{"id":"W7106288743","doi":"10.36227/techrxiv.176369738.87142789/v1","title":"ContextMentalQA: Modeling Cultural, Social, and Religious Context in Arabic Mental Health Question Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Mental health; Context (archaeology); Distress; Arabic; Question answering; Mental distress","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":[0.002534054,0.001225891,0.0004625672,0.001654009,0.001080302,0.001719362,0.001487401,0.001547232,0.004021768],"category_scores_gemma":[0.008336054,0.0003094436,0.00107529,0.001032599,0.0006507309,0.002424813,0.002623338,0.002168048,0.002066234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001843278,"about_ca_system_score_gemma":0.001508211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02115451,"about_ca_topic_score_gemma":0.03474831,"domain_scores_codex":[0.9983799,0.0007862809,0.0001113735,0.0004937149,0.0001394362,0.00008915038],"domain_scores_gemma":[0.9969255,0.001977017,0.0001446937,0.0003511246,0.0004685366,0.0001331042],"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":[0.001628037,0.001191902,0.06243121,0.002215472,0.0003128339,0.0009100303,0.01068903,0.1045659,0.03054905,0.02380227,0.1211348,0.6405695],"study_design_scores_gemma":[0.0001219593,0.0002278539,0.02180456,0.0002376517,0.0001146429,0.000438641,0.003489238,0.8556387,0.0132601,0.02658179,0.07798169,0.0001032664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3919994,0.004023755,0.503812,0.006888457,0.0008793439,0.002543343,0.05669206,0.01982385,0.0133377],"genre_scores_gemma":[0.5852305,0.0006433456,0.3273819,0.001244868,0.0002279944,0.001922534,0.0768905,0.0004101246,0.006048341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02115451,"threshold_uncertainty_score":0.04206276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03632445534299684,"score_gpt":0.3288648955707391,"score_spread":0.2925404402277423,"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."}}