{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.16609", "kind": "paper", "url": "https://arxiv.org/abs/2607.16609"}, {"id": "gh:baochenfu/oct-bench", "kind": "repo", "url": "https://github.com/baochenfu/OCT-Bench"}], "authors": ["Baochen Fu", "Wenzhi Deng", "Baihao Jin", "Yang Li", "Zihan Nie", "Kailin Jiang", "Yuntao Du", "Weiye Song"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.16609", "source_url": "https://arxiv.org/abs/2607.16609"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "OCT-Bench evaluates multimodal large language models on OCT image understanding with 10,076 multiple-choice questions from 4,137 images across seven public datasets, covering 20 tasks in Perception, Cognition, and Reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.16609", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.16609", "title": "OCT-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shandong University", "Centre for Artificial Intelligence and Robotics", "Shandong Provincial QianFoShan Hospital", "University of Science and Technology of China"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.16609", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.16609", "source_url": "https://openalex.org/W7169868302"}, "key": "claire-radar:2607.16609", "modality": null, "name": "OCT-Bench", "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_oct-bench_3914e5be", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "96fd2460c4c9b7b7e4621f23e62665942ec002024d3f107b9a4376512dee8f34", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.16609"}, "publisher": null, "released": "2026-07-18", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.16609", "source_url": "https://arxiv.org/abs/2607.16609"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-16609", "source": "claire_radar", "source_benchmark_id": "2607.16609", "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/baochenfu/OCT-Bench", "githubScope": "benchmark_repo", "githubStars": 241, "hfDailySubmittedAt": "2026-07-21T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 5, "hfPaperUrl": "https://huggingface.co/papers/2607.16609", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "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": "238c1136dffdc0b4d1084bc66bcb501e556b225bc0a4c86211000e3b45dc0ad4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OCT-Bench evaluates multimodal large language models on OCT image understanding with 10,076 multiple-choice questions from 4,137 images across seven public datasets, covering 20 tasks in Perception, Cognition, and Reasoning.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this limitation, we introduce OCT-Bench, a comprehensive benchmark dedicated to OCT image understanding."}, "familyId": "bmf_b657b809f328", "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/baochenfu/OCT-Bench", "url": "https://github.com/baochenfu/OCT-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/baochenfu/OCT-Bench", "url": "https://huggingface.co/papers/2607.16609"}], "scope": "benchmark_repo", "url": "https://github.com/baochenfu/OCT-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_oct-bench_3914e5be", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/baochenfu/OCT-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.16609", "paper": "https://arxiv.org/abs/2607.16609", "pdf": "https://arxiv.org/pdf/2607.16609", "project": null, "report": "https://arxiv.org/abs/2607.16609"}, "metrics": [], "motivation": "Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases.", "name": "OCT-Bench", "oneLine": "OCT-Bench evaluates multimodal large language models on OCT image understanding with 10,076 multiple-choice questions from 4,137 images across seven public datasets, covering 20 tasks in Perception, Cognition, and Reasoning.", "paperTitle": "Can Multimodal Large Language Models Understand OCT?", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.16609", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "baochenfu", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/baochenfu/OCT-Bench"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.7326745166326321, "value": 241}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.31659423970600165, "value": 5}}, "confidence": "Medium", "coverage": 0.7, "rank": 18, "score": 60}, "method": "attention-ranking-v13", "rank": 18, "score": 60}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-18", "source": {"authors": ["Baochen Fu", "Wenzhi Deng", "Baihao Jin", "Yang Li", "Zihan Nie", "Kailin Jiang", "Yuntao Du", "and Weiye Song"], "categories": ["cs.CV", "cs.CL"], "id": "2607.16609", "title": "Can Multimodal Large Language Models Understand OCT?", "type": "arxiv", "url": "https://arxiv.org/abs/2607.16609"}, "sourceUpdatedAt": "2026-07-18T03:08:31Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Offers a comprehensive benchmark for OCT understanding beyond coarse classification, enabling capability bottleneck analysis for clinical deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
