{"id":"W4412217228","doi":"","title":"Zero-shot Clustering of Embeddings with Pretrained and Self-Supervised Learnt Encoders","year":2023,"lang":"en","type":"article","venue":"VBN Forskningsportal (Aalborg Universitet)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Vector Institute; Dalhousie University","funders":"","keywords":"Zero (linguistics); Cluster analysis; Shot (pellet); Encoder; Artificial intelligence; Computer science; Pattern recognition (psychology); Speech recognition; Chemistry","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":[0.001816111,0.001130378,0.001199976,0.001198857,0.0006166855,0.001465179,0.002168929,0.001452743,0.001867392],"category_scores_gemma":[0.008682189,0.0005893818,0.0009103406,0.001031403,0.001221412,0.0031427,0.001422345,0.002102084,0.00135829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001735372,"about_ca_system_score_gemma":0.001055061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006663522,"about_ca_topic_score_gemma":0.01287683,"domain_scores_codex":[0.9984509,0.0003338227,0.00007495571,0.0007017967,0.0002329904,0.0002056204],"domain_scores_gemma":[0.9961869,0.0009575462,0.0002601154,0.001556075,0.000890135,0.0001492288],"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":[0.0008198703,0.0008087421,0.01306729,0.000437113,0.0003365396,0.000279825,0.0007843087,0.498495,0.03022496,0.01052586,0.01111131,0.4331092],"study_design_scores_gemma":[0.00001343948,0.0001008656,0.001158217,0.00001868731,0.00001591952,0.00007795283,0.00009748872,0.9779491,0.01419417,0.005369123,0.0009823254,0.000022695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3474797,0.0005550422,0.6401259,0.0003423062,0.0001830035,0.0002214174,0.001010191,0.006934956,0.003147488],"genre_scores_gemma":[0.736481,0.0001352676,0.2533926,0.0001794193,0.00003445104,0.0001569452,0.005273035,0.0005550315,0.003792223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006663522,"threshold_uncertainty_score":0.01324952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01199749518758924,"score_gpt":0.2196997971889412,"score_spread":0.207702302001352,"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."}}