{"id":94750,"name":null,"description":null,"url":"https://github.com/ai4bharat/deduplicate-text-datasets","last_synced_at":"2025-09-09T01:20:38.704Z","repository":{"id":194749129,"uuid":"691434994","full_name":"AI4Bharat/deduplicate-text-datasets","owner":"AI4Bharat","description":null,"archived":false,"fork":true,"pushed_at":"2023-09-14T09:57:15.000Z","size":78,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2023-09-15T00:40:59.951Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Rust","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":"google-research/deduplicate-text-datasets","license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AI4Bharat.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}},"created_at":"2023-09-14T07:10:22.000Z","updated_at":"2023-09-15T00:41:38.610Z","dependencies_parsed_at":"2023-09-15T00:51:37.385Z","dependency_job_id":null,"html_url":"https://github.com/AI4Bharat/deduplicate-text-datasets","commit_stats":null,"previous_names":["ai4bharat/deduplicate-text-datasets"],"tags_count":null,"template":null,"template_full_name":null,"purl":"pkg:github/AI4Bharat/deduplicate-text-datasets","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AI4Bharat%2Fdeduplicate-text-datasets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AI4Bharat%2Fdeduplicate-text-datasets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AI4Bharat%2Fdeduplicate-text-datasets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AI4Bharat%2Fdeduplicate-text-datasets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AI4Bharat","download_url":"https://codeload.github.com/AI4Bharat/deduplicate-text-datasets/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AI4Bharat%2Fdeduplicate-text-datasets/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274232002,"owners_count":25245854,"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":"2025-09-08T02:00:09.813Z","response_time":121,"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":"AI4Bharat","name":"AI4Bhārat","uuid":"69502895","kind":"organization","description":"Artificial-Intelligence-For-Bhārat : Building open-source AI solutions for India!","email":"opensource@ai4bharat.org","website":"https://ai4bharat.org","location":"India","twitter":"AI4Bharat","company":null,"icon_url":"https://avatars.githubusercontent.com/u/69502895?v=4","repositories_count":37,"last_synced_at":"2023-03-04T23:20:46.204Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/AI4Bharat","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-15T02:28:33.246Z","updated_at":"2023-03-04T23:20:46.215Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AI4Bharat","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AI4Bharat/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"ai4bharat/deduplicate-text-datasets","html_url":"https://github.com/ai4bharat/deduplicate-text-datasets","last_synced_at":null,"status":null,"issues_count":null,"pull_requests_count":null,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":null,"issues_closed_count":null,"pull_requests_closed_count":null,"pull_request_authors_count":null,"issue_authors_count":null,"avg_comments_per_issue":null,"avg_comments_per_pull_request":null,"merged_pull_requests_count":null,"bot_issues_count":null,"bot_pull_requests_count":null,"past_year_issues_count":null,"past_year_pull_requests_count":null,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":null,"past_year_pull_requests_closed_count":null,"past_year_pull_request_authors_count":null,"past_year_issue_authors_count":null,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":null,"past_year_bot_pull_requests_count":null,"past_year_merged_pull_requests_count":null,"created_at":"2025-09-09T01:20:06.895Z","updated_at":"2025-09-09T01:20:06.895Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4bharat%2Fdeduplicate-text-datasets","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4bharat%2Fdeduplicate-text-datasets/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{},"issue_authors":{},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-09T00:00:11.778Z","repositories_count":10174310,"issues_count":31919157,"pull_requests_count":100070755,"authors_count":10734448,"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":[],"active_maintainers":[]},"events":{"total":{},"last_year":{}},"keywords":[],"dependencies":[{"ecosystem":"cargo","filepath":"Cargo.toml","sha":null,"kind":"manifest","created_at":"2023-09-15T00:51:37.338Z","updated_at":"2023-09-15T00:51:37.338Z","repository_link":"https://github.com/AI4Bharat/deduplicate-text-datasets/blob/master/Cargo.toml","dependencies":[]}],"score":null,"created_at":"2025-09-08T21:47:50.183Z","updated_at":"2025-10-07T08:30:16.289Z","avatar_url":"https://github.com/AI4Bharat.png","language":"Rust","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/94750","html_url":"https://science.ecosyste.ms/projects/94750"}