{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.07601", "kind": "paper", "url": "https://arxiv.org/abs/2609.07601"}, {"id": "gh:xiangjun2003/obgynlongbench", "kind": "repo", "url": "https://github.com/xiangjun2003/ObgynLongbench"}], "authors": ["Jun Xiang", "Zhijie Bao", "Rong Hu", "Kaizhou Qin", "Wei Chen", "Zhongyu Wei"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.07601", "source_url": "https://arxiv.org/abs/2609.07601"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "Long Context"], "description": {"en": "Evaluates long-context EHR decision-making for obstetrics and gynecology using 1,500 rule-grounded cases across Evidence-only, Visit-level, and History-level settings."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.07601", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.07601", "title": "ObGynLongBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.07601", "modality": null, "name": "ObGynLongBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_obgynlongbench_eaf80816", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "4df26b32ecbd738a2c3a93add8c452c644cda1788b65102ea61908489a87c565", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-10T00:52:28.558291Z", "source_url": "https://arxiv.org/abs/2609.07601"}, "publisher": null, "released": "2026-09-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.07601", "source_url": "https://arxiv.org/abs/2609.07601"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-07601", "source": "claire_radar", "source_benchmark_id": "2609.07601", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-09", "attemptedAt": "2026-09-09T06:48:27.347268Z", "githubRepo": "https://github.com/xiangjun2003/ObgynLongbench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.07601", "observedAt": "2026-09-09T06:48:27.347268Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-09T06:48:27.347268Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-09T06:48:27.347268Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark targets a niche but timely EHR decision-making gap with a clear evaluation protocol and public code, attracting moderate initial attention from clinical NLP researchers.", "score": 45}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-10T00:52:28.558291Z", "inputHash": "fa7b5564b3fc9760e7b1a24c2cbc99a2005fb16581d0bb22f0d2e92b4139fb5a", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-Making", "canonicalNameSource": "paper_title", "decisionReason": "The paper formally introduces ObGynLongBench with a released GitHub repository containing evaluation code and data, enabling external replication and comparison.", "evaluationEvidence": {"reuse": "Code and data are available at https://github.com/xiangjun2003/ObgynLongbench, providing evaluation and judge pipelines.", "scoring": "LLM-as-judge scores reasoning against support_evidence on a 0-5 scale; accuracy via chosen_option vs. precise_scrub_targets.", "task": "1,500 clinical decision-point cases from 976 real pregnancy EHR histories with traceable rules, anchored to patient, timeline point, and information boundary."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-10T00:52:28.558291Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates long-context EHR decision-making for obstetrics and gynecology using 1,500 rule-grounded cases across Evidence-only, Visit-level, and History-level settings.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To bridge this gap, we introduce ObGynLongBench, a rule-grounded long-context EHR benchmark for obstetric and gynecologic decision-making, comprising 1,500 clinical decision-point cases from 976 real pregnancy EHR histories and traceable rules."}, "familyId": "bmf_dbca8165f42e", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_obgynlongbench_eaf80816", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/xiangjun2003/ObgynLongbench", "data": null, "paper": "https://arxiv.org/abs/2609.07601", "pdf": "https://arxiv.org/pdf/2609.07601", "project": null, "report": "https://arxiv.org/abs/2609.07601"}, "metrics": [], "motivation": "The application of large language models (LLMs) to personalized medical assistants has garnered growing interest.", "name": "ObGynLongBench", "oneLine": "Evaluates long-context EHR decision-making for obstetrics and gynecology using 1,500 rule-grounded cases across Evidence-only, Visit-level, and History-level settings.", "paperTitle": "ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-Making", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.07601", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 141, "score": 23}, "method": "attention-ranking-v13", "rank": 141, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 336, "score": 23}, "method": "attention-ranking-v13", "rank": 336, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-09-07", "source": {"authors": ["Jun Xiang", "Zhijie Bao", "Rong Hu", "Kaizhou Qin", "Wei Chen", "Zhongyu Wei"], "categories": ["cs.CL", "cs.AI"], "id": "2609.07601", "title": "ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-Making", "type": "arxiv", "url": "https://arxiv.org/abs/2609.07601"}, "sourceUpdatedAt": "2026-09-07T15:12:36Z", "topics": ["Long Context"], "venueAttempts": [], "whyItMatters": "Exposes the gap between evidence-provided and EHR-extracted clinical decisions, highlighting evidence utilization as a bottleneck for personalized medical assistants."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
