{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002489073,0.0001161466,0.0001452794,0.00003150885,0.0001286833,0.000316251,0.0004374958,0.00003875506,0.0002394414],"category_scores_gemma":[0.0001150807,0.0001027584,0.00003628857,0.0003141179,0.00000904222,0.0001354341,0.0003585299,0.0001768264,0.000422027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000138791,"about_ca_system_score_gemma":0.00007544829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006638388,"about_ca_topic_score_gemma":0.00001688824,"domain_scores_codex":[0.9988114,0.00007004512,0.0001775675,0.000412244,0.0002506233,0.0002781167],"domain_scores_gemma":[0.9992297,0.00005313345,0.00003579612,0.0004411034,0.0001121274,0.000128114],"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":[0.000006588901,0.0004627462,0.0005633436,0.00004642924,0.00006537781,0.00007814837,0.001354355,0.003763575,0.05023924,0.03464733,0.003022728,0.9057502],"study_design_scores_gemma":[0.0004542547,0.0001470573,0.0002164818,0.00003942862,0.000006372219,0.00003368319,0.0000258452,0.9108215,0.0616972,0.001446528,0.02475508,0.000356583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02573893,0.00006417328,0.953275,0.01039104,0.0002284214,0.0002216981,0.000001082153,0.0003970819,0.009682554],"genre_scores_gemma":[0.05381778,0.000003889279,0.9255689,0.006074481,0.0003913664,0.00005120486,0.000007040753,0.00001598137,0.01406929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9070579,"threshold_uncertainty_score":0.5424444,"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."}}