{"adoption": {"forks": 257, "observed_at": "2026-08-28T04:08:07.002776+00:00", "stars": 3486}, "canonical_url": "https://ross.abutalabs.com/products/docta", "card": {"archived": false, "artifact_type": "library", "description": "A Doctor for your data", "domain": ["data-science", "machine-learning", "large-language-models", "developer-tools"], "enriched": true, "function": ["data-science", "machine-learning", "nlp", "etl"], "health_score": 73, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["Docta-ai/docta"], "name": "Docta-ai/docta", "platform": ["python", "cross-platform"], "pushed_at": "2026-06-16T06:03:43+00:00", "repo": "Docta-ai/docta", "stars": 3486, "tags": ["data-curation", "data-diagnosis", "label-errors", "data-quality", "rlhf", "training-free", "data-centric-ai"], "topics": ["data", "data-centric-ai", "data-centric-machine-learning", "data-curation", "data-diagnosis", "language-model", "rlhf"], "urls": [], "use_cases": ["find label errors in my dataset", "clean noisy labels in RLHF data", "detect human annotation mistakes in LLM alignment data", "curate and diagnose image datasets", "fix mislabeled tabular data before training", "audit dataset quality without training a model"], "what_it_is": "Docta is a Python library for data-centric AI that diagnoses and fixes issues in datasets such as label errors, noise, and misannotations. It works training-free on tabular data, text, images, and pre-trained model embeddings, including LLM alignment/RLHF data.", "when_to_avoid": ["you need a fully automated production data pipeline rather than diagnostic tooling", "your use is commercial and you cannot accept the non-commercial CC BY-NC 4.0 license", "you need active data labeling or annotation workflow management"], "when_to_choose": ["you suspect label noise or annotation errors are hurting model performance", "you need training-free data diagnosis on tabular, text, or image data", "you are preparing RLHF or LLM alignment datasets and want to audit label quality"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/docta", "repo": "Docta-ai/docta", "role": "main", "score": 69}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.002776+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:36:23.008233+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7d6db27ae82cade02fec1cb95aeee987c49b70f86d41264921585ae8b4bd52d3", "fetched_at": "2026-08-28T04:08:07.002776+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Docta-ai/docta"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 87, "longevity": 87, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 1219, "days_push": 78, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 69, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}