{"id":"W2055622634","doi":"10.1109/cig.2009.5286455","title":"Improving testing of multi-unit computer players for unwanted behavior using coordination macros","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Macro; Computer science; Unit testing; Competition (biology); Strengths and weaknesses; Limit (mathematics); Resource (disambiguation); Software; Operating system; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002650835,0.0001324984,0.0001620031,0.0001443356,0.0001587195,0.000124089,0.0004554487,0.00006043824,0.000002966992],"category_scores_gemma":[0.0001271542,0.0001307354,0.00005551875,0.0003545227,0.00002646194,0.0004389715,0.0001110048,0.00009385013,0.000001888824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004930158,"about_ca_system_score_gemma":0.00005831514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003788487,"about_ca_topic_score_gemma":0.000001244163,"domain_scores_codex":[0.9988858,0.00002313807,0.0003561294,0.0002544702,0.0002037139,0.0002768131],"domain_scores_gemma":[0.9989172,0.0001673269,0.000269813,0.0002812109,0.0003130134,0.00005149106],"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":[0.000005224498,0.00007766494,0.005206067,0.0000331579,0.000009516209,0.000003380515,0.0002342747,0.7705587,0.1099291,0.002032278,0.00002693787,0.1118837],"study_design_scores_gemma":[0.0006561194,0.000256076,0.004686181,0.00003387524,0.00001471433,0.000008253082,0.00001719976,0.9794977,0.01464999,0.000009855225,0.00001792484,0.0001520984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05262708,0.00000379474,0.9464927,0.00003406532,0.0001809256,0.0004239139,0.000001086123,0.0001654498,0.00007103369],"genre_scores_gemma":[0.4659548,6.665537e-8,0.5338192,0.00007024482,0.00002084544,0.000002891519,0.000002325287,0.000005441058,0.0001241358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4133278,"threshold_uncertainty_score":0.5331235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07838992345998244,"score_gpt":0.3182366372027885,"score_spread":0.2398467137428061,"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."}}