{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.27219", "kind": "paper", "url": "https://arxiv.org/abs/2608.27219"}], "authors": ["Yu Yvonne Wu", "Arvind Pillai", "Yuliang Chen", "Yuwei Zhang", "Sudarshan Regmi", "Tess Z. Griffin", "Michael V. Heinz", "Lisa A. Marsch", "Nicholas C. Jacobson", "Andrew Campbell"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.27219", "source_url": "https://arxiv.org/abs/2608.27219"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Mental health assessment relies on episodic self-report scales, which convert subjective states such as stress into numerical scores but provide only sparse snapshots of wellbeing."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.27219", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.27219", "title": "BALMS"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.27219", "modality": null, "name": "BALMS", "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": "true", "origin_record_id": "bm_balms_57758cdd", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "50521949f2f4672d510c8b788e443973d85db0bb61aa9bf3c728d88e5a5b9e74", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.27219"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.27219", "source_url": "https://arxiv.org/abs/2608.27219"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-27219", "source": "claire_radar", "source_benchmark_id": "2608.27219", "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/2608.27219", "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": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce BALMS, the first systematic benchmark of LLM-based agentic systems for longitudinal mental health sensing."}, "familyId": "bmf_17b4729fcca2", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_balms_57758cdd", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.27219", "paper": "https://arxiv.org/abs/2608.27219", "pdf": "https://arxiv.org/pdf/2608.27219", "project": null, "report": "https://arxiv.org/abs/2608.27219"}, "metrics": [], "motivation": "Mental health assessment relies on episodic self-report scales, which convert subjective states such as stress into numerical scores but provide only sparse snapshots of wellbeing.", "name": "BALMS", "oneLine": "Mental health assessment relies on episodic self-report scales, which convert subjective states such as stress into numerical scores but provide only sparse snapshots of wellbeing.", "paperTitle": "BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP 2026 Main Conference", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.27219", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 Main Conference", "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": 1.0, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Yu Yvonne Wu", "Arvind Pillai", "Yuliang Chen", "Yuwei Zhang", "Sudarshan Regmi", "Tess Z. Griffin", "Michael V. Heinz", "Lisa A. Marsch", "Nicholas C. Jacobson", "Andrew Campbell"], "categories": ["cs.CL"], "id": "2608.27219", "title": "BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing", "type": "arxiv", "url": "https://arxiv.org/abs/2608.27219"}, "sourceUpdatedAt": "2026-08-27T15:00:17Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026 Main Conference", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to EMNLP 2026 Main Conference", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.27219"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 Main Conference"}]}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
