{"id":"W4417427795","doi":"10.1039/d5cp03741g","title":"WTMAD-4: a fair weighting scheme for GMTKN55","year":2025,"lang":"en","type":"article","venue":"Physical Chemistry Chemical Physics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts; Royal Society","keywords":"Weighting; Metric (unit); Set (abstract data type); Scheme (mathematics); Component (thermodynamics); Absolute deviation; Standard deviation","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":[0.0002761913,0.0003693645,0.0005043276,0.00001289896,0.000221636,0.0001820547,0.0009331069,0.0001319178,0.0001437881],"category_scores_gemma":[0.0005896066,0.0003470716,0.0002416752,0.0003618217,0.0003697188,0.0002219845,0.0003997734,0.0003316064,0.0001317143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001244174,"about_ca_system_score_gemma":0.0001260848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000932538,"about_ca_topic_score_gemma":5.626601e-8,"domain_scores_codex":[0.9976122,0.00003105516,0.0003759688,0.000877471,0.0004027316,0.0007006043],"domain_scores_gemma":[0.9983928,0.0004679493,0.0001841518,0.0006174092,0.0001758786,0.0001618126],"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":[0.00004973748,0.0002310683,0.0000388296,0.0003954527,0.00001018955,8.655638e-7,0.00006569603,0.0001851593,0.9931509,0.003786142,0.001655174,0.0004307326],"study_design_scores_gemma":[0.0004625381,0.00001257874,0.000009216695,0.00007867,0.0000282524,0.000001159591,0.00001583304,0.03569911,0.9270133,0.03439893,0.00193498,0.0003453725],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655818,0.00002261481,0.01925938,0.0005345714,0.0002035623,0.0002788468,0.00005655151,0.0004074253,0.01365522],"genre_scores_gemma":[0.983907,7.572043e-7,0.01315452,0.0002953848,0.001353048,0.0001673295,0.00005048231,0.00003788875,0.001033572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0661376,"threshold_uncertainty_score":0.9998981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009084065903775366,"score_gpt":0.2818966930704762,"score_spread":0.2728126271667008,"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."}}