{"id":"W2197326744","doi":"10.1017/s0269888910000354","title":"Robotics competitions as benchmarks for AI research","year":2011,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Robotics; Benchmark (surveying); Artificial intelligence; Computer science; Applications of artificial intelligence; Robot","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":[0.001883791,0.0001587589,0.0002392108,0.0001046274,0.0002326873,0.00007228665,0.001574926,0.00004819043,0.0001021167],"category_scores_gemma":[0.0006741792,0.0001182149,0.0001196599,0.0006996104,0.00005850954,0.0001781705,0.0003754309,0.0004430115,0.0004887831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006536955,"about_ca_system_score_gemma":0.00009518593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003649979,"about_ca_topic_score_gemma":9.115319e-7,"domain_scores_codex":[0.9986507,0.0001045652,0.0003171384,0.0002431092,0.000237343,0.0004470865],"domain_scores_gemma":[0.9980001,0.0005523476,0.00005118678,0.0009510533,0.0003458033,0.00009950138],"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":[0.000001169937,0.00004914116,0.0000100854,0.002300092,0.00004583272,0.00000334269,0.0009280858,0.0502697,0.00002364307,0.9254194,0.01521416,0.005735372],"study_design_scores_gemma":[0.0001683876,0.0001895056,0.0001074867,0.003651814,0.00004655369,0.00003595408,0.00001025351,0.5905299,0.0001291682,0.001893689,0.402916,0.0003212838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000004729257,0.027464,0.9506235,0.001260811,0.00053445,0.0007819554,6.369146e-7,0.0001599061,0.01917],"genre_scores_gemma":[0.1588029,0.08110286,0.7326562,0.003158629,0.001713633,0.00222928,0.00009030831,0.0003182791,0.0199279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9235257,"threshold_uncertainty_score":0.6282481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1069341295820813,"score_gpt":0.3609366505106727,"score_spread":0.2540025209285914,"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."}}