{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1238,"total_is_capped":false,"direct_labels_cover":4,"predictions_cover":1238,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"2d3804620fa3","filters":{"topic":"Bayesian Methods and Mixture Models"}},"results":[{"id":"W4246027503","doi":"10.1214/ba/1339616472","title":"Flexible paleoclimate age-depth models using an autoregressive gamma process","year":2011,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3800,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Radiocarbon dating; Autoregressive model; Outlier; Paleoclimatology; Prior probability; Markov chain Monte Carlo; Geology; Sampling (signal processing); Physical geography; Computer science; Statistics; Paleontology; Artificial intelligence; Bayesian probability; Mathematics; Geography; Climate change; Oceanography","retraction":null,"screen_n_in":null,"score":{"opus":0.1055040289042663,"gpt":0.3245205179113725,"spread":0.2190164890071061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006827576,0.0003996902,0.0007067616,0.0007817799,0.0002893116,0.0003038704,0.001560448,0.0001861498,0.00009437188],"category_scores_gemma":[0.00001741779,0.0003123986,0.0004373481,0.002241179,0.0001065164,0.001696978,0.0001879054,0.0002258195,0.00001140597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005105141,"about_ca_system_score_gemma":0.0001351325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002004112,"about_ca_topic_score_gemma":0.0001551929,"domain_scores_codex":[0.9968482,0.0003358649,0.0005176683,0.001094817,0.0004935025,0.0007099123],"domain_scores_gemma":[0.9974446,0.00002935535,0.0003284971,0.001558783,0.0002078148,0.000430891],"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":[0.0001648464,0.002431377,0.01671604,0.0003271608,0.006112124,0.002273351,0.06684305,0.03861808,0.002166072,0.5049411,0.0002029183,0.3592038],"study_design_scores_gemma":[0.0001945254,0.00005383668,0.0009666468,0.00002163948,0.0006346051,0.00001705622,0.00006304671,0.8494728,0.002509735,0.14559,0.00001062267,0.0004654513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003188377,0.000126458,0.9828826,0.00004711693,0.0001026247,0.0001789293,0.000006086117,0.0004222983,0.01304555],"genre_scores_gemma":[0.5034998,0.00001035377,0.4960066,0.0001421145,0.00004925174,0.00001394597,0.000006629544,0.00002263528,0.0002486967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8108547,"threshold_uncertainty_score":0.9999328,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135194391","doi":"10.1023/a:1020281327116","title":"An Introduction to MCMC for Machine Learning","year":2003,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2418,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Monte Carlo method; Probabilistic logic; Artificial intelligence; Machine learning; Bayesian probability; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01302649663491802,"gpt":0.28260567903664,"spread":0.269579182401722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001782363,0.0002148388,0.0002451608,0.0001878252,0.0004685462,0.0002113337,0.0004476219,0.00007874475,0.00005735251],"category_scores_gemma":[0.0007210961,0.0002010155,0.00008723621,0.0004230205,0.00001451331,0.0003948959,0.00007923493,0.0004847009,0.0000229029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004266309,"about_ca_system_score_gemma":0.00003083852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004168242,"about_ca_topic_score_gemma":0.00001999761,"domain_scores_codex":[0.9978321,0.0006021866,0.0002427748,0.0006886558,0.0001973759,0.000436896],"domain_scores_gemma":[0.9990399,0.0001152727,0.0001020812,0.0004515169,0.00008654518,0.0002046277],"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":[0.00004240217,0.0001103321,0.004663254,0.00004060822,0.00003135214,0.00000774934,0.002224323,0.03069295,0.01941396,0.2924618,0.0007739117,0.6495374],"study_design_scores_gemma":[0.0004521184,0.0005863546,0.0002234468,0.000007592253,0.0000114811,0.00004058112,0.0000155608,0.5805165,0.003174778,0.007521212,0.4070992,0.0003511086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00396141,0.0001988884,0.9908195,0.002861885,0.0004851263,0.0002622867,0.000001210925,0.0003611529,0.001048609],"genre_scores_gemma":[0.2371298,0.000006271267,0.7592789,0.0004624994,0.0004438872,0.00003414929,0.00001619873,0.00003479401,0.002593518],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6491863,"threshold_uncertainty_score":0.8197173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080972498","doi":"10.1080/10618600.2000.10474879","title":"Markov Chain Sampling Methods for Dirichlet Process Mixture Models","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2212,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Dirichlet distribution; Hierarchical Dirichlet process; Markov chain Monte Carlo; Metropolis–Hastings algorithm; Markov chain; Dirichlet process; Mathematics; Prior probability; Conjugate prior; Computer science; Sampling (signal processing); Mathematical optimization; Applied mathematics; Statistics; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.02605654607133213,"gpt":0.3550975326748263,"spread":0.3290409866034942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001054532,0.0001490798,0.000317417,0.0001293733,0.0001577878,0.0001299352,0.0003163076,0.00008485125,0.00001255237],"category_scores_gemma":[0.0001024154,0.0001148823,0.00009654633,0.0002752469,0.00007231227,0.0002832073,0.00002537238,0.0002461946,2.506947e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001035848,"about_ca_system_score_gemma":0.00009096467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.270688e-7,"about_ca_topic_score_gemma":3.06515e-7,"domain_scores_codex":[0.9986115,0.0001755477,0.0005095894,0.0002039827,0.0002955334,0.0002038791],"domain_scores_gemma":[0.9975937,0.001422531,0.000222535,0.00008576601,0.0004787429,0.000196707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004749068,0.00005001666,0.000008689816,0.00003801357,0.00003641401,0.000005503342,0.0001999221,0.01033575,0.000009194619,0.3817591,0.0004257402,0.6070842],"study_design_scores_gemma":[0.0002977845,0.000112482,0.0002847928,0.00001846716,0.00001606414,0.00009059925,0.000002083708,0.4208212,0.000005446339,0.5772555,0.001009269,0.00008626935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007547858,0.0005908089,0.9968912,0.001351629,0.0001305515,0.0001196621,0.0000493186,0.00001377339,0.00009827616],"genre_scores_gemma":[0.01772333,0.00011491,0.9812755,0.0006920618,0.0001310016,0.000004498093,0.000006813851,0.000009536401,0.0000423416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6069979,"threshold_uncertainty_score":0.4684763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147357149","doi":"10.1111/j.1467-9868.2006.00553.x","title":"Sequential Monte Carlo Samplers","year":2006,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1702,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Markov chain Monte Carlo; Monte Carlo method; Hybrid Monte Carlo; Computer science; Monte Carlo integration; Algorithm; Bayesian inference; Bayesian probability; Quasi-Monte Carlo method; Probability distribution; Mathematical optimization; Mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.043337857943991,"gpt":0.3038536844281268,"spread":0.2605158264841358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003415614,0.0003578856,0.0008399434,0.00004111323,0.0003948078,0.0002126273,0.001464375,0.0002781624,0.0001581019],"category_scores_gemma":[0.002537944,0.0002326797,0.0005163687,0.0003404127,0.0008886755,0.000281169,0.000476973,0.001037235,0.000007957679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001729325,"about_ca_system_score_gemma":0.0002668441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002872296,"about_ca_topic_score_gemma":0.00002546448,"domain_scores_codex":[0.9944029,0.002479623,0.001143988,0.0004467719,0.0007965683,0.0007301497],"domain_scores_gemma":[0.9936197,0.004599482,0.0005765222,0.0005287307,0.0003541135,0.0003214146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001111183,0.0001011202,0.0001588673,0.00004347815,0.0001508147,0.00009797193,0.0002421352,0.0007967676,0.0003228708,0.913177,0.05644052,0.02835738],"study_design_scores_gemma":[0.000957643,0.0005215146,0.01095953,0.00004018992,0.0002565462,0.000412713,0.00006481581,0.03624003,0.0006007178,0.9316776,0.01778129,0.0004874434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00056945,0.0002370108,0.9928307,0.003451334,0.001891934,0.0001687603,0.0001619929,0.0000469827,0.0006418273],"genre_scores_gemma":[0.01861012,0.00001928015,0.97913,0.0009496762,0.0005735142,0.000005666522,0.000002373345,0.00002704944,0.0006823377],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03865923,"threshold_uncertainty_score":0.9488404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147307434","doi":"10.1093/molbev/msh112","title":"A Bayesian Mixture Model for Across-Site Heterogeneities in the Amino-Acid Replacement Process","year":2004,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1608,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Biology; Process (computing); Bayesian probability; Computational biology; Evolutionary biology; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01280211934731184,"gpt":0.3132920961572663,"spread":0.3004899768099544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005192845,0.0001266274,0.0001285139,0.00004361859,0.0001628736,0.00004324819,0.0002692591,0.0001487123,1.81353e-7],"category_scores_gemma":[0.0000223998,0.00009057364,0.00005112054,0.0001298432,0.00008366698,0.0001077634,0.00006092794,0.000105677,5.621336e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003524361,"about_ca_system_score_gemma":0.00004335414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001558734,"about_ca_topic_score_gemma":0.00005599876,"domain_scores_codex":[0.9990227,0.0001019703,0.0001541989,0.0003655739,0.00006348455,0.0002921005],"domain_scores_gemma":[0.9995822,0.00001460567,0.00005078852,0.0002823914,0.00003760487,0.00003235777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001824113,0.0001924214,0.002779581,0.0001254644,0.00004978067,0.00001872042,0.01537821,0.006632899,0.09026554,0.8694966,0.00005645108,0.01482189],"study_design_scores_gemma":[0.0009935946,0.0002850809,0.0009391639,0.0000240326,0.000009929678,0.00006067743,0.00006299694,0.2841346,0.01092887,0.7022768,0.00006131285,0.0002229362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1668281,0.0009367353,0.8307969,0.001042234,0.00005404756,0.000278213,0.000009108783,0.00002322674,0.00003143571],"genre_scores_gemma":[0.8451821,0.00001135962,0.1537862,0.0008649543,0.00001772335,0.0001116288,0.00001068233,0.000004509943,0.00001081095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.678354,"threshold_uncertainty_score":0.3693486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1513873506","doi":"10.1023/a:1008923215028","title":"Annealed importance sampling","year":2001,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1225,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain; Mathematics; Sampling (signal processing); Markov chain Monte Carlo; Simulated annealing; Applied mathematics; Slice sampling; Autocorrelation; Markov chain mixing time; Sequence (biology); Mathematical optimization; Algorithm; Variable-order Markov model; Statistical physics; Statistics; Computer science; Markov model; Bayesian probability; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02817825423091845,"gpt":0.3042159619191862,"spread":0.2760377076882677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003037114,0.00009698753,0.0001309866,0.00003449643,0.0001832662,0.0001472421,0.0002106573,0.00002851691,0.000004811731],"category_scores_gemma":[0.00003831325,0.00009142861,0.00001543042,0.0001453439,0.00002479811,0.00007832657,0.0001449109,0.00009684648,0.000002790916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008535255,"about_ca_system_score_gemma":0.0000213027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009558441,"about_ca_topic_score_gemma":0.000003839426,"domain_scores_codex":[0.9991692,0.00003501304,0.0001812501,0.0002734818,0.0001038256,0.0002371957],"domain_scores_gemma":[0.9994213,0.0001575674,0.00007391885,0.000207942,0.00005098171,0.00008830702],"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":[9.534551e-7,0.000007061827,0.001247941,0.000007289827,0.000004352194,0.00003664851,0.0002050173,0.00002086721,0.0000503104,0.5157412,0.0002366218,0.4824417],"study_design_scores_gemma":[0.0002168428,0.00004150359,0.006223345,0.00002389247,0.000005067437,0.0001264454,0.0000117707,0.6799998,0.00002159022,0.3100245,0.003088773,0.0002164663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007272054,0.0002930914,0.9900172,0.000142899,0.0001751459,0.00005219457,0.000004703539,0.00007339964,0.001969357],"genre_scores_gemma":[0.2229621,0.0000436396,0.7765596,0.0002930668,0.00007120952,5.718973e-7,0.00000187093,0.000005272868,0.00006266254],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.679979,"threshold_uncertainty_score":0.3728351,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152298208","doi":"10.1093/sysbio/syt022","title":"PhyloBayes MPI: Phylogenetic Reconstruction with Infinite Mixtures of Profiles in a Parallel Environment","year":2013,"lang":"en","type":"article","venue":"Systematic Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":936,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Agriculture and Agri-Food Canada; Université de Montréal","funders":"","keywords":"Computer science; Dirichlet process; Phylogenomics; Hierarchical Dirichlet process; Dirichlet distribution; Gibbs sampling; Inference; Representation (politics); Tree (set theory); Phylogenetic tree; Algorithm; Theoretical computer science; Bayesian