{"adoption": {"forks": 291, "observed_at": "2026-08-28T04:04:41.223035+00:00", "stars": 1423}, "canonical_url": "https://ross.abutalabs.com/products/tencent-sensitive-words", "card": {"archived": true, "artifact_type": "dataset", "description": "腾讯的离线敏感词库", "domain": ["security", "censorship-circumvention", "developer-tools"], "enriched": true, "function": ["nlp", "security", "data-generation"], "health_score": 10, "homepage": null, "language": null, "license": "AGPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["cjh0613/tencent-sensitive-words"], "name": "cjh0613/tencent-sensitive-words", "platform": ["cross-platform"], "pushed_at": "2026-02-23T06:51:08+00:00", "repo": "cjh0613/tencent-sensitive-words", "stars": 1423, "tags": ["sensitive-words", "wordlist", "offline-dataset", "content-filtering", "chinese-text", "text-moderation", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["filter sensitive words in user-generated content", "build a Chinese profanity or censorship word filter", "research Tencent's content moderation vocabulary", "add a sensitive-word list to a chat or forum moderation tool", "preprocess Chinese text before publishing"], "what_it_is": "An offline dataset of sensitive words extracted from Tencent's software, published as a wordlist repository. It is intended for content moderation, filtering, and research on Chinese text censorship.", "when_to_avoid": ["you need real-time moderation with context understanding rather than a static wordlist", "you need an English or multilingual wordlist", "you require a maintained library with matching algorithms rather than raw data"], "when_to_choose": ["you need an offline Chinese sensitive-word list without calling an API", "you want a dataset for studying Chinese content filtering", "you need a wordlist to integrate into your own moderation pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tencent-sensitive-words", "repo": "cjh0613/tencent-sensitive-words", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:41.223035+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:37:38.924730+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "674d5d64168449c481941fc86478099531831967c7c937eedfaf5a208fa43dcf", "fetched_at": "2026-08-28T04:04:41.223035+00:00", "kind": "readme", "missing": false, "url": "https://github.com/cjh0613/tencent-sensitive-words"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 69, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1827, "days_push": 191, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}