{"adoption": {"forks": 2241, "observed_at": "2026-08-28T04:09:22.092727+00:00", "stars": 5538}, "canonical_url": "https://ross.abutalabs.com/products/stopwords", "card": {"archived": false, "artifact_type": "dataset", "description": "中文常用停用词表（哈工大停用词表、百度停用词表等）", "domain": ["data-science"], "enriched": true, "function": ["nlp", "search-engine"], "health_score": 20, "homepage": null, "language": null, "license": null, "license_family": "other", "maturity": "stable", "member_repos": ["goto456/stopwords"], "name": "goto456/stopwords", "platform": ["cross-platform"], "pushed_at": "2024-01-25T09:41:04+00:00", "repo": "goto456/stopwords", "stars": 5538, "tags": ["chinese", "stopwords", "text-processing", "word-lists", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["filter stopwords from Chinese text before indexing", "preprocess Chinese text for NLP tasks like classification or clustering", "remove common words when building a Chinese search engine", "clean tokenized Chinese text for keyword extraction", "use standard stopword lists in Chinese word segmentation pipelines"], "what_it_is": "A collection of commonly used Chinese stopword lists, including the HIT (Harbin Institute of Technology), Baidu, Sichuan University, and general Chinese stopword lists, provided as plain text files. It is a data resource for filtering out common words during Chinese text preprocessing.", "when_to_avoid": ["you need stopword lists for languages other than Chinese", "you need a library or API rather than raw text files", "you require actively maintained or customizable stopword management"], "when_to_choose": ["you need ready-made, widely used Chinese stopword lists in plain text format", "you are building a Chinese search engine or text analysis pipeline and want to filter noise words", "you want multiple authoritative stopword sources (HIT, Baidu, SCU) in one place"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/stopwords", "repo": "goto456/stopwords", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:22.092727+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:55:43.044719+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1be1615810e9090e95ca1a87952338f0c3321afd565e3e9c7f5bc9f6b938a4fc", "fetched_at": "2026-08-28T04:09:22.092727+00:00", "kind": "readme", "missing": false, "url": "https://github.com/goto456/stopwords"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 3186, "days_push": 951, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}