{"id":"W4399424565","doi":"10.48550/arxiv.2406.02465","title":"An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Danmarks Grundforskningsfond; Government of Canada; Canadian Institute for Advanced Research","keywords":"Cluster analysis; Computer science; Artificial intelligence; Encoder; Empirical research; Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004670798,0.0004453215,0.0005208376,0.0005625113,0.0001480232,0.0002108208,0.003736449,0.0002070969,0.0000125179],"category_scores_gemma":[0.00001877624,0.0004440946,0.0001090175,0.001238418,0.0001597243,0.0005808286,0.0079419,0.001084463,0.0000423652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003747168,"about_ca_system_score_gemma":0.0004816483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005069025,"about_ca_topic_score_gemma":0.0003725975,"domain_scores_codex":[0.9965574,0.0003459649,0.0003083364,0.001928756,0.000354753,0.0005048085],"domain_scores_gemma":[0.9964011,0.0001322788,0.0001583379,0.002776452,0.0001998884,0.0003319468],"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":[0.0001974635,0.001203486,0.00657112,0.0008354287,0.0006081315,0.003885865,0.009629204,0.9715337,0.00009694042,0.0007183488,0.0001200794,0.004600236],"study_design_scores_gemma":[0.0007417257,0.0007131621,0.0006618864,0.0001449297,0.00009087961,0.00001245671,0.0009683644,0.9922704,0.00007177748,0.003768725,0.00006083762,0.0004948474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3742937,0.00002777174,0.6242412,0.00005369085,0.0001835785,0.0005799247,0.00004959615,0.0004158001,0.0001547448],"genre_scores_gemma":[0.9461095,0.00002710755,0.05359545,0.00002478536,0.00004852076,0.000004028914,0.00004710909,0.00004470509,0.00009876205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5718159,"threshold_uncertainty_score":0.9998011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07352471772403338,"score_gpt":0.27488410284662,"score_spread":0.2013593851225866,"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."}}