{"adoption": {"forks": 917, "observed_at": "2026-08-28T04:10:49.230827+00:00", "stars": 11636}, "canonical_url": "https://ross.abutalabs.com/products/cleanlab", "card": {"archived": false, "artifact_type": "library", "description": "Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.", "domain": ["data-science", "machine-learning", "analytics"], "enriched": true, "function": ["machine-learning", "data-science", "analytics", "nlp", "image-processing", "audio-processing"], "health_score": 74, "homepage": "https://cleanlab.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["cleanlab/cleanlab"], "name": "cleanlab/cleanlab", "platform": ["python", "cross-platform"], "pushed_at": "2026-01-13T17:39:04+00:00", "repo": "cleanlab/cleanlab", "stars": 11636, "tags": ["data-quality", "noisy-labels", "label-errors", "outlier-detection", "out-of-distribution-detection", "data-centric-ai", "active-learning", "data-cleaning", "data-validation", "weak-supervision", "multi-annotator", "confident-learning", "data-engineering"], "topics": ["weak-supervision", "data-cleaning", "data-quality", "noisy-labels", "data-centric-ai", "out-of-distribution-detection", "outlier-detection", "active-learning", "data-labeling", "data-profiling", "data-validation", "labeling", "data-curation", "annotation", "datasets", "exploratory-data-analysis", "data-annotation", "machine-learning", "anomaly-detection", "data-science"], "urls": [], "use_cases": ["find mislabeled examples in my training dataset", "detect outliers and duplicates in a machine learning dataset", "clean noisy labels before training a classifier", "estimate which annotators produce low-quality labels", "decide which data points to label next with active learning", "audit dataset quality for image, text, audio, or tabular data", "train robust models on real-world messy data"], "what_it_is": "Cleanlab is a Python library for data-centric AI that automatically detects issues in ML datasets, such as label errors, outliers, duplicates, and other data quality problems, using your existing model outputs. It works with text, image, audio, and tabular data and supports robust training, multi-annotator consensus, and active learning.", "when_to_avoid": ["you need LLM output monitoring, guardrails, or hallucination detection - that is Cleanlab's separate commercial TLM platform, not this library", "you need general-purpose data wrangling or ETL rather than ML-specific dataset issue detection", "your workflow is outside Python"], "when_to_choose": ["you have a supervised ML dataset and suspect label errors or other data issues", "you want to leverage existing model predictions or embeddings to find dataset problems", "you need multi-annotator consensus or annotator-quality scoring", "you want a well-established, actively maintained open-source data quality library"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cleanlab", "repo": "cleanlab/cleanlab", "role": "main", "score": 62}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.230827+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:15:26.618851+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1e6a9dce125f9f1c62bcd1c4d68d389a8a363cf2ce0918cfc0272e847d4924a2", "fetched_at": "2026-08-28T04:10:49.230827+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cleanlab/cleanlab"}, {"content_hash": "26872bedc4ebc0130775a13d19a18d6d73035b3eaf086d8c54e36ca38b93d4e6", "fetched_at": "2026-08-29T08:13:52.075825+00:00", "kind": "homepage", "missing": false, "url": "https://cleanlab.ai"}, {"content_hash": "f8cb314c1a8679d6cf282a3b5744567ba24b9e8029e88d64baf943c7bb7d7304", "fetched_at": "2026-08-29T08:13:52.084943+00:00", "kind": "site_page", "missing": false, "url": "https://cleanlab.ai/about"}, {"content_hash": "57973e5bdbaab4d8abbba61cc530bb71a8c370ac33449599b271f8c56a5dc533", "fetched_at": "2026-08-29T08:13:52.087146+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cleanlab/json"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.079987+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai"}, {"content_hash": "24f7e8afb4bbaec25daad7f18df1dab553c946df3c269845246c875c38ebcf29", "fetched_at": "2026-08-29T08:13:52.082253+00:00", "kind": "site_page", "missing": false, "url": "https://help.cleanlab.ai/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 62, "longevity": 100, "rhythm": 41}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3037, "days_push": 232, "days_rel": 232, "gap_med": 153, "n_releases_24m": 4}, "score": 62, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}