{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.09396", "kind": "paper", "url": "https://arxiv.org/abs/2609.09396"}, {"id": "hf:nvidia/physicalai-vantage-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/nvidia/PhysicalAI-VANTAGE-Bench"}, {"kind": "website", "url": "https://vantage-bench.org/"}], "authors": ["Zaid Pervaiz Bhat", "Nimra Nayyar", "Arihant Jain", "Lap Fung Chan", "John Suchanek", "Yu Wang", "Varun Praveen", "Tomasz Kornuta", "Vidya Nariyambut Murali"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.09396", "source_url": "https://arxiv.org/abs/2609.09396"}, "categories": ["Logistics & Operations", "Multimodal"], "description": {"en": "Evaluates vision-language models on infrastructure camera video across logistics, transportation, and smart spaces using eight spatio-temporal tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.09396", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.09396", "title": "VANTAGE-BENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Clemson University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.09396", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.09396", "source_url": "https://openalex.org/W7212144841"}, "key": "claire-radar:2609.09396", "modality": null, "name": "VANTAGE-BENCH", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "High", "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_vantage-bench_f8c64682", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2c5122e5e1ad02655d46515c2df1ee1215240d030a8a716663fcfc2ca684c1ee", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-10T00:52:28.558291Z", "source_url": "https://arxiv.org/abs/2609.09396"}, "publisher": null, "released": "2026-09-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.09396", "source_url": "https://arxiv.org/abs/2609.09396"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-09396", "source": "claire_radar", "source_benchmark_id": "2609.09396", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Clemson-Capstone/VANTAGE-Bench", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": "nvidia/PhysicalAI-VANTAGE-Bench", "hfDatasetDownloads": 1854, "hfDatasetLikes": 16, "hfPaperUpvotes": 6, "hfPaperUrl": "https://huggingface.co/papers/2609.09396", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark covers practical infrastructure domains with a large public dataset and a leaderboard, which may attract broad interest from vision-language and applied AI researchers.", "score": 65}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-10T00:52:28.558291Z", "inputHash": "0c758fb54700f5ab08465e64eaebb22bdf2959693e5cc39a98262579baef59fa", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We introduce VANTAGE-Bench, a benchmark measuring this \"Infrastructure AI Gap.\"", "canonicalNameSource": "abstract", "decisionReason": "The benchmark provides a released dataset, submission portal, and leaderboard, establishing a public evaluation path.", "evaluationEvidence": {"reuse": "The VANTAGE-Bench GitHub repository provides a sample evaluation pipeline for generating model predictions.", "scoring": "Submit predictions via the VANTAGE-Bench submission portal and track results on the official leaderboard.", "task": "It spans three operational domains (Logistics, Transportation, and Smart Spaces), unifies image and video evaluation across semantic, spatial, temporal, and spatio-temporal capabilities, and moves beyond multiple-choice to eight task formulations including dense captioning and spatio-temporal grounding."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-10T00:52:28.558291Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vision-language models on infrastructure camera video across logistics, transportation, and smart spaces using eight spatio-temporal tasks.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "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 VANTAGE-Bench, a benchmark measuring this \"Infrastructure AI Gap.\" It spans three operational domains (Logistics, Transportation, and Smart Spaces), unifies image and video evaluation across semantic, spatial, temporal, and spatio-temporal capabilities, and moves beyond multiple-choice to eight task formulations including dense captioning and spatio-temporal grounding."}, "familyId": "bmf_1510672f77a0", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_vantage-bench_f8c64682", "indexedAt": "2026-09-10T00:47:26.889471Z", "industrySectors": ["Logistics"], "links": {"code": null, "data": "https://huggingface.co/datasets/nvidia/PhysicalAI-VANTAGE-Bench", "paper": "https://arxiv.org/abs/2609.09396", "pdf": "https://arxiv.org/pdf/2609.09396", "project": "https://vantage-bench.org/", "report": "https://arxiv.org/abs/2609.09396"}, "metrics": [], "motivation": "As Vision-Language Models (VLMs) advance toward physical deployment, the focus has remained on action-oriented Embodied AI evaluated on subject-centric consumer video.", "name": "VANTAGE-BENCH", "oneLine": "Evaluates vision-language models on infrastructure camera video across logistics, transportation, and smart spaces using eight spatio-temporal tasks.", "paperTitle": "VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.09396", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-10T00:47:26.889471Z"}, "publications": [], "publishers": [{"name": "NVIDIA", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/datasets/nvidia/PhysicalAI-VANTAGE-Bench"}], "ranking": {"30d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 4, "datasetRankPopulation": 34, "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": 0.16198483906027114, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.906239849750241, "value": 1854}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.36232383170565413, "value": 6}}, "confidence": "High", "coverage": 1.0, "rank": 64, "score": 33}, "method": "attention-ranking-v13", "rank": 64, "score": 33}, "90d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 9, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.7749898242784282, "value": 1854}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.34383183387990046, "value": 6}}, "confidence": "High", "coverage": 1.0, "rank": 166, "score": 36}, "method": "attention-ranking-v13", "rank": 166, "score": 36}}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-08", "source": {"authors": ["Zaid Pervaiz Bhat", "Nimra Nayyar", "Arihant Jain", "Lap Fung Chan", "John Suchanek", "Yu Wang", "Varun Praveen", "Tomasz Kornuta", "Vidya Nariyambut Murali"], "categories": ["cs.CV", "cs.AI"], "id": "2609.09396", "title": "VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2609.09396"}, "sourceUpdatedAt": "2026-09-08T19:50:25Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses the infrastructure AI gap by testing models on fixed-camera video, enabling deployment in warehouses, ITS, and smart environments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
