{"id":152,"name":"BenchmarkDataNLP.jl","description":"BenchmarkDataNLP.jl: Synthetic Data Generation for NLP Benchmarking - Published in JOSS (2025)","url":"https://github.com/mantzaris/benchmarkdatanlp.jl","last_synced_at":"2025-09-04T15:56:41.561Z","repository":{"id":264558775,"uuid":"893675049","full_name":"mantzaris/BenchmarkDataNLP.jl","owner":"mantzaris","description":"Generate synthetic text from a variety of methods, eg. Context Free Grammars (CFGs), with parameterized complexity to test your NLP methods (like LLMs)","archived":false,"fork":false,"pushed_at":"2025-05-27T20:53:05.000Z","size":1467,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-31T23:55:18.321Z","etag":null,"topics":["corpus-data","data-generation","data-generator","llm-training","nlp"],"latest_commit_sha":null,"homepage":"https://mantzaris.github.io/BenchmarkDataNLP.jl/","language":"Julia","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/mantzaris.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,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-11-25T02:13:18.000Z","updated_at":"2025-05-27T20:52:29.000Z","dependencies_parsed_at":"2025-01-19T05:19:59.953Z","dependency_job_id":"9368d597-98e3-4e2f-ab58-0dd7d1124dc6","html_url":"https://github.com/mantzaris/BenchmarkDataNLP.jl","commit_stats":null,"previous_names":["mantzaris/benchmarknlp.jl"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/mantzaris/BenchmarkDataNLP.jl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2FBenchmarkDataNLP.jl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2FBenchmarkDataNLP.jl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2FBenchmarkDataNLP.jl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2FBenchmarkDataNLP.jl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mantzaris","download_url":"https://codeload.github.com/mantzaris/BenchmarkDataNLP.jl/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2FBenchmarkDataNLP.jl/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273587943,"owners_count":25132849,"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":"2025-09-04T02:00:08.968Z","response_time":61,"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":"mantzaris","name":"a.v.mantzaris","uuid":"11978807","kind":"user","description":"Excited about the future of technology. Happy to participate in shaping that future through theory and practice.","email":"","website":null,"location":"USA","twitter":"avmantzaris","company":null,"icon_url":"https://avatars.githubusercontent.com/u/11978807?u=a9183039f7194fbf5eb6dfb93a69c4e1079ca725\u0026v=4","repositories_count":34,"last_synced_at":"2025-08-31T23:41:56.126Z","metadata":{"has_sponsors_listing":false},"html_url":"https://github.com/mantzaris","funding_links":[],"total_stars":54,"followers":47,"following":95,"created_at":"2022-11-20T11:23:27.331Z","updated_at":"2025-08-31T23:41:56.126Z","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mantzaris","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mantzaris/repositories"},"packages":[],"commits":{"id":8751311,"full_name":"mantzaris/benchmarkdatanlp.jl","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":"2025-02-14T04:52:04.290Z","updated_at":"2025-02-14T04:52:04.290Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2Fbenchmarkdatanlp.jl/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.936Z","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":"mantzaris/benchmarkdatanlp.jl","html_url":"https://github.com/mantzaris/benchmarkdatanlp.jl","last_synced_at":"2025-09-04T14:24:23.942Z","status":"active","issues_count":0,"pull_requests_count":2,"avg_time_to_close_issue":null,"avg_time_to_close_pull_request":33557.0,"issues_closed_count":0,"pull_requests_closed_count":2,"pull_request_authors_count":1,"issue_authors_count":0,"avg_comments_per_issue":null,"avg_comments_per_pull_request":1.0,"merged_pull_requests_count":2,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":0,"past_year_pull_requests_count":2,"past_year_avg_time_to_close_issue":null,"past_year_avg_time_to_close_pull_request":33557.0,"past_year_issues_closed_count":0,"past_year_pull_requests_closed_count":2,"past_year_pull_request_authors_count":1,"past_year_issue_authors_count":0,"past_year_avg_comments_per_issue":null,"past_year_avg_comments_per_pull_request":1.0,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":2,"created_at":"2025-02-14T04:52:04.416Z","updated_at":"2025-09-04T14:24:23.943Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2Fbenchmarkdatanlp.jl","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/mantzaris%2Fbenchmarkdatanlp.jl/issues","issue_labels_count":{},"pull_request_labels_count":{},"issue_author_associations_count":{},"pull_request_author_associations_count":{"NONE":1,"CONTRIBUTOR":1},"issue_authors":{},"pull_request_authors":{"jromanowska":2},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10080233,"issues_count":31311624,"pull_requests_count":96148338,"authors_count":10693059,"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":{"NONE":1,"CONTRIBUTOR":1},"past_year_issue_authors":{},"past_year_pull_request_authors":{"jromanowska":2},"maintainers":[],"active_maintainers":[]},"events":{"total":{"ReleaseEvent":2,"DeleteEvent":1,"IssueCommentEvent":1,"PushEvent":102,"PullRequestReviewEvent":5,"PullRequestReviewCommentEvent":5,"PullRequestEvent":2,"ForkEvent":1,"CreateEvent":5},"last_year":{"ReleaseEvent":2,"DeleteEvent":1,"IssueCommentEvent":1,"PushEvent":102,"PullRequestReviewEvent":5,"PullRequestReviewCommentEvent":5,"PullRequestEvent":2,"ForkEvent":1,"CreateEvent":5}},"keywords":["corpus-data","data-generation","data-generator","llm-training","nlp"],"dependencies":[{"ecosystem":"actions","filepath":".github/workflows/ci.yml","sha":null,"kind":"manifest","created_at":"2025-01-19T05:19:58.658Z","updated_at":"2025-01-19T05:19:58.658Z","repository_link":"https://github.com/mantzaris/BenchmarkDataNLP.jl/blob/main/.github/workflows/ci.yml","dependencies":[{"id":21528870383,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21528870384,"package_name":"julia-actions/setup-julia","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]},{"ecosystem":"actions","filepath":".github/workflows/documentation.yml","sha":null,"kind":"manifest","created_at":"2025-01-19T05:19:58.811Z","updated_at":"2025-01-19T05:19:58.811Z","repository_link":"https://github.com/mantzaris/BenchmarkDataNLP.jl/blob/main/.github/workflows/documentation.yml","dependencies":[{"id":21528870385,"package_name":"actions/checkout","ecosystem":"actions","requirements":"v4","direct":true,"kind":"composite","optional":false},{"id":21528870386,"package_name":"julia-actions/setup-julia","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false},{"id":21528870387,"package_name":"julia-actions/cache","ecosystem":"actions","requirements":"v2","direct":true,"kind":"composite","optional":false}]}],"score":null,"created_at":"2025-09-04T09:17:30.720Z","updated_at":"2025-10-07T08:04:23.310Z","avatar_url":"https://github.com/mantzaris.png","language":"Julia","category":"Scientific Software","sub_category":"Peer-reviewed","monthly_downloads":0,"funding_links":[],"readme_doi_urls":["https://doi.org/10.21105/joss.07844"],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/152","html_url":"https://science.ecosyste.ms/projects/152"}