{"id":"W4405880184","doi":"10.1007/s10619-024-07450-8","title":"Infomod: information-theoretic machine learning model diagnostics","year":2024,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Automatic summarization; Computer science; SPARK (programming language); Debugging; Process (computing); Machine learning; Artificial intelligence; Ranging; Test data; Data mining; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0002694633,0.0001987752,0.0001666944,0.0001236965,0.0002813168,0.0004747036,0.0004025266,0.00004753653,0.00002794412],"category_scores_gemma":[0.0007550444,0.0001761761,0.00004511146,0.0003575732,0.00008458475,0.002115711,0.0005146616,0.0004287251,0.00007791847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002517028,"about_ca_system_score_gemma":0.00008031782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006155226,"about_ca_topic_score_gemma":0.000005829277,"domain_scores_codex":[0.9988517,0.00006975053,0.0002718606,0.0002767256,0.0002417773,0.0002881825],"domain_scores_gemma":[0.9988809,0.0005503302,0.000062368,0.0003327411,0.00005259276,0.0001210428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009948129,0.0000165696,0.001823083,0.000129314,0.00002995886,0.00004264705,0.0005468507,0.3896468,0.000005303645,0.5937361,0.003116011,0.01089747],"study_design_scores_gemma":[0.0001910817,0.00002245593,0.0001576317,0.00007584573,0.00001919463,0.00002769026,0.00003772495,0.9483078,0.00001393846,0.0035454,0.04738162,0.000219679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001533345,0.001474095,0.9942979,0.0006037758,0.0001969384,0.0001084864,0.0008159112,0.0005072372,0.0004623013],"genre_scores_gemma":[0.921962,0.001793106,0.06916732,0.000313899,0.00008437326,0.00002952981,0.006547315,0.00001758493,0.00008489645],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9251306,"threshold_uncertainty_score":0.7184252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01595322642870192,"score_gpt":0.2595854938904334,"score_spread":0.2436322674617315,"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."}}