{"meta":{"query_hash":"2d3804620fa3","filters":{"topic":"Bayesian Methods and Mixture Models"},"cohort_total":1238,"direct_labels_cover":4,"predictions_cover":1238,"exported":1238,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/2d3804620fa3","api":"https://metacan.xera.ac/api/v1/cohort?topic=Bayesian+Methods+and+Mixture+Models"},"results":[{"id":"W10167074","doi":"10.1016/s0840-4704(10)61152-0","title":"Bayesian mixture modelling of species divergence","year":2004,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Divergence (linguistics); Econometrics; Mathematics; Computer science; Statistics; Artificial intelligence; Environmental science","score_opus":0.03293456059957325,"score_gpt":0.2660701383594805,"score_spread":0.23313557775990726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W10167074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021797369,0.00064655434,0.9755389,0.014738972,0.0004903926,0.0003653714,0.000005243327,0.00012760876,0.007868996],"genre_scores_gemma":[0.43638036,0.0003542452,0.56167626,0.0009660994,0.000031932803,0.000013280893,0.0000022874292,0.000010164984,0.0005653663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813724,0.00006794624,0.00037192713,0.00048794225,0.0004047501,0.00053018867],"domain_scores_gemma":[0.9988228,0.000017752433,0.00014348917,0.000782551,0.00008285202,0.00015055639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033766538,0.00019373774,0.0002542687,0.00018218608,0.00017713987,0.00005089386,0.00088735967,0.000081398925,0.000011406558],"category_scores_gemma":[0.0000037643263,0.00017888314,0.00011714994,0.0005106608,0.000044227352,0.00028986044,0.00045660723,0.00015923138,0.000011765133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051851002,0.000042434665,0.0002213468,0.00021702364,0.000020727333,0.00002784564,0.00041150607,0.0034847597,0.000012976529,0.9484425,0.00044678975,0.046666916],"study_design_scores_gemma":[0.0007525232,0.00022536164,0.00059690594,0.00032894374,0.000022744773,0.000012893254,0.00032539442,0.0536412,0.0014158327,0.9267943,0.015358276,0.0005256327],"about_ca_topic_score_codex":0.00015565891,"about_ca_topic_score_gemma":0.00003845871,"teacher_disagreement_score":0.43616238,"about_ca_system_score_codex":0.000076337565,"about_ca_system_score_gemma":0.000043535154,"threshold_uncertainty_score":0.7294643},"labels":[],"label_agreement":null},{"id":"W113727947","doi":"","title":"Credibililty Theory for Generalized Linear and Mixed Models","year":2006,"lang":"en","type":"article","venue":"Spectrum Research Repository (Concordia University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generalized linear model; Generalized linear mixed model; Estimator; Credibility; Econometrics; Mathematics; Credibility theory; Hierarchical generalized linear model; Linear model; Covariate; Generalized estimating equation; Statistical model; Statistics","score_opus":0.0424995407842404,"score_gpt":0.28794645728081425,"score_spread":0.24544691649657385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W113727947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123371415,0.00023499479,0.8456461,0.0006317371,0.0002731168,0.00045101563,0.000006494045,0.00014487408,0.029240299],"genre_scores_gemma":[0.8505905,0.00006699748,0.12603807,0.0000322715,0.0004841917,0.00000846723,0.0000051522716,0.00002850913,0.022745803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969307,0.00095384486,0.00020611152,0.0008028779,0.00039598384,0.0007104704],"domain_scores_gemma":[0.9980894,0.0005759504,0.00007575967,0.00077853777,0.00022736967,0.00025301898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016463911,0.00019641459,0.00028227616,0.0005143953,0.00071913627,0.00019871457,0.000983272,0.00015899287,0.0000032850382],"category_scores_gemma":[0.000046032834,0.0001958917,0.00015047222,0.00070088275,0.00031906864,0.00071043975,0.00049773697,0.0003497801,0.0000026890652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014917162,0.00006049944,0.0003920129,0.000031079126,0.000031765532,0.00013112808,0.000089641966,0.000086060136,0.005987257,0.98771036,0.0013725762,0.0039584585],"study_design_scores_gemma":[0.0017517344,0.00036772038,0.002206295,0.000024240671,0.000032639517,0.000052948562,0.000060769584,0.103879094,0.043482512,0.8313458,0.016361583,0.00043469013],"about_ca_topic_score_codex":0.0021954065,"about_ca_topic_score_gemma":0.00051252224,"teacher_disagreement_score":0.7272191,"about_ca_system_score_codex":0.00017531712,"about_ca_system_score_gemma":0.00032798562,"threshold_uncertainty_score":0.7988232},"labels":[],"label_agreement":null},{"id":"W113759710","doi":"","title":"Random mappings with a given number of cyclical points","year":2010,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Combinatorics; Random permutation; Permutation (music); Digraph; Joint probability distribution; Poisson distribution; Order (exchange); Section (typography); Distribution (mathematics); Dirichlet distribution; Random graph; Discrete mathematics; Statistics; Mathematical analysis; Symmetric group","score_opus":0.007285254594997016,"score_gpt":0.25104156829735746,"score_spread":0.24375631370236045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W113759710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39661014,0.000010009367,0.58986723,0.00117996,0.001080154,0.00017402385,0.0000010878795,0.00008561465,0.0109918015],"genre_scores_gemma":[0.68053365,0.0000015972284,0.31918234,0.00013123346,0.000007739202,0.000009208555,4.6916978e-7,0.000008637407,0.00012511104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891126,0.00008828048,0.00020212529,0.0003067319,0.0002558377,0.00023577175],"domain_scores_gemma":[0.9988899,0.00014981408,0.00010646107,0.0006185078,0.00011037237,0.00012489798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047874963,0.00013522555,0.00026907868,0.000042243642,0.000054946493,0.00004749947,0.0006641895,0.00010037743,0.000035313606],"category_scores_gemma":[0.000059546786,0.0001036371,0.000070243004,0.0002729312,0.000093780916,0.00022806537,0.00015162588,0.00029358896,0.00003416487],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030712723,0.00008896446,0.0018116528,0.000009542637,0.00001975949,0.000011998653,0.00033040956,1.1978204e-7,0.0025034884,0.9882724,0.00073736085,0.0061835623],"study_design_scores_gemma":[0.002821829,0.00007440608,0.0025511328,0.000025940091,0.000010917779,0.00007209303,0.0000033775023,0.0011830323,0.0060577705,0.9842681,0.002733148,0.00019823006],"about_ca_topic_score_codex":0.000024396828,"about_ca_topic_score_gemma":0.000002948991,"teacher_disagreement_score":0.28392354,"about_ca_system_score_codex":0.000007639958,"about_ca_system_score_gemma":0.000055076103,"threshold_uncertainty_score":0.42261985},"labels":[],"label_agreement":null},{"id":"W114980831","doi":"10.1007/978-3-662-43984-5_2","title":"Online Data Clustering Using Variational Learning of a Hierarchical Dirichlet Process Mixture of Dirichlet Distributions","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hierarchical Dirichlet process; Dirichlet process; Computer science; Dirichlet distribution; Cluster analysis; Generalized Dirichlet distribution; Hierarchical clustering; Latent Dirichlet allocation; Mixture model; Artificial intelligence; Data mining; Concentration parameter; Flexibility (engineering); Pattern recognition (psychology); Algorithm; Dirichlet's energy; Machine learning; Mathematics; Topic model; Statistics; Bayesian probability","score_opus":0.03894781772483317,"score_gpt":0.3141210490527649,"score_spread":0.2751732313279317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W114980831","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013413631,0.00025380583,0.9979294,0.0004082743,0.00055226474,0.0002671213,0.00015237708,0.000058660975,0.00024396506],"genre_scores_gemma":[0.11024703,0.000016967684,0.8890275,0.00016993616,0.00035676832,0.000001947224,0.00011523615,0.00002557315,0.000039059876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958925,0.00014850509,0.00087316247,0.0014708362,0.0010943385,0.00052062044],"domain_scores_gemma":[0.9960004,0.0008346697,0.00075186766,0.0017730872,0.00048069924,0.00015924026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016868653,0.0004545043,0.00082883495,0.00060015847,0.00022042713,0.00014761058,0.004597502,0.00036840115,0.000009546019],"category_scores_gemma":[0.0004872914,0.00041376555,0.00012313268,0.0008649776,0.00069704436,0.000465965,0.002899345,0.0011802904,8.233435e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024314837,0.00020831333,0.00018658693,0.0005148875,0.000069250054,0.000031433712,0.0012728974,0.18603204,0.0014431999,0.13190785,0.000015554097,0.67829365],"study_design_scores_gemma":[0.00020132336,0.00009471874,0.00012275041,0.0005491875,0.00002385222,0.000054992714,1.0630707e-7,0.8824409,0.00029727517,0.11560312,0.0002486885,0.0003630438],"about_ca_topic_score_codex":0.000021660004,"about_ca_topic_score_gemma":0.00002498744,"teacher_disagreement_score":0.69640887,"about_ca_system_score_codex":0.0001126742,"about_ca_system_score_gemma":0.00081536657,"threshold_uncertainty_score":0.99983144},"labels":[],"label_agreement":null},{"id":"W1155720097","doi":"10.3233/mas-2006-1406","title":"Multivariate Poisson Markov-dependent finite mixture models for analysis of weed counts","year":2006,"lang":"en","type":"article","venue":"Model Assisted Statistics and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Poisson distribution; Multivariate statistics; Markov chain; Mathematics; Statistics; Weed; Poisson regression; Multivariate analysis; Markov model; Computer science; Agronomy; Biology; Demography; Sociology; Population","score_opus":0.026928538223800418,"score_gpt":0.29867413302431534,"score_spread":0.2717455948005149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1155720097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000151378745,0.00009657152,0.9952265,0.00009848184,0.00001789152,0.0003265669,0.0016908047,0.000029829878,0.0024981871],"genre_scores_gemma":[0.12252086,0.000012040002,0.87583774,0.000054536085,0.000017654342,0.00021179518,0.00016823951,0.000008645461,0.001168515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991519,0.000024063691,0.00025699957,0.00029057238,0.00013650967,0.00013999823],"domain_scores_gemma":[0.99912715,0.00017849567,0.00013741784,0.00033292765,0.00017362749,0.000050405204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016657088,0.00010906762,0.0002220183,0.00013347511,0.00010610485,0.00005468357,0.00020671636,0.000070381146,0.0000034544732],"category_scores_gemma":[0.000008075412,0.000101419246,0.00006046907,0.00033847138,0.000028721732,0.000062841056,0.000046005025,0.000058575246,8.230281e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037594687,0.0000720489,0.000004439419,0.000018970426,0.00008654549,2.4251088e-7,0.00003302277,0.026822897,0.00054974767,0.9186401,0.0008257852,0.052942473],"study_design_scores_gemma":[0.00013158881,0.000006558509,0.00022608756,0.0000025387687,0.00017245015,3.064758e-7,9.31694e-7,0.7331003,0.00002899218,0.26559132,0.00065534166,0.00008361215],"about_ca_topic_score_codex":0.00007658772,"about_ca_topic_score_gemma":0.000028700835,"teacher_disagreement_score":0.7062774,"about_ca_system_score_codex":0.000015784031,"about_ca_system_score_gemma":0.000036954858,"threshold_uncertainty_score":0.41357568},"labels":[],"label_agreement":null},{"id":"W1171051319","doi":"10.1007/s10463-015-0521-1","title":"Erratum to: Parameterizing mixture models with generalized moments","year":2015,"lang":"en","type":"erratum","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Applied mathematics; Statistics; Generalized method of moments; Econometrics; Statistical physics; Physics; Estimator","score_opus":0.0921754455224483,"score_gpt":0.33773490636735914,"score_spread":0.24555946084491084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1171051319","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000056790737,0.00028259822,0.9703566,0.0014295197,0.004491235,0.0005792342,0.00034385113,0.000039712104,0.022420501],"genre_scores_gemma":[0.00056314905,0.000095587064,0.98723346,0.0007162142,0.00014210153,0.00003101148,0.000030532345,0.00004939135,0.011138578],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965862,0.00015633178,0.0009685723,0.0005390845,0.0012642456,0.00048554954],"domain_scores_gemma":[0.9962206,0.00015625519,0.00081814395,0.0017603297,0.00072724995,0.00031745146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008457902,0.0005170712,0.0012924348,0.0001635728,0.000089910216,0.00010763713,0.0025012577,0.0003760296,0.000004627494],"category_scores_gemma":[0.00049171405,0.0003176579,0.00019444604,0.0005462528,0.00033770708,0.00034904515,0.00080064655,0.0006172091,0.00000484358],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018406363,0.000156058,1.2469616e-7,0.00064026174,0.00014839807,0.000014374255,0.0006074938,0.000433654,0.00005326412,0.47581732,0.5194971,0.0026135428],"study_design_scores_gemma":[0.00027279626,0.00026953119,0.0000024656176,0.0016258297,0.00011342409,0.000027451915,0.000008391662,0.050973974,0.00061810424,0.92514384,0.020490516,0.0004536628],"about_ca_topic_score_codex":0.000044755176,"about_ca_topic_score_gemma":0.000012675888,"teacher_disagreement_score":0.49900657,"about_ca_system_score_codex":0.000030075842,"about_ca_system_score_gemma":0.0006188098,"threshold_uncertainty_score":0.9999275},"labels":[],"label_agreement":null},{"id":"W125715638","doi":"10.1007/978-1-4419-8342-8_4","title":"Familial Models for Count Data","year":2011,"lang":"en","type":"book-chapter","venue":"Springer series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Count data; Covariate; Poisson distribution; Poisson regression; Family member; Correlation; Random effects model; Statistics; Mathematics; Medicine; Demography; Population; Sociology; Family medicine; Internal medicine","score_opus":0.10343775658441684,"score_gpt":0.3041369732503587,"score_spread":0.20069921666594187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125715638","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.38541e-8,0.00044011435,0.85982937,0.000042203676,0.0013014076,0.0003921549,0.0028063962,0.0000700991,0.13511819],"genre_scores_gemma":[0.000025612708,0.00076728954,0.90116155,0.00015907004,0.00020979198,0.00002360157,0.00018435197,0.0000667816,0.097401924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978127,0.00002461783,0.00052980887,0.0009313389,0.00030251613,0.00039904017],"domain_scores_gemma":[0.99699503,0.00017998577,0.00023300498,0.002320478,0.0001685764,0.000102922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055852276,0.0004085087,0.0005439481,0.00013648253,0.00007935371,0.00011825404,0.0024027645,0.00031941192,0.000033352066],"category_scores_gemma":[0.00006091997,0.00041944982,0.000053404183,0.000034020908,0.00015135632,0.00059420126,0.0013458568,0.00037574806,0.000015958418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002202911,0.000010274926,5.435068e-7,0.00009852987,0.000026222213,0.000036344598,0.0002692486,0.0000089167015,0.0000014470378,0.9059877,0.0062207584,0.08731798],"study_design_scores_gemma":[0.00016360747,0.0000671149,0.0000030687602,0.0000753265,0.000025797774,0.0000072536254,0.0000011749258,0.028725624,0.0000072255784,0.77988917,0.19064417,0.000390482],"about_ca_topic_score_codex":0.000039241884,"about_ca_topic_score_gemma":0.00017995037,"teacher_disagreement_score":0.18442342,"about_ca_system_score_codex":0.00007229088,"about_ca_system_score_gemma":0.00026173078,"threshold_uncertainty_score":0.9998257},"labels":[],"label_agreement":null},{"id":"W133532789","doi":"","title":"Unsupervised Selection and Estimation of Non-Gaussian Mixtures for High Dimensional Data Analysis","year":2014,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Mixture model; Gaussian; Computer science; Artificial intelligence; Generalized inverse Gaussian distribution; Gaussian process; Machine learning; Model selection; Density estimation; Probability distribution; Algorithm; Data mining; Pattern recognition (psychology); Gaussian random field; Mathematics; Statistics","score_opus":0.026601273924710688,"score_gpt":0.3081239003071691,"score_spread":0.2815226263824584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W133532789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12143554,0.00008680518,0.8745643,0.00016854967,0.00036590136,0.0005364962,0.000034913362,0.000050171257,0.0027573581],"genre_scores_gemma":[0.9062763,0.000038135102,0.08675674,0.00000600698,0.00015378073,0.000005007414,0.00069344934,0.000023935732,0.006046652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684477,0.00059729733,0.00032406315,0.0011442548,0.00065222435,0.0004374029],"domain_scores_gemma":[0.99742985,0.00048090945,0.00029030352,0.00119709,0.00038848293,0.0002133451],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012619026,0.00026446357,0.00058978813,0.0019794928,0.00054911635,0.00017787585,0.0015118971,0.0003552179,0.0000057193315],"category_scores_gemma":[0.00011219808,0.00027413573,0.00016662515,0.0020519227,0.00010520569,0.0005941223,0.00034403027,0.00049428444,0.0000010607689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003913001,0.0010161182,0.008477121,0.0042256503,0.010271242,0.00032381568,0.0028335238,0.0041095745,0.114701785,0.5972623,0.005865266,0.2470006],"study_design_scores_gemma":[0.0012254115,0.0007158657,0.054456327,0.00017285378,0.0010416838,0.000011191468,0.000068741785,0.8645735,0.059156165,0.017104989,0.0008030144,0.0006702649],"about_ca_topic_score_codex":0.0058220876,"about_ca_topic_score_gemma":0.0056545828,"teacher_disagreement_score":0.8604639,"about_ca_system_score_codex":0.00012308783,"about_ca_system_score_gemma":0.0006304649,"threshold_uncertainty_score":0.9999711},"labels":[],"label_agreement":null},{"id":"W1409342234","doi":"10.1007/s11063-015-9466-x","title":"Model-Based Clustering Based on Variational Learning of Hierarchical Infinite Beta-Liouville Mixture Models","year":2015,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Huaqiao University","keywords":"Cluster analysis; Dirichlet distribution; Computer science; Categorization; Artificial intelligence; Bayes' theorem; BETA (programming language); Computational intelligence; Hierarchical clustering; Hierarchical Dirichlet process; Machine learning; Mathematics; Pattern recognition (psychology); Latent Dirichlet allocation; Topic model; Bayesian probability","score_opus":0.04569327713784346,"score_gpt":0.27489989022956135,"score_spread":0.2292066130917179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1409342234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005973484,0.00003514786,0.98388535,0.008687683,0.00016478766,0.00012365259,0.000002610228,0.00016784556,0.00095942785],"genre_scores_gemma":[0.55655295,1.5836727e-7,0.43756026,0.005783018,0.000058688547,0.0000084380345,0.0000050790427,0.000016528733,0.000014905077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977745,0.00026046677,0.0003638847,0.0005300307,0.00068359496,0.00038754608],"domain_scores_gemma":[0.99890393,0.00016345571,0.00022166455,0.00035536577,0.00015235326,0.00020320344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062903675,0.00025281738,0.00031344654,0.0002585888,0.00016899986,0.00017515774,0.0006324798,0.00012033474,0.0000019089005],"category_scores_gemma":[0.0000806019,0.00022776231,0.00011394456,0.00043102197,0.00008490044,0.0005841141,0.00010864667,0.0005773437,0.0000017208323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050848328,0.000038632537,0.000032944805,0.0000549828,0.000004531781,0.000008654847,0.0006310908,0.964654,0.002910173,0.003359289,0.00016685229,0.028087992],"study_design_scores_gemma":[0.0006964363,0.00009529198,0.0000281803,0.000088459456,0.000010649409,0.0000046457412,0.0000026359278,0.99004406,0.00058924017,0.008146335,0.00005258466,0.0002414949],"about_ca_topic_score_codex":0.0000060446228,"about_ca_topic_score_gemma":0.0000011358195,"teacher_disagreement_score":0.5505794,"about_ca_system_score_codex":0.000057392102,"about_ca_system_score_gemma":0.00031374354,"threshold_uncertainty_score":0.92878777},"labels":[],"label_agreement":null},{"id":"W144990860","doi":"","title":"SHIFT FUNCTION PLOTS FOR REGRESSION FITTING","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nonparametric regression; Regression analysis; Mathematics; Statistics; Estimator; Semiparametric regression; Function (biology); Nonparametric statistics; Regression; Plot (graphics); Regression diagnostic; Parametric statistics; Econometrics; Polynomial regression","score_opus":0.023811642410057322,"score_gpt":0.285761821416708,"score_spread":0.26195017900665063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W144990860","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085132825,0.00006551215,0.9924203,0.0015881377,0.0003909811,0.00013320871,3.4567415e-7,0.00018711387,0.004363079],"genre_scores_gemma":[0.21295065,0.00000171747,0.7859244,0.00063638284,0.000089940586,0.000011638791,4.8649486e-7,0.000004827416,0.00037998953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99938697,0.00002097022,0.00010636815,0.00023462894,0.000090974594,0.00016010184],"domain_scores_gemma":[0.9995854,0.000053452088,0.00003804357,0.00024347517,0.000028382954,0.000051261806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031619662,0.0000714793,0.00007714649,0.000037506732,0.000111757596,0.00006392043,0.00021462276,0.00004977148,0.0000060129864],"category_scores_gemma":[0.000031444422,0.00005026199,0.000051879342,0.000107904605,0.0000072142634,0.0002859137,0.00005981946,0.000050673094,0.000010922487],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004878118,0.00001342337,0.000007810497,0.0000063778803,0.0000027938186,7.084053e-7,0.00016903266,0.000021568272,0.00076524954,0.74168015,0.0003206024,0.2570074],"study_design_scores_gemma":[0.00063154224,0.00014542931,0.00085757393,0.00004628512,0.00000601219,0.0000043487303,0.0000057612,0.009822008,0.01086249,0.97288877,0.0045779254,0.00015186713],"about_ca_topic_score_codex":0.0000071894,"about_ca_topic_score_gemma":0.0000033998792,"teacher_disagreement_score":0.25685555,"about_ca_system_score_codex":0.000017975206,"about_ca_system_score_gemma":0.000030830444,"threshold_uncertainty_score":0.20496245},"labels":[],"label_agreement":null},{"id":"W144999544","doi":"10.1007/978-3-642-35527-1_17","title":"Variational Learning of Dirichlet Process Mixtures of Generalized Dirichlet Distributions and Its Applications","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Dirichlet process; Cluster analysis; Computer science; Dirichlet distribution; Hierarchical Dirichlet process; Artificial intelligence; Inference; Nonparametric statistics; Algorithm; Latent Dirichlet allocation; Applied mathematics; Pattern recognition (psychology); Mathematics; Topic model; Artificial neural network; Statistics","score_opus":0.017421766839658275,"score_gpt":0.2790416501951262,"score_spread":0.26161988335546793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W144999544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008742286,0.0032793921,0.9950093,0.00026461837,0.00020758393,0.00041903986,0.000038671667,0.000047797734,0.00064616377],"genre_scores_gemma":[0.23414218,0.00016592524,0.7651794,0.00012206645,0.00022466276,0.00003309594,0.00002176329,0.000017938788,0.000092980066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975213,0.00007518112,0.00056558894,0.00079471996,0.0006551523,0.0003880838],"domain_scores_gemma":[0.997734,0.00050047075,0.0005460306,0.00057220994,0.00049895194,0.00014831443],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009213437,0.00033780726,0.0005441274,0.00043367283,0.00020495823,0.00008952649,0.0013658648,0.0002586326,0.000013161852],"category_scores_gemma":[0.00013765582,0.0002992139,0.00009693925,0.000645072,0.00040969794,0.00039344022,0.0005812824,0.00050657225,0.0000018467878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047097883,0.00005796268,0.00010847914,0.00015529685,0.000023263088,0.0000017055171,0.00069309457,0.0036627897,0.0015256921,0.7167741,0.000005683302,0.2769872],"study_design_scores_gemma":[0.0003689621,0.00010649388,0.0004733945,0.0002538842,0.000045335877,0.000046341993,1.5244723e-7,0.37741593,0.010207958,0.6091498,0.0013120015,0.00061973446],"about_ca_topic_score_codex":0.00000673558,"about_ca_topic_score_gemma":0.000002750161,"teacher_disagreement_score":0.37375313,"about_ca_system_score_codex":0.00005904373,"about_ca_system_score_gemma":0.0003409995,"threshold_uncertainty_score":0.999946},"labels":[],"label_agreement":null},{"id":"W1482041358","doi":"10.1111/biom.12020","title":"Regularization in Finite Mixture of Regression Models with Diverging Number of Parameters","year":2013,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Feature selection; Sample size determination; Regularization (linguistics); Parametric statistics; Computer science; Feature (linguistics); Population; Regression analysis; Regression; Variable (mathematics); Mathematics; Statistics; Artificial intelligence; Machine learning; Medicine","score_opus":0.021378384879803373,"score_gpt":0.2590494504146491,"score_spread":0.23767106553484574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482041358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042870373,0.00013109756,0.95573616,0.00008662992,0.000070204165,0.00014753212,0.0000021745852,0.000016873577,0.00093893387],"genre_scores_gemma":[0.44189683,0.000027501914,0.5579474,0.000025402787,0.0000034494906,0.000003892977,0.0000016380768,0.0000045412444,0.00008932514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989662,0.000086620305,0.00025463986,0.00022821009,0.0003077855,0.00015655492],"domain_scores_gemma":[0.99899864,0.00017945906,0.00021587075,0.00038280728,0.00017357997,0.0000496385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030663598,0.000103283826,0.00021240412,0.0008316477,0.00001973963,0.000028876568,0.0003711476,0.00010077514,0.000004867075],"category_scores_gemma":[0.000097789656,0.0000730919,0.0000379706,0.005003843,0.000043487085,0.000484399,0.00011922901,0.00007861221,0.0000017551283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039285682,0.00045156645,0.02015885,0.00030298645,0.00005372929,0.000014109231,0.0025866425,0.004794162,0.00987331,0.3015404,0.0004865988,0.65969837],"study_design_scores_gemma":[0.0008849195,0.0001661489,0.0056891562,0.00033473395,0.000014893857,0.000008711564,0.000025377174,0.7047323,0.027237345,0.26052523,0.000047667494,0.00033353572],"about_ca_topic_score_codex":0.0000678022,"about_ca_topic_score_gemma":6.2944497e-7,"teacher_disagreement_score":0.6999381,"about_ca_system_score_codex":0.00002029599,"about_ca_system_score_gemma":0.000030561263,"threshold_uncertainty_score":0.29806012},"labels":[],"label_agreement":null},{"id":"W1492735889","doi":"10.1002/9781118162934.ch2","title":"Simple Random Sampling","year":2012,"lang":"en","type":"other","venue":"Wiley series in probability and statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Simple random sample; Cluster sampling; Sampling (signal processing); Poisson sampling; Statistics; Sampling design; Mathematics; Slice sampling; Estimator; Systematic sampling; Population; Bias of an estimator; Sample (material); Simple (philosophy); Importance sampling; Computer science; Minimum-variance unbiased estimator; Monte Carlo method","score_opus":0.02731347166906328,"score_gpt":0.2825683947962894,"score_spread":0.25525492312722614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492735889","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001978366,0.0025550257,0.9595038,0.000060157538,0.00043482517,0.00040027493,0.00026677514,0.00011786926,0.036659285],"genre_scores_gemma":[0.000054674292,0.0010366011,0.9774718,0.00008975401,0.000127634,0.00003463677,0.00003400497,0.000074843985,0.021076009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99848413,0.0002239648,0.00031366368,0.0004623002,0.00015845681,0.00035745997],"domain_scores_gemma":[0.99886763,0.00024867163,0.00013368083,0.0006048336,0.000029371042,0.00011582558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006803381,0.00026118863,0.00046589455,0.00009365107,0.000059111655,0.00009985349,0.00036453895,0.00025137974,0.00018648825],"category_scores_gemma":[0.00021910421,0.00023714411,0.00003106455,0.00014015536,0.0002013763,0.00016087756,0.00025154688,0.00027454074,0.00000647272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018047425,0.000048461712,0.00032933304,0.0003735106,0.000015215693,0.0000056491194,0.0003978838,0.0000018542503,0.0000015941523,0.7794103,0.030200146,0.18919799],"study_design_scores_gemma":[0.0003391111,0.00003534729,0.000110574205,0.00012501239,0.000011458764,0.00000916713,0.0000037459426,0.00080225564,0.0000031349414,0.6724772,0.32580474,0.00027828687],"about_ca_topic_score_codex":0.00010681816,"about_ca_topic_score_gemma":0.00040579605,"teacher_disagreement_score":0.2956046,"about_ca_system_score_codex":0.000029619023,"about_ca_system_score_gemma":0.0000691785,"threshold_uncertainty_score":0.9670456},"labels":[],"label_agreement":null},{"id":"W1498984154","doi":"10.1111/j.1467-9892.2010.00677.x","title":"Random effects mixture models for clustering electrical load series","year":2010,"lang":"en","type":"article","venue":"Journal of Time Series Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Series (stratigraphy); Cluster analysis; Time series; Set (abstract data type); Computer science; Mixture model; Covariance; Hierarchical clustering; Dimension (graph theory); Mathematical optimization; Mathematics; Statistics; Artificial intelligence","score_opus":0.00544687818867112,"score_gpt":0.23948948492075484,"score_spread":0.2340426067320837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498984154","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023535811,0.00041710548,0.9948007,0.00150064,0.00036193,0.00014428077,0.0000028517698,0.000032970063,0.00038596883],"genre_scores_gemma":[0.03767653,0.00009550896,0.95976067,0.00020416213,0.00039971093,0.00000846083,0.0000013812343,0.000017767941,0.0018358269],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818027,0.0001499605,0.00058014574,0.0002789474,0.0004526581,0.00035802968],"domain_scores_gemma":[0.99796116,0.0003146724,0.00048005395,0.00046465013,0.0005689845,0.00021047742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013859528,0.0002301245,0.0008681487,0.00038322312,0.00017972488,0.0002932331,0.0008589457,0.00017061138,0.000026925998],"category_scores_gemma":[0.00025249764,0.00017084683,0.0009326309,0.0010596683,0.000050818657,0.0015511482,0.0001226112,0.00043840148,0.000002996656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064532002,0.0008178275,0.0003382612,0.00053206366,0.01945204,0.000591543,0.0061681247,0.072337784,0.29769066,0.101601884,0.020527754,0.47348884],"study_design_scores_gemma":[0.0020412793,0.00071253313,0.000088822206,0.000030305479,0.0019092999,0.0004465005,0.000007979483,0.9042366,0.013610049,0.070949614,0.0055043777,0.00046260745],"about_ca_topic_score_codex":0.0000074650175,"about_ca_topic_score_gemma":0.000038364775,"teacher_disagreement_score":0.83189887,"about_ca_system_score_codex":0.000043822172,"about_ca_system_score_gemma":0.00015675873,"threshold_uncertainty_score":0.6966932},"labels":[],"label_agreement":null},{"id":"W1504730822","doi":"10.1002/cjs.10122","title":"Tuning the EM‐test for finite mixture models","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta; University of British Columbia","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Applied mathematics; Limiting; Rank (graph theory); Simple (philosophy); Distribution (mathematics); Value (mathematics); Asymptotic distribution; Statistical hypothesis testing; Algorithm; Mathematical optimization; Mathematics; Statistics; Machine learning; Engineering; Mathematical analysis","score_opus":0.055492000598388186,"score_gpt":0.2485196086697573,"score_spread":0.19302760807136912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504730822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048809787,0.00025985963,0.9972485,0.0004269147,0.00053888484,0.00008938064,0.00016844273,0.000003953785,0.0012152772],"genre_scores_gemma":[0.10309841,0.0000121950125,0.8956931,0.0008329785,0.00012550449,0.0000019688462,0.0000013221384,0.000011337222,0.00022315998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902886,0.00007148193,0.0003510038,0.00011514262,0.0001364518,0.00029705712],"domain_scores_gemma":[0.99801016,0.0005853924,0.0002602207,0.00029358274,0.00042220543,0.00042842867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000820348,0.00010957548,0.0001807609,0.00012097284,0.00021086626,0.00014658268,0.000912127,0.000056587887,0.000024588957],"category_scores_gemma":[0.00049753377,0.00007480802,0.00007151806,0.00014207714,0.000059416525,0.00024167582,0.000018266894,0.00023730317,0.000002281126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042289184,0.000009697896,0.00007816487,0.000013332577,0.000030327374,0.00016713334,0.00841981,0.00015373854,0.000014760229,0.85048956,0.03156945,0.10904982],"study_design_scores_gemma":[0.00024203515,0.00019365163,0.00031732948,0.0000373611,0.00003241392,0.00015605324,0.00008702553,0.1606929,0.000066189015,0.8282389,0.009782343,0.00015381449],"about_ca_topic_score_codex":0.00028997377,"about_ca_topic_score_gemma":0.0032405416,"teacher_disagreement_score":0.16053917,"about_ca_system_score_codex":0.000040707266,"about_ca_system_score_gemma":0.0008744568,"threshold_uncertainty_score":0.30505827},"labels":[],"label_agreement":null},{"id":"W1506273682","doi":"","title":"BAYES AND EMPIRICAL BAYES ESTIMATORS WITH THEIR UNIQUE SIMPLER FORMS AND THEIR SUPERIORITIES OVER BLUE IN TWO SEEMINGLY UNRELATED REGRESSIONS","year":2011,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Estimator; Bayes' theorem; Mathematics; Covariance matrix; Covariance; Bayes error rate; Bayes estimator; Statistics; Mean squared error; Gaussian; Bayesian probability; Bayes classifier","score_opus":0.03182173418661523,"score_gpt":0.29262410298616265,"score_spread":0.26080236879954743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1506273682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4115376,0.000197657,0.5858341,0.00018176736,0.000029390369,0.00013541886,0.0000036539495,0.00009693608,0.0019834954],"genre_scores_gemma":[0.74611044,0.000057337642,0.25333717,0.00034959574,0.000010352309,0.000014878058,0.0000011387774,0.000016772221,0.00010232183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99859905,0.00014067997,0.0002579277,0.00051424827,0.000108158914,0.00037991907],"domain_scores_gemma":[0.99900585,0.00029015128,0.000055788532,0.00040887226,0.00004714259,0.00019216663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040578304,0.00029911555,0.0003446705,0.00016253273,0.00014819714,0.00012956238,0.00030485503,0.000120356686,0.000030530504],"category_scores_gemma":[0.000029490315,0.00015611894,0.000036270387,0.00031594347,0.00020900265,0.0007008534,0.0002993464,0.0002734624,5.493824e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018275798,0.00032346556,0.26882598,0.00011184979,0.0001650571,0.00017509228,0.10760575,0.000017272856,0.0014517417,0.4341778,0.00068898086,0.18627428],"study_design_scores_gemma":[0.0045693996,0.0011052777,0.16417016,0.00097336416,0.000043031145,0.00096298475,0.0035346923,0.2806771,0.03447841,0.5051073,0.0019723885,0.002405877],"about_ca_topic_score_codex":0.00022989436,"about_ca_topic_score_gemma":0.00040368867,"teacher_disagreement_score":0.33457285,"about_ca_system_score_codex":0.000018430701,"about_ca_system_score_gemma":0.00008841456,"threshold_uncertainty_score":0.6366346},"labels":[],"label_agreement":null},{"id":"W1510262632","doi":"10.1007/s00357-019-09319-3","title":"A Mixture of Coalesced Generalized Hyperbolic Distributions","year":2019,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo; MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Bayesian information criterion; Identifiability; Mathematics; Convexity; Hyperbolic function; Applied mathematics; Regular polygon; Distribution (mathematics); Selection (genetic algorithm); Function (biology); Class (philosophy); Model selection; Mathematical analysis; Computer science; Statistics; Artificial intelligence; Geometry","score_opus":0.044589174929418086,"score_gpt":0.31198831372007,"score_spread":0.2673991387906519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510262632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012484822,0.0010307805,0.9817224,0.0023809986,0.0013611375,0.00021417966,0.00003154206,0.000018159262,0.0007559663],"genre_scores_gemma":[0.56370044,0.0003779661,0.4353949,0.00006686174,0.00024579023,0.0000053378353,0.000018074214,0.0000109274915,0.00017967058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997845,0.00034265828,0.0009320594,0.00026933986,0.00044890112,0.00016204499],"domain_scores_gemma":[0.99599594,0.00010426396,0.0021077192,0.00088018976,0.0008041894,0.00010770027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000946112,0.00019656795,0.00060815463,0.00023623297,0.00003969381,0.00009492286,0.0012610436,0.00035066638,0.000008878662],"category_scores_gemma":[0.00014474719,0.00016024889,0.00038731046,0.00023619004,0.00005098196,0.00020975347,0.00024670173,0.0007149424,0.0000046945943],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110639616,0.0006151004,0.00061129645,0.0005777118,0.00039876642,0.000016587574,0.0010363173,0.00084043975,0.16854744,0.67137104,0.019754857,0.1361198],"study_design_scores_gemma":[0.0040768445,0.00060458714,0.06726368,0.0021389965,0.0007597637,0.00054072065,0.000055995108,0.28017205,0.055357553,0.5441098,0.043321468,0.0015985535],"about_ca_topic_score_codex":0.000004699643,"about_ca_topic_score_gemma":7.02355e-7,"teacher_disagreement_score":0.55121565,"about_ca_system_score_codex":0.0001082211,"about_ca_system_score_gemma":0.0005916136,"threshold_uncertainty_score":0.653476},"labels":[],"label_agreement":null},{"id":"W1510824546","doi":"10.1920/wp.cem.2017.3917","title":"Testing for homogeneity in mixture models","year":2018,"lang":"en","type":"report","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Economic and Social Research Council","keywords":"Homogeneity (statistics); Mathematics; Statistics; Econometrics","score_opus":0.114413452535506,"score_gpt":0.3455116344777762,"score_spread":0.23109818194227022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510824546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002054688,0.00061102794,0.81617147,0.00013754115,0.0010950518,0.0005233625,0.000017921124,0.00015721258,0.18126588],"genre_scores_gemma":[0.0010935435,0.000046142624,0.98862803,0.0002551459,0.0008228749,0.00011579172,0.000012104787,0.00003987484,0.008986477],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972941,0.000093971845,0.00053298566,0.0010081438,0.0005293224,0.00054143],"domain_scores_gemma":[0.9973398,0.00034226998,0.00025382018,0.0010993466,0.0008392435,0.00012554326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002488186,0.00037459165,0.00061568955,0.00024881552,0.00009326965,0.00015644565,0.0013165253,0.00060086953,0.000008548818],"category_scores_gemma":[0.0004817026,0.00030918902,0.00019679789,0.00049304427,0.000039644314,0.0003202972,0.0003976089,0.00035662772,0.0000055523315],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066679972,0.00011863837,0.00013099305,0.00050735567,0.00005631267,0.00004562937,0.00025772152,0.000060061007,0.00021858515,0.07140133,0.13241841,0.7947783],"study_design_scores_gemma":[0.00038385697,0.00019463252,0.00018255464,0.00037314848,0.000032495038,0.00014573714,0.0000018516814,0.29198995,0.00058390916,0.64991105,0.05521911,0.0009817153],"about_ca_topic_score_codex":0.00031069308,"about_ca_topic_score_gemma":0.00017441125,"teacher_disagreement_score":0.7937966,"about_ca_system_score_codex":0.00017521443,"about_ca_system_score_gemma":0.001445534,"threshold_uncertainty_score":0.99993604},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02817825423091845,"score_gpt":0.3042159619191862,"score_spread":0.27603770768826774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1513873506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007272054,0.00029309138,0.9900172,0.00014289896,0.00017514589,0.00005219457,0.0000047035387,0.00007339964,0.001969357],"genre_scores_gemma":[0.22296214,0.000043639597,0.7765596,0.00029306675,0.00007120952,5.718973e-7,0.0000018709296,0.000005272868,0.00006266254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916923,0.000035013043,0.00018125011,0.00027348183,0.00010382557,0.00023719565],"domain_scores_gemma":[0.9994213,0.00015756741,0.000073918854,0.000207942,0.000050981707,0.000088307024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030371142,0.00009698753,0.00013098665,0.000034496432,0.00018326624,0.00014724207,0.00021065734,0.000028516912,0.0000048117313],"category_scores_gemma":[0.000038313254,0.000091428614,0.000015430422,0.00014534386,0.000024798106,0.00007832657,0.00014491085,0.00009684648,0.0000027909157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.534551e-7,0.0000070618266,0.0012479412,0.0000072898274,0.0000043521936,0.00003664851,0.00020501729,0.000020867214,0.000050310402,0.5157412,0.0002366218,0.4824417],"study_design_scores_gemma":[0.00021684283,0.00004150359,0.006223345,0.000023892471,0.0000050674366,0.00012644536,0.000011770701,0.6799998,0.000021590222,0.3100245,0.0030887735,0.00021646635],"about_ca_topic_score_codex":0.000009558441,"about_ca_topic_score_gemma":0.0000038394255,"teacher_disagreement_score":0.67997897,"about_ca_system_score_codex":0.000008535255,"about_ca_system_score_gemma":0.000021302698,"threshold_uncertainty_score":0.37283507},"labels":[],"label_agreement":null},{"id":"W1521364046","doi":"10.1002/9781118445112.stat07174","title":"Computer Intensive Sampling Methods in Ecology","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; University of Toronto","funders":"","keywords":"Jackknife resampling; Bonferroni correction; Statistics; Statistical hypothesis testing; Statistic; Resampling; Autocorrelation; Econometrics; Randomization; Computer science; Mathematics; Sampling (signal processing); Test statistic; Nonparametric statistics; Sampling distribution; Biology; Bioinformatics; Clinical trial","score_opus":0.06762049489324433,"score_gpt":0.39604354576762835,"score_spread":0.328423050874384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521364046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012177759,0.00065420585,0.9830757,0.00020871713,0.0016253811,0.0004544968,0.0017484264,0.00031337925,0.011918518],"genre_scores_gemma":[0.000007646421,0.0013263297,0.9679545,0.0018243744,0.0004552084,0.000032794327,0.0008072171,0.0003302532,0.02726164],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952077,0.0011171402,0.000942166,0.0014259993,0.00039087425,0.0009160818],"domain_scores_gemma":[0.9960423,0.0011640837,0.0007043386,0.0013881874,0.0004069137,0.000294173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009521839,0.0007639604,0.0014164335,0.00085348,0.000068025496,0.0001511157,0.0016923447,0.0007216535,0.00037031178],"category_scores_gemma":[0.00042518246,0.00070390815,0.00008811233,0.00049095094,0.0002128849,0.000095667885,0.0007625323,0.00124346,0.00012293883],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008436146,0.00011503152,0.00003259639,0.00013705241,0.000064278014,0.00007834541,0.00016446829,0.00002797021,0.00002343705,0.2243198,0.15803297,0.61699563],"study_design_scores_gemma":[0.0010664262,0.00046141044,0.00040977861,0.00094435306,0.00006432186,0.00005103721,0.000018483062,0.13392147,0.00001249417,0.19029394,0.6712557,0.0015005894],"about_ca_topic_score_codex":0.0002895935,"about_ca_topic_score_gemma":0.0012534431,"teacher_disagreement_score":0.615495,"about_ca_system_score_codex":0.00014541947,"about_ca_system_score_gemma":0.0003532272,"threshold_uncertainty_score":0.9995412},"labels":[],"label_agreement":null},{"id":"W1528477830","doi":"10.1090/fic/026/11","title":"Layered multishift coupling for use in perfect sampling algorithms (with a primer on CFTP)","year":2000,"lang":"en","type":"preprint","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Algorithm; Markov chain; Coupling (piping); Sampling (signal processing); Computer science; Distribution (mathematics); Mathematics; Discrete mathematics; Statistics; Engineering; Mathematical analysis","score_opus":0.08746989105590286,"score_gpt":0.3297174097301564,"score_spread":0.24224751867425354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528477830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013255576,0.00011470785,0.98377925,0.00017469433,0.00038243248,0.0014331792,0.000021045262,0.00024100495,0.0005981242],"genre_scores_gemma":[0.041446645,0.000044447755,0.95717114,0.00042005314,0.00015084057,0.0002544055,0.000019282123,0.000053447424,0.00043973443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970527,0.00007176379,0.00045882686,0.0014757864,0.00033495072,0.00060592074],"domain_scores_gemma":[0.9977352,0.0005964521,0.00016447231,0.0012501022,0.000103430226,0.00015032779],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008833741,0.00050322735,0.00064859714,0.00030126987,0.00011021837,0.00058564043,0.0010667355,0.00041435147,0.000018010523],"category_scores_gemma":[0.000047478872,0.00039562135,0.00020013419,0.00022610066,0.000033783785,0.00028084655,0.00044250002,0.00083531725,0.000008099797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043008183,0.0006806711,0.0010779403,0.000391386,0.00022755864,0.00009641686,0.0022131267,0.16644843,0.00028044745,0.032267183,0.00035732394,0.7955294],"study_design_scores_gemma":[0.001096685,0.00018407645,0.0009838706,0.00049498753,0.000019142863,0.000009046425,0.0000046554023,0.98639643,0.0009368624,0.008360798,0.00079384225,0.0007196104],"about_ca_topic_score_codex":0.0005893395,"about_ca_topic_score_gemma":0.00014230124,"teacher_disagreement_score":0.819948,"about_ca_system_score_codex":0.000113124224,"about_ca_system_score_gemma":0.0002358966,"threshold_uncertainty_score":0.99984956},"labels":[],"label_agreement":null},{"id":"W1528693933","doi":"10.1109/icassp.2015.7178328","title":"Online time-dependent clustering using probabilistic topic models","year":2015,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cluster analysis; Probabilistic logic; Data mining; Hierarchical Dirichlet process; Inference; Data stream mining; Dirichlet process; Overhead (engineering); Component (thermodynamics); Algorithm; Machine learning; Latent Dirichlet allocation; Artificial intelligence; Topic model","score_opus":0.10075651030361162,"score_gpt":0.307629924345805,"score_spread":0.2068734140421934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528693933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00348,0.00007077993,0.9863535,0.00031601332,0.00026472477,0.00015478677,0.000001160436,0.0001862746,0.00917275],"genre_scores_gemma":[0.066846006,0.000001405808,0.9300709,0.00036723146,0.00010497348,0.0000031185066,9.752287e-7,0.000010076301,0.0025953415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885535,0.00009335848,0.00020445409,0.00034502777,0.0002455894,0.00025620477],"domain_scores_gemma":[0.9991351,0.000030271192,0.000045247172,0.00050820014,0.00009733498,0.00018384025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043914613,0.00012906,0.0001701132,0.00005956823,0.000046391844,0.00011537983,0.0005368275,0.000060449216,0.000012325433],"category_scores_gemma":[0.000031043885,0.00010496917,0.000042083102,0.00014619864,0.000017774582,0.00048024967,0.0003922621,0.00010060223,0.000022623502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020581756,0.00061107805,0.000035110468,0.00008457188,0.000055819844,0.00010804346,0.0028969005,0.25158283,0.0037696024,0.4271244,0.0011348734,0.3125762],"study_design_scores_gemma":[0.00018914012,0.00002932096,0.0000031024133,0.000010961277,0.0000045685006,0.00003531923,0.000005230911,0.8478913,0.00014309332,0.15146853,0.000093162664,0.00012626972],"about_ca_topic_score_codex":0.00006416556,"about_ca_topic_score_gemma":0.000019118648,"teacher_disagreement_score":0.59630847,"about_ca_system_score_codex":0.00008101356,"about_ca_system_score_gemma":0.00011460621,"threshold_uncertainty_score":0.42805186},"labels":[],"label_agreement":null},{"id":"W1535027478","doi":"10.1007/11590316_26","title":"A New Approach for High-Dimensional Unsupervised Learning: Applications to Image Restoration","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Dirichlet distribution; Flexibility (engineering); Expectation–maximization algorithm; Maximization; Image (mathematics); Artificial intelligence; Unsupervised learning; Hierarchical Dirichlet process; Mathematical optimization; Pattern recognition (psychology); Algorithm; Latent Dirichlet allocation; Topic model; Mathematics; Maximum likelihood; Statistics; Boundary value problem","score_opus":0.02619745687332929,"score_gpt":0.28042772788479464,"score_spread":0.25423027101146534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1535027478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018107257,0.00016307946,0.99386734,0.0018861111,0.000385581,0.0014110259,0.0000057995317,0.00017656613,0.0021026987],"genre_scores_gemma":[0.0011555749,0.00000632744,0.99346733,0.0016496129,0.0010962749,0.00010559112,0.000027401164,0.00003952942,0.0024523716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963632,0.000052830615,0.00047304103,0.0018177846,0.00073009974,0.00056303345],"domain_scores_gemma":[0.997562,0.0003387152,0.00020007227,0.0012111852,0.00034321463,0.00034481997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010774237,0.00046844737,0.0004765012,0.0007014149,0.00036714372,0.0005125763,0.002317581,0.00031703533,0.000018343197],"category_scores_gemma":[0.00008137877,0.0004414143,0.00013064196,0.00066053105,0.00016603079,0.00052302424,0.0006951889,0.00063472753,0.00004379625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008700798,0.000022065376,6.7781644e-7,0.00001987211,0.000005824304,0.0000022223046,0.00027482666,0.034899827,0.0006207936,0.1275557,0.0002717119,0.8363178],"study_design_scores_gemma":[0.00041560383,0.00018182448,0.000013679643,0.00007753826,0.000013172962,0.000025518968,6.0260845e-8,0.6868825,0.0011113234,0.2989165,0.01166547,0.0006968173],"about_ca_topic_score_codex":0.000021262704,"about_ca_topic_score_gemma":0.00001622368,"teacher_disagreement_score":0.83562094,"about_ca_system_score_codex":0.0002601688,"about_ca_system_score_gemma":0.0008130878,"threshold_uncertainty_score":0.9998038},"labels":[],"label_agreement":null},{"id":"W1543408068","doi":"10.1002/0470011815.b2a16077","title":"Systematic Sampling Methods","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Systematic sampling; Sampling (signal processing); Simple random sample; Sampling design; Statistics; Mathematics; Estimator; Variance (accounting); Slice sampling; Stratified sampling; Bias of an estimator; Poisson sampling; Population; Best linear unbiased prediction; Sample (material); Importance sampling; Computer science; Minimum-variance unbiased estimator; Monte Carlo method; Selection (genetic algorithm); Artificial intelligence","score_opus":0.016885655820640867,"score_gpt":0.33374418068611905,"score_spread":0.31685852486547816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1543408068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1039825e-8,0.0031630138,0.58726346,0.00002683725,0.0007588864,0.0002866031,0.0000675435,0.00013116989,0.40830246],"genre_scores_gemma":[5.3083534e-7,0.0017289293,0.7400455,0.00007037441,0.00028602572,0.000016429622,0.000009937234,0.00016282524,0.25767943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977296,0.00044467123,0.00069618074,0.0004812426,0.00033105147,0.00031722803],"domain_scores_gemma":[0.9972028,0.0007647866,0.0007536642,0.0010805133,0.00006677925,0.00013142568],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008377638,0.0003635821,0.00094472105,0.00033809675,0.000031653468,0.000046261506,0.0010708247,0.0003228002,0.00026092748],"category_scores_gemma":[0.00051216537,0.00031496552,0.0001252662,0.00030002798,0.00006861556,0.00005576766,0.00022041691,0.00023953321,0.00005856252],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012417505,0.00006650858,0.000001691816,0.015313141,0.00018207266,0.00001760092,0.0004587352,0.0000018878768,0.000022599728,0.4192356,0.24612686,0.31857207],"study_design_scores_gemma":[0.00037261975,0.00011187753,0.000013469269,0.010089931,0.0003521073,0.000038795013,0.000016754848,0.006372963,0.00010698094,0.03594063,0.9453375,0.0012464279],"about_ca_topic_score_codex":0.000035892128,"about_ca_topic_score_gemma":0.000012031082,"teacher_disagreement_score":0.6992106,"about_ca_system_score_codex":0.0000292706,"about_ca_system_score_gemma":0.00013118226,"threshold_uncertainty_score":0.99993026},"labels":[],"label_agreement":null},{"id":"W1547161846","doi":"10.1016/j.neuroimage.2015.06.094","title":"Estimating anatomical trajectories with Bayesian mixed-effects modeling","year":2015,"lang":"en","type":"article","venue":"NeuroImage","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; Genentech; National Institutes of Health; IXICO; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Deutscher Akademischer Austauschdienst; F. Hoffmann-La Roche; University of Southern California; Wellcome Trust; Synarc; Medpace; Novartis Pharmaceuticals Corporation; Medical Engineering Centre King’s College London; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Bayesian probability; Random effects model; Prior probability; Voxel; Neuroimaging; Inference; Univariate; Covariate; Bayesian inference; Computer science; Statistical inference; Mixed model; Statistical model; Artificial intelligence; Machine learning; Statistics; Psychology; Mathematics; Multivariate statistics; Neuroscience; Medicine","score_opus":0.028313520537936013,"score_gpt":0.27364515912424814,"score_spread":0.24533163858631213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1547161846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033679556,0.00006605883,0.9627833,0.00030390578,0.0005830474,0.00016351821,7.6194124e-7,0.0003135851,0.0021063064],"genre_scores_gemma":[0.4499998,4.1669722e-7,0.5496481,0.00021410327,0.000089351306,0.000007884285,5.262604e-7,0.000015496273,0.000024319874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983364,0.00021091761,0.0001895487,0.00054098194,0.00034390017,0.00037830297],"domain_scores_gemma":[0.9988579,0.00011252148,0.000058184367,0.0005934098,0.000093990624,0.00028400484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039400742,0.00021258654,0.00024558327,0.00008387012,0.000104026105,0.00024159747,0.0005954531,0.00006150587,9.713171e-7],"category_scores_gemma":[0.00015539053,0.00016892099,0.000050882645,0.000335382,0.000046403144,0.0006171867,0.00015508148,0.00026582647,0.000009931821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001457988,0.00042939512,0.0013683372,0.00030288755,0.00008303123,0.002267723,0.007014228,0.03845316,0.008823463,0.31586337,0.0037073754,0.6215412],"study_design_scores_gemma":[0.00043484668,0.00017229351,0.00008186747,0.000027471211,0.00000942533,0.00009574312,0.0000069807293,0.9746271,0.0015197997,0.022751579,0.000058406964,0.00021448998],"about_ca_topic_score_codex":0.000023368762,"about_ca_topic_score_gemma":0.0000041949406,"teacher_disagreement_score":0.9361739,"about_ca_system_score_codex":0.000029559766,"about_ca_system_score_gemma":0.000106042324,"threshold_uncertainty_score":0.6888398},"labels":[],"label_agreement":null},{"id":"W1553958948","doi":"10.1016/j.jspi.2008.04.032","title":"An alternative to the out of bootstrap","year":2008,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Consistency (knowledge bases); Bootstrap aggregating; Dirichlet distribution; Statistic; Bayesian probability; Bayesian information criterion; Dirichlet process; Statistics; Econometrics; Discrete