{"id":"W3011390981","doi":"10.1038/s41524-020-0286-9","title":"An automated predictor for identifying transition states in solids","year":2020,"lang":"en","type":"article","venue":"npj Computational Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Science Challenge Project; Compute Canada","keywords":"Phase transition; Path (computing); Phase (matter); Statistical physics; Transformation (genetics); Computer science; Energy (signal processing); Crystal structure prediction; Particle swarm optimization; Algorithm; Materials science; Mathematical optimization; Thermodynamics; Mathematics; Chemistry; Physics; Crystal structure; Crystallography; Statistics; Quantum mechanics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005565894,0.0005751591,0.0006894778,0.001417815,0.0006302653,0.0006697563,0.001031183,0.001063163,0.004513619],"category_scores_gemma":[0.002306303,0.0003670307,0.0004771393,0.000937944,0.0004492315,0.0009125394,0.0007867695,0.0007690078,0.0007703684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004301526,"about_ca_system_score_gemma":0.00104367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001853966,"about_ca_topic_score_gemma":0.002022161,"domain_scores_codex":[0.9997714,0.00004983736,0.00001287117,0.00005043165,0.00008788753,0.00002765588],"domain_scores_gemma":[0.9991363,0.0004173171,0.0001060807,0.00007622586,0.0002297017,0.00003430511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002987494,0.0001680983,0.007472299,0.0004127884,0.00006470449,0.0002786626,0.0001025348,0.7681512,0.01783138,0.02107031,0.005599002,0.1785502],"study_design_scores_gemma":[0.000004585091,0.00001215456,0.0001737197,0.000004032257,0.000002832797,0.0000104316,0.000006410497,0.9963069,0.001514525,0.00168096,0.0002808432,0.00000263077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.190633,0.000394576,0.7963821,0.0002481829,0.00006934286,0.000164875,0.0008468428,0.00561381,0.005647307],"genre_scores_gemma":[0.6830125,0.0001465081,0.313038,0.0000639883,0.00002839491,0.0002225593,0.001140224,0.0003331183,0.002014682],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004513619,"threshold_uncertainty_score":0.01509959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02892268847871625,"score_gpt":0.3335909149301362,"score_spread":0.3046682264514199,"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."}}