{"adoption": {"forks": 154, "observed_at": "2026-08-28T04:03:21.532845+00:00", "stars": 1045}, "canonical_url": "https://ross.abutalabs.com/products/cc_net", "card": {"archived": true, "artifact_type": "library", "description": "Tools to download and cleanup Common Crawl data", "domain": ["machine-learning", "big-data"], "enriched": true, "function": ["etl", "nlp", "data-science", "web-scraping", "parser"], "health_score": 10, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["facebookresearch/cc_net"], "name": "facebookresearch/cc_net", "platform": ["python", "cli"], "pushed_at": "2023-04-25T08:02:37+00:00", "repo": "facebookresearch/cc_net", "stars": 1045, "tags": ["common-crawl", "corpus-mining", "language-model-filtering", "dataset-preparation", "deduplication", "natural-language-processing", "data-engineering", "linux"], "topics": [], "urls": [], "use_cases": ["download and clean Common Crawl snapshots", "extract monolingual corpora from web crawl data", "filter web text by language and perplexity", "deduplicate paragraphs across crawl data", "reproduce the CCNet corpus for multilingual model training", "prepare pretraining data for XLM-R style models"], "what_it_is": "CCNet is a Python pipeline from Facebook AI Research for downloading, deduplicating, and cleaning Common Crawl web data into high-quality monolingual datasets. It uses language models and perplexity filtering to extract per-language corpora for training multilingual language models.", "when_to_avoid": ["you only need a small curated dataset rather than web-scale crawling", "you need a maintained tool with recent updates and broad platform support", "you cannot run heavy CPU pipelines or external tools like KenLM and SentencePiece"], "when_to_choose": ["you need large-scale multilingual training corpora from Common Crawl", "you want to reproduce the CCNet or XLM-R data pipeline", "you need language identification and LM-based quality filtering on crawl data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cc_net", "repo": "facebookresearch/cc_net", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:21.532845+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:02:04.651372+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1eb6f30102acb02e71742071a5869b1aafa0b8fbdff51743dd928a9d5571119", "fetched_at": "2026-08-28T04:03:21.532845+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/cc_net"}, {"content_hash": "d7e243630cb351b293ca504ec46b7c0162816e144799fe12a7fdf58d3bad6119", "fetched_at": "2026-08-29T13:03:13.831525+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/cc_net/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2500, "days_push": 1226, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}