{"id":"W3118795356","doi":"10.5445/ir/1000133179","title":"Scientific intuition inspired by machine learning-generated hypotheses","year":2021,"lang":"en","type":"article","venue":"Repository KITopen (Karlsruhe Institute of Technology)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; National Research Council Canada; Vector Institute; University of Toronto","funders":"H2020 Marie Skłodowska-Curie Actions; Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada; Austrian Science Fund; European Commission","keywords":"Artificial intelligence; Computer science; Realm; Data science; Intuition; Gradient boosting; Machine learning; Cognitive science; Random forest","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009129189,0.0003409711,0.0005691787,0.0003915328,0.0009403967,0.0005454784,0.001255923,0.0003520993,0.0003916646],"category_scores_gemma":[0.001239204,0.0003258375,0.0001024458,0.00145331,0.001610851,0.0008578192,0.0006847791,0.0004546031,0.0002050646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371231,"about_ca_system_score_gemma":0.0004435146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002460739,"about_ca_topic_score_gemma":0.00004206249,"domain_scores_codex":[0.9966565,0.0002409022,0.0008325425,0.001060572,0.000666898,0.000542633],"domain_scores_gemma":[0.9975933,0.00004534181,0.0005897763,0.001069698,0.0005792588,0.0001226491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000307049,0.0001555025,0.002953179,0.0000601734,0.00001494927,0.0001126619,0.00005430065,0.001611303,0.9913322,0.001215089,0.001217586,0.001242323],"study_design_scores_gemma":[0.0003352448,0.0001234659,0.0003445272,0.0001166034,0.00002899291,0.0002093038,0.00003743232,0.001237468,0.9070528,0.0003326206,0.08985794,0.0003236634],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893358,0.001107071,0.00120965,0.0005510396,0.004164338,0.0002686974,0.00003734432,0.0006939875,0.002632021],"genre_scores_gemma":[0.9819454,0.00003921831,0.01241924,0.0000532948,0.000105874,0.00005057816,0.00008247157,0.00003782732,0.005266113],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08864035,"threshold_uncertainty_score":0.9999194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01129208235711743,"score_gpt":0.2356127655810104,"score_spread":0.224320683223893,"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."}}