{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002914559,0.0001894451,0.0002236999,0.0003749263,0.0001927998,0.0000745946,0.0005136897,0.00008259957,0.00002482767],"category_scores_gemma":[0.00003448881,0.0001785575,0.00005063976,0.001049223,0.00008732281,0.0007411762,0.0002724747,0.0001898092,0.00002178495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003777198,"about_ca_system_score_gemma":0.00007802945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001439492,"about_ca_topic_score_gemma":0.00002764275,"domain_scores_codex":[0.99863,0.00003606567,0.0002067118,0.0004841661,0.0003274177,0.0003155811],"domain_scores_gemma":[0.9990675,0.00007683464,0.0001968112,0.0004254902,0.00008979999,0.0001435459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009475625,0.0009316659,0.4786053,0.002111065,0.001319513,0.001483346,0.1454838,0.0296119,0.03810455,0.1804865,0.0148569,0.106058],"study_design_scores_gemma":[0.001865782,0.0006038533,0.04773138,0.0001656897,0.00007298184,0.00005899885,0.003031065,0.9296227,0.0007142255,0.0002432779,0.01525593,0.0006341473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.856274,0.00003632839,0.131991,0.0005967152,0.0001043793,0.0002710671,0.00001248196,0.0009994158,0.009714602],"genre_scores_gemma":[0.9739974,0.00004528568,0.02444565,0.00005113521,0.00001594275,0.000002084761,0.00007237404,0.00002027017,0.00134991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9000108,"threshold_uncertainty_score":0.7281364,"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."}}