{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.26535", "kind": "paper", "url": "https://arxiv.org/abs/2608.26535"}], "authors": ["Kaichao Jiang", "Changtao Miao", "Baiqi Wu", "Zhiyuan Lu", "Kang Yang", "Peiwei Zhao", "Junchi Chen", "Yunfeng Diao", "He Liu", "Qi Chu", "Tao Gong"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.26535", "source_url": "https://arxiv.org/abs/2608.26535"}, "categories": ["Factuality", "General AI", "Multimodal", "Safety", "Safety & Trustworthiness"], "description": {"en": "Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly shape the generated output."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.26535", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.26535", "title": "Multi2AV-Safety"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.26535", "modality": null, "name": "Multi2AV-Safety", "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": "true", "origin_record_id": "bm_multi2av-safety_13dc6c17", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "35ca4344230683c6f468b4b5ae35fe3127e8542e7337b6c59600ae5c8f9ef7f7", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.26535"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.26535", "source_url": "https://arxiv.org/abs/2608.26535"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-26535", "source": "claire_radar", "source_benchmark_id": "2608.26535", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.26535", "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", "lastSuccessfulDate": "2026-09-28", "state": "stale"}}, "status": "stale"}, "capabilities": ["Factuality"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To bridge this gap, we introduce Multi2AV-Safety, the first safety benchmark, to the best of our knowledge, to cover all 11 non-singleton T/I/A/V conditioning configurations for audio-video generation, comprising 11,024 attack instances."}, "familyId": "bmf_49c9d04bc162", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_multi2av-safety_13dc6c17", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.26535", "paper": "https://arxiv.org/abs/2608.26535", "pdf": "https://arxiv.org/pdf/2608.26535", "project": null, "report": "https://arxiv.org/abs/2608.26535"}, "metrics": [], "motivation": "Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly shape the generated output.", "name": "Multi2AV-Safety", "oneLine": "Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly shape the generated output.", "paperTitle": "Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.26535", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Kaichao Jiang", "Changtao Miao", "Baiqi Wu", "Zhiyuan Lu", "Kang Yang", "Peiwei Zhao", "Junchi Chen", "Yunfeng Diao", "He Liu", "Qi Chu", "Tao Gong", "and Nenghai Yu"], "categories": ["cs.AI"], "id": "2608.26535", "title": "Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.26535"}, "sourceUpdatedAt": "2026-08-27T02:12:25Z", "topics": ["Multimodal", "Safety"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