mathematics","score_opus":0.08928200312359241,"score_gpt":0.3817564217446524,"score_spread":0.29247441862106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553958948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018329233,0.00009855909,0.9806085,0.00034680977,0.00015818857,0.00002694305,0.0000077561845,0.0000037933826,0.00042019103],"genre_scores_gemma":[0.65084887,0.000016870412,0.34891057,0.00015915946,0.00005304859,2.685315e-7,1.2658911e-7,0.0000014223599,0.000009690701],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99922645,0.000097235534,0.00025965646,0.00009533013,0.00021136142,0.00010997886],"domain_scores_gemma":[0.9990177,0.0004254285,0.0001443874,0.00012562933,0.00014106103,0.00014575465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041487158,0.000065519554,0.00017005247,0.000051675648,0.0000703217,0.00003597895,0.00036975858,0.000022634451,0.000004051886],"category_scores_gemma":[0.00023211807,0.000038519003,0.00001860091,0.00006456272,0.00008039675,0.00021415194,0.0000416447,0.00018142471,0.0000010763775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011207167,0.00016720437,0.006185714,0.000028441094,0.00007074392,0.00045616904,0.026290493,0.0012343735,0.0020187548,0.59474283,0.005398983,0.36329424],"study_design_scores_gemma":[0.0014473886,0.007036411,0.2541306,0.0006329752,0.00006519791,0.0013416043,0.00030880008,0.1400225,0.0057701105,0.5837986,0.0047316654,0.0007141554],"about_ca_topic_score_codex":0.000008199652,"about_ca_topic_score_gemma":5.496517e-7,"teacher_disagreement_score":0.6325196,"about_ca_system_score_codex":0.00000538708,"about_ca_system_score_gemma":0.00006374601,"threshold_uncertainty_score":0.15707594},"labels":[],"label_agreement":null},{"id":"W1564946725","doi":"10.5281/zenodo.43364","title":"Video Background Subtraction Using Online Infinite Dirichlet Mixture Models","year":2013,"lang":"en","type":"article","venue":"INFM-OAR (INFN Catania)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Background subtraction; Dirichlet distribution; Nonparametric statistics; Mixture model; Computer science; Bayesian probability; Latent Dirichlet allocation; Artificial intelligence; Dirichlet process; Pattern recognition (psychology); Mathematics; Topic model; Pixel; Statistics","score_opus":0.060786302092409886,"score_gpt":0.29776840751670863,"score_spread":0.23698210542429876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564946725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11447703,0.0005042538,0.88025486,0.0011260327,0.0008325608,0.00042908444,0.000030663115,0.00029963595,0.002045899],"genre_scores_gemma":[0.3303184,0.000094921146,0.6660495,0.0023901302,0.0005248015,0.00003244473,0.000042682983,0.000055351145,0.0004917991],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970189,0.0002243721,0.0006250533,0.0008387349,0.0005685346,0.0007244563],"domain_scores_gemma":[0.99739414,0.0002288128,0.00029168025,0.0013853848,0.00036575756,0.00033420132],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005416031,0.00044551177,0.00045771297,0.00026526366,0.00028003237,0.00062974426,0.0011783708,0.00034853644,0.000095417374],"category_scores_gemma":[0.00006041974,0.00041711074,0.0001822505,0.0008180401,0.00009191384,0.00361246,0.00040128097,0.00064279145,0.00022715959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079836966,0.0012899641,0.00095262827,0.00036673958,0.0004094315,0.0002383378,0.0064914348,0.010556839,0.1367503,0.24868704,0.030975113,0.5632023],"study_design_scores_gemma":[0.0008807762,0.00014324352,0.001918275,0.00013970154,0.000066134744,0.0002938002,0.000088841174,0.83735335,0.0025342691,0.13806601,0.01731022,0.0012054086],"about_ca_topic_score_codex":0.0008279019,"about_ca_topic_score_gemma":0.000098597324,"teacher_disagreement_score":0.8267965,"about_ca_system_score_codex":0.00017399713,"about_ca_system_score_gemma":0.0001955161,"threshold_uncertainty_score":0.9998281},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01945512214444693,"score_gpt":0.309683401502441,"score_spread":0.29022827935799406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566710167","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.228118e-7,0.00087715656,0.612748,0.00005203722,0.00016901306,0.0001973479,0.0000025279985,0.00014798722,0.3858051],"genre_scores_gemma":[0.000015027969,0.000058149562,0.62396747,0.0003931178,0.00009933335,0.000017511285,0.000001398954,0.000028418759,0.3754196],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974794,0.00038222593,0.0005798329,0.00091753,0.00023575721,0.00040528062],"domain_scores_gemma":[0.9980194,0.00051571644,0.0002323038,0.0009633579,0.000058881647,0.00021031902],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012918686,0.00049132697,0.0007950595,0.00019630634,0.00012513321,0.0003105533,0.0009813543,0.0004214385,0.00006090032],"category_scores_gemma":[0.000058917598,0.0003913096,0.00017117045,0.00010251588,0.00010159375,0.00023614021,0.00039864294,0.0005769905,0.000019066983],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016649784,0.0000063247694,1.8216623e-7,0.00007181375,0.000026858228,0.000024283998,0.0002837884,0.0000011055131,0.000019073866,0.07499741,0.002934361,0.9216331],"study_design_scores_gemma":[0.00018920978,0.00010897256,0.0000024729427,0.00023890809,0.00007292365,0.0002460014,0.0000028492204,0.29127845,0.00014767461,0.6350766,0.07181535,0.0008206175],"about_ca_topic_score_codex":0.000024575475,"about_ca_topic_score_gemma":0.000003860058,"teacher_disagreement_score":0.9208125,"about_ca_system_score_codex":0.00006421036,"about_ca_system_score_gemma":0.00020125427,"threshold_uncertainty_score":0.9998539},"labels":[],"label_agreement":null},{"id":"W1576685640","doi":"10.1002/9781118162934.ch6","title":"Unequal Probability Sampling","year":2012,"lang":"en","type":"other","venue":"Wiley series in probability and statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Estimator; Probability sampling; Statistics; Sampling (signal processing); Mathematics; Population; Sample (material); Computer science","score_opus":0.04042750769912564,"score_gpt":0.2857076514136626,"score_spread":0.24528014371453696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576685640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011036869,0.0019694935,0.96159846,0.00013581043,0.00067718804,0.0007120604,0.00037680537,0.00020259705,0.03431656],"genre_scores_gemma":[0.000106993415,0.00057633483,0.9827556,0.00007934318,0.00014915931,0.00006697685,0.000035146277,0.00009837488,0.01613204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99750215,0.00039856505,0.0005021117,0.00080300577,0.0002594351,0.0005347312],"domain_scores_gemma":[0.9982838,0.00025929292,0.00021042129,0.0010062838,0.000058148984,0.00018203234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011887637,0.00040070555,0.000604094,0.00012111568,0.000080539794,0.00012921546,0.0005532445,0.0004152749,0.00017448461],"category_scores_gemma":[0.00037725244,0.00037123077,0.000045146156,0.00023794617,0.00040803358,0.00025432586,0.00043179572,0.00047078813,0.000009568802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001110018,0.000109721164,0.00064201624,0.00069233205,0.000014812601,0.0000050349786,0.00052082085,0.000002553131,0.0000014352922,0.8238976,0.008439938,0.16566266],"study_design_scores_gemma":[0.00018105445,0.00008203047,0.0003565122,0.00025743022,0.000016110334,0.00001054784,0.0000054450625,0.00076380797,0.000003634522,0.8529479,0.14491008,0.00046548236],"about_ca_topic_score_codex":0.00014342558,"about_ca_topic_score_gemma":0.00062506885,"teacher_disagreement_score":0.16519718,"about_ca_system_score_codex":0.00007895286,"about_ca_system_score_gemma":0.00015398636,"threshold_uncertainty_score":0.99987394},"labels":[],"label_agreement":null},{"id":"W1585102283","doi":"10.5281/zenodo.38926","title":"A Sequential Feature Selection Algorithm For Gmm-Based Speech Quality Estimation","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Estimator; Benchmark (surveying); Feature selection; Computer science; Feature (linguistics); Mean squared error; Selection (genetic algorithm); Algorithm; Computational complexity theory; Diagonal; Mixture model; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics","score_opus":0.030688428827822804,"score_gpt":0.34460875107645617,"score_spread":0.31392032224863337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1585102283","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010589413,0.000017397173,0.99461615,0.0036378934,0.00019883731,0.0003009485,0.000004260367,0.00025225204,0.00086635596],"genre_scores_gemma":[0.005492528,5.54977e-7,0.9917717,0.0010514219,0.0002494146,0.000030566116,0.0000146863795,0.000007638492,0.0013814631],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989832,0.00011126454,0.00016726558,0.00033666534,0.00018714857,0.00021445159],"domain_scores_gemma":[0.99940926,0.00007990138,0.0000727665,0.00024464744,0.0001243225,0.000069102076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074526574,0.0001170069,0.00013342853,0.000069574475,0.00012275184,0.00013794091,0.00024970574,0.00011464189,0.000022666714],"category_scores_gemma":[0.00003244825,0.00010097672,0.000093696886,0.00023596204,0.000012925538,0.00040878356,0.000027549255,0.00010428398,0.0000111795935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039668557,0.000036382058,0.0000024903743,0.0000077891245,0.000005359326,2.8717312e-7,0.00003738704,0.00026950423,0.0007527589,0.037084572,0.0032205107,0.958579],"study_design_scores_gemma":[0.00041843555,0.000050835704,0.000065245134,0.0000044822395,0.00000629323,0.000008566726,7.829893e-7,0.94059455,0.03781355,0.015685745,0.005212893,0.00013862096],"about_ca_topic_score_codex":0.000038020207,"about_ca_topic_score_gemma":0.0000488612,"teacher_disagreement_score":0.95844036,"about_ca_system_score_codex":0.0000705745,"about_ca_system_score_gemma":0.00009628654,"threshold_uncertainty_score":0.41177112},"labels":[],"label_agreement":null},{"id":"W1587070286","doi":"10.1007/11510888_5","title":"MML-Based Approach for Finite Dirichlet Mixture Estimation and Selection","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Minimum description length; Automatic summarization; Computer science; Dirichlet distribution; Artificial intelligence; Selection (genetic algorithm); Model selection; Unsupervised learning; Pattern recognition (psychology); Bayesian probability; Machine learning; Data mining; Algorithm; Mathematics","score_opus":0.0185513968506605,"score_gpt":0.2607570820387777,"score_spread":0.24220568518811716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1587070286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000043740597,0.0003980859,0.99653244,0.0006973667,0.00035742545,0.0005173636,0.000006857816,0.00013140033,0.0013547083],"genre_scores_gemma":[0.015357377,0.000015387688,0.9823258,0.0016139696,0.00040630318,0.00003302563,0.000013267309,0.000029543597,0.00020531319],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730134,0.00004293885,0.0003545371,0.0013385575,0.0004893525,0.00047324604],"domain_scores_gemma":[0.9983037,0.0005992136,0.0002351551,0.0005307643,0.00018967422,0.00014146425],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009955012,0.00042532192,0.00038668103,0.00058443786,0.00028584193,0.0004905367,0.0010920651,0.00041808584,0.000004494275],"category_scores_gemma":[0.00011703664,0.00039447495,0.00010930787,0.00043414521,0.00028847138,0.0004743378,0.00026658666,0.00052467163,0.0000021600404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007323423,0.000018636083,0.000002843289,0.00006341081,0.0000054729553,0.0000021399708,0.00016495767,0.11355847,0.000064975844,0.0364741,0.000035571375,0.8496021],"study_design_scores_gemma":[0.00026497382,0.0001287568,0.000011025413,0.000091574664,0.000011566222,0.000024664501,1.6982284e-8,0.86484724,0.0008610278,0.13239782,0.0009776138,0.00038371593],"about_ca_topic_score_codex":0.000004377189,"about_ca_topic_score_gemma":0.000010885731,"teacher_disagreement_score":0.84921837,"about_ca_system_score_codex":0.00012407317,"about_ca_system_score_gemma":0.00032953464,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W1588140678","doi":"","title":"A STATISTICAL FRAMEWORK FOR POSITIVE DATA CLUSTERING WITH FEATURE SELECTION : APPLICATION TO OBJECT DETECTION","year":2013,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Feature selection; Artificial intelligence; Selection (genetic algorithm); Feature (linguistics); Data mining; Pattern recognition (psychology); Object (grammar); Object detection","score_opus":0.016817961610783933,"score_gpt":0.2736784946301538,"score_spread":0.2568605330193699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588140678","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047101284,0.00011070808,0.98761,0.008225149,0.00019735246,0.0018033847,0.00016249051,0.00031903165,0.0011008667],"genre_scores_gemma":[0.12013259,0.000029363448,0.8779856,0.00020708334,0.00006233667,0.0005188691,0.00046216138,0.00004516789,0.0005568239],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949052,0.0023730304,0.00035131618,0.0015672161,0.00038829236,0.00041499303],"domain_scores_gemma":[0.9926287,0.0016561451,0.00039083,0.0032108652,0.0018658679,0.0002476093],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0034750958,0.0003753786,0.0003817427,0.00020329605,0.0004235419,0.0009099411,0.002348162,0.00042443423,0.0000075412845],"category_scores_gemma":[0.0010701616,0.00036115604,0.00007843495,0.0005545627,0.000087054985,0.00037141028,0.002278292,0.00082178594,0.000014588214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038548325,0.0001758015,0.000036532252,0.00015802379,0.00008204751,0.0000010397031,0.0032405537,0.00021270002,0.0021095804,0.34549305,0.00064377213,0.6478084],"study_design_scores_gemma":[0.00032720753,0.000004487703,0.001391459,0.0011802124,0.000070377966,0.00002894302,0.000020604864,0.8626199,0.02124868,0.10961526,0.0028577494,0.00063511747],"about_ca_topic_score_codex":0.00069346756,"about_ca_topic_score_gemma":0.001829175,"teacher_disagreement_score":0.8624072,"about_ca_system_score_codex":0.00017926321,"about_ca_system_score_gemma":0.0002583894,"threshold_uncertainty_score":0.99988407},"labels":[],"label_agreement":null},{"id":"W1589822290","doi":"10.1002/cjs.11196","title":"On the empirical efficiency of local MCMC algorithms with pools of proposals","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Jewish General Hospital; Université de Montréal","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Metropolis–Hastings algorithm; Markov chain Monte Carlo; Mathematics; Algorithm; Bayesian probability; Computer science; Statistics","score_opus":0.04159148816363465,"score_gpt":0.2636385319355158,"score_spread":0.22204704377188114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589822290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066676126,0.00007730084,0.9912954,0.0012339852,0.00013199041,0.0001296966,0.00004558816,0.0000018180631,0.00041658114],"genre_scores_gemma":[0.4907162,0.0000028648403,0.5089513,0.00026492926,0.000021793681,0.000001017379,2.6129788e-7,0.0000057950742,0.000035806297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988139,0.00013470306,0.00040221683,0.00010447759,0.00031104256,0.0002336473],"domain_scores_gemma":[0.99810106,0.00039901774,0.00032076443,0.0002605451,0.00056518405,0.00035340418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004885547,0.00010236983,0.00024826167,0.00013923984,0.00006246647,0.000050037626,0.0006439204,0.000044420678,0.000060890998],"category_scores_gemma":[0.00016368506,0.000057190213,0.00004093359,0.00025952302,0.00029492003,0.00010314882,0.000015748325,0.00022354515,0.000003796931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012324018,0.000076276854,0.00038139292,0.000048389047,0.00007209837,0.00019128351,0.002234712,0.00037989183,0.00016038562,0.6890028,0.031436596,0.27600384],"study_design_scores_gemma":[0.0019694956,0.007855091,0.016327921,0.00089279684,0.0001539189,0.0010728912,0.0007885024,0.20204376,0.011798647,0.7539337,0.0022816628,0.00088157144],"about_ca_topic_score_codex":0.0009334458,"about_ca_topic_score_gemma":0.0004545045,"teacher_disagreement_score":0.48404858,"about_ca_system_score_codex":0.00004632955,"about_ca_system_score_gemma":0.0014997746,"threshold_uncertainty_score":0.2660536},"labels":[],"label_agreement":null},{"id":"W1590238912","doi":"10.1111/biom.12351","title":"Mixtures of Multivariate Power Exponential Distributions","year":2015,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Mathematics; Statistics; Exponential function; Natural exponential family; Applied mathematics; Exponential distribution; Mathematical analysis","score_opus":0.05033286292360348,"score_gpt":0.30972213223128797,"score_spread":0.25938926930768447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590238912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003697809,0.00053010136,0.99292547,0.00020899075,0.00083644316,0.00007507858,0.00002481388,0.000060075014,0.0016411938],"genre_scores_gemma":[0.5092462,0.000004885846,0.4905886,0.000029021183,0.000029615523,0.0000023475288,0.0000041555045,0.0000035568103,0.00009162215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99897873,0.00008760324,0.00020783425,0.00021970276,0.00031070103,0.00019545043],"domain_scores_gemma":[0.9989859,0.000094993076,0.00010104774,0.00042723128,0.00022246178,0.00016840601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000571636,0.000094414325,0.0001535651,0.0005534034,0.00003801538,0.000052430318,0.0005571583,0.000084317304,0.0000053947438],"category_scores_gemma":[0.00049104396,0.000078718294,0.00007349989,0.0032709006,0.000044243385,0.0001853791,0.00021857662,0.00007027007,0.000012244405],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016315602,0.00044723778,0.00030002993,0.000015711355,0.00005106335,0.000019047298,0.00080421334,0.0000050339227,0.029791547,0.8325943,0.012031071,0.12392444],"study_design_scores_gemma":[0.0062256064,0.0014813821,0.02273548,0.000076983815,0.00011074635,0.00010252313,0.000061435465,0.039385248,0.32867607,0.3469174,0.25218204,0.002045079],"about_ca_topic_score_codex":0.00003338437,"about_ca_topic_score_gemma":3.0264349e-7,"teacher_disagreement_score":0.50554836,"about_ca_system_score_codex":0.000031438558,"about_ca_system_score_gemma":0.00008003405,"threshold_uncertainty_score":0.3210039},"labels":[],"label_agreement":null},{"id":"W1592887762","doi":"10.1002/9780470171455.app5","title":"Appendix E: Expectation–Maximization Algorithm","year":2007,"lang":"en","type":"other","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; McMaster University","funders":"","keywords":"Maximization; Appendix; Expectation–maximization algorithm; Algorithm; Gaussian; Energy (signal processing); Computer science; Mathematics; Maximum likelihood; Mathematical optimization; Statistics; Physics","score_opus":0.013332649418969996,"score_gpt":0.27670561697280294,"score_spread":0.26337296755383294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1592887762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.5959677e-9,0.00018728455,0.5186829,0.00004284057,0.00036590558,0.00009671984,0.0000017787187,0.00036056823,0.480262],"genre_scores_gemma":[2.325652e-7,0.000024160356,0.5334038,0.00021130465,0.0001939774,0.0000045638462,0.000018458984,0.000078055054,0.4660654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99888736,0.000053638858,0.00016376155,0.00042689135,0.00024955662,0.00021879181],"domain_scores_gemma":[0.99918956,0.000025554345,0.00012573878,0.0005467014,0.000029741004,0.00008272001],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020017887,0.00019578425,0.00019511791,0.0004729927,0.00003294812,0.00008472229,0.00057080033,0.00026469695,0.0026809683],"category_scores_gemma":[0.000007920216,0.00016942425,0.00006271639,0.0003680622,0.000018757302,0.00009969265,0.0000956373,0.000120757635,0.0008730899],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3699287e-7,0.000011013082,4.6842123e-7,0.000005862836,0.000007957196,0.000006816618,0.000049476464,2.7741248e-7,0.0000017147391,0.0830022,0.45627138,0.4606427],"study_design_scores_gemma":[0.00018965677,0.000019563719,0.0000035802257,0.000041438496,0.000008139779,0.000015311927,0.0000043191917,0.02349482,0.00019420545,0.011434077,0.96419847,0.00039641975],"about_ca_topic_score_codex":0.000042582727,"about_ca_topic_score_gemma":0.000009604132,"teacher_disagreement_score":0.5079271,"about_ca_system_score_codex":0.000021335552,"about_ca_system_score_gemma":0.000042856238,"threshold_uncertainty_score":0.9999049},"labels":[],"label_agreement":null},{"id":"W1593053801","doi":"","title":"Mixtures of 'Unrestricted' Skew-t Factor Analyzers","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Skew; Cluster analysis; Extension (predicate logic); sort; Factor (programming language); Computer science; Distribution (mathematics); Set (abstract data type); Mathematics; Algorithm; Statistics; Mathematical analysis","score_opus":0.07169780875165921,"score_gpt":0.20347985382323885,"score_spread":0.13178204507157965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593053801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1251265,0.00016518483,0.870697,0.00006858965,0.0005185082,0.00025810098,0.000028560327,0.00014999032,0.0029875755],"genre_scores_gemma":[0.90614843,0.00023197614,0.092170395,0.00007605453,0.00006344973,8.8017936e-7,0.000008021612,0.000018245806,0.0012825681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977935,0.00028142246,0.00029473167,0.0010993489,0.00013556209,0.00039542015],"domain_scores_gemma":[0.9972289,0.00016058564,0.00043408238,0.0016803404,0.0002511876,0.0002448891],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001742499,0.00038840968,0.00056017586,0.00043525244,0.00008183251,0.000100116114,0.0025401877,0.00047196465,0.00009827868],"category_scores_gemma":[0.000049679464,0.00039054998,0.00038259957,0.0007281868,0.00013081239,0.0003454284,0.0016961804,0.0006461123,0.00003998026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027964536,0.00023858833,0.0029894318,0.00028482432,0.00046997736,0.00027384152,0.00071892573,0.011617152,0.001204352,0.9621507,0.0032923487,0.01673192],"study_design_scores_gemma":[0.0007030119,0.00011894623,0.005891893,0.00019333893,0.00017183705,0.0000062832437,0.000019989595,0.370658,0.004131317,0.6158959,0.0010126476,0.0011967925],"about_ca_topic_score_codex":0.0003762408,"about_ca_topic_score_gemma":0.000009159346,"teacher_disagreement_score":0.7810219,"about_ca_system_score_codex":0.000096293894,"about_ca_system_score_gemma":0.00023665729,"threshold_uncertainty_score":0.9998546},"labels":[],"label_agreement":null},{"id":"W1601815945","doi":"10.3389/fpsyt.2015.00099","title":"A Bayesian Approach to Latent Class Modeling for Estimating the Prevalence of Schizophrenia Using Administrative Databases","year":2015,"lang":"en","type":"article","venue":"Frontiers in Psychiatry","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Schizophrenia (object-oriented programming); Medical diagnosis; Latent class model; Bayesian probability; Epidemiology; Psychiatry; Psychology; Medicine; Statistics; Computer science; Artificial intelligence","score_opus":0.10253349547548564,"score_gpt":0.34472651213345934,"score_spread":0.24219301665797371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601815945","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035397005,0.0007886643,0.9903756,0.00044389698,0.00386159,0.00065030594,0.000028153765,0.000033288972,0.00027884054],"genre_scores_gemma":[0.09636896,0.0000024811786,0.90321994,0.00016475144,0.00015558397,0.00005208895,0.000002035975,0.000014305173,0.00001988059],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998353,0.00016360662,0.00041263236,0.00050045626,0.00025352158,0.00031676085],"domain_scores_gemma":[0.9988877,0.000038843962,0.00015527455,0.00067681505,0.00009738763,0.00014397585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011200433,0.00018263109,0.00027185876,0.00014300397,0.00010251887,0.000058766538,0.00093804987,0.000057980138,2.454194e-7],"category_scores_gemma":[0.000115298164,0.00014010897,0.00007970139,0.00044791005,0.000049173577,0.0003338753,0.00017373468,0.00017498888,2.0787863e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007536049,0.0009158524,0.012723806,0.0019411958,0.00018274052,0.0000033254219,0.01264541,0.5563303,0.00013327406,0.30664158,0.025380798,0.08234806],"study_design_scores_gemma":[0.00045502945,0.00006907928,0.000044597982,0.0001536917,0.000022842447,0.000007413705,0.0001806735,0.94861233,0.000028813616,0.050240465,0.000021078613,0.00016395266],"about_ca_topic_score_codex":0.000023016828,"about_ca_topic_score_gemma":0.000005076227,"teacher_disagreement_score":0.392282,"about_ca_system_score_codex":0.00005318451,"about_ca_system_score_gemma":0.00043593394,"threshold_uncertainty_score":0.5713478},"labels":[],"label_agreement":null},{"id":"W1605557016","doi":"10.1007/978-3-642-01088-0_9","title":"Stability-Based Model Order Selection for Clustering Using Multiple Cooperative Particle Swarms","year":2009,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Stability (learning theory); Computer science; Selection (genetic algorithm); Data mining; Particle swarm optimization; Correlation clustering; CURE data clustering algorithm; Set (abstract data type); Consensus clustering; Data set; Artificial intelligence; Machine learning","score_opus":0.2291668230566935,"score_gpt":0.4008360216360463,"score_spread":0.1716691985793528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605557016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036401783,0.00065049477,0.9968551,0.00024812462,0.0002806941,0.0007043089,0.00001842001,0.00007723123,0.0011292283],"genre_scores_gemma":[0.06710371,0.000045273682,0.9307197,0.0004513983,0.00007945835,0.000048845224,0.000009500803,0.00002560352,0.0015165234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795616,0.00006402875,0.00060413923,0.0007535696,0.0003080339,0.0003140765],"domain_scores_gemma":[0.9974191,0.0010130241,0.0002016491,0.00023447922,0.0010724742,0.000059237962],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059596973,0.00035540218,0.00047257845,0.00013296836,0.0002525815,0.00007356826,0.00038551795,0.0001460555,0.0000050857025],"category_scores_gemma":[0.00021971963,0.00034773184,0.00011405307,0.00018597176,0.00017627045,0.0002294052,0.00017208877,0.00028915267,0.0000034433585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002608039,0.000031717413,0.000005194665,0.00005838321,0.000038771985,0.0000016920103,0.00082140905,0.804041,0.000015539083,0.16319132,0.000019887959,0.031748995],"study_design_scores_gemma":[0.00011309641,0.0000841446,7.199633e-7,0.00014052365,0.000010999267,0.0000029141597,0.000016774573,0.6776916,0.00035756428,0.32126114,0.00007310478,0.00024741393],"about_ca_topic_score_codex":0.00000772191,"about_ca_topic_score_gemma":0.00015766623,"teacher_disagreement_score":0.15806982,"about_ca_system_score_codex":0.00035919252,"about_ca_system_score_gemma":0.0003277781,"threshold_uncertainty_score":0.9998975},"labels":[],"label_agreement":null},{"id":"W1606724873","doi":"","title":"THE APPLICATION OF CIRCULAR STATISTICS TO PSYCHOPHYSICAL RESEARCH","year":2009,"lang":"en","type":"article","venue":"Proceedings of Fechner Day","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Point (geometry); Statistics; Mathematics; Magnitude (astronomy); Line (geometry); Computer science; Geometry; Physics","score_opus":0.02761066435146181,"score_gpt":0.3598538335043154,"score_spread":0.33224316915285357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606724873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039576124,0.000045739973,0.9892833,0.0021364274,0.000033282497,0.000266944,0.0000022152342,0.000026695438,0.0042477427],"genre_scores_gemma":[0.5296315,0.000013870364,0.4701529,0.00008143531,0.000040466464,0.000017759063,2.353688e-7,0.0000037900718,0.000058032136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883896,0.00001873225,0.00021129068,0.0002469606,0.00046422222,0.00021985339],"domain_scores_gemma":[0.9987962,0.00013589794,0.00008759127,0.00025641863,0.00065066566,0.00007317607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017615404,0.00007114798,0.00013196857,0.000090022615,0.00010654425,0.000059713697,0.0009997941,0.000045586905,3.493443e-7],"category_scores_gemma":[0.00016143419,0.00005067143,0.000032914908,0.0007048022,0.0000718931,0.00013086165,0.000107144326,0.00016750653,0.000004851408],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036044542,0.000033635748,0.000014761438,0.000010097444,0.0000024954954,6.008953e-8,0.00026143846,3.323113e-7,0.08425386,0.58595467,0.0027153736,0.32674968],"study_design_scores_gemma":[0.00011775135,0.00026664097,0.002117294,0.000026618736,0.000004747018,0.0000016929777,0.000020722924,0.007885347,0.08019496,0.9015351,0.0077252197,0.00010390326],"about_ca_topic_score_codex":0.000004601131,"about_ca_topic_score_gemma":1.7049882e-7,"teacher_disagreement_score":0.52567387,"about_ca_system_score_codex":0.000016328446,"about_ca_system_score_gemma":0.00002541133,"threshold_uncertainty_score":0.2066321},"labels":[],"label_agreement":null},{"id":"W1607348874","doi":"10.1109/eeeic.2015.7165433","title":"Expectation-maximization algorithm for evaluation of wind direction characteristics","year":2015,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Range (aeronautics); Maximization; Goodness of fit; Algorithm; Expectation–maximization algorithm; Computer science; Distribution (mathematics); Wind direction; Mathematics; Wind speed; Mathematical optimization; Statistics; Maximum likelihood; Engineering; Mathematical analysis; Meteorology; Physics; Aerospace engineering","score_opus":0.058167094350310845,"score_gpt":0.33069283207363503,"score_spread":0.27252573772332417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607348874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015242699,0.000029499273,0.9955336,0.000110563466,0.0004980509,0.0003009226,0.0000027890146,0.000046527748,0.0019538112],"genre_scores_gemma":[0.08700788,0.0000025238967,0.91265357,0.000035336925,0.000085498534,0.0000230196,0.000014936364,0.000004830672,0.00017241052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991527,0.00011291544,0.00018430642,0.00016419533,0.0003062094,0.00007964922],"domain_scores_gemma":[0.9986918,0.000055010954,0.00011915273,0.00018112319,0.00090485864,0.00004804678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001222107,0.000059448437,0.00009922165,0.000071158436,0.000031255728,0.000032086184,0.00012640632,0.000043248758,0.0000056131244],"category_scores_gemma":[0.00020008715,0.000053654378,0.000029780611,0.00017557097,0.000009555561,0.00032654192,0.00002007694,0.000021650787,0.0000017478309],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002198728,0.000028095523,0.000025852332,0.0000030519473,0.000005746552,4.372771e-8,0.0005850125,0.00007155219,0.00020121595,0.013612223,0.00027376824,0.9851912],"study_design_scores_gemma":[0.0005488943,0.00006166367,0.00085329945,0.00000503707,0.000018079569,0.0000015993216,0.000022571798,0.9622141,0.0036309317,0.032342076,0.00023328725,0.00006846557],"about_ca_topic_score_codex":0.0000075477687,"about_ca_topic_score_gemma":0.0000011509006,"teacher_disagreement_score":0.9851228,"about_ca_system_score_codex":0.000045946035,"about_ca_system_score_gemma":0.00011888282,"threshold_uncertainty_score":0.2187962},"labels":[],"label_agreement":null},{"id":"W1613812217","doi":"10.1111/rssb.12294","title":"Moment Conditions and Bayesian Non-Parametrics","year":2018,"lang":"en","type":"preprint","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Moment (physics); Bayesian probability; Computer science; Bayesian inference; Inference; Bayesian linear regression; Manifold (fluid mechanics); Algorithm; Nonlinear system; Machine learning; Applied mathematics; Mathematics; Artificial intelligence; Engineering; Physics","score_opus":0.046064275074745566,"score_gpt":0.3370919365698193,"score_spread":0.2910276614950737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1613812217","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003087311,0.00034340753,0.9905263,0.004317394,0.0030374941,0.00040555248,0.0006539494,0.000037124584,0.00037004417],"genre_scores_gemma":[0.005777449,0.00019728666,0.991784,0.001279116,0.0005777662,0.000020636631,0.00001212852,0.00004049874,0.00031114937],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933227,0.0027274466,0.0014830066,0.0007956504,0.0009202064,0.00075102743],"domain_scores_gemma":[0.98916507,0.007460388,0.0011474278,0.0009148541,0.00064478844,0.0006674951],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0050319093,0.00059877994,0.0014874471,0.00010908731,0.0005008377,0.00042012436,0.0019414921,0.00076140364,0.00016561526],"category_scores_gemma":[0.00521111,0.00040667722,0.00052763586,0.00040118082,0.0018688259,0.0001774921,0.0026766828,0.0025705977,0.0000063577486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012637858,0.00023274386,0.00017425972,0.00045088277,0.00076646137,0.00012675214,0.0011442357,0.00025296747,0.00006231263,0.8593778,0.09091082,0.046374366],"study_design_scores_gemma":[0.0005129102,0.00065887114,0.0063917614,0.00015431827,0.00044437058,0.00023570056,0.000051057457,0.0695123,0.00016128355,0.917951,0.0034217334,0.0005047241],"about_ca_topic_score_codex":0.00004322616,"about_ca_topic_score_gemma":0.0000038260077,"teacher_disagreement_score":0.08748909,"about_ca_system_score_codex":0.00023839195,"about_ca_system_score_gemma":0.00055232923,"threshold_uncertainty_score":0.99983853},"labels":[],"label_agreement":null},{"id":"W1645701135","doi":"10.1007/978-3-642-01307-2_42","title":"A Nonparametric Bayesian Learning Model: Application to Text and Image Categorization","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Categorization; Computer science; Gibbs sampling; Nonparametric statistics; Artificial intelligence; Bayesian probability; Mixture model; Flexibility (engineering); Posterior probability; Machine learning; Image (mathematics); Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.009606028271420444,"score_gpt":0.2556173150931961,"score_spread":0.24601128682177564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1645701135","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008507548,0.00018677296,0.9940741,0.0011325442,0.00020503713,0.0005961258,0.0000013047326,0.00018456162,0.0036110305],"genre_scores_gemma":[0.061408076,0.00004898797,0.936482,0.001394914,0.0001710491,0.000015053615,0.0000042119636,0.000031296688,0.00044437393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965157,0.000053993434,0.00044376284,0.0017439721,0.000679181,0.00056338275],"domain_scores_gemma":[0.99803394,0.00022660052,0.00023508033,0.0009782665,0.00023824279,0.0002878917],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010419106,0.00048427196,0.00048297833,0.0013702171,0.0002855148,0.00069371803,0.0016574536,0.00032211927,0.000002373857],"category_scores_gemma":[0.00012186716,0.000464259,0.00007338394,0.001360351,0.00020584157,0.00064089266,0.0006841466,0.0007645455,0.000016918022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026505497,0.00001095836,0.0000055414944,0.000014598772,0.0000021118149,0.000007620181,0.00044129207,0.06375334,0.00048249637,0.055054937,0.0000062101944,0.88021827],"study_design_scores_gemma":[0.00009011796,0.00010114083,0.00002652798,0.00005725443,0.00000499578,0.000023509081,2.8403507e-8,0.67411983,0.00038154307,0.32458577,0.00025022088,0.00035902864],"about_ca_topic_score_codex":0.000013399824,"about_ca_topic_score_gemma":0.000012600135,"teacher_disagreement_score":0.8798592,"about_ca_system_score_codex":0.0002062366,"about_ca_system_score_gemma":0.00027682201,"threshold_uncertainty_score":0.9997809},"labels":[],"label_agreement":null},{"id":"W16598393","doi":"10.1007/978-3-642-24958-7_32","title":"A Variational Statistical Framework for Object Detection","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Computer science; Object (grammar); Artificial intelligence; Dirichlet distribution; Object detection; Variational method; Computer vision; Algorithm; Pattern recognition (psychology); Mathematics","score_opus":0.02755002989151602,"score_gpt":0.2839064299132923,"score_spread":0.2563564000217763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W16598393","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.0224837e-7,0.00013768299,0.99464965,0.00022407288,0.0025236974,0.00052170927,0.000020285017,0.00012980141,0.0017924288],"genre_scores_gemma":[0.008345067,0.000012726407,0.9897804,0.0009825679,0.00067379046,0.000032607622,0.0000046447376,0.000031447133,0.00013670142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968127,0.000053694097,0.00045311023,0.001446883,0.00064441666,0.0005892236],"domain_scores_gemma":[0.9967915,0.0015427333,0.00024481915,0.0009696861,0.00027225196,0.00017903231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001241106,0.00043374219,0.00046190288,0.0005203094,0.0002717474,0.0003525568,0.0018712151,0.00050959573,0.000035751873],"category_scores_gemma":[0.00034444433,0.00039478517,0.00013872179,0.0003413505,0.00035159703,0.0003764638,0.00050889456,0.0007763908,0.00001975097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006271032,0.000010266476,9.855098e-7,0.000014063533,0.0000058198457,0.0000068326244,0.0001977524,0.00019168998,0.000019024834,0.5002854,0.0000045419474,0.49925733],"study_design_scores_gemma":[0.00012144231,0.00016886386,0.00004368178,0.00010036635,0.00000874118,0.000032267653,1.1839944e-8,0.24929892,0.00056676083,0.74877053,0.0005393987,0.00034902958],"about_ca_topic_score_codex":0.000013634837,"about_ca_topic_score_gemma":0.000026420954,"teacher_disagreement_score":0.4989083,"about_ca_system_score_codex":0.0002048508,"about_ca_system_score_gemma":0.00054644275,"threshold_uncertainty_score":0.9998504},"labels":[],"label_agreement":null},{"id":"W1669348267","doi":"10.1016/j.jeconom.2015.11.001","title":"Bayesian semiparametric modeling of realized covariance matrices","year":2015,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Wishart distribution; Inverse-Wishart distribution; Covariance; Mathematics; Bayesian probability; Posterior probability; Econometrics; Conditional probability distribution; Mixture model; Inverse; Applied mathematics; Statistics; Multivariate statistics","score_opus":0.18888745343781957,"score_gpt":0.2982408457396074,"score_spread":0.10935339230178784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1669348267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040552514,0.004944001,0.98606163,0.00026369136,0.0007198677,0.00006592064,0.0000027551168,0.000013764448,0.003873118],"genre_scores_gemma":[0.37229976,0.00041307745,0.62705654,0.00007605382,0.00010386577,5.5043864e-7,1.9016231e-7,0.000007740522,0.00004220359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804425,0.00013450724,0.0010102069,0.00019989602,0.00037259844,0.00023853447],"domain_scores_gemma":[0.9971502,0.00034497486,0.0011158792,0.0004135708,0.0006577878,0.00031760728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003372361,0.00014102015,0.00056573586,0.0022849028,0.000031524763,0.00011457563,0.0011321803,0.00010752148,0.000007074686],"category_scores_gemma":[0.0012059825,0.00012082365,0.00019177356,0.00421557,0.00002310813,0.0009495177,0.00012876015,0.00024758468,0.0000035838932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024314619,0.0008652063,0.004437195,0.0002585736,0.00048173836,0.00021113452,0.0025727716,0.22364116,0.00015968816,0.30093405,0.008186299,0.45800903],"study_design_scores_gemma":[0.0010674882,0.0003306969,0.000060560014,0.000040960327,0.000033864293,0.000178048,0.000033343083,0.8900466,0.00021999008,0.10641181,0.001384585,0.00019208161],"about_ca_topic_score_codex":0.000017933842,"about_ca_topic_score_gemma":5.8718166e-7,"teacher_disagreement_score":0.66640544,"about_ca_system_score_codex":0.00011435297,"about_ca_system_score_gemma":0.00032968642,"threshold_uncertainty_score":0.49270454},"labels":[],"label_agreement":null},{"id":"W1685527554","doi":"10.1016/j.jbi.2015.09.004","title":"Hidden Markov model using Dirichlet process for de-identification","year":2015,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"U.S. National Library of Medicine","keywords":"Hidden Markov model; Computer science; Conditional random field; Artificial intelligence; Dirichlet process; Feature (linguistics); Context (archaeology); Identification (biology); Machine learning; Dirichlet distribution; Hierarchical Dirichlet process; Vocabulary; Pattern recognition (psychology); Field (mathematics); Bayesian probability; Topic model; Latent Dirichlet allocation; Mathematics","score_opus":0.06895016093744245,"score_gpt":0.36020037196107,"score_spread":0.2912502110236276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1685527554","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010632936,0.000054503693,0.9878895,0.0008114631,0.00034107425,0.000097781645,0.0000034907978,0.000014379044,0.00015487043],"genre_scores_gemma":[0.057941273,0.000009204176,0.941393,0.00045422663,0.00015622399,0.000002086783,0.0000013939338,0.0000052336636,0.000037348003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983453,0.00003486126,0.0008344403,0.00005117133,0.00052578514,0.00020844636],"domain_scores_gemma":[0.9982479,0.00006789406,0.0006450941,0.00017678237,0.0005128287,0.00034949213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025829722,0.000086971304,0.00020143078,0.00019125346,0.00005089731,0.00012879269,0.00066795223,0.0001042663,8.3177736e-7],"category_scores_gemma":[0.00036976917,0.00006445082,0.000082486236,0.00027009915,0.000052473602,0.0010069557,0.000064657834,0.00015982952,0.0000013388661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009597219,0.00036119964,0.000047742353,0.0005718357,0.0001247931,0.000015752865,0.026511254,0.0030132183,0.0016202475,0.012952293,0.033000726,0.921685],"study_design_scores_gemma":[0.0004518561,0.000087754066,0.0000053038057,0.000042945117,0.000020171938,0.00016685796,0.00012767238,0.9269866,0.0004817395,0.07080599,0.00074447115,0.000078692436],"about_ca_topic_score_codex":5.9239096e-7,"about_ca_topic_score_gemma":6.7837455e-8,"teacher_disagreement_score":0.9239733,"about_ca_system_score_codex":0.00009699764,"about_ca_system_score_gemma":0.0006764988,"threshold_uncertainty_score":0.2628228},"labels":[],"label_agreement":null},{"id":"W1693289132","doi":"10.48550/arxiv.1412.8566","title":"Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Markov chain; Markov chain Monte Carlo; Mathematics; Statistics; Markov random field; Likelihood function; Partition (number theory); Computer science; Algorithm; Econometrics; Maximum likelihood; Artificial intelligence; Combinatorics; Bayesian probability","score_opus":0.1087392546217394,"score_gpt":0.23706334584655686,"score_spread":0.12832409122481747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1693289132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19108498,0.000107625136,0.80789137,0.000060622544,0.0002301699,0.00017428785,0.000016915023,0.00006861757,0.00036539766],"genre_scores_gemma":[0.687509,0.00009530009,0.31220073,0.00011186522,0.00002690887,2.2879124e-7,0.0000037892507,0.000011998536,0.00004017198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981782,0.00026569658,0.00025861303,0.00090932345,0.00007177368,0.000316404],"domain_scores_gemma":[0.9979792,0.00028846602,0.00049371173,0.0008314963,0.0002467273,0.00016039019],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005834212,0.00031318647,0.0005338729,0.00020068478,0.00012546756,0.0000785809,0.00088335073,0.0002789711,0.000004944107],"category_scores_gemma":[0.00009424461,0.0003393595,0.00013005156,0.0003324726,0.0002043759,0.0003423447,0.0015651338,0.0004023988,0.0000027922113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013162133,0.0001695533,0.0078029656,0.0013126093,0.0005907355,0.000551697,0.0029260945,0.18373685,0.0026975318,0.7900194,0.00039518063,0.009665777],"study_design_scores_gemma":[0.00028911416,0.000033269596,0.00027710828,0.00023743736,0.0000875245,0.000008295469,0.000029102457,0.7941694,0.0008242582,0.20370717,0.00003896677,0.00029834147],"about_ca_topic_score_codex":0.00030616784,"about_ca_topic_score_gemma":0.000011707903,"teacher_disagreement_score":0.61043257,"about_ca_system_score_codex":0.00006241766,"about_ca_system_score_gemma":0.00019860515,"threshold_uncertainty_score":0.9999058},"labels":[],"label_agreement":null},{"id":"W1698278400","doi":"","title":"Randomized Optimum Models for Structured Prediction","year":2012,"lang":"en","type":"article","venue":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain; Computer science; Partition function (quantum field theory); Partition (number theory); Computation; Theoretical computer science; Mathematical optimization; Mathematics; Algorithm; Machine learning; Combinatorics","score_opus":0.040948997035003605,"score_gpt":0.2681448390227858,"score_spread":0.2271958419877822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1698278400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027803106,0.000025972835,0.9516642,0.00022378626,0.0009765909,0.0017633201,0.00032844985,0.0005045301,0.016710062],"genre_scores_gemma":[0.82461417,0.000032852495,0.1690612,0.00076447555,0.00034088493,0.000029565786,0.00011839481,0.00006658776,0.0049718954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99647677,0.00035192867,0.00049104437,0.0009787844,0.0006099756,0.0010915082],"domain_scores_gemma":[0.99685943,0.00045199244,0.00027147873,0.0010318975,0.0004248782,0.0009603055],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0012542672,0.0005336257,0.0008395176,0.00074454234,0.0005462949,0.0019643174,0.0029198471,0.00032536435,0.000087042274],"category_scores_gemma":[0.00037838708,0.00052326627,0.0005964427,0.0011473569,0.00012401718,0.02089477,0.0017315607,0.0003856915,0.0003072772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025980454,0.0005355382,0.0043166745,0.00019626996,0.0007959767,0.000056871257,0.0021601936,0.0030520968,0.0010709586,0.8826506,0.006565215,0.07261915],"study_design_scores_gemma":[0.1355308,0.0004163454,0.0040053376,0.00028166987,0.0006039409,0.00012224275,0.000075330514,0.059469216,0.010095378,0.17478639,0.61101663,0.003596693],"about_ca_topic_score_codex":0.0000071939967,"about_ca_topic_score_gemma":0.000005269414,"teacher_disagreement_score":0.79681104,"about_ca_system_score_codex":0.0004284175,"about_ca_system_score_gemma":0.00012081946,"threshold_uncertainty_score":0.9997219},"labels":[],"label_agreement":null},{"id":"W1716124544","doi":"10.1109/icdm.2004.10103","title":"Semi-Supervised Mixture-of-Experts Classification","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Correctness; Generalization; Computer science; Artificial intelligence; Generalization error; Variance (accounting); Machine learning; Decomposition; Semi-supervised learning; Reduction (mathematics); Data modeling; Term (time); Mixture model; Pattern recognition (psychology); Mathematics; Unsupervised learning; Algorithm","score_opus":0.02774046286909406,"score_gpt":0.2803606596970886,"score_spread":0.2526201968279946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1716124544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016390613,0.00017538466,0.9522765,0.0032107856,0.000119601835,0.00008409238,4.0407946e-7,0.00010994157,0.042384207],"genre_scores_gemma":[0.33872238,0.00001674743,0.65932244,0.0007304113,0.000072805204,0.0000056678646,7.557659e-7,0.000004191779,0.0011246253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991464,0.00006715281,0.00020421679,0.00025897022,0.00016505271,0.00015821552],"domain_scores_gemma":[0.99920946,0.000050600447,0.00005267204,0.0005465523,0.00006740592,0.00007330866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002495287,0.000092416136,0.00012747628,0.00006323569,0.000038480473,0.0000365339,0.0005181976,0.000071508795,0.00006136819],"category_scores_gemma":[0.000017468792,0.00007205749,0.000061955005,0.00021150301,0.000022648557,0.0003435275,0.00006990928,0.0000550977,0.000024850631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016875248,0.00005106239,0.000052409676,0.0000048165857,0.000005087193,5.2812027e-7,0.0004944556,0.0000047487224,0.029792288,0.41829392,0.004602592,0.54669636],"study_design_scores_gemma":[0.0006442673,0.000085505875,0.0018243034,0.000026448795,0.000009986542,0.000023125172,0.00003456762,0.7218331,0.15197319,0.0371427,0.08594594,0.00045683738],"about_ca_topic_score_codex":0.0000067840288,"about_ca_topic_score_gemma":0.0000043066498,"teacher_disagreement_score":0.72182834,"about_ca_system_score_codex":0.00001738131,"about_ca_system_score_gemma":0.00003494359,"threshold_uncertainty_score":0.2938419},"labels":[],"label_agreement":null},{"id":"W171785542","doi":"10.1007/978-3-319-12571-8_17","title":"Fast Simultaneous Clustering and Feature Selection for Binary Data","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Cluster analysis; Computer science; Feature selection; Feature (linguistics); Data mining; Correlation clustering; Expectation–maximization algorithm; Context (archaeology); CURE data clustering algorithm; Canopy clustering algorithm; Selection (genetic algorithm); Artificial intelligence; Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Maximum likelihood; Statistics","score_opus":0.025987960295501118,"score_gpt":0.27931322445216256,"score_spread":0.25332526415666146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W171785542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000072237594,0.00053985196,0.9959463,0.0010411869,0.0012709956,0.0005550455,0.000018639204,0.00014978799,0.00047098243],"genre_scores_gemma":[0.009924091,0.000050341307,0.9871607,0.0012093632,0.0007356116,0.000007730045,0.000018037706,0.00004029387,0.00085383153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964294,0.00004906116,0.0003293562,0.0021160091,0.00047656044,0.0005996015],"domain_scores_gemma":[0.99670225,0.0010112725,0.00022617463,0.0016890366,0.00019207719,0.00017916795],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012696934,0.00051183946,0.0005396964,0.0004832083,0.0003546495,0.00063274766,0.0033217184,0.00043759955,0.0000024331744],"category_scores_gemma":[0.00018313831,0.00045594276,0.00006904124,0.00033001136,0.00032945542,0.00050727493,0.002557394,0.00069903577,0.0000031350214],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009785838,0.0000073188235,0.0000038843436,0.000082169245,0.000008597535,0.000015059679,0.00019410027,0.012742178,0.0002146825,0.007805247,0.00008808155,0.9788289],"study_design_scores_gemma":[0.00023428033,0.0002127433,0.000005472028,0.00022714774,0.000012387046,0.00017266201,3.9116948e-8,0.9242053,0.00014416984,0.06830184,0.005988832,0.000495099],"about_ca_topic_score_codex":0.000009898493,"about_ca_topic_score_gemma":0.000113284004,"teacher_disagreement_score":0.9783338,"about_ca_system_score_codex":0.000114842485,"about_ca_system_score_gemma":0.00024372332,"threshold_uncertainty_score":0.99978924},"labels":[],"label_agreement":null},{"id":"W1728217251","doi":"10.1109/icassp.2001.940512","title":"Wide band channel characterisation in coloured noise using the reversible jump MCMC","year":2002,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain Monte Carlo; Reversible-jump Markov chain Monte Carlo; Wideband; Computer science; Channel (broadcasting); Algorithm; Monte Carlo method; Noise (video); Bayesian probability; Wireless; Jump; Markov chain; Electronic engineering; Mathematics; Telecommunications; Engineering; Statistics; Artificial intelligence; Physics; Machine learning","score_opus":0.0493342980120453,"score_gpt":0.2584826744514191,"score_spread":0.20914837643937378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1728217251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037360683,0.000079809965,0.9551651,0.0034462668,0.00024927285,0.00017273755,5.46334e-7,0.000043906573,0.003481702],"genre_scores_gemma":[0.77995026,0.00004069557,0.2158898,0.002087434,0.000073441406,0.000008164776,5.609869e-7,0.000007832015,0.0019418189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911445,0.00013982745,0.00016147536,0.00023827681,0.00013309455,0.00021286293],"domain_scores_gemma":[0.99942404,0.00008251531,0.000061556886,0.00035275976,0.000032926,0.000046204543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048494863,0.000094954135,0.0001194527,0.00008358196,0.00010875809,0.00009994336,0.00039098124,0.00005926359,0.00006325625],"category_scores_gemma":[0.00003280622,0.0000658605,0.0000390851,0.00037703637,0.00002242858,0.0004274444,0.000072917675,0.0001164676,0.000018715064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011616705,0.0014831992,0.013440719,0.00022261815,0.00016849472,0.00029215467,0.076258995,0.0021953636,0.2279812,0.21565261,0.071790144,0.39039835],"study_design_scores_gemma":[0.00049917604,0.00003739146,0.0062609767,0.000035772497,0.0000073052774,0.000021431772,0.000035921115,0.9715445,0.0074969553,0.011680595,0.0021411788,0.00023877017],"about_ca_topic_score_codex":0.00007319697,"about_ca_topic_score_gemma":0.000024321047,"teacher_disagreement_score":0.96934915,"about_ca_system_score_codex":0.000040807277,"about_ca_system_score_gemma":0.000015072966,"threshold_uncertainty_score":0.26857132},"labels":[],"label_agreement":null},{"id":"W174976057","doi":"10.1201/9780203753064-8","title":"Tests for the Uniform Distribution","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Distribution (mathematics); Mathematics; Mathematical analysis","score_opus":0.04978451389410007,"score_gpt":0.30427323322167765,"score_spread":0.2544887193275776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W174976057","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.7680105e-9,0.00016572076,0.60153234,0.0012205245,0.0003335483,0.00022988071,0.00003124803,0.000045362136,0.39644137],"genre_scores_gemma":[0.000074431395,0.0000935214,0.24362873,0.00024783655,0.00025176094,0.000018745504,0.00002605363,0.000012770239,0.75564617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992304,0.0000052983737,0.00014142724,0.00030546516,0.00014368295,0.00017373261],"domain_scores_gemma":[0.9981897,0.00022597131,0.0001594621,0.0012672467,0.00010571569,0.000051913907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040028302,0.00018248869,0.00017591468,0.000017637265,0.00034680712,0.0002463419,0.0013821748,0.0001932165,0.000022812286],"category_scores_gemma":[0.000037686452,0.00010357301,0.00016541922,0.0000052265864,0.00006099695,0.00014939942,0.00022458697,0.00016571658,0.000031311727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.81594e-7,0.0000012185998,5.2446968e-8,0.00000479828,0.000010578589,7.766199e-7,0.0000066666144,1.2644286e-7,7.7072303e-7,0.69309306,0.0138445515,0.2930366],"study_design_scores_gemma":[0.000051683503,0.000019050396,0.0000052015585,0.000016825543,0.000012977889,0.0000049979635,7.773859e-8,0.0038679559,0.00001749955,0.47703123,0.518872,0.000100489975],"about_ca_topic_score_codex":0.000007300701,"about_ca_topic_score_gemma":0.000019969135,"teacher_disagreement_score":0.5050275,"about_ca_system_score_codex":0.00003249083,"about_ca_system_score_gemma":0.00007944316,"threshold_uncertainty_score":0.42235848},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_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","score_opus":0.03640317111091929,"score_gpt":0.2600045938295232,"score_spread":0.2236014227186039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1755019093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013421561,0.0006762969,0.9960006,0.0006358651,0.00051418383,0.00003402782,0.00029729106,0.000003077665,0.00049651146],"genre_scores_gemma":[0.14833342,0.000014615771,0.85132074,0.0001444088,0.00008858381,3.9949387e-7,0.0000043542705,0.0000051158236,0.00008838029],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99914885,0.00009228957,0.00031675954,0.00007645611,0.00016544503,0.00020023146],"domain_scores_gemma":[0.998098,0.000053548258,0.00021329368,0.00020061883,0.0006037947,0.0008307154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039702546,0.0000787313,0.0002124014,0.00014025415,0.00004715914,0.000050549017,0.00046724634,0.000050781426,0.000012302512],"category_scores_gemma":[0.00033113823,0.000068062705,0.00004673137,0.0002300585,0.00007223501,0.00012548012,0.000015349902,0.00014746512,0.000002365121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003273919,0.000011408126,0.00025622692,0.00000860265,0.000027375769,0.00020493616,0.00078507577,0.000034623314,0.00011852343,0.8976118,0.06739569,0.033542465],"study_design_scores_gemma":[0.0014892879,0.00040822913,0.0023090884,0.000083405655,0.00008665471,0.0009924215,0.0000550485,0.009800901,0.0011671502,0.8667476,0.11650015,0.0003600375],"about_ca_topic_score_codex":0.0009420893,"about_ca_topic_score_gemma":0.0017803739,"teacher_disagreement_score":0.14699127,"about_ca_system_score_codex":0.00008070122,"about_ca_system_score_gemma":0.002230659,"threshold_uncertainty_score":0.3957093},"labels":[],"label_agreement":null},{"id":"W1769669223","doi":"10.1007/978-3-642-01307-2_19","title":"A