{"id":"W4400064756","doi":"10.48550/arxiv.2406.17197","title":"Machine learning the screening factor in the soft bond valence approach for rapid crystal structure estimation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; JST-Mirai Program; National University of Singapore","keywords":"Valence (chemistry); Crystal structure; Bond; Computer science; Artificial intelligence; Materials science; Machine learning; Crystallography; Chemistry; Business; Organic chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00182797,0.0004341751,0.0003743904,0.0002004356,0.0005824306,0.0006621502,0.00217375,0.0002638368,0.0002412477],"category_scores_gemma":[0.0004908844,0.0002942561,0.0001764654,0.0005180996,0.0003389585,0.0002422785,0.001367093,0.001404179,0.00002530619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001219894,"about_ca_system_score_gemma":0.0001387333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003497639,"about_ca_topic_score_gemma":0.00004075796,"domain_scores_codex":[0.9969624,0.0006491809,0.0003427904,0.001229317,0.0002829907,0.0005333493],"domain_scores_gemma":[0.998064,0.0005765979,0.0003951245,0.0008061074,0.00008902173,0.00006908321],"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":[0.00006808842,0.00002262964,0.0008258338,0.0003870093,0.00001268898,0.00001955139,0.001447811,0.9800329,0.01210288,0.004648689,0.00008799707,0.000343977],"study_design_scores_gemma":[0.0002477472,0.00005911675,0.0007685134,0.0001214245,0.00007677048,0.00001525106,0.0004306236,0.9834033,0.0007337333,0.01343267,0.0003404524,0.0003704038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5993814,0.0002053255,0.3976489,0.0002160813,0.0006326678,0.001039793,0.0003254396,0.0001998473,0.0003505554],"genre_scores_gemma":[0.9865857,0.00002081891,0.01259538,0.00009128762,0.0001594247,0.0000100997,0.0001230005,0.00004007887,0.0003742339],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3872043,"threshold_uncertainty_score":0.9999509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05023243074571469,"score_gpt":0.2150479507983253,"score_spread":0.1648155200526107,"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."}}