{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.13076", "kind": "paper", "url": "https://arxiv.org/abs/2609.13076"}], "authors": ["Yi-Jen Shih", "Shih-Yun Shan Kuan", "Guan-Ting Lin", "Kai-Wei Chang", "Siddhant Arora", "Shu-wen Yang", "Abdelrahman Mohamed", "Shinji Watanabe", "Hung-yi Lee", "David Harwath"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.13076", "source_url": "https://arxiv.org/abs/2609.13076"}, "categories": ["General AI", "Speech & Audio", "eess.AS"], "description": {"en": "MP-Bench evaluates conversational speech systems acting as active participants within multi-party conversation contexts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.13076", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.13076", "title": "Multiparty Bench (MP-Bench)"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.13076", "modality": null, "name": "Multiparty Bench (MP-Bench)", "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": "false", "origin_record_id": "bm_mp-bench_04d97a7f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "556dbea7f45d12651cc00651b66c1ad2d3fc44bc3eace0762a74c62ee32ba723", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T06:44:31.931424Z", "source_url": "https://arxiv.org/abs/2609.13076"}, "publisher": null, "released": "2026-09-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.13076", "source_url": "https://arxiv.org/abs/2609.13076"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-13076", "source": "claire_radar", "source_benchmark_id": "2609.13076", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.13076", "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": "Low", "horizon": "7d", "reason": "Voice-agent evaluation is a growing area, but the record supplies no artifacts, scoring details, or public submission path to support higher attention.", "reason_note": "", "score": 35}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T10:07:09.772218Z", "inputHash": "1d15587b1e67121a11847ca84920b57d21973affd61bc7b379ae6f0ca26b0e6d", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "No artifact evidence is provided; the benchmark cannot be verified as released or reusable.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-14T06:44:31.931424Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MP-Bench evaluates conversational speech systems acting as active participants within multi-party conversation contexts.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce Multiparty Bench (MP-Bench), the first benchmark specifically designed to objectively evaluate conversational speech systems as active participants within multi-party contexts."}, "familyId": "bmf_268dd666db6d", "firstSeenAt": "2026-09-14", "heat": null, "id": "bm_mp-bench_04d97a7f", "indexedAt": "2026-09-14T06:39:43.852630Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.13076", "pdf": "https://arxiv.org/pdf/2609.13076", "project": null, "report": "https://arxiv.org/abs/2609.13076"}, "metrics": [], "motivation": "Conversational voice agents have advanced significantly, offering increasingly natural human-machine interactions through both cascaded and end-to-end architectures.", "name": "Multiparty Bench (MP-Bench)", "oneLine": "MP-Bench evaluates conversational speech systems acting as active participants within multi-party conversation contexts.", "paperTitle": "MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP 2026 Findings", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.13076", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 Findings", "verifiedAt": "2026-09-14T06:39:43.852630Z"}, "publications": [], "ranking": {"30d": {"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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "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}, "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": 1.0, "relation": "introduces", "releasedAt": "2026-09-11", "source": {"authors": ["Yi-Jen Shih", "Shih-Yun Shan Kuan", "Guan-Ting Lin", "Kai-Wei Chang", "Siddhant Arora", "Shu-wen Yang", "Abdelrahman Mohamed", "Shinji Watanabe", "Hung-yi Lee", "David Harwath"], "categories": ["eess.AS", "cs.AI", "cs.CL"], "id": "2609.13076", "title": "MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant", "type": "arxiv", "url": "https://arxiv.org/abs/2609.13076"}, "sourceUpdatedAt": "2026-09-11T17:11:55Z", "topics": ["eess.AS"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026 Findings", "evidence": [{"level": "author-claim", "observedAt": "2026-09-14T06:39:43.852630Z", "rawValue": "Accepted to EMNLP 2026 Findings", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.13076"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 Findings"}], "whyItMatters": "Multi-party speech interaction differs from dyadic dialogue, and objective evaluation would help compare systems on active participation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
