{"id":"W4403434240","doi":"10.26434/chemrxiv-2024-rrbhc","title":"Composition and structure analyzer/featurizer for explainable machine-learning models to predict solid state structures","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Python (programming language); Computer science; Spectrum analyzer; Artificial intelligence; Computational science; Machine learning; Algorithm; Open source; Data mining; Software; Programming language","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008958844,0.0006692203,0.0007888314,0.000309547,0.0004242888,0.00134101,0.0008168797,0.0003540021,0.000342214],"category_scores_gemma":[0.0001510238,0.0005807398,0.0001404754,0.000210131,0.0001811778,0.0002118915,0.002119753,0.0009751971,0.00002962829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001506556,"about_ca_system_score_gemma":0.0001546823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001886283,"about_ca_topic_score_gemma":0.00001951467,"domain_scores_codex":[0.9962536,0.0001951186,0.0005973792,0.001628735,0.0005562994,0.0007689247],"domain_scores_gemma":[0.9983501,0.0001344597,0.000327522,0.0006673147,0.0002082566,0.000312342],"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":[0.000112951,0.00001028507,0.00007966853,0.001191808,0.00002856975,0.00001143705,0.001301205,0.3663711,0.6293737,0.0005410145,0.0007351422,0.0002430879],"study_design_scores_gemma":[0.0004032805,0.0001508896,0.000254899,0.0004860969,0.0001614081,0.00004321347,0.00005235737,0.3942518,0.4425151,0.1600292,0.0006439484,0.001007739],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714598,0.0007105392,0.02289769,0.0005015206,0.001932051,0.001269151,0.0005117824,0.0005215713,0.000195902],"genre_scores_gemma":[0.9527002,0.00003729074,0.0453755,0.0001894642,0.0004240995,0.0001822949,0.0002872283,0.0001142349,0.0006896956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1868586,"threshold_uncertainty_score":0.9996957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0183463639295776,"score_gpt":0.2740470386822784,"score_spread":0.2557006747527008,"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."}}