{"id":"W4408565479","doi":"10.1109/mra.2025.3527291","title":"Advancing Reproducibility, Benchmarks, and Education With Remote Sim2real: Remote Simulation to Real Robot Hardware","year":2025,"lang":"en","type":"article","venue":"IEEE Robotics & Automation Magazine","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reproducibility; Computer science; Robot; Embedded system; Computer hardware; Simulation; Artificial intelligence","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":[0.02692348,0.001580859,0.0009418036,0.001837035,0.001199062,0.005701188,0.00509357,0.00173516,0.008299338],"category_scores_gemma":[0.1266712,0.0008781792,0.0008252957,0.00123198,0.002564595,0.006979843,0.00730039,0.005474932,0.003321926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001795155,"about_ca_system_score_gemma":0.005574517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002913411,"about_ca_topic_score_gemma":0.003338406,"domain_scores_codex":[0.9791176,0.01111282,0.001064543,0.001615159,0.006156717,0.0009331544],"domain_scores_gemma":[0.8928556,0.04512686,0.003900932,0.03624123,0.01925943,0.002616039],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001348107,0.002621525,0.02818415,0.0005737271,0.0002126223,0.0002287088,0.002967986,0.1280632,0.02013934,0.1235792,0.03067258,0.6614088],"study_design_scores_gemma":[0.0003759757,0.001078811,0.004589913,0.0003391582,0.00009478784,0.0002566033,0.0009572036,0.7630923,0.08429807,0.1093069,0.03545265,0.0001575835],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08093385,0.0005115581,0.8588431,0.00353534,0.0004803826,0.0001974494,0.00021272,0.02606031,0.02922512],"genre_scores_gemma":[0.6570983,0.0002749575,0.3303968,0.0004592938,0.0001431916,0.0002592306,0.0005336694,0.00653649,0.004298101],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9730765,"threshold_uncertainty_score":0.1423867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03653637704208325,"score_gpt":0.3984336097792792,"score_spread":0.361897232737196,"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."}}