{"id":"W4382344148","doi":"10.1002/adma.202302575","title":"Closed‐Loop Error‐Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials","year":2023,"lang":"en","type":"article","venue":"Advanced Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"King Abdullah University of Science and Technology; University of Toronto; Compute Canada; Northwestern University","keywords":"Thermoelectric effect; Materials science; Thermoelectric materials; Doping; Loop (graph theory); Throughput; Degrees of freedom (physics and chemistry); Characterization (materials science); Computer science; Nanotechnology; Optoelectronics; Physics; Thermodynamics; Mathematics","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":["insufficient_payload"],"category_scores_codex":[0.002298485,0.0004770673,0.0008590275,0.0003516137,0.0003944628,0.0004976693,0.0007541323,0.0001428005,0.004701527],"category_scores_gemma":[0.0008749507,0.0004255249,0.00008700841,0.0008393027,0.0002593297,0.001388031,0.0004070573,0.0001438586,0.001195461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001392937,"about_ca_system_score_gemma":0.0001071488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002678631,"about_ca_topic_score_gemma":0.000004940934,"domain_scores_codex":[0.9955881,0.0007120548,0.001089764,0.00089339,0.000792962,0.0009237091],"domain_scores_gemma":[0.998001,0.0003028087,0.0008396478,0.0005766449,0.0001804815,0.00009941278],"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":[0.0003431374,0.00006971442,0.0001061503,0.00009008913,0.000009545573,0.00001275725,0.0003728176,0.005023322,0.9928983,0.0003390493,0.0004073791,0.0003277822],"study_design_scores_gemma":[0.0005461308,0.0003822212,0.002243408,0.0001098158,0.00001743345,0.00001692485,0.0003585804,0.0001706431,0.9949893,0.0003499085,0.0003522151,0.0004634479],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901999,0.00009280404,0.0002676451,0.00006958139,0.007286176,0.0005555744,0.00007926847,0.0008375417,0.0006115236],"genre_scores_gemma":[0.9950228,0.00007698857,0.001201302,0.00006253762,0.0003126133,0.0001936369,0.0001016897,0.00009921702,0.002929249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006973563,"threshold_uncertainty_score":0.9998196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01609189109682698,"score_gpt":0.2997680624343009,"score_spread":0.283676171337474,"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."}}