{"id":"W2986899672","doi":"10.1107/s2052520619013040","title":"Automated oxidation-state assignment for metal sites in coordination complexes in the Cambridge Structural Database","year":2019,"lang":"en","type":"article","venue":"Acta Crystallographica Section B Structural Science Crystal Engineering and Materials","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Cambridge Crystallographic Data Centre; Engineering and Physical Sciences Research Council; McMaster University","keywords":"Scripting language; Workflow; Python (programming language); Computer science; Database; Oxidation state; Valence (chemistry); State (computer science); Data mining; Chemistry; Programming language; Metal","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":[],"consensus_categories":[],"category_scores_codex":[0.002812482,0.0003307909,0.0003940196,0.0006003066,0.0003425704,0.0008162339,0.0006470747,0.00008015456,0.0001084218],"category_scores_gemma":[0.0003067558,0.0002444185,0.00004454045,0.001115618,0.0003594215,0.001492496,0.0001804786,0.0001556676,9.935528e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000119824,"about_ca_system_score_gemma":0.00006162887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005733944,"about_ca_topic_score_gemma":0.00008787931,"domain_scores_codex":[0.997123,0.0001865672,0.0006172589,0.0007604032,0.0006133811,0.0006993946],"domain_scores_gemma":[0.998947,0.000248881,0.0002500831,0.0003565661,0.00009929362,0.00009821607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005089436,0.000008406148,0.001331707,0.0001101126,0.000002966683,0.000002143789,0.0003183059,0.01034125,0.9872681,0.0005320146,0.00001645374,0.00001766728],"study_design_scores_gemma":[0.002318603,0.0005125674,0.4731988,0.0001928358,0.00003171829,0.0002521866,0.0006689634,0.2614492,0.2586572,0.0007535891,0.0006914559,0.001272945],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996541,0.00001910967,0.0004628355,0.0002183293,0.001310147,0.001046066,0.0001466053,0.0002392426,0.00001661922],"genre_scores_gemma":[0.9972051,0.000005305404,0.002442055,0.00004793206,0.0000749844,0.00009499988,0.00009582094,0.0000205727,0.00001327188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7286109,"threshold_uncertainty_score":0.9967098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00819728652259349,"score_gpt":0.2488270515487404,"score_spread":0.2406297650261469,"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."}}