{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005473471,0.0004843828,0.0006320811,0.000517197,0.0006245312,0.0003794223,0.0008278656,0.0001559102,0.0001932338],"category_scores_gemma":[0.0002810377,0.0004867387,0.0002158281,0.001203114,0.00006739533,0.001243444,0.00007269212,0.0008448694,0.0001545695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003979575,"about_ca_system_score_gemma":0.0001389695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004462003,"about_ca_topic_score_gemma":0.001357254,"domain_scores_codex":[0.9949282,0.001500755,0.001222071,0.001111655,0.000739112,0.0004982062],"domain_scores_gemma":[0.9960313,0.001093387,0.0005072633,0.001060724,0.001106951,0.0002003898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007369122,0.01907697,0.001252579,0.0002376399,0.002850764,0.007749695,0.114945,0.5679182,0.1603372,0.002144781,0.001122858,0.1216274],"study_design_scores_gemma":[0.000552221,0.002294085,0.000005171701,0.000140197,0.00006746087,0.001814898,0.1033347,0.2261045,0.6629801,0.00008736001,0.002037169,0.0005821456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.325957,0.0003179556,0.6713002,0.0001415843,0.001258918,0.0006905709,0.00002259575,0.0001405825,0.0001706106],"genre_scores_gemma":[0.9958221,0.0001193361,0.001328279,0.00007389857,0.00008461688,0.0003940253,0.00002865523,0.00004977969,0.002099296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6699719,"threshold_uncertainty_score":0.9997584,"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."}}