{"id":"W4408012843","doi":"10.1007/978-981-96-0077-9_5","title":"Evolving Many-Model Agents with Vector and Matrix Operations in Tangled Program Graphs","year":2025,"lang":"en","type":"book-chapter","venue":"Genetic and evolutionary computation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Matrix (chemical analysis); Vector (molecular biology); Computer science; Mathematics; Biology; Materials science; Genetics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007849006,0.0002553466,0.0002248686,0.0003517859,0.0002075652,0.0001728829,0.0001899785,0.0001495531,0.000008494327],"category_scores_gemma":[0.00001192839,0.0002576516,0.00003272882,0.0001255271,0.00009099217,0.0002135023,0.0002029429,0.0002117558,0.000005224015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001007238,"about_ca_system_score_gemma":0.0001980595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001241123,"about_ca_topic_score_gemma":0.00001173641,"domain_scores_codex":[0.9986487,0.00002707722,0.0003325976,0.0004939462,0.00029268,0.0002049664],"domain_scores_gemma":[0.9994168,0.00006080854,0.0001032014,0.0002082864,0.0001408358,0.00007009314],"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":[0.000006434852,0.00001579372,0.0004474648,0.00006588725,0.00003675857,0.00001053382,0.0001765307,0.943974,0.000001932448,0.04686469,0.0006642644,0.007735678],"study_design_scores_gemma":[0.0003986685,0.0001712361,0.01846027,0.0002008357,0.00003399787,0.00002450147,0.000006016594,0.9717559,2.09907e-7,0.00838914,0.0003040994,0.0002550867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001109204,0.001516664,0.9845021,0.0001906451,0.0001195006,0.0008117981,0.00000504155,0.0001331672,0.0116119],"genre_scores_gemma":[0.2179898,0.0006009319,0.7206598,0.0001253669,0.00005012479,0.00008449049,0.000172209,0.00003829187,0.06027896],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2638423,"threshold_uncertainty_score":0.9999875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01344726544251667,"score_gpt":0.2528431059099153,"score_spread":0.2393958404673986,"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."}}