{"id":"W6939987376","doi":"10.6084/m9.figshare.c.7385948.v1","title":"Can supervised deep learning architecture outperform autoencoders in building propensity score models for matching?","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Propensity score matching; Deep learning; Supervised learning; Unsupervised learning; Observational study; Matching (statistics); Variance (accounting)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009543507,0.0006851488,0.000598215,0.0006479693,0.0002728546,0.001246368,0.001147071,0.0008727001,0.004512324],"category_scores_gemma":[0.03631067,0.0003239182,0.0008472949,0.0006117789,0.0007126617,0.001566077,0.001183528,0.001320519,0.0008848496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009059872,"about_ca_system_score_gemma":0.001575767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005522326,"about_ca_topic_score_gemma":0.007305993,"domain_scores_codex":[0.9980423,0.001350628,0.00007892106,0.0002829778,0.0001410069,0.0001041526],"domain_scores_gemma":[0.9885386,0.008163119,0.0009562753,0.001137866,0.0009919915,0.0002121801],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006744807,0.0003110613,0.05232314,0.0003178764,0.0006726566,0.0001338167,0.0002347766,0.5547974,0.00147416,0.03330627,0.007799993,0.3479544],"study_design_scores_gemma":[0.00004725512,0.00007130311,0.002755892,0.00006398901,0.00005560808,0.00002605662,0.00002275288,0.9699878,0.0008700807,0.02490305,0.001179142,0.00001711957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1832614,0.001029938,0.8069207,0.002817723,0.0001468207,0.0001529338,0.0009387431,0.00109476,0.003636981],"genre_scores_gemma":[0.8279049,0.0004505436,0.1666945,0.0007692438,0.00008698131,0.0002453235,0.0008301766,0.0001051219,0.002913287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9904565,"threshold_uncertainty_score":0.05047148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04716214669701183,"score_gpt":0.2337703470944879,"score_spread":0.186608200397476,"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."}}