{"id":"W4389983291","doi":"10.48550/arxiv.2312.10570","title":"Adversarially Balanced Representation for Continuous Treatment Effect Estimation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Counterfactual thinking; Representation (politics); Computer science; Divergence (linguistics); Outcome (game theory); Range (aeronautics); Machine learning; Binary number; Value (mathematics); Function (biology); Estimation; Binary classification; Artificial intelligence; Variable (mathematics); Econometrics; Mathematics; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003857981,0.0003282196,0.0004652386,0.0002624886,0.0002025955,0.0001305333,0.0009252803,0.0002760617,0.00000586304],"category_scores_gemma":[0.0003418406,0.0003450715,0.0002760237,0.0004317433,0.00003652196,0.0002409286,0.0005849837,0.0002882365,0.00008928189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005521755,"about_ca_system_score_gemma":0.0002266032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001178837,"about_ca_topic_score_gemma":0.0001062044,"domain_scores_codex":[0.9976904,0.0003589963,0.0002465982,0.001249188,0.0001056331,0.0003491933],"domain_scores_gemma":[0.9972817,0.0008507092,0.0003854093,0.001179947,0.0001749656,0.000127271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001286456,0.00004208468,0.0130805,0.0002508446,0.0001220728,0.0001142205,0.0004142569,0.9469874,0.00001845569,0.02672732,0.0003109864,0.01180321],"study_design_scores_gemma":[0.001261587,0.0004575613,0.005526537,0.00009626576,0.00008154238,0.000002032456,0.00001656737,0.9760305,0.0001284711,0.01591176,0.0001951322,0.000292015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1125184,0.0000166842,0.8825342,0.0004669664,0.001630707,0.001644755,0.00003017085,0.0008655902,0.0002925349],"genre_scores_gemma":[0.9860576,0.00004432713,0.01089059,0.00003612057,0.0001374391,0.00002698681,0.0002103609,0.00003245178,0.002564142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8735392,"threshold_uncertainty_score":0.9999001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09656920777411045,"score_gpt":0.2649068335483653,"score_spread":0.1683376257742549,"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."}}