{"id":"W6921069386","doi":"10.6084/m9.figshare.26488316.v1","title":"Additional file 1 of Can supervised deep learning architecture outperform autoencoders in building propensity score models for matching?","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deep learning; Propensity score matching; Architecture; Artificial neural network; F1 score; Deep neural networks","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002496601,0.001299566,0.001315137,0.001826748,0.0008119498,0.002059662,0.002613825,0.002142938,0.9118408],"category_scores_gemma":[0.06826288,0.0007539386,0.001439299,0.002335075,0.0003694406,0.002141338,0.00129289,0.001529249,0.2564166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059556,"about_ca_system_score_gemma":0.00206501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006385113,"about_ca_topic_score_gemma":0.01413044,"domain_scores_codex":[0.9991597,0.0002431133,0.00009035179,0.0002462816,0.0001560377,0.0001045127],"domain_scores_gemma":[0.9430446,0.05052809,0.001160211,0.00213216,0.002454039,0.0006810043],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002107815,0.00008603004,0.001935533,0.001715042,0.00008733865,0.00005648986,0.00002972801,0.001399548,0.00006603346,0.002607034,0.9811494,0.01065712],"study_design_scores_gemma":[0.00939021,0.0005572784,0.02206854,0.004420741,0.0004858011,0.0007581039,0.0003617608,0.02475847,0.00146367,0.1067001,0.8287449,0.0002903754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0004268695,0.00005727084,0.002252704,0.0003785832,0.0001086929,0.00008351141,0.9938625,0.0008982631,0.001931621],"genre_scores_gemma":[0.02737351,0.000360131,0.02354061,0.002074715,0.0004287091,0.003152416,0.915059,0.004090684,0.02392025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9975034,"threshold_uncertainty_score":0.1257483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0693289352225452,"score_gpt":0.2601704189500754,"score_spread":0.1908414837275302,"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."}}