{"adoption": {"forks": 477, "observed_at": "2026-08-28T04:06:19.510003+00:00", "stars": 2154}, "canonical_url": "https://ross.abutalabs.com/products/clusterdata", "card": {"archived": false, "artifact_type": "dataset", "description": "cluster data collected from production clusters in Alibaba for cluster management research", "domain": ["data-science", "big-data", "microservices", "cloud-computing", "machine-learning"], "enriched": true, "function": ["data-science", "analytics", "benchmarking"], "health_score": 71, "homepage": null, "language": "Jupyter Notebook", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["alibaba/clusterdata"], "name": "alibaba/clusterdata", "platform": ["python", "cross-platform"], "pushed_at": "2026-06-03T02:11:46+00:00", "repo": "alibaba/clusterdata", "stars": 2154, "tags": ["cluster-traces", "workload-analysis", "datacenter", "gpu-traces", "microservices", "research-dataset"], "topics": ["dataset"], "urls": [], "use_cases": ["analyze production datacenter workload traces", "research cluster scheduling and resource management", "study GPU cluster utilization for ML workloads", "model microservice call dependencies and latency", "simulate colocation of online and batch workloads", "study CPU microarchitecture contention in datacenters"], "what_it_is": "A collection of production cluster trace datasets from Alibaba covering batch workloads, GPU/ML workloads, microservices, and microarchitectural metrics. It is intended for research on cluster management, scheduling, and datacenter workload characterization.", "when_to_avoid": ["you need a tool or library rather than raw trace data", "you need small-scale or synthetic datasets with permissive licensing", "you cannot complete the download survey or handle large data volumes"], "when_to_choose": ["you need real-world production cluster traces for systems research", "you are studying scheduling, colocation, or resource management in large datacenters", "you need GPU or microservice workload data for simulation or modeling"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/clusterdata", "repo": "alibaba/clusterdata", "role": "main", "score": 70}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:19.510003+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:50:37.190094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "473a53c0eb0189dea7a5732b6564bc38dfea7b56440e97aedaec84a324b7967d", "fetched_at": "2026-08-28T04:06:19.510003+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alibaba/clusterdata"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 85, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3284, "days_push": 92, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 70, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}