{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.01515", "kind": "paper", "url": "https://arxiv.org/abs/2609.01515"}], "authors": ["Wenqi Pei", "Henry Hengyuan Zhao", "Yilai Liu", "Jiahao Meng", "Han Chen", "Ziyu Wang", "Hongyang Du"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.01515", "source_url": "https://arxiv.org/abs/2609.01515"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "A video cloze benchmark for visual temporal reasoning in Video-LLMs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.01515", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.01515", "title": "TempCloze"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.01515", "modality": null, "name": "TempCloze", "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": "false", "origin_record_id": "bm_tempcloze_ca030de5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ba1bd9b9a72ab91a249829c46909c6bb50fb3159359c808f2c92f96958ed63eb", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-03T00:59:34.317835Z", "source_url": "https://arxiv.org/abs/2609.01515"}, "publisher": null, "released": "2026-09-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.01515", "source_url": "https://arxiv.org/abs/2609.01515"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-01515", "source": "claire_radar", "source_benchmark_id": "2609.01515", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T06:30:32.214812Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.01515", "observedAt": "2026-08-31T04:56:28.279469Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T06:30:32.214812Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Video reasoning is a trending area, but no release details are provided.", "score": 35}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T00:59:34.317835Z", "inputHash": "58b1c33e5229845ae465bcc6d14d9cbe2bbda008b6923d7341f937b240d803e2", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs.", "canonicalNameSource": "abstract", "decisionReason": "No artifactEvidence or official project page is supplied to confirm reuse.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T00:59:34.317835Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A video cloze benchmark for visual temporal reasoning in Video-LLMs.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs."}, "familyId": "bmf_a400c20a5fd4", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_tempcloze_ca030de5", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.01515", "pdf": "https://arxiv.org/pdf/2609.01515", "project": null, "report": "https://arxiv.org/abs/2609.01515"}, "metrics": [], "motivation": "Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors.", "name": "TempCloze", "oneLine": "A video cloze benchmark for visual temporal reasoning in Video-LLMs.", "paperTitle": "TempCloze: Can Video-LLMs Identify the Missing Middle?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.01515", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "ranking": {"30d": {"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": 30}, "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}, "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}, "today": {"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": 2, "historyDate": "2026-08-31", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.65, "role": "bonus", "value": 65}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 16}, "method": "attention-ranking-v13", "rank": null, "score": 16}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-01", "source": {"authors": ["Wenqi Pei", "Henry Hengyuan Zhao", "Yilai Liu", "Jiahao Meng", "Han Chen", "Ziyu Wang", "Hongyang Du"], "categories": ["cs.CV", "cs.AI"], "id": "2609.01515", "title": "TempCloze: Can Video-LLMs Identify the Missing Middle?", "type": "arxiv", "url": "https://arxiv.org/abs/2609.01515"}, "sourceUpdatedAt": "2026-09-01T16:45:02Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Targets a core deficit in temporal reasoning for video-language models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