probability; Latent Dirichlet allocation; Mathematics; Artificial intelligence; Topic model; Combinatorics; Biology; Boundary value problem","retraction":null,"screen_n_in":null,"score":{"opus":0.01132984968193786,"gpt":0.22191598189564,"spread":0.2105861322137021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000388725,0.0001544729,0.0004838354,0.0001344572,0.00002329249,0.00002290817,0.00036416,0.0001209659,0.00002002259],"category_scores_gemma":[0.00002987906,0.00009709443,0.00004427782,0.0001370669,0.0001180128,0.00008734352,0.00009816771,0.0000913467,0.00001767327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002054749,"about_ca_system_score_gemma":0.00002983197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000649772,"about_ca_topic_score_gemma":0.000006544609,"domain_scores_codex":[0.9983173,0.0005602055,0.0005020757,0.0003137772,0.00008800294,0.0002186398],"domain_scores_gemma":[0.9990082,0.0001349406,0.0002943086,0.0004836112,0.00003376909,0.00004512804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000669699,0.0006301562,0.1262728,0.04511294,0.0005871805,0.00002417109,0.00875141,0.001084294,0.1952862,0.5137557,0.00007509468,0.1083532],"study_design_scores_gemma":[0.002974501,0.001977353,0.05667921,0.009489769,0.000102075,0.0006714131,0.0004839793,0.1199513,0.02279032,0.7834322,0.00001238424,0.001435522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1759017,0.0005762912,0.8220927,0.0001387719,0.0000859822,0.0009506887,0.00000132294,0.00001978404,0.0002328379],"genre_scores_gemma":[0.629857,0.00001147083,0.3698386,0.00003274267,0.00001021605,0.0002354088,6.580859e-7,0.000003672391,0.00001028003],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4539554,"threshold_uncertainty_score":0.3959396,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4237780050","doi":"10.2307/1390653","title":"Markov Chain Sampling Methods for Dirichlet Process Mixture Models","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":508,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet process; Markov chain; Mathematics; Dirichlet distribution; Sampling (signal processing); Slice sampling; Markov chain Monte Carlo; Hierarchical Dirichlet process; Computer science; Markov renewal process; Applied mathematics; Statistics; Econometrics; Statistical physics; Markov model; Variable-order Markov model; Bayesian probability; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.02605654607133213,"gpt":0.3550975326748263,"spread":0.3290409866034942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001054532,0.0001490798,0.000317417,0.0001293733,0.0001577878,0.0001299352,0.0003163076,0.00008485125,0.00001255237],"category_scores_gemma":[0.0001024154,0.0001148823,0.00009654633,0.0002752469,0.00007231227,0.0002832073,0.00002537238,0.0002461946,2.506947e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001035848,"about_ca_system_score_gemma":0.00009096467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.270688e-7,"about_ca_topic_score_gemma":3.06515e-7,"domain_scores_codex":[0.9986115,0.0001755477,0.0005095894,0.0002039827,0.0002955334,0.0002038791],"domain_scores_gemma":[0.9975937,0.001422531,0.000222535,0.00008576601,0.0004787429,0.000196707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004749068,0.00005001666,0.000008689816,0.00003801357,0.00003641401,0.000005503342,0.0001999221,0.01033575,0.000009194619,0.3817591,0.0004257402,0.6070842],"study_design_scores_gemma":[0.0002977845,0.000112482,0.0002847928,0.00001846716,0.00001606414,0.00009059925,0.000002083708,0.4208212,0.000005446339,0.5772555,0.001009269,0.00008626935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007547858,0.0005908089,0.9968912,0.001351629,0.0001305515,0.0001196621,0.0000493186,0.00001377339,0.00009827616],"genre_scores_gemma":[0.01772333,0.00011491,0.9812755,0.0006920618,0.0001310016,0.000004498093,0.000006813851,0.000009536401,0.0000423416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6069979,"threshold_uncertainty_score":0.4684763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162021827","doi":"10.1198/1061860043001","title":"A Split-Merge Markov chain Monte Carlo Procedure for the Dirichlet Process Mixture Model","year":2004,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":475,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Markov chain Monte Carlo; Metropolis–Hastings algorithm; Hierarchical Dirichlet process; Dirichlet distribution; Rejection sampling; Dirichlet process; Markov chain; Slice sampling; Computer science; Algorithm; Monte Carlo method; Merge (version control); Hybrid Monte Carlo; Mathematics; Bayesian probability; Artificial intelligence; Latent Dirichlet allocation; Machine learning; Statistics; Topic model","retraction":null,"screen_n_in":null,"score":{"opus":0.01124520141011327,"gpt":0.2784303576061979,"spread":0.2671851561960846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000533215,0.0001602078,0.0002509512,0.0000929427,0.0002325008,0.0001246344,0.0004054726,0.00007843803,8.961514e-7],"category_scores_gemma":[0.0001547017,0.0000978698,0.0001029805,0.0002779221,0.0001035469,0.0001900417,0.00004586494,0.0003021274,1.571832e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001764943,"about_ca_system_score_gemma":0.000251496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002483643,"about_ca_topic_score_gemma":0.000004454103,"domain_scores_codex":[0.9986659,0.00004307498,0.000430394,0.0001939945,0.0004587141,0.0002078824],"domain_scores_gemma":[0.9982944,0.0005357487,0.0002871034,0.00009981736,0.0006210398,0.0001619088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007410368,0.0001033606,0.00004695313,0.00009069731,0.00007770558,0.00001857869,0.0006759507,0.1643252,0.000007320963,0.8034155,0.001639788,0.02952489],"study_design_scores_gemma":[0.0004559327,0.0001078303,0.0009492292,0.00002413578,0.00002496358,0.00009606746,0.000006923928,0.4646638,0.000003281443,0.5334821,0.0001080475,0.00007762013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004489921,0.000765975,0.9869781,0.007298457,0.0001393472,0.0002099695,0.00009284593,0.00001156237,0.00001378097],"genre_scores_gemma":[0.3112903,0.00006376345,0.6876686,0.0008304665,0.0001061962,0.000008544285,0.000002019278,0.000007758885,0.00002239802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3068003,"threshold_uncertainty_score":0.3991015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118846274","doi":"10.1080/10705511.2014.919819","title":"Effect Size, Statistical Power, and Sample Size Requirements for the Bootstrap Likelihood Ratio Test in Latent Class Analysis","year":2014,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":456,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"National Cancer Institute; National Institute on Drug Abuse","keywords":"Sample size determination; Statistics; Latent class model; Statistical power; Likelihood-ratio test; Mathematics; Sample (material); Population; Monte Carlo method; Econometrics; Class (philosophy); Type I and type II errors; Power (physics); Computer science; Artificial intelligence; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.03295265194356398,"gpt":0.3401933839435168,"spread":0.3072407319999528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003221431,0.000276699,0.0004075342,0.0001661405,0.0007432176,0.0004431759,0.0004896882,0.0001050711,0.00001371228],"category_scores_gemma":[0.003127811,0.0001802693,0.0001826305,0.0004281975,0.00006103428,0.0005603496,0.0001834736,0.0004144237,7.226458e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009786471,"about_ca_system_score_gemma":0.00008321444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004309621,"about_ca_topic_score_gemma":0.00004344239,"domain_scores_codex":[0.9973204,0.0005220154,0.0007182815,0.0005007394,0.000461083,0.0004774892],"domain_scores_gemma":[0.9893811,0.0095755,0.0002711501,0.0003768994,0.0001949316,0.0002004182],"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":[0.0005536952,0.000132901,0.03167418,0.000121938,0.0006891673,0.00001869282,0.006035498,0.5483811,0.006600622,0.03034854,0.00003938332,0.3754043],"study_design_scores_gemma":[0.001201985,0.0004288102,0.01234292,0.000023868,0.000143222,0.00002361988,0.00003008141,0.8440143,0.0000567546,0.1415395,0.000001112852,0.0001937759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1529135,0.00009256522,0.8452139,0.001044246,0.0002815804,0.0003912281,0.00002568131,0.00002884183,0.000008398919],"genre_scores_gemma":[0.6078703,0.00001639647,0.3919539,0.0000418497,0.00007961295,0.00001841167,0.000004077918,0.000009844076,0.000005537872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4549569,"threshold_uncertainty_score":0.735117,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1984130041","doi":"10.1111/j.0006-341x.2000.00237.x","title":"A Nonparametric Mixture Model for Cure Rate Estimation","year":2000,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":445,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"Memorial University of Newfoundland; Newcastle University","keywords":"Covariate; Nonparametric statistics; Proportional hazards model; Parametric statistics; Econometrics; Statistics; Parametric model; Nonparametric regression; Semiparametric model; Estimation; Semiparametric regression; Accelerated failure time model; Regression analysis; Mixture model; Computer science; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03025689618870801,"gpt":0.2980956773642959,"spread":0.2678387811755879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007785044,0.0001703045,0.0002041887,0.001312149,0.0001275505,0.0002032794,0.0006824827,0.000170564,0.00001603912],"category_scores_gemma":[0.0002626637,0.000130792,0.0001196356,0.008166847,0.000021888,0.0004032095,0.00005032593,0.0001098674,0.00004327728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004846508,"about_ca_system_score_gemma":0.00007588274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003389712,"about_ca_topic_score_gemma":3.235197e-7,"domain_scores_codex":[0.9986842,0.00005821685,0.0002425043,0.0004396107,0.0002375685,0.0003379571],"domain_scores_gemma":[0.9988353,0.0002912849,0.0000806304,0.0005287394,0.0001297746,0.0001343213],"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":[0.000007689439,0.00006216502,0.000004247808,0.00002294793,0.000008784887,0.000001595604,0.0001135867,0.002594656,0.0001646183,0.02264315,0.005612776,0.9687638],"study_design_scores_gemma":[0.0003197915,0.00006195479,0.00005957541,0.000006079,0.00001119647,0.000005235709,3.562361e-7,0.9292281,0.0004135823,0.05988089,0.009824136,0.0001891339],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006590098,0.0004884544,0.9964045,0.0008178469,0.0002125522,0.0003447158,0.00002101129,0.0001604169,0.0008915191],"genre_scores_gemma":[0.03573868,0.000123982,0.9598693,0.0005943151,0.00006210097,0.00003991287,0.00001047805,0.00001543223,0.003545824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9685746,"threshold_uncertainty_score":0.5333543,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100163972","doi":"","title":"Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":434,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Hierarchical Dirichlet process; Computer science; Generalization; Cluster analysis; Hierarchical clustering; Dirichlet process; Nonparametric statistics; Dirichlet distribution; Latent Dirichlet allocation; Bayesian probability; Group (periodic table); Topic model; Data mining; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01351625547000949,"gpt":0.2516143638654544,"spread":0.238098108395445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003518295,0.0001542476,0.0001688101,0.0001007943,0.000124904,0.000194532,0.0009244811,0.0001041227,0.00001572787],"category_scores_gemma":[0.000079836,0.0001208519,0.00005720155,0.0006540015,0.00007161883,0.000699562,0.0003745174,0.0002521742,0.00002942343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004203576,"about_ca_system_score_gemma":0.00008158496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004189405,"about_ca_topic_score_gemma":0.00002572074,"domain_scores_codex":[0.9986117,0.00003798707,0.0002461472,0.0005354283,0.0002225404,0.0003461487],"domain_scores_gemma":[0.9991829,0.00006246905,0.00005521892,0.0004807938,0.00005568044,0.0001628994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005439698,0.0001035604,0.0009980056,0.00006531736,0.00002889518,0.00007058447,0.002566084,0.0003927223,0.0001898845,0.9626735,0.0002217742,0.03268427],"study_design_scores_gemma":[0.0009398107,0.00010537,0.003230894,0.0001159702,0.0000115889,0.0000728511,0.00002025994,0.03075473,0.002115061,0.9617366,0.0004051359,0.0004917475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02794317,0.00008931469,0.9489827,0.001744483,0.0001742956,0.0001367169,2.779517e-7,0.0003936999,0.02053531],"genre_scores_gemma":[0.509741,0.00001301134,0.4889354,0.0005516678,0.00003398028,0.00001063538,0.000001021905,0.00001011116,0.0007032111],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4817978,"threshold_uncertainty_score":0.4928197,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4230827384","doi":"10.1007/978-1-4757-3449-2","title":"Permutation Methods","year":2001,"lang":"en","type":"book","venue":"Springer series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":353,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. Geological Survey; Centers for Disease Control and Prevention; University of Ottawa; Colorado State University; American Psychological Association; American Educational Research Association","keywords":"Permutation (music); Statistic; Test statistic; Exact test; Mathematics; Resampling; Test (biology); Statistics; Computer science; Combinatorics; Statistical hypothesis