{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.22015", "kind": "paper", "url": "https://arxiv.org/abs/2607.22015"}], "authors": ["Haotian Si", "Junyi Chen", "Shuyang Yu", "Ruifeng Nie", "Jiate Li", "Jianqiang Zhao", "Meng Li", "Dengcheng He"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.22015", "source_url": "https://arxiv.org/abs/2607.22015"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "SkillAdeqBench evaluates whether Cloud Skill test suites exercise their specified operational obligations and identifies uncovered obligations."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.22015", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.22015", "title": "SkillAdeqBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Alibaba Group (China)", "Columbia University", "Aalto University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.22015", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.22015", "source_url": "https://openalex.org/W7171418253"}, "key": "claire-radar:2607.22015", "modality": null, "name": "SkillAdeqBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_skilladeqbench_b962d2a7", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "2142de22fcade3859b77cb40e77f4e88ba96b9a361cc6e97e363b0fb8b67e67b", "relation": "introduces", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T17:49:51.146918Z", "source_url": "https://arxiv.org/abs/2607.22015"}, "publisher": null, "released": "2026-07-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.22015", "source_url": "https://arxiv.org/abs/2607.22015"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-22015", "source": "claire_radar", "source_benchmark_id": "2607.22015", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The evaluation-governance focus may draw attention from agent-testing and cloud-platform practitioners.", "score": 2}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T17:49:51.146918Z", "inputHash": "d02526531c0f75b4dedd3eae7617271ab70143906f0fb7f4a4ce800e19137490", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "Finally, we release SkillAdeqBench", "canonicalNameSource": "abstract", "decisionReason": "The supplied abstract names the benchmark, defines its evaluation task and scoring basis, and states that a reusable subset is released.", "evaluationEvidence": {"reuse": "we release SkillAdeqBench, an exploratory subset of the reviewed records for studying automatic adequacy assessment.", "scoring": "determines whether each obligation is exercised by at least one testcase scenario; the resulting records provide both a suite-level score and explicit test gaps.", "task": "a scenario-conditioned criterion that evaluates a test suite against the complete set of operational test obligations specified by a Skill"}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T17:49:51.146918Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SkillAdeqBench evaluates whether Cloud Skill test suites exercise their specified operational obligations and identifies uncovered obligations.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence"], "snippet": "Finally, we release SkillAdeqBench, an exploratory subset of the reviewed records for studying automatic adequacy assessment."}, "familyId": "bmf_c49906710af5", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_skilladeqbench_b962d2a7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2607.22015", "pdf": "https://arxiv.org/pdf/2607.22015", "project": null, "report": "https://arxiv.org/abs/2607.22015"}, "metrics": [], "motivation": "Cloud platforms increasingly deliver reusable Cloud Skills that guide AI agents through multi-step resource operations, user choices, validation, and recovery.", "name": "SkillAdeqBench", "oneLine": "SkillAdeqBench evaluates whether Cloud Skill test suites exercise their specified operational obligations and identifies uncovered obligations.", "paperTitle": "Are Production Cloud Skills Adequately Tested? Measuring and Governing Skill Test Adequacy in Practice", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.22015", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 0.65, "relation": "introduces", "releasedAt": "2026-07-24", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Haotian Si", "Junyi Chen", "Shuyang Yu", "Ruifeng Nie", "Jiate Li", "Jianqiang Zhao", "Meng Li", "Dengcheng He"], "categories": ["cs.SE"], "id": "2607.22015", "title": "Are Production Cloud Skills Adequately Tested? Measuring and Governing Skill Test Adequacy in Practice", "type": "arxiv", "url": "https://arxiv.org/abs/2607.22015"}, "sourceUpdatedAt": "2026-08-12T03:22:04Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "It separates test-suite adequacy from downstream task success and provides obligation-level diagnostic gaps."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
