{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.24094", "kind": "paper", "url": "https://arxiv.org/abs/2608.24094"}], "authors": ["Yicheng Zhu", "Tianmu Zhao", "Haoxin Leng", "Fan Zuo", "Tao Li", "Zilin Bian"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.24094", "source_url": "https://arxiv.org/abs/2608.24094"}, "categories": ["General AI", "Robotics & Embodied AI", "cs.RO"], "description": {"en": "SIREN-Bench-v1 is a benchmark for emergency-vehicle (EMV) interactions, built on a SUMO-CARLA co-simulation platform. It includes seven parameterized interaction templates across emergency levels L1-L3 and three behavior families, with synchronized sensor observations and simulator-native annotations. Supports tasks such as 3D object detection, trajectory prediction, and vision-language risk understanding."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.24094", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.24094", "title": "SIREN-Bench-v1"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.24094", "modality": null, "name": "SIREN-Bench-v1", "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": "true", "origin_record_id": "bm_siren-bench_1d0cc158", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "369306b6df09f85e42418cd23b59010e6999c42b2d563de2c0e98497767b2a7e", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:08:47.245811Z", "source_url": "https://arxiv.org/abs/2608.24094"}, "publisher": null, "released": "2026-08-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.24094", "source_url": "https://arxiv.org/abs/2608.24094"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-24094", "source": "claire_radar", "source_benchmark_id": "2608.24094", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Robotics & Embodied AI", "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/2608.24094", "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"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Addresses safety-critical autonomous driving with a unique co-simulation approach, likely to attract attention from robotics and transportation researchers.", "score": 75}, "capabilities": [], "confidence": "Medium", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "f5d6159b18985b0bac6cd821f18230ca15e8b68bd4bd2669ebec8b5d755d2f69", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions", "canonicalNameSource": "paper_title", "decisionReason": "Benchmark defines a repeatable evaluation platform with parameterized templates and evaluated tasks, and public release is stated in the abstract.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:08:47.245811Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SIREN-Bench-v1 is a benchmark for emergency-vehicle (EMV) interactions, built on a SUMO-CARLA co-simulation platform. It includes seven parameterized interaction templates across emergency levels L1-L3 and three behavior families, with synchronized sensor observations and simulator-native annotations. Supports tasks such as 3D object detection, trajectory prediction, and vision-language risk understanding.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence"], "snippet": "We instantiate the platform as \\textbf{SIREN-Bench-v1}, comprising seven parameterized interaction templates across emergency levels L1--L3 and three behavior families, with synchronized sensor observations and simulator-native annotations."}, "familyId": "bmf_94eafd231d5e", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_siren-bench_1d0cc158", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.24094", "pdf": "https://arxiv.org/pdf/2608.24094", "project": null, "report": "https://arxiv.org/abs/2608.24094"}, "metrics": [], "motivation": "Emergency vehicles (EMVs) can reorganize surrounding traffic as civilian vehicles brake, change lanes, or form rescue corridors in response to their passage.", "name": "SIREN-Bench-v1", "oneLine": "SIREN-Bench-v1 is a benchmark for emergency-vehicle (EMV) interactions, built on a SUMO-CARLA co-simulation platform. It includes seven parameterized interaction templates across emergency levels L1-L3 and three behavior families, with synchronized sensor observations and simulator-native annotations. Supports tasks such as 3D object detection, trajectory prediction, and vision-language risk understanding.", "paperTitle": "SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.24094", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.65, "relation": "introduces", "releasedAt": "2026-08-25", "source": {"authors": ["Yicheng Zhu", "Tianmu Zhao", "Haoxin Leng", "Fan Zuo", "Tao Li", "Zilin Bian"], "categories": ["cs.RO"], "id": "2608.24094", "title": "SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions", "type": "arxiv", "url": "https://arxiv.org/abs/2608.24094"}, "sourceUpdatedAt": "2026-08-25T05:41:34Z", "topics": ["cs.RO"], "venueAttempts": [], "whyItMatters": "Evaluating EMV interactions requires behavior-level control over both EMV privileges and civilian responses, which existing benchmarks lack. SIREN-Bench-v1 provides a reproducible co-simulation environment with behavior-dependent failure modes, enabling standard evaluation for safety-critical autonomous driving research."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
