{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.07229", "kind": "paper", "url": "https://arxiv.org/abs/2606.07229"}, {"id": "gh:ddlbojack/mmae", "kind": "repo", "url": "https://github.com/ddlBoJack/MMAE"}], "authors": ["Ziyang Ma", "Ruiqi Yan", "Ruiyang Xu", "Jie Fang", "Zhikang Niu", "Yi-Wen Chao", "Wenming Tu", "Tianrui Wang", "Auden", "Qi Chen", "Wenxi Chen", "Jiaying Chi", "Yanru Huo", "Zixuan Jiang", "Xiquan Li", "Yalin Li", "Junxi Liu", "Minghao Liu", "Binghao Qiang", "Yijia Shan", "Zheshu Song", "Tian Tan", "Zixiang Wang", "Zeyu Xie", "Zhifei Xie", "Xiaoyu Xing", "Qixiang Xu", "Chen Yang", "Guanrou Yang", "Shan Yang", "Yifan Yang", "Steve Yves", "Haotian Zhang", "Haina Zhu", "Kai Yu", "Liefeng Bo", "Eng-Siong Chng", "Xie Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.07229", "source_url": "https://arxiv.org/abs/2606.07229"}, "categories": ["General AI", "Speech & Audio", "cs.SD"], "description": {"en": "MMAE is a benchmark for instruction-based audio editing with 2,000 samples across 7 modalities, 6 complexity levels, and rubric-based evaluation with 17,741 criteria for instruction following and context consistency."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.07229", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.07229", "title": "MMAE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "Nanyang Technological University", "Tencent (China)", "Shanghai Innovation Institute", "Peking University", "Fudan University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.07229", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.07229", "source_url": "https://openalex.org/W7163903257"}, "key": "claire-radar:2606.07229", "modality": null, "name": "MMAE", "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_mmae_ba12849c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "454f8db3030b4ce5a1c31d9c2cbfe60da8a9d368ace77c48cb65b280bfef627f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.07229"}, "publisher": null, "released": "2026-06-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.07229", "source_url": "https://arxiv.org/abs/2606.07229"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-07229", "source": "claire_radar", "source_benchmark_id": "2606.07229", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Speech & Audio", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/ddlBoJack/MMAE", "githubScope": "benchmark_repo", "githubStars": 111, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 46, "hfPaperUrl": "https://huggingface.co/papers/2606.07229", "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": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "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": "4e533933f8a78d6ec2a7735826001bb55f53e2cb74f909f504a2f9b467d6184c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MMAE is a benchmark for instruction-based audio editing with 2,000 samples across 7 modalities, 6 complexity levels, and rubric-based evaluation with 17,741 criteria for instruction following and context consistency.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing."}, "familyId": "bmf_ba3363208910", "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/ddlBoJack/MMAE", "url": "https://github.com/ddlBoJack/MMAE"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/ddlBoJack/MMAE", "url": "https://huggingface.co/papers/2606.07229"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/ddlBoJack/MMAE", "url": "https://arxiv.org/abs/2606.07229"}], "scope": "project_repo", "url": "https://github.com/ddlBoJack/MMAE", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_mmae_ba12849c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/ddlBoJack/MMAE", "data": null, "hfPaper": "https://huggingface.co/papers/2606.07229", "paper": "https://arxiv.org/abs/2606.07229", "pdf": "https://arxiv.org/pdf/2606.07229", "project": null, "report": "https://arxiv.org/abs/2606.07229"}, "metrics": [], "motivation": "We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing.", "name": "MMAE", "oneLine": "MMAE is a benchmark for instruction-based audio editing with 2,000 samples across 7 modalities, 6 complexity levels, and rubric-based evaluation with 17,741 criteria for instruction following and context consistency.", "paperTitle": "MMAE: A Massive Multitask Audio Editing Benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.07229", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-05", "source": {"authors": ["Ziyang Ma", "Ruiqi Yan", "Ruiyang Xu", "Jie Fang", "Zhikang Niu", "Yi-Wen Chao", "Wenming Tu", "Tianrui Wang", "Auden", "Qi Chen", "Wenxi Chen", "Jiaying Chi", "Yanru Huo", "Zixuan Jiang", "Xiquan Li", "Yalin Li", "Junxi Liu", "Minghao Liu", "Binghao Qiang", "Yijia Shan", "Zheshu Song", "Tian Tan", "Zixiang Wang", "Zeyu Xie", "Zhifei Xie", "Xiaoyu Xing", "Qixiang Xu", "Chen Yang", "Guanrou Yang", "Shan Yang", "Yifan Yang", "Steve Yves", "Haotian Zhang", "Haina Zhu", "Kai Yu", "Liefeng Bo", "Eng-Siong Chng", "Xie Chen"], "categories": ["cs.SD", "cs.CL", "cs.MM"], "id": "2606.07229", "title": "MMAE: A Massive Multitask Audio Editing Benchmark", "type": "arxiv", "url": "https://arxiv.org/abs/2606.07229"}, "sourceUpdatedAt": "2026-06-05T12:52:41Z", "topics": ["cs.SD"], "venueAttempts": [], "whyItMatters": "It provides the first comprehensive evaluation testbed for general-purpose audio editing, enabling precise multi-dimensional assessment and identifying bottlenecks in current models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
