{"adoption": {"forks": 858, "observed_at": "2026-08-28T04:09:34.163648+00:00", "stars": 6001}, "canonical_url": "https://ross.abutalabs.com/products/snorkel", "card": {"archived": false, "artifact_type": "library", "description": "A system for quickly generating training data with weak supervision", "domain": ["machine-learning", "data-science", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "data-science", "etl"], "health_score": 77, "homepage": "https://snorkel.org", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["snorkel-team/snorkel"], "name": "snorkel-team/snorkel", "platform": ["python", "cross-platform"], "pushed_at": "2026-06-08T19:59:20+00:00", "repo": "snorkel-team/snorkel", "stars": 6001, "tags": ["weak-supervision", "data-labeling", "training-data", "data-augmentation", "data-slicing", "labeling-functions"], "topics": ["machine-learning", "ai", "weak-supervision", "labeling", "data-science", "python", "snorkel", "training-data", "data-augmentation", "data-slicing"], "urls": [], "use_cases": ["generate training data without manual labeling", "write labeling functions for weak supervision", "programmatically label a large dataset", "augment training data for machine learning", "create data slices to evaluate model performance", "denoise noisy labels from multiple labeling sources"], "what_it_is": "Snorkel is a Python library for programmatically building and managing training data using weak supervision, letting users write labeling functions instead of hand-labeling data. It also supports data augmentation and data slicing, and originated as a Stanford research project.", "when_to_avoid": ["you need an end-to-end commercial platform with a UI (consider Snorkel Flow)", "you expect active feature development, as the team has shifted focus to Snorkel Flow", "you need fully automated labeling with no heuristic input"], "when_to_choose": ["you need to label large datasets quickly without hand-annotation", "you have domain heuristics that can be encoded as labeling functions", "you want research-backed weak supervision modeling in Python"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/snorkel", "repo": "snorkel-team/snorkel", "role": "main", "score": 62}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:34.163648+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:49:48.984961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "39c9a0a49113f956bca45674ef734a30ba9d866997b661fdae0d7c2a7e648505", "fetched_at": "2026-08-28T04:09:34.163648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/snorkel-team/snorkel"}, {"content_hash": "df57fbe0a8c4caf3e4fca8df3cb77c10287b1937661b441b2dd82efb20b331d8", "fetched_at": "2026-08-29T08:45:47.137898+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/snorkel/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 86, "longevity": 100, "rhythm": 8}, "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": 3841, "days_push": 86, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 62, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}