{"record": {"aliases": ["agentic-infrastructure-change-benchmark"], "artifacts": [{"id": "gh:aah20/agentic-infrastructure-change-benchmark", "kind": "repo", "url": "https://github.com/AAH20/agentic-infrastructure-change-benchmark"}], "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates AI agent proposals for cloud, Kubernetes, and network infrastructure changes across correctness, safety, reliability, economics, efficiency, and evidence using deterministic scenario-based checks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/AAH20/agentic-infrastructure-change-benchmark", "source": "claire_radar", "source_url": "https://github.com/AAH20/agentic-infrastructure-change-benchmark", "title": "Agentic Infrastructure ChangeBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:aah20/agentic-infrastructure-change-benchmark", "modality": null, "name": "Agentic Infrastructure ChangeBench", "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": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "true", "origin_record_id": "bm_agentic-infrastructure-change-benchmark_124c16f4", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "6b03952ba7f26c6d1601f34caead2f37f3ea25a9b5ebdcfa26b3edbc719d1d4b", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-09T01:01:18.936765Z", "source_url": "https://github.com/AAH20/agentic-infrastructure-change-benchmark"}, "publisher": null, "released": "2026-09-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:aah20/agentic-infrastructure-change-benchmark", "source_url": "https://github.com/AAH20/agentic-infrastructure-change-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-aah20-agentic-infrastructure-change-benchmark", "source": "claire_radar", "source_benchmark_id": "github:aah20/agentic-infrastructure-change-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["agentic-infrastructure-change-benchmark"], "annotation": "Mixed", "applicationDomains": ["Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/AAH20/agentic-infrastructure-change-benchmark", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark targets a specialized infrastructure-agent evaluation niche with a fresh repository and roadmap-stage adapters, leading to modest initial attention.", "score": 25}, "capabilities": [], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T01:01:18.936765Z", "inputHash": "e28380272c1cfc77ba098576c379486b0cbaf5b54c60724111b3da560666114e", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# Agentic Infrastructure ChangeBench **A vendor-neutral benchmark and evidence contract for AI agents that propose cloud, Kubernetes and network changes.**", "canonicalNameSource": "official_readme", "decisionReason": "The repository defines a deterministic evaluation kernel with three scenario seeds, a reference proposal, CLI, and local GitHub Action, providing a stable scoring contract and public reuse path.", "evaluationEvidence": {"reuse": "```bash python -m venv .venv source .venv/bin/activate python -m pip install -e . python -m unittest discover -s tests -p 'test_unittest.py' -v changebench \\ scenarios/azure-private-dns-outage.json \\ examples/reference-proposal.json \\ --output changebench-report.md", "scoring": "Scenario authors define the permissible actions and weighted checks. Any action outside the declared boundary is a hard safety failure regardless of the aggregate score.", "task": "Incident, ticket or desired state │ ▼ Agent under evaluation │ ▼ Terraform · OpenTofu · Bicep · Ansible · Kubernetes │ ▼ ChangeBench scenario runner"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T01:01:18.936765Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates AI agent proposals for cloud, Kubernetes, and network infrastructure changes across correctness, safety, reliability, economics, efficiency, and evidence using deterministic scenario-based checks.", "discoverySources": [{"id": "github:aah20/agentic-infrastructure-change-benchmark", "type": "github", "url": "https://github.com/AAH20/agentic-infrastructure-change-benchmark"}], "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "agentic-infrastructure-change-benchmark Vendor-neutral benchmark for AI agents proposing cloud, Kubernetes, network and Infrastructure as Code changes."}, "familyId": "bmf_c6825454ae49", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_agentic-infrastructure-change-benchmark_124c16f4", "indexedAt": "2026-09-07T06:22:04.880155Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/AAH20/agentic-infrastructure-change-benchmark", "project": "https://img.shields.io/badge/license-Apache--2.0-blue.svg"}, "metrics": [], "motivation": "agentic-infrastructure-change-benchmark Vendor-neutral benchmark for AI agents proposing cloud, Kubernetes, network and Infrastructure as Code changes.", "name": "Agentic Infrastructure ChangeBench", "oneLine": "Evaluates AI agent proposals for cloud, Kubernetes, and network infrastructure changes across correctness, safety, reliability, economics, efficiency, and evidence using deterministic scenario-based checks.", "paperTitle": "agentic-infrastructure-change-benchmark", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/AAH20/agentic-infrastructure-change-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T06:22:04.880155Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 207, "score": 23}, "method": "attention-ranking-v13", "rank": 207, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 471, "score": 23}, "method": "attention-ranking-v13", "rank": 471, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-05", "source": {"authors": ["AAH20"], "categories": [], "id": "github:aah20/agentic-infrastructure-change-benchmark", "publicSignals": {"githubStars": 0}, "title": "agentic-infrastructure-change-benchmark", "type": "github", "url": "https://github.com/AAH20/agentic-infrastructure-change-benchmark"}, "sourceUpdatedAt": "2026-09-05T07:07:41Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides a vendor-neutral, reviewable way to assess whether infrastructure change proposals are correct, safe, reversible, and economically rational before deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
