{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24422", "kind": "paper", "url": "https://arxiv.org/abs/2606.24422"}, {"kind": "repo", "url": "https://github.com/leiyj23/EgoSAT/blob/main/docs/model_guide.md"}, {"kind": "website", "url": "https://leiyj23.github.io/EgoSAT/"}], "authors": ["Yijia Lei", "Jinzhao Li", "Yichi Zhang", "Jiacheng Hua", "Yin Li", "Miao Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24422", "source_url": "https://arxiv.org/abs/2606.24422"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "EgoSAT evaluates vision-language models on egocentric video reasoning in streaming settings. It contains 1,997 videos (165 hours) and about 4,800 QA pairs covering retrospective, online, and prospective reasoning tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24422", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24422", "title": "EgoSAT"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.24422", "modality": null, "name": "EgoSAT", "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_egosat_1b88fd52", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a4db4a5d35a9b88ebccb0038bfee386be8fc1bf86b3e5a4031aefa4035959130", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24422"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24422", "source_url": "https://arxiv.org/abs/2606.24422"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24422", "source": "claire_radar", "source_benchmark_id": "2606.24422", "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/leiyj23/EgoSAT", "githubScope": "hosting_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.24422", "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": "2026-10-04", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "6a329f1bd677c01702fb8c5b6626912e87069c971f8da4966f3953260f71da1c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EgoSAT evaluates vision-language models on egocentric video reasoning in streaming settings. It contains 1,997 videos (165 hours) and about 4,800 QA pairs covering retrospective, online, and prospective reasoning tasks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce EgoSAT, the first comprehensive benchmark for egocentric video reasoning in streaming settings, designed to evaluate the capabilities of modern vision-language models (VLMs)."}, "familyId": "bmf_710c21ef2296", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/leiyj23/EgoSAT", "url": "https://leiyj23.github.io/EgoSAT/"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/leiyj23/EgoSAT/blob/main/docs/model_guide.md", "url": "https://leiyj23.github.io/EgoSAT/"}], "scope": "benchmark_repo", "url": "https://github.com/leiyj23/EgoSAT", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_egosat_1b88fd52", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/leiyj23/EgoSAT/blob/main/docs/model_guide.md", "data": null, "hfPaper": "https://huggingface.co/papers/2606.24422", "paper": "https://arxiv.org/abs/2606.24422", "pdf": "https://arxiv.org/pdf/2606.24422", "project": "https://leiyj23.github.io/EgoSAT/", "report": "https://arxiv.org/abs/2606.24422"}, "metrics": [], "motivation": "We introduce EgoSAT, the first comprehensive benchmark for egocentric video reasoning in streaming settings, designed to evaluate the capabilities of modern vision-language models (VLMs).", "name": "EgoSAT", "oneLine": "EgoSAT evaluates vision-language models on egocentric video reasoning in streaming settings. It contains 1,997 videos (165 hours) and about 4,800 QA pairs covering retrospective, online, and prospective reasoning tasks.", "paperTitle": "EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to ECCV 2026. Project page: https://leiyj23.github.io/EgoSAT/", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.24422", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECCV 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "EgoSAT Project", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://leiyj23.github.io/EgoSAT/"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Yijia Lei", "Jinzhao Li", "Yichi Zhang", "Jiacheng Hua", "Yin Li", "Miao Liu"], "categories": ["cs.CV"], "id": "2606.24422", "title": "EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24422"}, "sourceUpdatedAt": "2026-06-23T10:59:25Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to ECCV 2026. Project page: https://leiyj23.github.io/EgoSAT/", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to ECCV 2026. Project page: https://leiyj23.github.io/EgoSAT/", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.24422"}], "reviewStatus": "accepted", "venueName": "ECCV 2026"}], "whyItMatters": "Serves as a unified benchmark for streaming egocentric interaction understanding, enabling assessment of temporal reasoning and confidence calibration in VLMs, which is crucial for reliable deployment in real-time applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
