{"id":"W4285792189","doi":"10.1016/j.xpro.2022.101552","title":"Protocol to predict mechanical properties of multi-element ceramics using machine learning","year":2022,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Compute Canada","keywords":"Workflow; Protocol (science); Computer science; Ceramic; Element (criminal law); Machine learning; Artificial intelligence; Materials science; Database; Composite material","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003259282,0.0002784554,0.0004295388,0.0001545187,0.0006797969,0.0001397757,0.001024224,0.00004780497,0.003910834],"category_scores_gemma":[0.000443252,0.0002375636,0.00007647017,0.0003991757,0.0001139595,0.0001945744,0.00152332,0.0003842892,0.00004091632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002587002,"about_ca_system_score_gemma":0.000267023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004523151,"about_ca_topic_score_gemma":0.00002023323,"domain_scores_codex":[0.9957468,0.001035809,0.0008100955,0.0006603952,0.001149804,0.0005971119],"domain_scores_gemma":[0.9986662,0.00003242818,0.0004729762,0.0005257253,0.000144304,0.0001583213],"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":[0.0004386293,0.0002445405,0.000974007,0.000311953,0.000004670447,0.000005239844,0.0006483701,0.06993761,0.9270583,0.0001608371,0.00002031371,0.0001955496],"study_design_scores_gemma":[0.001426126,0.001669382,0.0001122649,0.0001801552,0.000008160312,0.00001868615,0.0002146054,0.2240315,0.7503746,0.00006202785,0.021538,0.000364518],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.2733336,0.000001890296,0.005512292,0.0001122513,0.0001487669,0.7205109,0.00008727131,0.0002369146,0.00005605831],"genre_scores_gemma":[0.09593756,3.167743e-8,0.06313907,0.00009915296,0.00005781911,0.8404678,0.000003552089,0.00004738661,0.0002476858],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.1773961,"threshold_uncertainty_score":0.9969997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0720617638430672,"score_gpt":0.3496620864038378,"score_spread":0.2776003225607706,"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."}}