{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.04850", "kind": "paper", "url": "https://arxiv.org/abs/2609.04850"}], "authors": ["Weide Zhan", "Qumu Shaqu", "Yuanqing Liu", "Peng Zhang", "Jiahao Liu", "Kam Him Lam", "Ning Gu", "Zhan Hu", "Tun Lu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.04850", "source_url": "https://arxiv.org/abs/2609.04850"}, "categories": ["Agents & Tool Use", "Mobile & Personal Computing", "cs.AI"], "description": {"en": "ElderBench is a benchmark for evaluating mobile GUI agents on tasks elicited from older adults, focusing on natural language patterns like indirect speech and ambiguity. It assesses agent performance on 249 tasks across 20 apps."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.04850", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.04850", "title": "ElderBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Fudan University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.04850", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.04850", "source_url": "https://openalex.org/W7211875132"}, "key": "claire-radar:2609.04850", "modality": null, "name": "ElderBench", "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_elderbench_e3027052", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d1f0dd773f2b5b2d81722f91022c12bbb9fa8a77f2a4155bd2591abf128d457b", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-08T00:56:29.478814Z", "source_url": "https://arxiv.org/abs/2609.04850"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.04850", "source_url": "https://arxiv.org/abs/2609.04850"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-04850", "source": "claire_radar", "source_benchmark_id": "2609.04850", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Mobile & Personal Computing"], "area": "Agents & Tool Use", "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/2609.04850", "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": "Timely topic of assistive AI and elderly care may attract attention, but lack of artifacts limits immediate practical use.", "score": 40}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:59:06.803818Z", "inputHash": "647881aced4b4d071b33ea7a4bdb3df3207f51a85668ad45f5551ee1bd0485d6", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "The paper presents a formally named benchmark with a clear evaluation object, a stable scoring approach, and a credible public path via publication, though its public reuse path is limited without direct code or data links.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-08T00:56:29.478814Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ElderBench is a benchmark for evaluating mobile GUI agents on tasks elicited from older adults, focusing on natural language patterns like indirect speech and ambiguity. It assesses agent performance on 249 tasks across 20 apps.", "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 present ElderBench, the first benchmark for evaluating mobile GUI agents in authentic elderly-oriented scenarios."}, "familyId": "bmf_504538a2723b", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_elderbench_e3027052", "indexedAt": "2026-09-07T00:39:11.978130Z", "industrySectors": ["Consumer Technology"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.04850", "pdf": "https://arxiv.org/pdf/2609.04850", "project": null, "report": "https://arxiv.org/abs/2609.04850"}, "metrics": [], "motivation": "While autonomous mobile agents hold great potential for assisting older adults with smartphone usage, existing GUI benchmarks mainly rely on explicit, goal-oriented instructions and rarely capture the naturally occurring language patterns of older users, such as indirect speech, referential ambiguity, and under-specified requests.", "name": "ElderBench", "oneLine": "ElderBench is a benchmark for evaluating mobile GUI agents on tasks elicited from older adults, focusing on natural language patterns like indirect speech and ambiguity. It assesses agent performance on 249 tasks across 20 apps.", "paperTitle": "ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults", "primaryDomain": "Mobile & Personal Computing", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.04850", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T00:39:11.978130Z"}, "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": "2026-09-04", "source": {"authors": ["Weide Zhan", "Qumu Shaqu", "Yuanqing Liu", "Peng Zhang", "Jiahao Liu", "Kam Him Lam", "Ning Gu", "Zhan Hu and Tun Lu"], "categories": ["cs.AI"], "id": "2609.04850", "title": "ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults", "type": "arxiv", "url": "https://arxiv.org/abs/2609.04850"}, "sourceUpdatedAt": "2026-09-04T08:09:47Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing GUI benchmarks miss elderly language patterns, hindering agent deployment for older users. ElderBench provides a realistic evaluation to improve age-inclusive agent design."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
