{"id":"W2124310882","doi":"10.48550/arxiv.1206.3294","title":"Flexible Priors for Exemplar-based Clustering","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Prior probability; Cluster analysis; Dirichlet process; Computer science; Dirichlet distribution; Similarity (geometry); Data mining; Artificial intelligence; Pairwise comparison; Machine learning; Mathematics; Bayesian probability","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":[0.0003817979,0.000129923,0.0001380431,0.000111438,0.0001552822,0.00004243418,0.0005902958,0.00007733478,0.0000111385],"category_scores_gemma":[0.00001879849,0.000137855,0.0001118807,0.0003635885,0.00002528362,0.0006466053,0.0001487598,0.00008362432,0.00002491581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005792338,"about_ca_system_score_gemma":0.00004647667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009314744,"about_ca_topic_score_gemma":0.000003648776,"domain_scores_codex":[0.9990377,0.00006405103,0.00009118802,0.0003412985,0.00004201067,0.0004237003],"domain_scores_gemma":[0.9991177,0.00009632875,0.00006177126,0.0004881331,0.00004999063,0.0001860478],"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":[0.00004755936,0.0001268191,0.001976941,0.00005244689,0.00002680054,0.00001577191,0.0003425782,0.006042123,0.001332027,0.9751853,0.000716581,0.01413502],"study_design_scores_gemma":[0.001443341,0.0001281079,0.000872085,0.00003434101,0.00004531828,0.000006753546,0.0000332377,0.931705,0.0107236,0.03569759,0.01874014,0.0005704659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01324175,0.00003984815,0.9831911,0.0001203138,0.0003636734,0.0001897192,0.000001942957,0.0001822184,0.002669476],"genre_scores_gemma":[0.7550093,0.000002890492,0.2436274,0.0002300842,0.00006339465,9.219979e-7,9.571073e-7,0.000008997295,0.001056106],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9394878,"threshold_uncertainty_score":0.5621564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1067688121327724,"score_gpt":0.2170292362896167,"score_spread":0.1102604241568443,"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."}}