{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005864525,0.00009119753,0.0001485527,0.00004922882,0.0001362506,0.0001040065,0.0002941529,0.00005268059,0.000007841762],"category_scores_gemma":[0.0001484966,0.00007522811,0.000045304,0.0002333276,0.00003538158,0.000199783,0.0001211756,0.00006185974,0.000001779114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005585073,"about_ca_system_score_gemma":0.0001138026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002366873,"about_ca_topic_score_gemma":0.0001302886,"domain_scores_codex":[0.9990401,0.00004789515,0.0002042211,0.0004150751,0.00009603196,0.0001966379],"domain_scores_gemma":[0.9989068,0.0003223846,0.0000412477,0.0005765974,0.0001060536,0.00004694558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001374139,0.0001643809,0.01209377,0.00007566,0.00001189469,2.485772e-7,0.0001362897,0.000003905719,0.001514704,0.9228749,0.001432969,0.06167749],"study_design_scores_gemma":[0.001271594,0.0001849032,0.4903527,0.00002584107,0.00001577805,0.000002947542,0.00007787159,0.220521,0.003718554,0.2429223,0.04060393,0.0003024727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06373496,0.00003465624,0.9262139,0.006299613,0.0001331728,0.00049503,0.000009349363,0.0001586625,0.002920675],"genre_scores_gemma":[0.9350843,0.000003552311,0.06304772,0.0004742536,0.00001039068,0.000111596,0.000009251037,0.000002132544,0.001256778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8713494,"threshold_uncertainty_score":0.3067713,"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."}}