{"id":146790,"name":null,"description":"PII Processing code to detect and remediate PII in BigScience datasets. Reference implementation for the PII Hackathon","url":"https://github.com/bigscience-workshop/pii_processing","last_synced_at":"2025-09-09T14:41:02.044Z","repository":{"id":95663454,"uuid":"416332186","full_name":"bigscience-workshop/pii_processing","owner":"bigscience-workshop","description":"PII Processing code to detect and remediate PII in BigScience datasets. Reference implementation for the PII Hackathon","archived":false,"fork":false,"pushed_at":"2022-10-06T23:35:10.000Z","size":145037,"stargazers_count":8,"open_issues_count":8,"forks_count":6,"subscribers_count":15,"default_branch":"init","last_synced_at":"2025-09-01T05:59:04.865Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-10-12T12:40:05.000Z","updated_at":"2024-03-23T14:43:54.000Z","dependencies_parsed_at":"2023-04-27T11:01:02.887Z","dependency_job_id":null,"html_url":"https://github.com/bigscience-workshop/pii_processing","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/bigscience-workshop/pii_processing","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","download_url":"https://codeload.github.com/bigscience-workshop/pii_processing/tar.gz/refs/heads/init","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274314279,"owners_count":25262605,"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":"2025-09-09T02:00:10.223Z","response_time":80,"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"}},"owner":{"login":"bigscience-workshop","name":"BigScience Workshop","uuid":"82455566","kind":"organization","description":"Research workshop on large language models - The Summer of Language Models 21","email":"bigscience-contact@googlegroups.com","website":"https://bigscience.huggingface.co","location":null,"twitter":"BigScienceW","company":null,"icon_url":"https://avatars.githubusercontent.com/u/82455566?v=4","repositories_count":28,"last_synced_at":"2023-03-03T19:53:10.825Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/bigscience-workshop","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-14T05:10:07.455Z","updated_at":"2023-03-03T19:53:10.861Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bigscience-workshop/repositories"},"packages":[],"commits":{"id":5057064,"full_name":"bigscience-workshop/pii_processing","default_branch":"master","committers":null,"total_commits":null,"total_committers":null,"total_bot_commits":null,"total_bot_committers":null,"mean_commits":null,"dds":null,"past_year_committers":null,"past_year_total_commits":null,"past_year_total_committers":null,"past_year_total_bot_commits":null,"past_year_total_bot_committers":null,"past_year_mean_commits":null,"past_year_dds":null,"last_synced_at":null,"last_synced_commit":null,"created_at":"2024-11-11T03:12:44.722Z","updated_at":"2024-11-11T03:12:44.722Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:17:06.873Z","repositories_count":5524511,"commits_count":868166479,"contributors_count":31942272,"owners_count":917070,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"bigscience-workshop/pii_processing","html_url":"https://github.com/bigscience-workshop/pii_processing","last_synced_at":"2024-11-11T03:12:54.140Z","status":null,"issues_count":7,"pull_requests_count":1,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":0,"pull_requests_closed_count":0,"pull_request_authors_count":1,"issue_authors_count":1,"avg_comments_per_issue":0.0,"avg_comments_per_pull_request":0.0,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2024-11-11T03:12:48.248Z","updated_at":"2024-11-11T03:12:54.141Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/bigscience-workshop%2Fpii_processing/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"COLLABORATOR":7},"pull_request_author_associations_count":{"NONE":1},"issue_authors":{"huu4ontocord":7},"pull_request_authors":{"TrellixVulnTeam":1},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:00:11.778Z","repositories_count":10193878,"issues_count":32254962,"pull_requests_count":101822519,"authors_count":10740620,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{},"past_year_pull_request_authors":{},"maintainers":[{"login":"huu4ontocord","count":7,"url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors/huu4ontocord"}],"active_maintainers":[]},"events":{"total":{},"last_year":{}},"keywords":[],"dependencies":[{"ecosystem":"pypi","filepath":"neuralcoref/train/training_requirements.txt","sha":null,"kind":"manifest","created_at":"2023-04-27T11:01:02.735Z","updated_at":"2023-04-27T11:01:02.735Z","repository_link":"https://github.com/bigscience-workshop/pii_processing/blob/init/neuralcoref/train/training_requirements.txt","dependencies":[{"id":9253461860,"package_name":"spacy","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false},{"id":9253461864,"package_name":"torch","ecosystem":"pypi","requirements":"\u003e=1.3.0,\u003c1.4.0","direct":true,"kind":"runtime","optional":false},{"id":9253461866,"package_name":"tensorboardX","ecosystem":"pypi","requirements":"*","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-09T00:23:01.076Z","updated_at":"2025-10-07T08:36:45.030Z","avatar_url":"https://github.com/bigscience-workshop.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":0,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/146790","html_url":"https://science.ecosyste.ms/projects/146790"}