{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.02269", "kind": "paper", "url": "https://arxiv.org/abs/2607.02269"}, {"id": "gh:rinost081/anygroundbench", "kind": "repo", "url": "https://github.com/rinost081/AnyGroundBench"}], "authors": ["Rintaro Otsubo", "Ryo Fujii", "Reina Ishikawa", "Taiki Kanaya", "Kanta Sawafuji", "Hiroki Kajita", "Shigeki Sakai", "Hideo Saito", "Ryo Hachiuma"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.02269", "source_url": "https://arxiv.org/abs/2607.02269"}, "categories": ["General AI", "Multimodal"], "description": {"en": "AnyGroundBench evaluates video grounding in vision-language models across five specialized domains (animal, industry, sports, surgery, public security) with spatio-temporal annotations. It provides training and test splits per domain for zero-shot and in-context learning evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.02269", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.02269", "title": "AnyGroundBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.02269", "modality": null, "name": "AnyGroundBench", "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_anygroundbench_08e0374e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ff6f965e76e7d01e35cd9a79aeea6ee146b8bb36182b477f965ac64613728315", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.02269"}, "publisher": null, "released": "2026-07-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.02269", "source_url": "https://arxiv.org/abs/2607.02269"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-02269", "source": "claire_radar", "source_benchmark_id": "2607.02269", "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": "https://github.com/rinost081/AnyGroundBench", "githubScope": "benchmark_repo", "githubStars": 4, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 6, "hfPaperUrl": "https://huggingface.co/papers/2607.02269", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "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": "f4722e2e2d9b2f384f477de3286a945be6cdf4e3c0a41f2234a454164b93a0b0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AnyGroundBench evaluates video grounding in vision-language models across five specialized domains (animal, industry, sports, surgery, public security) with spatio-temporal annotations. It provides training and test splits per domain for zero-shot and in-context learning evaluation.", "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": "To bridge this gap, we introduce AnyGroundBench, a domain-adaptation benchmark designed to shift the STVG evaluation paradigm from static zero-shot testing to rigorous domain adaptation."}, "familyId": "bmf_8d8cdd5ff428", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/rinost081/AnyGroundBench", "url": "https://github.com/rinost081/AnyGroundBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/rinost081/AnyGroundBench", "url": "https://huggingface.co/papers/2607.02269"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/rinost081/AnyGroundBench", "url": "https://huggingface.co/api/papers/2607.02269"}], "scope": "benchmark_repo", "url": "https://github.com/rinost081/AnyGroundBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_anygroundbench_08e0374e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/rinost081/AnyGroundBench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.02269", "paper": "https://arxiv.org/abs/2607.02269", "pdf": "https://arxiv.org/pdf/2607.02269", "project": null, "report": "https://arxiv.org/abs/2607.02269"}, "metrics": [], "motivation": "Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).", "name": "AnyGroundBench", "oneLine": "AnyGroundBench evaluates video grounding in vision-language models across five specialized domains (animal, industry, sports, surgery, public security) with spatio-temporal annotations. It provides training and test splits per domain for zero-shot and in-context learning evaluation.", "paperTitle": "AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.02269", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Keio University", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/rinost081/AnyGroundBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-02", "source": {"authors": ["Rintaro Otsubo", "Ryo Fujii", "Reina Ishikawa", "Taiki Kanaya", "Kanta Sawafuji", "Hiroki Kajita", "Shigeki Sakai", "Hideo Saito", "Ryo Hachiuma"], "categories": ["cs.CV", "cs.AI"], "id": "2607.02269", "title": "AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2607.02269"}, "sourceUpdatedAt": "2026-07-02T14:52:45Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses the gap between existing benchmark evaluations on general daily-life videos and real-world specialized applications. Provides a structured domain-adaptation protocol to assess model adaptability in specialized fields, enabling comparative evaluation of VLMs in practical scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
