{"id":19542040,"url":"https://github.com/bigscience-workshop/data_sourcing","last_synced_at":"2025-10-24T21:49:27.520Z","repository":{"id":46680703,"uuid":"411407421","full_name":"bigscience-workshop/data_sourcing","owner":"bigscience-workshop","description":"This directory gathers the tools developed by the Data Sourcing Working Group","archived":false,"fork":false,"pushed_at":"2021-10-25T19:16:46.000Z","size":773,"stargazers_count":31,"open_issues_count":5,"forks_count":6,"subscribers_count":17,"default_branch":"master","last_synced_at":"2025-09-09T16:09:25.060Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/bigscience-workshop.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-09-28T19:05:52.000Z","updated_at":"2024-02-14T13:21:22.000Z","dependencies_parsed_at":"2022-09-03T20:00:12.314Z","dependency_job_id":null,"html_url":"https://github.com/bigscience-workshop/data_sourcing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bigscience-workshop/data_sourcing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata_sourcing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata_sourcing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata_sourcing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata_sourcing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","download_url":"https://codeload.github.com/bigscience-workshop/data_sourcing/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fdata_sourcing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":280872031,"owners_count":26405606,"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","status":"online","status_checked_at":"2025-10-24T02:00:06.418Z","response_time":73,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-11-11T03:12:54.333Z","updated_at":"2025-10-24T21:49:27.477Z","avatar_url":"https://github.com/bigscience-workshop.png","language":"Python","readme":"# BigScience Data Sourcing Code\n\nThis directory gathers the tools developed by the Data Sourcing Working Group\n\n## First Sourcing Sprint: October 2021\n\nThe code for the input form can be found in `sourcing_sprint/streamlit_form.py`\n\nThe code for the exploration tool can be found in `sourcing_sprint/streamlit_explore.py`\n\nThe resource entries can be found in `sourcing_sprint/resources` (one folder per language, one `.jsonl` file per resource)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbigscience-workshop%2Fdata_sourcing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbigscience-workshop%2Fdata_sourcing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbigscience-workshop%2Fdata_sourcing/lists"}