{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005877828,0.0003914878,0.0003461869,0.0003390418,0.0002687665,0.0004079762,0.002268868,0.000261335,0.00001077955],"category_scores_gemma":[0.0004102101,0.0004408211,0.000123904,0.0007913611,0.00001922317,0.0002949009,0.002860646,0.0008968117,0.0002957119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004477342,"about_ca_system_score_gemma":0.0002036189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005935531,"about_ca_topic_score_gemma":0.00002368868,"domain_scores_codex":[0.9967949,0.00008453739,0.0005296206,0.001615413,0.0004362206,0.000539345],"domain_scores_gemma":[0.9975588,0.00004455333,0.0001970876,0.001631713,0.0002700305,0.0002978038],"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":[0.00009401554,0.0006291184,0.0103124,0.0006218681,0.0001425405,0.00003242039,0.08791854,0.1887682,0.2483413,0.01164112,0.007536042,0.4439624],"study_design_scores_gemma":[0.0000894438,0.0001126898,0.0006195897,0.0002208879,0.00001803459,0.000003526214,0.001326145,0.568535,0.3926718,0.002996672,0.03264619,0.000760032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06134612,0.00007766702,0.928758,0.004048569,0.001306098,0.00112135,0.000003259876,0.0007267799,0.002612132],"genre_scores_gemma":[0.9656919,0.00001737254,0.02554544,0.0007226889,0.0003772084,0.00128037,0.00002389298,0.00002620456,0.006314875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9043458,"threshold_uncertainty_score":0.9998044,"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."}}