{"id":27984408,"url":"https://github.com/CJReinforce/PURE","last_synced_at":"2025-05-08T05:01:59.017Z","repository":{"id":276608396,"uuid":"929766311","full_name":"CJReinforce/PURE","owner":"CJReinforce","description":"Official code for the paper, \"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning\"","archived":false,"fork":false,"pushed_at":"2025-05-06T09:55:25.000Z","size":33284,"stargazers_count":112,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"verl","last_synced_at":"2025-05-06T10:54:07.140Z","etag":null,"topics":["llm","mathematics","o1","r1","reasoning","reinforcement-finetuning","reinforcement-learning","rl"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CJReinforce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-02-09T10:56:28.000Z","updated_at":"2025-05-06T09:55:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"4797a46e-7ea7-4f45-8736-aa6d21374bcc","html_url":"https://github.com/CJReinforce/PURE","commit_stats":null,"previous_names":["cjreinforce/pure"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CJReinforce%2FPURE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CJReinforce%2FPURE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CJReinforce%2FPURE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CJReinforce%2FPURE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CJReinforce","download_url":"https://codeload.github.com/CJReinforce/PURE/tar.gz/refs/heads/verl","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253002856,"owners_count":21838640,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["llm","mathematics","o1","r1","reasoning","reinforcement-finetuning","reinforcement-learning","rl"],"created_at":"2025-05-08T05:01:53.035Z","updated_at":"2025-05-08T05:01:53.964Z","avatar_url":"https://github.com/CJReinforce.png","language":"Python","funding_links":[],"categories":["A01_文本生成_文本对话"],"sub_categories":["大语言对话模型及数据"],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCJReinforce%2FPURE","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCJReinforce%2FPURE","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCJReinforce%2FPURE/lists"}