Statistical Approach for Binary Vectors Modeling and Clustering","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Feature selection; Artificial intelligence; Binary number; Pattern recognition (psychology); Selection (genetic algorithm); Feature (linguistics); Statistical model; Data mining; Model selection; Machine learning; Mathematics","score_opus":0.031455562077756634,"score_gpt":0.27852840906590476,"score_spread":0.24707284698814813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1769669223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011119313,0.0005688382,0.9966798,0.00022664291,0.00046551062,0.00054024754,0.000008054955,0.000112151516,0.0013876426],"genre_scores_gemma":[0.01844343,0.0000363443,0.98034203,0.00074596435,0.00028713112,0.000013178134,0.000006095053,0.000028804836,0.000097032884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967896,0.000038543996,0.00042773705,0.0016146625,0.00048927235,0.0006402221],"domain_scores_gemma":[0.99835587,0.00038272067,0.00012594873,0.00079371233,0.0001269876,0.00021479302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010863412,0.0004793749,0.00056669343,0.0005194606,0.0002591083,0.0004822048,0.0014827682,0.00031031118,0.0000016309511],"category_scores_gemma":[0.00006818336,0.0004281317,0.00008921073,0.00024139787,0.0003000799,0.00038873285,0.0007906717,0.0005724481,9.2855805e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000083817,0.000016369957,0.000001305232,0.00006565985,0.000005657068,0.000018644298,0.0003332411,0.07153239,0.000050018618,0.056179043,0.0000056087715,0.8717837],"study_design_scores_gemma":[0.00016769419,0.0001541314,0.00000469774,0.00010083315,0.000007019555,0.0000498599,4.894939e-8,0.7174839,0.000026407044,0.28157705,0.00006871195,0.00035970067],"about_ca_topic_score_codex":0.0000082088,"about_ca_topic_score_gemma":0.0000058222627,"teacher_disagreement_score":0.87142396,"about_ca_system_score_codex":0.00012691854,"about_ca_system_score_gemma":0.00025368814,"threshold_uncertainty_score":0.9998171},"labels":[],"label_agreement":null},{"id":"W1783453637","doi":"10.1007/978-3-642-55032-4_28","title":"Online Learning for Two Novel Latent Topic Models","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Dirichlet distribution; Artificial intelligence; Machine learning; Latent variable; Mathematics","score_opus":0.039852724433394396,"score_gpt":0.2890081609870012,"score_spread":0.24915543655360683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1783453637","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021691949,0.0002992677,0.99502826,0.0008918371,0.001652702,0.000527878,0.0000060190296,0.00018284489,0.0013894807],"genre_scores_gemma":[0.022240724,0.000022789716,0.9731585,0.0019131087,0.00085562334,0.000015008771,0.000010095593,0.000045423294,0.0017387195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618644,0.000043966244,0.0005637007,0.001727722,0.000689538,0.0007886443],"domain_scores_gemma":[0.9973358,0.00061507727,0.00031205255,0.0012152322,0.0003099396,0.00021192203],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001322368,0.0005763402,0.00069895067,0.00056071725,0.0002937837,0.00043150468,0.0029630968,0.00033046887,0.00000550527],"category_scores_gemma":[0.00009108961,0.0005065068,0.00023760805,0.00031507303,0.00030013893,0.00040605993,0.0010627394,0.00096165854,0.0000066134558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029316147,0.000023402426,0.0000023117202,0.000029995159,0.000007498583,0.000005684726,0.00028317675,0.12127965,0.00014102332,0.22029597,0.0000070975666,0.65792125],"study_design_scores_gemma":[0.0003495928,0.00012504988,0.0000059445315,0.0001599943,0.000007267755,0.000024192956,2.1956103e-8,0.63852257,0.00022285772,0.3586637,0.0015231132,0.00039568983],"about_ca_topic_score_codex":0.000018016519,"about_ca_topic_score_gemma":0.000034975343,"teacher_disagreement_score":0.6575256,"about_ca_system_score_codex":0.00018379615,"about_ca_system_score_gemma":0.0003048057,"threshold_uncertainty_score":0.99973863},"labels":[],"label_agreement":null},{"id":"W1853432543","doi":"10.1007/s11118-015-9502-5","title":"Harnack Inequality and Applications for Infinite-Dimensional GEM Processes","year":2015,"lang":"en","type":"article","venue":"Potential Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Harnack's inequality; Mathematics; Harnack's principle; Poincaré inequality; Sobolev inequality; Potential theory; Dirichlet distribution; Pure mathematics; Heat kernel; Dimension (graph theory); Dirichlet form; Mathematical analysis; Log sum inequality; Upper and lower bounds; Sobolev space; Inequality; Kernel (algebra); Boundary value problem","score_opus":0.03778270112513178,"score_gpt":0.30180342445811076,"score_spread":0.264020723332979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1853432543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026199173,0.00027570396,0.9959938,0.000695102,0.00003551647,0.00016803993,0.000015617705,0.00005660346,0.00013971537],"genre_scores_gemma":[0.37125406,0.000009747409,0.6280074,0.0003119268,0.00011166073,0.00009272431,0.000024308787,0.0000048292072,0.00018336388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904567,0.000059247144,0.00019864771,0.0003492727,0.00019337273,0.00015378618],"domain_scores_gemma":[0.99899226,0.0000786778,0.00009068992,0.000305407,0.0003722762,0.00016069788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052243815,0.000096232696,0.00021085488,0.00015651557,0.00011143652,0.000121444704,0.00027002144,0.000047473743,0.0000040304512],"category_scores_gemma":[0.00008596732,0.00008019318,0.000101712234,0.001006607,0.00003382417,0.000220036,0.00013618848,0.000049492934,0.0000048904585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012047988,0.00083144946,0.006630499,0.00049527816,0.0034430139,0.000014118153,0.0024783567,0.013751227,0.0017039456,0.41706008,0.0040853596,0.5493862],"study_design_scores_gemma":[0.000880369,0.000094740266,0.0018532836,0.0000071842674,0.0017254603,0.000010882925,0.000032568274,0.6437247,0.0010166195,0.3390682,0.011064117,0.00052190246],"about_ca_topic_score_codex":0.000056552315,"about_ca_topic_score_gemma":0.000033803655,"teacher_disagreement_score":0.6299735,"about_ca_system_score_codex":0.000010497834,"about_ca_system_score_gemma":0.00008517771,"threshold_uncertainty_score":0.3270183},"labels":[],"label_agreement":null},{"id":"W1853714018","doi":"10.1007/s10489-015-0714-6","title":"Variational Bayesian inference for infinite generalized inverted Dirichlet mixtures with feature selection and its application to clustering","year":2015,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet distribution; Computer science; Dirichlet process; Hierarchical Dirichlet process; Cluster analysis; Prior probability; Artificial intelligence; Pattern recognition (psychology); Model selection; Inference; Bayesian inference; Feature selection; Generalized Dirichlet distribution; Feature (linguistics); Latent Dirichlet allocation; Selection (genetic algorithm); Bayesian probability; Data mining; Algorithm; Dirichlet's energy; Topic model; Mathematics","score_opus":0.030304668080942253,"score_gpt":0.29357553369055905,"score_spread":0.2632708656096168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1853714018","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006160155,0.00007670175,0.99660236,0.00092045875,0.000081565304,0.0009151625,0.000004955893,0.00013500212,0.0006477811],"genre_scores_gemma":[0.41205895,0.000008998958,0.58649886,0.00094713655,0.000074833755,0.00032607882,0.0000097363645,0.000012085021,0.000063341715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860966,0.00004695982,0.00021418676,0.0005907733,0.00025557482,0.0002828511],"domain_scores_gemma":[0.99893075,0.00014791977,0.00011171745,0.00027704026,0.00028857437,0.00024401647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042854252,0.00021769996,0.00020850255,0.00014389706,0.00013578031,0.00015559667,0.0004350047,0.00012663749,0.0000021762867],"category_scores_gemma":[0.00008132661,0.00018539213,0.000022817077,0.0006664679,0.000019452546,0.00025798616,0.00014339782,0.00015070116,0.000008765761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018061245,0.000044468587,0.000083117266,0.00004401986,0.000036908972,7.250158e-7,0.00197116,0.009538761,0.018016206,0.7656449,0.0006385205,0.20380056],"study_design_scores_gemma":[0.00028341598,0.0001658002,0.00012349818,0.000019713067,0.000014918551,0.000015874311,0.0000122686915,0.8812915,0.030769337,0.08447986,0.002479266,0.00034451997],"about_ca_topic_score_codex":0.000023972718,"about_ca_topic_score_gemma":0.000051208983,"teacher_disagreement_score":0.87175274,"about_ca_system_score_codex":0.000053598724,"about_ca_system_score_gemma":0.000117477386,"threshold_uncertainty_score":0.75600713},"labels":[],"label_agreement":null},{"id":"W1865403236","doi":"","title":"Atomic Spatial Processes","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Data mining; Process (computing); Spatial analysis; Grid; Bayesian probability; Data modeling; Data science; Artificial intelligence; Geography; Remote sensing; Database","score_opus":0.06616046280778096,"score_gpt":0.32998526289528973,"score_spread":0.26382480008750875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1865403236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002791246,0.00004386309,0.9200253,0.003253451,0.00052394974,0.000053608117,0.000002013257,0.00015552198,0.07315104],"genre_scores_gemma":[0.9126914,0.000019190427,0.084721334,0.0004248096,0.00016065864,0.000008861506,0.000010401118,0.000008769254,0.001954574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883807,0.00012032879,0.00016073562,0.0003193398,0.00039907702,0.0001624324],"domain_scores_gemma":[0.9992028,0.000063921216,0.00010150452,0.00017538683,0.00033759384,0.00011880261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037432957,0.0001302248,0.000119606775,0.00011798777,0.000060918595,0.00024251308,0.00083548384,0.000046869358,0.000090211535],"category_scores_gemma":[0.00040344775,0.00011261934,0.00003284277,0.00012563968,0.000023112581,0.00030494752,0.00017518245,0.000332287,0.00015410532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003743529,0.000052744028,0.002349755,0.000007668642,0.000023291124,0.00002652207,0.00081159075,0.0003383241,0.0003066658,0.7932025,0.0002612661,0.20258224],"study_design_scores_gemma":[0.0006502636,0.00020522528,0.00039731248,0.00005680305,0.0000035600672,0.00003737304,0.000021580976,0.84056824,0.0009629703,0.13775288,0.01907226,0.00027153507],"about_ca_topic_score_codex":0.00014804519,"about_ca_topic_score_gemma":0.000033409524,"teacher_disagreement_score":0.9099001,"about_ca_system_score_codex":0.000047933576,"about_ca_system_score_gemma":0.0002199927,"threshold_uncertainty_score":0.45924833},"labels":[],"label_agreement":null},{"id":"W1882901045","doi":"10.1007/978-3-642-24958-7_9","title":"An Infinite Mixture of Inverted Dirichlet Distributions","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Dirichlet distribution; Computer science; Cluster analysis; Latent Dirichlet allocation; Gaussian; Algorithm; Bayesian probability; Hierarchical Dirichlet process; Selection (genetic algorithm); Artificial intelligence; Pattern recognition (psychology); Categorization; Data mining; Topic model; Mathematics","score_opus":0.02493161102073771,"score_gpt":0.2655297200954098,"score_spread":0.2405981090746721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882901045","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034578876,0.0003935638,0.99267536,0.00029486968,0.0010625031,0.0003045448,0.000041991658,0.00014547538,0.0050471346],"genre_scores_gemma":[0.07969434,0.00005939813,0.9188405,0.0009788367,0.00023018284,0.000007414659,0.000021522203,0.000031912376,0.00013589162],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963748,0.00010183957,0.00067046,0.0014576813,0.0007518684,0.0006433522],"domain_scores_gemma":[0.99621195,0.0002887881,0.00043154001,0.0023376718,0.000430044,0.00030000988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010274634,0.0005746335,0.0007230513,0.0007862368,0.00020001046,0.00022119739,0.004292091,0.0005367891,0.000037895516],"category_scores_gemma":[0.000092642935,0.0004999167,0.00018659803,0.00092884636,0.00093188713,0.0007603229,0.00093567645,0.00092765834,0.000014815854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006309073,0.00007297523,0.000053595006,0.000039922474,0.00001661772,0.000040915013,0.00094050064,0.0004060016,0.0005706622,0.28626186,0.000050352653,0.7115403],"study_design_scores_gemma":[0.00024820902,0.00027134203,0.00027665513,0.00029904448,0.000020174963,0.00005394954,5.0446953e-8,0.14283061,0.004376724,0.8491664,0.0017016365,0.00075519463],"about_ca_topic_score_codex":0.000045518755,"about_ca_topic_score_gemma":0.000048849477,"teacher_disagreement_score":0.7107851,"about_ca_system_score_codex":0.00012449642,"about_ca_system_score_gemma":0.000589813,"threshold_uncertainty_score":0.99974525},"labels":[],"label_agreement":null},{"id":"W1883132424","doi":"10.1139/x10-020","title":"A resampling variance estimator for the<i>k</i>nearest neighbours technique","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"","keywords":"Estimator; Statistics; Resampling; Monte Carlo method; Simple random sample; Variance (accounting); Cluster sampling; Sampling (signal processing); Population; Mathematics; Sample size determination; Sampling design; Mean squared error; Computer science","score_opus":0.06275865723637336,"score_gpt":0.36847013641227405,"score_spread":0.3057114791759007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1883132424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024870061,0.00039177493,0.9875495,0.0073358174,0.00076414074,0.00048455145,0.000008652743,0.000010201511,0.0009683438],"genre_scores_gemma":[0.35644224,0.000012062043,0.6426771,0.00012752581,0.00047066197,0.000052838634,3.485536e-7,0.000018751174,0.00019841515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980293,0.00015976022,0.0003369714,0.00023483403,0.00043483963,0.00080427836],"domain_scores_gemma":[0.9958915,0.0013013585,0.00013525871,0.0007152638,0.00106356,0.00089305063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006925053,0.00012433204,0.00019912381,0.000487302,0.00083606574,0.0005895197,0.0024868005,0.00014550153,0.000021807884],"category_scores_gemma":[0.0019079996,0.00008738719,0.00013600236,0.0006504598,0.00030888242,0.00038345004,0.00007212293,0.0014800862,0.0000058481837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021467302,0.000016272059,0.0025819244,0.00002796243,0.000029694686,0.00018327979,0.0003630102,0.00010581283,0.0026504067,0.9214866,0.009838465,0.062695086],"study_design_scores_gemma":[0.00078927353,0.0005574333,0.015911596,0.00023158445,0.000018677427,0.0016145499,0.00004611106,0.022704512,0.0036320905,0.7244184,0.22967389,0.00040184706],"about_ca_topic_score_codex":0.0024428596,"about_ca_topic_score_gemma":0.036911163,"teacher_disagreement_score":0.35395524,"about_ca_system_score_codex":0.0000889415,"about_ca_system_score_gemma":0.0040051397,"threshold_uncertainty_score":0.9806627},"labels":[],"label_agreement":null},{"id":"W1896267853","doi":"10.1007/978-3-642-30721-8_10","title":"Face Detection and Facial Expression Recognition Using a Novel Variational Statistical Framework","year":2012,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Correctness; Cluster analysis; Feature selection; Artificial intelligence; Pattern recognition (psychology); Face (sociological concept); Dirichlet process; Mixture model; Bayesian probability; Statistical model; Feature (linguistics); Bayesian information criterion; Facial expression; Expression (computer science); Algorithm","score_opus":0.08361531771053259,"score_gpt":0.3316799101567951,"score_spread":0.2480645924462625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1896267853","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029290413,0.00022389504,0.9910914,0.00013895203,0.00029831947,0.00026831048,0.000037779922,0.000048108923,0.007863995],"genre_scores_gemma":[0.018275455,0.00055307936,0.98073924,0.00029069145,0.00006408803,0.000012335809,0.00002821837,0.000006295451,0.000030587908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854136,0.00005385713,0.0005136091,0.00028165244,0.00038916274,0.00022035684],"domain_scores_gemma":[0.99810094,0.0003598809,0.00029835312,0.0008539949,0.00024892308,0.00013789436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011636748,0.00020022453,0.00020676329,0.0005691947,0.0005601006,0.00051251677,0.00091915467,0.00022450105,0.0000111101535],"category_scores_gemma":[0.0000923366,0.00020091515,0.00002503242,0.00024367747,0.0004593888,0.005932203,0.0013280027,0.0005055038,0.000009617463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022747774,0.000011082381,0.0000036533568,0.000013092415,0.0000021019853,5.0288957e-8,0.001172686,0.000030221263,0.000068605485,0.39733058,0.0000033902086,0.6013623],"study_design_scores_gemma":[0.0002349224,0.00003357117,0.00067289075,0.0002347035,0.00001008987,0.000055073022,0.000008878807,0.8401737,0.000053733213,0.14805855,0.010126146,0.00033772],"about_ca_topic_score_codex":0.000009876613,"about_ca_topic_score_gemma":0.0000022532981,"teacher_disagreement_score":0.8401435,"about_ca_system_score_codex":0.000113758746,"about_ca_system_score_gemma":0.00015287193,"threshold_uncertainty_score":0.8193082},"labels":[],"label_agreement":null},{"id":"W1898940374","doi":"10.1007/s00357-015-9188-9","title":"Fractionally-Supervised Classification","year":2015,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McGill University","funders":"","keywords":"Pattern recognition (psychology); A priori and a posteriori; Mixture model; Gaussian; Statistical classification; One-class classification","score_opus":0.12305360804815736,"score_gpt":0.3333380223894209,"score_spread":0.21028441434126355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898940374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038200316,0.00018650849,0.9791811,0.0081115095,0.0007998519,0.0000672083,4.6202342e-7,0.000031373165,0.0078019593],"genre_scores_gemma":[0.53449017,0.00004075111,0.4646477,0.00026824969,0.00030758043,0.000003146377,0.0000015246544,0.0000066872562,0.00023417566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844766,0.00020640326,0.0005173742,0.0001639611,0.00053753715,0.00012704394],"domain_scores_gemma":[0.9978383,0.00009368473,0.00061372144,0.00036811113,0.00087859924,0.00020759027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015324042,0.000095774856,0.00017084867,0.00019492976,0.000053980562,0.00012524499,0.0006047123,0.000093841234,0.000007826966],"category_scores_gemma":[0.00025298406,0.00007868541,0.00009549817,0.000338146,0.00002756579,0.001163794,0.00002885226,0.00022599156,0.000035653582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046070887,0.0002050306,0.00070127106,0.00000868293,0.00003434387,0.000007831388,0.00075584714,0.000031293475,0.031006087,0.55235523,0.017972376,0.39687595],"study_design_scores_gemma":[0.0025724915,0.0005670213,0.11293639,0.00008477765,0.00007220502,0.00058543397,0.00042270852,0.36737117,0.005199163,0.36135578,0.14828308,0.0005497838],"about_ca_topic_score_codex":0.0000014172886,"about_ca_topic_score_gemma":4.9845465e-7,"teacher_disagreement_score":0.53067017,"about_ca_system_score_codex":0.00013528118,"about_ca_system_score_gemma":0.00035853952,"threshold_uncertainty_score":0.32086977},"labels":[],"label_agreement":null},{"id":"W1901230542","doi":"10.1002/cjs.11211","title":"Minimum profile Hellinger distance estimation for a semiparametric mixture model","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Hellinger distance; Estimator; Semiparametric regression; Cluster analysis; Component (thermodynamics); Mixture model; Mathematics; Semiparametric model; Statistics; Computer science; Applied mathematics","score_opus":0.018264807118921454,"score_gpt":0.25165805503387406,"score_spread":0.2333932479149526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1901230542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013459643,0.00027794944,0.99813896,0.000416786,0.00043097077,0.00013705391,0.0001757821,0.0000068900717,0.0002810239],"genre_scores_gemma":[0.08142766,0.000008555061,0.9177579,0.00032664379,0.00010228071,0.000004401708,0.0000061616192,0.000012566637,0.00035381957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989681,0.000055308334,0.0003534389,0.00015671927,0.00016641412,0.00030001727],"domain_scores_gemma":[0.99826694,0.00030541027,0.00028520366,0.00022484177,0.00043196723,0.00048561447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006274044,0.000120769444,0.0002246716,0.0002531606,0.00012784232,0.00015555446,0.0004694892,0.00007672061,0.0000051991296],"category_scores_gemma":[0.00067189784,0.00010928045,0.00005764192,0.0002707116,0.000042993335,0.00021416489,0.000008650042,0.00016971787,0.0000026978898],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000098495575,0.00001520157,0.000030135505,0.00008796473,0.000022307711,0.000022366901,0.0007419987,0.013014625,0.00005819937,0.6200487,0.05451118,0.3114375],"study_design_scores_gemma":[0.00018373187,0.000085063024,0.000019530537,0.00003123373,0.000015385825,0.000024386001,0.0000021594622,0.73392683,0.00010236481,0.26146126,0.004047103,0.00010096418],"about_ca_topic_score_codex":0.00004430164,"about_ca_topic_score_gemma":0.00039366845,"teacher_disagreement_score":0.7209122,"about_ca_system_score_codex":0.00008925347,"about_ca_system_score_gemma":0.0008077803,"threshold_uncertainty_score":0.44563276},"labels":[],"label_agreement":null},{"id":"W1909579684","doi":"10.1002/sim.6582","title":"A joint model for interval‐censored functional decline trajectories under informative observation","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Inference; Bivariate analysis; Computer science; Bayesian inference; Disease; Econometrics; Joint probability distribution; Statistics; Interval (graph theory); Bayesian probability; Process (computing); Random effects model; Bayes' theorem; Machine learning; Artificial intelligence; Medicine; Mathematics; Meta-analysis","score_opus":0.1438789696419815,"score_gpt":0.3567442275512428,"score_spread":0.2128652579092613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1909579684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002565739,0.00007063,0.99537176,0.0027189387,0.0006984684,0.0002720137,0.000053322703,0.000043458007,0.00051483384],"genre_scores_gemma":[0.038841687,0.000012661706,0.9584787,0.001955229,0.0001497352,0.00004759268,0.00008715414,0.000009316379,0.0004179619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866176,0.0000652135,0.00047962932,0.00021371325,0.00036650986,0.00021315874],"domain_scores_gemma":[0.9987467,0.00030969214,0.00014028285,0.00023582371,0.00044445423,0.000123035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012388765,0.0001421579,0.00028341293,0.0001364207,0.00004511919,0.000027094573,0.0002297295,0.00006277532,0.000006542623],"category_scores_gemma":[0.00096396654,0.00011168825,0.000022762355,0.00024091703,0.000097799304,0.00030011384,0.00008633168,0.0001549437,0.0000023468572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050204297,0.000027416747,0.000048870636,0.000032617707,0.000012582622,0.0000020111966,0.0059843115,0.0039836145,0.00004329295,0.9504852,0.018382506,0.020947367],"study_design_scores_gemma":[0.00089329627,0.00011850951,0.0006604059,0.000030393678,0.0000061335368,0.0000025002323,0.000110438705,0.5289862,0.00002014157,0.46891114,0.0001921493,0.00006869083],"about_ca_topic_score_codex":0.000038252518,"about_ca_topic_score_gemma":0.00009332276,"teacher_disagreement_score":0.5250026,"about_ca_system_score_codex":0.00011477757,"about_ca_system_score_gemma":0.00020107979,"threshold_uncertainty_score":0.45545146},"labels":[],"label_agreement":null},{"id":"W1916284516","doi":"","title":"Robust High-Dimensional Modeling with the Contaminated Gaussian Distribution","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Outlier; Gaussian; Spurious relationship; Mixture model; Gaussian noise; Mathematics; Computer science; Expectation–maximization algorithm; Generalization; Algorithm; Dimension (graph theory); Gaussian network model; Distribution (mathematics); Applied mathematics; Mathematical optimization; Statistics; Mathematical analysis; Physics; Combinatorics; Maximum likelihood","score_opus":0.05556797779894152,"score_gpt":0.17643035395800732,"score_spread":0.12086237615906581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916284516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066156566,0.000030188441,0.93200815,0.00066318613,0.00029102995,0.00025691715,0.000021748614,0.00017125739,0.0004009625],"genre_scores_gemma":[0.96593237,0.000013650829,0.033211667,0.00018524914,0.00007950729,0.0000014684944,0.00007356833,0.000016778185,0.00048574514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794143,0.00035967978,0.00016200454,0.0010268838,0.00014018187,0.00036983553],"domain_scores_gemma":[0.9980861,0.00009659594,0.00021049814,0.0012211015,0.00023278187,0.00015293938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005398239,0.0003412612,0.000336597,0.00008138265,0.00031697899,0.00014783195,0.0014509171,0.00027849388,0.000008981345],"category_scores_gemma":[0.00001379794,0.00024863382,0.00013282655,0.0003730949,0.000120490244,0.00022699358,0.0010632928,0.00073268125,0.000016970685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021958102,0.000023179022,0.00001338758,0.000013920245,0.000042617292,0.00006084544,0.00003957592,0.57999796,0.000007528445,0.41879785,0.00019805436,0.0007830901],"study_design_scores_gemma":[0.00039905836,0.000048105536,0.00012043096,0.00008610817,0.00007696217,0.000010080753,0.000008297184,0.9488088,0.00004210453,0.049969874,0.000088038614,0.00034217836],"about_ca_topic_score_codex":0.00022664253,"about_ca_topic_score_gemma":0.000049329028,"teacher_disagreement_score":0.8997758,"about_ca_system_score_codex":0.00015599825,"about_ca_system_score_gemma":0.00018023924,"threshold_uncertainty_score":0.9999966},"labels":[],"label_agreement":null},{"id":"W1918133462","doi":"10.1002/sim.4320","title":"Modeling continuous diagnostic test data using approximate Dirichlet process distributions","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University Health Centre; Royal Victoria Regional Health Centre; McGill University","funders":"","keywords":"Nonparametric statistics; Dirichlet process; Computer science; Context (archaeology); Hierarchical Dirichlet process; Latent Dirichlet allocation; Parametric statistics; Identifiability; Cluster analysis; Bayesian probability; Data mining; Econometrics; Mathematics; Statistics; Machine learning; Artificial intelligence; Topic model","score_opus":0.09951210076774852,"score_gpt":0.36345671379794736,"score_spread":0.26394461303019884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1918133462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005451012,0.0003175704,0.99729115,0.00014470656,0.00031055685,0.00023934327,0.00041699328,0.00006645076,0.00066815113],"genre_scores_gemma":[0.27169588,0.00006953253,0.7278955,0.00010549286,0.000084495914,0.000010789268,0.000114770686,0.0000118546095,0.000011710637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823844,0.000091995505,0.0004618968,0.00053035055,0.00029366824,0.0003836465],"domain_scores_gemma":[0.9976237,0.00096508843,0.00010369919,0.0010099617,0.0001628418,0.00013471098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010353995,0.0001829389,0.00034150342,0.00011086028,0.0001104334,0.000030299527,0.0012615253,0.00006116108,0.000022774413],"category_scores_gemma":[0.0055947085,0.00015079406,0.000009981279,0.0004541707,0.00014802242,0.00027404155,0.000349655,0.00026252153,0.0000026541447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017747803,0.00070654036,0.0060168193,0.00039705422,0.0000499377,0.00083225744,0.00852656,0.00076499843,0.00026644464,0.86658865,0.0026650291,0.11316796],"study_design_scores_gemma":[0.00033103957,0.00005621851,0.00014392154,0.00015802117,0.000028757055,0.000025438267,0.000046607485,0.7843422,0.00002045582,0.21467786,0.00002393642,0.00014554315],"about_ca_topic_score_codex":0.0002879171,"about_ca_topic_score_gemma":0.00004503204,"teacher_disagreement_score":0.7835772,"about_ca_system_score_codex":0.000037976697,"about_ca_system_score_gemma":0.00010277379,"threshold_uncertainty_score":0.66977924},"labels":[],"label_agreement":null},{"id":"W1924956554","doi":"10.1002/rsa.20601","title":"Structure of random 312‐avoiding permutations","year":2015,"lang":"en","type":"article","venue":"Random Structures and Algorithms","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Random permutation; Permutation (music); Mathematics; Combinatorics; Diagonal; Random walk; Joint probability distribution; Random graph; struct; Discrete mathematics; Set (abstract data type); Graph; Expected value; Statistics; Computer science; Symmetric group; Geometry; Physics","score_opus":0.021360138136575044,"score_gpt":0.2776378002865467,"score_spread":0.25627766214997166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1924956554","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031017128,0.0017104106,0.96573585,0.00024702458,0.0005258769,0.00023369081,0.000027645694,0.000060444916,0.00044195252],"genre_scores_gemma":[0.65069336,0.000048382954,0.34895363,0.00009431796,0.00013846309,0.0000029103865,0.000004862474,0.000009518468,0.00005452192],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99847245,0.00025488308,0.00032741218,0.0003735975,0.0003122018,0.0002594612],"domain_scores_gemma":[0.998876,0.00025101093,0.00014777221,0.00035489412,0.00014979216,0.00022053625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004481086,0.00021223375,0.00046165733,0.000120037905,0.00016921556,0.00012822227,0.00039024308,0.0001126723,0.000012181853],"category_scores_gemma":[0.00017063637,0.00015446363,0.00010049743,0.00025807068,0.00009647933,0.00030738304,0.00013574997,0.00022751604,5.1218177e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004299449,0.000042207397,0.0002556013,0.00011789014,0.00021603632,0.000039581068,0.011843703,0.0009899171,0.016270231,0.4484728,0.0016430632,0.519679],"study_design_scores_gemma":[0.01907189,0.0001555551,0.00073087076,0.00004016207,0.00006971765,0.00025446792,0.00022302006,0.09993662,0.016344931,0.86119944,0.0014658102,0.0005075059],"about_ca_topic_score_codex":0.000043158332,"about_ca_topic_score_gemma":0.0000046057257,"teacher_disagreement_score":0.61967623,"about_ca_system_score_codex":0.000014532412,"about_ca_system_score_gemma":0.0000842259,"threshold_uncertainty_score":0.6298844},"labels":[],"label_agreement":null},{"id":"W1926406141","doi":"10.1111/sjos.12119","title":"A Class of Pseudolikelihood Ratio Tests for Homogeneity in Exponential Tilt Mixture Models","year":2014,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Agency for Healthcare Research and Quality","keywords":"Mathematics; Exponential family; Homogeneity (statistics); Infimum and supremum; Statistics; Pairwise comparison; Null distribution; Likelihood-ratio test; Null (SQL); Score test; Asymptotic distribution; Exponential function; Null hypothesis; Applied mathematics; Statistical hypothesis testing; Combinatorics; Test statistic; Mathematical analysis; Computer science","score_opus":0.024001586005163205,"score_gpt":0.28538653626354776,"score_spread":0.26138495025838454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926406141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072188415,0.00016814932,0.99147093,0.00020466014,0.00050834933,0.00017222401,0.00009390054,0.000006980999,0.00015599062],"genre_scores_gemma":[0.4573794,0.00002369564,0.5423961,0.00005259172,0.00010669951,0.0000027195047,0.0000020824427,0.00000894001,0.000027751521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981991,0.0002119093,0.0007423042,0.00020796659,0.00034645764,0.00029227693],"domain_scores_gemma":[0.9981403,0.0003318022,0.0006033575,0.00031067632,0.00044405577,0.00016983594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011513461,0.00017060086,0.0004746299,0.00023501688,0.000058438145,0.00006436318,0.0006518455,0.0001029778,0.0000042340275],"category_scores_gemma":[0.0002332168,0.00014765514,0.000117420816,0.00025033933,0.000065010754,0.00034802826,0.000063769876,0.00023868428,5.723552e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016977885,0.00028173058,0.0014198999,0.00019028038,0.00006439747,0.000048650534,0.0017522951,0.0011436299,0.006336235,0.83753496,0.004784211,0.14627393],"study_design_scores_gemma":[0.0020298273,0.000815059,0.0025125619,0.00022426502,0.00004892636,0.0001399911,0.000017511782,0.2617868,0.0032083942,0.7287653,0.00020475805,0.000246643],"about_ca_topic_score_codex":0.000009399967,"about_ca_topic_score_gemma":0.000021411071,"teacher_disagreement_score":0.45016056,"about_ca_system_score_codex":0.00004844961,"about_ca_system_score_gemma":0.00016270907,"threshold_uncertainty_score":0.60212016},"labels":[],"label_agreement":null},{"id":"W1927455312","doi":"10.1016/j.csda.2015.10.008","title":"Clustering, classification, discriminant analysis, and dimension reduction via generalized hyperbolic mixtures","year":2015,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linear discriminant analysis; Mathematics; Dimensionality reduction; Cluster analysis; Discriminant; Pattern recognition (psychology); Dimension (graph theory); Optimal discriminant analysis; Reduction (mathematics); Artificial intelligence; Statistics; Combinatorics; Computer science; Geometry","score_opus":0.0754486668289481,"score_gpt":0.3390932652654944,"score_spread":0.2636445984365463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1927455312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015486905,0.00038863797,0.99675894,0.00050231005,0.00015422842,0.00011067991,0.00043404926,0.000065980006,0.000036482423],"genre_scores_gemma":[0.22602437,0.00006892631,0.76893437,0.00011300245,0.0000643599,0.000006912036,0.004714383,0.000009002503,0.000064699896],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973512,0.0003559842,0.000521234,0.0009440906,0.000585854,0.00024159513],"domain_scores_gemma":[0.9976725,0.00014755968,0.00029032008,0.001181228,0.0004276543,0.00028076363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086153037,0.000227387,0.00048819694,0.0006759506,0.00022557878,0.00032616704,0.0007387299,0.000073194286,0.000011856934],"category_scores_gemma":[0.00011932305,0.00020383277,0.00009331709,0.002336661,0.00010383829,0.0005105096,0.00060544914,0.00011955634,0.000007967352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008585783,0.00047957417,0.009227887,0.000066834,0.011180832,0.000055576547,0.0025386892,0.20646195,0.0012428329,0.36725673,0.02740455,0.37399867],"study_design_scores_gemma":[0.00023613537,0.000021360009,0.038969234,0.000002622189,0.0029207894,0.000014343056,0.000008073602,0.89177203,0.000013090028,0.06544658,0.000368914,0.00022684074],"about_ca_topic_score_codex":0.00070156145,"about_ca_topic_score_gemma":0.00022070885,"teacher_disagreement_score":0.68531007,"about_ca_system_score_codex":0.000058844915,"about_ca_system_score_gemma":0.00010597518,"threshold_uncertainty_score":0.8312059},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.047875923516430254,"score_gpt":0.29877534862908994,"score_spread":0.25089942511265967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W194034371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027290452,0.00007915936,0.99679303,0.000035193498,0.00004485125,0.000067148,0.0000632485,0.000024028956,0.00016427437],"genre_scores_gemma":[0.49958372,0.0000038879775,0.50037414,0.000018256294,0.0000042396077,9.685488e-7,0.000007414913,0.0000024680637,0.000004911665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912226,0.00007028395,0.00026547574,0.00028666866,0.00009454894,0.0001607754],"domain_scores_gemma":[0.9992904,0.00010064811,0.00016197166,0.0002487998,0.00011504878,0.00008312005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000281157,0.000111571426,0.00021126133,0.00010048976,0.00016026628,0.00004688162,0.0001736848,0.000039939452,0.0000015442944],"category_scores_gemma":[0.000031011743,0.00009721716,0.000034144206,0.00023534703,0.00008673535,0.00005368568,0.00013947109,0.000072228446,1.2614183e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006733356,0.00007357227,0.0010062739,0.00006372903,0.00010306799,0.0000045381894,0.0018760887,0.00092097145,0.0015382491,0.84513366,0.00003124187,0.14924185],"study_design_scores_gemma":[0.00012966715,0.000029020926,0.0222449,0.000012097933,0.00010973593,0.0000021834155,0.000007282641,0.9169793,0.00025772376,0.060115635,0.000004918546,0.00010754655],"about_ca_topic_score_codex":0.000121556535,"about_ca_topic_score_gemma":0.000025335285,"teacher_disagreement_score":0.9160583,"about_ca_system_score_codex":0.0000074852605,"about_ca_system_score_gemma":0.000030299481,"threshold_uncertainty_score":0.3964401},"labels":[],"label_agreement":null},{"id":"W1947760575","doi":"10.18637/jss.v047.i05","title":"High-Dimensional Bayesian Clustering with Variable Selection: The<i>R</i>Package<b>bclust</b>","year":2012,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Neuchâtel; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"R package; Cluster analysis; Computer science; Bayesian probability; Hierarchical clustering; Bayes' theorem; Bayes factor; Parametric statistics; Variable (mathematics); Data mining; Mathematics; Artificial intelligence; Statistics","score_opus":0.01069729842721405,"score_gpt":0.2481134082660615,"score_spread":0.23741610983884748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1947760575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021999533,0.0001824587,0.9980267,0.00070481416,0.00062455935,0.00008083745,0.000009942041,0.00004115682,0.00010949628],"genre_scores_gemma":[0.099877656,0.0000034759705,0.89879256,0.0007017149,0.0005002862,0.0000027179349,0.0000010302963,0.00001572708,0.00010482828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981723,0.00022046584,0.00040784795,0.00016884768,0.00057955796,0.0004509734],"domain_scores_gemma":[0.9981726,0.00071310526,0.0002605646,0.00023500252,0.00027444167,0.00034431188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010648316,0.00017811632,0.00030002368,0.00006991405,0.00025592832,0.00014014497,0.0004841047,0.00007509237,0.00014089336],"category_scores_gemma":[0.00024036107,0.00010205493,0.000055794677,0.00034998346,0.00008105119,0.0006750577,0.00013624127,0.00048917026,0.00000982468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022759278,0.0003944675,0.0024964241,0.000088705434,0.00023542235,0.00016447557,0.0007403185,0.0021057862,0.0003567246,0.78579915,0.020540465,0.18685047],"study_design_scores_gemma":[0.007143085,0.0044375747,0.04506832,0.0009666519,0.000759886,0.023276739,0.00009489867,0.12404591,0.00276952,0.7561005,0.032706946,0.00262999],"about_ca_topic_score_codex":0.00001885726,"about_ca_topic_score_gemma":0.000003331293,"teacher_disagreement_score":0.18422048,"about_ca_system_score_codex":0.000074184005,"about_ca_system_score_gemma":0.00017047157,"threshold_uncertainty_score":0.4161679},"labels":[],"label_agreement":null},{"id":"W1963917975","doi":"10.3758/brm.38.2.344","title":"An SPSS implementation of the nonrecursive outlier deletion procedure with shiftingz score criterion (Van Selst &amp; Jolicoeur, 1994)","year":2006,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Outlier; Computer science; Univariate; Popularity; Simple (philosophy); Data mining; Database; Restructuring; Artificial intelligence; Machine learning; Psychology","score_opus":0.11959399906640342,"score_gpt":0.5160720460885306,"score_spread":0.3964780470221272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963917975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31132844,0.000052665873,0.6870266,0.00033833185,0.00009843652,0.00089388416,0.000010562209,0.000049745697,0.00020130222],"genre_scores_gemma":[0.30195624,0.000005588505,0.69743353,0.00004501155,0.00010666441,0.00020949851,0.000015259413,0.000028486491,0.00019970656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9934628,0.003654263,0.00044018574,0.0007051111,0.0010730173,0.0006645946],"domain_scores_gemma":[0.9976627,0.00021857365,0.00021794393,0.0011585873,0.00058619084,0.00015597211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055869278,0.00023310521,0.00028127784,0.00029821173,0.00043632562,0.00027380584,0.0012799908,0.0001357614,0.00004169697],"category_scores_gemma":[0.000089136265,0.00015935778,0.00010351118,0.0013332486,0.0002509446,0.0006333599,0.00029842663,0.00057084486,0.0000032768596],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006022935,0.0005037858,0.027521895,0.00009622674,0.0000152342145,0.0000136143335,0.0039815125,0.000019725265,0.23077105,0.025052471,0.0006393085,0.71132493],"study_design_scores_gemma":[0.0019929965,0.0015155287,0.51777166,0.00030048346,0.00012022908,0.00017810639,0.0009004364,0.0020447646,0.42872405,0.038485814,0.006956401,0.0010095207],"about_ca_topic_score_codex":0.0011115365,"about_ca_topic_score_gemma":0.00064772926,"teacher_disagreement_score":0.7103154,"about_ca_system_score_codex":0.00011980222,"about_ca_system_score_gemma":0.00033904647,"threshold_uncertainty_score":0.64984214},"labels":[],"label_agreement":null},{"id":"W1964231120","doi":"10.1007/s11634-014-0165-7","title":"Variational Bayes approximations for clustering via mixtures of normal inverse Gaussian distributions","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Bayes' theorem; Gaussian; Univariate; Applied mathematics; Cluster analysis; Mixture model; Inverse Gaussian distribution; Multivariate normal distribution; Mathematics; Inverse; Inverse problem; Multivariate statistics; Mathematical optimization; Computer science; Statistics; Distribution (mathematics); Mathematical analysis; Bayesian probability; Chemistry; Computational chemistry","score_opus":0.028086007090192076,"score_gpt":0.3141116705601102,"score_spread":0.2860256634699181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964231120","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000120328106,0.00015362217,0.9985153,0.0005635862,0.000047341255,0.0001096411,0.00017838979,0.000014618084,0.0002971422],"genre_scores_gemma":[0.34361687,0.000118410106,0.6553992,0.000027101303,0.000025546971,0.000028318958,0.00076808746,0.0000022496477,0.00001423537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998966,0.000096497744,0.00031996376,0.00037938575,0.0001207978,0.00011739299],"domain_scores_gemma":[0.9987557,0.00020655249,0.00020292086,0.0007221245,0.000071810304,0.000040928153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006883994,0.00008289042,0.00018782428,0.00020256125,0.00010993011,0.000053101274,0.00052086817,0.0000455955,0.000004332203],"category_scores_gemma":[0.00014683107,0.000074637,0.000047082845,0.00073399325,0.000051629242,0.0011750644,0.00014386424,0.000052423387,4.1637674e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008323299,0.00008917396,0.0030594526,0.000059738144,0.00008638834,7.126057e-8,0.00015330725,0.001032707,0.0015592381,0.6952657,0.00007375784,0.29861215],"study_design_scores_gemma":[0.00014718367,0.00001170595,0.014476636,0.000007200678,0.00009127513,5.750022e-7,0.000010156096,0.9342356,0.00013921795,0.04818898,0.002608542,0.00008293272],"about_ca_topic_score_codex":0.0000147773635,"about_ca_topic_score_gemma":0.00042800963,"teacher_disagreement_score":0.93320286,"about_ca_system_score_codex":0.000014694457,"about_ca_system_score_gemma":0.000018731178,"threshold_uncertainty_score":0.30436084},"labels":[],"label_agreement":null},{"id":"W1964874888","doi":"10.1239/jap/1019737988","title":"On probability generating functions for waiting time distributions of compound patterns in a sequence of multistate trials","year":2002,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Markov chain; Mathematics; Probability distribution; Probability-generating function; Sequence (biology); Generating function; Probability mass function; Algorithm; Statistics; Discrete mathematics","score_opus":0.11092957150548823,"score_gpt":0.31637288672889785,"score_spread":0.20544331522340964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964874888","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36118433,0.000019286344,0.637676,0.00018124744,0.00006948365,0.00061348564,0.000117785574,0.000008611145,0.00012978147],"genre_scores_gemma":[0.6198422,0.00000276654,0.38006204,0.000015867177,0.00003685243,0.000027712082,0.0000029241348,0.000004360321,0.0000052933274],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968481,0.00044202432,0.0018399477,0.00031921986,0.00030339597,0.00024731323],"domain_scores_gemma":[0.99595165,0.0016855883,0.0014251744,0.00044824355,0.00039819136,0.000091159614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068100025,0.00016582964,0.0008140297,0.00010820853,0.000093368755,0.000038268925,0.0004373485,0.00008842493,0.000021581342],"category_scores_gemma":[0.001106437,0.00013282454,0.00027487037,0.0003194393,0.0001097257,0.00019790838,0.00007306092,0.00027946767,7.7703794e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008567054,0.004608942,0.0018212927,0.0013585809,0.0002484429,0.000011820308,0.0045850202,0.026861073,0.19576666,0.3666794,0.00045729484,0.3967448],"study_design_scores_gemma":[0.0025169936,0.0006633005,0.00077783875,0.00025432513,0.000064185704,0.000026468488,0.000025012805,0.41996503,0.020257745,0.5550751,0.00008354082,0.00029043073],"about_ca_topic_score_codex":0.000011832967,"about_ca_topic_score_gemma":0.000010979552,"teacher_disagreement_score":0.39645433,"about_ca_system_score_codex":0.00017027867,"about_ca_system_score_gemma":0.00010342201,"threshold_uncertainty_score":0.5416427},"labels":[],"label_agreement":null},{"id":"W1965801607","doi":"10.2307/3316028","title":"Generalized likelihood‐ratio test of the number of components in finite mixture models (chen 1994, lemma 1): Correction","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Lemma (botany); Chen; Zhàng; Citation; Statistics; Library science; Mathematical sciences; Mathematics; Test (biology); Computer science; China; History","score_opus":0.026668868473056693,"score_gpt":0.24500316587591078,"score_spread":0.2183342974028541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965801607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016296336,0.00011427705,0.9819422,0.00029465204,0.0008462658,0.00009042054,0.00014778337,0.0000021231917,0.00026598346],"genre_scores_gemma":[0.59574825,0.000018995512,0.40398774,0.00014823688,0.000037694368,6.7075723e-7,0.0000023338193,0.000007445083,0.00004864975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987073,0.00012060911,0.00058512896,0.00011652094,0.00024324025,0.00022719908],"domain_scores_gemma":[0.9985798,0.00017968816,0.00048135413,0.00025410307,0.0002672681,0.00023779726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003907252,0.00011942983,0.0002897562,0.00015264864,0.00006385585,0.000037701808,0.0005677476,0.000085099884,0.000011826688],"category_scores_gemma":[0.00019520176,0.0000945043,0.00007230331,0.00035407895,0.0000899129,0.00020286585,0.000026679973,0.00029002884,7.913364e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060375678,0.00035982003,0.035187814,0.00018736155,0.000177928,0.00043826306,0.013293722,0.11893381,0.007005259,0.7415777,0.012476465,0.070301495],"study_design_scores_gemma":[0.0024516596,0.0001874795,0.017602917,0.00051281013,0.000067540655,0.00037338992,0.000057064688,0.199811,0.0043609072,0.7736291,0.0005863818,0.00035971266],"about_ca_topic_score_codex":0.0075470745,"about_ca_topic_score_gemma":0.013453755,"teacher_disagreement_score":0.5794519,"about_ca_system_score_codex":0.00014162862,"about_ca_system_score_gemma":0.0012402922,"threshold_uncertainty_score":0.99906176},"labels":[],"label_agreement":null},{"id":"W1967330157","doi":"10.1002/sim.1015","title":"Identification of significant host factors for HIV dynamics modelled by non‐linear mixed‐effects models","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Covariate; Missing data; Bayes' theorem; Statistics; Linear model; Computer science; Bayes factor; Imputation (statistics); Model selection; Generalized linear mixed model; Data set; Econometrics; Mathematics; Bayesian probability","score_opus":0.022087407292849283,"score_gpt":0.29134701606028024,"score_spread":0.26925960876743094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967330157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016024414,0.00017371264,0.99619114,0.00041095773,0.00045187218,0.00059154653,0.0003603281,0.000029116225,0.0001889075],"genre_scores_gemma":[0.43605968,0.0001152629,0.5632087,0.000059377628,0.000034527136,0.00003237294,0.00007780673,0.000017009792,0.00039528022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813086,0.000109667984,0.0006695977,0.0004247584,0.0003695074,0.00029560938],"domain_scores_gemma":[0.99792373,0.0009816828,0.00027422514,0.0005182455,0.00018987418,0.000112253394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074060576,0.00020416937,0.000462454,0.00017801693,0.000058612968,0.000016018099,0.0005495753,0.00010047039,0.000007521651],"category_scores_gemma":[0.0004158783,0.00016906932,0.00003831281,0.0003199911,0.00013413894,0.00015496323,0.000055987744,0.00016413601,0.000002009946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021902002,0.0003054317,0.000092501934,0.00048735613,0.000046745292,0.00001316671,0.0048243385,0.0038659356,0.015556922,0.9128855,0.02435914,0.037541095],"study_design_scores_gemma":[0.00081431604,0.00015391828,0.000044695666,0.000059849088,0.000024315139,7.406281e-7,0.00003856041,0.8718145,0.002398304,0.12448126,0.000024063638,0.00014548506],"about_ca_topic_score_codex":0.000040506016,"about_ca_topic_score_gemma":0.000009569858,"teacher_disagreement_score":0.86794853,"about_ca_system_score_codex":0.000074383075,"about_ca_system_score_gemma":0.000020954625,"threshold_uncertainty_score":0.68944466},"labels":[],"label_agreement":null},{"id":"W1968451041","doi":"10.1016/j.csda.2004.11.002","title":"Online EM algorithm for mixture with application to internet traffic modeling","year":2004,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada); Université de Moncton","funders":"Atlantic Canada Opportunities Agency; Nortel Networks Inc","keywords":"Mixture model; Algorithm; Computer science; Expectation–maximization algorithm; Likelihood function; Bayesian information criterion; The Internet; Internet traffic; Function (biology); Data mining; Bayesian probability; Projection (relational algebra); Bayesian network; Maximum likelihood; Estimation theory; Mathematics; Artificial intelligence; Statistics","score_opus":0.02809426787345406,"score_gpt":0.3187321460669584,"score_spread":0.29063787819350434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968451041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029238066,0.000043415093,0.994761,0.00041537327,0.000040118724,0.00030155384,0.004068326,0.00007456709,0.0000032713685],"genre_scores_gemma":[0.030590601,0.0000040342366,0.95659554,0.0005005065,0.000079845086,0.00003198733,0.012158066,0.000015423218,0.000023980527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817187,0.000042520573,0.00035178446,0.0008170511,0.00038513466,0.00023166348],"domain_scores_gemma":[0.99835885,0.00016439603,0.00012184514,0.0007959512,0.00039617045,0.00016280217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032263045,0.00019130688,0.00030782152,0.00027967733,0.00011633831,0.00022251724,0.0011191264,0.000051186144,0.0000034974807],"category_scores_gemma":[0.000039338986,0.0001705605,0.000060264294,0.0011573494,0.000020234105,0.00027911685,0.00024961363,0.000106842934,0.00000746867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043003256,0.000082181636,0.000003796393,0.000005779437,0.0002286743,0.0000025297604,0.00017145884,0.63394976,7.8267686e-7,0.037232894,0.00023391283,0.32808396],"study_design_scores_gemma":[0.00034482463,0.000064914515,0.00014085199,0.000009423759,0.00036954638,0.0000032524497,0.0000072059415,0.93458176,0.0000019629092,0.06398468,0.00027941138,0.00021216222],"about_ca_topic_score_codex":0.00011247775,"about_ca_topic_score_gemma":0.00055775174,"teacher_disagreement_score":0.3278718,"about_ca_system_score_codex":0.0000687246,"about_ca_system_score_gemma":0.00013949984,"threshold_uncertainty_score":0.6955255},"labels":[],"label_agreement":null},{"id":"W1968582160","doi":"10.1109/ijcnn.2013.6706757","title":"Unsupervised feature selection for proportional data clustering via expectation propagation","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Feature selection; Artificial intelligence; Pattern recognition (psychology); Inference; Feature (linguistics); Model selection; Dirichlet distribution; Mixture model; Context (archaeology); Affinity propagation; Data mining; Machine learning; Canopy clustering algorithm; Correlation clustering; Mathematics","score_opus":0.03869070198068593,"score_gpt":0.2917159977199154,"score_spread":0.2530252957392295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968582160","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008111259,0.000016759202,0.9954011,0.0020598357,0.00018184147,0.0008693212,0.0000017869787,0.00017513198,0.00048312885],"genre_scores_gemma":[0.075438574,0.0000012509657,0.92312795,0.00029710506,0.00014624857,0.00017091035,0.000070670336,0.000008402127,0.0007389125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905074,0.000048652197,0.00015443953,0.0004127569,0.00016714148,0.0001662982],"domain_scores_gemma":[0.9992478,0.000033432894,0.00007222766,0.00039082736,0.00020394447,0.000051757186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027327857,0.00009751467,0.0000872548,0.00006243963,0.00013445315,0.00017628945,0.0004302393,0.000057135465,0.000035288063],"category_scores_gemma":[0.000028290671,0.00007787107,0.000026472182,0.0001974101,0.000009614239,0.0016617649,0.00012600608,0.00006891073,0.000014170858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019444702,0.000117098076,0.00040225746,0.00011166695,0.00003577031,5.2500206e-7,0.00059622223,0.00014672264,0.08689896,0.052116368,0.026617453,0.83293754],"study_design_scores_gemma":[0.00022004663,0.000050053884,0.0010675739,0.0000068316003,0.0000043313908,0.00001548799,0.0000074261884,0.97836274,0.004792897,0.014729215,0.00062399503,0.000119391494],"about_ca_topic_score_codex":0.000040025898,"about_ca_topic_score_gemma":0.000020957568,"teacher_disagreement_score":0.97821605,"about_ca_system_score_codex":0.000030108822,"about_ca_system_score_gemma":0.000055441495,"threshold_uncertainty_score":0.317549},"labels":[],"label_agreement":null},{"id":"W1968593589","doi":"10.1080/10485252.2013.856431","title":"Goodness-of-fit