390"}, "key": "claire-radar:2607.19201", "modality": null, "name": "MIRA-Ev", "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_mira-ev_98696803", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f3e40c2554ced2f13ec0fc0531b7a254a69ef0f1b9f1e2101003c1fab3f4d0d9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.19201"}, "publisher": null, "released": "2026-07-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.19201", "source_url": "https://arxiv.org/abs/2607.19201"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-19201", "source": "claire_radar", "source_benchmark_id": "2607.19201", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Vision & 3D", "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/2607.19201", "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": ["Reasoning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "c0a11c9dcd59b70e231f8a97cab34962be656fa22530b8fa557992f07c849f6d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MIRA-Ev evaluates clinical NLP on evidence detection and relational reasoning in Spanish MIR exam cases, with three tasks: evidence sentence retrieval, argumentative component extraction, and relation classification.", "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 MIRA-Ev, a clinical argument mining benchmark built on Spanish M\\'edico Interno Residente (MIR) licensing-exam cases, re-annotated by expert clinicians with span-level premises, claims, and directed support/attack relations, and released in parallel Spanish (native), English, and Basque versions, the first clinical argumentation resource in Basque."}, "familyId": "bmf_29781ac889f4", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mira-ev_98696803", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.19201", "paper": "https://arxiv.org/abs/2607.19201", "pdf": "https://arxiv.org/pdf/2607.19201", "project": null, "report": "https://arxiv.org/abs/2607.19201"}, "metrics": [], "motivation": "Clinical NLP evaluation remains dominated by multiple-choice question answering (MCQA), which scores only final-answer accuracy and cannot detect when a model reaches the correct diagnosis while grounding it in irrelevant, absent, or contradictory evidence.", "name": "MIRA-Ev", "oneLine": "MIRA-Ev evaluates clinical NLP on evidence detection and relational reasoning in Spanish MIR exam cases, with three tasks: evidence sentence retrieval, argumentative component extraction, and relation classification.", "paperTitle": "MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.19201", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-21", "source": {"authors": ["Iker De la Iglesia and Johanna Ramirez-Romero and Jose Maria Villa-Gonzalez and Irune Urroz Garc\\'ia and Ander Barrena and Aitziber Atutxa"], "categories": ["cs.CL", "cs.AI"], "id": "2607.19201", "title": "MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams", "type": "arxiv", "url": "https://arxiv.org/abs/2607.19201"}, "sourceUpdatedAt": "2026-07-21T15:34:44Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "It addresses the lack of evidence-level evaluation in clinical NLP, providing a multilingual benchmark (Spanish, English, Basque) to assess not just final answers but the grounding of diagnoses."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
