{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.26517", "kind": "paper", "url": "https://arxiv.org/abs/2608.26517"}, {"id": "gh:gml-mmgroup/hug-vis", "kind": "repo", "url": "https://github.com/GML-MMGroup/HUG-VIS"}], "authors": ["Fei Ma", "Zebang Cheng", "Minghui Li", "Hongbo Xu", "Yuyong Tan", "Yihua Shao", "Hanling Wang", "Zhou Liu", "Yuqing Gao", "Dong Wang", "Long Ma", "Laizhong Cui", "Nicu Sebe", "Qi Tian"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.26517", "source_url": "https://arxiv.org/abs/2608.26517"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Visual intelligence seeks to perceive, interpret, and synthesize the visual world and is central to modern computer vision."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.26517", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.26517", "title": "HUG-VIS"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.26517", "modality": null, "name": "HUG-VIS", "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": "true", "origin_record_id": "bm_hug-vis_24e7fc8b", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "1e46dc00b8a4aab7e2e703169c55f72b5e94cff0e3fa688427aec9e92c05a111", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.26517"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.26517", "source_url": "https://arxiv.org/abs/2608.26517"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-26517", "source": "claire_radar", "source_benchmark_id": "2608.26517", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/GML-MMGroup/HUG-VIS", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.26517", "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.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We address this gap with HUG-VIS, a unified benchmark for Human-centered Understanding and Generation in Visual Intelligence."}, "familyId": "bmf_3e006d284c40", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/GML-MMGroup/HUG-VIS", "url": "https://github.com/GML-MMGroup/HUG-VIS"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/GML-MMGroup/HUG-VIS", "url": "https://huggingface.co/papers/2608.26517"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/GML-MMGroup/HUG-VIS", "url": "https://arxiv.org/abs/2608.26517"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/GML-MMGroup/HUG-VIS.", "url": "https://arxiv.org/abs/2608.26517"}], "scope": "benchmark_repo", "url": "https://github.com/GML-MMGroup/HUG-VIS", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_hug-vis_24e7fc8b", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": "https://github.com/GML-MMGroup/HUG-VIS", "data": null, "hfPaper": "https://huggingface.co/papers/2608.26517", "paper": "https://arxiv.org/abs/2608.26517", "pdf": "https://arxiv.org/pdf/2608.26517", "project": null, "report": "https://arxiv.org/abs/2608.26517"}, "metrics": [], "motivation": "Visual intelligence seeks to perceive, interpret, and synthesize the visual world and is central to modern computer vision.", "name": "HUG-VIS", "oneLine": "Visual intelligence seeks to perceive, interpret, and synthesize the visual world and is central to modern computer vision.", "paperTitle": "HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.26517", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": 0.2391676802567412, "value": 5}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 177, "score": 36}, "method": "attention-ranking-v13", "rank": 177, "score": 36}}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Fei Ma", "Zebang Cheng", "Minghui Li", "Hongbo Xu", "Yuyong Tan", "Yihua Shao", "Hanling Wang", "Zhou Liu", "Yuqing Gao", "Dong Wang", "Long Ma", "Laizhong Cui", "Nicu Sebe", "Qi Tian"], "categories": ["cs.CV"], "id": "2608.26517", "title": "HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence", "type": "arxiv", "url": "https://arxiv.org/abs/2608.26517"}, "sourceUpdatedAt": "2026-08-27T01:43:47Z", "topics": ["Multimodal"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
