{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.08736", "kind": "paper", "url": "https://arxiv.org/abs/2608.08736"}], "authors": ["Kaili Zheng", "Kaiwen Wang", "Xun Zhu", "Qingyuan Yang", "Chenyi Guo", "Ji Wu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.08736", "source_url": "https://arxiv.org/abs/2608.08736"}, "categories": ["General AI", "Multimodal"], "description": {"en": "FitAQA evaluates fitness action quality assessment in MLLMs across perception, judgement, and temporal grounding tasks, using a unified taxonomy of 38 form errors in six dimensions over 30 exercises."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.08736", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.08736", "title": "FitAQA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.08736", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.08736", "source_url": "https://openalex.org/W7202168674"}, "key": "claire-radar:2608.08736", "modality": null, "name": "FitAQA", "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_fitaqa_e0a97bca", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e49af9dffe6520bda824359d873a1cb5a57e1fe91359797d5a568a5238a585af", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.08736"}, "publisher": null, "released": "2026-08-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.08736", "source_url": "https://arxiv.org/abs/2608.08736"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-08736", "source": "claire_radar", "source_benchmark_id": "2608.08736", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.08736", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "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": "21de7b802bd8ae885b3add2d9aa4da55c9bd3bef1b3c613a3199e2b920b327ad", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FitAQA evaluates fitness action quality assessment in MLLMs across perception, judgement, and temporal grounding tasks, using a unified taxonomy of 38 form errors in six dimensions over 30 exercises.", "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"], "snippet": "We introduce FitAQA, a systematic benchmark for evaluating MLLMs in fitness AQA, containing 2,219 videos and 5,512 QA instances across 30 bodyweight exercises."}, "familyId": "bmf_3b8db6654700", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_fitaqa_e0a97bca", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.08736", "paper": "https://arxiv.org/abs/2608.08736", "pdf": "https://arxiv.org/pdf/2608.08736", "project": null, "report": "https://arxiv.org/abs/2608.08736"}, "metrics": [], "motivation": "Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting remain underexplored.", "name": "FitAQA", "oneLine": "FitAQA evaluates fitness action quality assessment in MLLMs across perception, judgement, and temporal grounding tasks, using a unified taxonomy of 38 form errors in six dimensions over 30 exercises.", "paperTitle": "FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.08736", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-09", "source": {"authors": ["Kaili Zheng", "Kaiwen Wang", "Xun Zhu", "Qingyuan Yang", "Chenyi Guo", "Ji Wu"], "categories": ["cs.AI"], "id": "2608.08736", "title": "FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.08736"}, "sourceUpdatedAt": "2026-08-09T14:28:17Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "It provides a systematic benchmark for fitness AQA, enabling assessment of MLLMs' ability to perceive and reason about exercise quality, and identifies visual perception as a key bottleneck."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
