{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003342869,0.001225827,0.00160896,0.001188149,0.002035065,0.003441451,0.00494249,0.003490995,0.00536308],"category_scores_gemma":[0.02889441,0.0008453481,0.0009724559,0.001376089,0.003153845,0.007208901,0.003873354,0.004431303,0.005736423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007808967,"about_ca_system_score_gemma":0.001417461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002167689,"about_ca_topic_score_gemma":0.004960882,"domain_scores_codex":[0.9958743,0.001082509,0.0002489613,0.001508663,0.00109877,0.0001867841],"domain_scores_gemma":[0.9841712,0.004740925,0.001259338,0.006451662,0.0026842,0.0006926417],"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":[0.0009793668,0.00048871,0.01077399,0.000752689,0.0002074387,0.0005421446,0.001370811,0.03217468,0.02835597,0.06283909,0.04364975,0.8178654],"study_design_scores_gemma":[0.0002229047,0.0007326509,0.002620516,0.000426987,0.0001089924,0.001622439,0.001102893,0.6683726,0.06035958,0.202423,0.06171166,0.0002958183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03609392,0.0004303425,0.9496985,0.001728682,0.0004807456,0.0004391654,0.0005279099,0.005053921,0.005546884],"genre_scores_gemma":[0.1775378,0.0002750399,0.8100706,0.001682641,0.0001678964,0.0004690741,0.001480201,0.0009610618,0.007355626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00536308,"threshold_uncertainty_score":0.0179413,"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."}}