{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.26204", "kind": "paper", "url": "https://arxiv.org/abs/2608.26204"}], "authors": ["Joy Chen", "Alejandro Castillejo Munoz", "Pierluca D'Oro", "Yuxuan Sun", "Chloe Evans", "Joseph Tighe"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.26204", "source_url": "https://arxiv.org/abs/2608.26204"}, "categories": ["Agents & Tool Use", "Manufacturing & Process Control", "cs.CR"], "description": {"en": "Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively evaluates whether they can safely interact with visual interfaces while handling ambiguou…"}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.26204", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.26204", "title": "ADeptS-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.26204", "modality": null, "name": "ADeptS-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": "true", "origin_record_id": "bm_adepts-bench_6cc5b43a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3278b1844b15786ae729a06c6f4c8d20cd20a36831cb9933d6f16557c7fa71a2", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.26204"}, "publisher": null, "released": "2026-08-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.26204", "source_url": "https://arxiv.org/abs/2608.26204"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-26204", "source": "claire_radar", "source_benchmark_id": "2608.26204", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Manufacturing & Process Control"], "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/2608.26204", "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": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce ADeptS-Bench, a dual-stream trustworthiness benchmark, grounded in the ADEPTS capability framework and general population user studies."}, "familyId": "bmf_c0573fbf9739", "firstSeenAt": "2026-08-28", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_adepts-bench_6cc5b43a", "indexedAt": "2026-08-28T13:06:54.083176Z", "industrySectors": ["Manufacturing"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.26204", "paper": "https://arxiv.org/abs/2608.26204", "pdf": "https://arxiv.org/pdf/2608.26204", "project": null, "report": "https://arxiv.org/abs/2608.26204"}, "metrics": [], "motivation": "Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively evaluates whether they can safely interact with visual interfaces while handling ambiguous instructions.", "name": "ADeptS-Bench", "oneLine": "Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively evaluates whether they can safely interact with visual interfaces while handling ambiguou…", "paperTitle": "ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices", "primaryDomain": "Manufacturing & Process Control", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.26204", "source": "arxiv-metadata", "status": "unverified", "venue": null, "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": "2026-08-25", "source": {"authors": ["Joy Chen", "Alejandro Castillejo Munoz", "Pierluca D'Oro", "Yuxuan Sun", "Chloe Evans", "Joseph Tighe"], "categories": ["cs.CR", "cs.AI", "cs.SE"], "id": "2608.26204", "title": "ADeptS-Bench: Measuring the Trustworthiness of Computer Use Agents Across Devices", "type": "arxiv", "url": "https://arxiv.org/abs/2608.26204"}, "sourceUpdatedAt": "2026-08-25T23:21:57Z", "topics": ["cs.CR"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
