{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.22279", "kind": "paper", "url": "https://arxiv.org/abs/2608.22279"}], "authors": ["Naiming Liu", "Zhiheng Wu", "Shuning Wang", "Tie Zhang", "Bowen Liu", "Tong Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.22279", "source_url": "https://arxiv.org/abs/2608.22279"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates VLMs on online video question answering under user interruptions, with offline simulation and multi-dimensional metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.22279", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.22279", "title": "OVIBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.22279", "modality": null, "name": "OVIBench", "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": "true", "origin_record_id": "bm_ovibench_2e515c0e", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "ab0985fb8faad20cad853f3aa7fbfacb4dc5abd55efa0fc52bf6de1d95f0ace8", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.22279"}, "publisher": null, "released": "2026-08-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.22279", "source_url": "https://arxiv.org/abs/2608.22279"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-22279", "source": "claire_radar", "source_benchmark_id": "2608.22279", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-26T06:23:37.320575Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.22279", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-26T06:23:37.320575Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Interruption handling in video QA is a novel and practically relevant topic likely to attract moderate interest from VLM researchers.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:18:56.318436Z", "inputHash": "d6e638351a4681cac0a45690d104520594aac927b23370b050707cb1e9fa1150", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "OVIBench: Benchmarking Online Video Question Answering under Interruption", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark name is explicit, the paper describes standardized evaluation protocols, and a public release is announced.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates VLMs on online video question answering under user interruptions, with offline simulation and multi-dimensional metrics.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence"], "snippet": "To address this gap, we formulate the task of Online Video Question Answering under Interruption and introduce OVIBench, the first standardized benchmark for evaluating VLMs in this setting."}, "familyId": "bmf_007a9bd03766", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_ovibench_2e515c0e", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.22279", "pdf": "https://arxiv.org/pdf/2608.22279", "project": null, "report": "https://arxiv.org/abs/2608.22279"}, "metrics": [], "motivation": "Recent vision language models (VLMs) have achieved strong progress in video understanding.", "name": "OVIBench", "oneLine": "Evaluates VLMs on online video question answering under user interruptions, with offline simulation and multi-dimensional metrics.", "paperTitle": "OVIBench: Benchmarking Online Video Question Answering under Interruption", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.22279", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v12", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v12", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.65, "relation": "introduces", "releasedAt": "2026-08-23", "source": {"authors": ["Naiming Liu", "Zhiheng Wu", "Shuning Wang", "Tie Zhang", "Bowen Liu", "Tong Wang"], "categories": ["cs.CV", "cs.AI"], "id": "2608.22279", "title": "OVIBench: Benchmarking Online Video Question Answering under Interruption", "type": "arxiv", "url": "https://arxiv.org/abs/2608.22279"}, "sourceUpdatedAt": "2026-08-23T08:12:08Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Addresses the gap between offline benchmarks and real-time interactive video QA, which is essential for practical VLM deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
