{"id":"W4416037651","doi":"10.18653/v1/2025.arabicnlp-sharedtasks.46","title":"Noor at BAREC Shared Task 2025: A Hybrid Transformer-Feature Architecture for Sentence-level Readability Assessment","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Readability; Task (project management); Architecture; Task analysis","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002630937,0.002152006,0.001088028,0.001553955,0.0006824245,0.001699252,0.002225986,0.00169295,0.01249761],"category_scores_gemma":[0.008405987,0.0004656816,0.001225452,0.0006833399,0.0003756799,0.003072469,0.00268645,0.002021662,0.01145272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077509,"about_ca_system_score_gemma":0.001226027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01214049,"about_ca_topic_score_gemma":0.0192966,"domain_scores_codex":[0.998278,0.0004856908,0.00009361439,0.000634952,0.0003385964,0.0001691011],"domain_scores_gemma":[0.9969989,0.0007507315,0.0001271733,0.0007250129,0.001126059,0.0002722573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002351362,0.001405153,0.01302755,0.001112212,0.000494597,0.0004118856,0.0008958549,0.01889699,0.04763667,0.001693479,0.1569692,0.755105],"study_design_scores_gemma":[0.0007533774,0.003940946,0.05837953,0.0004101495,0.0006637411,0.0009174695,0.001197239,0.6961703,0.1160842,0.0149156,0.1060455,0.0005218916],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.504485,0.003565814,0.2280293,0.001363718,0.001780358,0.002556422,0.07552756,0.1456195,0.03707237],"genre_scores_gemma":[0.711646,0.0003534608,0.1195051,0.0006094865,0.0001840904,0.001758195,0.1359921,0.003164379,0.02678729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01249761,"threshold_uncertainty_score":0.04180866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03207726001327568,"score_gpt":0.3037281443476246,"score_spread":0.271650884334349,"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."}}