{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.18181", "kind": "paper", "url": "https://arxiv.org/abs/2607.18181"}, {"id": "hf:anonymousvehbench/vehbench", "kind": "dataset", "url": "https://huggingface.co/datasets/AnonymousVehbench/vehbench"}], "authors": ["Depeng Su", "Yuyu Luo", "Guobiao Hu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.18181", "source_url": "https://arxiv.org/abs/2607.18181"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "VEHBench is a diagnostic benchmark for LLM-assisted vibration energy harvester design, featuring 763 tasks across four design roles: specification triage, verifier-guided search, corrupted-state recovery, and policy-conditioned selection. It uses an analytical physical oracle for scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.18181", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.18181", "title": "VEHBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hong Kong University of Science and Technology", "University of Hong Kong"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.18181", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.18181", "source_url": "https://openalex.org/W7169851886"}, "key": "claire-radar:2607.18181", "modality": null, "name": "VEHBench", "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_vehbench_bf410800", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "48310e57b50d3c6381ce42229ded9d0edb6b692af8fed8eb81b4d5ac9093b3d9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.18181"}, "publisher": null, "released": "2026-07-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.18181", "source_url": "https://arxiv.org/abs/2607.18181"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-18181", "source": "claire_radar", "source_benchmark_id": "2607.18181", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "AnonymousVehbench/vehbench", "hfDatasetDownloads": 213, "hfDatasetLikes": 0, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.18181", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "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": "61fb0c8f13e3ab2a6f85fbcdd64789d095d4786248f6dc1a188b312d6f16662d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VEHBench is a diagnostic benchmark for LLM-assisted vibration energy harvester design, featuring 763 tasks across four design roles: specification triage, verifier-guided search, corrupted-state recovery, and policy-conditioned selection. It uses an analytical physical oracle for scoring.", "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 VEHBench, an engineering-native diagnostic benchmark for LLM-assisted VEH design, featuring 763 literature-grounded tasks scored by an analytical physical oracle."}, "familyId": "bmf_06afd602ad70", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_vehbench_bf410800", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": "https://huggingface.co/datasets/AnonymousVehbench/vehbench", "hfPaper": "https://huggingface.co/papers/2607.18181", "paper": "https://arxiv.org/abs/2607.18181", "pdf": "https://arxiv.org/pdf/2607.18181", "project": null, "report": "https://arxiv.org/abs/2607.18181"}, "metrics": [], "motivation": "Battery-free Internet of Things (IoT) requires iterative design of vibration energy harvesters (VEHs) under coupled physical constraints, while LLMs are emerging as interface layers for engineering workflows.", "name": "VEHBench", "oneLine": "VEHBench is a diagnostic benchmark for LLM-assisted vibration energy harvester design, featuring 763 tasks across four design roles: specification triage, verifier-guided search, corrupted-state recovery, and policy-conditioned selection. It uses an analytical physical oracle for scoring.", "paperTitle": "VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.18181", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 43, "datasetRankPopulation": 85, "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": 0.5525877962214227, "value": 213}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 52, "score": 52}, "method": "attention-ranking-v13", "rank": 52, "score": 52}}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-20", "source": {"authors": ["Depeng Su", "Yuyu Luo and Guobiao Hu"], "categories": ["cs.CL", "cs.SE"], "id": "2607.18181", "title": "VEHBench: A Stage-Local Diagnostic Benchmark for LLM-Assisted Vibration Energy Harvester Design", "type": "arxiv", "url": "https://arxiv.org/abs/2607.18181"}, "sourceUpdatedAt": "2026-07-20T17:17:05Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the need for stage-local evaluation of LLMs in coupled physical design workflows, revealing stage-dependent capabilities and response-control patterns. It provides practical value for selecting and routing models in engineering applications, highlighting that no single model dominates all stages."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
