{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.07641", "kind": "paper", "url": "https://arxiv.org/abs/2606.07641"}], "authors": ["Lexin Wang", "Shenghua Liu", "Yiwei Wang", "Jiafeng Guo", "Xueqi Cheng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.07641", "source_url": "https://arxiv.org/abs/2606.07641"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Paired diagnostic benchmark for rotated-outcome prediction in vision-language models, spanning open visual cases and controlled text-image rotations, with accuracy metrics for direct reading and prediction."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.07641", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.07641", "title": "RotOutBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.07641", "modality": null, "name": "RotOutBench", "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_rotoutbench_a7d65303", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "3e68acdc2e53eca3b6240f5d45a6345fb50047184dab0ae697d69312d2926f1b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.07641"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.07641", "source_url": "https://arxiv.org/abs/2606.07641"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-07641", "source": "claire_radar", "source_benchmark_id": "2606.07641", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.07641", "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": "621eed638574e244809bd38bf77a7430150c1d406be542f2ddae745a35773eed", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Paired diagnostic benchmark for rotated-outcome prediction in vision-language models, spanning open visual cases and controlled text-image rotations, with accuracy metrics for direct reading and prediction.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "To isolate this gap, we introduce RotOutBench, a paired diagnostic benchmark spanning open visual cases and controlled text-image rotations."}, "familyId": "bmf_67067fe3674d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_rotoutbench_a7d65303", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.07641", "paper": "https://arxiv.org/abs/2606.07641", "pdf": "https://arxiv.org/pdf/2606.07641", "project": null, "report": "https://arxiv.org/abs/2606.07641"}, "metrics": [], "motivation": "Can vision-language models predict what a 180{\\deg} rotation would reveal from the original image alone?", "name": "RotOutBench", "oneLine": "Paired diagnostic benchmark for rotated-outcome prediction in vision-language models, spanning open visual cases and controlled text-image rotations, with accuracy metrics for direct reading and prediction.", "paperTitle": "Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.07641", "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": "2026-06-01", "source": {"authors": ["Lexin Wang", "Shenghua Liu", "Yiwei Wang", "Jiafeng Guo and Xueqi Cheng"], "categories": ["cs.CV"], "id": "2606.07641", "title": "Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2606.07641"}, "sourceUpdatedAt": "2026-06-01T14:16:09Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Evaluates a specific cognitive ability in VLMs, but lacks a standalone public comparison path."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
