{"id":49319297,"url":"https://github.com/google/arc-gen","last_synced_at":"2026-04-26T17:00:37.260Z","repository":{"id":292865113,"uuid":"920759800","full_name":"google/ARC-GEN","owner":"google","description":"A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus","archived":false,"fork":false,"pushed_at":"2026-04-18T23:21:42.000Z","size":49878,"stargazers_count":42,"open_issues_count":0,"forks_count":9,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-04-26T04:31:08.887Z","etag":null,"topics":["arc-agi","artificial-intelligence","benchmark-generator","program-synthesis"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/google.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-01-22T18:14:49.000Z","updated_at":"2026-04-18T23:21:47.000Z","dependencies_parsed_at":"2025-05-12T15:37:38.217Z","dependency_job_id":"3f79f001-165d-49cb-87c1-70d5906948c9","html_url":"https://github.com/google/ARC-GEN","commit_stats":null,"previous_names":["google/arc-gen"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/google/ARC-GEN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google%2FARC-GEN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google%2FARC-GEN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google%2FARC-GEN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google%2FARC-GEN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/google","download_url":"https://codeload.github.com/google/ARC-GEN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/google%2FARC-GEN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32305039,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-26T09:34:17.070Z","status":"ssl_error","status_checked_at":"2026-04-26T09:34:00.993Z","response_time":129,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arc-agi","artificial-intelligence","benchmark-generator","program-synthesis"],"created_at":"2026-04-26T17:00:30.543Z","updated_at":"2026-04-26T17:00:37.250Z","avatar_url":"https://github.com/google.png","language":"Python","readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"misc/images/arc-gen-logo.jpg\"\u003e\n\u003c/p\u003e\n\nThis repository contains the source code for *ARC-GEN*, a mimetic procedural benchmark generator for the Abstraction and Reasoning Corpus.\n\nFor a more in-depth description of this work, see the [corresponding paper on arxiv](https://arxiv.org/abs/2511.00162).\n\n## News\n\n * `2026-04-04`: ARC-GEN to be used as the official benchmark generator in the [IJCAI-ECAI 2026 NeuroGolf Challenge](https://sites.google.com/view/neurogolf-2026/home).\n * `2026-03-25`: ARC-GEN now supports 500 additional tasks from [ARC-AGI-2](https://arcprize.org/arc-agi/2).\n * `2025-10-31`: An ARC-GEN overview is now available on [arxiv](https://arxiv.org/abs/2511.00162).\n * `2025-07-31`: ARC-GEN to be used as the official benchmark generator in the [2025 Google Code Golf Championship](https://www.kaggle.com/competitions/google-code-golf-2025).\n * `2025-05-15`: The initial ARC-GEN repository committed to GitHub.\n\n## Installation\n\n```\n$ git clone --recurse-submodules https://github.com/google/ARC-GEN.git \u0026\u0026 cd ARC-GEN\n```\n\n## Usage\n\nFor **benchmark generation**, use the `generate` command with two arguments: the task ID, and the desired number of example pairs.\n\n```\n$ python3 arc_gen.py generate 1e0a9b12 1000\n[{'input': [[4, 0, 0, 0], [0, 0, 0, 0], [4, 0, 8, 0], [0, 3, 8, 0]], 'output': ...\n```\n\nFor **validation** (i.e., to ensure that the ARC-GEN generators can collectively reproduce the original [ARC-AGI-1](https://github.com/fchollet/ARC-AGI) benchmark suite), use the `validate` command:\n\n```\n$ python3 arc_gen.py validate\nA total of 400 generators passed.\nA total of 0 generators failed.\n```\n\nFor an example of customized **variations**, refer to [arc_gen_variations.py](https://github.com/google/ARC-GEN/blob/main/arc_gen_variations.py), which produces two variations on [Task #125](https://arcprize.org/play?task=543a7ed5):\n\n```\n  generator, _ = task_list.task_list().get(\"543a7ed5\")\n  examples = []\n  # Two examples of a \"large\" variation on Task #125.\n  examples.extend([generator(boxes=8, size=28) for _ in range(2)])\n  # Two examples of a \"large + inverted\" variation on Task #125.\n  common.set_colors([0, 1, 2, 6, 8, 5, 3, 7, 4, 9])\n  examples.extend([generator(boxes=8, size=28) for _ in range(2)])\n```\n\n## The ARC-GEN-100K Dataset\n\nFor those seeking a pre-generated dataset of sample pairs, the link below provides a static benchmark suite containing 100,000 examples produced by ARC-GEN (covering all four-hundred tasks):\n\n\u003cp align=\"center\"\u003e\nhttps://www.kaggle.com/datasets/arcgen100k/the-arc-gen-100k-dataset\n\u003cbr\u003e\u003cbr\u003e\n\u003cimg src=\"misc/images/arc-gen-gallery-faded.png\"\u003e\n\u003c/p\u003e\n\n## How to Cite?\n\n```\n@misc{Moffitt2025,\n  title={{ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus}}, \n  author={Michael D. Moffitt},\n  year={2025},\n  eprint={2511.00162},\n  archivePrefix={arXiv},\n  primaryClass={cs.AI},\n  url={https://arxiv.org/abs/2511.00162}, \n}\n```\n\n## Other Resouces\n\n * [RE-ARC: Reverse-Engineering the Abstraction and Reasoning Corpus](https://github.com/michaelhodel/re-arc) by Michael Hodel\n * [Bootstrapping ARC: Synthetic Problem Generation for ARC Visual Reasoning Tasks](https://github.com/xu3kev/BARC) by Wen-Ding Li and others\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle%2Farc-gen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoogle%2Farc-gen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoogle%2Farc-gen/lists"}