{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.20868", "kind": "paper", "url": "https://arxiv.org/abs/2607.20868"}], "authors": ["Han Li", "Si Liu", "Zehao Huang", "Dongxin Lyu", "Longfei Xu", "Jiahui Fu", "Daxin Tian", "Yuliang Xiu", "Naiyan Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.20868", "source_url": "https://arxiv.org/abs/2607.20868"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "An evaluation suite of 1,340 video QA pairs across 15 subtasks assessing MLLM qualitative reasoning in dynamic scenes, covering motion perception, spatial relations, outcome prediction, and physical dynamics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.20868", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.20868", "title": "ViSTR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.20868", "modality": null, "name": "ViSTR-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_vistr-bench_5dcce2bf", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "38a32790e3492a70476ed227d7d86f559af85515b43faa585acfb30b00a66213", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.20868"}, "publisher": null, "released": "2026-07-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.20868", "source_url": "https://arxiv.org/abs/2607.20868"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-20868", "source": "claire_radar", "source_benchmark_id": "2607.20868", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2607.20868", "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", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Reasoning"], "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": "ae48f6b0717c5be8d9fc7c12b59a668785bbf50b112720db48735b9adf1332fe", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "An evaluation suite of 1,340 video QA pairs across 15 subtasks assessing MLLM qualitative reasoning in dynamic scenes, covering motion perception, spatial relations, outcome prediction, and physical dynamics.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "In this paper, we introduce the Visual Spatial-Temporal Reasoning Benchmark (ViSTR-Bench), a novel evaluation suite designed to systematically assess whether MLLMs can perform qualitative reasoning from continuous visual cues in dynamic scenes."}, "familyId": "bmf_744954eb90a9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_vistr-bench_5dcce2bf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.20868", "paper": "https://arxiv.org/abs/2607.20868", "pdf": "https://arxiv.org/pdf/2607.20868", "project": null, "report": "https://arxiv.org/abs/2607.20868"}, "metrics": [], "motivation": "Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse expert-level tasks, but they still struggle with fundamental abilities that humans naturally develop through continuous observation of the real world, such as spatial perception and dynamic reasoning.", "name": "ViSTR-Bench", "oneLine": "An evaluation suite of 1,340 video QA pairs across 15 subtasks assessing MLLM qualitative reasoning in dynamic scenes, covering motion perception, spatial relations, outcome prediction, and physical dynamics.", "paperTitle": "ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.20868", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-23", "source": {"authors": ["Han Li", "Si Liu", "Zehao Huang", "Dongxin Lyu", "Longfei Xu", "Jiahui Fu", "Daxin Tian", "Yuliang Xiu", "Naiyan Wang"], "categories": ["cs.CV"], "id": "2607.20868", "title": "ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?", "type": "arxiv", "url": "https://arxiv.org/abs/2607.20868"}, "sourceUpdatedAt": "2026-07-23T02:49:24Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Current MLLMs lag behind humans in intuitive spatial-temporal reasoning; this probe highlights those gaps but lacks a standalone reusable benchmark."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
