{"id":"W4210461484","doi":"10.1109/icmla52953.2021.00237","title":"Explainable Zero-Shot Modelling of Clinical Depression Symptoms from Text","year":2021,"lang":"en","type":"article","venue":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","topic":"Mental Health via Writing","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Sketch; Computer science; Task (project management); Artificial intelligence; Focus (optics); Machine learning; Process (computing); Ground truth; Zero (linguistics); Natural language processing; Algorithm; Programming language","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004727227,0.0001849881,0.0003340116,0.000105057,0.0002269938,0.00006432691,0.0002578841,0.0001627809,0.002680519],"category_scores_gemma":[0.00007841404,0.0001913137,0.00009157068,0.0001624993,0.00008557596,0.00009857319,0.0000970785,0.0007238538,0.0001874686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003460923,"about_ca_system_score_gemma":0.00009167071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005602502,"about_ca_topic_score_gemma":0.00002198371,"domain_scores_codex":[0.9976982,0.0002916911,0.0007612863,0.0006712938,0.0003353621,0.0002421312],"domain_scores_gemma":[0.9983047,0.0005476653,0.0003974398,0.0003229326,0.0002746504,0.0001525954],"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":[0.0005877555,0.001657531,0.2702734,0.0001208026,0.000475681,0.00005708741,0.001190729,0.01089237,0.007046582,0.2073896,0.00111034,0.4991981],"study_design_scores_gemma":[0.005451038,0.000472194,0.02271601,0.001223965,0.000155272,0.0000815766,0.003675231,0.7996354,0.00525517,0.01443099,0.1457228,0.00118036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6331948,0.001486406,0.1619165,0.001582883,0.00110156,0.0005409147,0.0002478143,0.0001164587,0.1998127],"genre_scores_gemma":[0.9891979,0.0005820072,0.002410299,0.0002055825,0.0003922851,0.0001873736,0.0003889448,0.00002694494,0.006608672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.788743,"threshold_uncertainty_score":0.9982312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1564698957436246,"score_gpt":0.4446100735106631,"score_spread":0.2881401777670385,"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."}}