{"id":"W2981479926","doi":"10.1145/3359566.3360070","title":"On Learning Symmetric Locomotion","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Symmetry (geometry); Computer science; Motion (physics); Function (biology); Artificial intelligence; Mathematics; Geometry","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008126724,0.00003719638,0.00003767942,0.000149321,0.00004245732,0.00006587515,0.0001094188,0.00001997037,0.0005951054],"category_scores_gemma":[0.00001215333,0.0000316939,0.00002291709,0.0002567781,0.000002091532,0.0002421342,0.00001672564,0.00008180452,0.009047588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001430864,"about_ca_system_score_gemma":0.000005247952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003132787,"about_ca_topic_score_gemma":3.102245e-7,"domain_scores_codex":[0.9996035,0.0000237099,0.00005502921,0.0001321458,0.0001078595,0.00007776153],"domain_scores_gemma":[0.999776,0.000046126,0.00002317444,0.0001101654,0.00002193258,0.00002259514],"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":[0.000002203735,0.00007720934,0.0007502353,0.000007831876,0.000006234894,0.000002236626,0.00007953923,0.0005788324,0.0009913523,0.6495791,0.002044215,0.345881],"study_design_scores_gemma":[0.002712693,0.002623254,0.044804,0.0001368972,0.00001077202,0.00004995304,0.000142584,0.6650162,0.06781901,0.1114868,0.104024,0.001173688],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3210574,0.000004240189,0.2543532,0.0003001324,0.0003832014,0.00009296941,5.062952e-8,0.0002979674,0.4235108],"genre_scores_gemma":[0.9896126,0.000002282631,0.0008579257,0.0003621698,0.00002118073,0.000001549631,0.000001283154,0.00000217248,0.009138814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6685552,"threshold_uncertainty_score":0.991724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009053006713402109,"score_gpt":0.2160538452589649,"score_spread":0.2070008385455628,"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."}}