{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25529", "kind": "paper", "url": "https://arxiv.org/abs/2608.25529"}, {"id": "gh:alexios-hub/video-ifbench", "kind": "repo", "url": "https://github.com/Alexios-hub/Video-IFBench"}], "authors": ["Hongbo Liu", "Peixian Chen", "Sihan Liu", "Peiyuan Zhang", "Kai Zou", "Dian Zheng", "Xiaoxing Hu", "Yuhao Dong", "Mengdan Zhang", "Yunhang Shen", "Haoyu Cao", "Wei Liu", "Weibo Gu", "Xing Sun", "Shengjie Zhao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25529", "source_url": "https://arxiv.org/abs/2608.25529"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Evaluates instruction following of multimodal LLMs in video understanding with 1.5K samples across constraint categories."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25529", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25529", "title": "Video-IFBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.25529", "modality": null, "name": "Video-IFBench", "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": "true", "origin_record_id": "bm_video-ifbench_4fc7a0ab", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6d880280a527e14c17f27e5957b98fb85591ff4d64bf9f2cf5ef122883035ce0", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.25529"}, "publisher": null, "released": "2026-08-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25529", "source_url": "https://arxiv.org/abs/2608.25529"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25529", "source": "claire_radar", "source_benchmark_id": "2608.25529", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Alexios-hub/Video-IFBench", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 17, "hfPaperUrl": "https://huggingface.co/papers/2608.25529", "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": "2026-09-24", "state": "stale"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Without released artifacts, interest may remain limited to paper readers despite the benchmark's topical relevance.", "score": 10}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:12:36.511123Z", "inputHash": "dd6e3a99912f549e400c2e2765a9d6888b5beafd1a804420beabda33caf84ae0", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates instruction following of multimodal LLMs in video understanding with 1.5K samples across constraint categories.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce Video-IFBench, a comprehensive benchmark for evaluating instruction following in video understanding, where models must satisfy diverse user-specified constraints, including those grounded in visual and audio content."}, "familyId": "bmf_cff0b9680f66", "firstSeenAt": "2026-08-29", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Alexios-hub/Video-IFBench", "url": "https://github.com/Alexios-hub/Video-IFBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Alexios-hub/Video-IFBench", "url": "https://huggingface.co/papers/2608.25529"}], "scope": "benchmark_repo", "url": "https://github.com/Alexios-hub/Video-IFBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_video-ifbench_4fc7a0ab", "indexedAt": "2026-08-29T08:02:23.506802Z", "industrySectors": [], "links": {"code": "https://github.com/Alexios-hub/Video-IFBench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.25529", "paper": "https://arxiv.org/abs/2608.25529", "pdf": "https://arxiv.org/pdf/2608.25529", "project": null, "report": "https://arxiv.org/abs/2608.25529"}, "metrics": [], "motivation": "Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding.", "name": "Video-IFBench", "oneLine": "Evaluates instruction following of multimodal LLMs in video understanding with 1.5K samples across constraint categories.", "paperTitle": "Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.25529", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.5107131090274512, "value": 17}}, "confidence": "Medium", "coverage": 0.7, "rank": 238, "score": 31}, "method": "attention-ranking-v13", "rank": 238, "score": 31}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-26", "source": {"authors": ["Hongbo Liu", "Peixian Chen", "Sihan Liu", "Peiyuan Zhang", "Kai Zou", "Dian Zheng", "Xiaoxing Hu", "Yuhao Dong", "Mengdan Zhang", "Yunhang Shen", "Haoyu Cao", "Wei Liu", "Weibo Gu", "Xing Sun", "Shengjie Zhao"], "categories": ["cs.CV"], "id": "2608.25529", "title": "Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25529"}, "sourceUpdatedAt": "2026-08-26T08:35:42Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses the underexplored area of instruction adherence in video understanding, where user-specified constraints are crucial."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
