{"id":"W3093041308","doi":"","title":"Training Data Generating Networks: Linking 3D Shapes and Few-Shot Classification","year":2021,"lang":"en","type":"preprint","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Representation (politics); Artificial intelligence; Active shape model; Set (abstract data type); Training set; Machine learning; Shape analysis (program analysis); One shot; Shot (pellet); Pattern recognition (psychology)","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":[0.001902317,0.001604189,0.001306352,0.001494766,0.0007354211,0.001626348,0.004711781,0.003610997,0.002419728],"category_scores_gemma":[0.008792925,0.00101119,0.001428785,0.001179371,0.001717089,0.003547798,0.002832283,0.002938292,0.001207696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001507037,"about_ca_system_score_gemma":0.0007634432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004553523,"about_ca_topic_score_gemma":0.006149814,"domain_scores_codex":[0.9986855,0.0003485997,0.00005049607,0.0005210756,0.0002712689,0.0001229941],"domain_scores_gemma":[0.9959268,0.001889657,0.0003015077,0.001117066,0.0005661529,0.0001987024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002465219,0.000345038,0.004781395,0.0002093978,0.0001488975,0.0002930686,0.0003070185,0.550885,0.01350286,0.01664649,0.006103081,0.4065313],"study_design_scores_gemma":[0.000004497231,0.00002687713,0.0002024042,0.00001125517,0.000007841066,0.00004191674,0.00001751167,0.9837993,0.002894975,0.01239222,0.000592303,0.000008803907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0338257,0.0003693147,0.961152,0.0003850709,0.00007542368,0.00009592297,0.0003042913,0.002095935,0.001696242],"genre_scores_gemma":[0.5556644,0.000354119,0.4346622,0.0006164635,0.0001247503,0.0003255658,0.003001281,0.0005063395,0.004744896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004711781,"threshold_uncertainty_score":0.01093441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03235116120963998,"score_gpt":0.2147092888084484,"score_spread":0.1823581275988084,"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."}}