{"id":"W4310375416","doi":"10.1007/s10710-022-09446-8","title":"Benchmarking ensemble genetic programming with a linked list external memory on scalable partially observable tasks","year":2022,"lang":"en","type":"article","venue":"Genetic Programming and Evolvable Machines","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Benchmarking; Computer science; Observable; Scalability; Operator (biology); State (computer science); Artificial intelligence; Machine learning; Set (abstract data type); Genetic programming; Identification (biology); Algorithm; Programming language","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0004619856,0.0003705168,0.0003184948,0.0001568171,0.001884423,0.0005734068,0.000848807,0.00006448429,0.00005732875],"category_scores_gemma":[0.00001433569,0.0003361623,0.00008759641,0.0008304466,0.0001279307,0.0002134216,0.0006337926,0.0004023066,0.00001069304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000090145,"about_ca_system_score_gemma":0.0001785192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009445468,"about_ca_topic_score_gemma":0.0001194456,"domain_scores_codex":[0.9969292,0.0001431412,0.0004298603,0.00098861,0.0006577041,0.0008514999],"domain_scores_gemma":[0.9985533,0.00009954916,0.0002069355,0.0007718738,0.0001068636,0.000261452],"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":[0.00004835029,0.0005250722,0.01854971,0.00008175883,0.00005568456,0.00008989003,0.0006261377,0.0403939,0.0006941429,0.001216159,0.0003438878,0.9373753],"study_design_scores_gemma":[0.001521299,0.002350619,0.03743979,0.000147843,0.00009265461,0.0006914349,0.0002046331,0.8825511,0.0002130307,0.003211925,0.07045731,0.001118413],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.490301,0.005882849,0.4993023,0.001106118,0.000479225,0.001590454,0.00001326472,0.0006922923,0.0006325081],"genre_scores_gemma":[0.4779515,0.00004404868,0.5196529,0.000196627,0.0002238257,0.001019737,0.000017494,0.00003449019,0.0008594118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9362569,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01327335965430916,"score_gpt":0.2288545776728534,"score_spread":0.2155812180185442,"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."}}