testing; Physics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02534143546384614,"gpt":0.3404566358269084,"spread":0.3151152003630623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008335222,0.0003625012,0.0005099621,0.0002556202,0.00007220006,0.0001777983,0.0008633616,0.0003280355,0.00007272032],"category_scores_gemma":[0.0001726882,0.0003815747,0.00006530704,0.0002049354,0.0001145743,0.0003190493,0.0003646239,0.0005854805,0.00003805328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002373904,"about_ca_system_score_gemma":0.0004282658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001069429,"about_ca_topic_score_gemma":0.00004079018,"domain_scores_codex":[0.9979057,0.0002649469,0.0005119391,0.0006246084,0.000304634,0.0003881333],"domain_scores_gemma":[0.9983399,0.0003487321,0.0002396414,0.0008377617,0.00013425,0.00009973845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003517196,0.00000891561,0.000003652859,0.00006243302,0.00001197833,0.0001243443,0.0004066151,0.000007268652,0.000007183735,0.6547874,0.008715013,0.3358617],"study_design_scores_gemma":[0.0001064682,0.0000477348,0.00005365525,0.00007539214,0.0000150498,0.00003582837,0.000003191435,0.003063776,0.00004625618,0.6875378,0.3086509,0.0003638893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.924295e-7,0.0004256231,0.7573299,0.00007757486,0.001022055,0.0001630078,0.00004796655,0.00009082923,0.2408428],"genre_scores_gemma":[0.000001245897,0.0003694603,0.6631719,0.0001216031,0.0001342752,0.00001597911,0.00002920827,0.00003400136,0.3361223],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3354978,"threshold_uncertainty_score":0.9998636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003144493","doi":"10.1198/jcgs.2010.08111","title":"Combining Mixture Components for Clustering","year":2010,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":348,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Mixture model; Cluster analysis; Mathematics; Determining the number of clusters in a data set; Gaussian; Entropy (arrow of time); Piecewise; Cluster (spacecraft); Computer science; Statistics; Correlation clustering; CURE data clustering algorithm; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01577668605565137,"gpt":0.280924284971499,"spread":0.2651475989158477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004665871,0.00009165982,0.0002030378,0.0001014583,0.0001262737,0.0001100951,0.0002381401,0.00006197485,0.000002374549],"category_scores_gemma":[0.0001015722,0.00007283157,0.00006240654,0.0001065524,0.00006594029,0.0001494417,0.00005604078,0.0003089091,2.48159e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003724058,"about_ca_system_score_gemma":0.00003890878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001102164,"about_ca_topic_score_gemma":0.000002284105,"domain_scores_codex":[0.9991261,0.00004425117,0.0003422043,0.0001142129,0.0002442923,0.000128986],"domain_scores_gemma":[0.9984448,0.0007855499,0.0002186642,0.00006470796,0.0003360366,0.0001502328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002969821,0.00006147537,0.0002309514,0.00002821711,0.0000366881,0.00001673255,0.0001437094,0.0003278636,0.0006863637,0.901702,0.001062051,0.09567425],"study_design_scores_gemma":[0.0004287992,0.0001330915,0.006401922,0.00001377224,0.00001109799,0.0001912329,0.000001415737,0.2819791,0.00001807441,0.7092867,0.001456692,0.0000780667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008619989,0.0000482209,0.9895879,0.001023947,0.0005816144,0.00006354139,0.00003137148,0.000008646407,0.00003476546],"genre_scores_gemma":[0.3087418,0.000006323152,0.6908777,0.0002702254,0.00008890734,8.255747e-7,0.000004089084,0.000003878346,0.00000629058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3001218,"threshold_uncertainty_score":0.2969985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1566710167","doi":"10.1093/oso/9780198502784.001.0001","title":"Approximating Integrals via Monte Carlo and Deterministic Methods","year":2000,"lang":"en","type":"book","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":296,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Monte Carlo method; Statistical physics; Applied mathematics; Monte Carlo method in statistical physics; Monte Carlo molecular modeling; Monte Carlo integration; Hybrid Monte Carlo; Computer science; Mathematics; Physics; Markov chain Monte Carlo; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01945512214444693,"gpt":0.309683401502441,"spread":0.2902282793579941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001291869,0.000491327,0.0007950595,0.0001963063,0.0001251332,0.0003105533,0.0009813543,0.0004214385,0.00006090032],"category_scores_gemma":[0.0000589176,0.0003913096,0.0001711705,0.0001025159,0.0001015938,0.0002361402,0.0003986429,0.0005769905,0.00001906698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006421036,"about_ca_system_score_gemma":0.0002012543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002457547,"about_ca_topic_score_gemma":0.000003860058,"domain_scores_codex":[0.9974794,0.0003822259,0.0005798329,0.00091753,0.0002357572,0.0004052806],"domain_scores_gemma":[0.9980194,0.0005157164,0.0002323038,0.0009633579,0.00005888165,0.000210319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001664978,0.000006324769,1.821662e-7,0.00007181375,0.00002685823,0.000024284,0.0002837884,0.000001105513,0.00001907387,0.07499741,0.002934361,0.9216331],"study_design_scores_gemma":[0.0001892098,0.0001089726,0.000002472943,0.0002389081,0.00007292365,0.0002460014,0.00000284922,0.2912785,0.0001476746,0.6350766,0.07181535,0.0008206175],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[8.228118e-7,0.0008771566,0.612748,0.00005203722,0.0001690131,0.0001973479,0.000002527999,0.0001479872,0.3858051],"genre_scores_gemma":[0.00001502797,0.00005814956,0.6239675,0.0003931178,0.00009933335,0.00001751129,0.000001398954,0.00002841876,0.3754196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9208125,"threshold_uncertainty_score":0.9998539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042829929","doi":"10.1002/cyto.a.20531","title":"Automated gating of flow cytometry data via robust model‐based clustering","year":2008,"lang":"en","type":"article","venue":"Cytometry Part A","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Terry Fox Research Institute; University of British Columbia","funders":"Michael Smith Health Research BC","keywords":"Computer science; Cluster analysis; Outlier; Mixture model; Robustness (evolution); Data mining; Cytometry; Expectation–maximization algorithm; Statistical model; Transformation (genetics); Artificial intelligence; Maximum likelihood; Flow cytometry; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1051308348991267,"gpt":0.3155985677931308,"spread":0.2104677328940041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011106,0.0002970953,0.0005229112,0.0005989323,0.0002342411,0.00007032152,0.002339588,0.0001731945,0.00002018111],"category_scores_gemma":[0.0002181168,0.0002865846,0.0001136952,0.002404705,0.0001141046,0.0008245229,0.001154782,0.0002820815,0.00002168981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006320428,"about_ca_system_score_gemma":0.0001973647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001747705,"about_ca_topic_score_gemma":0.000003675747,"domain_scores_codex":[0.9972288,0.0001765536,0.0006191282,0.0008500073,0.0005744555,0.0005510244],"domain_scores_gemma":[0.9966813,0.0002286124,0.0002699477,0.002446914,0.0001524921,0.0002207105],"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":[0.0001442106,0.001349802,0.008868182,0.001155884,0.0004367235,0.0006279516,0.002774549,0.6246839,0.06508062,0.001884365,0.02426958,0.2687242],"study_design_scores_gemma":[0.0004927311,0.00004975034,0.0005493917,0.00007972748,0.00001540104,0.00007660861,0.000003272711,0.9927831,0.005323014,0.0001973946,0.0001140334,0.0003155612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009002985,0.0001802376,0.9883643,0.00009781982,0.000342367,0.0001899202,0.00004520651,0.0007619906,0.00101516],"genre_scores_gemma":[0.4331763,0.000008377923,0.5664641,0.0001807934,0.00006584422,0.000006426005,0.00002560979,0.0000206797,0.00005186773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4241733,"threshold_uncertainty_score":0.9999586,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118036030","doi":"10.2307/3315951","title":"Exact and approximate sum representations for the Dirichlet process","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Dirichlet process; Hierarchical Dirichlet process; Dirichlet distribution; Latent Dirichlet allocation; Mathematics; Representation (politics); Context (archaeology); Bayesian probability; Metric (unit); Measure (data warehouse); Process (computing); Applied mathematics; Generalized Dirichlet distribution; Dirichlet's energy; Computer science; Statistics; Topic model; Mathematical analysis; Artificial intelligence; Data mining; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04002486311540775,"gpt":0.2838017468158548,"spread":0.2437768837004471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003044337,0.00006317952,0.0001028493,0.00007824734,0.0002133867,0.0001752156,0.0003277876,0.00002324055,0.00001621999],"category_scores_gemma":[0.0002567102,0.0000439187,0.00002272114,0.0001225727,0.00006918139,0.0001631905,0.000008341436,0.0001052453,6.42574e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001945213,"about_ca_system_score_gemma":0.0001691409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00014585,"about_ca_topic_score_gemma":0.0008468959,"domain_scores_codex":[0.9994149,0.00003363208,0.0001897119,0.0000903016,0.00009235777,0.0001791611],"domain_scores_gemma":[0.9988798,0.0003490124,0.0001316311,0.0001525612,0.0002157569,0.0002711703],"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":[0.000003578427,0.00001668208,0.0006596954,0.00007004567,0.0000684078,0.0001266271,0.006040539,0.0002110776,0.00001480874,0.5565445,0.09335211,0.3428919],"study_design_scores_gemma":[0.0006879707,0.0001921384,0.002610317,0.00004915339,0.00008791906,0.0005655567,0.0002307988,0.5847171,0.00009044166,0.3839567,0.02654974,0.0002621513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001263731,0.0008613637,0.9959174,0.002302044,0.0002223636,0.0001058904,0.00008452099,0.000002974183,0.0003770213],"genre_scores_gemma":[0.1297271,0.0001131159,0.869278,0.0004262706,0.0001105164,0.000005720392,9.115457e-7,0.000008662861,0.0003297623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.584506,"threshold_uncertainty_score":0.1790952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043122071","doi":"10.1002/bimj.200410102","title":"Generalized Poisson Distribution: the Property of Mixture of Poisson and Comparison with Negative Binomial Distribution","year":2005,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Negative binomial distribution; Count data; Poisson distribution; Compound Poisson distribution; Mathematics; Poisson binomial distribution; Zero-inflated model; Quasi-likelihood; Negative multinomial distribution; Binomial distribution; Statistics; Applied mathematics; Beta-binomial distribution; Statistical physics; Poisson regression; Physics; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.0223335932115592,"gpt":0.2780133281326238,"spread":0.2556797349210646,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008530124,0.0001573156,0.0003699737,0.0001682019,0.0001784284,0.0001082026,0.0004819347,0.0001073891,0.000007585976],"category_scores_gemma":[0.0002076754,0.00007085786,0.00009662541,0.002051718,0.0002009559,0.0002767142,0.0001171235,0.0003167693,6.846439e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009004782,"about_ca_system_score_gemma":0.00009216605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003934526,"about_ca_topic_score_gemma":0.000002883762,"domain_scores_codex":[0.9982408,0.0003374889,0.0004740862,0.0002212007,0.0004816165,0.0002448085],"domain_scores_gemma":[0.9986277,0.0001976795,0.0004445912,0.00023882,0.000325227,0.000165967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005171751,0.0006359549,0.003543001,0.00003870247,0.0001767242,0.00001183211,0.0008841428,0.00005973203,0.008257053,0.0352901,0.01164424,0.9389414],"study_design_scores_gemma":[0.01766269,0.00781089,0.2532491,0.000581568,0.000570419,0.002845966,0.0002295171,0.2139555,0.3546336,0.02156445,0.1248397,0.002056502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07930542,0.001007961,0.9148044,0.004524796,0.0001016054,0.0001479382,0.00005104873,0.00001275843,0.00004406229],"genre_scores_gemma":[0.8415416,0.00008226124,0.1580814,0.00005153169,0.0001877755,0.000002331892,0.000009425784,0.000004835769,0.0000388174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368848,"threshold_uncertainty_score":0.28895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154036191","doi":"10.48550/arxiv.math/0703292","title":"Nonlinear Models Using Dirichlet Process Mixtures","year":2007,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Dirichlet distribution; Multinomial logistic regression; Component (thermodynamics); Nonlinear system; Computer science; Support vector machine; Dirichlet process; Class (philosophy); Mixture model; Covariate; Machine learning; Multinomial distribution; Artificial intelligence; Process (computing); Mathematics; Pattern recognition (psychology); Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.06584906040963906,"gpt":0.3317421120016123,"spread":0.2658930515919732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008351275,0.0002220071,0.0002382049,0.0001305982,0.0001786628,0.00008195476,0.000871208,0.0001383578,0.000007416011],"category_scores_gemma":[0.00004416251,0.0001901636,0.00009410369,0.0005564294,0.00005573503,0.0007275113,0.0001848763,0.0002530669,0.0000198674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003622836,"about_ca_system_score_gemma":0.00009036568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003016156,"about_ca_topic_score_gemma":0.000006700303,"domain_scores_codex":[0.9982269,0.00006265631,0.000315254,0.000543033,0.0003022865,0.0005498575],"domain_scores_gemma":[0.9988172,0.00008871638,0.000115144,0.0006414012,0.000147461,0.0001900716],"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":[0.0002328462,0.002123885,0.1478432,0.0006091644,0.000432732,0.001396099,0.02011484,0.008360011,0.1753777,0.2222236,0.002410217,0.4188758],"study_design_scores_gemma":[0.0008295099,0.0001303672,0.005053224,0.0001081261,0.00004369495,0.0001326448,0.00004674362,0.7785844,0.1137467,0.09846864,0.001768964,0.001087029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3437844,0.0002535867,0.6535715,0.0001771195,0.0002469791,0.0001032174,0.000001214707,0.0001329247,0.001728998],"genre_scores_gemma":[0.5600075,0.000008063153,0.4387996,0.0008046918,0.0002219374,0.000002502964,0.000001131714,0.00001652836,0.0001381117],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7702243,"threshold_uncertainty_score":0.7754645,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152173558","doi":"10.1111/1467-9868.00273","title":"A Modified Likelihood Ratio Test for Homogeneity in Finite Mixture Models","year":2001,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":222,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Agencia Estatal de Investigación; Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneity (statistics); Mathematics; Likelihood-ratio test; Quantile; Asymptotic distribution; Parametric statistics; Statistics; Score test; Applied mathematics; Null distribution; Limiting; Statistic; Null hypothesis; Parametric model; Test statistic; Ratio test; Kernel density estimation; Statistical hypothesis testing; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06075234635197555,"gpt":0.3189824197277949,"spread":0.2582300733758193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004691347,0.0003876604,0.0009881558,0.00006382931,0.0003169598,0.0001677271,0.001397622,0.0003807397,0.00004044596],"category_scores_gemma":[0.00976174,0.0002622807,0.0004478672,0.0005040288,0.000468673,0.0003829185,0.0003489307,0.001048768,0.000002221831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001617996,"about_ca_system_score_gemma":0.0003437696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004183346,"about_ca_topic_score_gemma":0.00003542259,"domain_scores_codex":[0.9951695,0.001669343,0.001236014,0.0005277955,0.0005605113,0.0008368524],"domain_scores_gemma":[0.9820378,0.01610315,0.0005116477,0.0005347194,0.0004274583,0.0003851679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004100516,0.0003821512,0.000263395,0.00009853433,0.0001408811,0.0001056255,0.0008983568,0.006971536,0.0003013212,0.9127663,0.009396788,0.06826508],"study_design_scores_gemma":[0.000879304,0.0004529596,0.001662318,0.00003383288,0.00007817283,0.0001080615,0.00003815818,0.3652799,0.0001379324,0.6302401,0.0008547149,0.0002345332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003106367,0.0002567717,0.9930816,0.004484224,0.0007967521,0.0004356094,0.0003208593,0.00003190852,0.0002816478],"genre_scores_gemma":[0.02974011,0.00009613239,0.9681286,0.001440756,0.0002779416,0.00003291568,0.000005443534,0.00002988948,0.0002482231],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3583083,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148178414","doi":"10.1007/s11222-007-9028-9","title":"On population-based simulation for static inference","year":2007,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":207,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Markov chain Monte Carlo; Inference; Population; Markov chain; Bayesian inference; Computer science; Monte Carlo method; Sampling (signal processing); Statistics; Algorithm; Bayesian probability; Mathematics; Applied mathematics; Artificial intelligence; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.02437224421377677,"gpt":0.3512340842917407,"spread":0.326861840077964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005433388,0.0000869306,0.0001021198,0.0000651029,0.0001650676,0.00009416461,0.000106883,0.00002952984,0.000001146907],"category_scores_gemma":[0.0002690718,0.00008199173,0.00001390915,0.0001048039,0.00001049828,0.00004649907,0.00002721035,0.00005767151,6.615288e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001696098,"about_ca_system_score_gemma":0.00002784102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000153783,"about_ca_topic_score_gemma":0.000005656918,"domain_scores_codex":[0.9992528,0.00002833748,0.0002045547,0.0002113318,0.0001164896,0.0001865162],"domain_scores_gemma":[0.9972296,0.002391302,0.00009390586,0.0001361089,0.00008748206,0.00006155332],"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":[0.000006880323,0.000010121,0.0001636079,0.00001884386,0.000002184769,0.000001453897,0.00008389113,0.01953709,0.000005833374,0.6222907,0.00003731276,0.3578421],"study_design_scores_gemma":[0.0002656304,0.00007269792,0.003735252,0.00001761801,0.000002834749,2.684552e-7,0.000001575487,0.7447798,0.00002024291,0.2509853,0.00003954575,0.00007915006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003960921,0.000009452252,0.9954791,0.00005791274,0.0001528126,0.0001721831,0.00001658846,0.0000431609,0.0001078738],"genre_scores_gemma":[0.496882,1.607481e-7,0.5028064,0.0002726085,0.00001914374,7.128949e-7,0.000008473411,0.00000333478,0.000007095207],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7252427,"threshold_uncertainty_score":0.3343526,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982891217","doi":"10.1111/1467-9868.00219","title":"Bayesian Inference in Hidden Markov Models Through the Reversible Jump Markov Chain Monte Carlo Method","year":2000,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":205,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Royal Swedish Academy of Sciences; University of Glasgow; Trent University; Core Research for Evolutional Science and Technology; Nottingham Trent University","keywords":"Markov chain Monte Carlo; Reversible-jump Markov chain Monte Carlo; Markov chain; Variable-order Bayesian network; Hidden Markov model; Inference; Markov model; Variable-order Markov model; Bayesian inference; Statistical physics; Computer science; Bayesian probability; Hidden semi-Markov model; Monte Carlo method; Jump; Mathematics; Algorithm; Artificial intelligence; Statistics; Machine learning; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.04077475466133923,"gpt":0.3213892502813812,"spread":0.280614495620042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007977745,0.000543995,0.001257113,0.00005603511,0.0005198381,0.0002535201,0.002709447,0.0004229585,0.0005874342],"category_scores_gemma":[0.004101202,0.0003224,0.0005230093,0.0008131208,0.0009420276,0.000675178,0.0006005972,0.00208814,0.000008818255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002550779,"about_ca_system_score_gemma":0.0003940826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005397918,"about_ca_topic_score_gemma":0.00006816597,"domain_scores_codex":[0.9880075,0.007680672,0.001543507,0.0007226471,0.0009866806,0.001058977],"domain_scores_gemma":[0.9820801,0.01573667,0.0005506389,0.0009760506,0.0002879106,0.0003686561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004523026,0.0001781261,0.00009396698,0.00009660295,0.0002549009,0.0001687311,0.004073681,0.006501916,0.00003608298,0.5722495,0.01973285,0.3961614],"study_design_scores_gemma":[0.0006754987,0.0002948253,0.001340101,0.00007876732,0.0001299433,0.0001445486,0.0001920216,0.3495947,0.00005159982,0.6442544,0.002886311,0.0003572893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001553466,0.000460777,0.9864095,0.009615123,0.00073746,0.0004082308,0.0001410242,0.0000403341,0.002032199],"genre_scores_gemma":[0.01017222,0.000279465,0.9848375,0.002740645,0.0002374422,0.00002210398,0.000001796475,0.00003929962,0.001669541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3958041,"threshold_uncertainty_score":0.9999228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123782934","doi":"10.1109/tpami.2003.1159942","title":"Transformation-invariant clustering using the EM algorithm","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Artificial intelligence; Computer science; Pattern recognition (psychology); Invariant (physics); Transformation (genetics); Clutter; Computer vision; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02908415944746115,"gpt":0.2861228390117631,"spread":0.2570386795643019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000595131,0.0002015946,0.0002477081,0.0002794676,0.0004033474,0.0002322181,0.000376118,0.00005954918,0.0000643755],"category_scores_gemma":[0.000002754563,0.0001393182,0.0002348133,0.0009781569,0.00004278703,0.00028803,0.000002960242,0.0002641023,0.000005425154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002648953,"about_ca_system_score_gemma":0.00002424525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003665769,"about_ca_topic_score_gemma":0.0005305489,"domain_scores_codex":[0.9985626,0.0002382689,0.0003552137,0.0003732562,0.0002299758,0.0002406815],"domain_scores_gemma":[0.9991659,0.0001149367,0.00007931972,0.0004862853,0.00005254349,0.0001010272],"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":[0.000001488964,0.00004572751,0.000007702791,0.000006682381,0.0002229319,0.000004232246,0.001386561,0.02280025,0.0001278834,0.001181883,7.296e-7,0.9742139],"study_design_scores_gemma":[0.00006331199,0.00003396813,0.00002297024,0.0000123298,0.0002779127,0.0000467838,0.00008598133,0.9546159,0.0430581,0.00152396,0.00006878511,0.0001899831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002181143,0.0001081549,0.9988759,0.0002372049,0.0002176104,0.0001327494,0.00001371536,0.00004793649,0.0001486872],"genre_scores_gemma":[0.8214547,0.0001524207,0.1777793,0.0005156015,0.00001161425,0.00001113705,6.965864e-7,0.000008231679,0.00006631827],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740239,"threshold_uncertainty_score":0.5681231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152594362","doi":"10.1109/tip.2004.834664","title":"Unsupervised Learning of a Finite Mixture Model Based on the Dirichlet Distribution and Its Application","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais; Université de Sherbrooke","funders":"","keywords":"Automatic summarization; Mixture model; Computer science; Dirichlet distribution; Artificial intelligence; Pattern recognition (psychology); Data modeling; Latent Dirichlet allocation; Machine learning; Mathematics; Topic model","retraction":null,"screen_n_in":null,"score":{"opus":0.01421025074941218,"gpt":0.2553749113308786,"spread":0.2411646605814664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003241954,0.0001469859,0.0001331382,0.00007449997,0.0003749863,0.0001029872,0.0002398677,0.00007517565,0.000001593396],"category_scores_gemma":[0.00001922836,0.0001102283,0.00005634189,0.0004402828,0.00005028451,0.0003612473,0.00000233341,0.00033219,0.00000237718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003952438,"about_ca_system_score_gemma":0.0001003167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005105428,"about_ca_topic_score_gemma":0.000001114703,"domain_scores_codex":[0.9990277,0.00008138143,0.0001845306,0.0003211839,0.000216534,0.0001686467],"domain_scores_gemma":[0.9993622,0.0001208829,0.00009845414,0.0002352044,0.0001297109,0.0000535948],"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":[0.00005191093,0.0002636525,0.000001226003,0.0001564237,0.00001071047,0.000001779563,0.001269705,0.5259038,0.06427754,0.006384107,0.000005353042,0.4016738],"study_design_scores_gemma":[0.000321152,0.00005251138,0.000007706667,0.00009902601,0.0000154368,0.000002233352,0.000008751651,0.8963209,0.09646642,0.00658583,0.00001188126,0.0001081522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001909945,0.00007811659,0.9960406,0.001484249,0.00002690083,0.000221656,0.00001349517,0.00009428993,0.0001307788],"genre_scores_gemma":[0.852046,0.00001288194,0.1475876,0.0002578177,0.000009408475,0.00005017927,0.000002691228,0.00001037688,0.00002299484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8501361,"threshold_uncertainty_score":0.4494978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1755019093","doi":"10.1002/cjs.11246","title":"A mixture of generalized hyperbolic distributions","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Generalized inverse Gaussian distribution; Skew; Expectation–maximization algorithm; Cluster analysis; Generalized normal distribution; Mathematics; Gaussian; Applied mathematics; Mixture distribution; Multivariate statistics; Inverse distribution; Estimation theory; Inverse Gaussian distribution; Probability distribution; Distribution (mathematics); Statistics; Probability density function; Computer science; Heavy-tailed distribution; Normal distribution; Gaussian process; Maximum likelihood; Gaussian random field; Mathematical