{"id":"W4386465623","doi":"10.26434/chemrxiv-2023-zhlmr","title":"Global interpretability and geometry of graph convolu- tional neural networks for chemistry in terms of chemical moieties","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation; New Brunswick Innovation Foundation","keywords":"Embedding; Interpretability; Chemical space; Convolutional neural network; Artificial intelligence; Euclidean space; Computer science; Parametric statistics; Dimensionality reduction; Pattern recognition (psychology); Theoretical computer science; Algorithm; Mathematics; Chemistry; Combinatorics","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":[0.0006169542,0.0007656588,0.0004429027,0.0006671149,0.0003362795,0.001239817,0.000946194,0.0008849769,0.002798237],"category_scores_gemma":[0.003432756,0.0004094861,0.0006960548,0.0002880484,0.001949347,0.002128768,0.00108244,0.002052313,0.0004147033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001556408,"about_ca_system_score_gemma":0.0005084385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002097608,"about_ca_topic_score_gemma":0.002277695,"domain_scores_codex":[0.9995731,0.0001529702,0.00001437797,0.0001184369,0.0000923998,0.00004876754],"domain_scores_gemma":[0.9989918,0.0004969154,0.0001371267,0.0001835749,0.0001146025,0.00007606598],"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":[0.0002726035,0.00007469492,0.003537717,0.0001372285,0.00006515428,0.0002412115,0.0003500555,0.568326,0.01703859,0.3647357,0.002500876,0.04272023],"study_design_scores_gemma":[0.000009448932,0.00004032011,0.001207337,0.00001212466,0.000007503088,0.00004224722,0.00003413006,0.829048,0.002118356,0.1667091,0.0007571884,0.00001424068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3581554,0.0008592209,0.6267385,0.002374336,0.00008202259,0.00005470911,0.0006999311,0.0008026414,0.01023323],"genre_scores_gemma":[0.9527168,0.000328138,0.04319931,0.0001942246,0.00004080285,0.00004301829,0.000498065,0.0001658317,0.002814036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002798237,"threshold_uncertainty_score":0.01129264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01566286879365314,"score_gpt":0.2796967816402281,"score_spread":0.264033912846575,"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."}}