{"id":16736513,"url":"https://github.com/neizod/duppub","last_synced_at":"2026-01-24T16:43:31.437Z","repository":{"id":141853914,"uuid":"188539711","full_name":"neizod/duppub","owner":"neizod","description":"Detects duplicate publications","archived":false,"fork":false,"pushed_at":"2022-06-21T23:08:56.000Z","size":16,"stargazers_count":0,"open_issues_count":2,"forks_count":4,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-06T12:34:22.765Z","etag":null,"topics":["csv","hacktoberfest","python","string-matching","string-similarity"],"latest_commit_sha":null,"homepage":"","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/neizod.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2019-05-25T08:18:29.000Z","updated_at":"2021-10-21T17:07:49.000Z","dependencies_parsed_at":null,"dependency_job_id":"6be9804f-6a48-4d52-8769-3bba9b0533e1","html_url":"https://github.com/neizod/duppub","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/neizod/duppub","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neizod%2Fduppub","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neizod%2Fduppub/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neizod%2Fduppub/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neizod%2Fduppub/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/neizod","download_url":"https://codeload.github.com/neizod/duppub/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/neizod%2Fduppub/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28731767,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-24T10:24:43.181Z","status":"ssl_error","status_checked_at":"2026-01-24T10:24:36.112Z","response_time":89,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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"}},"keywords":["csv","hacktoberfest","python","string-matching","string-similarity"],"created_at":"2024-10-13T00:22:41.548Z","updated_at":"2026-01-24T16:43:31.433Z","avatar_url":"https://github.com/neizod.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"DupPub (Duplicate Publication)\n==============================\n\nDetect duplicate or similar publications from database. This project aim to reduce size of the database by showing pairs of suspect duplications, to help citation easier and cleaner.\n\n\nUsage\n-----\n\nExport database as CSV file without header, with these fields:\n\n1. ID\n2. Authors\n3. Title of the article\n4. Year\n5. Abstract\n\nFor example, if your exported CSV named `publications.csv`, then run it with:\n\n    python3 report.py publications.csv\n\n\nExample Result\n--------------\n\nFrom `example_input.csv`, this is the result:\n\n    |  score  |          id-1          |          id-2          |\n    |---------|------------------------|------------------------|\n    | 100.00% | cross-publisher-2      | cross-publisher-3      |\n    | 100.00% | cross-publisher-1      | cross-publisher-3      |\n    | 100.00% | cross-publisher-1      | cross-publisher-2      |\n    | 100.00% | arXiv-v3               | arXiv-v4               |\n    | 100.00% | arXiv-v1               | arXiv-v2               |\n    |  80.00% | arXiv-v2               | arXiv-v4               |\n    |  80.00% | arXiv-v2               | arXiv-v3               |\n    |  80.00% | arXiv-v1               | arXiv-v4               |\n    |  80.00% | arXiv-v1               | arXiv-v3               |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneizod%2Fduppub","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fneizod%2Fduppub","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fneizod%2Fduppub/lists"}