{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.22658", "kind": "paper", "url": "https://arxiv.org/abs/2607.22658"}], "authors": ["Yuzhe Wang", "Thomas Thebaud", "Jennifer Hu", "Jesús Villalba-Lopez", "Venkatesh Ravichandran", "Georgi Tinchev", "Najim Dehak", "Laureano Moro-Velázquez"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.22658", "source_url": "https://arxiv.org/abs/2607.22658"}, "categories": ["General AI", "Speech & Audio", "cs.AI"], "description": {"en": "StanceBench evaluates interpersonal stance in conversational speech across 9 dimensions using LLM-as-a-judge on the Seamless Interaction corpus."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.22658", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.22658", "title": "StanceBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Johns Hopkins University", "Amazon (United States)", "Amazon (United Kingdom)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.22658", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.22658", "source_url": "https://openalex.org/W7171518499"}, "key": "claire-radar:2607.22658", "modality": null, "name": "StanceBench", "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_stancebench_98c43cc6", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "5e91d0582e964f32af6f4e4529cbfa6a5984e83f7b1236e7e7fd44ed1cdccb20", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.22658"}, "publisher": null, "released": "2026-06-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.22658", "source_url": "https://arxiv.org/abs/2607.22658"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-22658", "source": "claire_radar", "source_benchmark_id": "2607.22658", "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/2607.22658", "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": "e307dc5489a394a269ec99c7fe7f269e93a311562eb3aec2ba23c4f7274e622c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "StanceBench evaluates interpersonal stance in conversational speech across 9 dimensions using LLM-as-a-judge on the Seamless Interaction corpus.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce StanceBench, a benchmark for measuring interpersonal stance in conversational speech and evaluating audio-capable LLMs as automated judges."}, "familyId": "bmf_8befc508f2a5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_stancebench_98c43cc6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.22658", "paper": "https://arxiv.org/abs/2607.22658", "pdf": "https://arxiv.org/pdf/2607.22658", "project": null, "report": "https://arxiv.org/abs/2607.22658"}, "metrics": [], "motivation": "Speech-to-speech dialogue models increasingly depend on prosody and interactional nuance to convey social intent, yet benchmarks for these cues remain limited.", "name": "StanceBench", "oneLine": "StanceBench evaluates interpersonal stance in conversational speech across 9 dimensions using LLM-as-a-judge on the Seamless Interaction corpus.", "paperTitle": "StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to Interspeech 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.22658", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Interspeech 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-27", "source": {"authors": ["Yuzhe Wang (1)", "Thomas Thebaud (1)", "Jennifer Hu (2)", "Jes\\'us Villalba-Lopez (1)", "Venkatesh Ravichandran (3)", "Georgi Tinchev (4)", "Najim Dehak (1)", "Laureano Moro-Vel\\'azquez (1) ((1) Electrical and Computer Engineering Department", "Johns Hopkins University", "Baltimore", "USA", "(2) Department of Cognitive Science", "Johns Hopkins University", "Baltimore", "USA", "(3) Amazon AGI", "USA", "(4) Amazon Research", "UK)"], "categories": ["cs.AI", "cs.SD", "eess.AS"], "id": "2607.22658", "title": "StanceBench: A Benchmark for Audio LLM-Based Interpersonal Stance Evaluation from Speech", "type": "arxiv", "url": "https://arxiv.org/abs/2607.22658"}, "sourceUpdatedAt": "2026-06-27T15:27:53Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "Accepted to Interspeech 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to Interspeech 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.22658"}], "reviewStatus": "accepted", "venueName": "Interspeech 2026"}], "whyItMatters": "Addresses the gap in benchmarks for prosody and interactional nuance in speech-to-speech models, focusing on judge bias and robustness."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