tests based on the distance between the Dirichlet process and its base measure","year":2014,"lang":"en","type":"article","venue":"Journal of nonparametric statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet process; Mathematics; Concentration parameter; Hierarchical Dirichlet process; Latent Dirichlet allocation; Goodness of fit; Measure (data warehouse); Nonparametric statistics; Dirichlet distribution; Inference; Base (topology); Applied mathematics; Statistics; Bayesian probability; Mathematical analysis; Computer science; Topic model; Data mining; Artificial intelligence; Boundary value problem","score_opus":0.04767650177503057,"score_gpt":0.3154568157603176,"score_spread":0.267780313985287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968593589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046262653,0.00037838466,0.9927004,0.001574046,0.00019639435,0.00014916284,0.000046788868,0.0000073223378,0.0003212287],"genre_scores_gemma":[0.7376444,0.000019265011,0.26184785,0.00035482147,0.0001053554,0.0000023357202,3.2412964e-7,0.000009102825,0.000016590895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977986,0.00047786502,0.000516837,0.00018806076,0.00080163457,0.00021696676],"domain_scores_gemma":[0.99046624,0.0076193814,0.00076061755,0.00041991373,0.0005996017,0.00013424287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029437733,0.00016997583,0.0003617897,0.00020311188,0.00014712327,0.00012623762,0.0010099947,0.00006176614,0.0000044273856],"category_scores_gemma":[0.0054603554,0.000086057014,0.00006249638,0.0012606046,0.00009121748,0.00014010457,0.00005506124,0.00042603342,0.0000015138052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094102455,0.00035534546,0.012615802,0.00027860032,0.00014063616,0.000050500144,0.00079482276,0.0014904896,0.00007621444,0.31528023,0.0058704126,0.66295284],"study_design_scores_gemma":[0.0014751388,0.0014737623,0.05960437,0.00039619792,0.00025570102,0.000060363567,0.000032287717,0.7500765,0.0013960139,0.18275464,0.0019779059,0.00049715256],"about_ca_topic_score_codex":0.0000017301609,"about_ca_topic_score_gemma":7.5453784e-7,"teacher_disagreement_score":0.748586,"about_ca_system_score_codex":0.000025938587,"about_ca_system_score_gemma":0.00015034765,"threshold_uncertainty_score":0.653695},"labels":[],"label_agreement":null},{"id":"W1968705029","doi":"10.1002/cjs.11170","title":"Generalized estimating equations for mixtures with varying concentrations","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Asymptotic distribution; Parametric statistics; Generalized estimating equation; Applied mathematics; Nonparametric statistics; Statistics; Nuisance parameter; Parametric model; Gee; Estimating equations; Covariance matrix; Distribution (mathematics); Covariance; Dispersion (optics); Mixing (physics); Mathematical analysis; Estimator; Physics","score_opus":0.031482776744084784,"score_gpt":0.26659893724020023,"score_spread":0.23511616049611544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968705029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001517177,0.000118614844,0.99790084,0.001011777,0.00033556766,0.00017023612,0.00005882624,0.000005772279,0.0002466229],"genre_scores_gemma":[0.073474936,0.0000017545336,0.9259185,0.00040169357,0.000120274264,0.000009134959,0.0000048611455,0.000007937007,0.000060862963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992542,0.00004495902,0.0002699784,0.00009060388,0.000105860054,0.00023438624],"domain_scores_gemma":[0.9983803,0.00032556368,0.00020431032,0.00012989799,0.0005582526,0.00040166188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019508053,0.00008233853,0.00014109511,0.00010779515,0.00023926227,0.00028286703,0.00028250142,0.000030158018,0.00003342246],"category_scores_gemma":[0.00030388252,0.000066257635,0.000028328552,0.00012258613,0.000046417972,0.0003249355,0.000005319677,0.00010110485,0.0000020397426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016953371,0.000006537623,0.00007057781,0.000016870797,0.000041660074,0.000029809938,0.0010256312,0.0027605486,0.00040518428,0.907127,0.01572591,0.07278857],"study_design_scores_gemma":[0.0005900599,0.00015326947,0.000110479996,0.000058216832,0.00003728238,0.00009800746,0.000012254498,0.70949686,0.00035266753,0.28798032,0.0009413769,0.00016919582],"about_ca_topic_score_codex":0.0008877389,"about_ca_topic_score_gemma":0.00078768743,"teacher_disagreement_score":0.7067363,"about_ca_system_score_codex":0.0000524853,"about_ca_system_score_gemma":0.0011831778,"threshold_uncertainty_score":0.2727693},"labels":[],"label_agreement":null},{"id":"W1968736717","doi":"10.1049/iet-ipr.2013.0232","title":"Image segmentation by Dirichlet process mixture model with generalised mean","year":2014,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Priority Academic Program Development of Jiangsu Higher Education Institutions; Deutsche Forschungsgemeinschaft","keywords":"Image segmentation; Artificial intelligence; Process (computing); Computer science; Segmentation; Pattern recognition (psychology); Dirichlet process; Mean-shift; Hierarchical Dirichlet process; Mathematics; Computer vision; Latent Dirichlet allocation; Topic model","score_opus":0.009403873022496807,"score_gpt":0.27166012926376565,"score_spread":0.26225625624126886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968736717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041205515,0.00023945166,0.99063057,0.0011833053,0.000049912524,0.00023283508,0.000006861283,0.0003050302,0.0032315098],"genre_scores_gemma":[0.13329759,0.0000061966866,0.86481166,0.0013325973,0.00009070038,0.00004902287,0.000017806979,0.000039792387,0.00035462642],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979354,0.00012781123,0.00027844877,0.0007230958,0.0004698566,0.00046540255],"domain_scores_gemma":[0.998806,0.000028597393,0.000226252,0.0004506181,0.0003192903,0.00016922988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000529925,0.00031691385,0.00027896193,0.00009038717,0.0002951517,0.0008109878,0.0007325056,0.00009651753,0.000004941873],"category_scores_gemma":[0.000027887108,0.0002463042,0.000049836486,0.00047930094,0.00009652586,0.0022655593,0.0000879924,0.00024058612,0.0000072296457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005325492,0.0002171485,0.00006007075,0.0006212223,0.000031156014,0.000017669938,0.0079984125,0.00061254244,0.5724727,0.0016447598,0.007829812,0.40844128],"study_design_scores_gemma":[0.0006496196,0.000057394012,0.0000076102206,0.00007942022,0.000024172892,0.000024417412,0.000029948898,0.8984935,0.084105924,0.015981862,0.00012879388,0.00041732445],"about_ca_topic_score_codex":0.0000061514825,"about_ca_topic_score_gemma":0.0000028462516,"teacher_disagreement_score":0.897881,"about_ca_system_score_codex":0.00003805439,"about_ca_system_score_gemma":0.00013566345,"threshold_uncertainty_score":0.9999989},"labels":[],"label_agreement":null},{"id":"W1969050958","doi":"10.1109/tnnls.2014.2314239","title":"Asymmetric Mixture Model With Simultaneous Feature Selection and Model Detection","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Model selection; Feature selection; Selection (genetic algorithm); Feature (linguistics); Mixture model; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Philosophy","score_opus":0.007324943025058875,"score_gpt":0.21271658364290602,"score_spread":0.20539164061784715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969050958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007709418,0.00032925667,0.99094117,0.00013353779,0.00029904273,0.00024138049,7.900699e-7,0.0002558196,0.00008961734],"genre_scores_gemma":[0.9632911,0.00008279059,0.03545012,0.00011044135,0.00010577333,0.000026580467,5.177611e-7,0.000028087741,0.00090457074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838316,0.00035525477,0.00017517386,0.0005574116,0.00021051128,0.00031850152],"domain_scores_gemma":[0.9991492,0.0002988861,0.000110697896,0.00019792345,0.00008535548,0.00015793454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039163115,0.00026548354,0.00027700604,0.00019645992,0.00066848187,0.00031327116,0.0001335361,0.00024052778,2.0961076e-7],"category_scores_gemma":[0.00000963413,0.00020618063,0.000050647497,0.00053689047,0.0000314403,0.00029608977,0.0000028783545,0.0010536503,4.287598e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000333594,0.000013646958,0.0000043177947,0.000020928306,0.000014540461,0.0000015987075,0.000094435556,0.7954582,0.00017075555,0.00022661332,0.000010620999,0.203951],"study_design_scores_gemma":[0.0003513374,0.00038747364,0.000007183352,0.000046166515,0.000034524255,0.00022310214,0.000007742773,0.998383,0.000093587674,0.000091726964,0.00012064384,0.0002535544],"about_ca_topic_score_codex":0.000032481385,"about_ca_topic_score_gemma":0.000033811997,"teacher_disagreement_score":0.9555817,"about_ca_system_score_codex":0.000028770872,"about_ca_system_score_gemma":0.000012812048,"threshold_uncertainty_score":0.8407802},"labels":[],"label_agreement":null},{"id":"W1969142716","doi":"10.1198/016214508000001075","title":"Order Selection in Finite Mixture Models With a Nonsmooth Penalty","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Selection (genetic algorithm); Applied mathematics; Mathematics; Mathematical optimization; Order (exchange); Model selection; Penalty method; Computer science; Artificial intelligence; Statistics; Economics","score_opus":0.011308483516022382,"score_gpt":0.2514568721316176,"score_spread":0.24014838861559523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969142716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01867895,0.000017723049,0.9787699,0.002089509,0.000076514865,0.000069046306,0.0000050173976,0.000009491732,0.00028386328],"genre_scores_gemma":[0.450462,0.000025985168,0.5487872,0.00053442176,0.000052762727,0.0000016081623,2.3530599e-7,0.0000055829746,0.00013022477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832827,0.00044234234,0.0003279645,0.00013668538,0.00055145286,0.00021326527],"domain_scores_gemma":[0.99802256,0.00059214345,0.00086751697,0.00010958963,0.0003367224,0.0000714549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067639095,0.000101634214,0.00028973477,0.0000944399,0.00010363867,0.00004123403,0.000336762,0.000036630154,0.0000039914958],"category_scores_gemma":[0.0004887182,0.000060643848,0.000054432567,0.00095308607,0.000057324803,0.00033774046,0.000041326686,0.00041957528,0.0000015872123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012879802,0.00192721,0.21817742,0.000059852773,0.00077535305,0.00051396474,0.01055421,0.0686668,0.0023228645,0.34482208,0.05209501,0.29879725],"study_design_scores_gemma":[0.0015381804,0.0009899996,0.3137843,0.00008593863,0.000072942574,0.0004749391,0.00003549651,0.5155862,0.0001958432,0.1661356,0.00070959906,0.00039095824],"about_ca_topic_score_codex":0.00007910571,"about_ca_topic_score_gemma":0.0000470488,"teacher_disagreement_score":0.44691938,"about_ca_system_score_codex":0.00030484993,"about_ca_system_score_gemma":0.0002595698,"threshold_uncertainty_score":0.24729843},"labels":[],"label_agreement":null},{"id":"W1971510992","doi":"10.2307/3315864","title":"Bayesian estimation of cognitive decline in patients with alzheimer's disease","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; Montreal General Hospital","funders":"","keywords":"Gibbs sampling; Bayesian probability; Bayes' theorem; Cognition; Cognitive decline; Econometrics; Estimation; Bayesian hierarchical modeling; Bayesian inference; Statistics; Computer science; Disease; Psychology; Mathematics; Dementia; Medicine; Psychiatry; Economics; Internal medicine","score_opus":0.016600390657204433,"score_gpt":0.23761748787201217,"score_spread":0.22101709721480775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971510992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006927605,0.00023879459,0.9922079,0.00017990648,0.00009646268,0.00008340469,0.00014530332,0.000001673973,0.000118936274],"genre_scores_gemma":[0.6017281,0.000003799075,0.39813036,0.00011566023,0.000009701936,3.9584634e-7,0.0000034865718,0.000004404911,0.0000040994114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99915373,0.00006958025,0.0003178035,0.000093202936,0.00019444214,0.00017122303],"domain_scores_gemma":[0.9986764,0.00013850589,0.00024617306,0.00011255666,0.0003212733,0.00050504215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017082364,0.00008489925,0.0001684631,0.00023535042,0.00003533973,0.00003445098,0.00022948517,0.000025649952,0.000032056458],"category_scores_gemma":[0.00024246245,0.00007260937,0.000020373835,0.00021904797,0.0000653152,0.0002222989,0.000010281082,0.000120034114,0.0000012410219],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063113504,0.00016832598,0.12625676,0.000029052964,0.00008431862,0.0005908498,0.001875638,0.0014635726,2.9672586e-7,0.04653435,0.0015595307,0.8213742],"study_design_scores_gemma":[0.0026682494,0.0007165774,0.6260268,0.00047908732,0.00014630721,0.00001814141,0.000017836966,0.31505477,0.000020620646,0.054427844,0.000113064736,0.00031068103],"about_ca_topic_score_codex":0.00035362178,"about_ca_topic_score_gemma":0.002084496,"teacher_disagreement_score":0.8210635,"about_ca_system_score_codex":0.0000361845,"about_ca_system_score_gemma":0.00034688262,"threshold_uncertainty_score":0.29609242},"labels":[],"label_agreement":null},{"id":"W1971566331","doi":"10.1239/aap/1275055237","title":"Conditionally identically distributed species sampling sequences","year":2010,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Independent and identically distributed random variables; Sequence (biology); Conditional independence; Dirichlet distribution; Poisson sampling; Random variable; Sampling (signal processing); Poisson distribution; Discrete mathematics; Combinatorics; Statistics; Slice sampling; Importance sampling; Mathematical analysis; Computer science","score_opus":0.02020482066945352,"score_gpt":0.29533833964606193,"score_spread":0.2751335189766084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971566331","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018350635,0.000066920096,0.9634666,0.0004305332,0.00042156232,0.0003602118,0.000011564638,0.00014133427,0.016750677],"genre_scores_gemma":[0.45459422,0.000017541966,0.5451503,0.00010555434,0.000046926587,0.00006006707,0.00001031824,0.0000037522555,0.000011317947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981479,0.0000647002,0.0004516772,0.00066981016,0.00030479685,0.00036113718],"domain_scores_gemma":[0.998643,0.00038515564,0.00011851048,0.000673584,0.000075724456,0.000104041515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011890339,0.00018090401,0.0002549461,0.00005593738,0.00011672862,0.00013345579,0.0009177718,0.00010167285,0.00007557486],"category_scores_gemma":[0.00023584263,0.00015998298,0.00005839847,0.0004224205,0.00033474155,0.0005864975,0.00021182813,0.0004388559,0.000026804115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007610334,0.000067165885,0.0012296992,0.000026264606,0.0000026670248,0.0000023317343,0.000064246495,0.0001983085,0.0075815977,0.93635595,0.000004662648,0.054459527],"study_design_scores_gemma":[0.00018683873,0.000014329812,0.012784355,0.000009113551,0.0000023960395,0.0000061040155,0.0000050090616,0.0009485324,0.0028069422,0.97568536,0.007347893,0.00020311934],"about_ca_topic_score_codex":0.000004392969,"about_ca_topic_score_gemma":0.00015693805,"teacher_disagreement_score":0.43624356,"about_ca_system_score_codex":0.00004965084,"about_ca_system_score_gemma":0.00009711722,"threshold_uncertainty_score":0.6523917},"labels":[],"label_agreement":null},{"id":"W1971991994","doi":"10.1080/15326349.2010.498318","title":"Count Data Time Series Models Based on Expectation Thinning","year":2010,"lang":"en","type":"article","venue":"Stochastic Models","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University","funders":"","keywords":"Mathematics; Series (stratigraphy); Random variable; Marginal distribution; Markov chain; Applied mathematics; Poisson distribution; Markov process; Statistics; Count data; Econometrics","score_opus":0.036633379781186685,"score_gpt":0.27559814708221125,"score_spread":0.23896476730102456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971991994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029275715,0.000025293079,0.9912713,0.0008907965,0.00056301244,0.00030306473,0.000040598377,0.00030975693,0.006303375],"genre_scores_gemma":[0.35688466,7.014108e-7,0.64210963,0.00052237464,0.0001326313,0.0000306954,0.0000390605,0.000025447238,0.0002547956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976979,0.00009431717,0.00031433636,0.0008930318,0.0005801072,0.000420331],"domain_scores_gemma":[0.9969736,0.00023316052,0.00013375295,0.0023482637,0.00013770063,0.00017357711],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086927286,0.00028370478,0.00028411832,0.00016180966,0.00023187367,0.0002470322,0.0018592752,0.0001504102,0.000034609115],"category_scores_gemma":[0.00009028204,0.00025395575,0.000058232104,0.00025149697,0.00007608034,0.0022297786,0.0003814846,0.00043591188,0.00004781396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003347993,0.00006958889,1.7931336e-7,0.000011573894,0.000012406779,0.00000997863,0.0011083502,0.4065295,0.0016138894,0.5751484,0.00094814744,0.014514489],"study_design_scores_gemma":[0.00021866744,0.00005680446,0.0000015859068,0.00002675506,0.00000906338,0.000009973047,0.000005000126,0.71004975,0.00010061761,0.28928012,0.000027340422,0.00021431352],"about_ca_topic_score_codex":0.000021871658,"about_ca_topic_score_gemma":0.0000074270065,"teacher_disagreement_score":0.3565919,"about_ca_system_score_codex":0.000027785114,"about_ca_system_score_gemma":0.00021358606,"threshold_uncertainty_score":0.99999124},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.028684516531176187,"score_gpt":0.269387716125938,"score_spread":0.2407031995947618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972168313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011698052,0.0004392366,0.9953478,0.0007658804,0.00060748286,0.0012370533,0.0001278654,0.00021792417,0.00008694469],"genre_scores_gemma":[0.7443218,0.00004102263,0.25482944,0.00010377452,0.000046574423,0.00046216173,0.0000025884435,0.000020171223,0.00017246188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871176,0.000044187607,0.00031131625,0.0004187676,0.00010410315,0.00040987175],"domain_scores_gemma":[0.9992036,0.00012690919,0.00012204045,0.00031150522,0.000106092404,0.00012985324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004301707,0.00021482345,0.00031918113,0.00030641252,0.00032971482,0.000115399904,0.00020428842,0.00027366178,0.0000010327549],"category_scores_gemma":[0.000010085098,0.00019167496,0.00007265637,0.00018840299,0.00012741622,0.00043048375,0.0000032413561,0.0001637546,8.2414147e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028893333,0.00020633727,0.000019204752,0.00048863824,0.00014412976,0.0000025935562,0.0016245173,0.0036254195,0.051528104,0.22578065,0.00027008954,0.7162814],"study_design_scores_gemma":[0.0014749438,0.00031730256,0.0000072316675,0.00007859789,0.00007935756,0.00024325706,0.0001597875,0.97360986,0.013050222,0.010306577,0.00029714245,0.000375695],"about_ca_topic_score_codex":0.0000118580065,"about_ca_topic_score_gemma":0.000018157534,"teacher_disagreement_score":0.9699845,"about_ca_system_score_codex":0.000035677473,"about_ca_system_score_gemma":0.000048198173,"threshold_uncertainty_score":0.78162783},"labels":[],"label_agreement":null},{"id":"W1972256887","doi":"10.1007/s11634-015-0204-z","title":"A mixture of generalized hyperbolic factor analyzers","year":2015,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bayesian information criterion; Mixture model; Hyperbolic function; Cluster analysis; Gaussian; Generalized inverse Gaussian distribution; Maximization; Expectation–maximization algorithm","score_opus":0.07739344212886445,"score_gpt":0.3564501671026479,"score_spread":0.2790567249737834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972256887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008989325,0.0039608357,0.98609734,0.0003752435,0.00004653846,0.000056352896,0.00003531373,0.000015562595,0.00042346262],"genre_scores_gemma":[0.60154766,0.0017747646,0.39643666,0.00005811729,0.000018401619,0.0000051847487,0.00011590888,0.0000030851593,0.000040228028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987878,0.00014602394,0.00029043874,0.0004636405,0.00019386546,0.000118217315],"domain_scores_gemma":[0.998415,0.000049293423,0.00017915595,0.001200237,0.00007483184,0.00008146173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048405345,0.00009474266,0.0002884489,0.00027879633,0.000023069702,0.000044475135,0.0008043842,0.000051528183,0.000004355059],"category_scores_gemma":[0.000089904424,0.000076306715,0.000043481712,0.0014825902,0.0000493172,0.0010726303,0.00017648064,0.00006699639,0.0000010191947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020045409,0.0001193326,0.03336242,0.000025063682,0.00022664363,0.000002564549,0.00075504015,0.0001962555,0.0041511143,0.1305437,0.00029860623,0.8302992],"study_design_scores_gemma":[0.0006195405,0.000033186967,0.048735432,0.000014203179,0.0002868312,0.000002379482,0.00009954814,0.8969435,0.00079197675,0.031946734,0.0202366,0.0002900598],"about_ca_topic_score_codex":0.00004005454,"about_ca_topic_score_gemma":0.00023359168,"teacher_disagreement_score":0.89674723,"about_ca_system_score_codex":0.000016646138,"about_ca_system_score_gemma":0.000036221456,"threshold_uncertainty_score":0.31116974},"labels":[],"label_agreement":null},{"id":"W1972308890","doi":"10.2307/3316001","title":"Consistent maximum likelihood estimation of a unimodal density using shape restrictions","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Hellinger distance; Almost everywhere; Maximum likelihood; Interval (graph theory); Mathematics; Convergence (economics); Mode (computer interface); Metric (unit); Rate of convergence; Maximum likelihood sequence estimation; Applied mathematics; Statistics; Mathematical optimization; Computer science; Combinatorics; Mathematical analysis; Engineering","score_opus":0.02911830506623323,"score_gpt":0.25804786181537204,"score_spread":0.2289295567491388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972308890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024278719,0.00010840689,0.9747002,0.00032358617,0.00039099285,0.000053782485,0.000054454547,0.000003895497,0.00008594146],"genre_scores_gemma":[0.40295047,0.0000059467534,0.59695154,0.000062216226,0.000023274048,1.2053566e-7,7.3625455e-7,0.0000038150906,0.0000018881256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907726,0.00005832424,0.00038712847,0.00009733383,0.00017161427,0.00020833123],"domain_scores_gemma":[0.9985831,0.00006552452,0.0003071201,0.00017384526,0.00043139476,0.00043901528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030491877,0.000085771855,0.00018944849,0.0002615008,0.00012959496,0.00006426918,0.0002618369,0.000052756688,0.000007164526],"category_scores_gemma":[0.00019523135,0.000085206455,0.00004955169,0.00027369722,0.000079576435,0.00018850292,0.000015883039,0.00017035734,0.0000011182738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009304106,0.000056020588,0.0006138006,0.000052762738,0.00008632859,0.0008480906,0.0015386889,0.017541235,0.0005730884,0.72324103,0.00075212744,0.2546875],"study_design_scores_gemma":[0.0006841849,0.0002491583,0.0056990194,0.00016336323,0.00009078647,0.0010771239,0.000044763714,0.19301276,0.0006159055,0.79801404,0.00015322528,0.00019563876],"about_ca_topic_score_codex":0.0032759649,"about_ca_topic_score_gemma":0.003527547,"teacher_disagreement_score":0.37867174,"about_ca_system_score_codex":0.00023048968,"about_ca_system_score_gemma":0.0030459377,"threshold_uncertainty_score":0.5403363},"labels":[],"label_agreement":null},{"id":"W1972820371","doi":"10.1002/cjs.11188","title":"A Bayesian nonparametric goodness of fit test for right censored data based on approximate samples from the beta‐Stacy process","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Goodness of fit; Bayesian probability; Dirichlet process; Generalization; Mathematics; Statistical hypothesis testing; Statistics; Econometrics; Computer science","score_opus":0.050568273748549164,"score_gpt":0.2857671253607677,"score_spread":0.23519885161221854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972820371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004463634,0.00014290382,0.991527,0.0016732479,0.00027667146,0.00036266938,0.005466429,0.0000055880214,0.00009908221],"genre_scores_gemma":[0.22851993,0.0000057242864,0.7707149,0.0005612335,0.000104879575,0.0000073558203,0.00005246796,0.00001673287,0.000016781483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835944,0.00011414865,0.00055824657,0.00028128928,0.00030537226,0.00038148326],"domain_scores_gemma":[0.99474037,0.0026802765,0.0005411143,0.00089814607,0.00063823536,0.00050188537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006541454,0.00018405143,0.00036821567,0.00023993655,0.00018249388,0.00028176815,0.0023390406,0.00007214647,0.000063554275],"category_scores_gemma":[0.0012615382,0.00012519768,0.000057376157,0.00048410223,0.0001284052,0.00035367513,0.000038307426,0.0002339094,0.0000021009744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008292313,0.000499708,0.011143094,0.000626266,0.0004045994,0.00029243872,0.0036783793,0.002293083,0.00020653858,0.19902185,0.2220007,0.55975044],"study_design_scores_gemma":[0.001028996,0.00039823228,0.0064980113,0.00022147362,0.00011604892,0.000023947974,0.000074494754,0.8004866,0.0004973338,0.18731946,0.002997424,0.00033794955],"about_ca_topic_score_codex":0.002836157,"about_ca_topic_score_gemma":0.0029092827,"teacher_disagreement_score":0.7981936,"about_ca_system_score_codex":0.000057596415,"about_ca_system_score_gemma":0.0015149023,"threshold_uncertainty_score":0.5105413},"labels":[],"label_agreement":null},{"id":"W1973247608","doi":"10.1007/s11634-013-0137-3","title":"Dimension reduction for model-based clustering via mixtures of multivariate $$t$$ t -distributions","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Dimensionality reduction; Cluster analysis; Subspace topology; Dimension (graph theory); Mixture model; Mathematics; Gaussian; Reduction (mathematics); Clustering high-dimensional data; Eigenvalues and eigenvectors; Data set; Curse of dimensionality; Algorithm; Multivariate normal distribution; Pattern recognition (psychology); Computer science; Multivariate statistics; Artificial intelligence; Statistics; Combinatorics; Physics","score_opus":0.03849028777574721,"score_gpt":0.3380154403337114,"score_spread":0.2995251525579642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973247608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001310196,0.00045195065,0.9974397,0.00044516756,0.00004855571,0.0002128719,0.00004230647,0.000018016099,0.00003124081],"genre_scores_gemma":[0.50217193,0.00010306591,0.49740967,0.000010757864,0.000007613687,0.000035318735,0.0002510174,0.000002117553,0.000008512945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989614,0.0000682758,0.00030464196,0.00044697543,0.000099270845,0.00011944423],"domain_scores_gemma":[0.9987509,0.00007901612,0.00019400138,0.0008256358,0.00011318229,0.0000372279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039299013,0.00008847016,0.00019426848,0.00018487254,0.00007938409,0.000046402023,0.00039363545,0.000051725572,0.0000017490958],"category_scores_gemma":[0.00005340814,0.00007643862,0.00004671946,0.00060276315,0.000043241627,0.0011841133,0.00010511453,0.00005166911,3.853091e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001957239,0.00016164737,0.00034233966,0.000071598944,0.000085511136,1.1038232e-7,0.00013441619,0.027865699,0.14029361,0.057654537,0.00008578561,0.77328515],"study_design_scores_gemma":[0.00016801308,0.000012324081,0.0019260794,0.0000119795795,0.000085270585,3.3256154e-7,0.0000065443855,0.97031564,0.0026640743,0.024588391,0.00013763095,0.00008374889],"about_ca_topic_score_codex":0.00004708462,"about_ca_topic_score_gemma":0.000056392622,"teacher_disagreement_score":0.9424499,"about_ca_system_score_codex":0.00001983124,"about_ca_system_score_gemma":0.000018191946,"threshold_uncertainty_score":0.31170765},"labels":[],"label_agreement":null},{"id":"W1973599906","doi":"10.1109/tnnls.2012.2228227","title":"Incorporating Mean Template Into Finite Mixture Model for Image Segmentation","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Pixel; Robustness (evolution); Computer science; Noise (video); Pattern recognition (psychology); Segmentation; Artificial intelligence; Conditional probability; Mathematics; Image segmentation; Conditional expectation; Algorithm; Image (mathematics); Statistics","score_opus":0.016858372270754103,"score_gpt":0.2537153513031255,"score_spread":0.2368569790323714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973599906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003777198,0.00013022826,0.9943224,0.00026699004,0.0006465153,0.00063656655,0.0000018055839,0.00017654688,0.000041712894],"genre_scores_gemma":[0.78820914,0.000015510757,0.21074267,0.00013909565,0.00009581605,0.00018227079,0.0000028816794,0.000021088645,0.0005915401],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855113,0.00028206815,0.00032197675,0.00042144387,0.0001461653,0.0002771951],"domain_scores_gemma":[0.9990546,0.00032877835,0.00017122636,0.0002146272,0.00010535457,0.00012538645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045095183,0.00021223201,0.00023602424,0.00009857324,0.0006679341,0.00049601495,0.00019627911,0.00013012504,0.0000021698609],"category_scores_gemma":[0.0000057400975,0.0001814075,0.00008793959,0.00019993297,0.000033918117,0.0006857336,0.0000035790886,0.00049531716,0.0000031090801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007896047,0.000014039627,0.0000039535234,0.0000435838,0.000016162443,0.0000012930692,0.0008154363,0.9064125,0.001396009,0.00040393864,0.00010376114,0.09078145],"study_design_scores_gemma":[0.0003163509,0.00014106279,0.000004267566,0.00005717786,0.000014884513,0.000016547163,0.000065726184,0.99816936,0.00015059774,0.0008303771,0.000028875653,0.0002047419],"about_ca_topic_score_codex":0.00012707573,"about_ca_topic_score_gemma":0.000014208583,"teacher_disagreement_score":0.78443193,"about_ca_system_score_codex":0.000024939189,"about_ca_system_score_gemma":0.000014227931,"threshold_uncertainty_score":0.7397583},"labels":[],"label_agreement":null},{"id":"W1974965884","doi":"10.1007/s00362-015-0665-3","title":"Testing homogeneity in a scale mixture of normal distributions","year":2015,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta","funders":"","keywords":"Homogeneity (statistics); Mathematics; Normal distribution; Statistics; Statistical physics; Physics","score_opus":0.03019725257155906,"score_gpt":0.2887532781627109,"score_spread":0.2585560255911518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974965884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00424096,0.000041170806,0.9763971,0.0002034519,0.000095842704,0.00007197438,0.000093877235,0.00003001095,0.01882563],"genre_scores_gemma":[0.44856715,4.3307878e-7,0.5513472,0.00004269111,0.000013285071,0.0000037136815,0.0000051084066,0.0000024296737,0.000017977633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902076,0.00012195427,0.00020874955,0.00022131397,0.00018997958,0.00023723683],"domain_scores_gemma":[0.9991695,0.0002869839,0.000041303938,0.00023337608,0.00008335155,0.00018548232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040611046,0.00008716273,0.00016328157,0.00003779549,0.000033974247,0.000021481974,0.00027832107,0.000054230906,0.000009008495],"category_scores_gemma":[0.0006693351,0.000075951604,0.000023850185,0.00038713668,0.00010179304,0.00009747675,0.000107960914,0.00013875292,0.000005587595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013738152,0.0001452739,0.008716733,0.000028702641,0.000007806752,0.000050170656,0.0004592945,0.0000377191,0.004253337,0.7811781,0.0009620108,0.20414712],"study_design_scores_gemma":[0.0022293953,0.00061838556,0.32806617,0.00013121805,0.000041917585,0.000096040305,0.00009507238,0.08084495,0.003956009,0.57962024,0.0034020424,0.000898559],"about_ca_topic_score_codex":0.00010347196,"about_ca_topic_score_gemma":0.00004812167,"teacher_disagreement_score":0.4443262,"about_ca_system_score_codex":0.00003672051,"about_ca_system_score_gemma":0.00012889488,"threshold_uncertainty_score":0.30972168},"labels":[],"label_agreement":null},{"id":"W1975698992","doi":"10.1016/j.csda.2006.08.029","title":"k-Sample tests based on the likelihood ratio","year":2006,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Sample (material); Sample size determination; Anderson–Darling test; Statistical hypothesis testing; Likelihood-ratio test; Kolmogorov–Smirnov test; Physics","score_opus":0.030429337236413105,"score_gpt":0.2991661943393945,"score_spread":0.2687368571029814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975698992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002991475,0.000028481747,0.99441034,0.0017630862,0.00006753245,0.00010627061,0.0031720754,0.000059436225,0.00036288798],"genre_scores_gemma":[0.12155051,0.0000014763925,0.8723438,0.0012012892,0.0000794322,0.000008746065,0.0047692736,0.0000081450125,0.000037351496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979269,0.00026604978,0.00034849206,0.000601265,0.00061400863,0.00024327352],"domain_scores_gemma":[0.99473536,0.003413644,0.0001646847,0.0013948535,0.0002181993,0.00007325631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007926304,0.00017167444,0.00022794491,0.0002138109,0.0003165416,0.0003993203,0.0014368391,0.000037977017,0.00009329046],"category_scores_gemma":[0.00034287688,0.00012749324,0.00007861689,0.0013865537,0.00006118184,0.00020936552,0.00026807873,0.00013402327,0.000039993705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024444764,0.00009332624,0.0007530642,0.000003377307,0.00012606451,0.000007910588,0.000013619432,0.14707834,0.000003352798,0.80690587,0.02765089,0.017361742],"study_design_scores_gemma":[0.00008518413,0.000014133175,0.014642173,0.0000022834952,0.0001471731,4.441981e-7,4.793978e-7,0.661788,0.0000033798065,0.32235983,0.00085036625,0.000106533604],"about_ca_topic_score_codex":0.00062891544,"about_ca_topic_score_gemma":0.00023192773,"teacher_disagreement_score":0.5147097,"about_ca_system_score_codex":0.000034196335,"about_ca_system_score_gemma":0.00016588188,"threshold_uncertainty_score":0.51990235},"labels":[],"label_agreement":null},{"id":"W1975851557","doi":"10.1002/sim.3470","title":"Modeling conditional dependence between diagnostic tests: A multiple latent variable model","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; Centers for Disease Control and Prevention","keywords":"Latent class model; Latent variable; Latent variable model; Covariate; Conditional dependence; Statistics; Bayesian probability; Computer science; Econometrics; Measure (data warehouse); Mathematics; Data mining","score_opus":0.054047281841197406,"score_gpt":0.31789441846119393,"score_spread":0.26384713661999654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975851557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016784483,0.00020530914,0.99672854,0.0003473532,0.00016769154,0.00019837769,0.00012517745,0.00006331517,0.00048579142],"genre_scores_gemma":[0.4019658,0.00009712536,0.59740645,0.00028624135,0.00009697081,0.000020594742,0.00004481872,0.000009206798,0.000072819355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805534,0.00010285266,0.00047824025,0.0004488349,0.00053447235,0.00038029044],"domain_scores_gemma":[0.99711996,0.0020578445,0.00007466627,0.000403451,0.00016707146,0.00017703002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070989266,0.00018946349,0.00036173064,0.00015820307,0.00014754065,0.00001570284,0.0005456737,0.0000874855,0.00002422888],"category_scores_gemma":[0.0023519725,0.0001651348,0.000018592753,0.00033201376,0.00013941895,0.00019840407,0.00013770655,0.00034844727,0.000010779924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007645884,0.000099272664,0.008652434,0.00005469252,0.00002623322,0.0003839998,0.0014784592,0.21359563,0.00024145,0.76576984,0.0027113755,0.0069789505],"study_design_scores_gemma":[0.00051433704,0.00004497738,0.0010504922,0.00006760059,0.000009116437,0.00002625674,0.0000032225012,0.62390816,0.000010987757,0.37423626,0.000012224818,0.000116367235],"about_ca_topic_score_codex":0.00021187204,"about_ca_topic_score_gemma":0.00002770581,"teacher_disagreement_score":0.41031253,"about_ca_system_score_codex":0.00007806957,"about_ca_system_score_gemma":0.00020184486,"threshold_uncertainty_score":0.67340016},"labels":[],"label_agreement":null},{"id":"W1976442863","doi":"10.1007/s11222-012-9364-2","title":"Orthogonal Stiefel manifold optimization for eigen-decomposed covariance parameter estimation in mixture models","year":2012,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Stiefel manifold; Covariance; Benchmark (surveying); Cluster analysis; Algorithm; Mathematics; Manifold (fluid mechanics); Computer science; Estimation of covariance matrices; Current (fluid); Covariance matrix; Applied mathematics; Mathematical optimization; Artificial intelligence; Statistics","score_opus":0.024657797309291143,"score_gpt":0.28607147035415204,"score_spread":0.2614136730448609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976442863","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009969004,0.00024092304,0.997892,0.00006808094,0.00030525267,0.00028304564,0.00003765257,0.000042403244,0.00013371448],"genre_scores_gemma":[0.30889747,0.000010341321,0.69081604,0.00017156423,0.00005135717,0.0000072906196,0.000024377397,0.000009652066,0.000011896859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988128,0.00008519825,0.0003069931,0.00029432133,0.00013897732,0.00036170278],"domain_scores_gemma":[0.99906313,0.00043937258,0.00013515296,0.00018135628,0.000080562524,0.00010044923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006213306,0.0001557118,0.00020105828,0.000081411934,0.00014318516,0.0001402092,0.00018489323,0.000079470774,0.000002216204],"category_scores_gemma":[0.00006664147,0.00015344923,0.000025781315,0.00015494927,0.000017450388,0.00036616987,0.00009750746,0.00012156802,6.310782e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070207448,0.000036101228,0.00008213576,0.00003942887,0.0000075395074,0.0000017611723,0.00051260815,0.118615575,0.000015098713,0.71605045,0.000087921166,0.16454437],"study_design_scores_gemma":[0.0003379146,0.000030433855,0.00050211826,0.000030316416,0.000007679019,0.000010805246,0.000004639815,0.84059095,0.00002011031,0.15827498,0.000029651514,0.00016040607],"about_ca_topic_score_codex":0.000008674611,"about_ca_topic_score_gemma":0.0000025201784,"teacher_disagreement_score":0.7219754,"about_ca_system_score_codex":0.000026063142,"about_ca_system_score_gemma":0.00003165996,"threshold_uncertainty_score":0.6257478},"labels":[],"label_agreement":null},{"id":"W1976595094","doi":"10.1007/s11117-010-0107-3","title":"Uniform estimates for order statistics and Orlicz functions","year":2010,"lang":"en","type":"article","venue":"Positivity","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Combinatorics; Random variable; Order (exchange); Independent and identically distributed random variables; Mathematics; Order statistic; Multivariate random variable; Sequence (biology); Statistics","score_opus":0.012172578449917489,"score_gpt":0.2819368948787755,"score_spread":0.269764316428858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976595094","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027859353,0.00001669645,0.9947848,0.0006837461,0.00031373923,0.00013181062,0.000065171276,0.00006607551,0.001152032],"genre_scores_gemma":[0.09484169,0.0000018164542,0.90469,0.00015220803,0.000044924247,0.000016274227,0.000005731348,0.000005278999,0.00024205077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995022,0.000017002802,0.00007153392,0.00019350855,0.00005938348,0.00015641472],"domain_scores_gemma":[0.9992637,0.00031636778,0.000028606748,0.000217272,0.00009748675,0.00007653721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026559795,0.00007796831,0.000093359806,0.00002963061,0.00016580075,0.0001057311,0.00012103623,0.0000457018,0.0000058222054],"category_scores_gemma":[0.000110857836,0.00006711197,0.000016011854,0.000093617055,0.00004441229,0.00020599306,0.00007305683,0.00011054657,0.000004005376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003469129,0.00003556011,0.00037102116,0.000014025075,0.000009264072,0.0000016948095,0.00009754249,0.00000146357,0.0057912567,0.67293954,0.00082378805,0.31991136],"study_design_scores_gemma":[0.00048844237,0.0001473268,0.017339226,0.000008555146,0.000039012197,0.00006953683,0.000003216043,0.3699362,0.0066506914,0.598586,0.006409771,0.00032197838],"about_ca_topic_score_codex":0.000031190535,"about_ca_topic_score_gemma":0.00010439402,"teacher_disagreement_score":0.36993474,"about_ca_system_score_codex":0.0000048570014,"about_ca_system_score_gemma":0.000036989364,"threshold_uncertainty_score":0.27367467},"labels":[],"label_agreement":null},{"id":"W1977941684","doi":"10.1007/s11009-012-9309-4","title":"On the Use of Bivariate Mellin Transform in Bivariate Random Scaling and Some Applications","year":2012,"lang":"en","type":"article","venue":"Methodology And Computing In Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bivariate analysis; Mathematics; Scaling; Mellin transform; Inverse; Bivariate data; Applied mathematics; Statistics; Fourier transform; Mathematical analysis; Geometry","score_opus":0.1523205192452904,"score_gpt":0.31574046430302605,"score_spread":0.16341994505773566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977941684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14003475,0.000213211,0.85814023,0.00053510827,0.00006883155,0.00082091574,0.0000012617418,0.00002914849,0.00015652183],"genre_scores_gemma":[0.4716324,0.000019714575,0.52806634,0.00021088604,0.000018786954,0.00004620983,3.8135036e-7,0.0000041160497,0.0000011761805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967108,0.0018392621,0.0005230115,0.0004592524,0.000099651355,0.00036807024],"domain_scores_gemma":[0.99171853,0.007603693,0.00013859676,0.00045111228,0.000019836492,0.00006822736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011836109,0.00017517238,0.00045644311,0.00012582062,0.00012173608,0.000033735472,0.00030138573,0.00016675485,0.0000016704363],"category_scores_gemma":[0.0002325965,0.00012539815,0.000041957937,0.0003927733,0.0002177245,0.00012700217,0.00017176593,0.00040305994,6.081487e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008402215,0.0001021607,0.00089176017,0.000048833746,0.000008912479,1.8526522e-7,0.0019302227,0.00066623447,0.0005302088,0.8300702,9.637299e-7,0.1656663],"study_design_scores_gemma":[0.00088466296,0.000024374129,0.009242633,0.000025847577,0.0000104343535,0.0000050077965,0.000011921629,0.056492798,0.0016847156,0.93137586,0.0000897229,0.00015202163],"about_ca_topic_score_codex":0.000061716055,"about_ca_topic_score_gemma":0.0000080212085,"teacher_disagreement_score":0.33159763,"about_ca_system_score_codex":0.000021261785,"about_ca_system_score_gemma":0.000025601872,"threshold_uncertainty_score":0.5113588},"labels":[],"label_agreement":null},{"id":"W1977958687","doi":"10.1007/s13171-013-0049-5","title":"On Generalized Wishart Distributions - II: Sphericity Test","year":2014,"lang":"en","type":"article","venue":"Sankhya A","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sphericity; Wishart distribution; Mathematics; Test (biology); Statistics; Geometry; Geology; Multivariate statistics","score_opus":0.011592760188292016,"score_gpt":0.25043433757392536,"score_spread":0.23884157738563333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977958687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007891767,0.000030056977,0.9740183,0.0013018274,0.00028196984,0.0000932573,0.000014548754,0.00017830852,0.016189996],"genre_scores_gemma":[0.4956399,0.000003783076,0.50188035,0.0014614221,0.00013832495,0.000017474593,0.0000076119504,0.000007779424,0.0008433502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895185,0.00011457991,0.00014818463,0.000344201,0.00016937341,0.0002718339],"domain_scores_gemma":[0.9989799,0.00017633288,0.000051933013,0.0006312797,0.000038949063,0.000121568926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032288593,0.0001315097,0.00016220138,0.000024713434,0.00025626714,0.000085538304,0.0005286942,0.00006253579,0.00008209051],"category_scores_gemma":[0.00022206786,0.00010890061,0.00008404824,0.00026416738,0.000038494803,0.0001490771,0.00017356963,0.00012985956,0.00008370179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023734392,0.00012160672,0.00013645052,0.000003659395,0.0000061328324,0.0000027652475,0.00008018993,0.000010309437,0.0019204286,0.91956174,0.019489143,0.058665168],"study_design_scores_gemma":[0.0008661165,0.00047589996,0.0051688254,0.000037100595,0.00001609719,0.000019391364,0.0000012885555,0.089694224,0.0071868147,0.75445354,0.14156854,0.0005121426],"about_ca_topic_score_codex":0.000023833889,"about_ca_topic_score_gemma":0.0000061867563,"teacher_disagreement_score":0.48774815,"about_ca_system_score_codex":0.000027855102,"about_ca_system_score_gemma":0.000030880256,"threshold_uncertainty_score":0.44408378},"labels":[],"label_agreement":null},{"id":"W1978142681","doi":"10.2307/3315937","title":"Asymptotic normality of the posterior given a statistic","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Asymptotic distribution; Statistic; Central limit theorem; Applied mathematics; Gaussian; Statistics; Multivariate normal distribution; Normality; Prior probability; Local asymptotic normality; Ancillary statistic; Multivariate statistics; Test statistic; Estimator; Statistical hypothesis testing; Bayesian probability","score_opus":0.014270709322339958,"score_gpt":0.2280901486823998,"score_spread":0.21381943936005984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978142681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057952623,0.00013006384,0.9919001,0.0010134211,0.00062051514,0.00007000727,0.0002306647,0.0000022753532,0.00023772102],"genre_scores_gemma":[0.4751358,0.0000029078017,0.5245354,0.00025902825,0.000029089506,2.7614936e-7,4.3207186e-7,0.000004943169,0.00003212771],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989033,0.00011394468,0.00042502806,0.00009515172,0.00022118543,0.00024142757],"domain_scores_gemma":[0.99850607,0.000110050336,0.000362809,0.00030337757,0.00033690856,0.00038077077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004237248,0.000097174234,0.00021129398,0.00010587966,0.00010347156,0.00006822228,0.00080620573,0.000040231833,0.00001857529],"category_scores_gemma":[0.00029680805,0.0000704383,0.000062206,0.00021772733,0.00014057691,0.00015142086,0.000033973058,0.00020148157,0.0000025996078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007875828,0.000029567913,0.002204891,0.000083713065,0.00006812556,0.00045043518,0.0030398336,0.00044571605,0.00029228532,0.9045575,0.0024767495,0.08634329],"study_design_scores_gemma":[0.0012581544,0.00050863915,0.1230866,0.00032490861,0.00010008341,0.0013271763,0.000055917622,0.0013998364,0.0011787467,0.8681565,0.0022616608,0.00034175802],"about_ca_topic_score_codex":0.0020374286,"about_ca_topic_score_gemma":0.006261671,"teacher_disagreement_score":0.46934053,"about_ca_system_score_codex":0.00013887658,"about_ca_system_score_gemma":0.0025077597,"threshold_uncertainty_score":0.4448658},"labels":[],"label_agreement":null},{"id":"W1978625515","doi":"10.1155/2012/463506","title":"Joint Models and Their Applications","year":2012,"lang":"en","type":"article","venue":"Journal of Probability and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Joint (building); Mathematics; Computer science; Engineering; Architectural engineering","score_opus":0.05573200771154548,"score_gpt":0.27770803301053903,"score_spread":0.22197602529899355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978625515","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077545457,0.0011081136,0.99740463,0.00032491641,0.00006649831,0.00009669141,0.000014036957,0.00000580392,0.00020384647],"genre_scores_gemma":[0.14334892,0.00011404828,0.8563793,0.00008181659,0.000059377766,0.0000025535242,2.017967e-7,0.0000022078711,0.000011596734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993542,0.00009086185,0.00025852412,0.00008427403,0.00008614715,0.00012602982],"domain_scores_gemma":[0.9992797,0.00014013007,0.00014341822,0.00014961015,0.00012868797,0.00015848901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001058111,0.00006953597,0.00015994401,0.00003253146,0.00007050566,0.0000542709,0.00011610242,0.000034583183,0.0000015693379],"category_scores_gemma":[0.00004967569,0.00004704696,0.000022139071,0.00005666126,0.000067522225,0.00039510347,0.000068611494,0.0001326104,2.681635e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001838273,0.000045501652,0.0000875691,0.000028354052,0.0000068491063,3.2939408e-7,0.0008222744,0.000006014364,0.000062082785,0.8186564,0.000116753625,0.18016605],"study_design_scores_gemma":[0.000100789024,0.00005241856,0.00083634653,0.0000075618495,0.000007849611,0.00009661497,0.000014001556,0.022955723,0.00007547516,0.97490585,0.0008901875,0.000057211448],"about_ca_topic_score_codex":0.0000015180957,"about_ca_topic_score_gemma":8.8622375e-7,"teacher_disagreement_score":0.18010885,"about_ca_system_score_codex":0.000013494963,"about_ca_system_score_gemma":0.00003795677,"threshold_uncertainty_score":0.19185194},"labels":[],"label_agreement":null},{"id":"W1979743121","doi":"10.2202/1948-4690.1011","title":"Using HIV Diagnostic Data to Estimate HIV Incidence: Method and Simulation","year":2011,"lang":"en","type":"article","venue":"Statistical Communications in Infectious Diseases","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Human immunodeficiency virus (HIV); Incidence (geometry); Distribution (mathematics); Virology; Medicine; Immunology; Biology; Statistics; Mathematics","score_opus":0.15154080077463397,"score_gpt":0.4562201761001769,"score_spread":0.3046793753255429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979743121","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008682785,0.00029361568,0.9970064,0.00016971614,0.000058959104,0.00031343717,0.00021422321,0.00012216234,0.0009531646],"genre_scores_gemma":[0.43433574,0.00002916828,0.5654356,0.00011818489,0.000007886709,0.000026210288,0.000036091475,0.000007762284,0.000003392396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811095,0.00070527464,0.00033677346,0.0004539278,0.00015311922,0.000239981],"domain_scores_gemma":[0.9921981,0.0047647334,0.00007728371,0.002638578,0.00009728833,0.00022398152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056588865,0.00015224419,0.00021353638,0.00018150324,0.00026248992,0.00012868286,0.0014943291,0.000051027524,0.000020072399],"category_scores_gemma":[0.0042986255,0.00015348919,0.00001712861,0.0004779091,0.00014570347,0.000558007,0.0021464673,0.00018718686,0.000015564332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001166236,0.00044299522,0.06523273,0.000044150755,0.000023773611,0.000015854643,0.0011481093,0.004887877,0.000018864366,0.7985253,0.0002136739,0.12943505],"study_design_scores_gemma":[0.00015085863,0.000026878068,0.03942321,0.000045353827,0.000037063102,0.000009973448,0.000006156862,0.7292465,0.0000030704773,0.23077382,0.00011968669,0.0001574331],"about_ca_topic_score_codex":0.00022901538,"about_ca_topic_score_gemma":0.00014765309,"teacher_disagreement_score":0.7243586,"about_ca_system_score_codex":0.000059523827,"about_ca_system_score_gemma":0.00009953172,"threshold_uncertainty_score":0.62591076},"labels":[],"label_agreement":null},{"id":"W1980323687","doi":"10.1109/icip.2012.6466848","title":"A robust non-symmetric mixture models for image segmentation","year":2012,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Robustness (evolution); Mixture model; Expectation–maximization algorithm; Gaussian; Computer science; Image segmentation; Segmentation; Pattern recognition (psychology); Artificial intelligence; Student's t-distribution; Data modeling; Maximization; Algorithm; Mathematical optimization; Maximum likelihood; Mathematics; Statistics","score_opus":0.04186118232032529,"score_gpt":0.28495194987346656,"score_spread":0.24309076755314127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980323687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015848744,0.00019347382,0.98261344,0.00052260864,0.0004103165,0.00039337354,0.00000333692,0.00010704454,0.015597926],"genre_scores_gemma":[0.060308743,0.000010667682,0.9374918,0.00077425677,0.00018243765,0.00007128985,0.0000044419435,0.000012092154,0.0011443056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989628,0.000045077617,0.0001691328,0.000262864,0.0001639539,0.00039617138],"domain_scores_gemma":[0.9992236,0.00010514129,0.000060448336,0.00035715933,0.00010235687,0.00015133286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059037155,0.0001363672,0.00014534815,0.00015437315,0.0000964345,0.00011705632,0.00039210904,0.0000802052,0.000013282507],"category_scores_gemma":[0.000022448176,0.0001080538,0.00009444902,0.00046881067,0.000012910092,0.0016372978,0.000094040384,0.00007660144,0.00001878267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066011125,0.00013234132,0.000019399844,0.000039757248,0.000021621881,9.710719e-7,0.0010132527,0.00018750246,0.005481138,0.73302823,0.0149445,0.24512471],"study_design_scores_gemma":[0.0005771566,0.00006132904,0.00012248033,0.000007516398,0.000017573671,0.000015859187,0.000020615089,0.884758,0.015961446,0.09728346,0.000884625,0.00028992066],"about_ca_topic_score_codex":0.000010492744,"about_ca_topic_score_gemma":0.000001085998,"teacher_disagreement_score":0.88457054,"about_ca_system_score_codex":0.000032835473,"about_ca_system_score_gemma":0.00002567891,"threshold_uncertainty_score":0.4406306},"labels":[],"label_agreement":null},{"id":"W1980390763","doi":"10.1214/ecp.v15-1563","title":"Explicit Conditions for the Convergence of Point Processes Associated to Stationary Arrays","year":2010,"lang":"en","type":"article","venue":"Electronic Communications in Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Université de Paris; Agence Nationale de la Recherche","keywords":"Mathematics; Sequence (biology); Convergence (economics); Independence (probability theory); Stationary sequence; Probabilistic logic; Stationary point; Applied mathematics; Point (geometry); Random variable; Point process; Weak convergence; Convergence of random variables; Mathematical optimization; Mathematical analysis; Statistics; Computer science; Geometry","score_opus":0.03206878643871408,"score_gpt":0.3325327365419993,"score_spread":0.3004639501032852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980390763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017124787,0.00022221844,0.97068954,0.010175997,0.00006859083,0.0012491385,0.000027781833,0.00005253982,0.00038938204],"genre_scores_gemma":[0.74920315,0.00005518758,0.24965183,0.00015683327,0.000005384018,0.0008833888,0.000013049302,0.0000047912317,0.00002638195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987501,0.00021209479,0.00037151808,0.00025951245,0.00012798737,0.0002787922],"domain_scores_gemma":[0.99510676,0.002030143,0.000141263,0.0022196872,0.00045997146,0.000042174714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019177641,0.00009753295,0.00015303587,0.000064050844,0.0002529794,0.000029049428,0.0022860705,0.000057999307,0.000013811784],"category_scores_gemma":[0.0017095915,0.000080285055,0.000052524603,0.00084563,0.00013648251,0.00022675472,0.00031450528,0.00037547905,0.0000018469349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063794314,0.00032695444,0.00048471964,0.00002332803,0.00001680912,2.156652e-8,0.0013789379,0.00008857501,0.0032241647,0.98783803,0.00018430718,0.006427766],"study_design_scores_gemma":[0.00022116133,0.000096014555,0.0050589265,0.00001696925,0.000009790105,0.0000017617365,0.00003522039,0.03193655,0.0028070768,0.9577723,0.0019150507,0.00012914155],"about_ca_topic_score_codex":0.000059739785,"about_ca_topic_score_gemma":0.0030081414,"teacher_disagreement_score":0.7320784,"about_ca_system_score_codex":0.00010408002,"about_ca_system_score_gemma":0.0007159389,"threshold_uncertainty_score":0.4248126},"labels":[],"label_agreement":null},{"id":"W1980420186","doi":"10.2307/3315943","title":"A