{"id":"W4400936793","doi":"10.1007/s10044-024-01306-8","title":"Causal generative explainers using counterfactual inference: a case study on the Morpho-MNIST dataset","year":2024,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Counterfactual thinking; Artificial intelligence; Machine learning; Computer science; Generative grammar; Classifier (UML); Inference; Interpretability; MNIST database; Generative model; Pattern recognition (psychology); Artificial neural network; Psychology","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":[0.005819527,0.0006099246,0.0004878218,0.001817703,0.001319354,0.001833926,0.002479781,0.002133087,0.006571393],"category_scores_gemma":[0.03117621,0.0002906321,0.001114688,0.002433056,0.0009411998,0.002430055,0.001634446,0.002037756,0.001740565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001303673,"about_ca_system_score_gemma":0.001860777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01442643,"about_ca_topic_score_gemma":0.03884703,"domain_scores_codex":[0.9968492,0.001836395,0.0001787207,0.0005924218,0.0004283584,0.0001148221],"domain_scores_gemma":[0.963246,0.03037449,0.000684391,0.004733426,0.0007407501,0.0002209407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002785215,0.001002217,0.1972436,0.002906968,0.001603294,0.006136979,0.005643316,0.07769041,0.003166893,0.1589992,0.2246474,0.3181746],"study_design_scores_gemma":[0.0007775196,0.0001609348,0.05096548,0.0005641973,0.0005758218,0.00259257,0.003596399,0.3850351,0.008644795,0.2484445,0.2984959,0.000146851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6617953,0.004545226,0.1454066,0.01273011,0.0003918107,0.0005558731,0.1229341,0.008557064,0.043084],"genre_scores_gemma":[0.7646453,0.0006635061,0.1259212,0.0007712122,0.0001398615,0.0001968279,0.1013744,0.001145414,0.005142351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01442643,"threshold_uncertainty_score":0.03077698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08872213112094182,"score_gpt":0.3729687433924339,"score_spread":0.2842466122714921,"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."}}