{"id":60116,"name":"semantic-outlier-removal","description":"Code and data for SORE (ACL 2025), a semantic boilerplate remover.","url":"https://github.com/meakbiyik/semantic-outlier-removal","last_synced_at":"2025-09-05T15:47:05.290Z","repository":{"id":307179954,"uuid":"1028619973","full_name":"meakbiyik/semantic-outlier-removal","owner":"meakbiyik","description":"Code and data for SORE (ACL 2025), a semantic boilerplate remover.","archived":false,"fork":false,"pushed_at":"2025-07-29T20:09:58.000Z","size":13,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-21T02:22:22.910Z","etag":null,"topics":["article-extractor","crawler","embedding","html-to-text","html2text","llm","nlp","outlier-removal","preprocessing","readability","scraping","text-extraction","text-mining","web-scraping"],"latest_commit_sha":null,"homepage":"https://meakbiyik.com/sore","language":null,"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/meakbiyik.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-29T19:59:31.000Z","updated_at":"2025-07-29T20:10:02.000Z","dependencies_parsed_at":"2025-07-29T23:04:09.107Z","dependency_job_id":null,"html_url":"https://github.com/meakbiyik/semantic-outlier-removal","commit_stats":null,"previous_names":["meakbiyik/semantic-outlier-removal"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/meakbiyik/semantic-outlier-removal","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/meakbiyik","download_url":"https://codeload.github.com/meakbiyik/semantic-outlier-removal/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273780937,"owners_count":25167122,"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":"2025-09-05T02:00:09.113Z","response_time":402,"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":"meakbiyik","name":"M. Eren Akbiyik","uuid":"23424198","kind":"user","description":"Data Science MSc at ETH Zurich","email":"","website":null,"location":null,"twitter":null,"company":"ETH Zurich","icon_url":"https://avatars.githubusercontent.com/u/23424198?u=89d29576f5263f3eea5b765cd7b7e6442c10c3a6\u0026v=4","repositories_count":10,"last_synced_at":"2023-08-01T07:32:32.547Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/meakbiyik","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2023-02-21T13:42:31.977Z","updated_at":"2023-08-01T07:32:32.576Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/meakbiyik","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/meakbiyik/repositories"},"packages":[],"commits":{"id":10805409,"full_name":"meakbiyik/semantic-outlier-removal","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":"2025-08-21T02:11:03.478Z","updated_at":"2025-08-21T02:11:03.478Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-05T00:00:10.343Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"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":"meakbiyik/semantic-outlier-removal","html_url":"https://github.com/meakbiyik/semantic-outlier-removal","last_synced_at":"2025-08-21T02:11:52.174Z","status":"error","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":"2025-08-21T02:11:03.738Z","updated_at":"2025-08-21T02:11:52.174Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/meakbiyik%2Fsemantic-outlier-removal/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":"2025-09-05T00:00:10.444Z","repositories_count":10103717,"issues_count":31516646,"pull_requests_count":97722052,"authors_count":10703692,"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":{"PushEvent":3,"CreateEvent":1},"last_year":{"PushEvent":3,"CreateEvent":1}},"keywords":["article-extractor","crawler","embedding","html-to-text","html2text","llm","nlp","outlier-removal","preprocessing","readability","scraping","text-extraction","text-mining","web-scraping"],"dependencies":[],"score":null,"created_at":"2025-09-04T15:51:36.870Z","updated_at":"2025-10-07T08:23:36.869Z","avatar_url":"https://github.com/meakbiyik.png","language":null,"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/60116","html_url":"https://science.ecosyste.ms/projects/60116","bibtex_url":"https://science.ecosyste.ms/projects/60116/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/60116/export.apalike"}