{"record": {"aliases": ["Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols"], "artifacts": [{"id": "arxiv:2608.31014", "kind": "paper", "url": "https://arxiv.org/abs/2608.31014"}], "authors": ["Chengyuan Gao", "Jiang Wu", "Tao Lu", "Jiayan Guo", "Mingkun Xu", "Tianyi Zang", "Shangyang Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.31014", "source_url": "https://arxiv.org/abs/2608.31014"}, "categories": ["Biology & Drug Discovery", "Reasoning", "Speech & Audio"], "description": {"en": "Evaluates evidence-bounded mental health reasoning over 1,870 packages from six heterogeneous speech-text sources, scoring diagnosis accuracy and claim violations under modality masks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.31014", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.31014", "title": "Evidence Package Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.31014", "modality": null, "name": "Evidence Package Benchmark", "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": "false", "origin_record_id": "bm_evidence-bounded-mental-health-reasoning-f_e3e77fe7", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "a4a805106e049752cd907770d326278454a31157c1adcce651cfa324a6a4c6fd", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.31014"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.31014", "source_url": "https://arxiv.org/abs/2608.31014"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-31014", "source": "claire_radar", "source_benchmark_id": "2608.31014", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols"], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "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/2608.31014", "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": "The benchmark targets a specialized mental health screening task with a formal evaluation protocol but lacks public artifact links, reducing expected early traction.", "score": 40}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "17052bbe5581c9f365f144e8332a634448628d2a52ef32e84210a718716f9fb6", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce the Evidence Package Benchmark, integrating 1,870 packages across six heterogeneous sources with explicit modality masks and evidence permissions.", "canonicalNameSource": "abstract", "decisionReason": "The paper formally names the benchmark, defines a clear evaluation object and scoring via AUROC and claim violations, but provides no public artifact link, limiting reuse readiness.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates evidence-bounded mental health reasoning over 1,870 packages from six heterogeneous speech-text sources, scoring diagnosis accuracy and claim violations under modality masks.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce the Evidence Package Benchmark, integrating 1,870 packages across six heterogeneous sources with explicit modality masks and evidence permissions."}, "familyId": "bmf_b274e5f7c560", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_evidence-bounded-mental-health-reasoning-f_e3e77fe7", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.31014", "pdf": "https://arxiv.org/pdf/2608.31014", "project": null, "report": "https://arxiv.org/abs/2608.31014"}, "metrics": [], "motivation": "Computational mental health screening using multimodal speech and text has shown great promise.", "name": "Evidence Package Benchmark", "oneLine": "Evaluates evidence-bounded mental health reasoning over 1,870 packages from six heterogeneous speech-text sources, scoring diagnosis accuracy and claim violations under modality masks.", "paperTitle": "Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": "Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026. Long paper", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.31014", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Findings of the Association for Computational Linguistics: EMNLP 2026", "verifiedAt": "2026-09-01T06:28:29.895112Z"}, "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": 0.6, "relation": "introduces", "releasedAt": "2026-08-31", "source": {"authors": ["Chengyuan Gao", "Jiang Wu", "Tao Lu", "Jiayan Guo", "Mingkun Xu", "Tianyi Zang", "Shangyang Li"], "categories": ["cs.CL"], "id": "2608.31014", "title": "Evidence-Bounded Mental Health Reasoning from Heterogeneous Speech Protocols", "type": "arxiv", "url": "https://arxiv.org/abs/2608.31014"}, "sourceUpdatedAt": "2026-08-31T15:58:22Z", "topics": ["Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026. Long paper", "evidence": [{"level": "author-claim", "observedAt": "2026-09-01T06:28:29.895112Z", "rawValue": "Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026. Long paper", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.31014"}], "reviewStatus": "accepted", "venueName": "Findings of the Association for Computational Linguistics: EMNLP 2026"}], "whyItMatters": "Addresses evidence consistency in multimodal screening, reducing hallucinated symptoms and unsupported claims that current models exhibit."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
