{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.08112", "kind": "paper", "url": "https://arxiv.org/abs/2607.08112"}], "authors": ["Iulia-Maria Udrea", "Alexandra Diaconu", "Bogdan Alexe"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.08112", "source_url": "https://arxiv.org/abs/2607.08112"}, "categories": ["General AI", "Multimodal", "Robustness", "Safety & Trustworthiness"], "description": {"en": "A large-scale dataset for visual speech recognition in Romanian, with 200 hours of video and annotations. It studies supervision quality, robustness under domain shift, and multimodal fusion."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.08112", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.08112", "title": "VSRo-200"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Bucharest"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.08112", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.08112", "source_url": "https://openalex.org/W7167900425"}, "key": "claire-radar:2607.08112", "modality": null, "name": "VSRo-200", "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": "unknown", "origin_record_id": "bm_vsro-200_f4255395", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "6b504b59f009f8df65caeee5098e52a3d201cd124cba8c24290c481b33ab9110", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.08112"}, "publisher": null, "released": "2026-07-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.08112", "source_url": "https://arxiv.org/abs/2607.08112"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-08112", "source": "claire_radar", "source_benchmark_id": "2607.08112", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "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/2607.08112", "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"}, "capabilities": ["Robustness"], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "8ba8ecc8b6641fbc945e1839ad3d4dd577d9fdde76d84ce9b6f52041124f65c3", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A large-scale dataset for visual speech recognition in Romanian, with 200 hours of video and annotations. It studies supervision quality, robustness under domain shift, and multimodal fusion.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "evaluation protocol evidence"], "snippet": "Building on this dataset, we establish a benchmark for visual speech recognition in low-resource settings."}, "familyId": "bmf_76014c7782c1", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_vsro-200_f4255395", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.08112", "paper": "https://arxiv.org/abs/2607.08112", "pdf": "https://arxiv.org/pdf/2607.08112", "project": null, "report": "https://arxiv.org/abs/2607.08112"}, "metrics": [], "motivation": "We introduce VSRo-200, the first large-scale dataset for visual speech recognition (lip reading) in Romanian, comprising 200 hours of real-world podcast videos.", "name": "VSRo-200", "oneLine": "A large-scale dataset for visual speech recognition in Romanian, with 200 hours of video and annotations. It studies supervision quality, robustness under domain shift, and multimodal fusion.", "paperTitle": "VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.08112", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "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": 0.85, "relation": "introduces", "releasedAt": "2026-07-09", "source": {"authors": ["Iulia-Maria Udrea", "Alexandra Diaconu", "Bogdan Alexe"], "categories": ["cs.CV"], "id": "2607.08112", "title": "VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness", "type": "arxiv", "url": "https://arxiv.org/abs/2607.08112"}, "sourceUpdatedAt": "2026-07-09T04:54:53Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "The dataset enables research in low-resource visual speech recognition, but the paper primarily focuses on studying supervision and robustness rather than defining a fixed benchmark with a scoring contract. It is a dataset resource for training, not a standalone evaluation benchmark."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
