{"adoption": {"forks": 627, "observed_at": "2026-08-28T04:08:50.543654+00:00", "stars": 4454}, "canonical_url": "https://ross.abutalabs.com/products/cluedatasetsearch", "card": {"archived": false, "artifact_type": "dataset", "description": "搜索所有中文NLP数据集，附常用英文NLP数据集", "domain": ["machine-learning", "data-science", "localization"], "enriched": true, "function": ["nlp", "search-engine", "data-science"], "health_score": 20, "homepage": "https://www.cluebenchmarks.com/dataSet_search.html", "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["CLUEbenchmark/CLUEDatasetSearch"], "name": "CLUEbenchmark/CLUEDatasetSearch", "platform": ["python", "cross-platform"], "pushed_at": "2022-11-21T08:04:52+00:00", "repo": "CLUEbenchmark/CLUEDatasetSearch", "stars": 4454, "tags": ["chinese-nlp", "dataset-catalog", "ner", "question-answering", "text-classification", "machine-translation", "knowledge-graph", "sentiment-analysis", "text-similarity", "text-summarization", "reading-comprehension", "corpus", "awesome-list", "natural-language-processing"], "topics": ["nlp", "datasets", "chinese", "ner", "qa", "match", "text-classification", "machine-translation", "knowledge-graph", "corpus", "machine-reading-comprehension", "sentiment-analysis", "text-similarity", "text-summarization"], "urls": [], "use_cases": ["find Chinese NER datasets", "locate Chinese question answering datasets for training", "search text classification datasets in Chinese", "find Chinese machine translation corpora", "discover sentiment analysis datasets for Chinese", "find reading comprehension datasets in Chinese", "compare Chinese and English NLP datasets"], "what_it_is": "A curated searchable catalog of Chinese NLP datasets (with common English NLP datasets included), organized by task such as NER, QA, text classification, matching, summarization, machine translation, and knowledge graphs. It is part of the CLUE benchmark ecosystem and links to dataset sources rather than hosting data itself.", "when_to_avoid": ["you need the actual dataset files hosted and maintained in one place - it only links to external sources", "you need datasets for languages other than Chinese and English", "you need a programmatically queryable dataset API rather than a curated list"], "when_to_choose": ["you need Chinese-language NLP training or evaluation data and want a task-organized index", "you are benchmarking Chinese language understanding models and need dataset references", "you want a quick catalog of both Chinese and common English NLP datasets"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cluedatasetsearch", "repo": "CLUEbenchmark/CLUEDatasetSearch", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:50.543654+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:20:44.990303+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "293da1225f0d7c0d31145283ce00019083c6671986db664781db7fa0797a90c8", "fetched_at": "2026-08-28T04:08:50.543654+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUEDatasetSearch"}, {"content_hash": "0f3d32cd59265f305a4521721b4231be3d6cdf8d7f5cb4c106e507cc0d578e20", "fetched_at": "2026-08-29T09:07:37.956305+00:00", "kind": "homepage", "missing": false, "url": "https://www.cluebenchmarks.com/dataSet_search.html"}, {"content_hash": "b318c2db06a4b497f7c3b279acb47543327b0f9135249b190f245eb8851fd93f", "fetched_at": "2026-08-29T09:07:37.965679+00:00", "kind": "site_page", "missing": false, "url": "https://www.cluebenchmarks.com/aboutClue.html"}], "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": 2385, "days_push": 1381, "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}}