{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.27828", "kind": "paper", "url": "https://arxiv.org/abs/2606.27828"}, {"id": "gh:mrakas/video-mme-logical", "kind": "repo", "url": "https://github.com/Mrakas/video-mme-logical"}], "authors": ["Hohin Kwan", "Hongyu Li", "Ray Zhang", "Manyuan Zhang", "Xianghao Kong", "Anyi Rao", "Jiahao Xie", "Si Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.27828", "source_url": "https://arxiv.org/abs/2606.27828"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "Evaluates video temporal-logical reasoning in multimodal LLMs across 25 fine-grained task categories, with difficulty-controlled final-answer scoring and intermediate-state diagnostics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.27828", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.27828", "title": "Video-MME-Logical"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.27828", "modality": null, "name": "Video-MME-Logical", "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_video-mme-logical_db483a80", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "88c9635209d77e9176b38da5f9719a4faf20393875ed98b3f0dee13fb6b2c9a6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.27828"}, "publisher": null, "released": "2026-06-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.27828", "source_url": "https://arxiv.org/abs/2606.27828"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-27828", "source": "claire_radar", "source_benchmark_id": "2606.27828", "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": "https://github.com/Mrakas/video-mme-logical", "githubScope": "benchmark_repo", "githubStars": 11, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 25, "hfPaperUrl": "https://huggingface.co/papers/2606.27828", "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": ["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": "c86aa692865b502b97e68aab95e557501c9e79f7922ecba42d53b13fb9dae09f", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates video temporal-logical reasoning in multimodal LLMs across 25 fine-grained task categories, with difficulty-controlled final-answer scoring and intermediate-state diagnostics.", "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": "To isolate this capability, we introduce Video-MME-Logical, a controlled benchmark organized around five temporal-logical operations: state tracking, sequential counting, temporal ordering, dynamic spatiality, and structural composition."}, "familyId": "bmf_406a86346e24", "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/Mrakas/video-mme-logical", "url": "https://github.com/Mrakas/video-mme-logical"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Mrakas/video-mme-logical", "url": "https://huggingface.co/papers/2606.27828"}], "scope": "benchmark_repo", "url": "https://github.com/Mrakas/video-mme-logical", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_video-mme-logical_db483a80", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Mrakas/video-mme-logical", "data": null, "hfPaper": "https://huggingface.co/papers/2606.27828", "paper": "https://arxiv.org/abs/2606.27828", "pdf": "https://arxiv.org/pdf/2606.27828", "project": null, "report": "https://arxiv.org/abs/2606.27828"}, "metrics": [], "motivation": "Recent interest in multimodal large language models (MLLMs) raises a central question: can they reason over dynamic visual evidence rather than merely recognize objects or events in individual frames?", "name": "Video-MME-Logical", "oneLine": "Evaluates video temporal-logical reasoning in multimodal LLMs across 25 fine-grained task categories, with difficulty-controlled final-answer scoring and intermediate-state diagnostics.", "paperTitle": "Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.27828", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Mrakas", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Mrakas/video-mme-logical"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-26", "source": {"authors": ["Hohin Kwan", "Hongyu Li", "Ray Zhang", "Manyuan Zhang", "Xianghao Kong", "Anyi Rao", "Jiahao Xie", "Si Liu"], "categories": ["cs.CV"], "id": "2606.27828", "title": "Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2606.27828"}, "sourceUpdatedAt": "2026-06-26T08:12:04Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Isolates temporal-logical capabilities from static recognition, revealing significant human-model gaps and providing a scalable testbed for analysis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
