{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03890", "kind": "paper", "url": "https://arxiv.org/abs/2606.03890"}, {"id": "gh:internlm/ovo-s-bench", "kind": "repo", "url": "https://github.com/InternLM/OVO-S-Bench"}, {"kind": "website", "url": "https://internlm.github.io/OVO-S-Bench/"}], "authors": ["Yifei Li", "Pengyiang Liu", "Yuhang Zang", "Zhongyue Shi", "Qi Fu", "Hongye Hao", "Jiwen Lu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03890", "source_url": "https://arxiv.org/abs/2606.03890"}, "categories": ["Autonomous Driving", "Multimodal"], "description": {"en": "OVO-S-Bench evaluates streaming spatial intelligence in MLLMs with 1,680 human-annotated questions across four abstraction levels, using streaming prefixes and evidence intervals."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03890", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03890", "title": "OVO-S-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.03890", "modality": null, "name": "OVO-S-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_ovo-s-bench_86757d1b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3817e8d88f547938cd8fd8f414ca7042f6a555e51034b346a759260090801f0a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03890"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03890", "source_url": "https://arxiv.org/abs/2606.03890"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03890", "source": "claire_radar", "source_benchmark_id": "2606.03890", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Autonomous Driving"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/InternLM/OVO-S-Bench", "githubScope": "benchmark_repo", "githubStars": 56, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 31, "hfPaperUrl": "https://huggingface.co/papers/2606.03890", "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": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "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": "793c04437aa772c94e4348fc66818bbd073cbb74c4760c56d616a826c0105775", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OVO-S-Bench evaluates streaming spatial intelligence in MLLMs with 1,680 human-annotated questions across four abstraction levels, using streaming prefixes and evidence intervals.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce OVO-S-Bench, a fully human-annotated benchmark for streaming spatial intelligence, comprising 1,680 questions over 348 source videos."}, "familyId": "bmf_0f3bc6059546", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/InternLM/OVO-S-Bench", "url": "https://github.com/InternLM/OVO-S-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/InternLM/OVO-S-Bench", "url": "https://huggingface.co/papers/2606.03890"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/InternLM/OVO-S-Bench", "url": "https://internlm.github.io/OVO-S-Bench/"}], "scope": "benchmark_repo", "url": "https://github.com/InternLM/OVO-S-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ovo-s-bench_86757d1b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Automotive"], "links": {"code": "https://github.com/InternLM/OVO-S-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.03890", "paper": "https://arxiv.org/abs/2606.03890", "pdf": "https://arxiv.org/pdf/2606.03890", "project": "https://internlm.github.io/OVO-S-Bench/", "report": "https://arxiv.org/abs/2606.03890"}, "metrics": [], "motivation": "Multimodal agents in robotics, AR, and autonomous driving must reason about places and layouts from continuous egocentric streams, often using evidence outside the current view.", "name": "OVO-S-Bench", "oneLine": "OVO-S-Bench evaluates streaming spatial intelligence in MLLMs with 1,680 human-annotated questions across four abstraction levels, using streaming prefixes and evidence intervals.", "paperTitle": "OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs", "primaryDomain": "Autonomous Driving", "publication": {"evidence": "Accepted to EMNLP 2026 Main Conference. 55 pages, 12 figures, 20 tables. Project page: https://internlm.github.io/OVO-S-Bench/", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.03890", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 Main Conference", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "InternLM", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/InternLM/OVO-S-Bench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Yifei Li", "Pengyiang Liu", "Yuhang Zang", "Zhongyue Shi", "Qi Fu", "Hongye Hao", "Jiwen Lu"], "categories": ["cs.CV"], "id": "2606.03890", "title": "OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03890"}, "sourceUpdatedAt": "2026-06-02T16:51:32Z", "topics": ["Multimodal"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026 Main Conference. 55 pages, 12 figures, 20 tables. Project page: https://internlm.github.io/OVO-S-Bench/", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to EMNLP 2026 Main Conference. 55 pages, 12 figures, 20 tables. Project page: https://internlm.github.io/OVO-S-Bench/", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.03890"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 Main Conference"}], "whyItMatters": "Addresses the gap in evaluating spatial reasoning from continuous egocentric streams, providing a standardized benchmark with human annotation and clear evaluation protocols."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
