{"id":"W2949091389","doi":"10.48550/arxiv.1212.1527","title":"Learning Mixtures of Arbitrary Distributions over Large Discrete Domains","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Mixture model; Dimension (graph theory); Point process; Point (geometry); Moment (physics); Unsupervised learning; Mathematics; Sequence (biology); Computer science; Algorithm; Artificial intelligence; Combinatorics; Physics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003976154,0.001286689,0.001616825,0.001681666,0.001119703,0.002119603,0.003024868,0.00238063,0.004781018],"category_scores_gemma":[0.01740522,0.001321458,0.002100948,0.001801091,0.001872975,0.006001878,0.006744357,0.004915119,0.001835298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001896057,"about_ca_system_score_gemma":0.00150585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003072943,"about_ca_topic_score_gemma":0.00428484,"domain_scores_codex":[0.9975988,0.0007478388,0.0001666354,0.0006783865,0.0005885386,0.0002197988],"domain_scores_gemma":[0.9947823,0.00340404,0.0003176812,0.0008553656,0.0004286152,0.0002120377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004475727,0.0002442352,0.002969424,0.0002434753,0.0001838194,0.0002116687,0.000534599,0.4467571,0.003962927,0.1988815,0.009311341,0.3362522],"study_design_scores_gemma":[0.00002615953,0.00001942477,0.0001447123,0.00001274859,0.000008623693,0.00004760447,0.00002664962,0.9299808,0.0009635884,0.06715883,0.001596814,0.00001407775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002931274,0.00007339818,0.9957898,0.0002427793,0.00001302284,0.00003345394,0.00004917758,0.0004322329,0.0004349092],"genre_scores_gemma":[0.1018504,0.0001698611,0.8935784,0.0003176162,0.0001027383,0.0003100812,0.0007860414,0.00024578,0.002639048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004781018,"threshold_uncertainty_score":0.02102816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02455428583374884,"score_gpt":0.2001401681885146,"score_spread":0.1755858823547658,"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."}}