{"id":34582342,"url":"https://github.com/experimaestro/datamaestro_text","last_synced_at":"2026-02-02T19:04:04.207Z","repository":{"id":62566667,"uuid":"157071240","full_name":"experimaestro/datamaestro_text","owner":"experimaestro","description":"Plugin for the dataset module containing information access related datasets","archived":false,"fork":false,"pushed_at":"2026-01-28T10:47:36.000Z","size":1098,"stargazers_count":5,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2026-01-29T01:04:13.906Z","etag":null,"topics":["dataset","dataset-catalog","dataset-manager"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/experimaestro.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2018-11-11T11:04:35.000Z","updated_at":"2026-01-28T10:47:41.000Z","dependencies_parsed_at":"2025-12-19T01:08:15.667Z","dependency_job_id":null,"html_url":"https://github.com/experimaestro/datamaestro_text","commit_stats":{"total_commits":190,"total_committers":3,"mean_commits":"63.333333333333336","dds":0.08421052631578951,"last_synced_commit":"5464e71ed06f62785b18cfefd3445adf5a80baff"},"previous_names":[],"tags_count":84,"template":false,"template_full_name":null,"purl":"pkg:github/experimaestro/datamaestro_text","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/experimaestro%2Fdatamaestro_text","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/experimaestro%2Fdatamaestro_text/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/experimaestro%2Fdatamaestro_text/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/experimaestro%2Fdatamaestro_text/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/experimaestro","download_url":"https://codeload.github.com/experimaestro/datamaestro_text/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/experimaestro%2Fdatamaestro_text/sbom","scorecard":{"id":388219,"data":{"date":"2025-08-11","repo":{"name":"github.com/experimaestro/datamaestro_text","commit":"3d751330240ffeb0d9100c89860a488f93633d70"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":4.5,"checks":[{"name":"Dangerous-Workflow","score":10,"reason":"no dangerous workflow patterns detected","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"Maintained","score":10,"reason":"28 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Code-Review","score":1,"reason":"Found 3/25 approved changesets -- score normalized to 1","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"Token-Permissions","score":0,"reason":"detected GitHub workflow tokens with excessive permissions","details":["Warn: no topLevel permission defined: .github/workflows/pytest.yml:1","Warn: no topLevel permission defined: .github/workflows/python-publish.yml:1","Info: no jobLevel write permissions found"],"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"Pinned-Dependencies","score":0,"reason":"dependency not pinned by hash detected -- score normalized to 0","details":["Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/pytest.yml:21: update your workflow using https://app.stepsecurity.io/secureworkflow/experimaestro/datamaestro_text/pytest.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/pytest.yml:23: update your workflow using https://app.stepsecurity.io/secureworkflow/experimaestro/datamaestro_text/pytest.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/python-publish.yml:15: update your workflow using https://app.stepsecurity.io/secureworkflow/experimaestro/datamaestro_text/python-publish.yml/master?enable=pin","Warn: GitHub-owned GitHubAction not pinned by hash: .github/workflows/python-publish.yml:17: update your workflow using https://app.stepsecurity.io/secureworkflow/experimaestro/datamaestro_text/python-publish.yml/master?enable=pin","Warn: pipCommand not pinned by hash: .github/workflows/pytest.yml:28","Warn: pipCommand not pinned by hash: .github/workflows/pytest.yml:29","Warn: pipCommand not pinned by hash: .github/workflows/python-publish.yml:22","Warn: pipCommand not pinned by hash: .github/workflows/python-publish.yml:23","Info:   0 out of   4 GitHub-owned GitHubAction dependencies pinned","Info:   0 out of   4 pipCommand dependencies pinned"],"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Vulnerabilities","score":10,"reason":"0 existing vulnerabilities detected","details":null,"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE:0","Info: FSF or OSI recognized license: GNU General Public License v3.0: LICENSE:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Signed-Releases","score":-1,"reason":"no releases found","details":null,"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Branch-Protection","score":0,"reason":"branch protection not enabled on development/release branches","details":["Warn: branch protection not enabled for branch 'master'"],"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"SAST","score":0,"reason":"SAST tool is not run on all commits -- score normalized to 0","details":["Warn: 0 commits out of 8 are checked with a SAST tool"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}}]},"last_synced_at":"2025-08-18T17:10:42.844Z","repository_id":62566667,"created_at":"2025-08-18T17:10:42.844Z","updated_at":"2025-08-18T17:10:42.844Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29017940,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-02T18:51:31.335Z","status":"ssl_error","status_checked_at":"2026-02-02T18:49:20.777Z","response_time":58,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["dataset","dataset-catalog","dataset-manager"],"created_at":"2025-12-24T10:18:53.864Z","updated_at":"2026-02-02T19:04:04.184Z","avatar_url":"https://github.com/experimaestro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":" [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit\u0026logoColor=white)](https://github.com/pre-commit/pre-commit) [![PyPI version](https://badge.fury.io/py/datamaestro-text.svg)](https://badge.fury.io/py/datamaestro-text)\n\n# Text-related datasets\n\nThis [datamaestro](https://github.com/bpiwowar/datasets) plugin covers text-related datasets:\n\n- Information Retrieval\n- Natural Language Processing tasks\n\nThe list of available datasets and usage instruction can be found in the [documentation](https://datamaestro-text.readthedocs.io/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexperimaestro%2Fdatamaestro_text","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fexperimaestro%2Fdatamaestro_text","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexperimaestro%2Fdatamaestro_text/lists"}