{"id":"W7115607610","doi":"","title":"Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Robotic Path Planning Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Benchmarking; Mobile robot; Robotics; Robot; Modular design; Python (programming language); Implementation; Obstacle","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001186692,0.0005237939,0.0005342252,0.000379358,0.0009326694,0.0005456838,0.0007971836,0.0003764181,0.00001443657],"category_scores_gemma":[0.0002379344,0.0006009886,0.0001740068,0.001051771,0.0001697644,0.001018507,0.000338443,0.0004462547,0.000026392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002562637,"about_ca_system_score_gemma":0.0003537803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001280819,"about_ca_topic_score_gemma":0.000005317678,"domain_scores_codex":[0.996162,0.0002030084,0.0009174292,0.001419211,0.0004640411,0.0008343049],"domain_scores_gemma":[0.9972249,0.0007448361,0.0005027293,0.0009674712,0.0003538261,0.0002062886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006559309,0.0002809591,0.4350419,0.0007156799,0.0001458948,0.00004641926,0.001757489,0.4308873,0.002452544,0.001805855,0.001101553,0.1256988],"study_design_scores_gemma":[0.001024067,0.0002902367,0.2529474,0.000836978,0.00009582944,0.000008000215,0.00004809988,0.741762,0.001338746,0.0006490421,0.0005712243,0.0004283125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.335666,0.0009053583,0.6585806,0.0007904269,0.002571482,0.001181734,0.00001401925,0.0001463469,0.0001440444],"genre_scores_gemma":[0.9042796,0.00002026056,0.09407402,0.0006091068,0.0003191907,0.0002377658,0.0001558187,0.00003303844,0.000271212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5686136,"threshold_uncertainty_score":0.9996442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03979216649602045,"score_gpt":0.3016447239538219,"score_spread":0.2618525574578014,"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."}}