{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.14385", "kind": "paper", "url": "https://arxiv.org/abs/2607.14385"}], "authors": ["Thanni Adewuyi", "Anuoluwa Sotome", "Samuel Okoko", "Angel Ezendu", "Oluwafunke Akinbuwa", "Oluwaseun Odunsi", "Oluwasegun Oguntuase", "Ifeoma Nwabueze", "Abiodun Adereni"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.14385", "source_url": "https://arxiv.org/abs/2607.14385"}, "categories": ["Biology & Drug Discovery", "Robustness", "Safety & Trustworthiness", "cs.CL"], "description": {"en": "MamaBench evaluates LLM robustness in maternal and child health diagnosis using counterfactual clinical narratives, with the Bias Trap Rate (BTR) metric."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.14385", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.14385", "title": "MamaBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Ibadan"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.14385", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.14385", "source_url": "https://openalex.org/W7169493124"}, "key": "claire-radar:2607.14385", "modality": null, "name": "MamaBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_mamabench_7ce134aa", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "398a66294be459af5b823da5acc5831ef71a021e1e813bd4ed0890d09f1901af", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.14385"}, "publisher": null, "released": "2026-07-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.14385", "source_url": "https://arxiv.org/abs/2607.14385"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-14385", "source": "claire_radar", "source_benchmark_id": "2607.14385", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Biology & Drug Discovery"], "area": "Safety & Trustworthiness", "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": 1, "hfPaperUrl": "https://huggingface.co/papers/2607.14385", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Robustness"], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "79b8aad9e670b441115c9dcf37c6f69a3a9c3e37fc478b338a5de9d518cc2a19", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MamaBench evaluates LLM robustness in maternal and child health diagnosis using counterfactual clinical narratives, with the Bias Trap Rate (BTR) metric.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce MamaBench, the first counterfactual benchmark for maternal and paediatric AI: 434 expert-authored clinical narratives in 217 pairs across 371 pathologies, evaluated via the Bias Trap Rate (BTR), the conditional probability that a model fails the counterfactual given success on the base case."}, "familyId": "bmf_db4a560447e2", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mamabench_7ce134aa", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.14385", "paper": "https://arxiv.org/abs/2607.14385", "pdf": "https://arxiv.org/pdf/2607.14385", "project": null, "report": "https://arxiv.org/abs/2607.14385"}, "metrics": [], "motivation": "Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation, providing no measure of whether a system can distinguish clinically similar presentations requiring different interventions.", "name": "MamaBench", "oneLine": "MamaBench evaluates LLM robustness in maternal and child health diagnosis using counterfactual clinical narratives, with the Bias Trap Rate (BTR) metric.", "paperTitle": "MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.14385", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.12247537038455211, "value": 1}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 44}, "method": "attention-ranking-v13", "rank": null, "score": 44}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-07-15", "source": {"authors": ["Thanni Adewuyi", "Anuoluwa Sotome", "Samuel Okoko", "Angel Ezendu", "Oluwafunke Akinbuwa", "Oluwaseun Odunsi", "Oluwasegun Oguntuase", "Ifeoma Nwabueze", "Abiodun Adereni"], "categories": ["cs.CL", "cs.LG"], "id": "2607.14385", "title": "MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.14385"}, "sourceUpdatedAt": "2026-07-19T14:47:36Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It highlights the gap between base accuracy and robust accuracy in clinical AI, showing that models can fail on clinically similar cases requiring different interventions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
