{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12904", "kind": "paper", "url": "https://arxiv.org/abs/2608.12904"}, {"id": "gh:byhwhite/hounsworld", "kind": "repo", "url": "https://github.com/byhwhite/HounsWorld.git"}], "authors": ["Yunhao Bai", "Zhongwei Qiu", "Guangyu Guo", "Yiming Huang", "Tony C. W. Mok", "Qinji Yu", "Ling Zhang", "Yan Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12904", "source_url": "https://arxiv.org/abs/2608.12904"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "HounsBench is a CT-centric patient-state benchmark evaluating three task families: readout, reconstruction, and simulation. It provides patient-disjoint splits and per-family metrics for evaluating models on volumetric medical images and clinical language."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12904", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12904", "title": "HounsBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Alibaba Group (Cayman Islands)", "Alibaba DAMO Academy (China)", "Alibaba Group (China)", "East China Normal University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.12904", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.12904", "source_url": "https://openalex.org/W7203466426"}, "key": "claire-radar:2608.12904", "modality": null, "name": "HounsBench", "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_hounsbench_1139158f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "79b541060620d6d4d051a86abf548f7c0661fd290096138c77d8b1084f66a94b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12904"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12904", "source_url": "https://arxiv.org/abs/2608.12904"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12904", "source": "claire_radar", "source_benchmark_id": "2608.12904", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/byhwhite/HounsWorld", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.12904", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "4b246dd78ed2bf04c1d377f54fe27c005aff81346d8028d094ad13239f99da87", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "HounsBench is a CT-centric patient-state benchmark evaluating three task families: readout, reconstruction, and simulation. It provides patient-disjoint splits and per-family metrics for evaluating models on volumetric medical images and clinical language.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To operationalize this view, we introduce HounsBench, a computed tomography (CT) centric patient-state benchmark that unifies these three task families with patient-disjoint splits and per-family metrics, and HounsWorld, a 3B multimodal world model that treats volumetric scans and language as observations of the shared state through Joint Understanding-Generation Learning."}, "familyId": "bmf_5e09e564fc52", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/byhwhite/HounsWorld.git", "url": "https://github.com/byhwhite/HounsWorld.git"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/byhwhite/HounsWorld", "url": "https://huggingface.co/papers/2608.12904"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/byhwhite/HounsWorld.git", "url": "https://arxiv.org/abs/2608.12904"}], "scope": "project_repo", "url": "https://github.com/byhwhite/HounsWorld", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_hounsbench_1139158f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/byhwhite/HounsWorld.git", "data": null, "hfPaper": "https://huggingface.co/papers/2608.12904", "paper": "https://arxiv.org/abs/2608.12904", "pdf": "https://arxiv.org/pdf/2608.12904", "project": null, "report": "https://arxiv.org/abs/2608.12904"}, "metrics": [], "motivation": "Clinical intelligence requires estimating a patient's underlying condition from incomplete observations rather than learning isolated mappings from scans to answers.", "name": "HounsBench", "oneLine": "HounsBench is a CT-centric patient-state benchmark evaluating three task families: readout, reconstruction, and simulation. It provides patient-disjoint splits and per-family metrics for evaluating models on volumetric medical images and clinical language.", "paperTitle": "HounsWorld: A Multimodal World Model for Hidden Patient-State Readout, Reconstruction, and Simulation", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.12904", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "HounsWorld Project", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/byhwhite/HounsWorld.git"}], "ranking": {"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": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 225, "score": 33}, "method": "attention-ranking-v13", "rank": 225, "score": 33}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-13", "source": {"authors": ["Yunhao Bai", "Zhongwei Qiu", "Guangyu Guo", "Yiming Huang", "Tony C.W. Mok", "Qinji Yu", "Ling Zhang", "Yan Wang"], "categories": ["cs.CV"], "id": "2608.12904", "title": "HounsWorld: A Multimodal World Model for Hidden Patient-State Readout, Reconstruction, and Simulation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12904"}, "sourceUpdatedAt": "2026-08-13T07:41:14Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "HounsBench addresses the evaluation gap for CT-centered intelligence by unifying diverse tasks under a shared patient-state inference framework, enabling assessment of models that must integrate imaging and language for clinical decision support."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