discussion of some inference issues in order restricted models","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Inference; Order (exchange); Computer science; Epistemology; Artificial intelligence; Philosophy; Economics","score_opus":0.0263069425271318,"score_gpt":0.280893136939284,"score_spread":0.25458619441215224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980420186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022675432,0.00029648255,0.9954524,0.0015681928,0.00019815729,0.00004889911,0.000043336568,0.0000023201983,0.00012266656],"genre_scores_gemma":[0.32007775,0.00006451505,0.6796854,0.000094125804,0.000027332815,3.6536917e-7,9.737759e-7,0.0000047821654,0.00004472597],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988553,0.000087328124,0.00051304937,0.00011201586,0.0002066785,0.00022564862],"domain_scores_gemma":[0.9986872,0.000067348745,0.00026251428,0.00021815741,0.00042253808,0.00034221905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032039956,0.00009423358,0.00026085708,0.00036907414,0.000037179492,0.00005578703,0.0005093408,0.00005903006,0.000008490145],"category_scores_gemma":[0.0004408245,0.0000648603,0.00002551017,0.0005268199,0.00006078826,0.00044432533,0.000021735168,0.00022070821,0.0000011010832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043307723,0.000021076563,0.00024230327,0.000016507942,0.000008375274,0.0003367328,0.002090745,0.006160967,0.00011287389,0.9390911,0.0007428988,0.051172074],"study_design_scores_gemma":[0.00047658262,0.00014375786,0.002545333,0.00016427528,0.0000062634676,0.000036489277,0.000024938472,0.020437902,0.00017693077,0.97556394,0.0003083544,0.00011524466],"about_ca_topic_score_codex":0.003939152,"about_ca_topic_score_gemma":0.007561088,"teacher_disagreement_score":0.3178102,"about_ca_system_score_codex":0.00010632909,"about_ca_system_score_gemma":0.002405238,"threshold_uncertainty_score":0.5954846},"labels":[],"label_agreement":null},{"id":"W1980718017","doi":"10.1080/00949655.2014.933223","title":"Confidence sets based on the positive part James–Stein estimator with the asymptotically constant coverage probability","year":2014,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; Regional Municipality of Niagara; Brock University","funders":"","keywords":"Mathematics; Estimator; Statistics; Constant (computer programming); Confidence interval; Applied mathematics; Econometrics","score_opus":0.016962998689204912,"score_gpt":0.28380846019064626,"score_spread":0.26684546150144134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980718017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037976662,0.0000060796774,0.9880896,0.007298295,0.00006404302,0.0002193753,0.0000072431544,0.000011223795,0.00050645246],"genre_scores_gemma":[0.7313361,6.9797443e-7,0.2671488,0.0014842823,0.000022130565,0.0000012777932,0.0000013306451,0.0000033606907,0.0000020211498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819857,0.00074363186,0.00032631474,0.00016661224,0.00044292235,0.00012192982],"domain_scores_gemma":[0.99228585,0.006800724,0.00026649714,0.00013868281,0.00040882255,0.000099403405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015832733,0.00011292622,0.00018182468,0.000035796158,0.0002092736,0.00022439238,0.00015912688,0.000037603695,0.000008305821],"category_scores_gemma":[0.0006503309,0.000054915083,0.000030140256,0.000121747085,0.00017778245,0.00016663785,0.000021772272,0.00023076174,0.0000015109567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108947104,0.000043697542,0.00004652416,0.000009782302,0.000010924403,0.000006670728,0.00017313425,0.27112314,0.0000070971832,0.682031,0.00012981486,0.046309307],"study_design_scores_gemma":[0.00040671325,0.00047697485,0.00345259,0.000052646323,0.000015696236,0.000014441467,0.0000063861144,0.80694926,0.000012948031,0.18846527,0.000082978295,0.00006408234],"about_ca_topic_score_codex":0.0000018124387,"about_ca_topic_score_gemma":7.4875885e-7,"teacher_disagreement_score":0.72753847,"about_ca_system_score_codex":0.000028378241,"about_ca_system_score_gemma":0.000104655264,"threshold_uncertainty_score":0.2239372},"labels":[],"label_agreement":null},{"id":"W1980774716","doi":"10.1007/s00180-011-0266-0","title":"Copula analysis of mixture models","year":2011,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Cluster analysis; Copula (linguistics); Computer science; Partition (number theory); Mixture model; Data mining; Mathematics; Algorithm; Econometrics; Artificial intelligence; Combinatorics","score_opus":0.05314227083472332,"score_gpt":0.28494431074003534,"score_spread":0.23180203990531204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980774716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002502335,0.00007782619,0.99615985,0.000023887957,0.000109311004,0.00006257303,0.00018913907,0.00003907444,0.00308812],"genre_scores_gemma":[0.22704996,0.000004387088,0.772688,0.00013390806,0.000008998364,0.0000025774343,0.000053304546,0.0000047959143,0.000054107648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989294,0.000088381064,0.00030283554,0.00024657592,0.00028903963,0.00014375802],"domain_scores_gemma":[0.99897885,0.00022724079,0.00015318985,0.0002650379,0.00029465824,0.00008102077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021480542,0.000108616885,0.00025929534,0.00023139431,0.000052953652,0.000023262506,0.00043864187,0.00004964021,0.000059795053],"category_scores_gemma":[0.000029596506,0.000102404,0.00008286353,0.00081672467,0.00005518758,0.00015967859,0.00009221676,0.00007590578,0.0000047388285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036305967,0.00005458491,0.00013849055,0.000007863415,0.00022192064,0.000007381281,0.00088606775,0.025833197,0.0000051978445,0.94943315,0.0008465391,0.022561964],"study_design_scores_gemma":[0.000056856086,0.00001767611,0.003982072,0.0000020576726,0.00008468725,0.0000013505467,0.0000015070904,0.5245109,0.000018852907,0.47123638,0.000024371664,0.00006328426],"about_ca_topic_score_codex":0.00003338141,"about_ca_topic_score_gemma":0.0000063479374,"teacher_disagreement_score":0.4986777,"about_ca_system_score_codex":0.000015594582,"about_ca_system_score_gemma":0.00006785706,"threshold_uncertainty_score":0.4175914},"labels":[],"label_agreement":null},{"id":"W1981031771","doi":"10.1016/j.jmva.2011.08.012","title":"Scale mixtures of Kotz–Dirichlet distributions","year":2011,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Science Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Mathematics; Scale (ratio); Dirichlet distribution; Statistics; Applied mathematics; Mathematical analysis","score_opus":0.026809167967337504,"score_gpt":0.2857955868126976,"score_spread":0.2589864188453601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981031771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014943076,0.00019907932,0.98352253,0.00023167401,0.00014042809,0.000032977165,0.000009711247,0.000010956897,0.00090954587],"genre_scores_gemma":[0.52084047,0.00002653654,0.47899207,0.00003144507,0.00003590644,5.2574256e-7,8.674665e-7,0.0000030414485,0.00006912874],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983766,0.00025150337,0.0006791576,0.00017605786,0.00032308942,0.00019357327],"domain_scores_gemma":[0.99804187,0.00010986065,0.00077218097,0.00044312223,0.00048213845,0.00015085826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010448463,0.00012920385,0.00054691813,0.0004894668,0.000072466595,0.000033853146,0.0008290913,0.00008207723,0.00006188678],"category_scores_gemma":[0.000111809895,0.00008306654,0.0006512114,0.0015000276,0.000050733717,0.00037477503,0.00011034808,0.0001942071,0.0000024502074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043106984,0.005091935,0.06135005,0.00012949877,0.025586309,0.00045057875,0.03369353,0.000875214,0.12351991,0.213553,0.003942336,0.5313766],"study_design_scores_gemma":[0.0034296368,0.00095132086,0.41359028,0.00017143886,0.010383933,0.00020978988,0.00020500917,0.10468667,0.26124614,0.20056666,0.003282333,0.0012767739],"about_ca_topic_score_codex":0.00015833369,"about_ca_topic_score_gemma":0.000013146707,"teacher_disagreement_score":0.5300998,"about_ca_system_score_codex":0.00002753113,"about_ca_system_score_gemma":0.00007271437,"threshold_uncertainty_score":0.33873552},"labels":[],"label_agreement":null},{"id":"W1981088595","doi":"10.1007/s10463-006-0095-z","title":"Local mixtures of the exponential distribution","year":2007,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Universidad Nacional Autónoma de México; Consejo Nacional de Ciencia y Tecnología","keywords":"Mathematics; Class (philosophy); Exponential family; Affine transformation; Applied mathematics; Statistical inference; Inference; Exponential function; Simple (philosophy); Exponential distribution; Distribution (mathematics); Type (biology); Scale (ratio); Statistical model; Statistical physics; Statistics; Mathematical analysis; Pure mathematics; Computer science; Artificial intelligence","score_opus":0.04069839359092124,"score_gpt":0.32356410519885803,"score_spread":0.2828657116079368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981088595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009455642,0.000052528263,0.98839533,0.0006590676,0.00041626632,0.00015708164,0.00010156902,0.000008961652,0.0007535556],"genre_scores_gemma":[0.6331611,0.0000061117616,0.36672083,0.00006800425,0.000015887717,9.206799e-7,0.000001512235,0.0000034569557,0.000022139013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985647,0.000063407795,0.00058171543,0.0001317735,0.0004694885,0.00018886723],"domain_scores_gemma":[0.9984085,0.00031820362,0.00037070483,0.00064471544,0.00020309641,0.000054764518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093124044,0.00011243621,0.00027530896,0.000023880191,0.0000682036,0.000011639644,0.001017559,0.0000721415,0.0000047807043],"category_scores_gemma":[0.00054347864,0.00006155503,0.00014422931,0.00026124416,0.000667818,0.000112246016,0.00032894115,0.00012320568,9.0092345e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009162015,0.00015817923,0.000008025387,0.00015883466,0.000024185512,0.0000013894202,0.0002215197,0.00004049245,0.0021985685,0.9768364,0.0009917308,0.019351516],"study_design_scores_gemma":[0.00014524697,0.00005481479,0.0012539368,0.00020297477,0.000030080195,0.000011924017,0.00001402424,0.007243357,0.2274048,0.7630107,0.0005338384,0.00009430528],"about_ca_topic_score_codex":0.000029788695,"about_ca_topic_score_gemma":0.000007870576,"teacher_disagreement_score":0.6237055,"about_ca_system_score_codex":0.000007841937,"about_ca_system_score_gemma":0.000071513816,"threshold_uncertainty_score":0.25101414},"labels":[],"label_agreement":null},{"id":"W1981573976","doi":"10.1016/j.patcog.2014.12.019","title":"A non-parametric Bayesian model for bounded data","year":2015,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Bounded function; Bayesian probability; Computer science; Parametric statistics; Artificial intelligence; Semiparametric model; Parametric model; Econometrics; Data mining; Mathematics; Algorithm; Machine learning; Statistics","score_opus":0.20885450861798388,"score_gpt":0.34650411412440074,"score_spread":0.13764960550641686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981573976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015388444,0.000044657838,0.9959363,0.00052535103,0.00038717204,0.00041582537,0.00008173663,0.00011333376,0.0009568107],"genre_scores_gemma":[0.2586807,0.000007073175,0.7399486,0.00087037124,0.0001372425,0.000067549925,0.00017242284,0.000016072525,0.00010000405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858785,0.00005829514,0.00023236725,0.0005914709,0.00022813147,0.00030190818],"domain_scores_gemma":[0.99849075,0.00008460763,0.00010428106,0.000950044,0.0001770514,0.00019327577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000946444,0.00014994327,0.00018115243,0.00017422234,0.00007513828,0.00021633775,0.0009907401,0.0000932378,0.0000036631677],"category_scores_gemma":[0.00012639491,0.00014301689,0.000053597596,0.00031637485,0.000017489054,0.00083246303,0.00028546999,0.00010805596,0.00005095568],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009845137,0.00006845692,0.000076967655,0.000025504229,0.000013805671,0.0000029866783,0.00028935872,0.000020854899,0.000033337987,0.00025701494,0.0050804866,0.9941214],"study_design_scores_gemma":[0.0005656638,0.000055240944,0.000029890494,0.000018789824,0.00001572106,0.000011401809,0.0000045308443,0.80845755,0.00026931727,0.19016546,0.00023032636,0.00017611042],"about_ca_topic_score_codex":0.00003200025,"about_ca_topic_score_gemma":0.000018324152,"teacher_disagreement_score":0.99394524,"about_ca_system_score_codex":0.00004141819,"about_ca_system_score_gemma":0.000118090895,"threshold_uncertainty_score":0.583206},"labels":[],"label_agreement":null},{"id":"W1981871516","doi":"10.1137/tprbau000047000002000236000001","title":"On Consistency of Bayes Procedures","year":2003,"lang":"en","type":"article","venue":"Theory of Probability and Its Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Prior probability; Bayes' theorem; Consistency (knowledge bases); Invariant (physics); Sigma; Statistical model; Applied mathematics; Class (philosophy); Strong consistency; Statistics; Pure mathematics; Discrete mathematics; Bayesian probability; Computer science; Artificial intelligence; Mathematical physics; Physics","score_opus":0.023490406857678076,"score_gpt":0.2652478351814662,"score_spread":0.24175742832378813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981871516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011590695,0.0005095091,0.973001,0.00016790969,0.000011175231,0.00045507238,0.000005871441,0.000023641727,0.014235117],"genre_scores_gemma":[0.7699227,0.000026153652,0.22984926,0.000054177075,0.0000031424267,0.000069399684,3.2208132e-7,0.0000023230953,0.000072524614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923307,0.00017281208,0.00020485205,0.00022526392,0.00007972066,0.00008428977],"domain_scores_gemma":[0.99899435,0.00036867874,0.00009340684,0.00039643957,0.00010488954,0.000042235275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008687255,0.000069506976,0.00014315729,0.00003396706,0.00006709747,0.000007313541,0.00021527245,0.00003997359,0.000014677648],"category_scores_gemma":[0.0002868476,0.000056259352,0.000035359586,0.0001609289,0.00014959628,0.00007456128,0.000031564534,0.000052836214,0.0000017411703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047957624,0.00013340046,0.00001139837,0.00011735522,0.0000055712053,1.8016065e-8,0.00024188333,0.000002534618,0.0015528699,0.98055553,0.000011209587,0.017363416],"study_design_scores_gemma":[0.00008220106,0.00005917421,0.00019026805,0.0000162317,0.00000644925,0.000002155191,0.000010225565,0.000103264225,0.017449053,0.9817942,0.00023186271,0.000054955246],"about_ca_topic_score_codex":6.8005903e-7,"about_ca_topic_score_gemma":9.273762e-7,"teacher_disagreement_score":0.758332,"about_ca_system_score_codex":0.0000046795367,"about_ca_system_score_gemma":0.00007798536,"threshold_uncertainty_score":0.22941898},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04077475466133923,"score_gpt":0.3213892502813812,"score_spread":0.280614495620042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982891217","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015534663,0.00046077702,0.9864095,0.009615123,0.00073746,0.00040823082,0.00014102423,0.000040334104,0.0020321994],"genre_scores_gemma":[0.010172224,0.00027946496,0.9848375,0.0027406448,0.0002374422,0.000022103985,0.0000017964746,0.000039299623,0.0016695414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98800755,0.007680672,0.0015435065,0.00072264706,0.0009866806,0.0010589771],"domain_scores_gemma":[0.9820801,0.01573667,0.0005506389,0.0009760506,0.0002879106,0.0003686561],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007977745,0.000543995,0.0012571127,0.000056035107,0.0005198381,0.00025352015,0.0027094472,0.0004229585,0.00058743416],"category_scores_gemma":[0.0041012024,0.0003224,0.00052300934,0.0008131208,0.0009420276,0.00067517796,0.0006005972,0.0020881405,0.000008818255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045230263,0.00017812608,0.00009396698,0.000096602955,0.0002549009,0.0001687311,0.004073681,0.006501916,0.000036082976,0.5722495,0.019732846,0.39616138],"study_design_scores_gemma":[0.00067549874,0.0002948253,0.0013401005,0.00007876732,0.00012994326,0.00014454861,0.00019202157,0.34959465,0.000051599818,0.64425445,0.0028863114,0.00035728927],"about_ca_topic_score_codex":0.00053979177,"about_ca_topic_score_gemma":0.00006816597,"teacher_disagreement_score":0.3958041,"about_ca_system_score_codex":0.0002550779,"about_ca_system_score_gemma":0.00039408257,"threshold_uncertainty_score":0.9999228},"labels":[],"label_agreement":null},{"id":"W1983096469","doi":"10.1016/j.spl.2005.04.027","title":"Optimal allocation in balanced sampling","year":2005,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Mathematics; Selection (genetic algorithm); Sampling (signal processing); Optimal allocation; Mathematical optimization; Statistics; Computer science; Artificial intelligence","score_opus":0.025969845861510833,"score_gpt":0.2886186013050123,"score_spread":0.26264875544350147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983096469","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023153504,0.000021155854,0.9699766,0.006244878,0.00012973696,0.00025641746,0.000012744087,0.00007601036,0.00012893969],"genre_scores_gemma":[0.044549678,0.0000037980137,0.9531981,0.0021255433,0.000066533765,0.000026828659,0.000009038785,0.0000077154145,0.000012792698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985415,0.00015046599,0.00032686308,0.0004518411,0.00020265166,0.00032671698],"domain_scores_gemma":[0.99913543,0.00018121125,0.000071308146,0.000485771,0.000053096428,0.00007319488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074433937,0.00013646793,0.0001698397,0.00006903387,0.000056528737,0.000092801834,0.00043414088,0.000047427046,0.00001036792],"category_scores_gemma":[0.00014179967,0.00013867936,0.000029002565,0.00021954537,0.000062585525,0.00029055987,0.000093701005,0.00019233208,0.000017768763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008942139,0.00008122647,0.00063823105,0.000035009685,0.000006014819,0.0000049551413,0.0009874926,0.0014769045,0.0048164595,0.78309554,0.0008242152,0.20802501],"study_design_scores_gemma":[0.0007003828,0.000055434535,0.014216533,0.000038342547,0.000008439317,0.0000095742325,0.0000014208126,0.21445385,0.0011771591,0.7663517,0.0024813863,0.0005057621],"about_ca_topic_score_codex":0.000030136054,"about_ca_topic_score_gemma":0.00006369816,"teacher_disagreement_score":0.21297693,"about_ca_system_score_codex":0.00015475138,"about_ca_system_score_gemma":0.000056107885,"threshold_uncertainty_score":0.565518},"labels":[],"label_agreement":null},{"id":"W1983409044","doi":"10.1002/cjs.10048","title":"Some tests for uniformity of circular distributions powerful against multimodal alternatives","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Null hypothesis; Statistical hypothesis testing; Statistics; Mathematics; Heuristic; Null (SQL); Sample size determination; Computer science; Statistical physics; Data mining; Mathematical optimization; Physics","score_opus":0.018582829326554855,"score_gpt":0.27685990881931477,"score_spread":0.2582770794927599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983409044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01315325,0.000115666895,0.98387176,0.0003385452,0.0009296091,0.00009849882,0.0014015728,0.0000035841142,0.00008751799],"genre_scores_gemma":[0.43269956,0.000008758445,0.56710124,0.00006439285,0.0000973632,6.2249086e-7,0.000007415687,0.0000051286,0.000015521438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99907416,0.000039114,0.0003666656,0.000114267,0.00014245453,0.00026331304],"domain_scores_gemma":[0.9980844,0.00022627914,0.00031306085,0.00023570347,0.0006002083,0.0005403521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004663235,0.00010326571,0.00021631042,0.00016352542,0.000108753506,0.000064594715,0.0005953724,0.000064187705,0.000007559933],"category_scores_gemma":[0.00068081985,0.000094839685,0.000079390426,0.00011978785,0.00014554018,0.00028118712,0.000017795646,0.00026995924,9.624895e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003318141,0.000030219877,0.0009746936,0.000031228825,0.000047096688,0.00009854495,0.0004137604,0.000037783215,0.002757772,0.923517,0.0018772817,0.070211336],"study_design_scores_gemma":[0.0015013902,0.00042019915,0.02159299,0.000096323245,0.00006951355,0.00024527864,0.00004144891,0.06255938,0.0062984945,0.89239836,0.014286667,0.00048993906],"about_ca_topic_score_codex":0.00033362018,"about_ca_topic_score_gemma":0.0017504191,"teacher_disagreement_score":0.4195463,"about_ca_system_score_codex":0.000055652996,"about_ca_system_score_gemma":0.0013264412,"threshold_uncertainty_score":0.386745},"labels":[],"label_agreement":null},{"id":"W1983497195","doi":"10.1139/x01-099","title":"Forest inventory: further results for optimal sampling schemes based on the anticipated variance","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sampling (signal processing); Variance (accounting); Statistics; Mathematics; Sampling design; Mathematical optimization; Forest inventory; Econometrics; Computer science; Forestry; Forest management; Economics; Geography","score_opus":0.1736960441809603,"score_gpt":0.38221235749611643,"score_spread":0.20851631331515613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983497195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078427605,0.00018657895,0.9029601,0.016320804,0.00027117255,0.00033996732,0.000013115801,0.000008817295,0.0014718102],"genre_scores_gemma":[0.84610486,0.000012927487,0.15270807,0.00046963707,0.00032803416,0.000018138044,0.0000021805067,0.000021157395,0.0003349986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740744,0.00041549222,0.00041232925,0.0002895772,0.00056998135,0.0009051949],"domain_scores_gemma":[0.9965517,0.0010060548,0.00016882912,0.0006375408,0.00089752953,0.0007383463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006684592,0.00015183994,0.00022183679,0.000592385,0.00053399557,0.00042094768,0.0016828533,0.000110550565,0.00001824348],"category_scores_gemma":[0.001924909,0.00010343878,0.00014683596,0.0008551636,0.00021399681,0.00027088096,0.000041572835,0.0006974428,0.0000084226085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001351164,0.00023383972,0.041934676,0.00009723179,0.00021973655,0.001392187,0.0038041829,0.031119177,0.0005472467,0.8002006,0.053945,0.06515498],"study_design_scores_gemma":[0.0032182268,0.0021817302,0.022416325,0.0007926035,0.000023998115,0.00021297045,0.00014653757,0.6600834,0.00068935275,0.10458423,0.20506549,0.00058510393],"about_ca_topic_score_codex":0.0010278347,"about_ca_topic_score_gemma":0.011701203,"teacher_disagreement_score":0.76767725,"about_ca_system_score_codex":0.00018759357,"about_ca_system_score_gemma":0.002493112,"threshold_uncertainty_score":0.6529546},"labels":[],"label_agreement":null},{"id":"W1983607497","doi":"10.1142/s0218127408022731","title":"BIAS REDUCTION OF THE NEAREST NEIGHBOR ENTROPY ESTIMATOR","year":2008,"lang":"en","type":"article","venue":"International Journal of Bifurcation and Chaos","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Estimator; Entropy estimation; k-nearest neighbors algorithm; Mathematics; Entropy (arrow of time); Applied mathematics; Maximum entropy spectral estimation; Algorithm; Statistics; Computer science; Principle of maximum entropy; Artificial intelligence; Physics","score_opus":0.03265355900944168,"score_gpt":0.2774594266563166,"score_spread":0.24480586764687495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983607497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15589325,0.00018428029,0.83604527,0.0062640803,0.0012860902,0.000045438333,0.0000015497072,0.000006118593,0.00027391815],"genre_scores_gemma":[0.93454903,0.00017924464,0.064731196,0.0001574989,0.0002270297,8.743616e-7,3.4570155e-7,0.0000029501134,0.00015185626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9991787,0.00006336968,0.00028322733,0.00007784228,0.00034252243,0.00005432328],"domain_scores_gemma":[0.99900866,0.000035664696,0.0003847157,0.0001196462,0.0004080096,0.000043336204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022224618,0.0000547162,0.00008971882,0.000098030425,0.00005781993,0.00003254841,0.0004558711,0.000029787341,0.000009412737],"category_scores_gemma":[0.00008078761,0.000036026457,0.00007020521,0.000105433806,0.00006184871,0.00029074147,0.00005772699,0.00009479485,0.0000012749098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012704532,0.0003930538,0.010735771,0.000021538608,0.0002353559,0.000037399695,0.0064040525,0.0002630967,0.051079445,0.61344767,0.0055413516,0.3117142],"study_design_scores_gemma":[0.006209008,0.00079276995,0.35787535,0.00070764736,0.00010622414,0.018324967,0.000369351,0.11820809,0.27833912,0.17526428,0.042961862,0.0008413308],"about_ca_topic_score_codex":0.000007724326,"about_ca_topic_score_gemma":4.6715047e-7,"teacher_disagreement_score":0.77865577,"about_ca_system_score_codex":0.000024224122,"about_ca_system_score_gemma":0.00009732878,"threshold_uncertainty_score":0.14691164},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03025689618870801,"score_gpt":0.29809567736429593,"score_spread":0.2678387811755879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984130041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065900985,0.00048845436,0.99640447,0.0008178469,0.00021255223,0.00034471578,0.00002101129,0.00016041686,0.0008915191],"genre_scores_gemma":[0.035738677,0.00012398201,0.95986927,0.00059431506,0.00006210097,0.000039912873,0.000010478049,0.000015432233,0.0035458242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868417,0.000058216854,0.00024250429,0.00043961068,0.00023756847,0.0003379571],"domain_scores_gemma":[0.99883527,0.00029128487,0.0000806304,0.0005287394,0.00012977465,0.00013432126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007785044,0.00017030448,0.00020418873,0.0013121495,0.00012755055,0.00020327944,0.0006824827,0.00017056402,0.000016039116],"category_scores_gemma":[0.00026266373,0.000130792,0.00011963564,0.008166847,0.000021887996,0.00040320947,0.000050325925,0.00010986745,0.000043277276],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007689439,0.00006216502,0.000004247808,0.000022947928,0.000008784887,0.0000015956036,0.000113586655,0.0025946558,0.00016461834,0.022643149,0.005612776,0.96876377],"study_design_scores_gemma":[0.0003197915,0.00006195479,0.000059575406,0.0000060790003,0.00001119647,0.0000052357086,3.5623611e-7,0.92922807,0.0004135823,0.059880886,0.009824136,0.00018913392],"about_ca_topic_score_codex":0.0000033897115,"about_ca_topic_score_gemma":3.2351969e-7,"teacher_disagreement_score":0.96857464,"about_ca_system_score_codex":0.000048465085,"about_ca_system_score_gemma":0.00007588274,"threshold_uncertainty_score":0.53335434},"labels":[],"label_agreement":null},{"id":"W1985001229","doi":"10.1002/cjs.5550360112","title":"Testing homogeneity in a mixture of von mises distributions with a structural parameter","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneity (statistics); von Mises yield criterion; Statistic; Limiting; Mathematics; Likelihood-ratio test; Maximum likelihood; Statistics; Applied mathematics; Test statistic; Estimation theory; Statistical hypothesis testing; Finite element method; Structural engineering; Engineering","score_opus":0.0317993577320001,"score_gpt":0.2456219002386322,"score_spread":0.2138225425066321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985001229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15558465,0.00017196784,0.8437452,0.00009529027,0.00008627916,0.000043179538,0.00021759159,0.0000021034432,0.00005377989],"genre_scores_gemma":[0.48949873,0.0000023745192,0.5104456,0.000026129464,0.000016460155,3.1812212e-7,0.0000014675919,0.0000029033458,0.000006036976],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99913037,0.00007344481,0.00031502612,0.00010403468,0.00014317589,0.00023394273],"domain_scores_gemma":[0.9986966,0.00024411698,0.0002259157,0.00016171348,0.00034744164,0.0003241837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016744487,0.00009724331,0.00022182763,0.00016307138,0.000097447635,0.000030083604,0.00032615158,0.000043556032,0.000005933943],"category_scores_gemma":[0.00045611133,0.00007631822,0.000028397386,0.00038608795,0.00014057859,0.00014898361,0.000011421262,0.00021532908,2.2298761e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067367175,0.00009150389,0.48867497,0.00019416111,0.00020126054,0.011770736,0.009069575,0.0012755768,0.0014163337,0.20648456,0.0074441615,0.2733098],"study_design_scores_gemma":[0.0016508354,0.0010813359,0.82084334,0.00044705754,0.00008101182,0.0080768345,0.00006797403,0.028085826,0.0018183686,0.13637877,0.0008024584,0.00066619593],"about_ca_topic_score_codex":0.002182196,"about_ca_topic_score_gemma":0.008010939,"teacher_disagreement_score":0.33391407,"about_ca_system_score_codex":0.00007426031,"about_ca_system_score_gemma":0.0013897902,"threshold_uncertainty_score":0.4470292},"labels":[],"label_agreement":null},{"id":"W1985045737","doi":"10.1007/s00362-014-0623-5","title":"A diagnostic tool for regression analysis of complex survey data","year":2014,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Wilfrid Laurier University","funders":"","keywords":"Nonparametric regression; Regression analysis; Statistics; Estimator; Nonparametric statistics; Plot (graphics); Mathematics; Regression diagnostic; Function (biology); Parametric statistics; Regression; Econometrics; Computer science; Polynomial regression","score_opus":0.08393571064839675,"score_gpt":0.36879003200034677,"score_spread":0.28485432135195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985045737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026741278,0.000013835006,0.9973609,0.00012053203,0.000084631974,0.00013429791,0.001038122,0.000023667675,0.00095662585],"genre_scores_gemma":[0.34971073,0.000004424106,0.6496323,0.00017253135,0.000014679801,0.0000058417054,0.00042376373,0.0000045906236,0.000031168784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848723,0.00039130892,0.00026723294,0.00044136803,0.00020697224,0.00020590606],"domain_scores_gemma":[0.98930454,0.009422513,0.00008537685,0.0010168934,0.00007865182,0.00009204793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014340499,0.00010499724,0.00035518061,0.00008429405,0.00006033575,0.000038974522,0.0008515708,0.000043744825,0.000052640567],"category_scores_gemma":[0.0062054708,0.00007874732,0.000053283613,0.00043518076,0.00008233423,0.000089394285,0.00024540065,0.000057598256,0.0000026480336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025369942,0.00006671041,0.003100246,0.000042670406,0.00022239117,0.0000022134466,0.00008766727,0.000038138765,0.00049310055,0.576515,0.006417698,0.41298878],"study_design_scores_gemma":[0.00028111573,0.000101420825,0.28832713,0.000014669903,0.00024975123,5.033559e-7,0.0000017935755,0.6846809,0.000020788648,0.023882056,0.0022718168,0.00016808041],"about_ca_topic_score_codex":0.00007788939,"about_ca_topic_score_gemma":0.00010506367,"teacher_disagreement_score":0.68464273,"about_ca_system_score_codex":0.000008693751,"about_ca_system_score_gemma":0.000029743891,"threshold_uncertainty_score":0.7428976},"labels":[],"label_agreement":null},{"id":"W1985367615","doi":"10.1007/s00521-012-1094-z","title":"Bayesian learning of inverted Dirichlet mixtures for SVM kernels generation","year":2012,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Computational Science and Engineering; Bayesian probability; Latent Dirichlet allocation; Computer science; Artificial intelligence; Support vector machine; Machine learning; Pattern recognition (psychology); Mathematics; Topic model; Mathematical analysis","score_opus":0.03271132433912297,"score_gpt":0.3062235702702,"score_spread":0.273512245931077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985367615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014193866,0.00041460278,0.9843593,0.00032469904,0.00007890755,0.000278843,0.0000023350433,0.00008686928,0.0002605646],"genre_scores_gemma":[0.724506,0.0000064317555,0.27498055,0.00016639753,0.0002595029,0.000028223652,0.000008421567,0.000006040676,0.000038450453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992214,0.00007982259,0.00019315741,0.00021971179,0.00008170424,0.00020421193],"domain_scores_gemma":[0.99936265,0.00016440365,0.00011703264,0.00020211359,0.00006656992,0.00008722104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032239044,0.00009678635,0.00013530787,0.000051943258,0.00025580273,0.00005054708,0.0001964569,0.00005130315,8.128358e-7],"category_scores_gemma":[0.000028458668,0.00008720056,0.000045270473,0.00019461254,0.000030356063,0.00014568049,0.000084152496,0.0001037622,7.4429823e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020980365,0.00006484475,0.0016981291,0.000045229062,0.000014172271,7.021993e-8,0.0007860178,0.0005752713,0.034808625,0.28007886,0.0006552991,0.6812714],"study_design_scores_gemma":[0.00017251696,0.000034511868,0.0011442736,0.000007597482,0.000012792402,0.000008726274,0.0000074213153,0.98037547,0.008790417,0.005716804,0.0035954148,0.00013405705],"about_ca_topic_score_codex":0.000007843392,"about_ca_topic_score_gemma":4.689289e-7,"teacher_disagreement_score":0.9798002,"about_ca_system_score_codex":0.0000068018508,"about_ca_system_score_gemma":0.000010712193,"threshold_uncertainty_score":0.35559356},"labels":[],"label_agreement":null},{"id":"W1985741712","doi":"10.1016/s0378-3758(01)00096-9","title":"The distribution of Hermitian quadratic forms in elliptically contoured random vectors","year":2002,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Hermitian matrix; Quadratic equation; Distribution (mathematics); Mathematical analysis; Combinatorics; Pure mathematics; Geometry","score_opus":0.022262255865732335,"score_gpt":0.2902068264556805,"score_spread":0.2679445705899482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985741712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016414078,0.0007123341,0.9819888,0.00038978553,0.00008783116,0.000044608274,0.0000063334373,0.000003813101,0.00035242838],"genre_scores_gemma":[0.94917977,0.00012687988,0.050619718,0.000033820197,0.000022749711,8.223146e-7,6.555372e-7,0.000002078445,0.000013504742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891216,0.0001331121,0.00048706343,0.00008980807,0.00020815806,0.00016969466],"domain_scores_gemma":[0.9978148,0.0016782267,0.00020271247,0.000100147285,0.00010242955,0.00010169153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007674097,0.000080420206,0.00024701082,0.000036593763,0.000071298644,0.000091087364,0.00022819305,0.00004513317,0.000005249478],"category_scores_gemma":[0.0009791112,0.000046636036,0.0000302715,0.00011224861,0.00011600024,0.0002100802,0.000029567447,0.00024834956,6.2211467e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013088094,0.000100769335,0.00421874,0.000044955566,0.000032106098,0.0001278175,0.0013292804,0.00012308666,0.0002619644,0.7030635,0.0010683804,0.28949854],"study_design_scores_gemma":[0.003284954,0.0012641834,0.09608762,0.00065896363,0.000041757292,0.00022110465,0.000097801574,0.44044754,0.00024249403,0.45649192,0.00084159244,0.00032007485],"about_ca_topic_score_codex":0.0000060448897,"about_ca_topic_score_gemma":0.0000023711946,"teacher_disagreement_score":0.9327657,"about_ca_system_score_codex":0.000016106098,"about_ca_system_score_gemma":0.000031433152,"threshold_uncertainty_score":0.19017623},"labels":[],"label_agreement":null},{"id":"W1986005174","doi":"10.4236/am.2012.312a292","title":"A New Randomized P&amp;#243;lya Urn Model","year":2012,"lang":"en","type":"article","venue":"Applied Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Combinatorics; Bounded function; Martingale (probability theory); Sequence (biology); Limit (mathematics); Class (philosophy); White (mutation); Mathematical analysis; Statistics; Computer science; Artificial intelligence","score_opus":0.034419633450290435,"score_gpt":0.2815762401596415,"score_spread":0.24715660670935108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986005174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011965058,0.00016359969,0.92958856,0.00027919505,0.00015553106,0.00048445407,9.249204e-7,0.00022093258,0.06898717],"genre_scores_gemma":[0.00909418,0.000022219867,0.9874975,0.0004993971,0.00016467115,0.00006740788,0.0000016533539,0.00002767112,0.002625272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846286,0.000046343328,0.0004235616,0.00025209168,0.00032135207,0.0004938221],"domain_scores_gemma":[0.9981996,0.00039192472,0.00017611051,0.0008996255,0.00003059128,0.00030219535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016753773,0.00024011782,0.0006075522,0.00007780578,0.00008104294,0.00010506249,0.00071951456,0.00012153177,0.000035098292],"category_scores_gemma":[0.00007455109,0.00018378647,0.00016300965,0.00021281862,0.00004115787,0.0002517381,0.0002487204,0.00017462934,0.00026890947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006542151,0.00007501897,1.6851182e-7,0.00003431447,0.000025893016,2.1480618e-7,0.0039244015,0.000035435234,0.00096989487,0.96668625,0.0039770966,0.024205917],"study_design_scores_gemma":[0.011511636,0.0000028442878,1.8167574e-7,0.000014367026,0.00004542846,0.0000133912945,0.000009944058,0.13232177,0.0008105167,0.8533308,0.0016900143,0.0002490977],"about_ca_topic_score_codex":0.000003105909,"about_ca_topic_score_gemma":8.6836326e-7,"teacher_disagreement_score":0.13228634,"about_ca_system_score_codex":0.000023966257,"about_ca_system_score_gemma":0.00007747745,"threshold_uncertainty_score":0.74945945},"labels":[],"label_agreement":null},{"id":"W1987091338","doi":"10.1109/tcyb.2013.2273714","title":"Bounded Asymmetrical Student's-t Mixture Model","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"AUTO21 Network of Centres of Excellence; National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Mixture model; Bounded function; Student's t-distribution; Gaussian; Distribution (mathematics); Computer science; Function (biology); Mathematics; Artificial intelligence; Mathematical analysis; Physics; Econometrics","score_opus":0.017817157600707845,"score_gpt":0.2691618840312702,"score_spread":0.2513447264305624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987091338","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002495912,0.000050469942,0.98817825,0.0009623153,0.00079462526,0.00032672074,0.000004396228,0.00023208749,0.0069552045],"genre_scores_gemma":[0.49502778,0.000041070805,0.49942052,0.0008725928,0.000034586483,0.000052742285,3.78943e-7,0.000019481004,0.004530857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818474,0.00010833664,0.00029808134,0.00050439104,0.0004858383,0.00041860074],"domain_scores_gemma":[0.99861777,0.00014307977,0.000060748494,0.0007887178,0.00013605341,0.00025362856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017731237,0.00024997504,0.00023670032,0.0002230372,0.00018397179,0.0003318512,0.00088026945,0.00020387991,0.00006304472],"category_scores_gemma":[0.0000052887117,0.0002223882,0.00016725998,0.0006179663,0.000061932165,0.0003640058,0.0000064627625,0.00048331742,0.0003648841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013530449,0.0016445043,0.000011023792,0.000026813259,0.00017319253,0.00002202054,0.0027712563,0.029811993,0.0031183094,0.13670596,0.012004637,0.81369674],"study_design_scores_gemma":[0.0006147614,0.00019900297,0.00015713606,0.000017843922,0.000038720194,0.000024600078,0.000012319955,0.9075001,0.011671592,0.078189,0.0010989828,0.00047596754],"about_ca_topic_score_codex":0.000028795126,"about_ca_topic_score_gemma":0.000010144276,"teacher_disagreement_score":0.8776881,"about_ca_system_score_codex":0.00007269445,"about_ca_system_score_gemma":0.000071495706,"threshold_uncertainty_score":0.9068728},"labels":[],"label_agreement":null},{"id":"W1987208751","doi":"10.1007/s10985-009-9120-x","title":"About an adaptively weighted Kaplan-Meier estimate","year":2009,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Università della Calabria","keywords":"Mathematics; Statistics; Nonparametric statistics; Survival function; Survival analysis; Kaplan–Meier estimator; Population; Empirical distribution function; Econometrics; Applied mathematics; Demography","score_opus":0.03127649750889609,"score_gpt":0.33281399877823425,"score_spread":0.30153750126933815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987208751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011411398,0.00032813652,0.99495804,0.0009348423,0.00006170646,0.00008453164,0.0002315523,0.00022748108,0.0020325393],"genre_scores_gemma":[0.046962887,0.000043286953,0.9493934,0.0016032044,0.0001282379,0.0000030054373,0.0012835708,0.000010177542,0.0005722125],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973643,0.00027825794,0.00037895632,0.0011309546,0.00041026558,0.00043728636],"domain_scores_gemma":[0.99547917,0.00007620997,0.00015934468,0.0037993854,0.00008724907,0.00039863473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008021274,0.00025921408,0.00049992616,0.00043301904,0.00017621224,0.00037418903,0.003491051,0.00011430383,0.00015086823],"category_scores_gemma":[0.00005944688,0.00021945554,0.00015430275,0.002192467,0.000039664905,0.0016346123,0.00041930546,0.00018620057,0.00012960527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046722856,0.0004349617,0.0007438838,0.000008546266,0.0014836915,0.00015570856,0.00077252253,0.0002670235,0.0006732045,0.10989068,0.016457548,0.8690655],"study_design_scores_gemma":[0.0001928099,0.00010189115,0.004600197,0.000008731932,0.0005880511,0.000008078166,0.0000045332004,0.9733979,0.00013990953,0.012627861,0.007971471,0.00035852432],"about_ca_topic_score_codex":0.000090113506,"about_ca_topic_score_gemma":0.000026508644,"teacher_disagreement_score":0.97313094,"about_ca_system_score_codex":0.00001845622,"about_ca_system_score_gemma":0.00007349745,"threshold_uncertainty_score":0.89491373},"labels":[],"label_agreement":null},{"id":"W1988018581","doi":"10.1002/sim.1748","title":"Simultaneous inference for longitudinal data with detection limits and covariates measured with errors, with application to AIDS studies","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Covariate; Censoring (clinical trials); Inference; Statistics; Computer science; Statistical inference; Gibbs sampling; Data set; Monte Carlo method; Observational error; Econometrics; Mathematics; Artificial intelligence; Bayesian probability","score_opus":0.054640807936469755,"score_gpt":0.3630267823652393,"score_spread":0.3083859744287695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988018581","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010710335,0.00018713053,0.99705046,0.000744315,0.000046196146,0.00079988636,0.000046718767,0.00003189163,0.000022367249],"genre_scores_gemma":[0.44109434,0.000027136653,0.55866027,0.000106232044,0.000025619453,0.000057906873,0.0000145858685,0.0000074122718,0.000006496681],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986834,0.000043775402,0.00019855992,0.00058597384,0.00028230486,0.00020596322],"domain_scores_gemma":[0.9981514,0.0006969632,0.000107687294,0.00058955513,0.00035691538,0.00009744549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007194574,0.00017240139,0.00031961987,0.000098884055,0.00011329708,0.000046443995,0.00051704387,0.000033586504,2.990701e-7],"category_scores_gemma":[0.000747005,0.000104010556,0.0000023690557,0.0004333162,0.00016632947,0.00018960386,0.00013457367,0.00012059844,3.0115336e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001348611,0.00017020768,0.0019727973,0.00035651584,0.00023810127,0.00015296484,0.006969298,0.009406898,0.0012274893,0.3631569,0.000106697466,0.6148935],"study_design_scores_gemma":[0.021933261,0.035178743,0.011134677,0.0032634404,0.00069091824,0.00053649105,0.00135215,0.35670525,0.0027806528,0.56336266,0.0011665416,0.0018951972],"about_ca_topic_score_codex":0.00020852643,"about_ca_topic_score_gemma":0.0047387425,"teacher_disagreement_score":0.6129983,"about_ca_system_score_codex":0.000056043435,"about_ca_system_score_gemma":0.00010857511,"threshold_uncertainty_score":0.42414275},"labels":[],"label_agreement":null},{"id":"W1988285521","doi":"10.1002/cjs.5540330110","title":"Testing the homogeneity of several two-parameter populations","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Exact test; Humanities; Philosophy","score_opus":0.07165058889988717,"score_gpt":0.2906501899881324,"score_spread":0.21899960108824523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988285521","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006021819,0.00014279723,0.992234,0.0007924232,0.00027176685,0.00004022938,0.000057811885,0.0000025184415,0.0004366207],"genre_scores_gemma":[0.38956612,8.423717e-7,0.6100975,0.00021617714,0.000089172274,2.1282446e-7,3.7986533e-7,0.0000031893542,0.000026381376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991833,0.00009237537,0.00033088858,0.000071151386,0.00013639583,0.00018591782],"domain_scores_gemma":[0.9987016,0.00027640155,0.00024100197,0.00020610052,0.00031877088,0.00025616487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046511838,0.00006938551,0.00013408337,0.0001024153,0.0001330549,0.000067021654,0.00047343367,0.000024559944,0.000014674984],"category_scores_gemma":[0.0004631868,0.00005065961,0.000039084185,0.00021014713,0.000069315465,0.00016194845,0.000016242584,0.00016811752,0.000001765826],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001881715,0.000014732273,0.0043066554,0.000009007035,0.00003272809,0.00007603662,0.0011896575,0.0055739074,0.00015271115,0.47803208,0.008415022,0.5021956],"study_design_scores_gemma":[0.00074317306,0.00024975004,0.111578636,0.00009684844,0.00010336705,0.0011107702,0.00003573021,0.4386825,0.00044687337,0.43672976,0.00982144,0.00040115358],"about_ca_topic_score_codex":0.001460307,"about_ca_topic_score_gemma":0.007857202,"teacher_disagreement_score":0.5017944,"about_ca_system_score_codex":0.000056744844,"about_ca_system_score_gemma":0.0007252341,"threshold_uncertainty_score":0.43845028},"labels":[],"label_agreement":null},{"id":"W1988550220","doi":"10.1117/12.503905","title":"&lt;title&gt;EM-ML algorithm for track initialization with features using possibly noninformative data&lt;/title&gt;","year":2003,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Initialization; Computer science; Track (disk drive); Algorithm; Programming language; Operating system","score_opus":0.019570011851832544,"score_gpt":0.2610832954590925,"score_spread":0.24151328360725993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988550220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0700024,0.00021818937,0.89259225,0.00044855618,0.00050363597,0.00069327303,0.00010757123,0.000119790435,0.035314355],"genre_scores_gemma":[0.004520155,0.00003323493,0.99465287,0.000099275654,0.00020597271,0.000028392193,0.000012403694,0.00002934999,0.000418322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988362,3.4297752e-8,0.00029540306,0.00026917626,0.00036775367,0.00023141879],"domain_scores_gemma":[0.998765,0.00006455352,0.00020631182,0.000081388906,0.00081504724,0.00006770571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047253634,0.00018351343,0.00021606732,0.00007193866,0.000071372626,0.00015500648,0.0007199172,0.00012073167,0.000012389878],"category_scores_gemma":[0.00017658254,0.00014157589,0.0001631974,0.00025462426,0.00007663792,0.00072944065,0.000100574005,0.00014403732,0.0000022074971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010173749,0.000036293095,0.0000023714908,0.00012288067,0.00013757884,9.638399e-8,0.00022035236,0.000027578299,0.013174912,0.96954143,0.008051777,0.008674579],"study_design_scores_gemma":[0.001486303,0.00040017063,0.000066376735,0.00042663197,0.00019877525,0.00010820493,0.00028994188,0.8687984,0.04758863,0.019124387,0.060779747,0.00073243666],"about_ca_topic_score_codex":9.4773577e-7,"about_ca_topic_score_gemma":6.71966e-8,"teacher_disagreement_score":0.95041704,"about_ca_system_score_codex":0.0000623691,"about_ca_system_score_gemma":0.000060716997,"threshold_uncertainty_score":0.57732975},"labels":[],"label_agreement":null},{"id":"W1988615079","doi":"10.1111/j.0006-341x.2004.00188.x","title":"A Conditional Markov Model for Clustered Progressive Multistate Processes under Incomplete Observation","year":2004,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Health Canada; Arthritis Society","keywords":"Markov chain; Generalization; Markov model; Multiplicative function; Random effects model; Computer science; Markov process; Mathematics; Econometrics; Statistics; Medicine; Internal medicine","score_opus":0.08145212404502242,"score_gpt":0.32566501476150006,"score_spread":0.24421289071647764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988615079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018522395,0.0003152803,0.99556524,0.0012221397,0.00019490825,0.0005699884,0.0001117265,0.00011877926,0.000049727805],"genre_scores_gemma":[0.14322305,0.000014971064,0.8555746,0.0006998588,0.000060668728,0.00012651716,0.00007777649,0.00001317287,0.00020934745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870074,0.00002800237,0.00026067,0.0004075633,0.00031473328,0.00028829876],"domain_scores_gemma":[0.99872476,0.0002087527,0.00017998839,0.00026745,0.0005167778,0.00010224325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031489044,0.00015623729,0.00016961714,0.00058586785,0.00016215774,0.00019567188,0.0004783905,0.00009365942,0.0000014643613],"category_scores_gemma":[0.00030594337,0.00014061002,0.00006158319,0.0028439043,0.00005096174,0.0005673867,0.00011704824,0.0000687808,0.0000040576274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011369843,0.0008380063,0.00017834196,0.0009069729,0.0001379175,0.000025894253,0.0015672931,0.015121037,0.0026345653,0.6918406,0.0029134979,0.2837222],"study_design_scores_gemma":[0.0012917252,0.000098087985,0.0008685162,0.000029463261,0.000010569682,0.000011597315,0.0000038805542,0.6415291,0.00083812437,0.3545856,0.0004970086,0.00023635536],"about_ca_topic_score_codex":0.000006327073,"about_ca_topic_score_gemma":0.000004347062,"teacher_disagreement_score":0.62640804,"about_ca_system_score_codex":0.00011656888,"about_ca_system_score_gemma":0.00033474126,"threshold_uncertainty_score":0.573391},"labels":[],"label_agreement":null},{"id":"W1989098379","doi":"10.1109/isspa.2012.6310592","title":"Online variational finite Dirichlet mixture model and its applications","year":2012,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Computer science; Inference; Dirichlet distribution; Artificial intelligence; Class (philosophy); Latent Dirichlet allocation; Online model; Machine learning; Mixture model; Face (sociological concept); Object (grammar); Topic model; Mathematics; Boundary value problem; Artificial neural network; Statistics","score_opus":0.02831214424250006,"score_gpt":0.2881747491763652,"score_spread":0.25986260493386515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989098379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015369387,0.0005766847,0.9925091,0.0019045488,0.0000529166,0.00013302827,0.000016914155,0.00008440227,0.0045686723],"genre_scores_gemma":[0.11025698,0.00003500901,0.88616455,0.0016142203,0.00015531653,0.000030247946,0.000010245167,0.0000052442856,0.0017282115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993322,0.000033474225,0.00011743019,0.00019611072,0.0001252127,0.00019559276],"domain_scores_gemma":[0.99939865,0.00012776232,0.000035866524,0.00024028654,0.000057813668,0.00013963594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022267825,0.00009065509,0.00008755621,0.000046211535,0.00008679731,0.00004340152,0.00025132054,0.00006401004,0.000015541229],"category_scores_gemma":[0.000023374305,0.000072691626,0.00002455634,0.0001741451,0.000009738662,0.00044322366,0.00013684294,0.00009315729,0.00001682741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.6132922e-7,0.00008969789,0.000029931825,0.000004600391,0.000005359719,9.1220926e-8,0.00016682425,0.00020057912,0.00029244085,0.97700554,0.0005922724,0.021612173],"study_design_scores_gemma":[0.00009842761,0.000005339628,0.0006423183,0.000001922345,0.000005764116,0.0000065853737,0.0000011526184,0.8979896,0.000096868476,0.09351029,0.007526196,0.000115535804],"about_ca_topic_score_codex":0.0000012671131,"about_ca_topic_score_gemma":0.0000011744797,"teacher_disagreement_score":0.897789,"about_ca_system_score_codex":0.000008379812,"about_ca_system_score_gemma":0.0000298148,"threshold_uncertainty_score":0.29642785},"labels":[],"label_agreement":null},{"id":"W1990449216","doi":"10.2307/3315913","title":"A general class of hierarchical ordinal regression models with applications to correlated roc analysis","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Markov chain Monte Carlo; Ordinal regression; Statistics; Bayesian probability; Artificial intelligence; Computer science","score_opus":0.016796907880410807,"score_gpt":0.25886444840629064,"score_spread":0.24206754052587984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990449216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035289098,0.00008957901,0.99481165,0.00045372127,0.00003895396,0.000092621805,0.00011948264,0.000004482971,0.00086061796],"genre_scores_gemma":[0.21166871,0.000014267067,0.787732,0.00018929473,0.000039040457,0.0000027288606,0.000005096289,0.0000071292534,0.00034169573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882716,0.00009554422,0.00040774923,0.00017110267,0.0002475883,0.00025087205],"domain_scores_gemma":[0.9982519,0.000071512855,0.00018548315,0.00029858877,0.00035966942,0.0008328461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025695658,0.00011406532,0.00032133318,0.00047278404,0.000105962834,0.00006169043,0.0005206199,0.00006187588,0.00008000921],"category_scores_gemma":[0.00001757617,0.00008851536,0.000068662426,0.0011253608,0.00007230064,0.00014469116,0.000011944815,0.00024370296,0.0000027087408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006036829,0.000044914243,0.0005612328,0.000014308107,0.00034320191,0.00028307503,0.0011562468,0.07401323,0.00006805145,0.496235,0.005086099,0.42213428],"study_design_scores_gemma":[0.00066472974,0.0006420831,0.0028390777,0.000108388806,0.00050066883,0.00032992195,0.000018450395,0.8476912,0.00008710329,0.13856527,0.008185777,0.00036733036],"about_ca_topic_score_codex":0.00078110915,"about_ca_topic_score_gemma":0.0031957433,"teacher_disagreement_score":0.77367795,"about_ca_system_score_codex":0.00007604182,"about_ca_system_score_gemma":0.0009730385,"threshold_uncertainty_score":0.36095515},"labels":[],"label_agreement":null},{"id":"W1990572220","doi":"10.1016/j.csda.2013.02.019","title":"Generating beta random numbers and Dirichlet random vectors in R: The package rBeta2009","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random number generation; Software package; Computer science; Software; Dirichlet distribution; R package; Algorithm; Theoretical computer science; Parallel computing; Mathematics; Computational