{"adoption": {"forks": 203, "observed_at": "2026-08-28T04:05:22.459213+00:00", "stars": 1689}, "canonical_url": "https://ross.abutalabs.com/products/project_codenet", "card": {"archived": false, "artifact_type": "dataset", "description": "This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX", "domain": ["artificial-intelligence", "machine-learning", "programming-languages", "education", "developer-tools"], "enriched": true, "function": ["machine-learning", "nlp", "data-science", "parser"], "health_score": 55, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["IBM/Project_CodeNet"], "name": "IBM/Project_CodeNet", "platform": ["python", "cross-platform"], "pushed_at": "2025-12-21T15:39:13+00:00", "repo": "IBM/Project_CodeNet", "stars": 1689, "tags": ["ai-for-code", "code-dataset", "code-generation", "code-translation", "benchmark", "competitive-programming"], "topics": [], "urls": [], "use_cases": ["train machine learning models on source code", "build code-to-code translation models", "research code summarization and completion", "benchmark AI models for code understanding", "filter and preprocess large code corpora by language or problem", "study competitive programming submissions for AI research"], "what_it_is": "Project CodeNet is a large-scale curated dataset of ~14 million code submissions across 50+ programming languages, built to support AI-for-Code research such as code search, summarization, completion, and code-to-code translation. This repository hosts tools and utilities in Python for accessing, selecting, and pre-processing the dataset, which is hosted on DAX.", "when_to_avoid": ["you need a production code analysis tool rather than a research dataset", "you want a small, clean dataset for quick experiments", "you need real-world production code rather than competitive programming submissions"], "when_to_choose": ["you need a large, diverse, curated dataset of code with metadata for AI-for-Code research", "you want benchmark problems with solutions in many programming languages", "you need Python tooling to access and preprocess code datasets"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/project_codenet", "repo": "IBM/Project_CodeNet", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:22.459213+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:38:39.851032+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "02e05f1da04d244af1885117c2b215323257dc9442bf2dbdef9ff5575208bcea", "fetched_at": "2026-08-28T04:05:22.459213+00:00", "kind": "readme", "missing": false, "url": "https://github.com/IBM/Project_CodeNet"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 58, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1948, "days_push": 255, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}