{"record": {"aliases": ["How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?"], "artifacts": [{"id": "arxiv:2608.13309", "kind": "paper", "url": "https://arxiv.org/abs/2608.13309"}, {"id": "gh:wafaalghallabi/time-aware-mri", "kind": "repo", "url": "https://github.com/wafaAlghallabi/Time-Aware-MRI"}], "authors": ["Wafa Al Ghallabi", "Ritesh Thawkar", "Sara Ghaboura", "Omkar Thawakar", "Numan Saeed", "Dana Al Nuaimi", "Ajnas Alkatheeri", "Salman Khan", "Fahad Shahbaz Khan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.13309", "source_url": "https://arxiv.org/abs/2608.13309"}, "categories": ["Biology & Drug Discovery", "Reasoning", "Vision & 3D"], "description": {"en": "The benchmark comprises 3,920 expert-verified QA pairs from 890 patients across longitudinal MRI timepoints, evaluating temporal reasoning, disease progression, structured localization, sequence ordering, and change localization."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13309", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13309", "title": "Time-Aware Multi-View MRI Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Mohamed bin Zayed University of Artificial Intelligence", "Linköping University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.13309", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.13309", "source_url": "https://openalex.org/W7203492280"}, "key": "claire-radar:2608.13309", "modality": null, "name": "Time-Aware Multi-View MRI Benchmark", "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": "true", "origin_record_id": "bm_how-good-are-foundation-models-in-longitud_4e643d29", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "7546d70dc2ea3df82050ac4850f8e942efa7770acf3cf8407cbf46e78063aa5c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.13309"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13309", "source_url": "https://arxiv.org/abs/2608.13309"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13309", "source": "claire_radar", "source_benchmark_id": "2608.13309", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?"], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/wafaAlghallabi/Time-Aware-MRI", "githubScope": "benchmark_repo", "githubStars": 4, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.13309", "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"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark targets a clinically relevant gap with extensive data and multiple model evaluations, likely to attract attention from medical AI and vision-language researchers.", "score": 65}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "252f7b40593a353d851641fd4b878ffb00c82183dfa86be00d967df9773d08c6", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning across longitudinal scans, and structured localization guidance.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is formally introduced with a public code repository and promised dataset release on Hugging Face, providing a clear public reuse path.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The benchmark comprises 3,920 expert-verified QA pairs from 890 patients across longitudinal MRI timepoints, evaluating temporal reasoning, disease progression, structured localization, sequence ordering, and change localization.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning across longitudinal scans, and structured localization guidance."}, "familyId": "bmf_dcb7036bfa01", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_how-good-are-foundation-models-in-longitud_4e643d29", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/wafaAlghallabi/Time-Aware-MRI", "data": null, "paper": "https://arxiv.org/abs/2608.13309", "pdf": "https://arxiv.org/pdf/2608.13309", "project": null, "report": "https://arxiv.org/abs/2608.13309"}, "metrics": [], "motivation": "Magnetic Resonance Imaging (MRI) interpretation is fundamental to clinical decision-making, requiring radiologists to integrate multi-view anatomical planes across sequential timepoints while precisely localizing interval changes.", "name": "Time-Aware Multi-View MRI Benchmark", "oneLine": "The benchmark comprises 3,920 expert-verified QA pairs from 890 patients across longitudinal MRI timepoints, evaluating temporal reasoning, disease progression, structured localization, sequence ordering, and change localization.", "paperTitle": "How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": "Accepted at MICCAI 2026 (Early Accept). 11 pages, 3 figures, 2 tables", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.13309", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "MICCAI 2026 (Early Accept)", "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "Mohamed bin Zayed University of Artificial Intelligence", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/wafaAlghallabi/Time-Aware-MRI"}], "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": 0.21483102985913266, "value": 4}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 200, "score": 34}, "method": "attention-ranking-v13", "rank": 200, "score": 34}}, "readiness": "Runnable", "recognitionConfidence": 0.55, "relation": "introduces", "releasedAt": "2026-08-13", "source": {"authors": ["Wafa Al Ghallabi", "Ritesh Thawkar", "Sara Ghaboura", "Omkar Thawakar", "Numan Saeed", "Dana Al Nuaimi", "Ajnas Alkatheeri", "Salman Khan", "Fahad Shahbaz Khan"], "categories": ["cs.CV"], "id": "2608.13309", "title": "How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13309"}, "sourceUpdatedAt": "2026-08-13T14:35:20Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted at MICCAI 2026 (Early Accept). 11 pages, 3 figures, 2 tables", "evidence": [{"level": "author-claim", "observedAt": "2026-08-19T11:05:13.395391Z", "rawValue": "Accepted at MICCAI 2026 (Early Accept). 11 pages, 3 figures, 2 tables", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.13309"}], "reviewStatus": "accepted", "venueName": "MICCAI 2026 (Early Accept)"}], "whyItMatters": "Addresses the gap in evaluating vision-language models on longitudinal, multi-view MRI reasoning, which is crucial for clinical progression tracking and treatment assessment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
