{"record": {"aliases": ["On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos"], "artifacts": [{"id": "arxiv:2608.14262", "kind": "paper", "url": "https://arxiv.org/abs/2608.14262"}], "authors": ["Darakshan Rashid", "Raza Imam", "Ufaq Khan", "Muhammad Bilal", "Shazad Ashraf", "Dwarikanath Mahapatra", "Mohammad Yaqub", "Muhammad Haris Khan", "Imran Razzak", "Brejesh Lall", "Lena Maier-Hein", "Yutong Xie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14262", "source_url": "https://arxiv.org/abs/2608.14262"}, "categories": ["Biology & Drug Discovery", "Multimodal", "Robustness", "Safety & Trustworthiness"], "description": {"en": "Evaluates temporal vision-language models on surgical endoscopy video understanding under six realistic corruptions, using public videos and standardized prompts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14262", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14262", "title": "Endo-C6"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.14262", "modality": null, "name": "Endo-C6", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_on-the-robustness-of-temporal-vision-langu_c61c2c1d", "origin_source": "arxiv", "recognition_confidence": "0.45", "record_sha256": "75cfccc8c268df3c4c4f0abe08f9e88fdba9094a8cebf4a25ec663bde0e538f1", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.14262"}, "publisher": null, "released": "2026-08-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14262", "source_url": "https://arxiv.org/abs/2608.14262"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14262", "source": "claire_radar", "source_benchmark_id": "2608.14262", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos"], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Safety & Trustworthiness", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.14262", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Acceptance at MICCAI and the clinical relevance of robustness evaluation are likely to generate moderate interest, though the benchmark is specialized.", "score": 45}, "capabilities": ["Robustness"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "88732cbde55c84ce1b15d56636c10b7c1bfc65914c6e85bc4f329e5454673d39", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce Endo-C6, a compact corruption benchmark of six endoscopy-realistic perturbations", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is described as reproducible with public videos and standardized protocols, and the paper was accepted to MICCAI 2026, indicating a formal evaluation setup.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates temporal vision-language models on surgical endoscopy video understanding under six realistic corruptions, using public videos and standardized prompts.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence"], "snippet": "We introduce Endo-C6, a compact corruption benchmark of six endoscopy-realistic perturbations evaluated at a fixed high severity, and apply it to public Gastrointestinal (GI) endoscopy and laparoscopic cholecystectomy videos."}, "familyId": "bmf_51771cb8904f", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_on-the-robustness-of-temporal-vision-langu_c61c2c1d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.14262", "pdf": "https://arxiv.org/pdf/2608.14262", "project": null, "report": "https://arxiv.org/abs/2608.14262"}, "metrics": [], "motivation": "Temporal vision-language models (TVLMs) offer a reusable, prompt-based interface for surgical video understanding, yet, their robustness under clinically realistic acquisition artifacts in endoscopy remains insufficiently characterized.", "name": "Endo-C6", "oneLine": "Evaluates temporal vision-language models on surgical endoscopy video understanding under six realistic corruptions, using public videos and standardized prompts.", "paperTitle": "On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": "Accepted to MICCAI 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.14262", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "MICCAI 2026", "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "ranking": {"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": "Paper only", "recognitionConfidence": 0.45, "relation": "introduces", "releasedAt": "2026-08-14", "source": {"authors": ["Darakshan Rashid", "Raza Imam", "Ufaq Khan", "Muhammad Bilal", "Shazad Ashraf", "Dwarikanath Mahapatra", "Mohammad Yaqub", "Muhammad Haris Khan", "Imran Razzak", "Brejesh Lall", "Lena Maier-Hein and Yutong Xie"], "categories": ["cs.CV"], "id": "2608.14262", "title": "On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14262"}, "sourceUpdatedAt": "2026-08-14T12:37:48Z", "topics": ["Multimodal"], "venueAttempts": [{"decisionRaw": "Accepted to MICCAI 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-08-19T11:05:13.395391Z", "rawValue": "Accepted to MICCAI 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.14262"}], "reviewStatus": "accepted", "venueName": "MICCAI 2026"}], "whyItMatters": "Provides a standardized robustness benchmark for clinical vision-language systems, exposing worst-case performance degradation under clinically relevant artifacts."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
