{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.29247", "kind": "paper", "url": "https://arxiv.org/abs/2606.29247"}, {"id": "gh:vcl-hnu/surgvla", "kind": "repo", "url": "https://github.com/VCL-HNU/SurgVLA"}], "authors": ["Jiashuo Sun", "Yue He", "Wenxuan Liu", "Tao Mao", "Jiazheng Wang", "Xiang Chen", "Min Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.29247", "source_url": "https://arxiv.org/abs/2606.29247"}, "categories": ["Multimodal", "Robotics & Embodied AI"], "description": {"en": "Evaluates vision-language-action models in laparoscopic surgical robotics across 8 tasks (atomic, conditional, composite) on the SurRoL simulator, using action accuracy and semantic consistency metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.29247", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.29247", "title": "SurgVLA-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.29247", "modality": null, "name": "SurgVLA-Bench", "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_surgvla-bench_a2867ef6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e53ad6fec63b728fb532ebc54ef4862b2b795ece0d31a8ac648a50747475a0f2", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.29247"}, "publisher": null, "released": "2026-06-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.29247", "source_url": "https://arxiv.org/abs/2606.29247"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-29247", "source": "claire_radar", "source_benchmark_id": "2606.29247", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/VCL-HNU/SurgVLA", "githubScope": "benchmark_repo", "githubStars": 7, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.29247", "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", "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": "b6a15db73b403a53c4833e5b37e9415d9420c71467e1d7c56a8dd26d430a164f", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vision-language-action models in laparoscopic surgical robotics across 8 tasks (atomic, conditional, composite) on the SurRoL simulator, using action accuracy and semantic consistency metrics.", "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": "To address this limitation, we present SurgVLA-Bench, the first comprehensive benchmark for evaluating VLA models in laparoscopic surgical robotics."}, "familyId": "bmf_71013fdc6c32", "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/VCL-HNU/SurgVLA", "url": "https://github.com/VCL-HNU/SurgVLA"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/VCL-HNU/SurgVLA", "url": "https://huggingface.co/papers/2606.29247"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/VCL-HNU/SurgVLA", "url": "https://arxiv.org/abs/2606.29247"}], "scope": "benchmark_repo", "url": "https://github.com/VCL-HNU/SurgVLA", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_surgvla-bench_a2867ef6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/VCL-HNU/SurgVLA", "data": null, "hfPaper": "https://huggingface.co/papers/2606.29247", "paper": "https://arxiv.org/abs/2606.29247", "pdf": "https://arxiv.org/pdf/2606.29247", "project": null, "report": "https://arxiv.org/abs/2606.29247"}, "metrics": [], "motivation": "Vision-Language-Action (VLA) models represent a promising direction for embodied intelligence in surgical robotics.", "name": "SurgVLA-Bench", "oneLine": "Evaluates vision-language-action models in laparoscopic surgical robotics across 8 tasks (atomic, conditional, composite) on the SurRoL simulator, using action accuracy and semantic consistency metrics.", "paperTitle": "SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Robotics", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.29247", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "VCL-HNU", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/VCL-HNU/SurgVLA"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-28", "source": {"authors": ["Jiashuo Sun", "Yue He", "Wenxuan Liu", "Tao Mao", "Jiazheng Wang", "Xiang Chen", "Min Liu"], "categories": ["cs.AI"], "id": "2606.29247", "title": "SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Robotics", "type": "arxiv", "url": "https://arxiv.org/abs/2606.29247"}, "sourceUpdatedAt": "2026-06-28T07:29:25Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Fills the lack of standardized surgical VLA benchmarks, enabling comparison of autoregressive vs. flow-matching models and identifying physical bottlenecks like limited field of view."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
