{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.12412", "kind": "paper", "url": "https://arxiv.org/abs/2609.12412"}, {"id": "gh:beesfleas/holibench", "kind": "repo", "url": "https://github.com/beesfleas/HoliBench"}], "authors": ["Inesh Chakrabarti", "Zejun Xiong", "Pragya Sharma", "Mani Srivastava"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.12412", "source_url": "https://arxiv.org/abs/2609.12412"}, "categories": ["General AI", "Language & Knowledge", "cs.DC"], "description": {"en": "A modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency and energy for foundation models across platforms from single-board computers to GPU servers in CPS-IoT applications."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.12412", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.12412", "title": "HoliBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California, Los Angeles"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.12412", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.12412", "source_url": "https://openalex.org/W7212901432"}, "key": "claire-radar:2609.12412", "modality": null, "name": "HoliBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_holibench_6d2d4ecd", "origin_source": "arxiv", "recognition_confidence": "0.75", "record_sha256": "c632faf6e6ba20314a68c6b91121c1abbe7366ca98c65fee44afa7809058d6f2", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T06:44:31.931424Z", "source_url": "https://arxiv.org/abs/2609.12412"}, "publisher": null, "released": "2026-09-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.12412", "source_url": "https://arxiv.org/abs/2609.12412"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-12412", "source": "claire_radar", "source_benchmark_id": "2609.12412", "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": "https://github.com/beesfleas/HoliBench", "githubScope": "benchmark_repo", "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.12412", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Excluded records are not forecast for attention.", "score": 0}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T10:07:09.772218Z", "inputHash": "0869d4b39c0f886a2b385d6f0565faa2a042c9892a5a84681b70ce920af61052", "model": "deepseek-v4-flash"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We present HoliBench, a modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency, and energy across platforms from single-board computers to GPU servers.", "canonicalNameSource": "abstract", "decisionReason": "No explicit task suite, evaluator, or public scoring contract is described in the supplied evidence, despite a code link.", "evaluationEvidence": {"reuse": "The toolkit is released as open-source infrastructure, providing a platform abstraction layer and constraint-aware configuration selection for external deployment-aware evaluation.", "scoring": "Reports accuracy, inference latency, and energy consumption; single-model profiles compose to predict combined pipeline latency and power within 1.2% and 2.5%.", "task": "Jointly characterize foundation model accuracy, latency, and energy across heterogeneous edge and embedded platforms, supporting multiple model modalities, inference engines, and concurrency levels."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-14T06:44:31.931424Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency and energy for foundation models across platforms from single-board computers to GPU servers in CPS-IoT applications.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence", "public artifact URL"], "snippet": "We present HoliBench, a modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency, and energy across platforms from single-board computers to GPU servers."}, "familyId": "bmf_b393809a6b64", "firstSeenAt": "2026-09-14", "heat": null, "id": "bm_holibench_6d2d4ecd", "indexedAt": "2026-09-14T00:39:56.575498Z", "industrySectors": [], "links": {"code": "https://github.com/beesfleas/HoliBench", "data": null, "paper": "https://arxiv.org/abs/2609.12412", "pdf": "https://arxiv.org/pdf/2609.12412", "project": null, "report": "https://arxiv.org/abs/2609.12412"}, "metrics": [], "motivation": "Foundation models, including large language models, vision-language models, and time-series foundation models, are increasingly deployed on embedded and edge platforms for CPS and IoT applications, where energy, latency, and memory are as critical as task accuracy.", "name": "HoliBench", "oneLine": "A modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency and energy for foundation models across platforms from single-board computers to GPU servers in CPS-IoT applications.", "paperTitle": "HoliBench: A Cross-Platform Benchmarking and Deployment Toolkit for Foundation Models in CPS-IoT Applications", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.12412", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-14T00:39:56.575498Z"}, "publications": [], "ranking": {"30d": {"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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "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}, "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": "Runnable", "recognitionConfidence": 0.75, "relation": "introduces", "releasedAt": "2026-09-11", "source": {"authors": ["Inesh Chakrabarti", "Zejun Xiong", "Pragya Sharma", "Mani Srivastava"], "categories": ["cs.DC", "cs.LG", "cs.PF"], "id": "2609.12412", "title": "HoliBench: A Cross-Platform Benchmarking and Deployment Toolkit for Foundation Models in CPS-IoT Applications", "type": "arxiv", "url": "https://arxiv.org/abs/2609.12412"}, "sourceUpdatedAt": "2026-09-11T04:03:20Z", "topics": ["cs.DC"], "venueAttempts": [], "whyItMatters": "Cross-platform measurement of accuracy, latency and energy could help teams compare foundation-model deployment choices under shared conditions rather than platform-specific reports."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
