{"id":"W4385571422","doi":"10.18653/v1/2023.findings-acl.426","title":"“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Global Water Futures; Canada First Research Excellence Fund","keywords":"Computer science; Artificial intelligence; Classifier (UML); Deep neural networks; Parametric statistics; Artificial neural network; k-nearest neighbors algorithm; Machine learning; Data mining; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00100618,0.0002612689,0.0002531694,0.0003615972,0.0003380899,0.000445592,0.002142432,0.0001254345,0.00006837613],"category_scores_gemma":[0.0003356352,0.0002048506,0.00007389439,0.001993546,0.00009281799,0.0006055104,0.0003652088,0.000328805,0.0008706848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005533688,"about_ca_system_score_gemma":0.00008202644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004022863,"about_ca_topic_score_gemma":0.00002111974,"domain_scores_codex":[0.997129,0.000414863,0.0004177692,0.0009561974,0.0006395392,0.0004426241],"domain_scores_gemma":[0.9958655,0.0007690848,0.0002710161,0.002762917,0.0001419628,0.0001895686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005430403,0.0002466057,0.003405307,0.00007272586,0.00007372149,0.00001457395,0.001027943,0.001268784,0.008469033,0.493114,0.09028828,0.4019647],"study_design_scores_gemma":[0.0006004988,0.0001135905,0.08856124,0.00002867993,0.00001492625,0.00002208879,0.0003128961,0.7858118,0.0009208395,0.002093264,0.1211684,0.0003517581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00372929,0.00001772455,0.9490837,0.01624559,0.0001483878,0.000331965,0.00001126772,0.002058735,0.02837328],"genre_scores_gemma":[0.6089689,0.00002962891,0.3811097,0.0009242491,0.0001987834,0.0002906446,0.0004187508,0.00005564478,0.008003681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.784543,"threshold_uncertainty_score":0.9999073,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04413472812042506,"score_gpt":0.3074148113399623,"score_spread":0.2632800832195373,"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."}}