analysis; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03640317111091929,"gpt":0.2600045938295232,"spread":0.2236014227186039,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003970255,0.0000787313,0.0002124014,0.0001402542,0.00004715914,0.00005054902,0.0004672463,0.00005078143,0.00001230251],"category_scores_gemma":[0.0003311382,0.00006806271,0.00004673137,0.0002300585,0.00007223501,0.0001254801,0.0000153499,0.0001474651,0.000002365121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008070122,"about_ca_system_score_gemma":0.002230659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009420893,"about_ca_topic_score_gemma":0.001780374,"domain_scores_codex":[0.9991488,0.00009228957,0.0003167595,0.00007645611,0.000165445,0.0002002315],"domain_scores_gemma":[0.998098,0.00005354826,0.0002132937,0.0002006188,0.0006037947,0.0008307154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003273919,0.00001140813,0.0002562269,0.00000860265,0.00002737577,0.0002049362,0.0007850758,0.00003462331,0.0001185234,0.8976118,0.06739569,0.03354247],"study_design_scores_gemma":[0.001489288,0.0004082291,0.002309088,0.00008340566,0.00008665471,0.0009924215,0.0000550485,0.009800901,0.00116715,0.8667476,0.1165001,0.0003600375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001342156,0.0006762969,0.9960006,0.0006358651,0.0005141838,0.00003402782,0.0002972911,0.000003077665,0.0004965115],"genre_scores_gemma":[0.1483334,0.00001461577,0.8513207,0.0001444088,0.00008858381,3.994939e-7,0.00000435427,0.000005115824,0.00008838029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1469913,"threshold_uncertainty_score":0.3957093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096784803","doi":"10.1109/tpami.2007.1095","title":"High-Dimensional Unsupervised Selection and Estimation of a Finite Generalized Dirichlet Mixture Model Based on Minimum Message Length","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"University of California, Irvine","keywords":"Minimum description length; Generalized Dirichlet distribution; Mixture model; Hierarchical Dirichlet process; Dirichlet distribution; Cluster analysis; Latent Dirichlet allocation; Mathematics; Computer science; Model selection; Algorithm; Determining the number of clusters in a data set; Automatic summarization; Pattern recognition (psychology); Artificial intelligence; Topic model; Dirichlet's principle; Correlation clustering; CURE data clustering algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01552536188303195,"gpt":0.2702911791012604,"spread":0.2547658172182285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006693006,0.0002657941,0.0004084686,0.000726112,0.0001771576,0.000061388,0.0002063495,0.0001236152,0.0000463726],"category_scores_gemma":[0.000009429482,0.000222647,0.0001876271,0.0009953924,0.00005245326,0.0001721356,0.000004952339,0.0002621909,0.000001729318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002279483,"about_ca_system_score_gemma":0.00002988353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003437356,"about_ca_topic_score_gemma":0.000389992,"domain_scores_codex":[0.9982287,0.0001490855,0.0004659922,0.0005672296,0.0003575029,0.0002314718],"domain_scores_gemma":[0.9989521,0.0002958413,0.0001490703,0.0003566839,0.000104867,0.0001414752],"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":[0.00005524016,0.000151339,0.00002465885,0.00001786088,0.0001272141,0.000002793861,0.0001357116,0.588766,0.001765587,0.0005046509,0.000002771386,0.4084461],"study_design_scores_gemma":[0.0002274704,0.0001512443,0.0001650407,0.00002615636,0.0002583931,0.000003123486,0.000002295287,0.8608004,0.1370116,0.001164152,0.000001809434,0.0001882728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0203106,0.00005636992,0.9790038,0.0002835246,0.00008138119,0.0001486111,0.00004145832,0.00005164169,0.00002261688],"genre_scores_gemma":[0.7654629,0.00005032983,0.2338655,0.000527448,0.000009125491,0.000008462421,0.00000861118,0.000009987315,0.0000575995],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7451523,"threshold_uncertainty_score":0.9079282,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105787212","doi":"10.1109/tpami.2013.216","title":"Mixtures of Shifted AsymmetricLaplace Distributions","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"Ontario Ministry of Research and Innovation","keywords":"Cluster analysis; Mixture model; Gaussian; Laplace distribution; Laplace transform; Computer science; Artificial intelligence; Pattern recognition (psychology); Inverse Gaussian distribution; Algorithm; Estimation theory; Mathematics; Distribution (mathematics); Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01552783805678325,"gpt":0.2711309065625086,"spread":0.2556030685057253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004603666,0.000191678,0.0003717207,0.0005851311,0.0001503883,0.0000719019,0.0004684505,0.00007940357,0.00005343341],"category_scores_gemma":[0.00001707876,0.0001580247,0.0002808315,0.001920646,0.00007531125,0.0001478341,0.000006589492,0.000226956,0.000007254547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001611061,"about_ca_system_score_gemma":0.00001390262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005190182,"about_ca_topic_score_gemma":0.0002404428,"domain_scores_codex":[0.9985159,0.0002027852,0.0003812168,0.000446557,0.0002422009,0.0002113357],"domain_scores_gemma":[0.9987311,0.0003195851,0.0001286663,0.0005898837,0.00009429403,0.0001365108],"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":[0.000005710248,0.0001392116,0.0002238181,0.00001310687,0.0002746629,0.000001262652,0.0001039731,0.0008653497,0.0003448801,0.00838962,0.000009174374,0.9896292],"study_design_scores_gemma":[0.0001711167,0.0002714018,0.002198961,0.00002999994,0.0007076063,0.00001141196,0.00000851297,0.5001582,0.4809383,0.01485601,0.000224317,0.0004241912],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001103929,0.0001117624,0.9978187,0.000402695,0.0001328511,0.00007879104,0.00005481712,0.00005748868,0.000238938],"genre_scores_gemma":[0.9387209,0.0001304061,0.06081571,0.0001945713,0.00001250987,0.000009836383,0.000004297276,0.00000650814,0.0001051854],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9892051,"threshold_uncertainty_score":0.6444059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972168313","doi":"10.1109/tcsvt.2012.2211176","title":"Fast and Robust Spatially Constrained Gaussian Mixture Model for Image Segmentation","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":167,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Mixture model; Markov random field; Robustness (evolution); Expectation–maximization algorithm; Grayscale; Image segmentation; Pixel; Artificial intelligence; Computer science; Pattern recognition (psychology); Markov chain; Maximization; Gaussian; Segmentation; Algorithm; Mathematics; Mathematical optimization; Maximum likelihood; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02868451653117619,"gpt":0.269387716125938,"spread":0.2407031995947618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004301707,0.0002148234,0.0003191811,0.0003064125,0.0003297148,0.0001153999,0.0002042884,0.0002736618,0.000001032755],"category_scores_gemma":[0.0000100851,0.000191675,0.00007265637,0.000188403,0.0001274162,0.0004304837,0.000003241356,0.0001637546,8.241415e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003567747,"about_ca_system_score_gemma":0.00004819817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001185801,"about_ca_topic_score_gemma":0.00001815753,"domain_scores_codex":[0.9987118,0.00004418761,0.0003113163,0.0004187676,0.0001041032,0.0004098717],"domain_scores_gemma":[0.9992036,0.0001269092,0.0001220405,0.0003115052,0.0001060924,0.0001298532],"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":[0.00002889333,0.0002063373,0.00001920475,0.0004886382,0.0001441298,0.000002593556,0.001624517,0.003625419,0.0515281,0.2257807,0.0002700895,0.7162814],"study_design_scores_gemma":[0.001474944,0.0003173026,0.000007231667,0.00007859789,0.00007935756,0.0002432571,0.0001597875,0.9736099,0.01305022,0.01030658,0.0002971425,0.000375695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001169805,0.0004392366,0.9953478,0.0007658804,0.0006074829,0.001237053,0.0001278654,0.0002179242,0.00008694469],"genre_scores_gemma":[0.7443218,0.00004102263,0.2548294,0.0001037745,0.00004657442,0.0004621617,0.000002588444,0.00002017122,0.0001724619],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9699845,"threshold_uncertainty_score":0.7816278,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031212901","doi":"10.1002/cjs.10047","title":"Model‐based clustering of longitudinal data","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland","keywords":"Bayesian information criterion; Cluster analysis; Information Criteria; Model selection; Covariance; Convergence (economics); Computer science; Statistical model; Bayesian probability; Exponential family; Expectation–maximization algorithm; Mathematics; Data mining; Statistics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.09939433401187582,"gpt":0.2985575540033773,"spread":0.1991632199915015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006256946,0.00008184599,0.0001826861,0.0001772934,0.00006030583,0.00007338684,0.001373337,0.00004975659,0.0000234646],"category_scores_gemma":[0.0002215398,0.00007561273,0.00002626573,0.0001218004,0.00007980759,0.0002660644,0.00005843075,0.0003026571,9.541334e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002073489,"about_ca_system_score_gemma":0.001967372,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006173212,"about_ca_topic_score_gemma":0.02157757,"domain_scores_codex":[0.9991363,0.00003126355,0.0003310634,0.0001302753,0.0001665322,0.0002045213],"domain_scores_gemma":[0.9983247,0.00009628603,0.0002392785,0.0006014713,0.0002771275,0.0004611425],"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":[0.00001531585,0.00004298363,0.002397558,0.0001212717,0.00007321832,0.0009016725,0.0006887466,0.008561687,0.002311429,0.5728716,0.027976,0.3840385],"study_design_scores_gemma":[0.0001812348,0.00004629264,0.0006669075,0.0000257304,0.00001640465,0.000103712,0.000002143827,0.9689576,0.0001303815,0.02881806,0.0009627321,0.00008877712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005987664,0.00004995086,0.9977868,0.0002762499,0.0006123403,0.00002887947,0.0002953907,0.000002658211,0.0003489454],"genre_scores_gemma":[0.2895901,0.000002153959,0.7102405,0.00008669934,0.00005320163,1.042749e-7,0.000003212693,0.000005348157,0.00001875827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9603959,"threshold_uncertainty_score":0.9962761,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2039672920","doi":"10.1016/j.cmpb.2012.08.013","title":"smcure: An R-package for estimating semiparametric mixture cure models","year":2012,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Mixture model; Accelerated failure time model; Proportional hazards model; Semiparametric model; Event (particle physics); Cure rate; Semiparametric regression; Population; R package; Econometrics; Survival analysis; Computer science; Statistics; Mathematics; Medicine; Nonparametric statistics; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.09130992573247135,"gpt":0.3883450864695328,"spread":0.2970351607370615,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005590823,0.0003797212,0.0006351658,0.0004649129,0.0001515102,0.0001940314,0.0007693638,0.0002705712,0.000002075089],"category_scores_gemma":[0.00007948087,0.0002916697,0.00009963998,0.001481361,0.0001443175,0.00100298,0.0003250707,0.0003689702,7.15938e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003533836,"about_ca_system_score_gemma":0.00003544661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001682782,"about_ca_topic_score_gemma":0.000001089999,"domain_scores_codex":[0.996944,0.0006579212,0.0005501213,0.0007338964,0.0002516749,0.0008624422],"domain_scores_gemma":[0.9978248,0.0006234404,0.0001868255,0.0007620229,0.000109567,0.0004933201],"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":[0.000008846648,0.0001948131,0.0002788324,0.0001298918,0.00001919076,0.000003774936,0.002353413,0.00001101392,0.0002569379,0.03606533,0.0002826808,0.9603953],"study_design_scores_gemma":[0.0009479822,0.0006078489,0.0002312923,0.000153986,0.00002922564,0.00008661386,0.00002081422,0.8723708,0.0002316412,0.1181337,0.006779017,0.0004071539],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001021445,0.004545305,0.9906603,0.0007485422,0.001870227,0.0008579165,0.000003182447,0.0002043776,0.00008877592],"genre_scores_gemma":[0.009783559,0.00007107371,0.9879334,0.0007482714,0.001251817,0.0001257514,0.00002672535,0.0000324021,0.00002699972],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9599881,"threshold_uncertainty_score":0.9999536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W194034371","doi":"10.1007/s11222-011-9272-x","title":"Model-based clustering, classification, and discriminant analysis via mixtures of multivariate t-distributions","year":2011,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"University of Washington","keywords":"Cluster analysis; Mixture model; Linear discriminant analysis; Covariance; Mathematics; Pattern recognition (psychology); Artificial intelligence; Multivariate statistics; Multivariate normal distribution; Gaussian; Covariance matrix; Principal component analysis; Statistics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04787592351643025,"gpt":0.2987753486290899,"spread":0.2508994251126597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000281157,0.0001115714,0.0002112613,0.0001004898,0.0001602663,0.00004688162,0.0001736848,0.00003993945,0.000001544294],"category_scores_gemma":[0.00003101174,0.00009721716,0.00003414421,0.000235347,0.00008673535,0.00005368568,0.0001394711,0.00007222845,1.261418e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007485261,"about_ca_system_score_gemma":0.00003029948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001215565,"about_ca_topic_score_gemma":0.00002533528,"domain_scores_codex":[0.9991223,0.00007028395,0.0002654757,0.0002866687,0.00009454894,0.0001607754],"domain_scores_gemma":[0.9992904,0.0001006481,0.0001619717,0.0002487998,0.0001150488,0.00008312005],"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":[0.000006733356,0.00007357227,0.001006274,0.00006372903,0.000103068,0.000004538189,0.001876089,0.0009209714,0.001538249,0.8451337,0.00003124187,0.1492418],"study_design_scores_gemma":[0.0001296672,0.00002902093,0.0222449,0.00001209793,0.0001097359,0.000002183416,0.000007282641,0.9169793,0.0002577238,0.06011564,0.000004918546,0.0001075465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002729045,0.00007915936,0.996793,0.0000351935,0.00004485125,0.000067148,0.0000632485,0.00002402896,0.0001642744],"genre_scores_gemma":[0.4995837,0.000003887978,0.5003741,0.00001825629,0.000004239608,9.685488e-7,0.000007414913,0.000002468064,0.000004911665],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9160583,"threshold_uncertainty_score":0.3964401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157487910","doi":"10.1109/tpami.2008.155","title":"A