{"id":"W3129917300","doi":"10.48550/arxiv.2102.07834","title":"One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Modular design; Machine learning; Artificial intelligence; Code (set theory); Set (abstract data type); Class (philosophy); Training set; Line (geometry); k-nearest neighbors algorithm; Soft computing; Data mining; Artificial neural network","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"],"consensus_categories":[],"category_scores_codex":[0.0003763015,0.0002811113,0.0003115583,0.0001569953,0.0002000496,0.0004593924,0.001716637,0.0002201431,0.00006393384],"category_scores_gemma":[0.0001422199,0.0003380639,0.0001024445,0.0005545848,0.0000367109,0.0003314226,0.002342025,0.0006889136,0.0002300867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000130058,"about_ca_system_score_gemma":0.0002402917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002770509,"about_ca_topic_score_gemma":0.00006854734,"domain_scores_codex":[0.997719,0.0002209648,0.000232599,0.001337758,0.0001469292,0.0003427363],"domain_scores_gemma":[0.9976321,0.00008186023,0.0002299569,0.001618182,0.0002271196,0.000210791],"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":[0.000123778,0.001503298,0.007793242,0.0006772507,0.0005656678,0.0005344066,0.003084035,0.6476696,0.01195212,0.2438543,0.001526822,0.08071552],"study_design_scores_gemma":[0.0003773228,0.0000714934,0.001025728,0.0001592062,0.00005464319,0.000004617791,0.00005921528,0.991116,0.001025551,0.002658994,0.00287667,0.000570533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1826639,0.00003660347,0.8136227,0.0009201349,0.0002803936,0.0004679307,0.00001302759,0.000339381,0.001655884],"genre_scores_gemma":[0.9385589,0.00005116437,0.05828725,0.0005873397,0.0001788013,0.00000797502,0.0001910645,0.00002436111,0.00211314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.755895,"threshold_uncertainty_score":0.9999071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1807184178787145,"score_gpt":0.2369790677369637,"score_spread":0.05626064985824922,"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."}}