{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.02522", "kind": "paper", "url": "https://arxiv.org/abs/2606.02522"}], "authors": ["Xiaolin Liu", "Yilun Zhu", "Xiangyu Zhao", "Xuehui Wang", "Yan Li", "Xin Li", "Haoyu Cao", "Xing Sun", "Shaofeng Zhang", "Xu Yang", "Zhihang Zhong", "Xue Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.02522", "source_url": "https://arxiv.org/abs/2606.02522"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Moment-Video evaluates video MLLMs on momentary visual event understanding through 1,000 human-verified video-QA pairs across four task types: temporal occurrence, temporal counting, action description, and temporal reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.02522", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.02522", "title": "Moment-Video"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shandong University", "Southeast University", "Shanghai Jiao Tong University", "Tencent (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.02522", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.02522", "source_url": "https://openalex.org/W7163203368"}, "key": "claire-radar:2606.02522", "modality": null, "name": "Moment-Video", "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_moment-video_26d94dc0", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "fa2eef6c645a3e712331f2100009427348e4fdb77cf3559860c5fc4470eabf1e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.02522"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.02522", "source_url": "https://arxiv.org/abs/2606.02522"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-02522", "source": "claire_radar", "source_benchmark_id": "2606.02522", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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": 13, "hfPaperUrl": "https://huggingface.co/papers/2606.02522", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "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": "de72bb5d2df58b3152d36085960cec92ec1d9654f413e113c8033b53390744aa", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Moment-Video evaluates video MLLMs on momentary visual event understanding through 1,000 human-verified video-QA pairs across four task types: temporal occurrence, temporal counting, action description, and temporal reasoning.", "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 Moment-Video, a benchmark for diagnosing the temporal fidelity of video MLLMs through momentary visual event understanding."}, "familyId": "bmf_3b12aecab48e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_moment-video_26d94dc0", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.02522", "paper": "https://arxiv.org/abs/2606.02522", "pdf": "https://arxiv.org/pdf/2606.02522", "project": null, "report": "https://arxiv.org/abs/2606.02522"}, "metrics": [], "motivation": "Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evidence remains underexplored.", "name": "Moment-Video", "oneLine": "Moment-Video evaluates video MLLMs on momentary visual event understanding through 1,000 human-verified video-QA pairs across four task types: temporal occurrence, temporal counting, action description, and temporal reasoning.", "paperTitle": "Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.02522", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Xiaolin Liu", "Yilun Zhu", "Xiangyu Zhao", "Xuehui Wang", "Yan Li", "Xin Li", "Haoyu Cao", "Xing Sun", "Shaofeng Zhang", "Xu Yang", "Zhihang Zhong", "Xue Yang"], "categories": ["cs.CV", "cs.AI"], "id": "2606.02522", "title": "Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events", "type": "arxiv", "url": "https://arxiv.org/abs/2606.02522"}, "sourceUpdatedAt": "2026-06-01T17:32:20Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "It addresses the gap in evaluating models' ability to capture brief answer-critical visual evidence, which is common in practical video understanding and not covered by general video benchmarks. The results show significant room for improvement, offering a diagnostic tool for model development."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
