{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.01548", "kind": "paper", "url": "https://arxiv.org/abs/2609.01548"}], "authors": ["Stephanie Fong", "Yiwen Jiang", "Zimu Wang", "Hongxi Yang", "Yaling Shen", "Hiu Weh Naomi Chow", "Heung Ying Lai", "Xiangyu Zhao", "Qingyang Xu", "Zhongxing Xu", "Jiahe Liu", "Guilherme C. Oliveira", "Vincent Lee", "Zongyuan Ge", "Dominic Dwyer"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.01548", "source_url": "https://arxiv.org/abs/2609.01548"}, "categories": ["Cybersecurity", "Vision & 3D", "cs.CL"], "description": {"en": "Evaluates stigma detection and response generation in dyadic and group dialogues."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.01548", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.01548", "title": "SDARE-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.01548", "modality": null, "name": "SDARE-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_sdare-bench_17a9668f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ee4b6315fce962ff8384cf2802324b4540d9e9c8cc96b455f2e48a5b1dd3efc3", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-03T00:59:34.317835Z", "source_url": "https://arxiv.org/abs/2609.01548"}, "publisher": null, "released": "2026-09-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.01548", "source_url": "https://arxiv.org/abs/2609.01548"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-01548", "source": "claire_radar", "source_benchmark_id": "2609.01548", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity"], "area": "Vision & 3D", "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/2609.01548", "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": "Socially relevant but niche topic with no release specifics.", "score": 20}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T00:59:34.317835Z", "inputHash": "701844bfe902396d580f49b224f35baab85e21d96e8191385481538489424996", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue", "canonicalNameSource": "paper_title", "decisionReason": "No artifactEvidence or public project page is provided, preventing reuse confirmation.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T00:59:34.317835Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates stigma detection and response generation in dyadic and group dialogues.", "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 these gaps, we introduce SDARE-Bench, the first scenario-based benchmark evaluating both stigma detection and open-ended response generation in LLMs, comprising 1,138 dyadic queries and 1,388 group dialogue."}, "familyId": "bmf_bad3f5465e96", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_sdare-bench_17a9668f", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": ["Cybersecurity"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.01548", "pdf": "https://arxiv.org/pdf/2609.01548", "project": null, "report": "https://arxiv.org/abs/2609.01548"}, "metrics": [], "motivation": "Large Language Models (LLMs) are increasingly used in advice seeking and decision making that may affect social judgements.", "name": "SDARE-Bench", "oneLine": "Evaluates stigma detection and response generation in dyadic and group dialogues.", "paperTitle": "SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue", "primaryDomain": "Cybersecurity", "publication": {"evidence": "Paper accepted at EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.01548", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026", "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "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": 1.0, "relation": "introduces", "releasedAt": "2026-09-01", "source": {"authors": ["Stephanie Fong", "Yiwen Jiang", "Zimu Wang", "Hongxi Yang", "Yaling Shen", "Hiu Weh Naomi Chow", "Heung Ying Lai", "Xiangyu Zhao", "Qingyang Xu", "Zhongxing Xu", "Jiahe Liu", "Guilherme C. Oliveira", "Vincent Lee", "Zongyuan Ge", "Dominic Dwyer"], "categories": ["cs.CL"], "id": "2609.01548", "title": "SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue", "type": "arxiv", "url": "https://arxiv.org/abs/2609.01548"}, "sourceUpdatedAt": "2026-09-01T17:15:22Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Paper accepted at EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-02T05:21:06.631990Z", "rawValue": "Paper accepted at EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.01548"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026"}], "whyItMatters": "First scenario-based benchmark for conversational stigma detection and response."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
