{"id":"W4413956711","doi":"10.1088/2632-2153/ae6416","title":"Multi-task Attention for Doped Thermoelectric Properties Prediction","year":2025,"lang":"en","type":"preprint","venue":"Machine Learning Science and Technology","topic":"Advanced Thermoelectric Materials and Devices","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Army Research Office; Nanyang Technological University","keywords":"Thermoelectric effect; Task (project management); Doping; Materials science; Thermoelectric materials; Computer science; Engineering physics; Optoelectronics; Physics; Engineering; Systems engineering; Thermodynamics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001268681,0.0002894775,0.0004050464,0.0008341589,0.0008440883,0.0002509524,0.0006849795,0.0003382603,0.00002006163],"category_scores_gemma":[0.0008794167,0.0002267004,0.00004305534,0.0009125911,0.000650129,0.0001914449,0.0007516374,0.0004998791,0.000008794006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001092314,"about_ca_system_score_gemma":0.0003274679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001246193,"about_ca_topic_score_gemma":0.00001781552,"domain_scores_codex":[0.9977502,0.00006707785,0.000368818,0.0009823852,0.0002988428,0.0005327245],"domain_scores_gemma":[0.9987661,0.0000442438,0.0003281396,0.0003646974,0.0004474282,0.00004944188],"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":[0.00003823631,0.0000377484,0.000768564,0.0002103776,0.000007962093,9.046514e-7,0.00007249811,0.0002809142,0.9740953,0.0009375787,0.000009032209,0.02354082],"study_design_scores_gemma":[0.00110693,0.0006511713,0.001198576,0.0003898727,0.0001122443,0.00002894711,0.0001291199,0.2133901,0.7688782,0.007088867,0.006350443,0.000675542],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770948,0.003191736,0.01550003,0.001111868,0.0008492903,0.001104423,0.00005853274,0.0008802867,0.0002090007],"genre_scores_gemma":[0.9932013,0.0002817367,0.004937752,0.0000559916,0.00006542498,0.000368737,0.00002062184,0.00001665933,0.001051739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2131092,"threshold_uncertainty_score":0.9244576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01439925231097692,"score_gpt":0.2648935638034858,"score_spread":0.2504943114925089,"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."}}