Hybrid Feature Extraction Selection Approach for High-Dimensional Non-Gaussian Data Clustering","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":139,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Université de Sherbrooke","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Cluster analysis; Computer science; Mixture model; Feature extraction; Feature selection; Gaussian; Selection (genetic algorithm); Dirichlet distribution; Categorization; Expectation–maximization algorithm; Gaussian process; Maximization; Model selection; Bhattacharyya distance; Mathematics; Maximum likelihood; Statistics; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.02827560538389571,"gpt":0.3004763755083246,"spread":0.2722007701244288,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004921359,0.0002741195,0.0003610959,0.000461934,0.0003540303,0.0002059969,0.000596146,0.00009762505,0.00001722624],"category_scores_gemma":[0.000004308138,0.0002358431,0.0001801085,0.0006794218,0.00002637419,0.0005737132,0.000009525882,0.0003609981,0.000002478824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003902281,"about_ca_system_score_gemma":0.00002669399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003111201,"about_ca_topic_score_gemma":0.0002098887,"domain_scores_codex":[0.9980856,0.00009043067,0.0003208734,0.0009518872,0.0002592269,0.0002920162],"domain_scores_gemma":[0.9988016,0.00008535276,0.0001319006,0.0007586658,0.00008027926,0.0001422132],"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":[0.00003139177,0.0002018641,0.000008719669,0.000015307,0.0002255241,0.000003066161,0.00006273248,0.0275031,0.001259149,0.0001436959,0.00007429381,0.9704711],"study_design_scores_gemma":[0.0001335205,0.0001821307,0.0003558447,0.000014201,0.0003639947,0.00005449178,0.000003771842,0.9571747,0.04027386,0.001144731,0.00003693989,0.0002618831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002774845,0.00006083906,0.9980765,0.0008782992,0.0002088556,0.0002755381,0.00008529455,0.00009191694,0.00004524728],"genre_scores_gemma":[0.6694055,0.00005054794,0.3297952,0.0004534845,0.0000495796,0.00001743213,0.00004834816,0.000008478099,0.000171531],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9702092,"threshold_uncertainty_score":0.9617403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123094878","doi":"","title":"Tree-Structured Stick Breaking for Hierarchical Data","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Hierarchical database model; Tree structure; Cluster analysis; Tree (set theory); Hierarchical clustering; Bayesian inference; Data mining; Algorithm; Bayesian probability; Theoretical computer science; Mathematics; Artificial intelligence; Binary tree","retraction":null,"screen_n_in":null,"score":{"opus":0.03733069654240435,"gpt":0.3100610288616286,"spread":0.2727303323192243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006692196,0.0001504575,0.0001894879,0.0001197456,0.0002721427,0.001203386,0.001345998,0.0001258127,0.000001656245],"category_scores_gemma":[0.0001986914,0.0001186932,0.00003456381,0.000234063,0.0000387472,0.005284132,0.0002148401,0.0002882918,0.000005566268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003675,"about_ca_system_score_gemma":0.0001158998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001650438,"about_ca_topic_score_gemma":0.000008229025,"domain_scores_codex":[0.9986669,0.00004531028,0.0004837115,0.0002485148,0.00027976,0.0002757923],"domain_scores_gemma":[0.998578,0.00009548951,0.0002866503,0.0007376051,0.0001970061,0.0001053108],"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":[0.000008552557,0.000006245245,0.00001664724,0.0002516727,0.000004628752,5.239289e-7,0.001000651,0.00005574284,0.001270003,0.04611196,0.001368679,0.9499047],"study_design_scores_gemma":[0.0002966162,0.00002248079,0.0001326442,0.00003402929,0.000006430737,0.0001056325,0.00001904734,0.9771347,0.0002319321,0.003097704,0.01875703,0.0001617232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001467369,0.00004410333,0.9944399,0.0005430471,0.001729994,0.0003699114,0.0000268501,0.0002313771,0.001147466],"genre_scores_gemma":[0.6035504,5.026927e-7,0.3956171,0.0003759789,0.0002877887,0.00003141219,0.00007129092,0.000007481575,0.00005799459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.977079,"threshold_uncertainty_score":0.9998335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2014306350","doi":"10.1007/s11222-010-9175-2","title":"Extending mixtures of multivariate t-factor analyzers","year":2010,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian information criterion; Cluster analysis; Model selection; Multivariate statistics; Curse of dimensionality; Mixture model; Information Criteria; Expectation–maximization algorithm; Mathematics; Computer science; Statistics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.01289836342498767,"gpt":0.2963991425847564,"spread":0.2835007791597687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002796798,0.0001035924,0.0001716839,0.00006765704,0.0001117188,0.000081256,0.0002555086,0.00004591068,0.000005859259],"category_scores_gemma":[0.00009893282,0.00009006667,0.00002571554,0.0001224136,0.00005270778,0.00006814759,0.0001650793,0.00018494,5.701468e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003131262,"about_ca_system_score_gemma":0.00002595619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004082179,"about_ca_topic_score_gemma":0.000005700022,"domain_scores_codex":[0.9991943,0.0000473041,0.0002088611,0.0002393771,0.0001225555,0.000187605],"domain_scores_gemma":[0.9992345,0.0002763735,0.0001296517,0.0002227157,0.00005296512,0.00008376814],"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":[0.000001013753,0.0000107999,0.0001993525,0.00001481802,0.00001095094,0.000006620906,0.0004397115,0.000005217829,0.0191437,0.5448049,0.00004479828,0.4353181],"study_design_scores_gemma":[0.0003126677,0.0000549071,0.01141681,0.00003124712,0.00001292989,0.0000249806,0.000009028856,0.8369298,0.00554389,0.1449541,0.0004549629,0.0002546998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02835454,0.00005817916,0.9706005,0.00003922575,0.0004299376,0.00004864431,0.00001512082,0.00003217701,0.0004217135],"genre_scores_gemma":[0.4751455,0.000003469835,0.5247736,0.00002726285,0.00003178213,2.091145e-7,7.949167e-7,0.000003547289,0.00001385813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8369246,"threshold_uncertainty_score":0.3672812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109904733","doi":"10.2307/3315985","title":"Estimating the number of clusters","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute","keywords":"Estimator; Nonparametric statistics; Computation; Mathematics; Constant (computer programming); Random variate; Cluster (spacecraft); Set (abstract data type); Function (biology); Population; Data set; Algorithm; Applied mathematics; Probability density function; Statistics; Computer science; Combinatorics; Random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.01626948947403848,"gpt":0.2627838807639077,"spread":0.2465143912898692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004266874,0.00005873208,0.00012464,0.00004200073,0.00008740363,0.00006050323,0.0005211158,0.00002478785,0.000198356],"category_scores_gemma":[0.00008647767,0.00004103359,0.00003403552,0.0001306333,0.00007866458,0.0001110852,0.000007258458,0.0001461414,0.000007479269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012931,"about_ca_system_score_gemma":0.0005896848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007854907,"about_ca_topic_score_gemma":0.0006802859,"domain_scores_codex":[0.9992975,0.00007443649,0.0002796644,0.00005773209,0.000127794,0.0001628536],"domain_scores_gemma":[0.9991592,0.0001396606,0.0001551063,0.0001747864,0.0001355378,0.0002357708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002296043,0.000004957738,0.0004482499,0.00001397379,0.00002465161,0.0001465761,0.001899905,0.001162404,0.000005765542,0.133256,0.01396492,0.8490703],"study_design_scores_gemma":[0.0006977001,0.0001591532,0.005304284,0.0002234156,0.00007421098,0.002103501,0.00006621882,0.4305762,0.0001116895,0.54,0.02032536,0.0003583523],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002592858,0.00006651093,0.993228,0.0005631827,0.000317164,0.00002592249,0.0000233783,0.000001687029,0.003181319],"genre_scores_gemma":[0.1156956,0.000004386557,0.8836773,0.0003350122,0.00006959558,1.858312e-7,2.518827e-7,0.000004344545,0.0002133853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8487119,"threshold_uncertainty_score":0.2171859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025952763","doi":"10.1145/1596519.1596523","title":"Random variate generation for exponentially and polynomially tilted stable distributions","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Modeling and Computer Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random variate; Mathematics; Exponential growth; Convolution random number generator; Representation (politics); Random variable; Applied mathematics; Distribution (mathematics); Exponential distribution; Variable (mathematics); Stability (learning theory); Key (lock); Combinatorics; Discrete mathematics; Mathematical analysis; Computer science; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03773040701898536,"gpt":0.2846753339540069,"spread":0.2469449269350215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003180046,0.0001602053,0.0001799642,0.000115781,0.0004796197,0.000279376,0.000175043,0.00009557566,0.000001252889],"category_scores_gemma":[0.00001091727,0.0001572953,0.0000644909,0.0001300268,0.00001158463,0.000473634,0.000009300996,0.0001047822,5.720919e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002199685,"about_ca_system_score_gemma":0.00003233445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001202239,"about_ca_topic_score_gemma":0.000003442108,"domain_scores_codex":[0.9989015,0.00008318352,0.0002676621,0.0004350138,0.0001170893,0.0001954981],"domain_scores_gemma":[0.9992226,0.0001459481,0.00005438563,0.0003673387,0.0001201199,0.00008957693],"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":[0.00004310612,0.00004764998,3.825594e-7,0.00000367349,0.00001344937,2.491876e-7,0.0001808877,0.697825,0.0006622078,0.005641019,0.000006686453,0.2955757],"study_design_scores_gemma":[0.001395675,0.0001801343,0.00002783848,0.00001501373,0.00003134909,0.000003791051,0.00000114348,0.9587752,0.0002600752,0.03909825,0.00004421819,0.0001672728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008773706,0.00007267336,0.9894937,0.0008969858,0.0002606045,0.0003418298,0.00001398346,0.0001351736,0.00001134808],"genre_scores_gemma":[0.5366978,0.00002142543,0.4629867,0.0001671243,0.00008275422,0.00001016893,0.00001426891,0.000004582423,0.00001513475],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5279241,"threshold_uncertainty_score":0.6414315,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050627451","doi":"10.1007/s11222-006-8451-7","title":"Practical Bayesian estimation of a finite beta mixture through gibbs sampling and its applications","year":2006,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Gibbs sampling; Posterior probability; Mixture model; Estimator; Histogram; Bayesian probability; Artificial intelligence; Beta distribution; Pattern recognition (psychology); Mathematics; Computer science; Sampling (signal processing); Conditional probability distribution; Statistics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02906756747162057,"gpt":0.333769758462675,"spread":0.3047021909910544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002570776,0.0001117214,0.0001698613,0.00003754934,0.0001834084,0.0001105036,0.0001086681,0.00005498102,0.000001211947],"category_scores_gemma":[0.00006398759,0.0001072426,0.00001574926,0.000158219,0.0000422574,0.0001452108,0.0001311931,0.0001237018,6.02352e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006478454,"about_ca_system_score_gemma":0.00004024402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000298823,"about_ca_topic_score_gemma":0.0000035604,"domain_scores_codex":[0.9990912,0.00005890342,0.0002703802,0.0002815413,0.0001300627,0.0001678826],"domain_scores_gemma":[0.9987881,0.0007539222,0.0001608381,0.0001625845,0.00008732847,0.0000472563],"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":[0.000001049139,0.00002029768,0.00002755808,0.00005274521,0.000006432906,0.000002273517,0.0001915144,0.0004825162,0.00008987442,0.8747104,0.00007232679,0.124343],"study_design_scores_gemma":[0.0001104302,0.0000244131,0.0004496107,0.00002427226,0.00001486679,0.00002275691,0.000005676688,0.7312534,0.0001708637,0.2674717,0.0003549151,0.00009703719],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003585105,0.0003375218,0.9981812,0.0003675786,0.00004352867,0.000159698,0.00003196905,0.00003480943,0.0004851496],"genre_scores_gemma":[0.312583,0.00001804495,0.6872697,0.00005650343,0.00004346935,0.000002916571,0.000009432907,0.000005235762,0.00001166876],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7307709,"threshold_uncertainty_score":0.4373228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108884300","doi":"10.1109/tpami.2005.166","title":"Online clustering algorithms for radar emitter