{"id":"W2963384642","doi":"","title":"Learning what you can do before doing anything","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Action (physics); Computer science; Composability; Artificial intelligence; Space (punctuation); Machine learning; Supervised learning; Plan (archaeology); Human–computer interaction; Artificial neural network; Distributed computing","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":[],"consensus_categories":[],"category_scores_codex":[0.0004652947,0.0007782065,0.0003072863,0.0003561158,0.0002712891,0.0006847265,0.0007231878,0.0006968696,0.005418241],"category_scores_gemma":[0.003145668,0.0002784254,0.0005323206,0.0003015409,0.0008629095,0.002121151,0.0006920854,0.001530879,0.001843542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005218892,"about_ca_system_score_gemma":0.0007362699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003431104,"about_ca_topic_score_gemma":0.006449813,"domain_scores_codex":[0.9996214,0.0001108038,0.00001160738,0.0001776855,0.00004879623,0.00002985768],"domain_scores_gemma":[0.9992629,0.0003273626,0.0001038886,0.0001537904,0.000082633,0.00006945487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004444173,0.0004076351,0.0169315,0.0005480342,0.0002026122,0.0002335322,0.0004089243,0.2426125,0.009241615,0.06942435,0.03938966,0.6201552],"study_design_scores_gemma":[0.00002298143,0.0001455475,0.003953969,0.0001079685,0.00004065971,0.000103565,0.0001646319,0.8344598,0.005658678,0.1391563,0.0161524,0.00003342127],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06741302,0.0007940944,0.9077442,0.003676362,0.0002943492,0.0001325818,0.001565637,0.002696374,0.01568351],"genre_scores_gemma":[0.7736279,0.00115112,0.2061831,0.0007718094,0.0001251595,0.0002167112,0.002810752,0.0002550841,0.01485842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005418241,"threshold_uncertainty_score":0.01812583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04364345204537157,"score_gpt":0.1868279278435497,"score_spread":0.1431844757981782,"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."}}