{"id":"W4293676943","doi":"10.3389/frobt.2022.951663","title":"Making Bipedal Robot Experiments Reproducible and Comparable: The Eurobench Software Approach","year":2022,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","topic":"Prosthetics and Rehabilitation Robotics","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Horizon 2020 Framework Programme; European Commission","keywords":"Computer science; Benchmarking; Executable; Benchmark (surveying); Software; Metric (unit); Documentation; Process (computing); Software engineering; Consistency (knowledge bases); Protocol (science); Standardization; Machine learning; Data mining; Artificial intelligence; Programming language; Operating system","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":[0.0003035208,0.0001426814,0.0001910366,0.0001021592,0.000296807,0.00007423021,0.000154621,0.00003641566,0.000005970529],"category_scores_gemma":[0.00002131066,0.0001222954,0.00002525218,0.0002421488,0.00009775897,0.00005684885,0.0001736469,0.000327857,3.279669e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004791978,"about_ca_system_score_gemma":0.00001411719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004003694,"about_ca_topic_score_gemma":5.522185e-7,"domain_scores_codex":[0.9990289,0.00005398359,0.0002200375,0.0002881035,0.0001686639,0.0002403169],"domain_scores_gemma":[0.9995956,0.00002872245,0.00003107149,0.0002832796,0.00001801485,0.00004330333],"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":[0.000005093203,0.00004313196,0.01210405,0.00005378886,0.00001819884,0.000002540141,0.001073589,0.9797909,0.00004896838,0.0006775292,0.004240684,0.001941521],"study_design_scores_gemma":[0.0005005264,0.00007488908,0.005454078,0.00002199134,0.00001655614,0.0000254478,0.002190225,0.9827032,0.00005221069,0.002204664,0.006448725,0.0003074993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04240008,0.02583806,0.9236043,0.001706601,0.003681144,0.001026988,0.00003007052,0.0002578705,0.001454906],"genre_scores_gemma":[0.8515613,0.0002011588,0.1476949,0.0002055116,0.00004132684,0.00004810169,0.00001138321,0.0000383866,0.000197979],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8091612,"threshold_uncertainty_score":0.498706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02169815831347332,"score_gpt":0.2459880041892696,"score_spread":0.2242898458757963,"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."}}