{"id":"W4406525604","doi":"10.1039/d4dd00332b","title":"Composition and structure analyzer/featurizer for explainable machine-learning models to predict solid state structures","year":2025,"lang":"en","type":"article","venue":"Digital Discovery","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Hunter College; City University of New York","keywords":"Spectrum analyzer; Computer science; Solid-state; Artificial intelligence; Machine learning; Chemistry; Physical chemistry","routes":{"ca_aff":true,"ca_fund":false,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000227403,0.0002737002,0.0003386363,0.0001838054,0.0003686209,0.002145636,0.0003540147,0.00006982831,0.00003996933],"category_scores_gemma":[0.0001618034,0.0002287189,0.00006305396,0.0002311562,0.0001242715,0.002114395,0.0003298693,0.0001433612,0.000006259094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006226661,"about_ca_system_score_gemma":0.00006762828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000639302,"about_ca_topic_score_gemma":0.00001155722,"domain_scores_codex":[0.9982027,0.00006796992,0.0003264821,0.0006351639,0.0002927212,0.0004749128],"domain_scores_gemma":[0.9992542,0.0001491516,0.0001197116,0.0002736415,0.00008548112,0.0001178722],"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":[0.0004084344,0.00003252189,0.002417643,0.0002317943,0.00002451916,0.000006328009,0.000566272,0.3442833,0.6427863,0.007401008,0.000723402,0.001118426],"study_design_scores_gemma":[0.002515085,0.0007961005,0.01463571,0.0005083294,0.0001261305,0.00005349503,0.0004920701,0.2481762,0.4547209,0.2722504,0.003883118,0.001842398],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8898681,0.00009533513,0.1068429,0.0001732597,0.0004305479,0.0004962175,0.001168483,0.0001353876,0.0007897625],"genre_scores_gemma":[0.9931354,0.000005714734,0.004503327,0.0002926296,0.00005760347,0.00003635755,0.000185642,0.00002443366,0.001758882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2648494,"threshold_uncertainty_score":0.9988902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009439380776572958,"score_gpt":0.2505650215909377,"score_spread":0.2411256408143647,"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."}}