classification","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Defence Research and Development Canada","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence; Radar; Statistical classification; Algorithm; Pattern recognition (psychology); Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.04733484034962512,"gpt":0.320574049874947,"spread":0.2732392095253219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003212591,0.0002062792,0.0002854686,0.0003699608,0.0001913726,0.0001261383,0.0003900768,0.0000792863,0.00003959184],"category_scores_gemma":[0.000003080036,0.0001778913,0.0002618614,0.0005553485,0.00003632512,0.0002714902,0.000005131626,0.0001962627,0.000008337287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003677999,"about_ca_system_score_gemma":0.00001396474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001300523,"about_ca_topic_score_gemma":0.0006893582,"domain_scores_codex":[0.9985635,0.00007218248,0.0003838769,0.0005612149,0.0001802612,0.0002389579],"domain_scores_gemma":[0.9990808,0.00013456,0.0001012425,0.0004875782,0.00007641983,0.0001194048],"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":[0.000005672892,0.0001525808,0.00001901097,0.00001005112,0.0001710889,0.000001000511,0.000206175,0.003022009,0.0004688417,0.0001652725,0.00001297937,0.9957653],"study_design_scores_gemma":[0.0001096886,0.00007250744,0.0002808992,0.00001234455,0.0002351166,0.000009613113,0.00001377878,0.9582887,0.03975604,0.0005081812,0.0004903215,0.0002228655],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000337736,0.00009992366,0.9970328,0.0020104,0.0001655007,0.0001776657,0.00006217485,0.00008073885,0.00003309469],"genre_scores_gemma":[0.6459587,0.0001783438,0.3525309,0.0009633857,0.00006212848,0.00002827739,0.000007854842,0.000009935928,0.0002604735],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9955425,"threshold_uncertainty_score":0.7254196,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140574335","doi":"10.48550/arxiv.1306.0186","title":"RNADE: The real-valued neural autoregressive density-estimator","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Autoregressive model; Estimator; Computer science; Representation (politics); Density estimation; Artificial neural network; Algorithm; Mixture model; Artificial intelligence; Data modeling; Pattern recognition (psychology); Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04652883767389224,"gpt":0.1932940925685076,"spread":0.1467652548946153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002311031,0.0001899018,0.0001827352,0.00007814523,0.0003772434,0.0001640982,0.00135648,0.00009402305,0.00004365766],"category_scores_gemma":[0.00004071348,0.0001416191,0.0001196985,0.0004390552,0.0001495587,0.000754307,0.0003904099,0.00025827,0.000196718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000602117,"about_ca_system_score_gemma":0.00006876988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003659742,"about_ca_topic_score_gemma":0.0000185822,"domain_scores_codex":[0.9985817,0.0002817599,0.0001251385,0.0005474378,0.00009093465,0.0003730025],"domain_scores_gemma":[0.9984572,0.0001504141,0.0001204489,0.0009376456,0.0001445536,0.0001897312],"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":[0.000007066521,0.00003477402,0.00139902,0.000006504394,0.00003276228,0.0001982652,0.0003577567,0.001026643,0.0004184602,0.9860439,0.003242784,0.007232107],"study_design_scores_gemma":[0.000321494,0.00004400074,0.01107627,0.00001191802,0.00002618953,0.00002419018,0.00003856529,0.8783959,0.0004388377,0.1091127,0.0002563531,0.0002536295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1750544,0.00002062886,0.8198949,0.0006817736,0.0002762466,0.0002094506,8.607747e-7,0.000176692,0.003685099],"genre_scores_gemma":[0.9595979,0.000018498,0.03722296,0.0004588529,0.00006264989,0.000001248645,7.643713e-7,0.00001105096,0.002626027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8773692,"threshold_uncertainty_score":0.5775059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036312115","doi":"10.1016/j.jctb.2004.09.005","title":"Counting connected graphs inside-out","year":2004,"lang":"en","type":"article","venue":"Journal of Combinatorial Theory Series B","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Mathematics; Enumeration; Vertex (graph theory); Connected component; Partition (number theory); Path graph; Degree (music); Discrete mathematics; Graph; Graph power; Line graph; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01152035719613075,"gpt":0.2496369002918883,"spread":0.2381165430957575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002215106,0.0001824383,0.0004029624,0.0001789779,0.0001674329,0.0002136652,0.000900637,0.0001162109,0.00001574541],"category_scores_gemma":[0.00048539,0.000148288,0.0001971452,0.0003489822,0.0001114686,0.001369154,0.0001352193,0.0003982143,0.000005665222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006843424,"about_ca_system_score_gemma":0.000291726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002594495,"about_ca_topic_score_gemma":9.532142e-7,"domain_scores_codex":[0.9982072,0.0003401607,0.0005778778,0.0001749071,0.0004227652,0.00027705],"domain_scores_gemma":[0.9981837,0.0002742025,0.000550685,0.0003500137,0.0004856842,0.0001557686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001321247,0.00006686818,0.00001236331,0.000007734729,0.00004977201,0.00008543013,0.00108926,0.00001331103,0.002477782,0.9909279,0.0001297254,0.005007717],"study_design_scores_gemma":[0.001580543,0.000447909,0.00004856954,0.0000668979,0.00001916931,0.0002799878,0.00005184511,0.000009492752,0.01648496,0.9769621,0.003876231,0.0001723304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03835228,0.0003762661,0.9451465,0.0007964541,0.0110472,0.00008620624,8.184971e-7,0.00006256452,0.004131724],"genre_scores_gemma":[0.8649027,0.0000585509,0.1340518,0.0003357335,0.0005568862,0.000001419561,2.677365e-7,0.00001657401,0.00007612728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8265504,"threshold_uncertainty_score":0.6047011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036631917","doi":"10.1007/s10651-006-0015-7","title":"Hidden Markov models for circular and linear-circular time series","year":2006,"lang":"en","type":"article","venue":"Environmental and Ecological Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Montreal General Hospital","funders":"","keywords":"Series (stratigraphy); Bivariate analysis; Markov chain; Hidden Markov model; Mathematics; Markov model; Applied mathematics; Variable-order Markov model; Time series; Computer science; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.009405148207206006,"gpt":0.2064210615585611,"spread":0.1970159133513551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001764693,0.0001459086,0.0001909655,0.00001635375,0.00018263,0.00006467085,0.0001348982,0.00009584795,0.00005037129],"category_scores_gemma":[0.00001011229,0.0001189415,0.00002912392,0.00002257867,0.000153616,0.0001766803,0.0001800477,0.00007465923,0.0000104252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002625546,"about_ca_system_score_gemma":0.000005175266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005012299,"about_ca_topic_score_gemma":8.113061e-7,"domain_scores_codex":[0.9990622,0.00005250546,0.0001710681,0.0003614015,0.0001075407,0.0002452237],"domain_scores_gemma":[0.9995899,0.0001295234,0.00004585765,0.0001353199,0.000003928904,0.00009545517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006281205,0.0007013271,0.002507284,0.0001455603,0.00008111083,0.0002158798,0.000283131,0.0002455104,0.01512139,0.6728348,0.004392967,0.3034082],"study_design_scores_gemma":[0.0004715102,0.0003165232,0.02699726,0.00000323942,0.0000248611,0.00005986236,0.000007026749,0.248322,0.0002007048,0.7203681,0.002924697,0.0003041312],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02226472,0.0003592212,0.9764444,0.0002062665,0.00004205532,0.0002192979,0.0001698636,0.0000313462,0.0002628046],"genre_scores_gemma":[0.1633265,0.0001275289,0.8355545,0.000217241,0.00005046981,0.00002495318,0.00004052009,0.000007818362,0.0006504467],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3031041,"threshold_uncertainty_score":0.4850292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2094952625","doi":"10.1109/tmi.2011.2165342","title":"Robust Student's-t Mixture Model With Spatial Constraints and Its Application in Medical Image Segmentation","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Mixture model; Expectation–maximization algorithm; Image segmentation; Pixel; Dirichlet distribution; Gaussian; Computer science; Segmentation; Image (mathematics); Algorithm; Artificial intelligence; Mathematics; Pattern recognition (psychology); Applied mathematics; Maximum likelihood; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02112872927693803,"gpt":0.2842474548968144,"spread":0.2631187256198763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007013482,0.0001824861,0.0001963906,0.0001671688,0.000110749,0.00004954415,0.0004249125,0.0001238472,0.00010727],"category_scores_gemma":[0.00001464731,0.0001510427,0.0000351807,0.000251029,0.0002072377,0.0004765716,0.000007402326,0.0005590504,0.000007715746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004364671,"about_ca_system_score_gemma":0.0001835061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006802133,"about_ca_topic_score_gemma":0.0001396877,"domain_scores_codex":[0.9979221,0.0001376921,0.0002990192,0.0005013475,0.0008571801,0.0002826228],"domain_scores_gemma":[0.9991993,0.00008216698,0.00006328776,0.0002359431,0.00006389144,0.0003553587],"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":[0.00003442922,0.0004088506,0.0001054918,0.00003071376,0.00002301575,0.0001496635,0.002711903,0.0003412913,0.001245618,0.002559794,0.00002170667,0.9923675],"study_design_scores_gemma":[0.001178582,0.00003791275,0.0002538952,0.0001102899,0.00001830912,0.0001490641,0.00007006172,0.9910765,0.00561424,0.001289337,0.000003623847,0.0001981529],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003602631,0.00004155689,0.9935082,0.001546227,0.0001441426,0.0003052371,0.000003045695,0.0000979796,0.0007510192],"genre_scores_gemma":[0.7504133,0.00005435218,0.2485373,0.0008678248,0.00002574066,0.00006919239,0.000001254748,0.00001296648,0.0000181016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9921694,"threshold_uncertainty_score":0.6159342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4249826780","doi":"10.1111/1467-9469.00223","title":"Likelihood Asymptotics","year":2001,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Ottawa Mental Health Centre","funders":"","keywords":"Mathematics; Applied mathematics; Laplace's method; Generalization; Parametric statistics; Statistic; Likelihood-ratio test; Asymptotic analysis; Statistical hypothesis testing; Test statistic; Likelihood principle; Computation; Inference; Marginal likelihood; Laplace transform; Likelihood function; Estimation theory; Maximum likelihood; Statistics; Algorithm; Mathematical analysis; Computer science; Quasi-maximum likelihood; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01240405222427752,"gpt":0.2602093939982498,"spread":0.2478053417739723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005892119,0.0001302842,0.0002551018,0.0001504297,0.00008383118,0.0001359803,0.000691672,0.00005497773,0.00003570922],"category_scores_gemma":[0.0001082994,0.0001075165,0.00007375231,0.0002988055,0.00004692014,0.0003098185,0.000066229,0.0002602838,0.00001540843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000519004,"about_ca_system_score_gemma":0.0001256628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002360513,"about_ca_topic_score_gemma":0.000001687039,"domain_scores_codex":[0.9986476,0.0000992013,0.000453283,0.0001340989,0.0003637408,0.0003020989],"domain_scores_gemma":[0.9986493,0.0001299483,0.0003494087,0.000270714,0.0003258858,0.0002747625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000227286,0.00009575835,0.003288624,0.00001551332,0.00005177858,0.001056194,0.0006276654,0.00001582025,0.0001595154,0.3480384,0.0131619,0.6334661],"study_design_scores_gemma":[0.001296148,0.0009712352,0.008228043,0.0001843355,0.00007049285,0.003712571,0.00004622398,0.00940287,0.0004183064,0.9618265,0.01342818,0.0004150925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009550209,0.0002930677,0.9951751,0.0004734105,0.0008459304,0.00004162541,0.00001263857,0.00001594331,0.002187285],"genre_scores_gemma":[0.1272126,0.0002833522,0.8718057,0.0002309031,0.0002164618,3.339431e-7,7.133638e-7,0.00001021568,0.0002396897],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.633051,"threshold_uncertainty_score":0.4384394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165255548","doi":"10.1155/2009/247646","title":"Merging Mixture Components for Cell Population Identification in Flow Cytometry","year":2009,"lang":"en","type":"article","venue":"Advances in Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Terry Fox Research Institute; Université de Montréal; Montreal Clinical Research Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Mixture model; Identification (biology); Data mining; Pipeline (software); Software; Population; Selection (genetic algorithm); Throughput; Artificial