{"id":"W4385989212","doi":"10.1016/j.mlwa.2023.100491","title":"A novel application of XAI in squinting models: A position paper","year":2023,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Mistake; Process (computing); Automation; Field (mathematics); Risk analysis (engineering); Data science; Operations research; Machine learning; Engineering; Business","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":[],"consensus_categories":[],"category_scores_codex":[0.0004555247,0.0001246518,0.0001503939,0.0003098037,0.0001871488,0.00005898743,0.0005150868,0.00005327142,0.000004645012],"category_scores_gemma":[0.00003724253,0.0001209056,0.00003503486,0.002385104,0.00004782135,0.000493432,0.0001493853,0.0002572557,0.0001057926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000530788,"about_ca_system_score_gemma":0.00004530785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009627969,"about_ca_topic_score_gemma":0.0003022374,"domain_scores_codex":[0.9986908,0.00004427915,0.000325313,0.0004239621,0.000242143,0.0002734888],"domain_scores_gemma":[0.9989852,0.0001521804,0.0001827712,0.0005009842,0.0001257049,0.00005316216],"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":[0.00001164029,0.0001634747,0.004242006,0.00004138443,0.00001051812,0.000001687686,0.001677616,0.4833764,0.04838508,0.410948,0.00001468353,0.0511275],"study_design_scores_gemma":[0.0001348552,0.00005106105,0.002226543,0.00002603453,0.000004859317,0.000008109327,0.0001586357,0.9812636,0.002315531,0.01198304,0.001684861,0.0001428347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01299036,0.00003656954,0.9826975,0.001598642,0.000009573721,0.0005395039,0.000002789919,0.0003736634,0.001751367],"genre_scores_gemma":[0.9512717,0.0000117085,0.04754071,0.0001054223,0.00002428894,0.0008541086,0.00004129184,0.00001914671,0.0001316154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9382814,"threshold_uncertainty_score":0.4930386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01903322690591561,"score_gpt":0.264956386830006,"score_spread":0.2459231599240904,"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."}}