{"id":"W3198189810","doi":"10.1145/3465407","title":"Learn, Generate, Rank, Explain: A Case Study of Visual Explanation by Generative Machine Learning","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Interactive Intelligent Systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Guelph; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Discriminative model; Computer science; Ranking (information retrieval); Machine learning; Rank (graph theory); Artificial intelligence; Generative model; Generative grammar; Conceptualization; Motion (physics); Information retrieval; Mathematics","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":[0.003464788,0.0009198722,0.000504404,0.0007638402,0.0006425437,0.001411755,0.002036132,0.002697903,0.004038528],"category_scores_gemma":[0.01429644,0.0003372872,0.0009777234,0.0006116425,0.001586821,0.002686606,0.001610423,0.001585592,0.0006964198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009977681,"about_ca_system_score_gemma":0.0005172254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004156398,"about_ca_topic_score_gemma":0.005278617,"domain_scores_codex":[0.99717,0.002052458,0.0000833401,0.0002722566,0.0002917707,0.00013022],"domain_scores_gemma":[0.9852948,0.01250408,0.0003453545,0.001322688,0.000290924,0.0002421245],"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":[0.002428154,0.002956614,0.05799549,0.002814416,0.0005576136,0.01906176,0.04299723,0.3496718,0.03878213,0.08414612,0.0255896,0.372999],"study_design_scores_gemma":[0.0003235196,0.00115406,0.006889231,0.0001384022,0.00009872918,0.004569336,0.005317683,0.894834,0.01930056,0.03032181,0.03692229,0.0001304318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6177064,0.001036385,0.3611968,0.003233358,0.00006683278,0.0008870729,0.001105812,0.004229132,0.01053818],"genre_scores_gemma":[0.8513134,0.000258029,0.1436717,0.0003030752,0.00002311726,0.0002068181,0.0006338111,0.0002581645,0.003331879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004156398,"threshold_uncertainty_score":0.01832378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0416245849989824,"score_gpt":0.3182963108914026,"score_spread":0.2766717258924202,"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."}}