{"id":"W3187199493","doi":"10.1109/cec45853.2021.9504998","title":"Evolving Simple Solutions to the CIFAR-10 Benchmark using Tangled Program Graphs","year":2021,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Benchmark (surveying); Benchmarking; Genetic programming; Class (philosophy); Simplicity; Machine learning; Modularity (biology); Artificial intelligence; Cardinality (data modeling); Graph; Contextual image classification; Theoretical computer science; Data mining; Image (mathematics)","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":[0.0002012146,0.0001057463,0.00009197729,0.00005437702,0.0009255006,0.0002615622,0.0006214558,0.00003583779,0.0003547693],"category_scores_gemma":[0.00005044705,0.00008144576,0.00009188995,0.001554767,0.00003689726,0.0003047501,0.0003948368,0.00009663678,0.00009635719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005076269,"about_ca_system_score_gemma":0.0001694865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008500721,"about_ca_topic_score_gemma":0.0001204944,"domain_scores_codex":[0.9987962,0.00005202735,0.0001890449,0.0003734456,0.0002283053,0.0003609235],"domain_scores_gemma":[0.9987516,0.00008516145,0.0000383726,0.0007414822,0.0002647741,0.0001186474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001608873,0.0008012539,0.00059702,0.00001090622,0.00007246879,0.00001630637,0.0006038836,0.004575986,0.008533303,0.7602167,0.1250391,0.09953152],"study_design_scores_gemma":[0.0002026145,0.00006846469,0.008368938,0.00001703458,0.00002170157,0.0000928099,0.0003075559,0.6728507,0.001237347,0.03187203,0.2845617,0.0003991406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002767971,0.0003113934,0.9795537,0.007761526,0.000143352,0.0003883899,0.000006891645,0.0002875545,0.008779237],"genre_scores_gemma":[0.2665238,0.000009057716,0.7307652,0.0007890759,0.0001230353,0.0002014343,0.00002028994,0.000009596303,0.00155849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7283446,"threshold_uncertainty_score":0.7118296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0301849842186758,"score_gpt":0.2877595361043339,"score_spread":0.2575745518856581,"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."}}