{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.001694423,0.0003929056,0.0007671742,0.003103059,0.002928418,0.0001967178,0.002608505,0.0008517829,0.000002577104],"category_scores_gemma":[0.0002117401,0.0005089988,0.00005578818,0.004192253,0.01691444,0.0008760226,0.003948138,0.00112035,3.244332e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002388419,"about_ca_system_score_gemma":0.0007946618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003085109,"about_ca_topic_score_gemma":0.0001644367,"domain_scores_codex":[0.9965093,0.00003267542,0.0003795161,0.001678201,0.0007205516,0.0006797329],"domain_scores_gemma":[0.9970108,0.00006704805,0.0004900196,0.001077439,0.001187641,0.0001670514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003487707,0.0001541673,0.0485721,0.001144869,0.000594328,0.0004705064,0.011054,0.03557542,0.5551191,0.002440541,0.00006939845,0.3447707],"study_design_scores_gemma":[0.0003461472,0.00006956841,0.001009971,0.001307036,0.0003078269,0.0001389333,0.04942353,0.9434148,0.002842234,0.0002458415,0.0002771022,0.0006170024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825575,0.002459546,0.01265022,0.0005381034,0.0002450743,0.0001832126,0.00001373443,0.0005969153,0.0007557052],"genre_scores_gemma":[0.9768281,0.002520656,0.02054541,0.000009744155,0.00003066929,2.162285e-7,0.00001092472,0.00001754431,0.00003673892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9078394,"threshold_uncertainty_score":0.9997362,"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."}}