{"adoption": {"forks": 82, "observed_at": "2026-08-28T04:03:48.388469+00:00", "stars": 1158}, "canonical_url": "https://ross.abutalabs.com/products/data-centric-ai", "card": {"archived": false, "artifact_type": "learning-resource", "description": "A curated, but incomplete, list of data-centric AI resources.", "domain": ["artificial-intelligence", "machine-learning", "data-science", "awesome-lists"], "enriched": true, "function": ["documentation"], "health_score": 20, "homepage": null, "language": null, "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["daochenzha/data-centric-AI"], "name": "daochenzha/data-centric-AI", "platform": ["cross-platform"], "pushed_at": "2024-06-26T23:03:47+00:00", "repo": "daochenzha/data-centric-AI", "stars": 1158, "tags": ["awesome-list", "data-centric-ai", "data-curation", "data-quality", "curated-resources"], "topics": ["artificial-intelligence", "data-centric-ai", "ai", "machine-learning", "data-curation", "data-centric", "data-centric-machine-learning", "data-science", "data-quality", "data-engineering"], "urls": [], "use_cases": ["find papers on data-centric AI", "learn about data quality and curation for machine learning", "get started with data-centric AI research", "find tutorials and surveys on data-centric machine learning", "discover data-centric AI tools and benchmarks"], "what_it_is": "A curated awesome-list of data-centric AI resources, including survey papers, tutorials, blogs, and related projects. It selectively collects papers presenting distinct ideas in data-centric machine learning.", "when_to_avoid": ["you need runnable software or code libraries", "you need an exhaustive bibliography of every data-centric AI paper", "you need actively maintained tooling"], "when_to_choose": ["you want a curated reading list on data-centric AI", "you are researching data quality and curation in ML", "you need survey papers and tutorials on the topic"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/data-centric-ai", "repo": "daochenzha/data-centric-AI", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:48.388469+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:31:57.017015+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "aae739febd8c26e31f493f91f3acb4cabb67b6e68a2084eb4b9d6699f2300776", "fetched_at": "2026-08-28T04:03:48.388469+00:00", "kind": "readme", "missing": false, "url": "https://github.com/daochenzha/data-centric-AI"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 91, "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": 1275, "days_push": 798, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 30, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}