{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008033651,0.0004193969,0.0006415209,0.0003081472,0.0006779908,0.0005692256,0.0004778688,0.0001861436,0.000007414734],"category_scores_gemma":[0.00002651546,0.0004263532,0.000102891,0.000526027,0.0001235336,0.001053446,0.0005565439,0.0004362771,0.00000906996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008987231,"about_ca_system_score_gemma":0.0003262465,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006652229,"about_ca_topic_score_gemma":0.001540829,"domain_scores_codex":[0.9963972,0.0002772761,0.001127553,0.001109912,0.0003283552,0.0007597102],"domain_scores_gemma":[0.9991295,0.00004458788,0.0001931814,0.0003690952,0.000105461,0.0001582171],"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":[0.00007970928,0.0003596343,0.003603587,0.0004043507,0.0001125606,0.00001967544,0.05562869,0.008405806,0.0007555585,0.1982983,0.002118299,0.7302138],"study_design_scores_gemma":[0.001718938,0.00009620985,0.0003624744,0.0007925266,0.000008299866,0.00001670903,0.006635106,0.9874228,0.00006907759,0.002067539,0.0004384539,0.000371901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4533719,0.02882148,0.485545,0.02700112,0.00144713,0.001169449,0.000006315114,0.0001950521,0.00244258],"genre_scores_gemma":[0.986573,0.004366121,0.004798804,0.00368573,0.00006951836,0.00002608872,0.000006368167,0.00001465182,0.0004596624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.979017,"threshold_uncertainty_score":0.9999626,"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."}}