{"id":"W2983647115","doi":"10.1109/ijcnn52387.2021.9533769","title":"Soft-Label Dataset Distillation and Text Dataset Distillation","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Distillation; Computer science; Code (set theory); Artificial intelligence; Sample (material); Pattern recognition (psychology); Image (mathematics); Task (project management); MNIST database; Machine learning; Data mining; Deep learning; Chromatography; Engineering","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":[0.0002977492,0.0002710685,0.0002829022,0.00009014275,0.0001208469,0.0008463411,0.0007699274,0.0001987569,0.00006909486],"category_scores_gemma":[0.0001145425,0.0002617026,0.00002745975,0.000125408,0.0000398326,0.0005681888,0.003879259,0.0003256593,0.00002756351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005943496,"about_ca_system_score_gemma":0.0001218187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004158594,"about_ca_topic_score_gemma":0.0001724634,"domain_scores_codex":[0.9977612,0.00008391778,0.0004043691,0.00114401,0.0003693114,0.0002372314],"domain_scores_gemma":[0.9975811,0.0001128402,0.0001913807,0.001921555,0.00006875873,0.0001243856],"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":[0.0000179125,0.0002346278,0.003523029,0.0009134382,0.0001913464,0.0001139097,0.001240767,0.02127914,0.0003741914,0.04630999,0.1765726,0.749229],"study_design_scores_gemma":[0.0002095718,0.00000940017,0.001613783,0.00006954497,0.00002326909,0.00001698306,0.00001735628,0.9697167,0.00004101065,0.002476186,0.02542597,0.0003802617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003703787,0.0003158318,0.9834049,0.0009023698,0.000607439,0.0002500472,0.01043473,0.0001284038,0.000252534],"genre_scores_gemma":[0.4999582,0.0001527776,0.2743631,0.0006986405,0.0003288998,0.0000286451,0.2242631,0.00002694866,0.0001796223],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9484375,"threshold_uncertainty_score":0.9999835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04822326090122638,"score_gpt":0.296521998139149,"score_spread":0.2482987372379227,"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."}}