{"id":13769387,"url":"https://github.com/ckorzen/pdf-text-extraction-benchmark","last_synced_at":"2025-05-11T02:32:15.651Z","repository":{"id":56439348,"uuid":"48033951","full_name":"ckorzen/pdf-text-extraction-benchmark","owner":"ckorzen","description":"A project about benchmarking and evaluating existing PDF extraction tools on their semantic abilities to extract the body texts from PDF documents, especially from scientific articles.","archived":false,"fork":false,"pushed_at":"2020-11-07T16:13:35.000Z","size":529557,"stargazers_count":63,"open_issues_count":2,"forks_count":11,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-08-03T17:08:13.531Z","etag":null,"topics":["arxiv","benchmark","evaluation","extraction","pdf","tex","text-extraction"],"latest_commit_sha":null,"homepage":"","language":"TeX","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/ckorzen.png","metadata":{},"created_at":"2015-12-15T09:48:20.000Z","updated_at":"2024-06-13T14:27:31.000Z","dependencies_parsed_at":"2022-08-15T18:41:01.569Z","dependency_job_id":null,"html_url":"https://github.com/ckorzen/pdf-text-extraction-benchmark","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ckorzen%2Fpdf-text-extraction-benchmark","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ckorzen%2Fpdf-text-extraction-benchmark/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ckorzen%2Fpdf-text-extraction-benchmark/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ckorzen%2Fpdf-text-extraction-benchmark/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ckorzen","download_url":"https://codeload.github.com/ckorzen/pdf-text-extraction-benchmark/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225004575,"owners_count":17405644,"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","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":["arxiv","benchmark","evaluation","extraction","pdf","tex","text-extraction"],"created_at":"2024-08-03T17:00:23.494Z","updated_at":"2024-11-17T05:30:49.343Z","avatar_url":"https://github.com/ckorzen.png","language":"TeX","funding_links":[],"categories":["TeX","Resources"],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fckorzen%2Fpdf-text-extraction-benchmark","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fckorzen%2Fpdf-text-extraction-benchmark","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fckorzen%2Fpdf-text-extraction-benchmark/lists"}