science; Programming language","score_opus":0.024027990918040656,"score_gpt":0.2945454916717646,"score_spread":0.27051750075372394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990572220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031086807,0.00035007522,0.99482054,0.0008445213,0.000060688366,0.00024429068,0.00042451418,0.000025330657,0.000121340854],"genre_scores_gemma":[0.19687472,0.00005411805,0.8009184,0.0007241363,0.00005345473,0.000019337931,0.0013238898,0.0000074277355,0.000024485353],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749064,0.0006659501,0.0004772761,0.0006131546,0.00048466478,0.00026831473],"domain_scores_gemma":[0.99670374,0.0020260834,0.00017682926,0.0008607033,0.00013447294,0.00009814692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014292878,0.00019620004,0.00041588745,0.0002270197,0.00023968056,0.0006880358,0.0011422146,0.000047484828,0.000050078557],"category_scores_gemma":[0.00022112278,0.0001431686,0.000067403176,0.0011893254,0.00008686302,0.00055337104,0.0003668192,0.00018399299,0.000017345406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049511593,0.000349907,0.025594814,0.00007802867,0.0026598405,0.00013935483,0.0051052435,0.11190436,0.00009074149,0.3516548,0.09054372,0.41182968],"study_design_scores_gemma":[0.00095708657,0.000010651246,0.0233061,0.0000045052566,0.00027377575,0.000005678791,0.000014555741,0.9178985,0.0000013087995,0.057082128,0.00027048695,0.00017521724],"about_ca_topic_score_codex":0.00087777205,"about_ca_topic_score_gemma":0.00032063288,"teacher_disagreement_score":0.80599415,"about_ca_system_score_codex":0.000020430658,"about_ca_system_score_gemma":0.000057891582,"threshold_uncertainty_score":0.6634745},"labels":[],"label_agreement":null},{"id":"W1992368742","doi":"10.1239/aap/1324045699","title":"The sampling formula and Laplace transform associated with the two-parameter Poisson-Dirichlet distribution","year":2011,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Dirichlet distribution; Laplace distribution; Laplace transform; Poisson distribution; Applied mathematics; Central limit theorem; Mathematical analysis; Statistics","score_opus":0.023740790130915686,"score_gpt":0.26585208943576366,"score_spread":0.24211129930484798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992368742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022742394,0.00048625527,0.97139275,0.0005614469,0.00005595924,0.0007432893,0.000007395854,0.0000654594,0.0039450503],"genre_scores_gemma":[0.80550694,0.0000731667,0.19411947,0.00011058966,0.000010366832,0.00015765407,0.0000037436682,0.00000636437,0.000011708975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863803,0.0001389082,0.0002361707,0.0004269789,0.0001923265,0.00036760847],"domain_scores_gemma":[0.99842453,0.00084655726,0.000111439316,0.0005207766,0.00004385303,0.00005284235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019119643,0.00017220173,0.00018469842,0.000012938591,0.00031932697,0.000086012085,0.00055265264,0.00005999637,0.0000013065127],"category_scores_gemma":[0.000087688866,0.00008702109,0.000034066405,0.0003471908,0.00026800632,0.00034525277,0.000092672846,0.00028045633,7.2078006e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010070255,0.00007084458,0.0008037413,0.000015312738,0.000013130302,6.881131e-7,0.0013951494,0.000048522157,0.00003425845,0.56938267,0.000009178384,0.4281258],"study_design_scores_gemma":[0.00058527594,0.00007562092,0.0047699767,0.000019209536,0.0000122293895,0.0000042011065,0.000032997254,0.0046459967,0.0010525228,0.9850302,0.0035604418,0.00021133962],"about_ca_topic_score_codex":0.00001607142,"about_ca_topic_score_gemma":0.00049097365,"teacher_disagreement_score":0.78276455,"about_ca_system_score_codex":0.00007848327,"about_ca_system_score_gemma":0.000031778025,"threshold_uncertainty_score":0.35486174},"labels":[],"label_agreement":null},{"id":"W1992572895","doi":"10.1023/a:1004152916478","title":"On the Bessel Distribution and Related Problems","year":2000,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Bessel function; von Mises distribution; Mathematics; Bessel process; Computation; Distribution (mathematics); Applied mathematics; Bayesian probability; Monte Carlo method; Statistical physics; von Mises yield criterion; Algorithm; Statistics; Mathematical analysis; Physics","score_opus":0.04085020324197114,"score_gpt":0.296292397445917,"score_spread":0.25544219420394587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992572895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018100195,0.000043869357,0.9727342,0.004199788,0.000079331825,0.00020038882,0.00006486277,0.000014006471,0.004563353],"genre_scores_gemma":[0.7313678,0.000103792365,0.26792482,0.00027834787,0.000008681435,0.0000076045835,0.0000034430816,0.000006587481,0.00029892588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991085,0.00006848209,0.00032965912,0.00012885622,0.00023778938,0.00012669283],"domain_scores_gemma":[0.9988879,0.00042066397,0.00013101927,0.00044680623,0.00007192038,0.00004170544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005492905,0.000094736824,0.00018394901,0.000012529095,0.00009266809,0.000026317437,0.00048062828,0.000047975715,0.000018920322],"category_scores_gemma":[0.00035910573,0.000048270886,0.000046364563,0.0001732791,0.00032373003,0.00010482509,0.00008395187,0.000118423566,0.000004282524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002118323,0.00008849957,9.450259e-7,0.00006826408,0.000017025388,7.7015767e-7,0.00024852628,0.000058710157,0.000054116892,0.9736897,0.0012665072,0.02450483],"study_design_scores_gemma":[0.00007541939,0.000061793995,0.00018129118,0.0001732117,0.000011887909,0.00001069209,0.0000027341482,0.02270794,0.0011335271,0.9749688,0.00061283476,0.00005989918],"about_ca_topic_score_codex":0.000009047549,"about_ca_topic_score_gemma":9.728448e-7,"teacher_disagreement_score":0.7132676,"about_ca_system_score_codex":0.000003482309,"about_ca_system_score_gemma":0.000027060014,"threshold_uncertainty_score":0.19684295},"labels":[],"label_agreement":null},{"id":"W1994281788","doi":"10.1007/s11634-014-0182-6","title":"Mixture model averaging for clustering","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Model selection; Bayesian information criterion; Pattern recognition (psychology); Bayesian probability; Rand index; Closeness; Single-linkage clustering","score_opus":0.04141965676927712,"score_gpt":0.3381464725389695,"score_spread":0.2967268157696924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994281788","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013547942,0.0005505018,0.9979959,0.0006220736,0.00004287848,0.00007861712,0.000012917174,0.000024001884,0.0005376022],"genre_scores_gemma":[0.30220348,0.00045617507,0.6970089,0.0001426955,0.000026383439,0.000016019607,0.00009130057,0.0000033527133,0.00005169584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897105,0.00005750171,0.00020163869,0.0005396885,0.00009337755,0.00013673514],"domain_scores_gemma":[0.99872684,0.00010877065,0.000097561024,0.000996219,0.00003241819,0.000038199614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076471735,0.0000854039,0.00017987099,0.0001628572,0.0000796238,0.00010204065,0.0006801596,0.00004012916,6.587238e-7],"category_scores_gemma":[0.00006805253,0.0000749035,0.000035130382,0.00047828894,0.000019584522,0.0011947922,0.00018867824,0.000060694925,4.501002e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038212315,0.000016739676,0.0006448089,0.0000226495,0.000027597363,1.00079426e-7,0.00012375339,0.005377385,0.0005454545,0.15206075,0.00005609185,0.84112084],"study_design_scores_gemma":[0.00011273996,0.000005119533,0.000832351,0.0000070187425,0.00005676861,3.8619118e-7,0.000006225768,0.94569427,0.000038097885,0.047834914,0.0053189783,0.0000931247],"about_ca_topic_score_codex":0.000003245882,"about_ca_topic_score_gemma":0.00016143586,"teacher_disagreement_score":0.9403169,"about_ca_system_score_codex":0.000012300705,"about_ca_system_score_gemma":0.0000093656945,"threshold_uncertainty_score":0.30544764},"labels":[],"label_agreement":null},{"id":"W1994972523","doi":"10.1016/j.engappai.2015.03.016","title":"Expectation propagation learning of a Dirichlet process mixture of Beta-Liouville distributions for proportional data clustering","year":2015,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; BETA (programming language); Dirichlet distribution; Process (computing); Latent Dirichlet allocation; Applied mathematics; Artificial intelligence; Mathematics; Topic model; Mathematical analysis","score_opus":0.06267223480045654,"score_gpt":0.3369024524358526,"score_spread":0.27423021763539607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994972523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021070594,0.00011458397,0.99683815,0.00015125201,0.000057987996,0.00058209134,0.00005916556,0.000055588473,0.00003411173],"genre_scores_gemma":[0.57063353,0.0000036478093,0.42909214,9.578198e-7,0.000033291548,0.00014422066,0.000080521306,0.000006055499,0.0000056535114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876994,0.000023125976,0.0005573529,0.0002866475,0.00023339155,0.00012954292],"domain_scores_gemma":[0.9983707,0.00011952841,0.0003262366,0.0005146063,0.00061179406,0.00005709958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059740664,0.00010174899,0.00019051932,0.00013290344,0.00005214078,0.000017784263,0.00065724086,0.00005771219,0.0000014267562],"category_scores_gemma":[0.00028078535,0.000102632875,0.000043723783,0.00064260623,0.000052143103,0.00029819182,0.00012015206,0.00009436738,7.567166e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031203916,0.00031704459,0.00008094357,0.00053387386,0.000050044397,1.9380603e-7,0.0025668642,0.21622665,0.042200945,0.5940233,0.000063659834,0.14390531],"study_design_scores_gemma":[0.00002665508,0.00006382501,0.00003203395,0.000041139483,0.000015254286,0.0000018719564,0.00010965984,0.8100724,0.17832607,0.011012636,0.00020243539,0.000096023614],"about_ca_topic_score_codex":0.0000117617055,"about_ca_topic_score_gemma":0.0000022226993,"teacher_disagreement_score":0.5938458,"about_ca_system_score_codex":0.000022950926,"about_ca_system_score_gemma":0.00012430653,"threshold_uncertainty_score":0.4185247},"labels":[],"label_agreement":null},{"id":"W1994981962","doi":"10.1109/ccca.2011.6031397","title":"A probabilistic algorithm for spatial color image segmentation","year":2011,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Image segmentation; Scale-space segmentation; Artificial intelligence; Mixture model; Segmentation-based object categorization; Pattern recognition (psychology); Computer science; Segmentation; Minimum spanning tree-based segmentation; Computer vision; Region growing; Image texture; Statistical model; Algorithm; Mathematics","score_opus":0.03325165093396945,"score_gpt":0.27988789629670413,"score_spread":0.24663624536273468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994981962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000899358,0.000005808837,0.9930914,0.00012371005,0.00023352735,0.00049345894,0.000003552365,0.00010309006,0.0058555156],"genre_scores_gemma":[0.0021180443,7.841769e-7,0.9968298,0.00031805632,0.000050533,0.00012112633,0.000002067014,0.0000056394074,0.0005539473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936,0.000038040198,0.00012498406,0.00023857599,0.000079907986,0.00015848917],"domain_scores_gemma":[0.9995723,0.000046626137,0.000040210234,0.00020809971,0.000077666955,0.00005510467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023911195,0.00007649151,0.00008795977,0.00003181315,0.000055264845,0.000048248305,0.00026050262,0.000033870085,0.000043802178],"category_scores_gemma":[0.000019793752,0.000060689734,0.00004402626,0.000076487275,0.000022426322,0.0002499127,0.000055650846,0.00003114929,0.000015053498],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004061015,0.00005006222,0.0000012869261,0.000008114592,0.0000053843955,0.00000183099,0.00055114954,1.3747037e-7,0.0010980912,0.13881402,0.00045135588,0.8590145],"study_design_scores_gemma":[0.0005287196,0.00025390994,0.000126008,0.0000041770686,0.0000106672815,0.000007838136,0.000009862346,0.69227403,0.030159758,0.27616617,0.00029742808,0.00016142859],"about_ca_topic_score_codex":0.00006912073,"about_ca_topic_score_gemma":0.000013480681,"teacher_disagreement_score":0.8588531,"about_ca_system_score_codex":0.000017658955,"about_ca_system_score_gemma":0.00003659087,"threshold_uncertainty_score":0.24748555},"labels":[],"label_agreement":null},{"id":"W1995050491","doi":"10.1016/j.csda.2007.09.009","title":"Interacting sequential Monte Carlo samplers for trans-dimensional simulation","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Markov chain Monte Carlo; Particle filter; Monte Carlo method; Importance sampling; Sampling (signal processing); Population; Resampling; Algorithm; Inference; Computer science; Convergence (economics); Slice sampling; Bayesian inference; Mathematical optimization; Statistical physics; State space; Hybrid Monte Carlo; Mathematics; Bayesian probability; Statistics; Artificial intelligence; Physics; Kalman filter; Filter (signal processing)","score_opus":0.09360254122331375,"score_gpt":0.4022379766698072,"score_spread":0.30863543544649347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995050491","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007532408,0.000043902673,0.996292,0.00015391715,0.00021971005,0.00017717185,0.0022773524,0.000057809568,0.000024881325],"genre_scores_gemma":[0.34032658,0.0000011638102,0.657285,0.00016690863,0.000082000646,0.0000027342962,0.0021024002,0.000008687476,0.00002456187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784255,0.000103821716,0.00056079775,0.0006868942,0.0004968834,0.00030906804],"domain_scores_gemma":[0.99572414,0.0029752257,0.00023648504,0.0005063374,0.00041626493,0.0001415662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014176384,0.00018042373,0.00030174857,0.0003540729,0.00026940586,0.00020603539,0.0007426753,0.000060103845,0.000029856501],"category_scores_gemma":[0.00030671468,0.00018647934,0.00013215576,0.000795058,0.00004259107,0.00057684747,0.00021517846,0.00012615559,0.0000036950541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028024198,0.00004223674,0.00016086563,0.000012382197,0.0005595876,0.000009866629,0.00024525527,0.8828508,0.000024783116,0.036003776,0.0008967599,0.079165645],"study_design_scores_gemma":[0.0002893369,0.00002293636,0.002940178,0.000006262761,0.000470566,0.0000026388525,0.000004757107,0.95731467,0.0000071313752,0.03737098,0.001370987,0.00019953324],"about_ca_topic_score_codex":0.00023342259,"about_ca_topic_score_gemma":0.00031231006,"teacher_disagreement_score":0.33957335,"about_ca_system_score_codex":0.00006828495,"about_ca_system_score_gemma":0.000093812996,"threshold_uncertainty_score":0.7604407},"labels":[],"label_agreement":null},{"id":"W1995056262","doi":"10.1139/x04-005","title":"A mixture model-based approach to the classification of ecological habitats using Forest Inventory and Analysis data","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mixture model; Random forest; Habitat; Linear discriminant analysis; Multilayer perceptron; Artificial intelligence; Artificial neural network; Perceptron; Ecology; Pattern recognition (psychology); Statistics; Computer science; Mathematics; Biology","score_opus":0.21994075636117544,"score_gpt":0.3814767095572855,"score_spread":0.16153595319611008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995056262","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19218111,0.0003219004,0.80481535,0.0022611145,0.000034284294,0.00016282435,0.00001547205,0.000002016554,0.00020592238],"genre_scores_gemma":[0.7006248,0.0000039970782,0.2992122,0.00009723916,0.000040651485,0.0000025731008,0.000004619694,0.0000048875286,0.0000090304975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806875,0.00037102256,0.0003420949,0.00030296185,0.00050274,0.00041245835],"domain_scores_gemma":[0.99759054,0.00013532476,0.00014180355,0.0008898214,0.00053666014,0.0007058487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043297093,0.00010006013,0.00025181376,0.0009758494,0.00027634142,0.00018454132,0.002092756,0.00010450123,0.0000015468079],"category_scores_gemma":[0.00046334995,0.00006653224,0.000087768065,0.001643014,0.00027089845,0.00029985403,0.00015027364,0.0004916018,5.3146766e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005117463,0.00021827171,0.08256422,0.00008388233,0.00033161326,0.00010575972,0.0025229482,0.6373332,0.0005742623,0.25895154,0.0021629618,0.015100127],"study_design_scores_gemma":[0.0002457305,0.00012543355,0.08827745,0.0000310924,0.00005263377,0.00003135014,0.00004123309,0.88253814,0.000021103662,0.028335683,0.00021589459,0.00008423488],"about_ca_topic_score_codex":0.0016837106,"about_ca_topic_score_gemma":0.051441826,"teacher_disagreement_score":0.5084437,"about_ca_system_score_codex":0.0002115503,"about_ca_system_score_gemma":0.0031291994,"threshold_uncertainty_score":0.96586686},"labels":[],"label_agreement":null},{"id":"W1995559990","doi":"10.1016/j.jmva.2003.09.009","title":"Improving on the mle of a bounded location parameter for spherical distributions","year":2003,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of New Brunswick","funders":"","keywords":"Mathematics; Identity matrix; Multivariate normal distribution; Estimator; Trimmed estimator; Scale parameter; Minimum-variance unbiased estimator; Statistics; Location parameter; Consistent estimator; Minimax estimator; Bounded function; Bias of an estimator; Efficient estimator; Shape parameter; Applied mathematics; Covariance; Estimation theory; Parameter space; Mathematical analysis; Multivariate statistics; Eigenvalues and eigenvectors","score_opus":0.027159846498516885,"score_gpt":0.30030733100644685,"score_spread":0.27314748450792997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995559990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0086495625,0.000050384635,0.99039406,0.0006668787,0.00008323736,0.000082737846,0.0000029809285,0.000004110161,0.000066080866],"genre_scores_gemma":[0.5333587,0.0000024123601,0.4665336,0.00005921795,0.000017861763,0.00000284096,4.5086176e-7,0.0000022125066,0.000022714894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987843,0.00029306806,0.0004396472,0.00013265156,0.00021217285,0.00013817353],"domain_scores_gemma":[0.99789786,0.00075218006,0.000567444,0.00031184583,0.0004123157,0.00005835392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001476424,0.00008584829,0.00029017066,0.00011344499,0.000106609994,0.000072343,0.0003489233,0.00004826527,0.000009693265],"category_scores_gemma":[0.0011647036,0.000050426755,0.00040110172,0.000943597,0.000029519791,0.00016357997,0.000021387945,0.00013152766,5.348934e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012398897,0.0006753393,0.00046759282,0.00002904421,0.0028331552,0.000006106507,0.0009872228,0.0046349107,0.017639497,0.9039672,0.0003178976,0.06831803],"study_design_scores_gemma":[0.0012742366,0.00045850856,0.0031238531,0.00003828914,0.0018091605,0.00001609358,0.000066210974,0.83981085,0.028176293,0.123768605,0.0012124603,0.00024543202],"about_ca_topic_score_codex":0.000030415486,"about_ca_topic_score_gemma":0.0000044063113,"teacher_disagreement_score":0.83517593,"about_ca_system_score_codex":0.000046373756,"about_ca_system_score_gemma":0.00009681366,"threshold_uncertainty_score":0.20563434},"labels":[],"label_agreement":null},{"id":"W1996133602","doi":"10.1007/s00362-007-0361-4","title":"A practical sampling approach for a Bayesian mixture model with unknown number of components","year":2007,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Approximate Bayesian computation; Computation; Computer science; Bayesian probability; Bayesian inference; Mixture model; Multiplicative function; Algorithm; Sampling (signal processing); Markov chain Monte Carlo; Inference; Gibbs sampling; Bayesian statistics; Mathematics; Artificial intelligence","score_opus":0.04849651572576249,"score_gpt":0.3555198557031111,"score_spread":0.30702333997734865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996133602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010671883,0.000007034936,0.9821409,0.00026756947,0.00004895793,0.00033445956,0.000037781294,0.000053275184,0.017003275],"genre_scores_gemma":[0.20570004,0.0000011666343,0.79386175,0.00025062347,0.000030660372,0.00001565454,0.000017911596,0.000017331522,0.00010486268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826264,0.000067166424,0.00032820605,0.0004927212,0.0003673572,0.0004819011],"domain_scores_gemma":[0.99827385,0.00087596866,0.00010484297,0.00036378048,0.00011768712,0.00026388525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073547557,0.00019875317,0.00032789056,0.000045310673,0.00009810593,0.000046515597,0.00030645158,0.00012020927,0.000011645516],"category_scores_gemma":[0.00018799545,0.00014945898,0.000066193694,0.00019954279,0.00015843612,0.0001446997,0.000072173934,0.00023150949,0.0000015024622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015909015,0.00017252032,0.00006257053,0.00007980292,0.000038191232,0.000010824013,0.00021384699,0.00017802333,0.0011542427,0.9782174,0.00025346383,0.019459995],"study_design_scores_gemma":[0.0010321815,0.00014757278,0.000420038,0.000029084165,0.00005789022,0.00008858364,0.000028863822,0.8824132,0.00026223328,0.11444918,0.0007068876,0.00036426567],"about_ca_topic_score_codex":0.000009387675,"about_ca_topic_score_gemma":0.000003873722,"teacher_disagreement_score":0.88223517,"about_ca_system_score_codex":0.000033209344,"about_ca_system_score_gemma":0.00011022244,"threshold_uncertainty_score":0.60947603},"labels":[],"label_agreement":null},{"id":"W1996448267","doi":"10.2307/3315986","title":"Directional mixture models and optimal estimation of the mixing density","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Yonsei University","keywords":"Smoothness; Minimax; Mixing (physics); Gaussian; Mathematics; Nonparametric statistics; von Mises yield criterion; Density estimation; Applied mathematics; Spherical harmonics; Convergence (economics); Euclidean geometry; Mathematical optimization; Mathematical analysis; Statistics; Estimator; Geometry; Physics","score_opus":0.014682811143196984,"score_gpt":0.22787411068473634,"score_spread":0.21319129954153937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996448267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01889556,0.0002034739,0.97992396,0.00036131337,0.00019381702,0.0000333174,0.000035909907,0.0000018987917,0.00035077345],"genre_scores_gemma":[0.35263607,0.000013992591,0.64713997,0.00009462695,0.000026936643,1.4041804e-7,3.5043067e-7,0.0000027913889,0.00008511215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993851,0.00006891861,0.00020861819,0.00007549894,0.00014070122,0.0001211255],"domain_scores_gemma":[0.99932855,0.000076439486,0.00012533029,0.000118727075,0.00015074034,0.00020020019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026645578,0.00006368819,0.000120262535,0.000063151296,0.00012686942,0.000054758955,0.00023415415,0.000039893337,0.000021175376],"category_scores_gemma":[0.000057860252,0.000047831873,0.00003032431,0.00011697721,0.00007704624,0.00020478311,0.000010401338,0.00015082356,3.4275917e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009633723,0.000012340455,0.00031697188,0.000027278904,0.000040807943,0.0000709089,0.0020814175,0.046340793,0.000080280806,0.2835846,0.0049393824,0.6624956],"study_design_scores_gemma":[0.00028103162,0.000059131133,0.0063693374,0.00007689128,0.000032227363,0.00061502046,0.000009616595,0.72934616,0.0004678983,0.26190335,0.00071726757,0.00012205498],"about_ca_topic_score_codex":0.00047313457,"about_ca_topic_score_gemma":0.0007943575,"teacher_disagreement_score":0.6830054,"about_ca_system_score_codex":0.00003777483,"about_ca_system_score_gemma":0.0004924453,"threshold_uncertainty_score":0.19505271},"labels":[],"label_agreement":null},{"id":"W1996771956","doi":"10.1016/j.jmva.2014.03.016","title":"Kendall’s tau for hierarchical data","year":2014,"lang":"de","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Mathematics; Statistics; Econometrics","score_opus":0.051044203766054674,"score_gpt":0.34654611562033677,"score_spread":0.2955019118542821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996771956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040602393,0.0015300303,0.9912445,0.0047909343,0.0016343343,0.00014936231,0.00008389115,0.000014967797,0.00014595894],"genre_scores_gemma":[0.099061735,0.00032788457,0.89685506,0.00063098007,0.0026308172,0.0000019460729,0.000037758615,0.0000276186,0.0004262008],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99497604,0.0012596602,0.0015823072,0.0007804036,0.00079991925,0.00060164597],"domain_scores_gemma":[0.99336594,0.0015696427,0.0016461168,0.0021142876,0.0007816149,0.0005223845],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0085388515,0.00037532405,0.0015514693,0.0009488941,0.00024586706,0.0004758433,0.0040078936,0.0002713505,0.00005823901],"category_scores_gemma":[0.0017419627,0.00029138682,0.0012170969,0.0015706781,0.00010075643,0.00087489985,0.00079380703,0.00070937,0.000017886614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048339576,0.0011589304,0.0004919165,0.0001649103,0.026540816,0.00013519057,0.003219079,0.003945476,0.0018210266,0.079376124,0.014396824,0.8682663],"study_design_scores_gemma":[0.0014881017,0.00035331264,0.0014948864,0.000062703264,0.008522653,0.000022166723,0.0000076512815,0.8913671,0.000115662704,0.02073736,0.07548346,0.0003449891],"about_ca_topic_score_codex":0.000091656926,"about_ca_topic_score_gemma":0.000025851212,"teacher_disagreement_score":0.88742155,"about_ca_system_score_codex":0.00006777934,"about_ca_system_score_gemma":0.0003113968,"threshold_uncertainty_score":0.9999538},"labels":[],"label_agreement":null},{"id":"W1997354990","doi":"10.1007/s11634-013-0139-1","title":"Estimating common principal components in high dimensions","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Convergence (economics); Principal component analysis; Majorization; Orthonormal basis; Mathematical optimization; Simple (philosophy); Cluster analysis; Minification; Computer science; Matrix (chemical analysis); Function (biology); Mathematics; Algorithm; Artificial intelligence","score_opus":0.05393879753402075,"score_gpt":0.3370129092875392,"score_spread":0.28307411175351843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997354990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07764351,0.0004010169,0.9210874,0.0004978869,0.00005549312,0.00010801239,0.00000646554,0.000018275985,0.00018193024],"genre_scores_gemma":[0.54787076,0.00015420822,0.45179597,0.000043152704,0.0000072927282,0.000014922851,0.00010341536,0.0000018505435,0.000008414064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873537,0.0001455837,0.00032929578,0.0004973369,0.00013811929,0.00015428239],"domain_scores_gemma":[0.99863297,0.00012711014,0.00013169053,0.0010329311,0.000025970783,0.00004931675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047461264,0.0000917754,0.00022914135,0.00024656663,0.00006336966,0.000100467354,0.0006831347,0.000039352493,0.00000643834],"category_scores_gemma":[0.000047712176,0.00007898128,0.000019638244,0.0009824861,0.000037053345,0.0017342276,0.00034190482,0.00011204728,0.0000064130104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025797503,0.00015336343,0.12407073,0.00001737058,0.000034562847,0.0000030518884,0.00020462596,0.0011009129,0.0016205398,0.08750453,0.000034172375,0.7852536],"study_design_scores_gemma":[0.00009691018,0.00000404466,0.24393202,0.000012785019,0.000020117228,5.048125e-7,0.00000888804,0.7358992,0.000013899946,0.019754775,0.00018421441,0.00007259391],"about_ca_topic_score_codex":0.000331958,"about_ca_topic_score_gemma":0.00075877865,"teacher_disagreement_score":0.785181,"about_ca_system_score_codex":0.000022992223,"about_ca_system_score_gemma":0.0000086579785,"threshold_uncertainty_score":0.3220763},"labels":[],"label_agreement":null},{"id":"W1997430148","doi":"10.3166/ria.18.383-410","title":"Un algorithme accéléré d'échantillonnage bayésien pour le modèle CART","year":2004,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mod; Cart; Mathematics; Combinatorics; Geography","score_opus":0.06497506700784612,"score_gpt":0.2834681431845764,"score_spread":0.2184930761767303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997430148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012786029,0.01097808,0.93314016,0.027718138,0.0037205063,0.0005679607,0.000028554887,0.00022906502,0.022338927],"genre_scores_gemma":[0.28307536,0.0008907672,0.6746283,0.00085926853,0.0008245666,0.000044523353,0.000007458515,0.00008504852,0.03958469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995095,0.0003535763,0.0010526396,0.0015459603,0.00046157767,0.0014912458],"domain_scores_gemma":[0.9966692,0.00022233343,0.00031403647,0.0018599869,0.0003741963,0.0005602694],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014902245,0.00065218477,0.0007096409,0.00025191164,0.0006209659,0.0005450345,0.001990377,0.00045557084,0.00035903841],"category_scores_gemma":[0.0001900854,0.0007189076,0.00048930245,0.0014455498,0.00039273285,0.0011420208,0.00067499717,0.0007733582,0.0027576059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008062668,0.0005428041,0.000005734438,0.00010079027,0.000047450063,0.00025960518,0.0038270098,0.029736906,0.004166479,0.5519553,0.0010349331,0.40831494],"study_design_scores_gemma":[0.0001786289,0.00018618735,0.000019467025,0.00037119957,0.000041856394,0.00042462497,0.00039144862,0.5255281,0.17468642,0.2688782,0.028623356,0.00067056756],"about_ca_topic_score_codex":0.0010809972,"about_ca_topic_score_gemma":0.00005345899,"teacher_disagreement_score":0.49579114,"about_ca_system_score_codex":0.00021258347,"about_ca_system_score_gemma":0.0007474587,"threshold_uncertainty_score":0.9995262},"labels":[],"label_agreement":null},{"id":"W1998562287","doi":"10.1109/icmla.2012.67","title":"Online Variational Learning for a Dirichlet Process Mixture of Dirichlet Distributions and its Application","year":2012,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet process; Hierarchical Dirichlet process; Dirichlet distribution; Cluster analysis; Latent Dirichlet allocation; Computer science; Categorization; Mixture model; Artificial intelligence; Topic model; Extension (predicate logic); Algorithm; Mathematics; Pattern recognition (psychology); Bayesian probability; Mathematical analysis","score_opus":0.01811751014910415,"score_gpt":0.3069615912138441,"score_spread":0.2888440810647399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998562287","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004146276,0.00033903302,0.9937773,0.0010530727,0.000049718405,0.00028345422,0.000036463425,0.000054318003,0.000260375],"genre_scores_gemma":[0.60488033,0.000007778521,0.39468992,0.000076284225,0.00008657417,0.00005459585,0.00005725101,0.000004043395,0.00014324264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928474,0.00004420113,0.00016918693,0.00019151357,0.00012371506,0.00018663883],"domain_scores_gemma":[0.9993344,0.00015657414,0.000106684725,0.00013276405,0.0001853583,0.0000842294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036554932,0.000087833294,0.00012646227,0.000042523665,0.00010608278,0.00002070279,0.00018964184,0.0000655524,0.000004350097],"category_scores_gemma":[0.00012574982,0.00007181673,0.00003311377,0.00024943356,0.000014501389,0.00035333133,0.000061726416,0.00008584794,0.0000010164623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004733302,0.00021264223,0.001010253,0.00006213534,0.000015201822,3.9110954e-8,0.00041733292,0.000030979518,0.0028332097,0.96359915,0.00017971662,0.031634606],"study_design_scores_gemma":[0.0008590524,0.00013684065,0.030291976,0.000030512594,0.000060988736,0.000023393291,0.000034398006,0.8207799,0.010139111,0.12094408,0.016241688,0.00045800992],"about_ca_topic_score_codex":0.0000022939869,"about_ca_topic_score_gemma":0.0000011466598,"teacher_disagreement_score":0.84265506,"about_ca_system_score_codex":0.000011331204,"about_ca_system_score_gemma":0.00003314258,"threshold_uncertainty_score":0.29286012},"labels":[],"label_agreement":null},{"id":"W1999271084","doi":"10.1007/s10260-006-0012-x","title":"Bounds for the Bayes Error in Classification: A Bayesian Approach Using Discriminant Analysis","year":2006,"lang":"en","type":"article","venue":"Statistical Methods & Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Bhattacharyya distance; Linear discriminant analysis; Bayes' theorem; Mathematics; Posterior probability; Bayes error rate; Optimal discriminant analysis; Statistics; Discriminant; Pattern recognition (psychology); Bayesian probability; Naive Bayes classifier; Prior probability; Classification rule; Probability distribution; Artificial intelligence; Dirichlet distribution; Bayes classifier; Computer science","score_opus":0.07805381755449632,"score_gpt":0.4176665682304711,"score_spread":0.3396127506759748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999271084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000052084874,0.00026857387,0.9954641,0.0011950268,0.00005711137,0.0011155123,0.000099708755,0.000072171606,0.0017226222],"genre_scores_gemma":[0.034152616,0.0000062998083,0.9634813,0.00012761701,0.000117537544,0.00192979,0.000054669148,0.000019120003,0.000111047055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717635,0.0007335278,0.00060673564,0.0007985002,0.00023210768,0.0004527693],"domain_scores_gemma":[0.9952524,0.0032094938,0.0001724558,0.0011292339,0.00012582795,0.000110592686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026357188,0.00022511893,0.00040451298,0.00027576546,0.0004692224,0.00025213088,0.00092259597,0.00010871395,0.000012055348],"category_scores_gemma":[0.00018474275,0.00016306686,0.00017455473,0.0023319954,0.00022943686,0.00016107266,0.00011907083,0.0002139361,0.0000019782958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038391267,0.00011820826,0.000082318016,0.000017038727,0.0000435819,3.3454285e-7,0.00008753375,0.00026571527,0.0004947774,0.801937,0.00010316504,0.19684653],"study_design_scores_gemma":[0.00010575425,0.000009290554,0.0064703966,0.0000022064885,0.00023875842,0.0000033741064,0.000037495625,0.61849284,0.000046690762,0.37131837,0.0031285745,0.00014622763],"about_ca_topic_score_codex":0.00026664636,"about_ca_topic_score_gemma":0.000080319005,"teacher_disagreement_score":0.6182271,"about_ca_system_score_codex":0.00009467694,"about_ca_system_score_gemma":0.00012059073,"threshold_uncertainty_score":0.66496736},"labels":[],"label_agreement":null},{"id":"W1999456916","doi":"10.1023/a:1004148814661","title":"Joint Distribution of Rises and Falls","year":2000,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Joint probability distribution; Markov chain; Applied mathematics; Joint (building); Distribution (mathematics); Marginal distribution; Parametric statistics; Statistical inference; Generating function; Statistics; Combinatorics; Random variable; Mathematical analysis","score_opus":0.05618700145579095,"score_gpt":0.312606646524457,"score_spread":0.2564196450686661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999456916","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045191146,0.00007836971,0.9525996,0.0004785374,0.00005477478,0.00010429886,0.00012380266,0.0000075767143,0.0013619196],"genre_scores_gemma":[0.4430272,0.00009535235,0.5567741,0.00004497471,0.000006406405,0.0000013109284,0.0000015960048,0.0000026520859,0.000046434685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99908525,0.000041990177,0.00042535298,0.00011218886,0.00022484308,0.000110406814],"domain_scores_gemma":[0.9991374,0.00015453412,0.00018278386,0.00036617383,0.00010995229,0.000049172733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036446165,0.0000855709,0.00028642424,0.00001856522,0.000034440844,0.000011832674,0.0003369515,0.000040784416,0.0000135932505],"category_scores_gemma":[0.000280701,0.000055766737,0.000057502155,0.00012772006,0.00034463266,0.00012972273,0.00010583305,0.000059655984,0.0000012558216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037725024,0.00011547094,0.0000063086795,0.00022785904,0.000018160972,9.320671e-7,0.00023566668,0.000023665047,0.00044432702,0.9355634,0.00045899607,0.06290147],"study_design_scores_gemma":[0.00013527331,0.00009085567,0.0013790603,0.0002481528,0.000024072144,0.00001146853,0.0000065597687,0.012245309,0.021049578,0.96409136,0.0006276992,0.00009058854],"about_ca_topic_score_codex":0.000022103091,"about_ca_topic_score_gemma":0.0000012963837,"teacher_disagreement_score":0.39783606,"about_ca_system_score_codex":0.0000026473217,"about_ca_system_score_gemma":0.00003554917,"threshold_uncertainty_score":0.22741015},"labels":[],"label_agreement":null},{"id":"W2000012135","doi":"10.1016/j.spa.2006.08.001","title":"Markov jump random c.d.f.’s and their posterior distributions","year":2006,"lang":"en","type":"article","venue":"Stochastic Processes and their Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Jump; Markov chain; Markov process; Statistical physics; Jump process; Posterior probability; Variable-order Markov model; Markov model; Applied mathematics; Combinatorics; Statistics; Bayesian probability; Physics","score_opus":0.006595683344180379,"score_gpt":0.22692993495875216,"score_spread":0.2203342516145718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000012135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070423505,0.0025331916,0.99397665,0.0012128447,0.00002987622,0.00049957394,0.000103521874,0.0001251571,0.00081494474],"genre_scores_gemma":[0.9463416,0.000023849594,0.05275986,0.00011145761,0.0001069427,0.00049100467,0.000027926637,0.000011422932,0.00012593815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990613,0.000026099588,0.00020149033,0.00041471858,0.000059804104,0.0002366035],"domain_scores_gemma":[0.9990834,0.00025337024,0.000081224214,0.0003530682,0.00012624348,0.00010268266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016626611,0.0001939938,0.0002083896,0.00005699458,0.00040749498,0.00019460595,0.00030396215,0.000059602295,0.00000301802],"category_scores_gemma":[0.000024416879,0.00013457889,0.00003564037,0.0003600086,0.00013415664,0.00019518031,0.0001687924,0.0000972339,0.0000028581344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018579658,0.00014295794,0.000010147426,0.00014933568,0.00003100399,4.2598526e-7,0.0006239215,0.0000042032616,0.002608299,0.71787703,0.00021286601,0.27832127],"study_design_scores_gemma":[0.00080773723,0.000050527462,0.00023355773,0.00004772575,0.00002235809,0.00011150514,0.00007180611,0.011165905,0.0009942644,0.98344004,0.0026928065,0.00036176364],"about_ca_topic_score_codex":0.000024479681,"about_ca_topic_score_gemma":0.000019689158,"teacher_disagreement_score":0.94563735,"about_ca_system_score_codex":0.000010796352,"about_ca_system_score_gemma":0.00007828106,"threshold_uncertainty_score":0.5487968},"labels":[],"label_agreement":null},{"id":"W2000356105","doi":"10.1002/jae.587","title":"Bayesian semiparametric estimation of discrete duration models: an application of the dirichlet process prior","year":2001,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Dirichlet process; Estimator; Dirichlet distribution; Econometrics; Inference; Duration (music); Semiparametric model; Parametric statistics; Bayesian probability; Mathematics; Nonparametric statistics; Statistics; Hazard; Computer science; Artificial intelligence","score_opus":0.02291918336677499,"score_gpt":0.27456853615045623,"score_spread":0.2516493527836812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000356105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071416706,0.00012248203,0.92634404,0.00015414566,0.000099846955,0.00027391504,0.000002712072,0.000010339296,0.0015757922],"genre_scores_gemma":[0.7188233,0.00005797228,0.2810195,0.00003800786,0.00003989357,0.000006718754,0.0000011309506,0.000008086421,0.000005349501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981753,0.000052222822,0.0010135116,0.00022261411,0.0003752613,0.0001610912],"domain_scores_gemma":[0.997009,0.00016181813,0.0019401113,0.0005094171,0.00027888722,0.00010080659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014006511,0.00013686289,0.00036737949,0.0009566473,0.000072242474,0.00006156919,0.0009799183,0.00010392527,0.0000027266756],"category_scores_gemma":[0.00012000599,0.000100119054,0.000118919685,0.0038093384,0.00004699805,0.0010064227,0.00006952774,0.00019538596,6.1663496e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006300122,0.0002650314,0.0006883578,0.00010273792,0.00004461524,7.111e-7,0.0011988212,0.22544296,0.0006224161,0.10796592,0.000024344232,0.6635811],"study_design_scores_gemma":[0.00032781862,0.00010582831,0.0016687352,0.000014324444,0.00003059043,0.000022803368,0.000037026013,0.8331958,0.0043469463,0.16010426,0.000038038404,0.000107834334],"about_ca_topic_score_codex":0.0000041426492,"about_ca_topic_score_gemma":0.0000013244922,"teacher_disagreement_score":0.66347325,"about_ca_system_score_codex":0.00007719642,"about_ca_system_score_gemma":0.00012374423,"threshold_uncertainty_score":0.40827364},"labels":[],"label_agreement":null},{"id":"W2001005965","doi":"10.1002/env.707","title":"A mixture model approach to analyzing major element chemistry data of the Changjiang (Yangtze River)","year":2005,"lang":"en","type":"article","venue":"Environmetrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; CancerCare Manitoba","funders":"","keywords":"Discretization; Yangtze river; Sampling (signal processing); Environmental science; Monte Carlo method; Drainage basin; Hydrology (agriculture); Bayesian probability; Posterior probability; Statistics; Mathematics; Soil science; China; Geology; Geography; Computer science; Cartography; Geotechnical engineering","score_opus":0.03580947390202155,"score_gpt":0.25712101216819444,"score_spread":0.2213115382661729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001005965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029843638,0.0007141335,0.9927743,0.00083117606,0.000049708364,0.00020381753,0.00004367153,0.000026982101,0.0023718674],"genre_scores_gemma":[0.13151029,0.000045008077,0.866805,0.00048512884,0.00011628807,0.000009220814,0.000009838781,0.000013850815,0.0010053441],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832255,0.00006383705,0.00026357485,0.0005967295,0.00043900686,0.0003142809],"domain_scores_gemma":[0.9973667,0.00005259245,0.00013943588,0.0022946498,0.000016071157,0.00013051304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007402145,0.00017537648,0.00021045055,0.00012210452,0.000102398546,0.000042774485,0.0029614903,0.000104226965,0.0000087401095],"category_scores_gemma":[0.00011003078,0.00013132641,0.0000852442,0.0012324919,0.000051244333,0.0002601283,0.00190668,0.00022874784,0.000008961638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013582828,0.0009888688,0.0013488631,0.00018062706,0.00016975986,0.000004386105,0.0046857586,0.044817172,0.023271095,0.020044643,0.017031955,0.8874433],"study_design_scores_gemma":[0.00024999297,0.000011242802,0.00090356235,0.000013755577,0.000039357754,0.000006758824,0.000010944661,0.973822,0.0114309415,0.0011918212,0.012047624,0.000271986],"about_ca_topic_score_codex":0.000007752474,"about_ca_topic_score_gemma":9.3390827e-7,"teacher_disagreement_score":0.92900485,"about_ca_system_score_codex":0.0000739643,"about_ca_system_score_gemma":0.000036332644,"threshold_uncertainty_score":0.5503235},"labels":[],"label_agreement":null},{"id":"W2001189174","doi":"10.7557/3.2848","title":"Visibility of St Lawrence belugas to aerial photography, estimated by direct observation","year":2002,"lang":"en","type":"article","venue":"NAMMCO Scientific Publications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Rimouski; Fisheries and Oceans Canada","funders":"","keywords":"Aerial survey; Population; Visibility; Geography; Secchi disk; Range (aeronautics); Aerial photography; Turbidity; Environmental science; Remote sensing; Ecology; Biology; Meteorology; Demography","score_opus":0.06014418515910193,"score_gpt":0.3014744625847675,"score_spread":0.2413302774256656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001189174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025360195,0.00012163614,0.9653968,0.0030118877,0.0010025454,0.00047863263,0.00019378308,0.0002861856,0.0041483035],"genre_scores_gemma":[0.43739912,0.0000060120874,0.55914557,0.00018348721,0.000037286332,0.00012168891,0.0000782004,0.000009965433,0.003018708],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765843,0.00015256845,0.00045832258,0.00085505226,0.00052172283,0.00035391416],"domain_scores_gemma":[0.9969324,0.00012603705,0.0001886359,0.0015734903,0.00092665694,0.00025282215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014852318,0.00015086966,0.00020797545,0.00037923272,0.00041424937,0.00066600926,0.0014846617,0.00008320015,0.00014418343],"category_scores_gemma":[0.0007102431,0.00014579247,0.00009700674,0.004792878,0.0002022272,0.0010042121,0.00020751593,0.00010748237,0.000041169627],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068623044,0.0011742831,0.0032185437,0.000034483048,0.000035810805,4.3449322e-7,0.0018136884,0.00005424153,0.1328611,0.16791096,0.53135186,0.16153777],"study_design_scores_gemma":[0.0012776029,0.0003003942,0.041672587,0.00011149922,0.00006194364,0.000009206226,0.000027807955,0.4206478,0.09183317,0.055069458,0.38753426,0.0014542805],"about_ca_topic_score_codex":0.000073685056,"about_ca_topic_score_gemma":0.000039676343,"teacher_disagreement_score":0.42059356,"about_ca_system_score_codex":0.000044505727,"about_ca_system_score_gemma":0.000078864956,"threshold_uncertainty_score":0.64223427},"labels":[],"label_agreement":null},{"id":"W2001295690","doi":"10.1007/s11009-008-9095-1","title":"On the Number of i.i.d. Samples Required to Observe All of the Balls in an Urn","year":2008,"lang":"en","type":"article","venue":"Methodology And Computing In Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Combinatorics; Type (biology); Markov chain; Random variable; Large deviations theory; Statistics","score_opus":0.22054668214366438,"score_gpt":0.3569695720804086,"score_spread":0.1364228899367442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001295690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5199142,0.000011048033,0.47892803,0.00037908676,0.000055593584,0.00029840643,7.372789e-7,0.000009782397,0.0004031147],"genre_scores_gemma":[0.51934326,0.0000012057377,0.48022252,0.0004114445,0.000007195021,0.00000939087,1.5356657e-7,0.0000028547117,0.0000019862828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953059,0.003247571,0.0005206877,0.000509901,0.00015050979,0.00026541072],"domain_scores_gemma":[0.9947844,0.0040849485,0.00017833571,0.00086103467,0.00004457326,0.000046699504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008371898,0.0001473561,0.0004321065,0.000046550358,0.000083587525,0.000008336463,0.0009159742,0.0001382922,0.000004094774],"category_scores_gemma":[0.0006658999,0.000090538175,0.000056231238,0.00047237225,0.00030756966,0.000036625897,0.00047156395,0.00031951827,5.8233996e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009946157,0.00020493445,0.055617508,0.00004401871,0.00001053124,0.0000013405607,0.006839517,0.0011212897,0.0035430829,0.8961215,0.000014033829,0.036382753],"study_design_scores_gemma":[0.00026619024,0.000056068966,0.26527926,0.00003015208,0.000003491257,0.000010566258,0.000025333806,0.0052764285,0.0052632014,0.7236638,0.000014987967,0.00011049136],"about_ca_topic_score_codex":0.000107122796,"about_ca_topic_score_gemma":0.00007661371,"teacher_disagreement_score":0.20966177,"about_ca_system_score_codex":0.00002474866,"about_ca_system_score_gemma":0.000059173624,"threshold_uncertainty_score":0.36920395},"labels":[],"label_agreement":null},{"id":"W2002026546","doi":"10.1177/0962280212453891","title":"Meta-analysis using Dirichlet process","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Dirichlet process; Latent Dirichlet allocation; Hierarchical Dirichlet process; Dirichlet distribution; Generalized Dirichlet distribution; Computer science; Bayesian probability; Process (computing); Marginal likelihood; Statistics; Econometrics; Data mining; Mathematics; Topic model; Dirichlet's energy; Information retrieval","score_opus":0.4948803650150258,"score_gpt":0.630971933392843,"score_spread":0.13609156837781716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002026546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007816501,0.0018750445,0.9918189,0.0013445152,0.00015717714,0.00023650359,0.0000107406195,0.000043952394,0.0044349744],"genre_scores_gemma":[0.02442529,0.000030257506,0.9747289,0.00043941877,0.0001301363,0.000088618224,0.000002381294,0.000016741193,0.00013827636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.980588,0.013076015,0.00071644725,0.0007521882,0.0032778047,0.0015895115],"domain_scores_gemma":[0.9807393,0.016575923,0.000069323774,0.00091966754,0.00032683756,0.0013689412],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058727,0.00022494895,0.0011721717,0.0008780709,0.00017841606,0.00013225336,0.0017143138,0.00028522997,0.0027699247],"category_scores_gemma":[0.019036142,0.0001580214,0.00032917573,0.00526842,0.00052219746,0.00036979522,0.0007024528,0.0016684253,0.00002841638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010670499,0.00027689483,0.00022510887,0.00005560078,0.005549999,0.000097513155,0.0007766966,0.0000097397515,0.00007002739,0.6479138,0.00018810036,0.3448258],"study_design_scores_gemma":[0.00024497314,0.00006877726,0.00083179714,0.000009289601,0.0067778775,0.000026288648,0.000053427946,0.38855582,0.00052885804,0.60121447,0.0013259761,0.0003624685],"about_ca_topic_score_codex":0.00010646818,"about_ca_topic_score_gemma":0.000009614274,"teacher_disagreement_score":0.38854608,"about_ca_system_score_codex":0.000101010235,"about_ca_system_score_gemma":0.00039060047,"threshold_uncertainty_score":0.9981417},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01577668605565137,"score_gpt":0.280924284971499,"score_spread":0.26514759891584766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003144493","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008619989,0.000048220903,0.9895879,0.0010239475,0.00058161444,0.00006354139,0.000031371477,0.000008646407,0.000034765464],"genre_scores_gemma":[0.30874178,0.0000063231523,0.6908777,0.00027022537,0.00008890734,8.2557466e-7,0.0000040890836,0.000003878346,0.0000062905797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991261,0.00004425117,0.0003422043,0.00011421289,0.00024429226,0.00012898598],"domain_scores_gemma":[0.9984448,0.0007855499,0.0002186642,0.00006470796,0.00033603664,0.00015023284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046658705,0.00009165982,0.00020303781,0.00010145828,0.00012627366,0.000110095054,0.00023814013,0.000061974846,0.0000023745495],"category_scores_gemma":[0.00010157215,0.00007283157,0.000062406536,0.00010655243,0.000065940294,0.00014944172,0.000056040775,0.0003089091,2.4815898e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029698207,0.00006147537,0.00023095138,0.000028217111,0.0000366881,0.000016732549,0.00014370942,0.0003278636,0.00068636367,0.901702,0.0010620512,0.095674254],"study_design_scores_gemma":[0.00042879916,0.00013309147,0.0064019216,0.000013772244,0.000011097991,0.00019123286,0.0000014157368,0.2819791,0.000018074414,0.7092867,0.0014566922,0.000078066696],"about_ca_topic_score_codex":0.0000011021642,"about_ca_topic_score_gemma":0.0000022841048,"teacher_disagreement_score":0.30012178,"about_ca_system_score_codex":0.0000037240584,"about_ca_system_score_gemma":0.000038908776,"threshold_uncertainty_score":0.29699853},"labels":[],"label_agreement":null},{"id":"W2003307016","doi":"10.1016/j.spl.2008.01.056","title":"A variance component test for mixed hidden Markov models","year":2008,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Component (thermodynamics); Hidden Markov model; Variable-order Markov model; Markov model; Statistics; Covariate; Markov chain; Variance components; Variance (accounting); Random effects model; Econometrics; Test (biology); Artificial intelligence; Computer science","score_opus":0.032919297261613606,"score_gpt":0.25752666972937194,"score_spread":0.22460737246775833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003307016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022022908,0.000039115002,0.9912802,0.0043809367,0.00043142398,0.00096573913,0.00031956928,0.0001644554,0.00021627898],"genre_scores_gemma":[0.014464547,0.000010939168,0.98267186,0.0024371422,0.00009110986,0.00017771768,0.000028362687,0.000023011291,0.00009531036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997601,0.00020373423,0.00047594382,0.0007992457,0.00035825055,0.000561832],"domain_scores_gemma":[0.9974063,0.0010891524,0.00015434754,0.000975501,0.00018838173,0.00018632549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074885716,0.00027727446,0.00037177917,0.00006394972,0.00029827346,0.00009387113,0.00087808305,0.0000793892,0.000006518078],"category_scores_gemma":[0.00031181736,0.00026856066,0.000106005165,0.00021162549,0.00023318792,0.0003382431,0.00019551703,0.00020282809,0.000009833594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027477454,0.00025161848,0.0001953484,0.00014103226,0.000031052165,0.000042878735,0.0008233363,0.00003586988,0.0026231527,0.91325676,0.03302383,0.049547613],"study_design_scores_gemma":[0.00051857973,0.0000919967,0.0013095088,0.000016685513,0.0000151090635,0.000036458492,3.641918e-7,0.13307923,0.00024553298,0.8634878,0.0008628372,0.0003358961],"about_ca_topic_score_codex":0.000045675268,"about_ca_topic_score_gemma":0.000014019943,"teacher_disagreement_score":0.13304336,"about_ca_system_score_codex":0.00012883895,"about_ca_system_score_gemma":0.0001389725,"threshold_uncertainty_score":0.99997663},"labels":[],"label_agreement":null},{"id":"W2004213020","doi":"10.2307/3315964","title":"Smooth estimates of normal mixtures","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Component (thermodynamics); Variance (accounting); Inverse; Mathematics; Parameter space; Statistics; Boundary (topology); Space (punctuation); Variance components; Mathematical analysis; Physics; Computer science; Geometry","score_opus":0.01316271469102046,"score_gpt":0.2380873497194269,"score_spread":0.22492463502840646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004213020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017182841,0.0005304226,0.99451715,0.00022284598,0.00023522011,0.000026979778,0.00007976086,0.0000032807282,0.0026660715],"genre_scores_gemma":[0.10666767,0.000036094443,0.8928781,0.00019995584,0.000060905408,2.0588952e-7,0.0000011282299,0.000006424708,0.0001495169],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916726,0.00004345128,0.0003327514,0.00008073806,0.00014859675,0.00022721091],"domain_scores_gemma":[0.99886954,0.00011633192,0.00015729447,0.00017430577,0.00024675875,0.00043577174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026960412,0.00008798858,0.00019955591,0.00014402083,0.00006291367,0.00006277335,0.00051872525,0.000044086137,0.00028697427],"category_scores_gemma":[0.00011148082,0.00007663105,0.00003905357,0.00018290922,0.000085113476,0.00017286831,0.000007226357,0.00014810672,0.0000052765213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005900722,0.000012556481,0.0005019283,0.000023415061,0.000026834865,0.0004009632,0.0008191799,0.00016720161,0.00012419521,0.15078413,0.020783985,0.82634974],"study_design_scores_gemma":[0.0014848846,0.001072458,0.021395784,0.00032184928,0.00013756189,0.0014662796,0.00003509157,0.040258225,0.0062225,0.8336994,0.09308752,0.00081847137],"about_ca_topic_score_codex":0.0010482161,"about_ca_topic_score_gemma":0.0012257551,"teacher_disagreement_score":0.82553124,"about_ca_system_score_codex":0.00002957615,"about_ca_system_score_gemma":0.00095036643,"threshold_uncertainty_score":0.3142167},"labels":[],"label_agreement":null},{"id":"W2004939947","doi":"10.1016/j.csda.2007.04.018","title":"Mixture