{"adoption": {"forks": 1088, "observed_at": "2026-08-28T04:05:41.565648+00:00", "stars": 1827}, "canonical_url": "https://ross.abutalabs.com/products/nltk_data", "card": {"archived": false, "artifact_type": "dataset", "description": "NLTK Data", "domain": ["data-science"], "enriched": true, "function": ["nlp", "machine-learning"], "health_score": 74, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["nltk/nltk_data"], "name": "nltk/nltk_data", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-01T00:40:19+00:00", "repo": "nltk/nltk_data", "stars": 1827, "tags": ["corpora", "tokenizers", "nltk", "language-models", "text-data", "natural-language-processing", "linguistics"], "topics": ["nltk", "nlp", "natural-language-processing", "corpora", "linguistics"], "urls": [], "use_cases": ["download corpora for nltk text processing", "get tokenizer models for sentence and word splitting", "find labeled datasets for nlp teaching and experiments", "obtain pretrained models for pos tagging and named entity recognition", "set up nltk data for a python nlp project", "access stopwords and wordnet for text preprocessing"], "what_it_is": "The official data distribution repository for NLTK, containing corpora, trained models, tokenizers, and other data packages used with the Natural Language Toolkit. Data is installed via NLTK's built-in downloader (nltk.download()).", "when_to_avoid": ["you need a modern deep-learning model hub rather than classic NLP data", "you require strict licensing guarantees without checking per-dataset terms, since individual package licenses vary"], "when_to_choose": ["you use NLTK and need its corpora, grammars, or trained models", "you want well-known reference datasets for NLP education and prototyping"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/nltk_data", "repo": "nltk/nltk_data", "role": "main", "score": 73}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:41.565648+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:19:25.888186+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c15eb1477201863e4ec02afe48dccf3490c4374b4fbb1fc3b1ce90809dc7cd24", "fetched_at": "2026-08-28T04:05:41.565648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/nltk/nltk_data"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5228, "days_push": 64, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 73, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}