{"id":"W3052028990","doi":"10.1109/iros45743.2020.9341677","title":"Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents","year":2020,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Science Foundation","keywords":"Benchmarking; Robotics; Computer science; Robot; Artificial intelligence; Autonomy; Software engineering; Software; Automation; Variance (accounting); Embedded system; Human–computer interaction; Machine learning; Systems engineering; Operating system; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04645076,0.001325792,0.001709096,0.002044524,0.0007807587,0.005580216,0.005121464,0.001793888,0.00315309],"category_scores_gemma":[0.07948799,0.00114531,0.001058007,0.001288682,0.002374278,0.004725899,0.005158977,0.002619742,0.001664016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002483364,"about_ca_system_score_gemma":0.003847707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00143725,"about_ca_topic_score_gemma":0.0009181949,"domain_scores_codex":[0.9503422,0.02466191,0.004813684,0.0047279,0.01360439,0.001849895],"domain_scores_gemma":[0.9382154,0.0173547,0.005247605,0.02211289,0.0151765,0.001892975],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001609981,0.00191019,0.01618434,0.00126698,0.0004786481,0.0005309679,0.002271695,0.216398,0.06239191,0.07385539,0.01405235,0.6090496],"study_design_scores_gemma":[0.0003964164,0.001742661,0.006763794,0.0003148109,0.0001647225,0.000325674,0.0003825728,0.7895026,0.1150414,0.04658124,0.03851034,0.0002737491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01401678,0.0001316569,0.966997,0.0002241118,0.00006360823,0.0009731359,0.0001014422,0.01515005,0.002342212],"genre_scores_gemma":[0.2552216,0.0001614236,0.736064,0.0002508372,0.00005658784,0.002311649,0.0008643157,0.003359168,0.001710389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9535493,"threshold_uncertainty_score":0.245658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6155147781886495,"score_gpt":0.4672346836766887,"score_spread":0.1482800945119608,"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."}}