{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.10055", "kind": "paper", "url": "https://arxiv.org/abs/2609.10055"}, {"id": "gh:zhelishisongjie/ontologyaligner", "kind": "repo", "url": "https://github.com/zhelishisongjie/OntologyAligner"}], "categories": ["Biology & Drug Discovery", "Information retrieval", "Language & Knowledge", "cs.AI"], "description": {"en": "Provides 13,390 samples across seven HPO normalization datasets for mapping free-text phenotype mentions to standardized concepts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.10055", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.10055", "title": "PhenoNormBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.10055", "modality": null, "name": "PhenoNormBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "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_phenonormbench_4748cc53", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "1176957e3e45c36dcf546ea806d1ef16d5430146a134bbd8e7117b6b962d013e", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-11T00:52:53.785364Z", "source_url": "https://arxiv.org/abs/2609.10055"}, "publisher": null, "released": "2026-09-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.10055", "source_url": "https://arxiv.org/abs/2609.10055"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-10055", "source": "claire_radar", "source_benchmark_id": "2609.10055", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-10", "attemptedAt": "2026-09-10T01:41:07.072503Z", "githubRepo": "https://github.com/zhelishisongjie/OntologyAligner", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.10055", "observedAt": "2026-09-10T01:41:07.072503Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-10T01:41:07.072503Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-10T01:41:07.072503Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Biomedical ontology normalization is a specialized domain, but the unified dataset may draw users from biomedical NLP.", "score": 42}, "capabilities": ["Information retrieval"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-11T00:52:53.785364Z", "inputHash": "a0869448bedff5c3f7b844f84d0c9ac6cbd01949f94e6efa741e7f391652a475", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "PhenoNormBench unifies seven HPO normalization datasets into a common mention-level format.", "canonicalNameSource": "official_readme", "decisionReason": "Public dataset and code with clear scoring metrics on GitHub; fixed protocol for reuse.", "evaluationEvidence": {"reuse": "https://github.com/zhelishisongjie/OntologyAligner", "scoring": "evaluated using Macro Top-1 Accuracy and Micro Top-1 Accuracy", "task": "maps free-text biomedical phenotype expressions to standardized Human Phenotype Ontology (HPO) concepts"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-11T00:52:53.785364Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Provides 13,390 samples across seven HPO normalization datasets for mapping free-text phenotype mentions to standardized concepts.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence", "public artifact URL", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We also construct PhenoNormBench, a unified benchmark comprising 13,390 samples from seven Human Phenotype Ontology datasets."}, "familyId": "bmf_c2d49a4b4477", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_phenonormbench_4748cc53", "indexedAt": "2026-09-10T00:47:26.889471Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/zhelishisongjie/OntologyAligner", "data": null, "paper": "https://arxiv.org/abs/2609.10055", "pdf": "https://arxiv.org/pdf/2609.10055", "project": null, "report": "https://arxiv.org/abs/2609.10055"}, "metrics": [], "motivation": "Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data.", "name": "PhenoNormBench", "oneLine": "Provides 13,390 samples across seven HPO normalization datasets for mapping free-text phenotype mentions to standardized concepts.", "paperTitle": "OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.10055", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-10T00:47:26.889471Z"}, "publications": [], "publishers": [{"name": "OntologyAligner Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/zhelishisongjie/OntologyAligner"}], "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": 0.10323645750017778, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 100, "score": 28}, "method": "attention-ranking-v13", "rank": 100, "score": 28}, "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": 0.09355303223343062, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 256, "score": 28}, "method": "attention-ranking-v13", "rank": 256, "score": 28}, "today": {"confidence": "Low", "coverage": 0.25, "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": 1, "historyDate": "2026-09-09", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": 0.8333333333333334, "percentile": 0.8333333333333334, "value": 1}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.68, "role": "bonus", "value": 68}}, "confidence": "Low", "coverage": 0.25, "rank": 1, "score": 63}, "method": "attention-ranking-v13", "rank": 1, "score": 63}}, "readiness": "Runnable", "recognitionConfidence": 0.55, "relation": "evaluates_only", "releasedAt": "2026-09-09", "source": {"authors": ["Jie Song", "Zhichuan Xu", "Ziyu Lu", "Meng Xiao", "Cheng Bi", "Yuxin Zhang", "Xin Zheng", "Xiaoran Li", "Qiongfang Cao", "Hao Yang", "Bairong Shen"], "categories": ["cs.AI", "cs.CL"], "id": "2609.10055", "title": "OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization", "type": "arxiv", "url": "https://arxiv.org/abs/2609.10055"}, "sourceUpdatedAt": "2026-09-09T11:30:25Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Standardizes evaluation for biomedical ontology normalization, enabling comparable assessment across methods and improving data integration."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
