{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.23537", "kind": "paper", "url": "https://arxiv.org/abs/2607.23537"}, {"id": "gh:russellyq/obsdrivebench", "kind": "repo", "url": "https://github.com/russellyq/ObsDriveBench"}], "authors": ["Qiao Yan", "Yihan Wang", "Zhenghao Xing", "Jiaqi Xu", "Pheng-Ann Heng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.23537", "source_url": "https://arxiv.org/abs/2607.23537"}, "categories": ["Autonomous Driving", "Multimodal"], "description": {"en": "ObsDriveBench evaluates multimodal understanding in autonomous driving under adverse weather, covering observability awareness, spatial reliability, and risk-aware decision-making with multiple-choice tasks over camera, LiDAR, and radar inputs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.23537", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.23537", "title": "ObsDriveBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.23537", "modality": null, "name": "ObsDriveBench", "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_obsdrivebench_13a5d40b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0d4a9f3ea0e52234c796c28054fc7a9fdf00ae7c42950c237fe6ec0f35498f10", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.23537"}, "publisher": null, "released": "2026-07-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.23537", "source_url": "https://arxiv.org/abs/2607.23537"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-23537", "source": "claire_radar", "source_benchmark_id": "2607.23537", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Autonomous Driving"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/russellyq/ObsDriveBench", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.23537", "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", "state": "unavailable"}}, "status": "fresh"}, "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": "1b189325d747f14dcd6725eb7c971dae0b02064d2bff6eeecd592514a1f01262", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ObsDriveBench evaluates multimodal understanding in autonomous driving under adverse weather, covering observability awareness, spatial reliability, and risk-aware decision-making with multiple-choice tasks over camera, LiDAR, and radar inputs.", "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": "To study this, we introduce \\textbf{ObsDriveBench}, a real-world multi-modal benchmark for adverse-weather autonomous driving."}, "familyId": "bmf_75ddbe4da96d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/russellyq/ObsDriveBench", "url": "https://github.com/russellyq/ObsDriveBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/russellyq/ObsDriveBench", "url": "https://huggingface.co/papers/2607.23537"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/russellyq/ObsDriveBench", "url": "https://arxiv.org/abs/2607.23537"}], "scope": "benchmark_repo", "url": "https://github.com/russellyq/ObsDriveBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_obsdrivebench_13a5d40b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Automotive"], "links": {"code": "https://github.com/russellyq/ObsDriveBench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.23537", "paper": "https://arxiv.org/abs/2607.23537", "pdf": "https://arxiv.org/pdf/2607.23537", "project": null, "report": "https://arxiv.org/abs/2607.23537"}, "metrics": [], "motivation": "Autonomous driving under adverse weather remains a critical challenge, yet existing vision-language benchmarks mainly evaluate under standard conditions, synthetic corruptions, or single modality.", "name": "ObsDriveBench", "oneLine": "ObsDriveBench evaluates multimodal understanding in autonomous driving under adverse weather, covering observability awareness, spatial reliability, and risk-aware decision-making with multiple-choice tasks over camera, LiDAR, and radar inputs.", "paperTitle": "ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness", "primaryDomain": "Autonomous Driving", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.23537", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 270, "score": 31}, "method": "attention-ranking-v13", "rank": 270, "score": 31}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-26", "source": {"authors": ["Qiao Yan", "Yihan Wang", "Zhenghao Xing", "Jiaqi Xu", "Pheng-Ann Heng"], "categories": ["cs.AI"], "id": "2607.23537", "title": "ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness", "type": "arxiv", "url": "https://arxiv.org/abs/2607.23537"}, "sourceUpdatedAt": "2026-07-26T08:13:46Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing benchmarks rarely assess vision-language models under real-world adverse conditions with multimodal inputs. ObsDriveBench targets this gap by providing a fine-grained diagnosis of model behavior when observations are unreliable, supporting safer autonomous driving systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
