{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.04588", "kind": "paper", "url": "https://arxiv.org/abs/2606.04588"}], "authors": ["Huangchen Xu", "Yuan Wu", "Yi Chang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.04588", "source_url": "https://arxiv.org/abs/2606.04588"}, "categories": ["General AI", "Vision & 3D", "cs.CL"], "description": {"en": "Evaluates complex instruction following for video understanding across content, format, style, and structure constraints with 306 test instructions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.04588", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.04588", "title": "VCIFBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.04588", "modality": null, "name": "VCIFBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_vcifbench_33b2eb08", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "617ab42d0f1a4dff8855d3f2f46cb618e34854a8205de7634403c1197714d38a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.04588"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.04588", "source_url": "https://arxiv.org/abs/2606.04588"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-04588", "source": "claire_radar", "source_benchmark_id": "2606.04588", "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/2606.04588", "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": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "a0650f57d226b4afb6aa37efdb4be71bc755d1d86b26e2289def51ca7d3cbada", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates complex instruction following for video understanding across content, format, style, and structure constraints with 306 test instructions.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce VCIFBench, a benchmark for evaluating complex instruction following in video understanding."}, "familyId": "bmf_6ff650c908db", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_vcifbench_33b2eb08", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.04588", "paper": "https://arxiv.org/abs/2606.04588", "pdf": "https://arxiv.org/pdf/2606.04588", "project": null, "report": "https://arxiv.org/abs/2606.04588"}, "metrics": [], "motivation": "Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether models can satisfy explicit output constraints.", "name": "VCIFBench", "oneLine": "Evaluates complex instruction following for video understanding across content, format, style, and structure constraints with 306 test instructions.", "paperTitle": "VCIFBench: Evaluating Complex Instruction Following for Video Understanding", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.04588", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Huangchen Xu", "Yuan Wu", "Yi Chang"], "categories": ["cs.CL"], "id": "2606.04588", "title": "VCIFBench: Evaluating Complex Instruction Following for Video Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2606.04588"}, "sourceUpdatedAt": "2026-06-03T08:27:53Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Could address the need for video benchmarks testing explicit output constraints, but lacks public evidence of reuse path."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