cure models for multivariate survival data","year":2007,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Censoring (clinical trials); Statistics; Covariate; Multivariate statistics; Bivariate analysis; Jackknife resampling; Mathematics; Survival analysis; Marginal model; Survival function; Marginal distribution; Random effects model; Multivariate analysis; Econometrics; Correlation; Regression analysis; Medicine; Random variable; Internal medicine","score_opus":0.10922552757236624,"score_gpt":0.3880269756108853,"score_spread":0.27880144803851903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004939947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007677857,0.00017056067,0.9775237,0.00042117308,0.00029679228,0.00022471341,0.021117743,0.00008623282,0.00015142634],"genre_scores_gemma":[0.011569146,0.000022142238,0.9503093,0.00030553722,0.00018297756,0.0000045227944,0.037477225,0.000019514662,0.000109658904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673176,0.00016091952,0.0006215435,0.0013559243,0.00067393394,0.00045589337],"domain_scores_gemma":[0.99407005,0.0019222992,0.00028217694,0.003008758,0.00049377553,0.00022294796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029783328,0.00026720008,0.0004850928,0.00033288077,0.00029506095,0.00032820975,0.0040854244,0.00010970263,0.000019241237],"category_scores_gemma":[0.00031327392,0.0002550517,0.00009374362,0.001319437,0.000065150736,0.0011540384,0.0018086156,0.00019031687,0.000009110466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022080636,0.00011068461,0.0001177793,0.00002524557,0.001126122,0.000021849559,0.00013859748,0.065331675,0.0000066490475,0.8140328,0.020848067,0.098218426],"study_design_scores_gemma":[0.00025578044,0.000012013437,0.0012058943,0.0000035902217,0.000494224,0.0000020210052,0.00000265947,0.6687246,0.0000014341306,0.32581705,0.003271025,0.00020967904],"about_ca_topic_score_codex":0.00024072436,"about_ca_topic_score_gemma":0.0004154935,"teacher_disagreement_score":0.60339296,"about_ca_system_score_codex":0.000039163206,"about_ca_system_score_gemma":0.000182942,"threshold_uncertainty_score":0.99999017},"labels":[],"label_agreement":null},{"id":"W2005212382","doi":"10.1002/env.986","title":"The multi‐clump finite mixture distribution and model selection","year":2009,"lang":"en","type":"article","venue":"Environmetrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Nanyang Technological University","keywords":"Model selection; Selection (genetic algorithm); Multinomial distribution; Mixture model; Statistics; Distribution (mathematics); Sample (material); Mathematics; Computer science; Econometrics; Applied mathematics; Artificial intelligence; Physics","score_opus":0.013077934367745606,"score_gpt":0.23919093560980162,"score_spread":0.22611300124205602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005212382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012983931,0.00081551896,0.9963367,0.0011449241,0.00008038241,0.000096737895,0.000004895439,0.00005721383,0.0001652261],"genre_scores_gemma":[0.37662286,0.00072469865,0.6214004,0.0004006313,0.000049017286,0.0000040504783,0.0000055031674,0.0000054864686,0.000787367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990977,0.00008077491,0.00013349754,0.00028253798,0.00018047947,0.00022499003],"domain_scores_gemma":[0.9993731,0.00018359443,0.000059765174,0.00028746974,0.000014555807,0.00008156154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047254047,0.00011513682,0.000091555055,0.000060531034,0.00034807247,0.00014171496,0.00029608456,0.0001023194,8.2848504e-7],"category_scores_gemma":[0.00018555885,0.000082705265,0.00003988415,0.0005796783,0.000038134443,0.0002284214,0.00007115062,0.00021218903,0.0000064418055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004204763,0.00006312721,0.00018852169,0.00000210689,0.0000055422,0.0000019029495,0.00013842352,0.002357075,0.0006287074,0.07791201,0.0011484383,0.91754997],"study_design_scores_gemma":[0.00017017756,0.00004832966,0.006157708,0.000001980641,0.0000060947464,0.0000075781586,0.0000012330561,0.95480025,0.00060819375,0.028505176,0.009570915,0.0001223359],"about_ca_topic_score_codex":0.0000017859525,"about_ca_topic_score_gemma":0.0000010632418,"teacher_disagreement_score":0.9524432,"about_ca_system_score_codex":0.00004247766,"about_ca_system_score_gemma":0.000013225411,"threshold_uncertainty_score":0.33726227},"labels":[],"label_agreement":null},{"id":"W2005265490","doi":"10.1111/j.1467-842x.2010.00583.x","title":"A SEMIPARAMETRIC BAYESIAN APPROACH TO NETWORK MODELLING USING DIRICHLET PROCESS PRIOR DISTRIBUTIONS","year":2010,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Dirichlet process; Dirichlet distribution; Hierarchical Dirichlet process; Mathematics; Parametric statistics; Cluster analysis; Process (computing); Latent Dirichlet allocation; Bayesian network; Data mining; Bayesian probability; Computer science; Mathematical optimization; Statistics; Artificial intelligence; Topic model","score_opus":0.0383757490922231,"score_gpt":0.31041086788791455,"score_spread":0.2720351187956915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005265490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005838748,0.000027706245,0.9925968,0.0005632806,0.0006140059,0.00018315938,0.00006187628,0.000023710865,0.00009071809],"genre_scores_gemma":[0.12044515,0.000012610932,0.87815785,0.00009542833,0.00062167033,0.0000015144251,0.0000069865278,0.00001852819,0.00064023427],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978207,0.00009098323,0.000710763,0.0003112968,0.00047582603,0.0005904514],"domain_scores_gemma":[0.9978379,0.0001736849,0.0004811001,0.00037466388,0.00037549838,0.00075714116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081697234,0.00024810585,0.0004354137,0.00023465791,0.00020850009,0.00033342678,0.0008634417,0.00014550662,0.000010218815],"category_scores_gemma":[0.00013842099,0.00020971868,0.00009630967,0.0012140636,0.000044746816,0.00038416652,0.00007281692,0.0007955526,0.0000029544954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014346438,0.00093988946,0.0045938743,0.00018548312,0.0003434559,0.00032704385,0.00420674,0.37982154,0.0010657549,0.2752124,0.18027937,0.152881],"study_design_scores_gemma":[0.0013818358,0.00047468836,0.0012422159,0.00018995236,0.00025271298,0.0015745537,0.000034852517,0.6461642,0.00038381046,0.33066463,0.016742451,0.0008941022],"about_ca_topic_score_codex":0.00005168659,"about_ca_topic_score_gemma":0.0000061289193,"teacher_disagreement_score":0.26634267,"about_ca_system_score_codex":0.000047195594,"about_ca_system_score_gemma":0.00043234148,"threshold_uncertainty_score":0.855208},"labels":[],"label_agreement":null},{"id":"W2006123051","doi":"10.1080/10485250903499667","title":"Spearman's footrule and Gini's gamma: a review with complements","year":2010,"lang":"en","type":"review","venue":"Journal of nonparametric statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Mathematics; Jackknife resampling; Independence (probability theory); Statistics; Asymptotic distribution; Multivariate statistics; Sample (material); Econometrics; Variance (accounting); Applied mathematics; Estimator","score_opus":0.04910565724919263,"score_gpt":0.37263355474698867,"score_spread":0.32352789749779604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006123051","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4704777e-8,0.5007446,0.49850133,0.00002884406,0.00027032424,0.00024159337,0.00004564429,0.0000059664344,0.00016170475],"genre_scores_gemma":[8.9496915e-8,0.5106852,0.48902646,0.00010559645,0.00009810353,0.000003467747,0.0000035944802,0.000019294943,0.00005817341],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996764,0.00038993178,0.0013549346,0.00036550922,0.0007652208,0.00036037725],"domain_scores_gemma":[0.9948742,0.0013360826,0.00237226,0.0006048379,0.00047245456,0.00034016257],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001729682,0.0004581743,0.0025075772,0.0007156324,0.00007753151,0.0002043156,0.0011652542,0.00017587886,0.000026706652],"category_scores_gemma":[0.0006221071,0.00029334187,0.00022409006,0.0014636797,0.000092916,0.00020890695,0.00022194764,0.0013262209,0.000010228099],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019385595,0.00004606614,0.0000015815846,0.0102315955,0.00012373422,0.00026175316,0.000011525027,5.077761e-8,2.1306123e-8,0.008600602,0.007879686,0.97284144],"study_design_scores_gemma":[0.0003091552,0.00041338318,0.0000074246373,0.015715463,0.0011918051,0.0029031092,5.6491825e-7,0.00012892277,1.2306621e-7,0.0034838978,0.9755028,0.00034335456],"about_ca_topic_score_codex":0.0000032834348,"about_ca_topic_score_gemma":0.0000013977993,"teacher_disagreement_score":0.9724981,"about_ca_system_score_codex":0.00006680628,"about_ca_system_score_gemma":0.00059675303,"threshold_uncertainty_score":0.9999519},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.02999587880155407,"score_gpt":0.2541209905354787,"score_spread":0.22412511173392463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006213144","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12693083,0.0022910603,0.8666398,0.0038848154,0.000116677395,0.00007124342,0.00003003076,0.0000023552839,0.000033221633],"genre_scores_gemma":[0.4137881,0.00004540975,0.5857961,0.00019534823,0.0001272059,0.0000014043063,0.000007448361,0.000002974259,0.00003597051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906206,0.00006958582,0.0002630839,0.00023254182,0.00016880255,0.00020389962],"domain_scores_gemma":[0.9989508,0.00037093586,0.00019323743,0.0002595369,0.00005334799,0.00017218769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078485085,0.00009397274,0.00018777823,0.0001274962,0.0006403103,0.0006934235,0.0006517142,0.000027077882,0.0000044945336],"category_scores_gemma":[0.000097887474,0.000052195042,0.000031370688,0.00047418373,0.00028225695,0.00046156265,0.000033610722,0.000052170013,4.9201102e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002638035,0.000013195837,0.46485645,0.000020278132,0.00030818026,0.000029581824,0.00089013256,0.0003182657,0.000065885055,0.033355463,0.006291269,0.49382493],"study_design_scores_gemma":[0.00037628695,0.0002949963,0.38118228,0.000045263358,0.00031961355,0.000048559603,0.0001537624,0.45527416,0.000012230172,0.13690262,0.025099933,0.00029029153],"about_ca_topic_score_codex":0.021346593,"about_ca_topic_score_gemma":0.13462868,"teacher_disagreement_score":0.49353465,"about_ca_system_score_codex":0.000008971033,"about_ca_system_score_gemma":0.00026311763,"threshold_uncertainty_score":0.98517036},"labels":[],"label_agreement":null},{"id":"W2007402758","doi":"10.1198/106186001317114901","title":"Computational Algorithms for Censored-Data Problems Using Intersection Graphs","year":2001,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Censoring (clinical trials); Mathematics; Algorithm; Bivariate analysis; Intersection (aeronautics); Intersection graph; Graph; Nonparametric statistics; Computer science; Mathematical optimization; Discrete mathematics; Statistics; Line graph","score_opus":0.05423319711498033,"score_gpt":0.3320901280037434,"score_spread":0.27785693088876307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007402758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032875617,0.00019973307,0.995171,0.0006550979,0.00038406387,0.00013233186,0.0001395685,0.0000146252205,0.000016013595],"genre_scores_gemma":[0.07841685,0.00005016488,0.9210658,0.0002460568,0.00015933362,0.00000128634,0.000045277695,0.000008545439,0.000006665371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847037,0.000100940924,0.00057249184,0.0002510243,0.00041973498,0.00018542496],"domain_scores_gemma":[0.99795115,0.0007063116,0.000371521,0.0001280543,0.0006785521,0.00016440828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068362406,0.00014061423,0.00025762222,0.00024141606,0.00018703856,0.00015732758,0.00041696514,0.00006734417,0.0000035207672],"category_scores_gemma":[0.00009990378,0.000117853764,0.00007401053,0.0003409556,0.000106581305,0.00045727467,0.000109278546,0.00020288465,2.930445e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006212935,0.00015917385,0.00046147744,0.000044662294,0.000122384,0.000034917302,0.000180084,0.058371354,0.000020626196,0.74540514,0.0014805791,0.19365747],"study_design_scores_gemma":[0.0004011035,0.00013830762,0.0015674622,0.000020886726,0.000019387391,0.00042902035,0.0000037786724,0.500366,8.256669e-7,0.496426,0.0005517068,0.0000755339],"about_ca_topic_score_codex":0.0000067685387,"about_ca_topic_score_gemma":0.000002287989,"teacher_disagreement_score":0.44199464,"about_ca_system_score_codex":0.00002189191,"about_ca_system_score_gemma":0.00011026359,"threshold_uncertainty_score":0.4805937},"labels":[],"label_agreement":null},{"id":"W2007411577","doi":"10.1080/00949650701810406","title":"Parametric estimation of mixtures of two uniform distributions","year":2009,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Estimator; Mathematics; Moment (physics); M-estimator; Maximum likelihood; Mixing (physics); Parametric statistics; Statistics; Method of moments (probability theory); Distribution (mathematics); Applied mathematics; Mathematical analysis; Physics","score_opus":0.02146272547583996,"score_gpt":0.35433552082455466,"score_spread":0.3328727953487147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007411577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023760183,0.00006746217,0.975785,0.00016395895,0.000061877865,0.000063560794,0.000011145783,0.000006489597,0.00008032293],"genre_scores_gemma":[0.5328788,0.000004457917,0.4670844,0.000016836444,0.000009331027,6.895613e-8,0.0000042564398,9.617705e-7,8.86621e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998902,0.000103331105,0.000572608,0.000082531595,0.00026497946,0.000074512376],"domain_scores_gemma":[0.9982708,0.00072144455,0.00048548,0.00006664292,0.00038603166,0.0000695807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000449872,0.00006903554,0.00021935735,0.00020839811,0.000040846462,0.00003182365,0.000092654496,0.00003717313,0.0000028749953],"category_scores_gemma":[0.00035308625,0.000056927922,0.00004167418,0.00036460813,0.000040003397,0.00030212544,0.000012537512,0.00009160356,2.0472474e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017281716,0.00006042793,0.000032880736,0.000013666383,0.000007209867,0.000001552125,0.000104014405,0.35665438,0.00014106417,0.29708153,0.000018954212,0.34586704],"study_design_scores_gemma":[0.00034879716,0.00023327938,0.009768647,0.000019383542,0.000015399391,0.000008579105,0.0000021210788,0.6587124,0.00027360625,0.33057922,0.0000035031412,0.000035109944],"about_ca_topic_score_codex":0.0000026331752,"about_ca_topic_score_gemma":1.4847454e-7,"teacher_disagreement_score":0.5091186,"about_ca_system_score_codex":0.00001845083,"about_ca_system_score_gemma":0.000044971082,"threshold_uncertainty_score":0.23214534},"labels":[],"label_agreement":null},{"id":"W2007413993","doi":"10.1016/j.eswa.2011.12.038","title":"A finite mixture model for simultaneous high-dimensional clustering, localized feature selection and outlier rejection","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Outlier; Artificial intelligence; A priori and a posteriori; Pattern recognition (psychology); Data mining; Clustering high-dimensional data; Feature (linguistics); CURE data clustering algorithm; Set (abstract data type); Data set; Feature selection; Correlation clustering; Machine learning","score_opus":0.019937885009994123,"score_gpt":0.255815781509133,"score_spread":0.23587789649913884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007413993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009527794,0.0004148562,0.99721736,0.00024914966,0.00012762178,0.0014313324,0.000013281487,0.00023150531,0.00021960579],"genre_scores_gemma":[0.25644022,0.000011192606,0.7397997,0.00023007233,0.00013477172,0.0018486237,0.000011747329,0.000024447841,0.0014992706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873525,0.00006438527,0.00020778361,0.0005782696,0.00017021816,0.00024408133],"domain_scores_gemma":[0.9989578,0.00012122972,0.00013683485,0.00043010735,0.00022161752,0.00013238337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019994048,0.0002098008,0.00023209065,0.000096362244,0.00033285707,0.00009243229,0.0002307086,0.00017906273,0.0000018093858],"category_scores_gemma":[0.000016162661,0.0001625715,0.000041935178,0.00026343323,0.000033807006,0.00020557799,0.000055489698,0.00013858973,0.0000034161362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001064525,0.0010063049,0.00009373997,0.00060335797,0.0005097376,0.000018001116,0.024430078,0.22719929,0.013460956,0.5877444,0.027405873,0.11646373],"study_design_scores_gemma":[0.00052406103,0.00010445828,0.000005479661,0.00003489298,0.000014172614,0.00009702798,0.000017012178,0.98784953,0.0002496061,0.00288955,0.007990054,0.00022413874],"about_ca_topic_score_codex":0.00012814636,"about_ca_topic_score_gemma":0.00007136176,"teacher_disagreement_score":0.7606503,"about_ca_system_score_codex":0.000049367918,"about_ca_system_score_gemma":0.00006382485,"threshold_uncertainty_score":0.6629473},"labels":[],"label_agreement":null},{"id":"W2008519152","doi":"10.1002/wics.128","title":"Geometry in statistics","year":2010,"lang":"en","type":"review","venue":"Wiley Interdisciplinary Reviews Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Information geometry; Statistical inference; Nonparametric statistics; Euclidean geometry; Geometry; Computer science; Focus (optics); Inference; Mathematics; Statistics; Artificial intelligence","score_opus":0.06107983404593441,"score_gpt":0.40300702137615696,"score_spread":0.34192718733022254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008519152","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2894979e-8,0.49312198,0.5039703,0.000027108272,0.0008271073,0.0007942276,0.0009824552,0.000048110956,0.00022867034],"genre_scores_gemma":[5.122457e-8,0.5043157,0.49422264,0.00007574501,0.00015156047,0.00014929647,0.0008035981,0.00004832944,0.00023306672],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99339366,0.0010885953,0.0028040877,0.0013408205,0.0006462937,0.00072655064],"domain_scores_gemma":[0.9948617,0.0020450177,0.0013403712,0.0011962207,0.00022668134,0.00032999707],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017022124,0.0010481357,0.0035133688,0.0008325364,0.00023809302,0.00034635514,0.0024134216,0.0005527977,0.00012419245],"category_scores_gemma":[0.0003193197,0.0008814461,0.00048779865,0.0013862315,0.00018481235,0.0003439883,0.0021719453,0.0020271328,0.0006491124],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001461536,0.00011082946,9.509895e-7,0.005446726,0.00003076635,0.00014548647,0.00010614315,0.00001971387,1.7618824e-8,0.15280479,0.021066587,0.82026654],"study_design_scores_gemma":[0.00015196558,0.000086947555,0.0000057201596,0.009427024,0.00013804334,0.00022863262,0.0000016021748,0.013785282,1.4993976e-8,0.17486645,0.80053246,0.0007758615],"about_ca_topic_score_codex":0.000005305161,"about_ca_topic_score_gemma":0.000032160482,"teacher_disagreement_score":0.8194907,"about_ca_system_score_codex":0.0002845726,"about_ca_system_score_gemma":0.0006687861,"threshold_uncertainty_score":0.9993636},"labels":[],"label_agreement":null},{"id":"W2009157972","doi":"10.1080/13504860701718448","title":"Return and Value at Risk using the Dirichlet Process","year":2008,"lang":"en","type":"article","venue":"Applied Mathematical Finance","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Professional Engineers Ontario; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Illinois at Urbana-Champaign; University of Ottawa","keywords":"Dirichlet distribution; Computer science; Dirichlet process; Monte Carlo method; Bayesian probability; Econometrics; Value at risk; Process (computing); Asset (computer security); Mathematical optimization; Artificial intelligence; Mathematics; Statistics; Risk management; Economics","score_opus":0.02424534989453917,"score_gpt":0.26811299085631213,"score_spread":0.24386764096177296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009157972","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13982679,0.0002462673,0.8545425,0.00020413562,0.000027867556,0.00021319384,0.000001199207,0.000050504743,0.0048875283],"genre_scores_gemma":[0.46006408,0.00008269202,0.53946465,0.00019655294,0.000030553398,0.000024450692,1.05055165e-7,0.000009063119,0.00012785617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99889535,0.000046978577,0.00020750897,0.00036229772,0.000224793,0.0002630794],"domain_scores_gemma":[0.99898374,0.00026708105,0.000110442845,0.0005592643,0.000025651092,0.0000538246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044241038,0.00015060349,0.00022111458,0.000019279847,0.0004131166,0.000046249803,0.00048821952,0.0000696804,0.0000049764712],"category_scores_gemma":[0.00006017312,0.00009340671,0.00003654175,0.00023809688,0.0001856357,0.00010197361,0.0002559749,0.00018717766,0.000015118331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050893773,0.000034518187,0.00004988091,0.000044455766,0.0000066583348,0.000009249825,0.0021405471,0.000023304367,0.00043645312,0.9875481,0.0001963362,0.009505374],"study_design_scores_gemma":[0.00016795844,0.0000131661,0.00018427895,0.000027667611,0.000011934859,0.00018168119,0.000007590123,0.122612484,0.002663251,0.8735091,0.00044520595,0.00017566644],"about_ca_topic_score_codex":0.0000013390229,"about_ca_topic_score_gemma":1.6936794e-7,"teacher_disagreement_score":0.32023728,"about_ca_system_score_codex":0.000018801062,"about_ca_system_score_gemma":0.000028882781,"threshold_uncertainty_score":0.3809015},"labels":[],"label_agreement":null},{"id":"W2009629869","doi":"10.1239/jap/1059060892","title":"On ordered series and later waiting time distributions in a sequence of Markov dependent multistate trials","year":2003,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Markov chain; Mathematics; Series (stratigraphy); Sequence (biology); Markov process; Probability distribution; Simple (philosophy); Variable-order Markov model; Discrete phase-type distribution; Markov model; Applied mathematics; Markov property; Statistics","score_opus":0.03631565173903959,"score_gpt":0.29071477998055023,"score_spread":0.2543991282415106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009629869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4337394,0.00004028085,0.56467676,0.0002876156,0.00005991642,0.00030783066,0.000017351838,0.000008088491,0.0008627547],"genre_scores_gemma":[0.6487449,0.00000944028,0.35120118,0.000018569543,0.0000076179986,0.000004914535,4.2989763e-7,0.0000027775275,0.00001021215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980654,0.00047918857,0.00085303985,0.00021275092,0.00021209155,0.00017750864],"domain_scores_gemma":[0.99854875,0.0004869984,0.00052563066,0.00023924396,0.00011945816,0.00007991851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006029503,0.00011865326,0.0004909344,0.00006973216,0.000047746653,0.000049776358,0.00021893236,0.00006410979,0.000013428638],"category_scores_gemma":[0.000670807,0.00008773901,0.00007287681,0.00018247511,0.000078829515,0.00020320056,0.000052570475,0.00022398244,7.599072e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009900742,0.0005971322,0.00059096224,0.00021164911,0.00008717476,0.00005074084,0.0018739409,0.00059566926,0.07246488,0.7890808,0.00007763709,0.13337931],"study_design_scores_gemma":[0.0013130383,0.00022195207,0.0007433589,0.00007502281,0.000018529334,0.00008506533,0.000015232627,0.0030470644,0.036678072,0.9575346,0.0001071495,0.00016091917],"about_ca_topic_score_codex":0.0000035982728,"about_ca_topic_score_gemma":0.000005764766,"teacher_disagreement_score":0.21500549,"about_ca_system_score_codex":0.0000706666,"about_ca_system_score_gemma":0.00012346207,"threshold_uncertainty_score":0.3577893},"labels":[],"label_agreement":null},{"id":"W2010591341","doi":"10.1239/jap/1014842286","title":"NWU property of a class of random sums","year":2000,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Class (philosophy); Binomial (polynomial); Combinatorics; Property (philosophy); Identity (music); Renewal theory; Negative binomial distribution; Poisson distribution; Poisson process; Discrete mathematics; Statistics","score_opus":0.016864405626746095,"score_gpt":0.2406202301730825,"score_spread":0.2237558245463364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010591341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17541866,0.00011395699,0.80284834,0.0004203661,0.00010251371,0.0003933908,0.0000021130325,0.00001325528,0.02068742],"genre_scores_gemma":[0.57384086,0.000021366533,0.4259712,0.000054815107,0.000039061884,0.0000034292273,8.717223e-8,0.000004387214,0.00006479767],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981465,0.00015906752,0.00090684835,0.00020480169,0.00040391687,0.00017888908],"domain_scores_gemma":[0.9984422,0.00014101059,0.00053142506,0.0005212893,0.00025915424,0.00010493006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026590393,0.00012737997,0.00057925197,0.0000632728,0.000029893376,0.000019715533,0.00075279793,0.00008949533,0.000073362906],"category_scores_gemma":[0.00004982676,0.000072685914,0.00021667684,0.00028398618,0.00013954507,0.00019469667,0.00006437126,0.00024553598,0.0000020214136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015768209,0.0007495042,0.0002575899,0.00026261597,0.000090384376,0.000005409555,0.001725457,0.0005081634,0.014357064,0.05540089,0.0004589362,0.92460716],"study_design_scores_gemma":[0.005875901,0.00075913063,0.0019855509,0.00014195543,0.000077851466,0.00008703298,0.000018465584,0.008593907,0.08883996,0.88404125,0.009231863,0.000347149],"about_ca_topic_score_codex":0.000007991759,"about_ca_topic_score_gemma":0.0000020253772,"teacher_disagreement_score":0.92426,"about_ca_system_score_codex":0.000034752957,"about_ca_system_score_gemma":0.00021315468,"threshold_uncertainty_score":0.29640454},"labels":[],"label_agreement":null},{"id":"W2010689979","doi":"10.1016/j.jmva.2010.01.013","title":"Generating random AR(<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si60.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>p</mml:mi></mml:math>) and MA(<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si61.gif\" display=\"inline\" overflow=\"scroll\"><mml:mi>q</mml:mi></mml:math>) Toeplitz correlation matrices","year":2010,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Toeplitz matrix; Mathematics; Autoregressive model; Invertible matrix; Series (stratigraphy); Gaussian; Matrix (chemical analysis); Discrete mathematics; Applied mathematics; Combinatorics; Pure mathematics; Statistics","score_opus":0.014761078820367608,"score_gpt":0.2582122102370381,"score_spread":0.2434511314166705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010689979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74982107,0.0010044036,0.24567951,0.00058300974,0.0019074006,0.00013257646,0.00013993392,0.00019128741,0.0005407821],"genre_scores_gemma":[0.85018474,0.0010545013,0.14461447,0.0009813517,0.0022399765,0.00016814336,0.00024811932,0.00030393756,0.00020475812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9894722,0.0007043875,0.0032819735,0.002006924,0.0026779682,0.001856521],"domain_scores_gemma":[0.9894304,0.002054126,0.004433414,0.0024613508,0.0005192429,0.0011014406],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.005057315,0.0013054024,0.0013616693,0.001050938,0.0019705766,0.0025127907,0.0023651237,0.0017504247,0.000103375256],"category_scores_gemma":[0.001594798,0.0014177191,0.002615762,0.001956425,0.000593337,0.0030447782,0.0015316991,0.0026506716,0.00039906197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010686136,0.0005254315,0.0000995735,0.00035037706,0.002918098,0.0007906901,0.0022602375,0.017371207,0.011386286,0.9552499,0.0004329855,0.007546569],"study_design_scores_gemma":[0.0038759154,0.0006857151,0.00050084473,0.0005531282,0.0034813066,0.0010345774,0.0003421996,0.9810415,0.004518429,0.0011087029,0.001631771,0.0012259191],"about_ca_topic_score_codex":0.0016001096,"about_ca_topic_score_gemma":0.00080033863,"teacher_disagreement_score":0.9636703,"about_ca_system_score_codex":0.00007284856,"about_ca_system_score_gemma":0.0010242491,"threshold_uncertainty_score":0.9999698},"labels":[],"label_agreement":null},{"id":"W2010748082","doi":"10.1007/s10044-013-0323-0","title":"Beyond hybrid generative discriminative learning: spherical data classification","year":2013,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Categorization; Generative grammar; Computer science; Probabilistic logic; Artificial intelligence; Generative model; Machine learning; Pattern recognition (psychology); Contrast (vision)","score_opus":0.04171890366918496,"score_gpt":0.3063761530275938,"score_spread":0.26465724935840884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010748082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088464416,0.00010016832,0.9945978,0.0022493207,0.0000107386595,0.00024236177,0.000018146646,0.00005247438,0.001844368],"genre_scores_gemma":[0.73065585,0.00006561622,0.267897,0.00033307832,0.0000778642,0.00027535265,0.00025689695,0.000006595575,0.00043171723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868536,0.0001430809,0.00021573386,0.0006462266,0.00015000222,0.00015957658],"domain_scores_gemma":[0.9986328,0.00008660464,0.00012627692,0.0009341678,0.00010100405,0.00011918538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021037718,0.00012523813,0.00020459724,0.00009296722,0.00023566374,0.00028210107,0.00070006197,0.000031024923,0.000070183705],"category_scores_gemma":[0.000012783433,0.000102171034,0.000060894814,0.0006414891,0.00006431146,0.00041982968,0.00033484623,0.00013830134,0.00005437113],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.999688e-7,0.00006391964,0.002657709,0.0000037047655,0.0001637916,3.340386e-7,0.00017805662,0.0000144609985,0.0010416289,0.030962216,0.00076512824,0.9641489],"study_design_scores_gemma":[0.00010632558,0.000025406796,0.032957073,0.000002135755,0.00031147982,0.0000029246569,0.00009871204,0.9284629,0.000810872,0.03179048,0.0051737013,0.0002579893],"about_ca_topic_score_codex":0.00014750945,"about_ca_topic_score_gemma":0.000026310892,"teacher_disagreement_score":0.96389085,"about_ca_system_score_codex":0.000014097488,"about_ca_system_score_gemma":0.000015251505,"threshold_uncertainty_score":0.41664138},"labels":[],"label_agreement":null},{"id":"W2010980257","doi":"10.1007/s10260-014-0260-0","title":"On simulation and properties of the stable law","year":2014,"lang":"en","type":"article","venue":"Statistical Methods & Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Random variate; Statistical physics; Stability (learning theory); Mathematics; Random variable; Applied mathematics; Stable distribution; Stochastic process; Distribution (mathematics); Law; Computer science; Statistics; Mathematical analysis; Physics; Political science","score_opus":0.03959150195684236,"score_gpt":0.364215229285318,"score_spread":0.32462372732847566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010980257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000457609,0.000043507534,0.99380445,0.00041243073,0.00003731202,0.00030084013,0.000008536486,0.000031782303,0.005315355],"genre_scores_gemma":[0.28803197,0.0000011252258,0.71154565,0.00029153656,0.000014140977,0.000065679356,3.8947243e-7,0.000004332678,0.000045164816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877596,0.00054951117,0.00018245722,0.00024150137,0.0001291766,0.0001214066],"domain_scores_gemma":[0.9979417,0.0013365799,0.00006679125,0.00052838086,0.000068600384,0.000057998688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008193458,0.000079101155,0.00013276064,0.000020310035,0.00016206205,0.000041180392,0.0002953782,0.000038645496,0.0000048029],"category_scores_gemma":[0.00029141188,0.000049818096,0.000021617174,0.00017378027,0.00017816098,0.00006662458,0.000110107554,0.00009923074,0.0000028946865],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000148335,0.000017500352,0.0000015201468,0.00001264088,0.0000024173085,9.197584e-9,0.000049047034,0.00014929213,0.0015023524,0.74716187,0.00001294819,0.25108892],"study_design_scores_gemma":[0.00006145022,0.000025108637,0.00019892148,0.000009715372,0.000008431568,5.3709647e-7,0.0000015980863,0.22981371,0.00602874,0.7583581,0.0054372065,0.00005647665],"about_ca_topic_score_codex":0.000020453494,"about_ca_topic_score_gemma":0.0000023486728,"teacher_disagreement_score":0.28798622,"about_ca_system_score_codex":0.000008756924,"about_ca_system_score_gemma":0.000018251105,"threshold_uncertainty_score":0.2031523},"labels":[],"label_agreement":null},{"id":"W2011071923","doi":"10.1049/iet-ipr.2012.0340","title":"Image segmentation by a new weighted Student's <i>t</i> ‐mixture model","year":2013,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Health and Medical Research Fund; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Image segmentation; Artificial intelligence; Segmentation; Computer science; Computer vision; Image (mathematics); Pattern recognition (psychology); Scale-space segmentation","score_opus":0.0098581669263251,"score_gpt":0.28317252492517625,"score_spread":0.2733143579988512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011071923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013870618,0.0008602373,0.9907266,0.002350838,0.00010553781,0.0003688125,0.000003557312,0.00030692478,0.0038904462],"genre_scores_gemma":[0.014137186,0.000024735178,0.98162377,0.0019142581,0.000105357896,0.000050150877,0.000010994655,0.000031820826,0.0021017343],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981167,0.000081476464,0.00032058376,0.00060604163,0.00042009348,0.000455146],"domain_scores_gemma":[0.9989154,0.000027231974,0.00017758358,0.00042466444,0.00021761045,0.0002375417],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00024781135,0.00027483405,0.0002379955,0.00008296757,0.00022273493,0.0015207374,0.0008549003,0.00010526868,0.00003773418],"category_scores_gemma":[0.000015040788,0.00023755236,0.00007259725,0.0004192077,0.00005184199,0.003834239,0.00021435568,0.00025737676,0.000094065384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030761869,0.00009121705,0.000014735205,0.000059178936,0.000011779176,0.0000063907887,0.0023964534,0.0000054732627,0.49866697,0.00045035998,0.058781903,0.43951246],"study_design_scores_gemma":[0.000840876,0.00004117561,0.00004014779,0.00008020172,0.000025711646,0.00002427812,0.00006518037,0.86746496,0.04575915,0.08458541,0.00053114817,0.00054176047],"about_ca_topic_score_codex":0.000034991197,"about_ca_topic_score_gemma":0.0000010505754,"teacher_disagreement_score":0.8674595,"about_ca_system_score_codex":0.000050860424,"about_ca_system_score_gemma":0.0001836473,"threshold_uncertainty_score":0.9995158},"labels":[],"label_agreement":null},{"id":"W2011218435","doi":"10.1093/biostatistics/kxt052","title":"Analysis of counts with two latent classes, with application to risk assessment based on physician-visit records of cancer survivors","year":2013,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"BC Cancer Agency","keywords":"Estimator; Statistics; Consistency (knowledge bases); Unobservable; Normality; Variance (accounting); Inference; Mathematics; Latent class model; Asymptotic distribution; Econometrics; Delta method; Computer science; Artificial intelligence","score_opus":0.009125071757745046,"score_gpt":0.2977986433723875,"score_spread":0.28867357161464247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011218435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061144447,0.000007813947,0.99244815,0.00010363198,0.00003714062,0.00021374537,0.00015256651,0.000012477767,0.00091003877],"genre_scores_gemma":[0.4631993,0.000007639143,0.536571,0.0001438736,0.000008146589,0.000024899762,0.000010008116,0.000005068791,0.00003002019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921376,0.00006258065,0.0001521048,0.00021098317,0.00025745571,0.00010310436],"domain_scores_gemma":[0.9990058,0.00010530929,0.00020433617,0.00037609081,0.00025684314,0.000051614035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013842905,0.00009129601,0.00020611948,0.00011871829,0.000022904667,0.000022401202,0.00018073696,0.000020688434,0.000015869726],"category_scores_gemma":[0.0000058382066,0.00006428225,0.00002436662,0.0007114671,0.000025299456,0.000042042837,0.000017740771,0.000051966123,0.000003845691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049459908,0.00033076663,0.10240594,0.00007129887,0.0006212793,0.000002269452,0.00019131039,0.03160256,0.0008039968,0.07621808,0.0013954666,0.7863076],"study_design_scores_gemma":[0.00019225806,0.00027119298,0.15798499,0.000031869135,0.0002454834,5.737732e-8,0.0000036129316,0.8393471,0.00057289744,0.00087780063,0.00033978655,0.00013294216],"about_ca_topic_score_codex":0.0026976173,"about_ca_topic_score_gemma":0.0007724636,"teacher_disagreement_score":0.80774456,"about_ca_system_score_codex":0.000039199742,"about_ca_system_score_gemma":0.00008848509,"threshold_uncertainty_score":0.40780085},"labels":[],"label_agreement":null},{"id":"W2012415426","doi":"10.1145/2464576.2464606","title":"Estimation of distribution algorithm based on hidden Markov models for combinatorial optimization","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Estimation of distribution algorithm; Hidden Markov model; Computer science; Graphical model; Algorithm; EDAS; Bernoulli distribution; Estimator; Artificial intelligence; Machine learning; Mathematics; Random variable; Statistics","score_opus":0.011678238163387922,"score_gpt":0.2480142867565683,"score_spread":0.2363360485931804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012415426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028817152,0.0000047764324,0.9975191,0.0004604902,0.00039044803,0.00055873184,0.000016712203,0.00007563971,0.00094530184],"genre_scores_gemma":[0.07380709,0.0000012031354,0.92583364,0.00009884475,0.00003709364,0.00008094153,0.00008449542,0.000006296225,0.000050384617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991493,0.00006768346,0.00021611959,0.00022956468,0.0001926308,0.00014467801],"domain_scores_gemma":[0.99921215,0.00014199813,0.00010046975,0.00030037263,0.00018996511,0.000055058703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003061626,0.00010011488,0.00013973226,0.000040985855,0.00005922908,0.0000714534,0.00024861784,0.0000820475,0.000017813696],"category_scores_gemma":[0.000043179116,0.00008541443,0.000061404,0.00016594822,0.000016515438,0.00055625057,0.00003132386,0.00004304106,0.0000025281854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005890328,0.00006925029,3.7047212e-7,0.000010830147,0.0000031607099,6.407738e-8,0.000015289184,0.113018066,0.000016471631,0.2594135,0.0012292553,0.62621784],"study_design_scores_gemma":[0.0005031438,0.00012438057,0.000008155018,0.000010715623,0.00000444446,2.6578311e-7,7.5840444e-7,0.8149763,0.0019423146,0.18233703,0.000011689686,0.00008079784],"about_ca_topic_score_codex":0.000025005618,"about_ca_topic_score_gemma":7.9178335e-8,"teacher_disagreement_score":0.70195824,"about_ca_system_score_codex":0.000038776696,"about_ca_system_score_gemma":0.000045625246,"threshold_uncertainty_score":0.34830996},"labels":[],"label_agreement":null},{"id":"W2013577242","doi":"10.1080/10485250008832819","title":"Nonparametric empirical bayes procedures, asymptotic optimality And rates Of convergence For two‐tail tests In exponential family<sup>*</sup>","year":2000,"lang":"en","type":"article","venue":"Journal of nonparametric statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mathematics; Nonparametric statistics; Exponential family; Smoothness; Bayes' theorem; Applied mathematics; Function (biology); Exponential function; Empirical distribution function; Rate of convergence; Parametric statistics; Statistics; Combinatorics; Bayesian probability; Mathematical analysis","score_opus":0.03891727131582158,"score_gpt":0.35031804740095646,"score_spread":0.3114007760851349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013577242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24039084,0.001266246,0.7576409,0.0000912033,0.000167155,0.0003053335,0.000056920544,0.000010828923,0.00007055305],"genre_scores_gemma":[0.44494984,0.0003592258,0.55445707,0.00010555925,0.000064453096,0.0000067523115,0.0000017806937,0.0000135590735,0.00004177043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965051,0.0003376653,0.0014774388,0.00046228545,0.00070456765,0.0005129533],"domain_scores_gemma":[0.9941854,0.003817598,0.00071251555,0.00037706355,0.00061038864,0.0002970419],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019240868,0.00031663655,0.00089632376,0.0011546697,0.00008400262,0.00015061267,0.0008294139,0.00016021379,0.00003396131],"category_scores_gemma":[0.0033652568,0.00027334312,0.00014725121,0.002818535,0.00018709125,0.0004787574,0.00010205666,0.0004261471,0.0000033918375],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012012459,0.0027023447,0.07459736,0.0011749777,0.00040295575,0.00044007046,0.002659996,0.019522065,0.0006381327,0.030531175,0.009997405,0.85613227],"study_design_scores_gemma":[0.0053298003,0.0023987943,0.12454852,0.00026885065,0.00019888759,0.00052651315,0.00007198258,0.79418564,0.0009420396,0.07029566,0.0004439778,0.00078936847],"about_ca_topic_score_codex":0.00004132303,"about_ca_topic_score_gemma":0.0000030193014,"teacher_disagreement_score":0.8553429,"about_ca_system_score_codex":0.00009508834,"about_ca_system_score_gemma":0.0005370785,"threshold_uncertainty_score":0.99997187},"labels":[],"label_agreement":null},{"id":"W2013652217","doi":"10.1080/03610918.2012.698773","title":"Bayesian Analysis of Ordinal Survey Data Using the Dirichlet Process to Account for Respondent Personality Traits","year":2013,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Manitoba","funders":"","keywords":"Ordinal data; Respondent; Dirichlet distribution; Statistics; Latent variable; Bayesian probability; Goodness of fit; Econometrics; Computer science; Multivariate statistics; Dirichlet process; Ordinal regression; Survey data collection; Mathematics; Data mining","score_opus":0.32631280529753415,"score_gpt":0.5114101476715228,"score_spread":0.18509734237398867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013652217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018884063,0.000066888635,0.9796419,0.00039823112,0.000026138745,0.0005865723,0.00035951546,0.000013777576,0.000022886377],"genre_scores_gemma":[0.55041635,0.000004001968,0.4492291,0.00008647022,0.0000037499165,0.000018758967,0.00023452748,0.0000035587118,0.0000034917832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983546,0.00057893334,0.0004536328,0.0002879416,0.00020025531,0.00012461227],"domain_scores_gemma":[0.9954182,0.0027108053,0.00021657119,0.0009876551,0.00061580597,0.000050976167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016276347,0.000101177146,0.00021658241,0.00027862363,0.00022527186,0.00017284125,0.0011293029,0.00004104152,0.000004032666],"category_scores_gemma":[0.00048873643,0.00008738667,0.000023323057,0.0013867534,0.000071556286,0.00035676002,0.00035202142,0.00008988737,3.7101233e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030773543,0.00015553724,0.0068161055,0.000040371862,0.00013891987,1.16330774e-7,0.0057676574,0.7699726,0.000048318354,0.036402445,0.0001243598,0.1805028],"study_design_scores_gemma":[0.00014442309,0.000017774732,0.16476397,0.000009643733,0.00006284818,2.6281225e-7,0.00006881277,0.81685776,0.0000015124803,0.017964782,0.000027010872,0.000081209124],"about_ca_topic_score_codex":0.00047569422,"about_ca_topic_score_gemma":0.00068593194,"teacher_disagreement_score":0.5315323,"about_ca_system_score_codex":0.00003870213,"about_ca_system_score_gemma":0.00008420163,"threshold_uncertainty_score":0.35635248},"labels":[],"label_agreement":null},{"id":"W2014262831","doi":"10.1111/1467-9574.t01-1-00057","title":"A new approximation of the posterior distribution of the log–odds ratio","year":2002,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Waterloo","funders":"","keywords":"Dirichlet distribution; Mathematics; Multinomial distribution; Distribution (mathematics); Posterior probability; Concentration parameter; Applied mathematics; Statistics; Mathematical analysis; Bayesian probability","score_opus":0.014094731546854549,"score_gpt":0.23518343713262224,"score_spread":0.22108870558576768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014262831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001297434,0.00006607641,0.9957159,0.0015829134,0.00022168888,0.0002108603,0.000087076536,0.000014819421,0.0008031864],"genre_scores_gemma":[0.82201123,0.0000057191864,0.17741247,0.00008845151,0.000028009335,0.000005030079,0.000005021972,0.000004450177,0.00043958897],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990214,0.00016043792,0.000260183,0.00015113322,0.00027469153,0.00013212646],"domain_scores_gemma":[0.99906826,0.0001187147,0.00020138254,0.0005114659,0.00005502737,0.000045132314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018652124,0.000084797204,0.00014163456,0.000018262685,0.00008176041,0.000029567122,0.00056629913,0.000045497207,0.000052060695],"category_scores_gemma":[0.0001574128,0.000046724494,0.000063871885,0.0003073501,0.00008264713,0.00008653703,0.00012950768,0.000094705436,0.0000036971967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066607654,0.0000425348,0.00018431606,0.00004222152,0.000016152411,6.7497757e-7,0.0011568847,0.000009244588,0.0029207051,0.8137426,0.009191168,0.17268685],"study_design_scores_gemma":[0.0019478339,0.0004177956,0.120221764,0.00028990078,0.00015532189,0.00008280475,0.000033466844,0.50526416,0.033115167,0.3331426,0.0047876425,0.0005415486],"about_ca_topic_score_codex":0.000032490916,"about_ca_topic_score_gemma":0.0000051625225,"teacher_disagreement_score":0.8207138,"about_ca_system_score_codex":0.000018137507,"about_ca_system_score_gemma":0.000052430732,"threshold_uncertainty_score":0.19053696},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01289836342498767,"score_gpt":0.29639914258475636,"score_spread":0.2835007791597687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014306350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028354542,0.000058179157,0.9706005,0.00003922575,0.0004299376,0.000048644306,0.000015120822,0.00003217701,0.00042171346],"genre_scores_gemma":[0.4751455,0.0000034698346,0.5247736,0.000027262855,0.00003178213,2.0911449e-7,7.9491673e-7,0.000003547289,0.000013858126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991943,0.000047304096,0.0002088611,0.00023937713,0.00012255549,0.00018760495],"domain_scores_gemma":[0.9992345,0.00027637352,0.00012965167,0.00022271568,0.000052965122,0.000083768144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027967984,0.00010359239,0.00017168386,0.00006765704,0.00011171883,0.000081256,0.00025550855,0.000045910678,0.0000058592586],"category_scores_gemma":[0.00009893282,0.00009006667,0.000025715544,0.00012241358,0.00005270778,0.000068147594,0.00016507925,0.00018494004,5.701468e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010137528,0.0000107999,0.00019935252,0.000014818019,0.000010950939,0.000006620906,0.00043971153,0.0000052178293,0.019143697,0.54480493,0.00004479828,0.43531808],"study_design_scores_gemma":[0.00031266775,0.000054907097,0.011416812,0.00003124712,0.0000129298905,0.0000249806,0.000009028856,0.8369298,0.00554389,0.14495406,0.00045496292,0.0002546998],"about_ca_topic_score_codex":0.000040821786,"about_ca_topic_score_gemma":0.0000057000216,"teacher_disagreement_score":0.8369246,"about_ca_system_score_codex":0.000003131262,"about_ca_system_score_gemma":0.000025956186,"threshold_uncertainty_score":0.36728123},"labels":[],"label_agreement":null},{"id":"W2014728006","doi":"10.1007/s00180-014-0535-9","title":"Kernel-based mixture models for classification","year":2014,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Kernel (algebra); Mixture model; Mathematics; Pattern recognition (psychology); Artificial intelligence; Kernel embedding of distributions; Centroid; Akaike information criterion; Kernel method; Radial basis function kernel; Variable kernel density estimation; Computer science; Support vector machine; Statistics; Combinatorics","score_opus":0.038382844688531835,"score_gpt":0.299106430379149,"score_spread":0.2607235856906172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014728006","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011907078,0.000028585708,0.9973424,0.00085525063,0.00027106656,0.00022680798,0.00011400724,0.00010821101,0.0010417819],"genre_scores_gemma":[0.10571593,9.384241e-7,0.8927452,0.0010750591,0.00010003203,0.00003978098,0.0001740912,0.0000132367495,0.0001357321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884593,0.00010288235,0.00024461863,0.00035157867,0.00025623836,0.00019873765],"domain_scores_gemma":[0.99814504,0.0009984,0.00012369061,0.00026593969,0.00036739948,0.00009953778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038485473,0.00013498087,0.00015165654,0.00006948009,0.00016178518,0.00012762107,0.00040894846,0.00007004762,0.0000058916685],"category_scores_gemma":[0.00012863839,0.00013170642,0.000049544047,0.00014687586,0.000041805273,0.0001641447,0.000035009783,0.000083544575,0.000011756343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004796254,0.000029048353,0.000005905074,0.000020737676,0.000005356349,3.5146687e-7,0.000046142035,0.0611912,0.000021873191,0.8287113,0.007783306,0.10217999],"study_design_scores_gemma":[0.00022173444,0.00003297181,0.000263648,0.000004532114,0.0000044400067,0.0000010673115,4.617772e-7,0.51776034,0.00001537871,0.47952217,0.0020866322,0.00008660507],"about_ca_topic_score_codex":0.0000018645736,"about_ca_topic_score_gemma":0.0000011569266,"teacher_disagreement_score":0.45656916,"about_ca_system_score_codex":0.00003667566,"about_ca_system_score_gemma":0.0001220882,"threshold_uncertainty_score":0.5370832},"labels":[],"label_agreement":null},{"id":"W2015116977","doi":"10.1080/00949655.2015.1005014","title":"A flexible approach for multivariate mixed-effects models with non-ignorable missing values","year":2015,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; York University; University of New Brunswick; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Covariate; Mathematics; Statistics; Multivariate statistics; Nonparametric statistics; Normality; Econometrics; Random effects model; Multivariate normal distribution; Bayesian probability","score_opus":0.05847549284891438,"score_gpt":0.34353210507083787,"score_spread":0.28505661222192347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015116977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006845847,0.00007014431,0.99851024,0.00008614449,0.000115381095,0.0002401393,0.0000026813154,0.00002090943,0.0002697815],"genre_scores_gemma":[0.44530058,7.4464793e-7,0.5545888,0.00005087071,0.000038001595,0.0000017347427,0.0000031686047,0.0000054096304,0.000010654954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889356,0.00015534299,0.00032992134,0.0001797058,0.00029343652,0.00014805954],"domain_scores_gemma":[0.99809915,0.0008280799,0.00024981893,0.00007316617,0.0005418576,0.00020792827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085019326,0.0001163637,0.00025654267,0.00011760821,0.000102503895,0.00020066324,0.0001033223,0.00005290562,2.4042842e-7],"category_scores_gemma":[0.00016439837,0.00008581604,0.000031230833,0.00014578915,0.000032658267,0.00068846095,0.000024052395,0.00010724111,2.2284118e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011746082,0.00006325281,0.000009784153,0.000056297293,0.00001972182,0.000004566456,0.00070465467,0.816058,0.000035712674,0.06285853,0.00012363888,0.1199484],"study_design_scores_gemma":[0.0012926088,0.00036489218,0.00016676205,0.000029787972,0.000022715372,0.000016632943,0.000015345544,0.6755119,0.00006253578,0.32242903,0.000009551336,0.000078227036],"about_ca_topic_score_codex":0.0000040384207,"about_ca_topic_score_gemma":9.9240204e-8,"teacher_disagreement_score":0.44461602,"about_ca_system_score_codex":0.000035061472,"about_ca_system_score_gemma":0.000100041296,"threshold_uncertainty_score":0.34994766},"labels":[],"label_agreement":null},{"id":"W2015482051","doi":"10.2307/3316073","title":"The likelihood ratio test for homogeneity in finite mixture models","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Likelihood-ratio test; Statistics; Homogeneity (statistics); Applied mathematics; Infimum and supremum; Asymptotic distribution; Statistic; Parametric statistics; Score test; Combinatorics","score_opus":0.024031544022259082,"score_gpt":0.2514606562080007,"score_spread":0.2274291121857416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015482051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019745929,0.00066623685,0.996072,0.0019603427,0.00043619552,0.00012621398,0.00017821623,0.0000027416263,0.00036059637],"genre_scores_gemma":[0.13860014,0.00013714525,0.8602794,0.0005812004,0.00016595371,0.000004550997,0.0000025892427,0.000011601396,0.00021741621],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987801,0.00009199232,0.00045730904,0.00013063841,0.00015425593,0.00038573818],"domain_scores_gemma":[0.997572,0.0011168689,0.0002221989,0.0002772867,0.00039073732,0.00042093318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011203004,0.000112287926,0.0001930071,0.00014170949,0.0002319829,0.00024377122,0.0007382131,0.00006522823,0.0000048597085],"category_scores_gemma":[0.0007926965,0.000081458216,0.000059529706,0.00025362647,0.000055227105,0.00023377514,0.0000149156285,0.00023882663,0.000001454598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013023782,0.000029184588,0.001243867,0.000014102491,0.000027140086,0.0005087298,0.001212318,0.0019223023,0.00005324691,0.57564616,0.034570057,0.38475984],"study_design_scores_gemma":[0.00044023135,0.00016371899,0.001229738,0.000030142004,0.000012385159,0.0001575691,0.000026057933,0.26494545,0.00004797784,0.7106587,0.02213585,0.00015217351],"about_ca_topic_score_codex":0.00048374082,"about_ca_topic_score_gemma":0.039331492,"teacher_disagreement_score":0.38460767,"about_ca_system_score_codex":0.00009595622,"about_ca_system_score_gemma":0.0014562848,"threshold_uncertainty_score":0.97819823},"labels":[],"label_agreement":null},{"id":"W2015596626","doi":"10.1016/j.jmva.2004.04.011","title":"Density estimation by the penalized combinatorial method","year":2004,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mathematics; Density estimation; Dimension (graph theory); Range (aeronautics); Multivariate statistics; Combinatorics; Class (philosophy); Exponential family; Multivariate kernel density estimation; Parametric statistics; Exponential function; Applied mathematics; Discrete mathematics; Statistics; Mathematical analysis; Estimator; Artificial intelligence; Variable kernel density estimation; Computer science; Kernel