{"id":"W3160701863","doi":"10.1093/imaiai/iaab007","title":"Distributed information-theoretic clustering","year":2021,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Vienna Science and Technology Fund; Arizona State University","keywords":"Information bottleneck method; Mutual information; Constraint (computer-aided design); Cluster analysis; Encoder; Bottleneck; Computer science; Binary number; Combinatorics; Information theory; Characterization (materials science); Cardinality (data modeling); Independence (probability theory); Mathematics; Discrete mathematics; Algorithm; Data mining; Artificial intelligence; Statistics; Physics","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":[0.0002202672,0.00005775638,0.00008483026,0.00005518476,0.0001271592,0.000491697,0.0004196303,0.00002695688,0.00001886381],"category_scores_gemma":[0.0002877132,0.00003543505,0.00003972441,0.0001987215,0.00003028873,0.007454037,0.0003624482,0.0001332901,0.00001316359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001890238,"about_ca_system_score_gemma":0.0001438467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002828352,"about_ca_topic_score_gemma":5.581011e-7,"domain_scores_codex":[0.9992208,0.00003120487,0.0004053779,0.00002608002,0.0002311119,0.0000853896],"domain_scores_gemma":[0.9989418,0.00005099221,0.0003647153,0.0001975325,0.0003904091,0.0000545993],"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":[0.000037184,0.00004593626,0.002185843,0.0001270701,0.00005122873,0.000008759132,0.007213858,0.004332718,0.0002096743,0.1511543,0.008534767,0.8260987],"study_design_scores_gemma":[0.001809589,0.0001357681,0.03148016,0.0004818889,0.00002179385,0.001486325,0.0009969349,0.6970232,0.003805692,0.01985509,0.2425585,0.0003450738],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008774438,0.0000567011,0.988194,0.001830633,0.0003908204,0.00003171165,0.00001116374,0.00001030056,0.0007002353],"genre_scores_gemma":[0.982869,0.0001682283,0.01544689,0.001463038,0.00003073605,9.376628e-7,0.00001082603,0.000001087641,0.000009278445],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740946,"threshold_uncertainty_score":0.5403997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008085186106822037,"score_gpt":0.232273134839672,"score_spread":0.2241879487328499,"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."}}