{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006352793,0.001276383,0.0004495404,0.0008800791,0.0005164925,0.000811318,0.001505578,0.0008956484,0.03073642],"category_scores_gemma":[0.002415374,0.0005802302,0.0007598251,0.000666974,0.000373688,0.001600478,0.0007551181,0.001924739,0.00629936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005212687,"about_ca_system_score_gemma":0.0006050431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000805525,"about_ca_topic_score_gemma":0.001364959,"domain_scores_codex":[0.9998059,0.00003397831,0.00001406325,0.00003918787,0.00009245703,0.00001447749],"domain_scores_gemma":[0.9995708,0.0002390438,0.00002287755,0.00009205612,0.00006249602,0.00001273749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007318633,0.0003889563,0.003933282,0.001546507,0.000252044,0.001109384,0.0005860255,0.1294689,0.1429075,0.2642899,0.1160599,0.3387258],"study_design_scores_gemma":[0.00008963924,0.00005878259,0.000533509,0.00007484655,0.00005042154,0.0002468192,0.00006140384,0.680444,0.1518342,0.07024914,0.09629963,0.00005759199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01766054,0.000186625,0.8941211,0.0003291541,0.0001778429,0.0001633268,0.005650552,0.06916578,0.01254515],"genre_scores_gemma":[0.1935823,0.0004621365,0.7675967,0.0002620144,0.00006287697,0.0007770633,0.00898032,0.01858955,0.009687117],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03073642,"threshold_uncertainty_score":0.1028236,"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."}}