{"id":"W4388978577","doi":"10.1088/2632-2153/ad0fa3","title":"Improved decision making with similarity based machine learning: applications in chemistry","year":2023,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"H2020 European Research Council; Canada First Research Excellence Fund; National Science Foundation","keywords":"Curse of dimensionality; Computer science; Scarcity; Similarity (geometry); Chemical space; Machine learning; Artificial intelligence; Space (punctuation); Feature (linguistics); Data mining; Chemistry; Drug discovery","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003776953,0.0004740655,0.001249601,0.0006889245,0.0006027021,0.001562473,0.001361693,0.001498856,0.002502211],"category_scores_gemma":[0.014934,0.0002986108,0.0005961535,0.001117287,0.001667709,0.002156933,0.002286032,0.001844212,0.0003892532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001309904,"about_ca_system_score_gemma":0.0008769722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002301474,"about_ca_topic_score_gemma":0.001315053,"domain_scores_codex":[0.9978482,0.00119515,0.00009346188,0.00026405,0.0004817686,0.0001173517],"domain_scores_gemma":[0.9892353,0.00855064,0.0005260469,0.0006953428,0.0007559811,0.0002366116],"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":[0.0001219989,0.0001595889,0.0007093964,0.00008231847,0.00003371729,0.00008216083,0.0000860424,0.8733765,0.001129777,0.06684763,0.001056318,0.05631447],"study_design_scores_gemma":[0.000005026476,0.00001574398,0.00003843621,0.000002685708,0.000001233552,0.000005144356,0.000004149868,0.9809231,0.0001852722,0.01870223,0.0001139053,0.000003194614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09213784,0.002046597,0.8958789,0.002647134,0.0001599448,0.000086763,0.00008956309,0.0003741596,0.006579095],"genre_scores_gemma":[0.8838279,0.0004128056,0.1136948,0.0002323407,0.0001604467,0.00007221652,0.00006255764,0.00004323409,0.001493661],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003776953,"threshold_uncertainty_score":0.01997465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00697190578342071,"score_gpt":0.2662006005477507,"score_spread":0.25922869476433,"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."}}