{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002425433,0.000956585,0.000662299,0.0005807566,0.0002969308,0.0007377793,0.002214603,0.0006562502,0.00217019],"category_scores_gemma":[0.01093302,0.000414452,0.0004119472,0.0002073725,0.001104149,0.001366135,0.001417345,0.001007188,0.0004459913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005138659,"about_ca_system_score_gemma":0.0009568585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001985291,"about_ca_topic_score_gemma":0.001607455,"domain_scores_codex":[0.9974533,0.0008491152,0.000201294,0.0005075724,0.000798632,0.0001899908],"domain_scores_gemma":[0.9898486,0.005481316,0.001164699,0.001787852,0.001188963,0.0005286824],"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":[0.001451851,0.001932844,0.03027948,0.000423671,0.0002263513,0.0009629902,0.0009973258,0.2215797,0.2920063,0.01313835,0.001723924,0.4352772],"study_design_scores_gemma":[0.00008171378,0.001032914,0.003133103,0.00001938826,0.00003697534,0.0002703854,0.00005634626,0.9141359,0.07660203,0.003203175,0.001378571,0.00004946318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2736585,0.00006824756,0.7179497,0.0001469943,0.00004006454,0.0003110703,0.00006516738,0.005365798,0.002394578],"genre_scores_gemma":[0.766764,0.00003160483,0.2313702,0.00008072385,0.000009427171,0.0002064533,0.00007477493,0.0002018625,0.00126096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002425433,"threshold_uncertainty_score":0.01282704,"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."}}