{"id":"W4392928048","doi":"10.32920/25417270.v1","title":"Information Theoretic Measures Applied to Deep Learning Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mutual information; Computer science; Maximization; Artificial intelligence; Deep learning; Machine learning; Architecture; Information theory; Interaction information; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002169985,0.0002400269,0.000194591,0.0002132222,0.0001146931,0.0004858032,0.00126318,0.000138333,0.000009411107],"category_scores_gemma":[0.00002126427,0.0002138445,0.00007296262,0.0004517238,0.00002535231,0.0003052803,0.003653825,0.0008023116,0.0009709594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000898732,"about_ca_system_score_gemma":0.00005647121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005530578,"about_ca_topic_score_gemma":0.00000396841,"domain_scores_codex":[0.9985863,0.00002896724,0.0003362866,0.000407728,0.0003709584,0.0002697677],"domain_scores_gemma":[0.9987478,0.00007810623,0.0001022196,0.0008419679,0.0001048516,0.0001251146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[9.769805e-7,0.00000198039,1.460329e-7,0.00001948036,0.000004775864,1.486507e-7,0.0006754762,0.45842,0.00001465091,0.4548818,0.0001633347,0.08581719],"study_design_scores_gemma":[0.00002027397,0.000005662103,0.000003164474,0.00001873923,0.000005332037,0.000001442377,0.00002485945,0.4916396,0.0001698871,0.5050791,0.002870821,0.000161088],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001900645,0.00009647752,0.9054222,0.001312909,0.0002460449,0.0006611435,0.000001216267,0.00113906,0.09093089],"genre_scores_gemma":[0.8245202,0.00005157315,0.1736113,0.0008469642,0.00008368688,0.0005784252,0.0000181271,0.00001801173,0.0002716889],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8243302,"threshold_uncertainty_score":0.9998069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02582926654290517,"score_gpt":0.2557815616739663,"score_spread":0.2299522951310611,"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."}}