{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003834529,0.0003312321,0.0003980959,0.0009998694,0.001288908,0.0003314893,0.001238979,0.0002066253,0.0002526687],"category_scores_gemma":[0.002830987,0.0002682286,0.00002630981,0.005921863,0.001779895,0.0003439158,0.0007096867,0.001059035,0.00007022877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001279082,"about_ca_system_score_gemma":0.000279813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001861297,"about_ca_topic_score_gemma":0.0001161868,"domain_scores_codex":[0.9965025,0.0001150164,0.000421929,0.001252942,0.0007534485,0.0009542157],"domain_scores_gemma":[0.9984004,0.0003757,0.0002861713,0.0005745065,0.0002342813,0.0001289469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005014517,0.00005125893,0.2217256,0.00006225782,0.000001615881,0.0000257488,0.0001196795,0.02134742,0.7479423,0.0003588797,0.000005877212,0.008309275],"study_design_scores_gemma":[0.0008278036,0.0002990581,0.01522215,0.0001303724,0.00001218053,0.0000589667,0.0002404018,0.9194462,0.05758986,0.00131307,0.004302355,0.0005575483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872043,0.0001075115,0.008912223,0.00146324,0.00008377589,0.0003845378,0.00000822775,0.00137066,0.0004654964],"genre_scores_gemma":[0.9868647,0.00001820642,0.01265979,0.00007844983,0.00002501484,0.0001199729,0.00001499237,0.00003392042,0.0001849363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8980988,"threshold_uncertainty_score":0.999977,"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."}}