{"id":"W4416037532","doi":"10.18653/v1/2025.emnlp-demos.74","title":"BAREC Demo: Resources and Tools for Sentence-level Arabic 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":"","funders":"York University; New York University Abu Dhabi","keywords":"Readability; Arabic; Legibility; Feature (linguistics)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002435775,0.0004020367,0.000550609,0.0001775067,0.0007683399,0.002057557,0.001070933,0.000281584,0.00005913084],"category_scores_gemma":[0.001122083,0.000361846,0.0002048367,0.000732117,0.0004572273,0.001864887,0.0006171297,0.0003117317,0.000008402083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004083524,"about_ca_system_score_gemma":0.0008313928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003439889,"about_ca_topic_score_gemma":0.0002879949,"domain_scores_codex":[0.9958968,0.0003587827,0.00100414,0.001652683,0.0004410538,0.000646574],"domain_scores_gemma":[0.9947723,0.002542041,0.000207446,0.001676042,0.0005754763,0.0002266875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006520945,0.0003097576,0.008627689,0.0004746165,0.00006937701,8.100457e-7,0.0009182074,0.00004660411,0.000755567,0.1327431,0.0012155,0.8547735],"study_design_scores_gemma":[0.000898426,0.0004468232,0.5882961,0.0002610939,0.000126731,0.00001098053,0.002068055,0.2886467,0.003330764,0.06628842,0.04883429,0.0007916318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1706051,0.0003228734,0.8050925,0.01356819,0.000573543,0.001715834,0.00005841829,0.0001338759,0.007929707],"genre_scores_gemma":[0.902447,0.00008731917,0.09249795,0.0008768298,0.00006453785,0.0001928592,0.00001286533,0.000009235851,0.003811379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8539819,"threshold_uncertainty_score":0.9998834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07263354252581768,"score_gpt":0.331101482548212,"score_spread":0.2584679400223943,"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."}}