{"id":178355,"name":null,"description":"An awesome list of data deduplication use cases, papers, tools, and methods.","url":"https://github.com/chenghaomou/awesome-data-deduplication","last_synced_at":"2025-09-10T00:03:27.573Z","repository":{"id":233406445,"uuid":"696460629","full_name":"ChenghaoMou/awesome-data-deduplication","owner":"ChenghaoMou","description":"An awesome list of data deduplication use cases, papers, tools, and methods.","archived":false,"fork":false,"pushed_at":"2024-05-11T07:49:58.000Z","size":7,"stargazers_count":4,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-29T04:26:49.118Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ChenghaoMou.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}},"created_at":"2023-09-25T19:37:39.000Z","updated_at":"2024-10-17T08:20:14.000Z","dependencies_parsed_at":"2024-04-16T04:11:16.144Z","dependency_job_id":"e50d77a9-2c59-4219-ad26-97c110ad2a46","html_url":"https://github.com/ChenghaoMou/awesome-data-deduplication","commit_stats":null,"previous_names":["chenghaomou/awesome-data-deduplication"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ChenghaoMou/awesome-data-deduplication","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenghaoMou","download_url":"https://codeload.github.com/ChenghaoMou/awesome-data-deduplication/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274388855,"owners_count":25276207,"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":"ChenghaoMou","name":"Chenghao Mou","uuid":"32014649","kind":"user","description":"NLP/AI\r\n","email":"","website":"https://sleeplessindebugging.blog/","location":"Ireland","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/32014649?u=bf7b28ce77de4c43a90023474dd208c971e8a872\u0026v=4","repositories_count":32,"last_synced_at":"2025-09-04T22:57:35.666Z","metadata":{"has_sponsors_listing":true},"html_url":"https://github.com/ChenghaoMou","funding_links":["https://github.com/sponsors/ChenghaoMou"],"total_stars":623,"followers":130,"following":254,"created_at":"2022-11-14T19:51:49.742Z","updated_at":"2025-09-04T22:57:35.666Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenghaoMou","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenghaoMou/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"ChenghaoMou/awesome-data-deduplication","html_url":"https://github.com/ChenghaoMou/awesome-data-deduplication","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":"2025-09-01T12:21:23.804Z","updated_at":"2025-09-01T14:05:10.460Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenghaoMou%2Fawesome-data-deduplication/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":1},"pull_request_author_associations_count":{},"issue_authors":{"longxudou":1},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-10T00:00:25.260Z","repositories_count":10198088,"issues_count":32233623,"pull_requests_count":101763769,"authors_count":10741856,"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":{"WatchEvent":1},"last_year":{"WatchEvent":1}},"keywords":[],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2024-04-16T04:11:16.033Z","updated_at":"2024-04-16T04:11:16.033Z","repository_link":"https://github.com/ChenghaoMou/awesome-data-deduplication/blob/main/requirements.txt","dependencies":[{"id":17435166982,"package_name":"pandas","ecosystem":"pypi","requirements":"==2.0.3","direct":true,"kind":"runtime","optional":false},{"id":17435166983,"package_name":"tabulate","ecosystem":"pypi","requirements":"==0.9.0","direct":true,"kind":"runtime","optional":false},{"id":17435166984,"package_name":"pre-commit","ecosystem":"pypi","requirements":"==2.21.0","direct":true,"kind":"runtime","optional":false}]}],"score":null,"created_at":"2025-09-09T01:50:01.693Z","updated_at":"2025-10-07T08:40:54.432Z","avatar_url":"https://github.com/ChenghaoMou.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/178355","html_url":"https://science.ecosyste.ms/projects/178355"}