{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002499424,0.0002876382,0.00042402,0.0001167729,0.001342718,0.0002045656,0.001394348,0.00006952466,0.0004579054],"category_scores_gemma":[0.0006868129,0.0002255896,0.000064519,0.0007873089,0.001392523,0.0007844244,0.0006569759,0.0003654548,0.000009920064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002351605,"about_ca_system_score_gemma":0.0001573916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001936671,"about_ca_topic_score_gemma":0.000009129976,"domain_scores_codex":[0.9961998,0.0001688588,0.0004807573,0.001114708,0.001216438,0.0008194635],"domain_scores_gemma":[0.9984965,0.0004238033,0.0002959838,0.0003838872,0.0002257108,0.0001740674],"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":[0.0004359086,0.00009082576,0.0005701772,0.00004772174,0.000003159224,8.371243e-7,0.0006532233,0.04407804,0.9533182,0.00008344415,0.000004133983,0.0007142798],"study_design_scores_gemma":[0.001047746,0.0003105349,0.001142577,0.00002390091,0.00001345437,0.00003218137,0.0002849025,0.2135151,0.7828601,0.00001151295,0.0004433008,0.000314675],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8041254,0.0000173024,0.1947489,0.00006630435,0.0002101998,0.0006205651,0.00004010829,0.0001092336,0.00006196846],"genre_scores_gemma":[0.9716936,0.000003491409,0.02747997,0.000122354,0.00007411274,0.0004006492,0.00003315144,0.0000260263,0.0001666365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1704582,"threshold_uncertainty_score":0.9999574,"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."}}