{"id":"W4226338259","doi":"10.1039/d2sc00393g","title":"Detection of multi-reference character imbalances enables a transfer learning approach for virtual high throughput screening with coupled cluster accuracy at DFT cost","year":2022,"lang":"en","type":"article","venue":"Chemical Science","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; Association of Medical Microbiology and Infectious Disease Canada; Burroughs Wellcome Fund; U.S. Department of Energy; Canadian Cancer Society Research Institute; Sparks; Alberta Cancer Foundation; National Science Foundation","keywords":"Throughput; Cluster (spacecraft); Character (mathematics); Computer science; Virtual screening; Transfer of learning; Transfer (computing); High-throughput screening; Artificial intelligence; Chemistry; Computer network; Computational chemistry; Telecommunications; Parallel computing; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002038855,0.0008426801,0.0009059858,0.000759911,0.0006884214,0.001204667,0.001983821,0.0009905886,0.003373029],"category_scores_gemma":[0.006748217,0.0004096563,0.0004301329,0.0009158175,0.0009421465,0.002051075,0.001725443,0.001684036,0.0009381018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008995,"about_ca_system_score_gemma":0.001037201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001208197,"about_ca_topic_score_gemma":0.002110933,"domain_scores_codex":[0.998611,0.0002421334,0.00004298151,0.000295105,0.0007016178,0.0001070991],"domain_scores_gemma":[0.9978858,0.0006722954,0.000245093,0.0007075262,0.0004023011,0.00008706635],"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":[0.0007752595,0.0006005676,0.006407237,0.0003919696,0.0002444005,0.0003363916,0.0002450575,0.3726712,0.3457059,0.0312325,0.005434718,0.2359549],"study_design_scores_gemma":[0.00001457251,0.0002209838,0.0009713257,0.000007805334,0.00002094539,0.00007085801,0.00002471083,0.8487716,0.1364008,0.0117183,0.001739468,0.00003861819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1863228,0.0003496445,0.799206,0.0007517018,0.0001352954,0.0001412324,0.0005701745,0.006386298,0.006136823],"genre_scores_gemma":[0.8644481,0.0001406023,0.1323024,0.0002509126,0.00002801432,0.0001422282,0.0005621378,0.0003571966,0.001768372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003373029,"threshold_uncertainty_score":0.01128387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02400487637032605,"score_gpt":0.2651254543446764,"score_spread":0.2411205779743503,"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."}}