{"adoption": {"forks": 407, "observed_at": "2026-08-28T04:06:52.520777+00:00", "stars": 2443}, "canonical_url": "https://ross.abutalabs.com/products/codesearchnet", "card": {"archived": true, "artifact_type": "dataset", "description": "Datasets, tools, and benchmarks for representation learning of code.", "domain": ["machine-learning", "programming-languages", "big-data"], "enriched": true, "function": ["machine-learning", "deep-learning", "nlp", "search-engine", "benchmarking", "data-science"], "health_score": 10, "homepage": "https://arxiv.org/abs/1909.09436", "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["github/CodeSearchNet"], "name": "github/CodeSearchNet", "platform": ["python"], "pushed_at": "2022-01-31T09:25:07+00:00", "repo": "github/CodeSearchNet", "stars": 2443, "tags": ["code-search", "semantic-code-search", "representation-learning", "code-embeddings", "benchmark", "corpus", "tensorflow", "bert", "natural-language-processing", "search", "docker", "gpu", "linux"], "topics": ["deep-learning", "natural-language-processing", "programming-language-theory", "machine-learning", "tensorflow", "datasets", "data-science", "machine-learning-on-source-code", "representation-learning", "neural-networks", "python", "ml", "open-data", "data", "cnn", "rnn", "self-attention", "bert", "nlp", "nlp-machine-learning"], "urls": [], "use_cases": ["train models to search code from natural language queries", "learn code embeddings for functions", "benchmark semantic code search models", "pretrain models on a large code corpus", "evaluate code retrieval with human relevance annotations", "research neural networks on source code"], "what_it_is": "CodeSearchNet is a dataset and benchmark suite from GitHub for semantic code search, containing about 6 million functions across six programming languages with natural language documentation, plus expert relevance annotations. It includes baseline models and training scripts for representation learning of code.", "when_to_avoid": ["you need an actively maintained tool or recent framework support", "you want a production code search engine rather than research data", "you need languages outside the six supported ones"], "when_to_choose": ["you need a large labeled corpus of code and docstrings for research", "you want to benchmark semantic code search or code embedding models", "you need training data spanning Go, Java, JavaScript, PHP, Python, and Ruby"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/codesearchnet", "repo": "github/CodeSearchNet", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+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": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+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": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:52.520777+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+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": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+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": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+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": "2026-08-30T02:30:36.145281+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6482859d0c8396239a488afe59541f1f7d87c6e832e1559a1c74d2b7f59411cc", "fetched_at": "2026-08-28T04:06:52.520777+00:00", "kind": "readme", "missing": false, "url": "https://github.com/github/CodeSearchNet"}, {"content_hash": "e0782dfeee279602b3e0414fdf009ae4e65b2d4f279232a592250a92ab404418", "fetched_at": "2026-08-29T10:12:08.160593+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1909.09436"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T10:12:08.169967+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T10:12:08.173450+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T10:12:08.175242+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T10:12:08.171807+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.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", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2743, "days_push": 1675, "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}}