{"id":"W2949784712","doi":"10.48550/arxiv.1906.04477","title":"Causal Discovery with Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Cognitive science; Psychology; Artificial intelligence; Social psychology","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":[0.0001875922,0.0003345591,0.0003157435,0.0001661771,0.000142276,0.0003338496,0.00147095,0.0002191383,0.00001536828],"category_scores_gemma":[0.0000118961,0.0003263781,0.0001199564,0.0003266186,0.00007527115,0.00070095,0.001719844,0.0009324851,0.0001562379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001734911,"about_ca_system_score_gemma":0.0003970638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002023338,"about_ca_topic_score_gemma":0.00001741649,"domain_scores_codex":[0.9981109,0.00009610541,0.000169576,0.001077095,0.0001437614,0.0004025425],"domain_scores_gemma":[0.9983106,0.00006006262,0.0002327085,0.001131308,0.0001303361,0.000135013],"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":[0.00002231316,0.00001920711,0.001554521,0.0000443352,0.00005398342,0.0001173381,0.000131957,0.8454975,0.00001157056,0.1522834,0.00007192886,0.0001919748],"study_design_scores_gemma":[0.0003518933,0.0001768312,0.0002855003,0.0002053438,0.00004458534,0.00000643311,0.0000485754,0.9908364,0.00008544921,0.007147679,0.00028139,0.0005298827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08962592,0.00002778623,0.9031602,0.00006177197,0.0003338647,0.0001839463,0.000001698298,0.0002462313,0.006358566],"genre_scores_gemma":[0.9857723,0.00009746067,0.001412871,0.00009301594,0.00004950579,8.910727e-7,0.00001692203,0.00001843936,0.01253861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9017473,"threshold_uncertainty_score":0.9999188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05887176603568913,"score_gpt":0.1842319754472586,"score_spread":0.1253602094115694,"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."}}