{"adoption": {"forks": 186, "observed_at": "2026-08-28T04:03:54.755691+00:00", "stars": 1184}, "canonical_url": "https://ross.abutalabs.com/products/azurepublicdataset", "card": {"archived": false, "artifact_type": "dataset", "description": "Microsoft Azure Traces", "domain": ["cloud-computing", "data-science", "large-language-models", "microservices"], "enriched": true, "function": ["data-science", "benchmarking", "analytics"], "health_score": 90, "homepage": null, "language": "Jupyter Notebook", "license": "CC-BY-4.0", "license_family": "other", "maturity": "active", "member_repos": ["Azure/AzurePublicDataset"], "name": "Azure/AzurePublicDataset", "platform": ["cross-platform", "python"], "pushed_at": "2026-06-03T12:53:37+00:00", "repo": "Azure/AzurePublicDataset", "stars": 1184, "tags": ["azure-traces", "cloud-workloads", "vm-traces", "serverless", "llm-inference-traces", "research-dataset", "jupyter-notebook", "research"], "topics": [], "urls": [], "use_cases": ["study cloud VM workload patterns from Azure production traces", "research serverless function invocation behavior", "model LLM inference request workloads with token counts", "evaluate VM packing and allocation algorithms", "analyze performance variability of Azure VM SKUs", "benchmark cloud resource management research"], "what_it_is": "A repository of public Microsoft Azure workload traces released for the research community, including VM workloads, Azure Functions invocations and blob accesses, LLM inference traces, and VM benchmark noise data. Trace files are hosted as GitHub release assets with documentation pages per dataset.", "when_to_avoid": ["you need live or streaming cloud telemetry", "you need a tool or library rather than raw trace data", "your research requires non-Azure or non-cloud workloads"], "when_to_choose": ["you need real-world cloud workload data for academic research", "you are studying serverless, VM scheduling, or LLM inference capacity planning", "you want reproducible traces tied to published systems papers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/azurepublicdataset", "repo": "Azure/AzurePublicDataset", "role": "main", "score": 88}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:54.755691+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:24:13.588450+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a95a1c9af2f0d712e8c75a3cb9fc71b7205722f6f29f603423a14341930c013a", "fetched_at": "2026-08-28T04:03:54.755691+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Azure/AzurePublicDataset"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 85, "longevity": 100, "rhythm": 86}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3302, "days_push": 91, "days_rel": 92, "gap_med": 0, "n_releases_24m": 6}, "score": 88, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}