{"id":"W4408361374","doi":"10.1021/acs.chemmater.5c00022","title":"Driving Thermoelectric Optimization in AgSbTe<sub>2</sub> via Design of Experiments and Machine Learning","year":2025,"lang":"en","type":"article","venue":"Chemistry of Materials","topic":"Advanced Thermoelectric Materials and Devices","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; McMaster University; University of New Brunswick","funders":"National Science Foundation Graduate Research Fellowship Program; Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Thermoelectric effect; Computer science; Machine design; Materials science; Nanotechnology; Artificial intelligence; Engineering; Mechanical engineering; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005743314,0.000176408,0.000450993,0.00007374652,0.00007405603,0.00003184168,0.0001836779,0.0001057958,0.000275821],"category_scores_gemma":[0.0001483911,0.0001672808,0.00002076056,0.0002045655,0.00007579894,0.0001162452,0.0001744832,0.00004605083,0.000001251224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003379153,"about_ca_system_score_gemma":0.00004143982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002610866,"about_ca_topic_score_gemma":3.161198e-7,"domain_scores_codex":[0.9986523,0.0001304858,0.0005632984,0.0002848813,0.0001437877,0.0002252371],"domain_scores_gemma":[0.9992523,0.0001108847,0.0003790486,0.0001684352,0.00005776285,0.00003155611],"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":[0.0001310487,0.00004897832,0.00006841799,0.0003327172,0.00000873203,0.000001622206,0.0001089701,0.007260079,0.9913079,0.00001146525,0.000001873983,0.0007181927],"study_design_scores_gemma":[0.000461807,0.00003547713,0.00008903565,0.000169384,0.00001315148,0.000003299375,0.00002099066,0.001716856,0.9970008,0.0003533714,0.000003899975,0.0001319954],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9715222,0.0006921582,0.02726563,0.000008752104,0.00009995905,0.000190917,0.000007605098,0.00003340875,0.0001793782],"genre_scores_gemma":[0.9969706,0.0002683876,0.002646329,0.000009951184,0.00002234685,0.00002794598,0.00001215419,0.00001625171,0.00002605298],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02544839,"threshold_uncertainty_score":0.6821513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01013910215950326,"score_gpt":0.2350557559794624,"score_spread":0.2249166538199591,"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."}}