{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.25915", "kind": "paper", "url": "https://arxiv.org/abs/2606.25915"}, {"id": "gh:penway/funpiq", "kind": "repo", "url": "https://github.com/penway/FunPiQ"}], "authors": ["Pengwei Wang", "José Morano", "Virginia Mares", "Hrvoje Bogunović"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.25915", "source_url": "https://arxiv.org/abs/2606.25915"}, "categories": ["Biology & Drug Discovery", "Vision & 3D", "cs.CV"], "description": {"en": "FunPiQ is a benchmark for pixel-level fundus image quality assessment with pixel-level annotations for anatomical visibility, using a three-class scheme (good, usable, bad). It also introduces EFIQA-CP, an explainable method trained with pseudo-labels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.25915", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.25915", "title": "FunPiQ"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Medical University of Vienna"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.25915", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.25915", "source_url": "https://openalex.org/W7165849638"}, "key": "claire-radar:2606.25915", "modality": null, "name": "FunPiQ", "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_funpiq_ac17b6fd", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e8ff763c416a2284f54030a002d6240f5f959ed6a2ef514ef6954ba478bba6ca", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.25915"}, "publisher": null, "released": "2026-06-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.25915", "source_url": "https://arxiv.org/abs/2606.25915"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-25915", "source": "claire_radar", "source_benchmark_id": "2606.25915", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "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/penway/FunPiQ", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.25915", "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", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "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": "cb7daff2c922718533100460e5fa5b1c1c9fe3e8e47e882df05bab32cf186c94", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FunPiQ is a benchmark for pixel-level fundus image quality assessment with pixel-level annotations for anatomical visibility, using a three-class scheme (good, usable, bad). It also introduces EFIQA-CP, an explainable method trained with pseudo-labels.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "In this work, we introduce FunPiQ, the first FIQA benchmark to provide pixel-level quality annotations."}, "familyId": "bmf_d55ffcdf5c6f", "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/penway/FunPiQ", "url": "https://github.com/penway/FunPiQ"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/penway/FunPiQ", "url": "https://huggingface.co/papers/2606.25915"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/penway/FunPiQ", "url": "https://arxiv.org/abs/2606.25915"}], "scope": "benchmark_repo", "url": "https://github.com/penway/FunPiQ", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_funpiq_ac17b6fd", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": "https://github.com/penway/FunPiQ", "data": null, "hfPaper": "https://huggingface.co/papers/2606.25915", "paper": "https://arxiv.org/abs/2606.25915", "pdf": "https://arxiv.org/pdf/2606.25915", "project": null, "report": "https://arxiv.org/abs/2606.25915"}, "metrics": [], "motivation": "Color fundus photography (CFP) is the most common ophthalmic imaging modality for large-scale screening.", "name": "FunPiQ", "oneLine": "FunPiQ is a benchmark for pixel-level fundus image quality assessment with pixel-level annotations for anatomical visibility, using a three-class scheme (good, usable, bad). It also introduces EFIQA-CP, an explainable method trained with pseudo-labels.", "paperTitle": "FunPiQ: A New Benchmark for Pixel-Level Quality Assessment in Fundus Images", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": "Accepted at MICCAI 2026 main conference. Our code, weights, and dataset are available at https://github.com/penway/FunPiQ", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.25915", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "MICCAI 2026 main conference", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "GitHub", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/penway/FunPiQ"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-24", "source": {"authors": ["Pengwei Wang", "Jos\\'e Morano", "Virginia Mares", "Hrvoje Bogunovi\\'c"], "categories": ["cs.CV"], "id": "2606.25915", "title": "FunPiQ: A New Benchmark for Pixel-Level Quality Assessment in Fundus Images", "type": "arxiv", "url": "https://arxiv.org/abs/2606.25915"}, "sourceUpdatedAt": "2026-06-24T14:59:34Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted at MICCAI 2026 main conference. Our code, weights, and dataset are available at https://github.com/penway/FunPiQ", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at MICCAI 2026 main conference. Our code, weights, and dataset are available at https://github.com/penway/FunPiQ", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.25915"}], "reviewStatus": "accepted", "venueName": "MICCAI 2026 main conference"}], "whyItMatters": "Existing FIQA benchmarks provide only image-level labels, limiting localized degradation analysis. FunPiQ enables task-agnostic explainable quality evaluation through pixel-level ground truth and offers a public dataset for method comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
