{"id":"W4410478524","doi":"10.26434/chemrxiv-2024-bpd53-v3","title":"Leveraging our Teacher’s Experience to Improve Machine Learning: Application to pKa Prediction","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; Compute Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Mathematics education; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001978373,0.0008319272,0.0005214474,0.0004553285,0.0003862305,0.0009839198,0.001124132,0.001064736,0.002488808],"category_scores_gemma":[0.01193105,0.0002651997,0.0003925566,0.0005332927,0.0006777204,0.001740985,0.001456977,0.001785574,0.0009520444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005611797,"about_ca_system_score_gemma":0.0008217981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002000044,"about_ca_topic_score_gemma":0.002139002,"domain_scores_codex":[0.9993464,0.0002898792,0.00002599465,0.0001660979,0.0001253714,0.00004632285],"domain_scores_gemma":[0.9953324,0.002954743,0.000271335,0.0005658596,0.0006315122,0.0002441737],"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":[0.0005947084,0.001443654,0.03507283,0.00081777,0.0001367304,0.0006847173,0.001659321,0.1801595,0.03335895,0.01435405,0.01427654,0.7174412],"study_design_scores_gemma":[0.0001248657,0.000900354,0.003934409,0.00009157811,0.00009156579,0.0003560981,0.0002462014,0.897684,0.05619334,0.0169645,0.02332352,0.00008956435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.344587,0.003240293,0.6197619,0.007516001,0.0004995602,0.0001843913,0.0004223594,0.005955436,0.01783298],"genre_scores_gemma":[0.8072149,0.001220396,0.1860016,0.0004683491,0.0001567777,0.00008338629,0.000296166,0.0002415897,0.004316772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002488808,"threshold_uncertainty_score":0.01046276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03205546262022915,"score_gpt":0.3048258779332454,"score_spread":0.2727704153130163,"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."}}