{"id":60302,"name":"parallel-urls-classifier","description":"Parallel URLs Classifier (PUC) infers the parallelness of a pair of documents from their URLs","url":"https://github.com/transducens/parallel-urls-classifier","last_synced_at":"2025-09-05T15:50:02.912Z","repository":{"id":264916747,"uuid":"465312652","full_name":"transducens/parallel-urls-classifier","owner":"transducens","description":"Parallel URLs Classifier (PUC) infers the parallelness of a pair of documents from their URLs","archived":false,"fork":false,"pushed_at":"2024-03-18T18:03:05.000Z","size":710,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-08-27T06:43:39.658Z","etag":null,"topics":["crawling","document-aligner","url"],"latest_commit_sha":null,"homepage":"https://huggingface.co/Transducens/xlm-roberta-base-parallel-urls-classifier","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/transducens.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":"2022-03-02T13:15:20.000Z","updated_at":"2024-05-24T09:06:35.000Z","dependencies_parsed_at":"2024-11-27T00:03:03.227Z","dependency_job_id":null,"html_url":"https://github.com/transducens/parallel-urls-classifier","commit_stats":null,"previous_names":["transducens/parallel-urls-classifier"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/transducens/parallel-urls-classifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/transducens","download_url":"https://codeload.github.com/transducens/parallel-urls-classifier/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273781185,"owners_count":25167123,"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":"transducens","name":"Transducens","uuid":"12795384","kind":"organization","description":"","email":"info.transducens@dlsi.ua.es","website":"http://transducens.dlsi.ua.es/","location":"Departament de Llenguatges i Sistemes Informàtics Universitat d’Alacant 03690 Sant Vicent del Raspeig, Spain","twitter":null,"company":null,"icon_url":"https://avatars.githubusercontent.com/u/12795384?v=4","repositories_count":26,"last_synced_at":"2023-08-10T03:11:29.846Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/transducens","funding_links":[],"total_stars":null,"followers":null,"following":null,"created_at":"2022-11-06T22:53:30.249Z","updated_at":"2023-08-10T03:11:34.493Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/transducens","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/transducens/repositories"},"packages":[],"commits":{"message":"Repository syncing started."},"issues_stats":{"full_name":"transducens/parallel-urls-classifier","html_url":"https://github.com/transducens/parallel-urls-classifier","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":"2025-09-05T15:49:29.635Z","updated_at":"2025-09-05T15:49:29.635Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/transducens%2Fparallel-urls-classifier/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":{},"last_year":{}},"keywords":["crawling","document-aligner","url"],"dependencies":[{"ecosystem":"pypi","filepath":"requirements.txt","sha":null,"kind":"manifest","created_at":"2024-11-26T19:42:39.929Z","updated_at":"2024-11-26T19:42:39.929Z","repository_link":"https://github.com/transducens/parallel-urls-classifier/blob/master/requirements.txt","dependencies":[{"id":20914389445,"package_name":"numpy","ecosystem":"pypi","requirements":"==1.22.1","direct":true,"kind":"runtime","optional":false},{"id":20914389446,"package_name":"torch","ecosystem":"pypi","requirements":"==1.12.1","direct":true,"kind":"runtime","optional":false},{"id":20914389447,"package_name":"transformers","ecosystem":"pypi","requirements":"==4.15.0","direct":true,"kind":"runtime","optional":false},{"id":20914389448,"package_name":"matplotlib","ecosystem":"pypi","requirements":"==3.5.1","direct":true,"kind":"runtime","optional":false},{"id":20914389449,"package_name":"html5lib","ecosystem":"pypi","requirements":"==1.1","direct":true,"kind":"runtime","optional":false},{"id":20914389450,"package_name":"beautifulsoup4","ecosystem":"pypi","requirements":"==4.10.0","direct":true,"kind":"runtime","optional":false},{"id":20914389451,"package_name":"Flask","ecosystem":"pypi","requirements":"==2.2.2","direct":true,"kind":"runtime","optional":false},{"id":20914389452,"package_name":"psutil","ecosystem":"pypi","requirements":"==5.9.0","direct":true,"kind":"runtime","optional":false},{"id":20914389453,"package_name":"nltk","ecosystem":"pypi","requirements":"==3.7","direct":true,"kind":"runtime","optional":false},{"id":20914389454,"package_name":"Levenshtein","ecosystem":"pypi","requirements":"==0.20.6","direct":true,"kind":"runtime","optional":false},{"id":20914389455,"package_name":"more-itertools","ecosystem":"pypi","requirements":"==9.0.0","direct":true,"kind":"runtime","optional":false},{"id":20914389456,"package_name":"tldextract","ecosystem":"pypi","requirements":"==3.4.0","direct":true,"kind":"runtime","optional":false},{"id":20914389457,"package_name":"scikit-learn","ecosystem":"pypi","requirements":"==1.1.3","direct":true,"kind":"runtime","optional":false},{"id":20914389458,"package_name":"imbalanced-learn","ecosystem":"pypi","requirements":"==0.9.1","direct":true,"kind":"runtime","optional":false},{"id":20914389459,"package_name":"joblib","ecosystem":"pypi","requirements":"==1.2.0","direct":true,"kind":"runtime","optional":false},{"id":20914389460,"package_name":"requests","ecosystem":"pypi","requirements":"==2.28.2","direct":true,"kind":"runtime","optional":false},{"id":20914389461,"package_name":"gunicorn","ecosystem":"pypi","requirements":"==20.1.0","direct":true,"kind":"runtime","optional":false}]},{"ecosystem":"pypi","filepath":"setup.py","sha":null,"kind":"manifest","created_at":"2024-11-26T19:42:39.991Z","updated_at":"2024-11-26T19:42:39.991Z","repository_link":"https://github.com/transducens/parallel-urls-classifier/blob/master/setup.py","dependencies":[]}],"score":null,"created_at":"2025-09-04T15:51:37.106Z","updated_at":"2025-10-07T08:23:41.007Z","avatar_url":"https://github.com/transducens.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/60302","html_url":"https://science.ecosyste.ms/projects/60302","bibtex_url":"https://science.ecosyste.ms/projects/60302/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/60302/export.apalike"}