intelligence; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01079761116616644,"gpt":0.2884897705351704,"spread":0.277692159369004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005099905,0.0001203543,0.0001741625,0.0003223301,0.00005549847,0.00007738116,0.0004063072,0.00007637496,6.230386e-7],"category_scores_gemma":[0.00004634248,0.000114618,0.00004093661,0.0006160444,0.00000985354,0.002051827,0.00003366298,0.0001164927,0.000003829621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006871091,"about_ca_system_score_gemma":0.00001060241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002736324,"about_ca_topic_score_gemma":0.000006570768,"domain_scores_codex":[0.9988628,0.00003209702,0.0005267655,0.000163107,0.0001760759,0.0002391338],"domain_scores_gemma":[0.9993482,0.00008066665,0.0001929925,0.0003033658,0.00003658001,0.00003824731],"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":[0.00001216293,0.00009236405,0.001189822,0.0001345735,0.000001354604,0.000001352465,0.001462532,0.003196726,0.0007849854,0.02519943,0.0000524766,0.9678722],"study_design_scores_gemma":[0.0004928651,0.00003772746,0.008889678,0.00005923411,0.000002075631,0.000002246759,0.00002350075,0.9187962,0.001513072,0.06925569,0.0007582684,0.0001694389],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004492773,0.0005406722,0.993175,0.0001965827,0.0003307374,0.0003160784,0.000004094937,0.00004488022,0.0008991457],"genre_scores_gemma":[0.3257069,0.0001332442,0.6739078,0.0001798877,0.00001782145,0.000008899141,0.00002469045,0.000003022762,0.00001770744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9677028,"threshold_uncertainty_score":0.4673988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206548271","doi":"10.1111/2041-210x.13801","title":"Hidden Markov models: Pitfalls and opportunities in ecology","year":2022,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Hidden Markov model; Computer science; Snapshot (computer storage); Process (computing); Data science; Artificial intelligence; Ecology; Machine learning; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.05268794575636098,"gpt":0.3223231908272784,"spread":0.2696352450709174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004884853,0.0001359857,0.0003137271,0.0004198787,0.0002070519,0.00002120408,0.0002949779,0.0001582218,0.00002253647],"category_scores_gemma":[0.00009187197,0.0001464682,0.00002592021,0.0002403899,0.0001329712,0.000329569,0.0006641384,0.0004134681,4.391566e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001729584,"about_ca_system_score_gemma":0.0001106693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007459159,"about_ca_topic_score_gemma":0.0002724401,"domain_scores_codex":[0.9955243,0.003262263,0.0003119023,0.0004615919,0.00007838886,0.0003615018],"domain_scores_gemma":[0.9989836,0.0006085826,0.00008691998,0.0002348863,0.0000201736,0.00006587332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003874314,0.0001050923,0.02176576,0.00002111331,0.00001115292,0.00006699188,0.001547621,0.0002412776,0.0001610292,0.6149306,0.0001838842,0.3609268],"study_design_scores_gemma":[0.0004792501,0.0001735697,0.1398,0.000003683097,0.000005681741,0.0001197222,0.0001692191,0.2286492,0.00001050826,0.629954,0.0004754875,0.0001597282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08249398,0.001316191,0.9116451,0.001971402,0.0005302711,0.0001905025,0.000002570682,0.00003535284,0.001814631],"genre_scores_gemma":[0.2899701,0.0003128041,0.7086961,0.000620281,0.00001717843,0.0001116926,0.000001510046,0.000006012678,0.0002643417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.360767,"threshold_uncertainty_score":0.59728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144245426","doi":"10.1109/tnn.2010.2091428","title":"Count Data Modeling and Classification Using Finite Mixtures of Distributions","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Mixture model; Cluster analysis; Computer science; Pattern recognition (psychology); Artificial intelligence; Data modeling; Expectation–maximization algorithm; Data mining; Mathematics; Statistics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.06841040994015102,"gpt":0.30705565796957,"spread":0.2386452480294189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002730863,0.0001294277,0.000149062,0.00006935414,0.0002259643,0.00008242708,0.0005216588,0.0001246487,0.000004137491],"category_scores_gemma":[0.000006636501,0.0001173447,0.00004373947,0.0002309444,0.00006949506,0.0004581103,0.000009456883,0.0004742753,4.150301e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009466215,"about_ca_system_score_gemma":0.00002730863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002627585,"about_ca_topic_score_gemma":0.00003147444,"domain_scores_codex":[0.9989723,0.00007432298,0.000241408,0.0003833209,0.0001384971,0.0001901787],"domain_scores_gemma":[0.9987435,0.0001588031,0.00007684717,0.0008623133,0.00007226752,0.00008626264],"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":[0.0000219914,0.000125245,0.00000667068,0.00001465317,0.00002908367,0.000002602044,0.00009527194,0.7017992,0.02019012,0.01052649,0.00005432987,0.2671344],"study_design_scores_gemma":[0.0001256689,0.00002206884,0.00001809129,0.00001322749,0.00002659775,0.00001760356,0.000001459575,0.9973598,0.0008158539,0.00144604,0.00003902408,0.0001145954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01164272,0.00008017186,0.9868882,0.0003028357,0.0008228244,0.0001195209,0.00005894568,0.00005934222,0.00002544704],"genre_scores_gemma":[0.8444837,0.00005920474,0.1552862,0.00008371889,0.00005949878,0.000004302088,0.000008705058,0.000007716335,0.000006964681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.832841,"threshold_uncertainty_score":0.4785176,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029217165","doi":"10.1016/j.csda.2014.09.006","title":"Clustering with the multivariate normal inverse Gaussian distribution","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Science Foundation Ireland","keywords":"Mathematics; Inverse Gaussian distribution; Mixture model; Normal-inverse Gaussian distribution; Multivariate normal distribution; Univariate; Gaussian; Generalized inverse Gaussian distribution; Statistics; Cluster analysis; Normal distribution; Bayesian information criterion; Multivariate statistics; Mixture distribution; Covariance; Applied mathematics; Gaussian random field; Gaussian process; Distribution (mathematics); Probability density function; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.02441071631197747,"gpt":0.2880331788376962,"spread":0.2636224625257187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008033668,0.0001510609,0.0002118163,0.00008765271,0.0003380551,0.0003052522,0.00112147,0.00003315074,0.00001824549],"category_scores_gemma":[0.00009263698,0.000102043,0.0000432075,0.0009148151,0.00008553365,0.0004050896,0.0005536236,0.0001366515,0.00001714954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003145169,"about_ca_system_score_gemma":0.00006155846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002728321,"about_ca_topic_score_gemma":0.0005234349,"domain_scores_codex":[0.9983581,0.0002829209,0.0002353924,0.0004942203,0.0004076669,0.0002217127],"domain_scores_gemma":[0.9981121,0.0004884677,0.0001725316,0.0009627922,0.0001612866,0.0001028442],"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":[0.00001881003,0.00006350973,0.0009538177,0.00001773967,0.0008571987,0.00001501446,0.0003370233,0.3358417,0.00000570416,0.5197473,0.009915096,0.1322271],"study_design_scores_gemma":[0.0002010404,0.00002298997,0.02196561,0.000004064371,0.0003478548,0.00000473066,0.000003129701,0.9583609,0.000001294241,0.01663585,0.002303387,0.0001491461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008611817,0.000008240526,0.997566,0.0008848337,0.00005505264,0.00007476995,0.001152815,0.0000456907,0.0001264843],"genre_scores_gemma":[0.17018,0.000002353295,0.8251161,0.0003147993,0.00005360138,0.000004362783,0.00427937,0.000006010198,0.00004340551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6225192,"threshold_uncertainty_score":0.4161194,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285391282","doi":"10.1186/s12874-022-01622-9","title":"Does group-based trajectory modeling estimate spurious trajectories?","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Spurious relationship; Trajectory; Group (periodic table); Computer science; Statistics; Data mining; Econometrics; Machine learning; Mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.2969045554887873,"gpt":0.4814858611530845,"spread":0.1845813056642972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06369945,0.0002800957,0.000701327,0.0006579676,0.0009644847,0.0001010836,0.003473467,0.0002849789,0.0009789652],"category_scores_gemma":[0.01944599,0.0001907181,0.0002399442,0.001370657,0.0004696315,0.0001855235,0.001612708,0.002588861,0.00001924991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002508617,"about_ca_system_score_gemma":0.002693106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005067118,"about_ca_topic_score_gemma":0.000342809,"domain_scores_codex":[0.9560808,0.03689243,0.0006701403,0.001291584,0.003529687,0.001535341],"domain_scores_gemma":[0.9714215,0.02602224,0.0001016627,0.001313439,0.0002326207,0.0009085155],"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":[0.0004797052,0.0006103415,0.0003591234,0.0003281897,0.00006985704,0.0009321039,0.001979746,0.009021951,0.003272955,0.4216443,0.001776146,0.5595256],"study_design_scores_gemma":[0.0008403413,0.0004450204,0.00006278621,0.00002311127,0.000007151791,0.00007309267,0.00009546171,0.8422306,0.0004638321,0.1519192,0.0035735,0.0002659308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006333249,0.0005972068,0.9871492,0.002649769,0.001873902,0.0004250135,0.000008317417,0.0002845448,0.0006788381],"genre_scores_gemma":[0.0689428,0.00004148172,0.9290143,0.0009164156,0.000342979,0.0004285153,0.0000087825,0.00003841893,0.0002662965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8332086,"threshold_uncertainty_score":0.9999343,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006213144","doi":"10.1139/f05-224","title":"The Gibbs and splitmerge sampler for population mixture analysis from genetic data with incomplete baselines","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Mixture model; Gibbs sampling; Statistics; Markov chain; Mathematics; Population; Markov chain Monte Carlo; Merge (version control); Bayesian probability; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02999587880155407,"gpt":0.2541209905354787,"spread":0.2241251117339246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007848509,0.00009397274,0.0001877782,0.0001274962,0.0006403103,0.0006934235,0.0006517142,0.00002707788,0.000004494534],"category_scores_gemma":[0.00009788747,0.00005219504,0.00003137069,0.0004741837,0.000282257,0.0004615627,0.00003361072,0.00005217001,4.92011e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008971033,"about_ca_system_score_gemma":0.0002631176,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02134659,"about_ca_topic_score_gemma":0.1346287,"domain_scores_codex":[0.9990621,0.00006958582,0.0002630839,0.0002325418,0.0001688026,0.0002038996],"domain_scores_gemma":[0.9989508,0.0003709359,0.0001932374,0.0002595369,0.00005334799,0.0001721877],"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":[0.00002638035,0.00001319584,0.4648564,0.00002027813,0.0003081803,0.00002958182,0.0008901326,0.0003182657,0.00006588505,0.03335546,0.006291269,0.4938249],"study_design_scores_gemma":[0.0003762869,0.0002949963,0.3811823,0.00004526336,0.0003196136,0.0000485596,0.0001537624,0.4552742,0.00001223017,0.1369026,0.02509993,0.0002902915],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1269308,0.00229106,0.8666398,0.003884815,0.0001166774,0.00007124342,0.00003003076,0.000002355284,0.00003322163],"genre_scores_gemma":[0.4137881,0.00004540975,0.5857961,0.0001953482,0.0001272059,0.000001404306,0.000007448361,0.000002974259,0.00003597051],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4935347,"threshold_uncertainty_score":0.9851704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121034387","doi":"10.1111/j.1467-9868.2004.00434.x","title":"Testing for a Finite Mixture Model with Two Components","year":2003,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Likelihood-ratio test; Score test; Applied mathematics; Likelihood function; Null distribution; Estimator; Null (SQL); Statistics; Test statistic; Mixture model; Poisson distribution; Statistical hypothesis testing; Asymptotic distribution; Restricted maximum likelihood; Binomial (polynomial); Marginal likelihood; Maximum likelihood; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.08795022052045552,"gpt":0.3292867301058385,"spread":0.2413365095853829,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003827916,0.0003651433,0.0008314525,0.00003374803,0.0004649198,0.0001577915,0.001005341,0.0001919108,0.00002365328],"category_scores_gemma":[0.01106982,0.0002161029,0.0002831097,0.0003507345,0.000587829,0.0002202779,0.0001843962,0.0008720869,0.000001670612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009788113,"about_ca_system_score_gemma":0.0003468573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001092542,"about_ca_topic_score_gemma":0.000003130108,"domain_scores_codex":[0.9956539,0.001773893,0.0008434337,0.0004521019,0.0005815933,0.0006950518],"domain_scores_gemma":[0.9840247,0.01398351,0.0005692849,0.0004510802,0.0005941371,0.0003773051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002312375,0.0001277249,0.0001557435,0.00008923461,0.000196594,0.00003375056,0.0003915115,0.006634693,0.000578999,0.9683393,0.005172855,0.0180483],"study_design_scores_gemma":[0.001236307,0.0007174589,0.0007042033,0.00005746749,0.000179973,0.0002255483,0.00002883649,0.3550229,0.0003026618,0.6397171,0.001518638,0.0002889274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002446497,0.00009481388,0.9968132,0.001349551,0.0005396464,0.0003224388,0.0001599097,0.00003386713,0.0004419577],"genre_scores_gemma":[0.0111607,0.00000382893,0.9870731,0.001306527,0.0001213233,0.00001779716,0.000002611107,0.00003401712,0.0002800538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3483882,"threshold_uncertainty_score":0.9972603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}