{"id":"W1978144947","doi":"10.3390/molecules171214937","title":"QSPR Models for Predicting Log Pliver Values for Volatile Organic Compounds Combining Statistical Methods and Domain Knowledge","year":2012,"lang":"en","type":"article","venue":"Molecules","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Universidad Nacional del Sur; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Quantitative structure–activity relationship; Applicability domain; Artificial neural network; Computer science; Selection (genetic algorithm); Set (abstract data type); Partition (number theory); Artificial intelligence; Feature selection; Machine learning; Linear regression; Test set; Property (philosophy); Regression; Data mining; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001263985,0.0001713811,0.0002347145,0.00004436436,0.00009428262,0.00002135572,0.0001091744,0.0001290888,0.000004692369],"category_scores_gemma":[0.0002363971,0.0001696304,0.0000349619,0.00006597725,0.00009877743,0.0001320976,0.00007348379,0.000126959,0.000001307331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006214759,"about_ca_system_score_gemma":0.000002692333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.906979e-7,"about_ca_topic_score_gemma":8.225846e-7,"domain_scores_codex":[0.9991551,0.00001984647,0.0001929837,0.0001749124,0.00005457317,0.0004025869],"domain_scores_gemma":[0.9987633,0.0009527139,0.00002851306,0.0001415797,0.00003723193,0.00007665033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003017168,0.00005452089,0.000283432,0.0003721972,0.0001054358,6.707245e-7,0.001014428,0.00387287,0.9419692,0.03672377,0.001172436,0.01440092],"study_design_scores_gemma":[0.0005807909,0.00006154853,0.00007228909,0.0000341598,0.00004716969,0.000005539323,0.0003291848,0.5236945,0.3293991,0.1441445,0.001352563,0.0002787292],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1916533,0.001371942,0.8056034,0.00001539223,0.00009776969,0.0002499815,0.00005750125,0.0005145604,0.0004361298],"genre_scores_gemma":[0.5577578,0.00001035989,0.442067,0.000006335348,0.00003513032,0.00005601497,0.00001547914,0.00003863883,0.00001325504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.61257,"threshold_uncertainty_score":0.6917325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02445868235107477,"score_gpt":0.3104669770137137,"score_spread":0.2860082946626389,"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."}}