{"adoption": {"forks": 83, "observed_at": "2026-08-28T04:03:14.830178+00:00", "stars": 1018}, "canonical_url": "https://ross.abutalabs.com/products/cluecorpus2020", "card": {"archived": false, "artifact_type": "dataset", "description": "Large-scale Pre-training Corpus for Chinese 100G 中文预训练语料 ", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "nlp", "data-generation"], "health_score": 60, "homepage": "https://arxiv.org/abs/2003.01355", "language": null, "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["CLUEbenchmark/CLUECorpus2020"], "name": "CLUEbenchmark/CLUECorpus2020", "platform": ["python", "cross-platform"], "pushed_at": "2026-02-06T11:43:34+00:00", "repo": "CLUEbenchmark/CLUECorpus2020", "stars": 1018, "tags": ["chinese-corpus", "pretraining", "language-modeling", "common-crawl", "vocabulary", "bert", "natural-language-processing"], "topics": ["chinese", "chinese-corpus", "datasets", "pretrain", "corpus", "nlp", "bert", "roberta", "albert"], "urls": [], "use_cases": ["pretrain a Chinese language model like BERT or RoBERTa", "find a large Chinese text corpus for language modeling", "train a Chinese text generation model", "reduce tokenizer vocabulary size for Chinese NLP", "get cleaned Chinese web text for self-supervised learning", "fine-tune Chinese NLP models on a quality corpus"], "what_it_is": "CLUECorpus2020 is a 100GB cleaned Chinese text corpus (35 billion characters) derived from Common Crawl for pre-training language models, plus a smaller 14GB CLUECorpusSmall and a compact 8K-token Chinese vocabulary. It is distributed by the CLUE benchmark organization with an accompanying technical report and pre-trained models.", "when_to_avoid": ["you need multilingual corpora beyond Chinese", "you cannot or will not apply via email and agree to the no-redistribution terms", "you need an actively updated corpus rather than a fixed 2020 snapshot"], "when_to_choose": ["you need large-scale Chinese text for pretraining or language generation", "you want a smaller Chinese vocabulary to cut compute and memory costs", "you need pre-formatted training data with one sentence per line"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cluecorpus2020", "repo": "CLUEbenchmark/CLUECorpus2020", "role": "main", "score": 62}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.830178+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:09:25.492882+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "852fa296ea2b06a13b38ddf50d95f160ecc3e144a7c006728f089f3b070c037a", "fetched_at": "2026-08-28T04:03:14.830178+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CLUEbenchmark/CLUECorpus2020"}, {"content_hash": "fc36d967248df402974cdb4c0336dc52edb37da8d763f568ccfb411b80870763", "fetched_at": "2026-08-29T13:09:58.579799+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2003.01355"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T13:09:58.627186+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T13:09:58.645583+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T13:09:58.647658+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T13:09:58.643687+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 66, "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": 2412, "days_push": 208, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 62, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}