{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.29125", "kind": "paper", "url": "https://arxiv.org/abs/2607.29125"}], "authors": ["Ryo Fukuda", "Atsushi Ando", "Hiroki Kanagawa", "Takatomo Kano", "Marc Delcroix", "Naohiro Tawara", "Yuya Chiba"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.29125", "source_url": "https://arxiv.org/abs/2607.29125"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "M3-DuplexBench evaluates full-duplex spoken dialogue models in multi-turn, multilingual (English and Japanese), multidomain settings, with multiple dialogue context settings and turn-taking analysis."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.29125", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.29125", "title": "M3-DuplexBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.29125", "modality": null, "name": "M3-DuplexBench", "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_m3-duplexbench_afd47e79", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "b0e0d93d6bfc4d9fe8f0e89695cc4dfeeea9619d8735beef5d41883c428850d0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.29125"}, "publisher": null, "released": "2026-07-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.29125", "source_url": "https://arxiv.org/abs/2607.29125"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-29125", "source": "claire_radar", "source_benchmark_id": "2607.29125", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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/2607.29125", "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": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "db782de0dec032683a528a2956e516d9940a7a9d3ac98815983d456e9789d0d4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "M3-DuplexBench evaluates full-duplex spoken dialogue models in multi-turn, multilingual (English and Japanese), multidomain settings, with multiple dialogue context settings and turn-taking analysis.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We propose M3-DuplexBench, a multi-turn, multilingual, multidomain benchmark for FDSDSs."}, "familyId": "bmf_8b667f9a2394", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_m3-duplexbench_afd47e79", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.29125", "paper": "https://arxiv.org/abs/2607.29125", "pdf": "https://arxiv.org/pdf/2607.29125", "project": null, "report": "https://arxiv.org/abs/2607.29125"}, "metrics": [], "motivation": "Full-duplex spoken dialogue systems (FDSDSs) can listen while speaking, enabling natural behaviors such as smooth turn-taking, backchannel handling, and user barge-in handling.", "name": "M3-DuplexBench", "oneLine": "M3-DuplexBench evaluates full-duplex spoken dialogue models in multi-turn, multilingual (English and Japanese), multidomain settings, with multiple dialogue context settings and turn-taking analysis.", "paperTitle": "M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.29125", "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": "2026-07-31", "source": {"authors": ["Ryo Fukuda", "Atsushi Ando", "Hiroki Kanagawa", "Takatomo Kano", "Marc Delcroix", "Naohiro Tawara", "Yuya Chiba"], "categories": ["cs.CL"], "id": "2607.29125", "title": "M3-DuplexBench: A Multi-Turn, Multilingual, Multidomain Benchmark for Full-Duplex Spoken Dialogue Models", "type": "arxiv", "url": "https://arxiv.org/abs/2607.29125"}, "sourceUpdatedAt": "2026-07-31T07:56:25Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the lack of fair multi-turn comparisons in full-duplex dialogue systems, enabling analysis across languages, domains, and context settings."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
