{"id":"W2729335696","doi":"10.48550/arxiv.1707.01473","title":"Machine-Learning Tests for Effects on Multiple Outcomes","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Booth University College","funders":"","keywords":"Intuition; Computer science; Machine learning; Randomized experiment; Inference; Artificial intelligence; Outcome (game theory); Data collection; Set (abstract data type); Data science; Psychology; Statistics; Mathematics","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":[0.0002920944,0.0004935603,0.000683658,0.0002168879,0.0003397865,0.00007166209,0.0009440414,0.0004497422,0.00001538649],"category_scores_gemma":[0.005401638,0.0005029796,0.0003602041,0.0000657588,0.00009657982,0.0001571699,0.0008012332,0.0009609989,0.00003309691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002539361,"about_ca_system_score_gemma":0.00006558439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006483563,"about_ca_topic_score_gemma":0.0000968577,"domain_scores_codex":[0.9983272,0.0001171764,0.0002091777,0.0008443727,0.00009079005,0.0004113078],"domain_scores_gemma":[0.9935753,0.004194298,0.0005886836,0.001347627,0.0001606636,0.0001333981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004450465,0.0005824442,0.1911551,0.003001368,0.000688975,0.0005684405,0.0003705877,0.01961232,0.0004631114,0.7761603,0.00185968,0.005092666],"study_design_scores_gemma":[0.00111442,0.0002832368,0.002106084,0.0006057587,0.000228759,0.000001414178,0.00002276135,0.03878415,0.002869917,0.9517873,0.001393223,0.0008029641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4865417,0.00005186881,0.4997722,0.0001368096,0.0007417083,0.003204377,0.0001453495,0.002261891,0.007144108],"genre_scores_gemma":[0.9829696,0.00007326723,0.01128474,0.00005194059,0.00007678977,0.00001717148,0.00004175145,0.00008541342,0.00539926],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.496428,"threshold_uncertainty_score":0.9997422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2748012721513939,"score_gpt":0.3244005404485151,"score_spread":0.04959926829712125,"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."}}