{"adoption": {"forks": 213, "observed_at": "2026-08-28T04:03:38.827662+00:00", "stars": 1116}, "canonical_url": "https://ross.abutalabs.com/products/thuocl", "card": {"archived": false, "artifact_type": "dataset", "description": "THUOCL（THU Open Chinese Lexicon）中文词库", "domain": [], "enriched": true, "function": ["nlp", "parser"], "health_score": 20, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["thunlp/THUOCL"], "name": "thunlp/THUOCL", "platform": ["cross-platform"], "pushed_at": "2023-04-03T01:21:32+00:00", "repo": "thunlp/THUOCL", "stars": 1116, "tags": ["chinese-lexicon", "word-segmentation", "word-frequency", "text-corpus", "thulac", "natural-language-processing", "chinese-language"], "topics": ["nlp", "chinese"], "urls": [], "use_cases": ["improve chinese word segmentation accuracy", "get domain-specific chinese vocabulary lists", "find chinese word frequency statistics", "build a chinese nlp custom dictionary", "segment medical or legal chinese text better", "download chinese idiom and place name word lists"], "what_it_is": "THUOCL (THU Open Chinese Lexicon) is a set of high-quality open Chinese word lists curated by Tsinghua University's NLP lab, covering domains like IT, finance, medicine, law, food, and place names. Each entry includes document frequency statistics, and the lexicons are designed to improve Chinese word segmentation, particularly when paired with the THULAC toolkit.", "when_to_avoid": ["you need a segmentation tool or runtime library rather than static word lists", "you need non-Chinese language lexicons", "you need frequently updated vocabularies, as updates are infrequent"], "when_to_choose": ["you need curated, human-verified Chinese domain vocabularies with DF values", "you use THULAC or another segmenter and want domain-specific dictionaries", "you need Chinese lexicons for IT, finance, medicine, law, or other domains"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/thuocl", "repo": "thunlp/THUOCL", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.827662+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:42:06.459704+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3a8b1fcb89c07651c4f45fcb68dc1313759cd8335d7053aa9414bf9b52238298", "fetched_at": "2026-08-28T04:03:38.827662+00:00", "kind": "readme", "missing": false, "url": "https://github.com/thunlp/THUOCL"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "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": 2842, "days_push": 1249, "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}}