{"id":"W7118177928","doi":"10.1109/aiccsa66935.2025.11315347","title":"Evaluating Arabic Language Embedding Models for Semantic Retrieval in Fatwas","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Generative grammar; Sentence; Embedding; Natural language; Universal Networking Language; Context (archaeology); Transformer; Language model","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":[0.003272441,0.0008140834,0.0004420185,0.001100533,0.0003347525,0.001525181,0.000756248,0.0008098303,0.0026018],"category_scores_gemma":[0.0104871,0.0002067106,0.0005757073,0.0006192632,0.0004229235,0.002354922,0.0009301264,0.0009375482,0.001218664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008305138,"about_ca_system_score_gemma":0.0007955374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004555897,"about_ca_topic_score_gemma":0.00419851,"domain_scores_codex":[0.9987192,0.0008693691,0.00006943531,0.000173938,0.0001214328,0.00004659728],"domain_scores_gemma":[0.9921774,0.006513028,0.0001803428,0.0004730538,0.0005418341,0.0001143668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002330179,0.001251063,0.01582518,0.0009172321,0.0004462408,0.0003710387,0.002811408,0.47049,0.01614585,0.01147804,0.005485959,0.4724478],"study_design_scores_gemma":[0.0000483111,0.0002542506,0.001523014,0.00002045254,0.00007301956,0.00005865328,0.0004133389,0.9875413,0.006318105,0.002440086,0.001288117,0.00002151604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9044237,0.0006800211,0.08276682,0.0005127125,0.00008337138,0.0003197563,0.0007805423,0.003542562,0.006890457],"genre_scores_gemma":[0.9602457,0.0002081712,0.03563233,0.00005787557,0.00002409892,0.0001111122,0.001903529,0.0001230424,0.00169404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004555897,"threshold_uncertainty_score":0.01730657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07815616242647719,"score_gpt":0.3935413530976968,"score_spread":0.3153851906712196,"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."}}