{"adoption": {"forks": 73, "observed_at": "2026-08-28T04:04:49.009535+00:00", "stars": 1469}, "canonical_url": "https://ross.abutalabs.com/products/code-kern-ai-refinery", "card": {"archived": false, "artifact_type": "application", "description": "The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.", "domain": ["machine-learning", "data-science", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "nlp", "data-science", "etl"], "health_score": 27, "homepage": "https://www.kern.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["code-kern-ai/refinery"], "name": "code-kern-ai/refinery", "platform": ["python", "self-hosted"], "pushed_at": "2024-12-09T12:46:40+00:00", "repo": "code-kern-ai/refinery", "stars": 1469, "tags": ["data-labeling", "text-annotation", "data-centric-ai", "active-learning", "human-in-the-loop", "training-data", "weak-supervision", "text-classification", "natural-language-processing", "web-server", "docker"], "topics": ["annotations", "data-centric-ai", "data-labeling", "deep-learning", "labeling", "labeling-tool", "machine-learning", "natural-language-processing", "neural-search", "nlp", "text-annotation", "transformers", "python", "human-in-the-loop", "spacy", "artificial-intelligence", "data-science", "text-classification", "active-learning", "supervised-learning"], "urls": [], "use_cases": ["label text data for NLP model training", "manage and version training datasets", "run active learning annotation workflows", "assess quality of labeled text data", "bootstrap labeled data for a text classifier", "collaborate on text annotation with a team"], "what_it_is": "An open-source tool for scaling, assessing, and maintaining natural language training data, treating datasets like software artifacts. It provides text annotation, labeling workflows, and data-centric AI capabilities for NLP projects.", "when_to_avoid": ["you need image or audio annotation rather than text", "you want a fully automated pipeline with no human-in-the-loop"], "when_to_choose": ["you need labeled NLP training data but lack annotations", "you want a data-centric workflow for maintaining text datasets", "you want an open-source alternative to commercial labeling tools"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/code-kern-ai-refinery", "repo": "code-kern-ai/refinery", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:49.009535+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:34:52.683388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e376ca50321ea06c680a3898ac6069266a4a085339979f9bd3a4035792ee3900", "fetched_at": "2026-08-28T04:04:49.009535+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code-kern-ai/refinery"}, {"content_hash": "076e07aa30f4ca6b0a54ddd13ba6e154d59cc736570d763d88527aca8a7ee2da", "fetched_at": "2026-08-29T11:43:05.408287+00:00", "kind": "homepage", "missing": false, "url": "https://www.kern.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "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": 1521, "days_push": 632, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}