{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.15778", "kind": "paper", "url": "https://arxiv.org/abs/2607.15778"}], "authors": ["Wei Feng", "Xin Wang", "Yu-Wei Zhan", "Yuwei Zhou", "Wenwu Zhu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.15778", "source_url": "https://arxiv.org/abs/2607.15778"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "MEventBench is a multi-event long video understanding benchmark introduced alongside the MoD-VLLM framework, evaluating temporal grounding and semantic understanding."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.15778", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.15778", "title": "MEventBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University", "Beijing National Research Center for Information Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.15778", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.15778", "source_url": "https://openalex.org/W7169759084"}, "key": "claire-radar:2607.15778", "modality": null, "name": "MEventBench", "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_meventbench_dad2f997", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ab6fc72ba47d62369eba5331ec3aca129811cb8cc882f28ca40b225df3717a86", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.15778"}, "publisher": null, "released": "2026-07-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.15778", "source_url": "https://arxiv.org/abs/2607.15778"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-15778", "source": "claire_radar", "source_benchmark_id": "2607.15778", "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/2607.15778", "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": "4446152766221e78ac06b96b8455613f180321d81d48c3bbfd04420ee9e51804", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MEventBench is a multi-event long video understanding benchmark introduced alongside the MoD-VLLM framework, evaluating temporal grounding and semantic understanding.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "Moreover, we propose MEventBench, a challenging Multi-Event Long Video Benchmark for complex long video reasoning."}, "familyId": "bmf_bdb6464af549", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_meventbench_dad2f997", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.15778", "paper": "https://arxiv.org/abs/2607.15778", "pdf": "https://arxiv.org/pdf/2607.15778", "project": null, "report": "https://arxiv.org/abs/2607.15778"}, "metrics": [], "motivation": "Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks.", "name": "MEventBench", "oneLine": "MEventBench is a multi-event long video understanding benchmark introduced alongside the MoD-VLLM framework, evaluating temporal grounding and semantic understanding.", "paperTitle": "Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by 2026 IEEE International Conference on Multimedia and Expo (ICME 2026)", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.15778", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "2026 IEEE International Conference on Multimedia and Expo (ICME 2026)", "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": "2026-07-17", "source": {"authors": ["Wei Feng", "Xin Wang", "Yu-Wei Zhan", "Yuwei Zhou", "Wenwu Zhu"], "categories": ["cs.CV", "cs.AI"], "id": "2607.15778", "title": "Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2607.15778"}, "sourceUpdatedAt": "2026-07-17T09:21:52Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted by 2026 IEEE International Conference on Multimedia and Expo (ICME 2026)", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted by 2026 IEEE International Conference on Multimedia and Expo (ICME 2026)", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.15778"}], "reviewStatus": "accepted", "venueName": "2026 IEEE International Conference on Multimedia and Expo (ICME 2026)"}], "whyItMatters": "Could support evaluation of long-video understanding, but primarily serves as a testbed for the proposed method."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
