{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.09547", "kind": "paper", "url": "https://arxiv.org/abs/2606.09547"}, {"kind": "website", "url": "https://apratimbh.github.io/livecookv2/"}], "authors": ["Apratim Bhattacharyya", "Shweta Mahajan", "Sanjay Haresh", "Rajeev Yasarla", "Reza Pourreza", "Litian Liu", "Risheek Garrepalli", "Roland Memisevic"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.09547", "source_url": "https://arxiv.org/abs/2606.09547"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Ego-MC-Bench is a benchmark for evaluating reactive step-by-step task guidance in cooking scenarios, focusing on timely interventions when mistakes occur."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.09547", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.09547", "title": "Ego-MC-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Qualcomm (United States)", "York University", "Vector Institute"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.09547", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.09547", "source_url": "https://openalex.org/W7164054598"}, "key": "claire-radar:2606.09547", "modality": null, "name": "Ego-MC-Bench", "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": "unknown", "origin_record_id": "bm_ego-mc-bench_91c3532a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "fc87c8c1587ef76274d90b856300340a32a62986428a6cc432be4faa43c5f05b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.09547"}, "publisher": null, "released": "2026-06-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.09547", "source_url": "https://arxiv.org/abs/2606.09547"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-09547", "source": "claire_radar", "source_benchmark_id": "2606.09547", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "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/2606.09547", "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": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "efe3fea054f05e12cc57d5c8a88984974ac3199414ebe5a629dea5eda6950954", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Ego-MC-Bench is a benchmark for evaluating reactive step-by-step task guidance in cooking scenarios, focusing on timely interventions when mistakes occur.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To evaluate this crucial capability, we introduce Ego-MC-Bench (Mistake Corrections), a benchmark for evaluating reactive, step-by-step task guidance in realistic cooking scenarios."}, "familyId": "bmf_4df235e7cb24", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_ego-mc-bench_91c3532a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.09547", "paper": "https://arxiv.org/abs/2606.09547", "pdf": "https://arxiv.org/pdf/2606.09547", "project": "https://apratimbh.github.io/livecookv2/", "report": "https://arxiv.org/abs/2606.09547"}, "metrics": [], "motivation": "Learning everyday skills, like cooking a dish, relies increasingly on instructional media such as online videos.", "name": "Ego-MC-Bench", "oneLine": "Ego-MC-Bench is a benchmark for evaluating reactive step-by-step task guidance in cooking scenarios, focusing on timely interventions when mistakes occur.", "paperTitle": "Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.09547", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-08", "source": {"authors": ["Apratim Bhattacharyya", "Shweta Mahajan", "Sanjay Haresh", "Rajeev Yasarla", "Reza Pourreza", "Litian Liu", "Risheek Garrepalli", "Roland Memisevic"], "categories": ["cs.CV", "cs.LG"], "id": "2606.09547", "title": "Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?", "type": "arxiv", "url": "https://arxiv.org/abs/2606.09547"}, "sourceUpdatedAt": "2026-06-17T20:05:01Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the capability of video LLMs to intervene proactively during task execution, which is crucial for practical guidance assistants."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
