{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.15410", "kind": "paper", "url": "https://arxiv.org/abs/2608.15410"}], "authors": ["Rajat Bhattacharjya", "Yoomee Jung", "Minwoo Kim", "Sing-Yao Wu", "Eli Bozorgzadeh", "Nalini Venkatasubramanian", "Nikil Dutt"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.15410", "source_url": "https://arxiv.org/abs/2608.15410"}, "categories": ["Reasoning", "Robotics & Embodied AI"], "description": {"en": "FloodReasonBench is a benchmark for vision-language model reasoning segmentation in flood response scenarios. It introduces FloodResponseSeg, a flood-specific dataset, and evaluates pipelines under lightweight visual encoding, split inference, and compressed representations. It also measures accuracy, latency, energy, and communication tradeoffs on an embedded platform."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.15410", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.15410", "title": "FloodReasonBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California, Irvine", "Kookmin University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.15410", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.15410", "source_url": "https://openalex.org/W7203670691"}, "key": "claire-radar:2608.15410", "modality": null, "name": "FloodReasonBench", "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_floodreasonbench_bd08edc8", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "afd02bf6038c0e06446bafe22f3eb5cc1523b0df3a33e64a56182d41f26c1a6f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.15410"}, "publisher": null, "released": "2026-08-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.15410", "source_url": "https://arxiv.org/abs/2608.15410"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-15410", "source": "claire_radar", "source_benchmark_id": "2608.15410", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied 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/2608.15410", "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": ["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": "b194550bd74d53b69aa27092dc5f9186a08edb06b78004764fcfa55eda96ab14", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FloodReasonBench is a benchmark for vision-language model reasoning segmentation in flood response scenarios. It introduces FloodResponseSeg, a flood-specific dataset, and evaluates pipelines under lightweight visual encoding, split inference, and compressed representations. It also measures accuracy, latency, energy, and communication tradeoffs on an embedded platform.", "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 present FloodReasonBench, a benchmark for VLM reasoning segmentation for embodied flood response at the edge."}, "familyId": "bmf_c65f287d8be1", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_floodreasonbench_bd08edc8", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.15410", "paper": "https://arxiv.org/abs/2608.15410", "pdf": "https://arxiv.org/pdf/2608.15410", "project": null, "report": "https://arxiv.org/abs/2608.15410"}, "metrics": [], "motivation": "Reasoning segmentation enables vision-language models (VLMs) to translate mission-relevant language requests into pixel-level visual grounding, offering a natural perception interface for embodied agents.", "name": "FloodReasonBench", "oneLine": "FloodReasonBench is a benchmark for vision-language model reasoning segmentation in flood response scenarios. It introduces FloodResponseSeg, a flood-specific dataset, and evaluates pipelines under lightweight visual encoding, split inference, and compressed representations. It also measures accuracy, latency, energy, and communication tradeoffs on an embedded platform.", "paperTitle": "FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.15410", "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": "2026-08-15", "source": {"authors": ["Rajat Bhattacharjya", "Yoomee Jung", "Minwoo Kim", "Sing-Yao Wu", "Eli Bozorgzadeh", "Nalini Venkatasubramanian", "Nikil Dutt"], "categories": ["cs.DC", "cs.AI", "cs.CV", "cs.RO", "cs.SY", "eess.SY"], "id": "2608.15410", "title": "FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge", "type": "arxiv", "url": "https://arxiv.org/abs/2608.15410"}, "sourceUpdatedAt": "2026-08-15T20:56:39Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Reasoning segmentation for flood response has domain-specific constraints, and this benchmark characterizes model performance and system-level tradeoffs at the edge, which could inform deployment decisions for resource-constrained platforms."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
