{"adoption": {"forks": 601, "observed_at": "2026-08-28T04:04:59.769261+00:00", "stars": 1535}, "canonical_url": "https://ross.abutalabs.com/products/frequencywords", "card": {"archived": false, "artifact_type": "dataset", "description": "Repository for Frequency Word List Generator and processed files", "domain": ["data-science"], "enriched": true, "function": ["nlp", "data-generation"], "health_score": 20, "homepage": null, "language": "C#", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["hermitdave/FrequencyWords"], "name": "hermitdave/FrequencyWords", "platform": ["cross-platform"], "pushed_at": "2022-02-07T10:32:14+00:00", "repo": "hermitdave/FrequencyWords", "stars": 1535, "tags": ["word-frequency-lists", "opensubtitles", "corpus", "text-processing", "csharp", "natural-language-processing", "localization"], "topics": [], "urls": [], "use_cases": ["get a frequency word list for a language", "build an autocomplete or predictive keyboard", "rank vocabulary words by commonness for language learning", "filter or prioritize tokens in NLP preprocessing", "generate word clouds weighted by real usage"], "what_it_is": "A repository of preprocessed word frequency lists for many languages, generated from OpenSubtitles corpora, plus the C# generator code. Each list maps words to occurrence counts (e.g. en_50k.txt).", "when_to_avoid": ["you need part-of-speech tags, lemmas, or rich linguistic annotations", "you need up-to-date corpora or domain-specific frequency data", "you need sentence-level or contextual language data"], "when_to_choose": ["you need ready-made frequency data for many languages", "you want simple word-count lists without heavy NLP tooling", "you need corpus-derived word rankings for input methods or education apps"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/frequencywords", "repo": "hermitdave/FrequencyWords", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.769261+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:09.202158+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a92fcc50e27f7b2d5860ec1c1ce794dc4c892d945bfa4c8c3136cdfd213ee710", "fetched_at": "2026-08-28T04:04:59.769261+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hermitdave/FrequencyWords"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3669, "days_push": 1668, "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}}