{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005138495,0.001418697,0.001363683,0.002081189,0.0005566264,0.00273288,0.002836804,0.001963186,0.01240654],"category_scores_gemma":[0.02993492,0.0008719405,0.001706366,0.0008952031,0.001228538,0.003338355,0.003251799,0.003248174,0.003271794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001093608,"about_ca_system_score_gemma":0.002290945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001317453,"about_ca_topic_score_gemma":0.001223194,"domain_scores_codex":[0.9972691,0.001152565,0.0001421111,0.0003800189,0.0009345331,0.0001216435],"domain_scores_gemma":[0.9890215,0.00745992,0.0006270899,0.001892858,0.0008359735,0.0001627675],"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":[0.0007947109,0.0003470592,0.003478945,0.0004906884,0.0003869615,0.0004387731,0.00008515013,0.5007887,0.003502041,0.1846364,0.04187145,0.2631791],"study_design_scores_gemma":[0.00002349188,0.00003391631,0.0001297536,0.00001624272,0.00001533261,0.00006687093,0.000006629534,0.9305277,0.002308945,0.0649524,0.00190691,0.00001181364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004871241,0.0002806037,0.9821751,0.0007284019,0.00009510927,0.00008129604,0.001102216,0.008340497,0.002325528],"genre_scores_gemma":[0.4078665,0.0006090464,0.5774255,0.0009063344,0.0003541858,0.0005318095,0.003752094,0.003021488,0.005533024],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01240654,"threshold_uncertainty_score":0.04150397,"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."}}