{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.23870", "kind": "paper", "url": "https://arxiv.org/abs/2607.23870"}], "authors": ["Belal S. Alsinglawi", "Weizheng Wang", "Junyi Wu", "Lianhai Lin", "Merouane Debbah", "Izzat Alsmadi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.23870", "source_url": "https://arxiv.org/abs/2607.23870"}, "categories": ["General AI", "Multimodal"], "description": {"en": "An offline protocol-conditioned benchmark for Vision-Language-Action UAV agents, evaluating operational context understanding, multimodal evidence arbitration, degradation-aware reasoning, and risk-aware action planning across 3,024 samples with semantic scoring and structural diagnostics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.23870", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.23870", "title": "MulRobBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Zayed University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.23870", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.23870", "source_url": "https://openalex.org/W7171552391"}, "key": "claire-radar:2607.23870", "modality": null, "name": "MulRobBench", "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_mulrobbench_1e33deff", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "8efbbdbc4e70b8d998b06d80743dacc9b0d5dd91233bf340d4bb4b5d5497add7", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.23870"}, "publisher": null, "released": "2026-07-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.23870", "source_url": "https://arxiv.org/abs/2607.23870"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-23870", "source": "claire_radar", "source_benchmark_id": "2607.23870", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.23870", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "7682d3bd8cd4ab6557a48eb7c2a9eca8ef94a2f94d0283ca218d970cdb977320", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "An offline protocol-conditioned benchmark for Vision-Language-Action UAV agents, evaluating operational context understanding, multimodal evidence arbitration, degradation-aware reasoning, and risk-aware action planning across 3,024 samples with semantic scoring and structural diagnostics.", "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"], "snippet": "We introduce MulRobBench, an offline, protocol-conditioned benchmark for Vision-Language-Action (VLA) UAV agents in smart-city environments."}, "familyId": "bmf_65e0c7a5af31", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mulrobbench_1e33deff", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.23870", "paper": "https://arxiv.org/abs/2607.23870", "pdf": "https://arxiv.org/pdf/2607.23870", "project": null, "report": "https://arxiv.org/abs/2607.23870"}, "metrics": [], "motivation": "Smart-city airspace is transforming Uncrewed Aerial Vehicles (UAVs) from passive sensing platforms into cyber-physical decision makers that must follow operational rules under degraded observations and ambiguous language.", "name": "MulRobBench", "oneLine": "An offline protocol-conditioned benchmark for Vision-Language-Action UAV agents, evaluating operational context understanding, multimodal evidence arbitration, degradation-aware reasoning, and risk-aware action planning across 3,024 samples with semantic scoring and structural diagnostics.", "paperTitle": "MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.23870", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "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": 1.0, "relation": "introduces", "releasedAt": "2026-07-26", "source": {"authors": ["Belal S. Alsinglawi", "Weizheng Wang", "Junyi Wu", "Yi Jiang", "Lianhai Lin", "Merouane Debbah", "and Izzat Alsmadi"], "categories": ["cs.MA", "cs.AI"], "id": "2607.23870", "title": "MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2607.23870"}, "sourceUpdatedAt": "2026-07-26T22:23:43Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Most UAV benchmarks focus on perception or navigation, leaving a gap in assessing coupled physical evidence, protocol constraints, and action risk. MulRobBench's diagnostic dimensions could inform safety-critical UAV deployment decisions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
