{"id":"W4412888009","doi":"10.18653/v1/2025.findings-acl.842","title":"A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment","year":2025,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Zayed University; York University; New York University Abu Dhabi","keywords":"Readability; Computer science; Arabic; Natural language processing; Artificial intelligence; Linguistics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003012356,0.001697807,0.0008334244,0.00620155,0.001676666,0.001931911,0.001126521,0.001084213,0.01646578],"category_scores_gemma":[0.01890058,0.0002845242,0.0005019736,0.003075988,0.0008678442,0.002421297,0.003427708,0.001477531,0.01033995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008511559,"about_ca_system_score_gemma":0.00135195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003278109,"about_ca_topic_score_gemma":0.004898556,"domain_scores_codex":[0.9958461,0.001498941,0.0005790103,0.0008906564,0.00101875,0.0001664976],"domain_scores_gemma":[0.9821508,0.005571486,0.0009421954,0.002248474,0.008292869,0.0007941469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001364141,0.0007986341,0.02372586,0.00557125,0.0001998134,0.001579369,0.0076092,0.004835567,0.07184,0.004899821,0.2680904,0.609486],"study_design_scores_gemma":[0.0005102232,0.001082526,0.1980383,0.0017886,0.0003346814,0.003696784,0.01053007,0.04401047,0.08776163,0.01051213,0.6411248,0.0006097713],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.4916981,0.005911742,0.1735726,0.002162712,0.002200969,0.004797754,0.2235878,0.02328113,0.07278722],"genre_scores_gemma":[0.4177875,0.0009797564,0.1905833,0.000654578,0.0005523766,0.00687612,0.3629083,0.002930603,0.01672753],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01646578,"threshold_uncertainty_score":0.05508351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01269413613571176,"score_gpt":0.3010816904852457,"score_spread":0.288387554349534,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}