{"id":"W4412487375","doi":"10.1016/j.neunet.2025.107802","title":"Disentangled representation learning for multi-view clustering via von Mises–Fisher hyperspherical embedding","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Cluster analysis; Discriminative model; Embedding; Artificial intelligence; Representation (politics); Gaussian; Similarity (geometry); Feature learning; Consistency (knowledge bases); Benchmark (surveying); Data mining; Machine learning; Pattern recognition (psychology)","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":[0.0001147802,0.0001393588,0.0001797917,0.00004530098,0.0002672895,0.0001850807,0.0002801651,0.00009107993,0.00001712472],"category_scores_gemma":[0.00006431522,0.0001290428,0.0001157573,0.0003423856,0.00001942974,0.0004194654,0.0002006941,0.0002112014,0.000006312664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003597325,"about_ca_system_score_gemma":0.000008400781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001499491,"about_ca_topic_score_gemma":0.000008364283,"domain_scores_codex":[0.9988276,0.0001037736,0.0002366163,0.0004136432,0.0001193796,0.0002989916],"domain_scores_gemma":[0.9993954,0.0001783097,0.0000830794,0.0002140526,0.00006351018,0.00006568784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000746217,0.00006909095,0.003907093,0.00005980317,0.00002840615,0.00001046403,0.0002268658,0.3328698,0.002013567,0.00007769462,0.004282494,0.6563801],"study_design_scores_gemma":[0.0005877717,0.00003409739,0.0009291327,0.00009530254,0.00001369246,0.00000382065,0.00005089117,0.9962418,0.0002476483,0.00007991006,0.001581365,0.0001345396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01418258,0.0002921381,0.9830089,0.0006250521,0.001035237,0.0003286495,2.54495e-7,0.000211915,0.000315294],"genre_scores_gemma":[0.9427944,0.0000697549,0.0542609,0.001184625,0.0002206525,0.0001238537,0.0000252377,0.00001854727,0.001302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.928748,"threshold_uncertainty_score":0.5262212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03519562897882195,"score_gpt":0.3202713545366525,"score_spread":0.2850757255578305,"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."}}