{"id":"W4415374521","doi":"10.1021/acsaem.5c02609","title":"Machine Learning Predictions of Thermopower for Thermoelectric Material Screening","year":2025,"lang":"en","type":"article","venue":"ACS Applied Energy Materials","topic":"Advanced Thermoelectric Materials and Devices","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Thermoelectric effect; Seebeck coefficient; Thermoelectric materials; Power (physics); Test data; Experimental data","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006468801,0.0003496112,0.0006922259,0.000225867,0.0003251044,0.0001445131,0.0004519422,0.00019854,0.001483702],"category_scores_gemma":[0.00006557893,0.0002993113,0.00007206952,0.0003549425,0.0001066218,0.0001357073,0.0001560066,0.00005994289,0.00001011286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004052489,"about_ca_system_score_gemma":0.00007052287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002501273,"about_ca_topic_score_gemma":0.000008343903,"domain_scores_codex":[0.9977433,0.0001266431,0.0008143934,0.0005279688,0.0002291234,0.0005585573],"domain_scores_gemma":[0.9987464,0.000211545,0.0004658139,0.0003913749,0.0001264759,0.00005837423],"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":[0.0007319469,0.00005658876,0.000004681813,0.00009842713,0.00005090017,5.961637e-7,0.00004078587,0.0007445201,0.9119313,0.08326221,0.0001232845,0.002954765],"study_design_scores_gemma":[0.0007866277,0.0001189108,0.0000580913,0.00004411222,0.00007368035,0.000002525415,0.00002792705,0.0001086679,0.9792942,0.01017476,0.009045234,0.0002653067],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8917004,0.0004281038,0.09652788,0.00007622795,0.001661603,0.0006510448,0.0004602931,0.0004297133,0.008064683],"genre_scores_gemma":[0.9955794,0.000137399,0.002296852,0.0001737539,0.000279527,0.0004491522,0.0001811729,0.0000615114,0.0008412675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1038789,"threshold_uncertainty_score":0.9999459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007673060986386136,"score_gpt":0.2356570371029627,"score_spread":0.2279839761165765,"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."}}