{"id":41847686,"url":"https://github.com/camel-lab/camelprop","last_synced_at":"2026-01-25T10:04:37.649Z","repository":{"id":299782907,"uuid":"1001397527","full_name":"CAMeL-Lab/CamelProp","owner":"CAMeL-Lab","description":"A dataset with Arabic words, English glosses, sourced from Wikimedia and annotated with maximal diacritization  Resources","archived":false,"fork":false,"pushed_at":"2025-08-14T16:22:55.000Z","size":75,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-09T22:06:14.627Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CAMeL-Lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-06-13T10:03:08.000Z","updated_at":"2025-08-14T16:22:59.000Z","dependencies_parsed_at":"2025-08-14T18:11:43.200Z","dependency_job_id":null,"html_url":"https://github.com/CAMeL-Lab/CamelProp","commit_stats":null,"previous_names":["camel-lab/camelprop"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CAMeL-Lab/CamelProp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CAMeL-Lab%2FCamelProp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CAMeL-Lab%2FCamelProp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CAMeL-Lab%2FCamelProp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CAMeL-Lab%2FCamelProp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CAMeL-Lab","download_url":"https://codeload.github.com/CAMeL-Lab/CamelProp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CAMeL-Lab%2FCamelProp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28751103,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-25T09:58:17.166Z","status":"ssl_error","status_checked_at":"2026-01-25T09:55:56.104Z","response_time":113,"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":[],"created_at":"2026-01-25T10:04:37.577Z","updated_at":"2026-01-25T10:04:37.627Z","avatar_url":"https://github.com/CAMeL-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CamelProp\nThis repository contains CP-WIKI-D3K, a dataset of 3,362 Arabic proper nouns from Wikipedia, each annotated with gold-standard lemma diacritizations and aligned with their English equivalents.\nIt includes:\n\n1. The full dataset\n2. The postprocessing pipeline used to convert ChatGPT-4o outputs into final annotations, as described in [^1]\n3.  Markdown tables listing the examples used for few-shot and one-shot prompting\n\n[^1]: Proper Name Diacritization for Arabic Wikipedia: A Benchmark Dataset\nRawan Bondok, Mayar Nassar, Salam Khalifa, Kurt Micallef, Nizar Habash (2025)\narXiv:2505.02656\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcamel-lab%2Fcamelprop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcamel-lab%2Fcamelprop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcamel-lab%2Fcamelprop/lists"}