{"id":"W4236673905","doi":"10.26434/chemrxiv.7905017.v1","title":"Solving the Colouring Problem in Half-Heusler Structures: Machine-Learning Predictions and Experimental Validation","year":2019,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Heusler alloys: electronic and magnetic properties","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Sensitivity (control systems); Support vector machine; Selectivity; Diffraction; Artificial intelligence; Computer science; Crystal structure; Experimental data; Machine learning; Algorithm; Materials science; Chemistry; Crystallography; Physics; Mathematics; Optics; Engineering; Statistics; Electronic engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001172491,0.0005706925,0.0006279234,0.0003778957,0.0004087211,0.000460436,0.0008320176,0.0007766359,0.002158188],"category_scores_gemma":[0.002219434,0.0003081626,0.0002794943,0.0005234767,0.0006751157,0.0008630436,0.0003136386,0.0007513121,0.000317596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006775545,"about_ca_system_score_gemma":0.000545372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001931832,"about_ca_topic_score_gemma":0.002776566,"domain_scores_codex":[0.9998118,0.00005284377,0.000007430773,0.00004642435,0.00005977708,0.0000217265],"domain_scores_gemma":[0.9990362,0.0005829913,0.00007244633,0.0001565633,0.0001204992,0.00003135899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008752961,0.0004702656,0.005149309,0.0005882372,0.00007336421,0.0002047122,0.0002232493,0.7904396,0.139709,0.01091992,0.00145451,0.04989244],"study_design_scores_gemma":[0.00004805607,0.000311629,0.0007798943,0.0000112688,0.000009996341,0.00003757911,0.00005392588,0.9320349,0.06322323,0.002860534,0.0006138648,0.00001507124],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756786,0.0003490152,0.02155868,0.0001315231,0.00001600095,0.00003286152,0.0002581694,0.0003065493,0.001668595],"genre_scores_gemma":[0.9685804,0.0001920776,0.02987952,0.00002373085,0.000003168026,0.00003618319,0.0005003257,0.00005025934,0.0007344607],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002158188,"threshold_uncertainty_score":0.007219851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01513386264042661,"score_gpt":0.2379200387495583,"score_spread":0.2227861761091317,"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."}}