{"id":"W4319653775","doi":"10.48550/arxiv.2302.03391","title":"Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre hospitalier de l'Université Laval","funders":"Agence Nationale de la Recherche","keywords":"Cluster analysis; Discriminative model; Feature selection; Pattern recognition (psychology); Computer science; Scalability; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Relevance (law); Clustering high-dimensional data; Data mining; Machine learning; Mathematics","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":[0.0002471966,0.0001601424,0.000179284,0.0002995742,0.0001970469,0.0001055845,0.0004044309,0.0001544539,5.825269e-7],"category_scores_gemma":[0.0001048139,0.0001476993,0.00006229532,0.0004998943,0.0001036985,0.0007477067,0.002064648,0.0003190446,0.000001030579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001703625,"about_ca_system_score_gemma":0.00007040907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001100876,"about_ca_topic_score_gemma":0.00009002114,"domain_scores_codex":[0.9990717,0.00007642689,0.0001428514,0.0004051464,0.0001112984,0.0001926061],"domain_scores_gemma":[0.9990226,0.00009571081,0.0002346139,0.000338338,0.000250373,0.000058375],"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":[0.00009683635,0.00003530905,0.002059688,0.001352442,0.000143905,0.000007584633,0.005079534,0.9504946,0.0005086615,0.01700981,0.0003133826,0.02289827],"study_design_scores_gemma":[0.0003347266,0.00005607482,0.00977891,0.00009896266,0.0000207783,0.000005034461,0.0002851388,0.9822691,0.0006688188,0.00627465,0.00005516749,0.0001526363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1689353,0.000008818422,0.8299785,0.0002749918,0.0002272952,0.0004593913,0.00003595746,0.00006565975,0.00001408518],"genre_scores_gemma":[0.9894201,0.00008187314,0.009871056,0.00001849572,0.00003766495,0.000004918601,0.0000199304,0.00001053237,0.0005354012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8204848,"threshold_uncertainty_score":0.6023001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1268804352697365,"score_gpt":0.2295491491202739,"score_spread":0.1026687138505374,"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."}}