{"id":"W3199885714","doi":"10.1109/ijcnn52387.2021.9534284","title":"One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Shot (pellet); Computer science; Line (geometry); Artificial intelligence; Mathematics; Materials science","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":[0.002870914,0.001174381,0.001497859,0.001110046,0.001831099,0.003068908,0.00478882,0.003123398,0.005748712],"category_scores_gemma":[0.02432053,0.0007946073,0.000923734,0.001198385,0.002641365,0.006241564,0.003538263,0.003801073,0.005830368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007420665,"about_ca_system_score_gemma":0.00131518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002315278,"about_ca_topic_score_gemma":0.005347008,"domain_scores_codex":[0.9965066,0.0008751086,0.0002134842,0.001296125,0.0009344156,0.0001742032],"domain_scores_gemma":[0.9874603,0.003643058,0.0009706307,0.005123784,0.002239718,0.0005625259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008774961,0.0004642179,0.009360421,0.0006502913,0.0001847786,0.0005529814,0.001249482,0.03531835,0.02839085,0.04987407,0.03791399,0.8351631],"study_design_scores_gemma":[0.000189942,0.0006184197,0.002151472,0.0003462902,0.00009155129,0.001442261,0.0009262469,0.7406179,0.05582185,0.147738,0.04980509,0.0002509388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03658558,0.0003710706,0.9491925,0.001307135,0.0004100638,0.0004745534,0.0004970704,0.00578814,0.005373908],"genre_scores_gemma":[0.1745655,0.0002131177,0.8139655,0.001371473,0.0001201051,0.0004384174,0.001425008,0.0009212535,0.006979613],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005748712,"threshold_uncertainty_score":0.01923138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05844571377374178,"score_gpt":0.2997609432157832,"score_spread":0.2413152294420415,"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."}}