method","score_opus":0.013015194739328776,"score_gpt":0.31540786482181005,"score_spread":0.3023926700824813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015596626","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044247503,0.000117930125,0.99237275,0.002507739,0.00038244625,0.00006054099,0.000001001311,0.000014985191,0.00011787934],"genre_scores_gemma":[0.33811045,0.000010438753,0.66158646,0.00018754661,0.000070190414,8.019586e-7,8.199099e-7,0.000003906271,0.000029415154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979743,0.00062738784,0.0005375015,0.00018856928,0.0004953311,0.00017691148],"domain_scores_gemma":[0.99814963,0.00030827787,0.0006813303,0.00039819194,0.00034925356,0.00011332576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031003219,0.00013594059,0.0004608277,0.00022745808,0.000175451,0.00018362784,0.0008146747,0.000078912206,0.00001013559],"category_scores_gemma":[0.00026928645,0.00008106169,0.0004959086,0.0011691523,0.000026083457,0.00046599476,0.00009411001,0.00028803764,0.0000033190083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023062565,0.00085992296,0.00027703124,0.000017588212,0.00773619,0.00013850616,0.0058638053,0.06964827,0.027452325,0.6649212,0.0015512861,0.22130321],"study_design_scores_gemma":[0.0038237628,0.00016303618,0.0022350007,0.000023548417,0.002543786,0.00012964125,0.00002365347,0.507222,0.015549161,0.4672586,0.00072584813,0.00030198033],"about_ca_topic_score_codex":0.00027129528,"about_ca_topic_score_gemma":0.000007129522,"teacher_disagreement_score":0.4375737,"about_ca_system_score_codex":0.000089148234,"about_ca_system_score_gemma":0.00010688985,"threshold_uncertainty_score":0.33055997},"labels":[],"label_agreement":null},{"id":"W2016073783","doi":"10.1007/s11063-013-9293-x","title":"Non-Gaussian Data Clustering via Expectation Propagation Learning of Finite Dirichlet Mixture Models and Applications","year":2013,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Computer science; Artificial intelligence; Inference; Machine learning; Cluster analysis; Computational intelligence; Dirichlet distribution; Hierarchical Dirichlet process; Dirichlet process; Latent Dirichlet allocation; Synthetic data; Unsupervised learning; Topic model; Mathematics","score_opus":0.02669352920091828,"score_gpt":0.27011387498759215,"score_spread":0.24342034578667388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016073783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010367422,0.00011723536,0.9860076,0.002875551,0.000044161916,0.0003644349,0.0000010261828,0.000091182475,0.00013142188],"genre_scores_gemma":[0.71638757,0.0000047526983,0.28284943,0.00058825023,0.000068039,0.000055899945,0.00001615907,0.0000117650225,0.000018128452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987864,0.000067381465,0.0002577875,0.00048211584,0.00019598052,0.00021037248],"domain_scores_gemma":[0.99915165,0.00005331264,0.00022027675,0.00043307786,0.00007332722,0.000068368965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018453861,0.00014766697,0.00016623174,0.00010470501,0.00020265584,0.00024159465,0.0005615155,0.00005740372,0.000001403688],"category_scores_gemma":[0.000017430071,0.00012956426,0.000020204345,0.00029919698,0.000058423193,0.0021801714,0.00026411214,0.00021505098,0.000001975459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033618098,0.00001887415,0.00011537582,0.00021898418,0.0000074647314,0.000001475467,0.0028030192,0.008860748,0.103150934,0.0003016092,0.00013246568,0.8843857],"study_design_scores_gemma":[0.00012731293,0.000017528293,0.00043295196,0.000047363326,0.000008577321,0.000011026689,0.000023119463,0.9956374,0.00092380587,0.002577735,0.000047502308,0.00014568595],"about_ca_topic_score_codex":0.000027461667,"about_ca_topic_score_gemma":0.0000015620357,"teacher_disagreement_score":0.98677665,"about_ca_system_score_codex":0.000012794374,"about_ca_system_score_gemma":0.000023026078,"threshold_uncertainty_score":0.52834773},"labels":[],"label_agreement":null},{"id":"W2016116954","doi":"10.1080/10618600.2014.988337","title":"Parameter Expanded Algorithms for Bayesian Latent Variable Modeling of Genetic Pleiotropy Data","year":2014,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"National Institute of Diabetes and Digestive and Kidney Diseases","keywords":"Latent variable; Bayesian probability; Computer science; Markov chain Monte Carlo; Bayesian hierarchical modeling; Latent variable model; Pleiotropy; Algorithm; Posterior probability; Bayesian inference; Machine learning; Artificial intelligence; Data mining","score_opus":0.0422801346652598,"score_gpt":0.3027630919014125,"score_spread":0.26048295723615267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016116954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010611181,0.00014404728,0.99816525,0.000269713,0.00016541833,0.00008020026,0.00009977772,0.0000054056172,0.00000907399],"genre_scores_gemma":[0.1586403,0.000033098193,0.8410621,0.00015121963,0.00008861823,0.0000010740927,0.000014210277,0.000006017106,0.0000033194117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985974,0.000110794674,0.00060295116,0.00019949602,0.00033563908,0.0001537387],"domain_scores_gemma":[0.997899,0.0010369532,0.00029700872,0.00019452085,0.00042985933,0.00014265563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007294361,0.0001095209,0.00030868783,0.00011079218,0.0000740099,0.0000709136,0.00047115688,0.00005782168,0.0000025295415],"category_scores_gemma":[0.00022398998,0.00008499975,0.000051288578,0.00014519908,0.000055608827,0.00017034786,0.00011233109,0.0001312747,9.9476175e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052367785,0.00012230685,0.00022040647,0.00007775908,0.00010421501,0.0000056094714,0.00008769375,0.08407614,0.00004641268,0.74015296,0.0005282847,0.17452587],"study_design_scores_gemma":[0.00033810618,0.00016164411,0.0004950317,0.000015909298,0.000021888152,0.000033859287,6.439463e-7,0.52150035,0.0000030073293,0.47730392,0.0000723586,0.000053297164],"about_ca_topic_score_codex":0.0000054458196,"about_ca_topic_score_gemma":5.908299e-7,"teacher_disagreement_score":0.43742418,"about_ca_system_score_codex":0.000005950049,"about_ca_system_score_gemma":0.00007714436,"threshold_uncertainty_score":0.34661892},"labels":[],"label_agreement":null},{"id":"W2016394018","doi":"10.1016/j.spl.2004.11.013","title":"Ergodicity and existence of moments for local mixtures of linear autoregressions","year":2005,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Ergodicity; Mixing (physics); Applied mathematics; Nonlinear system; Probabilistic logic; Class (philosophy); Autoregressive model; Series (stratigraphy); Mathematical analysis; Focus (optics); Econometrics; Statistics","score_opus":0.022522824971669447,"score_gpt":0.29208341837700674,"score_spread":0.2695605934053373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016394018","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015054099,0.00008169942,0.9820675,0.0021278267,0.00008644718,0.00035348747,0.00018297907,0.000022521055,0.000023434584],"genre_scores_gemma":[0.07071848,0.000008576018,0.9287809,0.00042077922,0.000027496622,0.000018465127,0.0000068522104,0.0000060276534,0.000012424979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870723,0.0001146012,0.0003929849,0.00034678887,0.00022312121,0.00021524585],"domain_scores_gemma":[0.99877995,0.0003790262,0.00017830363,0.00042701355,0.00014436957,0.000091357295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053359225,0.00013202932,0.00027681398,0.000049617884,0.000071409115,0.000014004907,0.0003536017,0.000055441906,0.0000032758608],"category_scores_gemma":[0.00019376088,0.00011141672,0.000049878323,0.00010947287,0.00040221505,0.00012217522,0.00013283256,0.00009999969,3.4656136e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003758574,0.00020888823,0.00068044395,0.00046080246,0.000034580782,0.0000015853401,0.0013079402,0.00011322933,0.011390677,0.8235336,0.002384491,0.15984617],"study_design_scores_gemma":[0.00068970554,0.00022165298,0.003092069,0.00009830456,0.000035745332,0.000005000379,0.0000023460432,0.12665907,0.011385647,0.85647476,0.0010782863,0.00025739684],"about_ca_topic_score_codex":0.000042356234,"about_ca_topic_score_gemma":0.000019510715,"teacher_disagreement_score":0.15958878,"about_ca_system_score_codex":0.00003302115,"about_ca_system_score_gemma":0.000057951358,"threshold_uncertainty_score":0.45434418},"labels":[],"label_agreement":null},{"id":"W2016517500","doi":"10.1007/s10959-004-0579-9","title":"The Hyperoctahedral Group, Symmetric Group Representations and the Moments of the Real Wishart Distribution","year":2005,"lang":"en","type":"article","venue":"Journal of Theoretical Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Wishart distribution; Mathematics; Group (periodic table); Symmetric group; Distribution (mathematics); Combinatorics; Mathematical analysis; Statistics; Multivariate statistics; Physics","score_opus":0.009972976290301716,"score_gpt":0.2613021889082457,"score_spread":0.251329212617944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016517500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085061885,0.0002751242,0.89169353,0.020988865,0.00026979521,0.00036850348,0.0000072321054,0.000008924955,0.0013261604],"genre_scores_gemma":[0.9690541,0.00012316067,0.030574104,0.000112559166,0.00011396138,0.000006291165,4.2620638e-7,0.0000034548689,0.00001194585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99731904,0.0012176532,0.0006092813,0.00017843406,0.00047739182,0.00019819746],"domain_scores_gemma":[0.997285,0.0014446342,0.00037004284,0.00061139377,0.00019946996,0.00008947491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004678327,0.00010420261,0.0002236563,0.000022538732,0.0003179212,0.000116523945,0.0010368683,0.00005199221,0.0000042658558],"category_scores_gemma":[0.0012498042,0.0000410327,0.00021524813,0.00043268403,0.0015600984,0.0002810403,0.0003501606,0.00036389678,5.229708e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009117109,0.00009187064,0.00072160654,0.0000066347984,0.000021934675,3.3042275e-7,0.00015555577,0.000014251077,0.000041467796,0.9595099,0.00015708957,0.039188184],"study_design_scores_gemma":[0.0006356658,0.00009150358,0.020169029,0.000014856708,0.000041794385,0.000042160387,0.000013001145,0.011510569,0.00017329116,0.9668086,0.00044484044,0.00005466744],"about_ca_topic_score_codex":0.0000064045926,"about_ca_topic_score_gemma":0.0000052457403,"teacher_disagreement_score":0.8839922,"about_ca_system_score_codex":0.00007266277,"about_ca_system_score_gemma":0.000045348173,"threshold_uncertainty_score":0.57482475},"labels":[],"label_agreement":null},{"id":"W2017521979","doi":"10.1016/j.jspi.2009.06.002","title":"Test for homogeneity in normal mixtures with unknown means and variances","year":2009,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Mathematics; Homogeneity (statistics); Statistics; F-test of equality of variances; Levene's test; Econometrics; Statistical hypothesis testing; Test statistic","score_opus":0.02071402928215842,"score_gpt":0.30868031343794783,"score_spread":0.2879662841557894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017521979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00822825,0.0004790921,0.9903858,0.000471221,0.000035450073,0.00004414941,0.000008929884,0.00000523979,0.00034187012],"genre_scores_gemma":[0.51947105,0.00002705106,0.48033988,0.00012699999,0.00002784175,4.679751e-7,2.6516443e-7,0.0000011745025,0.0000052414525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99932367,0.00003863063,0.00022447539,0.00013349944,0.00012024929,0.00015947287],"domain_scores_gemma":[0.9987301,0.00090042985,0.0001094375,0.00006288155,0.000082995415,0.00011411053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004355145,0.00008991551,0.00020942153,0.00006756974,0.00006124016,0.000111773574,0.00014228118,0.000039629747,9.837697e-7],"category_scores_gemma":[0.0003376175,0.000059626178,0.0000112415955,0.000083905594,0.000057780046,0.00029112195,0.000017911758,0.0001753916,5.7617896e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001785845,0.00015076261,0.0200522,0.000060116414,0.000020392694,0.00023028076,0.0014130331,0.00018825468,0.00092457107,0.49629223,0.00051118043,0.47997838],"study_design_scores_gemma":[0.0021479172,0.005057426,0.3255412,0.00061152526,0.000044997032,0.00070561114,0.000028470922,0.084525235,0.00073762465,0.57941395,0.00074787374,0.00043819737],"about_ca_topic_score_codex":0.0000044005174,"about_ca_topic_score_gemma":0.0000024341307,"teacher_disagreement_score":0.5112428,"about_ca_system_score_codex":0.000006410796,"about_ca_system_score_gemma":0.00006305323,"threshold_uncertainty_score":0.24314849},"labels":[],"label_agreement":null},{"id":"W2017659064","doi":"10.1080/10543406.2013.813517","title":"Bayesian Inference for Skew-Normal Mixture Models With Left-Censoring","year":2013,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; University of Windsor","keywords":"Censoring (clinical trials); Skewness; Mathematics; Statistics; Markov chain Monte Carlo; Skew; Tobit model; Bayesian probability; Econometrics; Computer science","score_opus":0.03471245508587097,"score_gpt":0.32403610444395414,"score_spread":0.2893236493580832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017659064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00058766187,0.00024421563,0.99695414,0.001160021,0.00036444995,0.0002817361,0.000036107773,0.000027580105,0.0003440693],"genre_scores_gemma":[0.20462233,0.00008957355,0.79430956,0.00067721424,0.00018565322,0.000005888334,0.0000012005186,0.00001704028,0.00009151756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805504,0.000111807516,0.0005945495,0.0002500982,0.00048399178,0.0005045083],"domain_scores_gemma":[0.99757224,0.00059217005,0.00033413255,0.00025214016,0.0007449001,0.0005044197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051701016,0.00024064624,0.00039332875,0.00012514845,0.00013286197,0.00028732058,0.00074300077,0.00015859089,0.00006324674],"category_scores_gemma":[0.00013505368,0.0001686263,0.00009666553,0.0001780468,0.00009876472,0.0008797095,0.000101629674,0.00068583706,0.00000719396],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014912643,0.00021671854,0.00019727547,0.00016426388,0.00016336917,0.00013210482,0.000584562,0.0009962335,0.003699858,0.6279337,0.004902416,0.36086038],"study_design_scores_gemma":[0.0013662055,0.0005684124,0.00023796935,0.000078358804,0.00008284319,0.0002965714,0.000010921907,0.6933047,0.0038470924,0.29695058,0.0029126785,0.00034365538],"about_ca_topic_score_codex":0.0000061181227,"about_ca_topic_score_gemma":0.0000013813902,"teacher_disagreement_score":0.6923085,"about_ca_system_score_codex":0.000053018317,"about_ca_system_score_gemma":0.00018829347,"threshold_uncertainty_score":0.68763804},"labels":[],"label_agreement":null},{"id":"W2018494618","doi":"10.1080/03610918.2013.781628","title":"A Thresholding Algorithm for Order Selection in Finite Mixture Models","year":2014,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Overfitting; Mathematical optimization; Penalty method; Algorithm; Computer science; Thresholding; Model selection; Rate of convergence; Regularization (linguistics); Mathematics; Artificial intelligence; Artificial neural network","score_opus":0.10649885062518127,"score_gpt":0.4142663330969215,"score_spread":0.30776748247174024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018494618","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001770743,0.000121046294,0.9985735,0.00029691635,0.00006175373,0.00038899435,0.000014948553,0.000055829245,0.0003099811],"genre_scores_gemma":[0.3876735,0.000033656663,0.6120251,0.00014163656,0.000011783673,0.00004112749,0.000052078296,0.000007532073,0.000013637894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987564,0.00029055253,0.0003904969,0.00027795348,0.000118415635,0.00016615183],"domain_scores_gemma":[0.99741423,0.0018392691,0.00013015054,0.0003269457,0.0002471263,0.000042259755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007299383,0.00012459344,0.00017242797,0.0002874712,0.00018764107,0.00013955691,0.00033836474,0.00009107989,9.0430774e-7],"category_scores_gemma":[0.00018565914,0.00013925157,0.000017994036,0.0006054153,0.000041586296,0.0004092837,0.00013024473,0.00017942663,8.4990705e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021248043,0.00003192361,0.00004848625,0.000007483178,0.000001920314,6.8085114e-8,0.0004954135,0.36782327,0.000004476768,0.22323252,0.000015933447,0.40833637],"study_design_scores_gemma":[0.0004420616,0.000026601205,0.0005337803,0.000020548285,0.000003326576,7.186603e-7,0.000008771129,0.6308301,0.00000253263,0.36777946,0.00025605736,0.00009602083],"about_ca_topic_score_codex":0.000028290531,"about_ca_topic_score_gemma":0.00009753636,"teacher_disagreement_score":0.40824035,"about_ca_system_score_codex":0.000057208963,"about_ca_system_score_gemma":0.000041933254,"threshold_uncertainty_score":0.5678514},"labels":[],"label_agreement":null},{"id":"W2018905040","doi":"10.1016/j.csda.2010.05.019","title":"Model-based classification via mixtures of multivariate -distributions","year":2010,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Initialization; Covariance; Multivariate statistics; Expectation–maximization algorithm; Mathematics; Convergence (economics); Mixture model; Multivariate normal distribution; Maximization; Pattern recognition (psychology); Algorithm; Computer science; Artificial intelligence; Statistics; Mathematical optimization; Maximum likelihood","score_opus":0.05214006332080729,"score_gpt":0.34818186668338064,"score_spread":0.29604180336257335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018905040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023084659,0.000017089931,0.9943468,0.0003142799,0.000102836224,0.00009264638,0.004776102,0.000049163817,0.00007024802],"genre_scores_gemma":[0.39508894,0.000001395254,0.5990223,0.000056980087,0.00001721511,0.0000045150955,0.005793007,0.000004613574,0.000010997862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982041,0.00012791989,0.00047533284,0.0005764121,0.0004310753,0.00018514621],"domain_scores_gemma":[0.99717045,0.00052414206,0.0003162218,0.0013298163,0.0005374912,0.00012189545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006173932,0.00015599756,0.00029487,0.0002833882,0.00017390253,0.00010817052,0.0012644846,0.000083740655,0.000030312558],"category_scores_gemma":[0.00025260902,0.00015150475,0.00009323906,0.0011383344,0.00011900841,0.00029130912,0.00025121408,0.00020874965,0.000006643281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004842478,0.00015379155,0.00033934598,0.000013361889,0.00029150653,0.0000021022395,0.00004070129,0.12508751,0.0019775813,0.8320449,0.0012213785,0.038822997],"study_design_scores_gemma":[0.00013732453,0.0000076149454,0.009662473,0.000001908821,0.0003081012,7.6037446e-7,2.5163172e-7,0.7616818,0.00008304133,0.22787513,0.0001205824,0.00012100118],"about_ca_topic_score_codex":0.0001347925,"about_ca_topic_score_gemma":0.00012820367,"teacher_disagreement_score":0.6365943,"about_ca_system_score_codex":0.000019108202,"about_ca_system_score_gemma":0.00023870215,"threshold_uncertainty_score":0.6178184},"labels":[],"label_agreement":null},{"id":"W2020243273","doi":"10.1002/cjce.21711","title":"Sequential Markov Chain Monte Carlo (MCMC) model discrimination","year":2012,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov chain Monte Carlo; Marginal likelihood; Monte Carlo method; Computer science; Model selection; Metropolis–Hastings algorithm; Applied mathematics; Algorithm; Statistics; Mathematics; Econometrics; Bayesian probability; Artificial intelligence","score_opus":0.017598596579455224,"score_gpt":0.2240046019156037,"score_spread":0.20640600533614847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020243273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04215371,0.0004933164,0.9553251,0.0013230303,0.00041634307,0.00003903018,0.0000016298235,0.000011490244,0.00023632229],"genre_scores_gemma":[0.86395264,0.0000013933942,0.135576,0.000117411866,0.000293617,0.0000013021611,1.7861854e-7,0.000009988408,0.0000474943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991664,0.000025869153,0.0002092098,0.00007137528,0.00017073212,0.00035638624],"domain_scores_gemma":[0.9991225,0.000038387025,0.00007401442,0.00018970188,0.00007287861,0.0005025013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006654393,0.000104503706,0.00013640124,0.00010122797,0.000052830856,0.000084506544,0.0005676665,0.000063774074,0.000003844744],"category_scores_gemma":[0.00009651611,0.00007677839,0.00009048181,0.00012862845,0.000024924873,0.00042281018,0.000031530864,0.00030784137,9.888793e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020927555,0.00005489177,0.0001328332,0.00012630063,0.00022362045,0.00011057615,0.015289733,0.1674113,0.23993756,0.44620287,0.0043651527,0.12612422],"study_design_scores_gemma":[0.00014784723,0.000008836805,0.000035607332,0.000040930452,0.000020616213,0.0001980888,0.000003408165,0.9712794,0.025464281,0.0022986112,0.00035120512,0.00015119242],"about_ca_topic_score_codex":0.00027113812,"about_ca_topic_score_gemma":0.000044349963,"teacher_disagreement_score":0.8217989,"about_ca_system_score_codex":0.00016950846,"about_ca_system_score_gemma":0.00020631983,"threshold_uncertainty_score":0.3130932},"labels":[],"label_agreement":null},{"id":"W2021096350","doi":"10.5539/ijsp.v4n2p73","title":"Comparison of Two Means of Two Log-Normal Distributions When Data is Singly Censored","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Statistics; Limit (mathematics); Test (biology); Chi-square test; Normal distribution; Log-normal distribution; Applied mathematics; Mathematical analysis","score_opus":0.10130105728472012,"score_gpt":0.3958758612656778,"score_spread":0.2945748039809577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021096350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012939602,0.00014858418,0.98376256,0.0008131829,0.00041096236,0.00006302978,0.0016608662,0.000003589026,0.00019761141],"genre_scores_gemma":[0.44063932,0.0000087764465,0.55925804,0.000023709032,0.000042551892,2.3146985e-7,0.000020786038,0.0000018513073,0.0000047689205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829274,0.00015341268,0.000735351,0.0001737111,0.00053830235,0.00010648184],"domain_scores_gemma":[0.99705476,0.0002507202,0.00064237433,0.00034260887,0.0015819774,0.00012755599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014064559,0.000090993,0.0002920082,0.00006295231,0.000027257316,0.000060874172,0.0010425695,0.000029603158,0.000012845964],"category_scores_gemma":[0.00045610862,0.00007572437,0.000040248466,0.00006890303,0.00016357869,0.0003487136,0.00035225978,0.00015724839,3.4550473e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012470521,0.00061787164,0.036806658,0.000047210207,0.00019955357,0.000014755471,0.0027549416,0.000269311,0.00036785495,0.83188474,0.0056304685,0.121281914],"study_design_scores_gemma":[0.0010934968,0.00023913987,0.0036980768,0.00005349415,0.000042915355,0.000057274938,0.000024236037,0.1091812,0.0013725847,0.8830589,0.0010772757,0.00010139397],"about_ca_topic_score_codex":0.00012801799,"about_ca_topic_score_gemma":0.000042357835,"teacher_disagreement_score":0.4276997,"about_ca_system_score_codex":0.000046404264,"about_ca_system_score_gemma":0.00023200746,"threshold_uncertainty_score":0.308795},"labels":[],"label_agreement":null},{"id":"W2023897752","doi":"10.1007/s11222-005-1308-7","title":"Importance sampling with the generalized exponential power density","year":2005,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Mathematics; Exponential function; Credence; Context (archaeology); Applied mathematics; Logarithm; Probability density function; Monte Carlo method; Statistical physics; Density estimation; Exponential family; Importance sampling; Statistics; Mathematical analysis; Physics","score_opus":0.01619264440647443,"score_gpt":0.2693408045406934,"score_spread":0.253148160134219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023897752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07218991,0.0001357555,0.92656547,0.0006328807,0.00008818427,0.00007030331,0.0000033539322,0.000040370986,0.00027374923],"genre_scores_gemma":[0.4220691,0.0000047132535,0.5773476,0.00047346362,0.000070499445,6.140734e-7,8.9588343e-7,0.0000043062364,0.000028833572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916416,0.000059940154,0.0001430263,0.00026300157,0.00014899952,0.00022086821],"domain_scores_gemma":[0.9994042,0.00013309735,0.000090635156,0.00024804994,0.00006190243,0.000062114595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035807388,0.00010971793,0.0001261397,0.000018801815,0.0003126964,0.00018933442,0.00023665362,0.000020904936,0.000004305492],"category_scores_gemma":[0.000012640627,0.00007062564,0.00001638721,0.00009004906,0.000049664508,0.000075429176,0.00015368531,0.00012001109,0.000001757492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072267912,0.000015348362,0.0003099584,0.0000062021877,0.000020147085,0.00001745594,0.0011760265,0.00023525784,0.00034645761,0.67553157,0.0010106015,0.32132378],"study_design_scores_gemma":[0.00084024266,0.0001173945,0.011733981,0.000034815308,0.000029408655,0.0001623389,0.000042238327,0.9303247,0.00050185533,0.04970589,0.0059887744,0.0005183613],"about_ca_topic_score_codex":0.00001190374,"about_ca_topic_score_gemma":0.000020865209,"teacher_disagreement_score":0.9300895,"about_ca_system_score_codex":0.000010288773,"about_ca_system_score_gemma":0.000027711305,"threshold_uncertainty_score":0.288003},"labels":[],"label_agreement":null},{"id":"W2023906997","doi":"10.1007/s00500-014-1557-5","title":"Variational learning of hierarchical infinite generalized Dirichlet mixture models and applications","year":2014,"lang":"en","type":"article","venue":"Soft Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"King Abdulaziz City for Science and Technology","keywords":"Hierarchical Dirichlet process; Computer science; Cluster analysis; Artificial intelligence; Dirichlet distribution; Inference; Latent Dirichlet allocation; Data mining; Pattern recognition (psychology); Hierarchical clustering; Machine learning; Topic model; Mathematics","score_opus":0.015220243628167348,"score_gpt":0.2629896730756922,"score_spread":0.24776942944752486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023906997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022354347,0.00013894225,0.9948858,0.0002848912,0.000061059356,0.00011830003,0.0000010314433,0.00011086152,0.0021637017],"genre_scores_gemma":[0.38252994,0.000004509159,0.61705935,0.00022087805,0.0001392335,0.0000045342063,0.000003465047,0.000006554303,0.000031523145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987119,0.00026383894,0.00027684943,0.0003434916,0.00019827204,0.00020566252],"domain_scores_gemma":[0.99892384,0.0004728872,0.00015307774,0.00026107815,0.00009896003,0.0000901676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079282036,0.00011959665,0.00021598933,0.000093625145,0.00020336994,0.000072776835,0.00034368373,0.00008139938,0.0000019579752],"category_scores_gemma":[0.00008223097,0.00011472382,0.000051974777,0.00027660767,0.00005262055,0.00015227505,0.0002904355,0.00025681008,0.0000015413633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015450751,0.000014752829,0.00020523244,0.000017034903,0.000009589526,2.540475e-7,0.00043665626,0.012644939,0.00033184685,0.804107,0.000021880885,0.18220927],"study_design_scores_gemma":[0.00019075933,0.000018357923,0.000364978,0.000012895656,0.0000047854296,0.000008538134,0.0000014087233,0.7419191,0.00005027197,0.25589013,0.0014428294,0.000095984935],"about_ca_topic_score_codex":0.000007618907,"about_ca_topic_score_gemma":3.334579e-7,"teacher_disagreement_score":0.72927415,"about_ca_system_score_codex":0.000008481383,"about_ca_system_score_gemma":0.0000377186,"threshold_uncertainty_score":0.46783015},"labels":[],"label_agreement":null},{"id":"W2024542855","doi":"10.1002/acs.1239","title":"Bayesian estimation of dynamic finite mixtures","year":2011,"lang":"en","type":"article","venue":"International Journal of Adaptive Control and Signal Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Global Institute for Water Security, University of Saskatchewan","keywords":"Dynamic Bayesian network; Pointer (user interface); Modal; Computer science; Feature (linguistics); Mixture model; Component (thermodynamics); Bayesian probability; Algorithm; Distinctive feature; Artificial intelligence","score_opus":0.017669833488606176,"score_gpt":0.266139785767202,"score_spread":0.2484699522785958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024542855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016123815,0.0011689805,0.99608994,0.00025675033,0.0001445762,0.00004280196,0.0000030391795,0.00000790402,0.0006736534],"genre_scores_gemma":[0.6703092,0.00001621294,0.3294958,0.00012292228,0.000040282554,6.549515e-7,1.9119955e-7,0.000003528897,0.000011217517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893886,0.00008321892,0.000415105,0.00012641572,0.00033405138,0.00010234512],"domain_scores_gemma":[0.9985414,0.00010511198,0.0005599547,0.000055715158,0.00066757604,0.00007022368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047867268,0.00010397265,0.0002143296,0.00020374717,0.000042156793,0.00006645852,0.00045162754,0.00004706537,0.0000094062],"category_scores_gemma":[0.000055855544,0.00008002877,0.00008022357,0.00008015804,0.00006737665,0.0007619635,0.000041842362,0.00014899262,3.407946e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020436407,0.000066344706,0.000050516428,0.000011679915,0.000107814994,0.000050006878,0.0014790038,0.0003654869,0.0046749944,0.011415096,0.000008603591,0.9815661],"study_design_scores_gemma":[0.00097016356,0.000264617,0.0015819962,0.00020424386,0.000028854387,0.00014421885,0.000026800975,0.8684082,0.0019640098,0.12629096,0.000012924277,0.000103017854],"about_ca_topic_score_codex":0.0000064942237,"about_ca_topic_score_gemma":8.7952407e-7,"teacher_disagreement_score":0.9814631,"about_ca_system_score_codex":0.00002188088,"about_ca_system_score_gemma":0.000109082444,"threshold_uncertainty_score":0.32634786},"labels":[],"label_agreement":null},{"id":"W2024725886","doi":"10.1080/03610918.2012.697240","title":"Edgeworth Expansion of the Moment-Based Test for Homogeneity in an NEF-QVF Mixture Model","year":2013,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Windsor","keywords":"Exponential family; Mathematics; Natural exponential family; Negative binomial distribution; Statistics; Exponential distribution; Homogeneity (statistics); Applied mathematics; Edgeworth series; Test statistic; Null distribution; Exponential function; Statistical hypothesis testing; Mathematical analysis; Poisson distribution","score_opus":0.10592330641825451,"score_gpt":0.4075235282450917,"score_spread":0.3016002218268372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024725886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021663725,0.00008265029,0.97691894,0.00049254013,0.000043237313,0.0006926467,0.000043927655,0.0000209338,0.00004141643],"genre_scores_gemma":[0.52061296,0.000007570209,0.4791741,0.00010179412,0.0000029649764,0.000047792506,0.000042140633,0.0000047342187,0.00000595068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886423,0.00023896738,0.00041843142,0.00021483803,0.00013772264,0.0001258308],"domain_scores_gemma":[0.9975856,0.0010727702,0.00019005028,0.0008065821,0.00030163504,0.00004335044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036153838,0.00010986753,0.00015326099,0.00015399372,0.00015673583,0.00007954319,0.00058637065,0.000073115414,0.0000011478429],"category_scores_gemma":[0.00013749146,0.00009681926,0.00002519001,0.00041140566,0.0000850774,0.00031426526,0.00015878584,0.0001337873,4.4244777e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004163144,0.00017780084,0.0032998172,0.000026289463,0.0000018643024,5.1093014e-8,0.00079967256,0.73896295,0.00025021806,0.08790261,0.000037178168,0.1685374],"study_design_scores_gemma":[0.00045672528,0.000037614263,0.026753841,0.000029084818,0.000004514104,1.7319745e-7,0.000015315502,0.84405535,0.00006159162,0.12848224,0.000014984344,0.00008859523],"about_ca_topic_score_codex":0.00004386561,"about_ca_topic_score_gemma":0.000119106655,"teacher_disagreement_score":0.49894923,"about_ca_system_score_codex":0.000043293916,"about_ca_system_score_gemma":0.00009959128,"threshold_uncertainty_score":0.39481747},"labels":[],"label_agreement":null},{"id":"W2025014254","doi":"10.1109/icmcs.2011.5945719","title":"A Bayesian approach for texture images classification and retrieval","year":2011,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reversible-jump Markov chain Monte Carlo; Computer science; Artificial intelligence; Mixture model; Bayesian probability; Image retrieval; Image texture; Pattern recognition (psychology); Gaussian; Markov chain Monte Carlo; Posterior probability; Computer vision; Image (mathematics); Image processing","score_opus":0.056468875206609696,"score_gpt":0.2725581751907122,"score_spread":0.21608929998410248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025014254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034859975,0.00009708134,0.95711654,0.00027046376,0.000053581494,0.0002460735,0.0000016674628,0.00009778273,0.042081952],"genre_scores_gemma":[0.1953819,0.000008492392,0.8033814,0.00021698917,0.000035222994,0.0000131562565,0.0000015600084,0.000005773243,0.00095553487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992447,0.000045023626,0.00011715116,0.00035050168,0.000079439116,0.00016319766],"domain_scores_gemma":[0.9994499,0.000034615015,0.00004322316,0.00033688798,0.000054671647,0.000080705315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038298764,0.00009419314,0.000107327745,0.000049835453,0.00007884251,0.000071705035,0.0002985803,0.000080979116,0.0000071210548],"category_scores_gemma":[0.00002712273,0.00007084531,0.000038026476,0.00013424794,0.00003711977,0.00028141952,0.00006242506,0.00006795366,0.0000011261176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019697578,0.000053989555,0.00010810662,0.000026321928,0.000009548256,6.6522506e-7,0.00078377506,8.058863e-8,0.0024383753,0.78623754,0.0019481778,0.20837373],"study_design_scores_gemma":[0.00066706754,0.00020054085,0.0071787285,0.000007777547,0.000022081498,0.000044080323,0.00007374011,0.6810183,0.010403122,0.29834282,0.0016281399,0.0004135658],"about_ca_topic_score_codex":0.0000048930747,"about_ca_topic_score_gemma":3.667079e-7,"teacher_disagreement_score":0.68101823,"about_ca_system_score_codex":0.0000070803303,"about_ca_system_score_gemma":0.000021206704,"threshold_uncertainty_score":0.2888988},"labels":[],"label_agreement":null},{"id":"W2025219341","doi":"10.1002/cjs.11192","title":"Simultaneous fixed and random effects selection in finite mixture of linear mixed‐effects models","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Random effects model; Generalized linear mixed model; Mixed model; Mathematics; Selection (genetic algorithm); Fixed effects model; Statistical physics; Applied mathematics; Statistics; Computer science; Physics; Artificial intelligence; Medicine; Panel data; Internal medicine","score_opus":0.007377280002936357,"score_gpt":0.21401831149417658,"score_spread":0.20664103149124022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025219341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017961698,0.00051924645,0.9807944,0.00011438463,0.00030932494,0.0002205885,0.000018842518,0.000003707041,0.00005776042],"genre_scores_gemma":[0.50740075,0.000027446295,0.49239054,0.000102624515,0.00003677502,0.0000017722969,7.2815317e-7,0.0000071676586,0.000032164902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986509,0.00029096717,0.00045168193,0.00015498642,0.00017332284,0.00027815488],"domain_scores_gemma":[0.9968906,0.0018910671,0.00027890803,0.00012836151,0.0003654953,0.0004455861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047700084,0.0001455403,0.00040445154,0.0003204447,0.00006498606,0.00007962383,0.00027673095,0.00010837767,0.0000066884354],"category_scores_gemma":[0.0010383497,0.00012471848,0.000044032106,0.00027632524,0.00005902963,0.0002788397,0.000016751896,0.00030800575,0.0000017224637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091273156,0.000100967234,0.0016144915,0.0009409124,0.00018493978,0.0022359935,0.007167736,0.05411122,0.004319392,0.124277435,0.009989936,0.7949657],"study_design_scores_gemma":[0.0015545507,0.00035359172,0.0013637913,0.0001865418,0.000026630558,0.00015287234,0.000008961753,0.88312376,0.0011844208,0.11172718,0.00014376572,0.00017392373],"about_ca_topic_score_codex":0.0016121349,"about_ca_topic_score_gemma":0.002893117,"teacher_disagreement_score":0.8290126,"about_ca_system_score_codex":0.00006073622,"about_ca_system_score_gemma":0.0004085261,"threshold_uncertainty_score":0.50858724},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.037730407018985355,"score_gpt":0.2846753339540069,"score_spread":0.24694492693502154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025952763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008773706,0.00007267336,0.98949367,0.00089698576,0.00026060452,0.0003418298,0.000013983463,0.0001351736,0.000011348078],"genre_scores_gemma":[0.5366978,0.000021425429,0.46298674,0.00016712431,0.000082754224,0.000010168935,0.000014268914,0.0000045824227,0.0000151347485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890155,0.00008318352,0.0002676621,0.0004350138,0.00011708933,0.00019549814],"domain_scores_gemma":[0.99922264,0.00014594807,0.00005438563,0.00036733865,0.00012011989,0.000089576926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031800463,0.00016020532,0.00017996416,0.000115781004,0.00047961975,0.00027937602,0.00017504298,0.00009557566,0.0000012528893],"category_scores_gemma":[0.0000109172715,0.00015729528,0.0000644909,0.00013002678,0.00001158463,0.00047363405,0.000009300996,0.00010478216,5.7209195e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004310612,0.00004764998,3.8255942e-7,0.0000036734898,0.00001344937,2.4918762e-7,0.00018088771,0.69782495,0.00066220784,0.005641019,0.000006686453,0.29557574],"study_design_scores_gemma":[0.001395675,0.00018013432,0.000027838483,0.000015013735,0.00003134909,0.0000037910506,0.0000011434803,0.9587752,0.00026007518,0.03909825,0.00004421819,0.00016727278],"about_ca_topic_score_codex":0.00001202239,"about_ca_topic_score_gemma":0.0000034421078,"teacher_disagreement_score":0.52792406,"about_ca_system_score_codex":0.000021996853,"about_ca_system_score_gemma":0.000032334454,"threshold_uncertainty_score":0.6414315},"labels":[],"label_agreement":null},{"id":"W2026103592","doi":"10.1016/j.insmatheco.2005.10.001","title":"The preservation of classes of discrete distributions under convolution and mixing","year":2005,"lang":"en","type":"article","venue":"Insurance Mathematics and Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Mixing (physics); Convolution (computer science); Computer science; Mathematics; Applied mathematics; Statistical physics; Artificial intelligence; Physics","score_opus":0.019326933658988934,"score_gpt":0.24935963167079728,"score_spread":0.23003269801180834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026103592","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33764002,0.00029271786,0.6611961,0.0005551708,0.000023661081,0.00005158129,0.000010262479,0.0000042930246,0.00022616325],"genre_scores_gemma":[0.746495,0.0005775987,0.25288117,0.000012234922,0.0000111648515,0.0000030333085,6.975529e-7,0.0000022227632,0.000016888202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99955094,0.000012996149,0.0002406246,0.00009013435,0.00002823102,0.00007704743],"domain_scores_gemma":[0.99940205,0.00018705551,0.00016901927,0.00018412639,0.000036384048,0.000021386184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029592792,0.000053295535,0.00011909932,0.00001499129,0.00008510425,0.000043971944,0.0001269407,0.000028641938,3.0185092e-7],"category_scores_gemma":[0.00002825979,0.000039368566,0.000020647558,0.00003752172,0.00008766913,0.00026978322,0.00006526133,0.00003442818,1.7215534e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014358212,0.000013251095,0.00040705784,0.000038522412,0.000010108903,1.52526e-8,0.00032330287,0.00012421567,0.00030985315,0.9781582,0.000010099808,0.020603979],"study_design_scores_gemma":[0.00018840299,0.000023062323,0.008815255,0.000042548723,0.000007053306,0.000005931655,0.000052697193,0.43446016,0.002536624,0.5532712,0.0005134888,0.000083587576],"about_ca_topic_score_codex":0.0000054781412,"about_ca_topic_score_gemma":0.00001726848,"teacher_disagreement_score":0.43433595,"about_ca_system_score_codex":0.000009697265,"about_ca_system_score_gemma":0.000015023093,"threshold_uncertainty_score":0.16054036},"labels":[],"label_agreement":null},{"id":"W2026415815","doi":"10.1007/s11464-014-0408-0","title":"Gamma-Dirichlet algebra and applications","year":2014,"lang":"en","type":"article","venue":"Frontiers of Mathematics in China","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Imperial Bank of Commerce (Canada); McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Beijing Normal University","keywords":"Mathematics; Hierarchical Dirichlet process; Dirichlet distribution; Dirichlet process; Generalized Dirichlet distribution; Dirichlet series; Pure mathematics; Mathematical analysis; Statistics","score_opus":0.0068981826515419386,"score_gpt":0.23511562546311296,"score_spread":0.22821744281157103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026415815","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018017413,0.00040219867,0.9896001,0.00031654467,0.000079660036,0.00016446333,0.0000010779021,0.000031454732,0.007602741],"genre_scores_gemma":[0.054811344,0.00004174159,0.9449176,0.00004959521,0.000027471673,0.000021538308,4.850138e-7,0.0000070143847,0.00012316702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999273,0.000046881018,0.00023199861,0.00018984494,0.00012434537,0.00013389943],"domain_scores_gemma":[0.99927735,0.00007453926,0.00010873842,0.00046933137,0.000019451843,0.00005057639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006421145,0.000091392496,0.00022253487,0.00010498265,0.000032122676,0.000028686349,0.00044777864,0.000052810534,0.0000012273734],"category_scores_gemma":[0.000058435613,0.00008038987,0.000031105,0.00017997618,0.000055307133,0.00011496692,0.0001175738,0.00009324986,0.000001918441],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.391167e-7,0.00008301697,0.00029867268,0.000082745566,0.0000072025687,3.8445586e-7,0.0011095075,0.0000053743893,0.00007102059,0.8868509,0.0025353422,0.1089553],"study_design_scores_gemma":[0.00016525271,0.000021499327,0.0007191786,0.000021699487,0.000005290274,0.000005096822,0.00001944068,0.08867697,0.00040173923,0.9074322,0.0024300765,0.00010155252],"about_ca_topic_score_codex":0.0000035727003,"about_ca_topic_score_gemma":0.0000014392336,"teacher_disagreement_score":0.10885375,"about_ca_system_score_codex":0.000009672156,"about_ca_system_score_gemma":0.0000122857755,"threshold_uncertainty_score":0.3278204},"labels":[],"label_agreement":null},{"id":"W2027152673","doi":"10.1081/sta-100002259","title":"REGRESSION IN THE BIVARIATE POISSON DISTRIBUTION","year":2001,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Poisson regression; Mathematics; Statistics; Poisson distribution; Regression diagnostic; Regression analysis; Cross-sectional regression; Linear regression; Count data; Bivariate data; Generalized linear model; Marginal distribution; Econometrics; Bayesian multivariate linear regression; Random variable; Population","score_opus":0.03431513293694066,"score_gpt":0.40948670569743656,"score_spread":0.3751715727604959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027152673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007272271,0.0016178176,0.99506676,0.0010070818,0.000079896614,0.00016645469,0.000009688509,0.000023548691,0.0013015091],"genre_scores_gemma":[0.12197566,0.0014690818,0.8760915,0.0003039618,0.000010362657,0.000035344652,0.000023272552,0.000004719132,0.00008610394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895943,0.009613429,0.00029598095,0.00021628519,0.0001020576,0.00017799482],"domain_scores_gemma":[0.9954613,0.003351598,0.000113410875,0.0009922921,0.000043212203,0.000038228263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012591336,0.00011144349,0.00016222062,0.00007610025,0.00016880927,0.00009789342,0.00086407684,0.00007520091,0.000007352287],"category_scores_gemma":[0.0008479558,0.000077180564,0.000017876835,0.00044299266,0.00010874962,0.00020973192,0.0002299666,0.00031513665,0.0000015845787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016761474,0.000026779115,0.00012115613,0.000004299368,0.0000012046172,0.0000026462328,0.0014378857,0.0000022027805,0.00006253556,0.61314094,0.000065941975,0.38511765],"study_design_scores_gemma":[0.00027068958,0.00002301486,0.014523904,0.00006814034,0.0000050906747,0.000022549595,0.0001078532,0.010050658,0.00009361309,0.9677697,0.00696035,0.00010445224],"about_ca_topic_score_codex":0.000043880333,"about_ca_topic_score_gemma":0.000021056332,"teacher_disagreement_score":0.3850132,"about_ca_system_score_codex":0.00002978775,"about_ca_system_score_gemma":0.000023386521,"threshold_uncertainty_score":0.43639308},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02441071631197747,"score_gpt":0.2880331788376962,"score_spread":0.26362246252571875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029217165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008611817,0.000008240526,0.997566,0.00088483375,0.000055052642,0.00007476995,0.0011528146,0.000045690696,0.00012648429],"genre_scores_gemma":[0.17018,0.0000023532955,0.8251161,0.00031479934,0.000053601376,0.0000043627833,0.0042793704,0.000006010198,0.00004340551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983581,0.0002829209,0.00023539236,0.0004942203,0.0004076669,0.00022171269],"domain_scores_gemma":[0.9981121,0.00048846775,0.00017253157,0.0009627922,0.00016128659,0.000102844235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080336677,0.0001510609,0.00021181634,0.00008765271,0.00033805508,0.00030525218,0.0011214701,0.000033150736,0.00001824549],"category_scores_gemma":[0.000092636976,0.000102043035,0.0000432075,0.00091481506,0.000085533655,0.00040508955,0.0005536236,0.00013665146,0.000017149545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018810033,0.00006350973,0.0009538177,0.000017739672,0.00085719867,0.000015014463,0.00033702332,0.33584172,0.00000570416,0.51974726,0.009915096,0.13222711],"study_design_scores_gemma":[0.0002010404,0.000022989969,0.021965612,0.000004064371,0.00034785477,0.00000473066,0.0000031297013,0.9583609,0.0000012942414,0.016635846,0.002303387,0.00014914607],"about_ca_topic_score_codex":0.00027283205,"about_ca_topic_score_gemma":0.0005234349,"teacher_disagreement_score":0.6225192,"about_ca_system_score_codex":0.00003145169,"about_ca_system_score_gemma":0.000061558465,"threshold_uncertainty_score":0.41611943},"labels":[],"label_agreement":null},{"id":"W2029359551","doi":"10.1002/sim.781","title":"Testing for the presence of cured patients: a simulation study","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Council Canada; Alberta Heritage Foundation for Medical Research","keywords":"Censoring (clinical trials); Weibull distribution; Statistics; Likelihood-ratio test; Mathematics; Hazard ratio; Score test; Null distribution; Null hypothesis; Null (SQL); Maximum likelihood; Asymptotic distribution; Sample size determination; Applied mathematics; Statistical hypothesis testing; Econometrics; Test statistic; Confidence interval; Computer science","score_opus":0.058367907964955994,"score_gpt":0.38105411797635275,"score_spread":0.32268621001139675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029359551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002509654,0.00006251787,0.99616224,0.00017306708,0.00024231526,0.00063485,0.000008111172,0.000011600427,0.00019567042],"genre_scores_gemma":[0.5376808,0.00000288159,0.46217945,0.000054404274,0.000038781418,0.000017392287,0.0000014384143,0.0000030460108,0.000021820313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990759,0.00009717941,0.00028976772,0.00016607942,0.00024339625,0.0001277163],"domain_scores_gemma":[0.9951166,0.004185748,0.00012061621,0.00028923023,0.00026233378,0.000025492382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094564434,0.000068902686,0.00015020464,0.00005619522,0.00005258796,0.0000082684355,0.00034011086,0.000017666436,0.0000035394473],"category_scores_gemma":[0.004125593,0.000042642212,0.0000075370235,0.00036343408,0.000058224072,0.000061829065,0.0000544474,0.000074363335,2.2004866e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036911748,0.00035906018,0.055562306,0.00004419687,0.000018412218,0.000009006506,0.007135235,0.0044825138,0.00006216497,0.0789133,0.0010132807,0.8523636],"study_design_scores_gemma":[0.001108118,0.00068490754,0.07407087,0.000050295566,0.000015368576,4.7019694e-7,0.00008801268,0.8349212,0.0000035624503,0.08880323,0.00019891631,0.000055086224],"about_ca_topic_score_codex":0.00007691734,"about_ca_topic_score_gemma":0.00002817902,"teacher_disagreement_score":0.8523085,"about_ca_system_score_codex":0.000012582045,"about_ca_system_score_gemma":0.000022363804,"threshold_uncertainty_score":0.49390182},"labels":[],"label_agreement":null},{"id":"W2031037082","doi":"10.6000/1929-6029.2014.03.02.8","title":"Efficient Blockwise Permutation Tests Preserving Exchangeability","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Center for Research Resources; National Institute of General Medical Sciences; National Institute on Aging; National Institutes of Health; U.S. Social Security Administration","keywords":"Permutation (music); Statistic; Test statistic; Resampling; Set (abstract data type); Algorithm; Mathematics; Voxel; Data set; Random permutation; Computer science; Pattern recognition (psychology); Artificial intelligence; Block (permutation group theory); Statistical hypothesis testing; Data mining; Statistics; Combinatorics","score_opus":0.056245631371795404,"score_gpt":0.4453815832593215,"score_spread":0.3891359518875261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031037082","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020640012,0.00008284475,0.9725132,0.0046111266,0.0007211459,0.000072204806,0.0000055393643,0.0000064107753,0.0013475401],"genre_scores_gemma":[0.62056506,0.000054193613,0.3788717,0.00014831468,0.00030597879,0.00000359418,0.0000010702189,0.0000051448833,0.00004489762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939025,0.0010040632,0.00058565184,0.00020972427,0.004010431,0.00028761526],"domain_scores_gemma":[0.99337214,0.0039804773,0.00015640099,0.00022794648,0.0019722215,0.0002908171],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014176053,0.00007902539,0.00017666571,0.00048703895,0.00005145895,0.00013558257,0.0019887863,0.000087250584,0.00015667197],"category_scores_gemma":[0.022267371,0.00006428893,0.0000407906,0.0003179396,0.00015793942,0.00010405199,0.0004479263,0.0008713328,0.00000963618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043574408,0.00030356395,0.0010878977,0.000029000295,0.000021423664,0.00042774406,0.0010121318,0.00049216143,0.0001463398,0.27964875,0.002179729,0.71460766],"study_design_scores_gemma":[0.00063810044,0.0001543967,0.009289193,0.00019400235,0.0000016718542,0.00010593558,0.000018920953,0.70632,0.000108996726,0.28147417,0.0016216235,0.000072973846],"about_ca_topic_score_codex":0.000045802462,"about_ca_topic_score_gemma":0.000048915943,"teacher_disagreement_score":0.7145347,"about_ca_system_score_codex":0.00019510262,"about_ca_system_score_gemma":0.00041449998,"threshold_uncertainty_score":0.9859685},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_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","score_opus":0.09939433401187582,"score_gpt":0.2985575540033773,"score_spread":0.1991632199915015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031212901","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059876643,0.000049950857,0.9977868,0.00027624986,0.00061234034,0.00002887947,0.00029539072,0.000002658211,0.00034894544],"genre_scores_gemma":[0.28959006,0.0000021539586,0.7102405,0.00008669934,0.00005320163,1.04274896e-7,0.000003212693,0.0000053481567,0.000018758266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991363,0.000031263546,0.00033106343,0.0001302753,0.00016653222,0.00020452129],"domain_scores_gemma":[0.9983247,0.00009628603,0.0002392785,0.00060147134,0.0002771275,0.00046114245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006256946,0.00008184599,0.00018268614,0.0001772934,0.000060305825,0.000073386844,0.0013733369,0.000049756585,0.000023464601],"category_scores_gemma":[0.00022153977,0.000075612734,0.000026265734,0.00012180036,0.000079807585,0.00026606442,0.00005843075,0.0003026571,9.541334e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015315849,0.000042983625,0.0023975577,0.00012127174,0.00007321832,0.0009016725,0.00068874663,0.008561687,0.0023114292,0.5728716,0.027975999,0.38403848],"study_design_scores_gemma":[0.00018123479,0.00004629264,0.00066690746,0.000025730402,0.000016404649,0.000103711965,0.0000021438275,0.9689576,0.00013038151,0.028818062,0.0009627321,0.00008877712],"about_ca_topic_score_codex":0.0006173212,"about_ca_topic_score_gemma":0.021577574,"teacher_disagreement_score":0.96039593,"about_ca_system_score_codex":0.000020734888,"about_ca_system_score_gemma":0.0019673721,"threshold_uncertainty_score":0.9962761},"labels":[],"label_agreement":null},{"id":"W2032156573","doi":"10.2307/3316098","title":"Testing circular symmetry","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Monte Carlo method; Test statistic; Mathematics; Statistic; Symmetry (geometry); Sample (material); Statistics; Statistical hypothesis testing; Sampling distribution; Applied mathematics; Geometry; Physics","score_opus":0.04607588704548786,"score_gpt":0.233857456048734,"score_spread":0.18778156900324616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032156573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003015301,0.00084210106,0.9939116,0.00033989077,0.00049766095,0.000024166357,0.000019974648,0.000005815935,0.004057261],"genre_scores_gemma":[0.1592055,0.000007928851,0.84015507,0.0004116859,0.00011109578,1.7879778e-7,1.9594926e-7,0.0000068982404,0.0001014641],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991648,0.00006056069,0.00026746403,0.00009589986,0.00015052465,0.00026075353],"domain_scores_gemma":[0.99859077,0.00016928058,0.00016086208,0.0001903007,0.00028173538,0.00060702575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003346891,0.000080702564,0.00014745015,0.00020002412,0.00010985429,0.00013727655,0.00049738854,0.000041196385,0.000059191778],"category_scores_gemma":[0.0005662205,0.00007632113,0.000032701493,0.00030602273,0.000041552503,0.00017492562,0.000011894958,0.00020582811,0.00001602758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2940173e-7,0.000008711614,0.0011293611,0.000018146171,0.0000234953,0.001770283,0.00051824923,0.000020337295,0.00009963366,0.3544445,0.033160195,0.60880685],"study_design_scores_gemma":[0.0009894408,0.00054613966,0.012748539,0.00025911312,0.00009133288,0.0053093764,0.00005133083,0.2035073,0.00027852843,0.6964086,0.07893298,0.0008772891],"about_ca_topic_score_codex":0.00032943796,"about_ca_topic_score_gemma":0.00022134613,"teacher_disagreement_score":0.6079296,"about_ca_system_score_codex":0.000072060124,"about_ca_system_score_gemma":0.00033292983,"threshold_uncertainty_score":0.3112285},"labels":[],"label_agreement":null},{"id":"W2032180763","doi":"10.1002/gepi.20429","title":"Bayesian mixture modeling of gene‐environment and gene‐gene interactions","year":2009,"lang":"en","type":"article","venue":"Genetic Epidemiology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute","funders":"National Human Genome Research Institute; National Institutes of Health; Cancer Research UK","keywords":"Curse of dimensionality; Bayesian probability; Set (abstract data type); Gene; Computer science; Computational biology; Multifactor dimensionality reduction; Bayes' theorem; Bayesian hierarchical modeling; Genotyping; Data set; Mixture model; Biology; Genetics; Machine learning; Artificial intelligence","score_opus":0.03657026031436507,"score_gpt":0.30264877891441166,"score_spread":0.2660785186000466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032180763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014689913,0.0040765298,0.97722197,0.0031764146,0.00022984925,0.00016683264,0.0000045273146,0.000042168787,0.00039182274],"genre_scores_gemma":[0.27103233,0.0006600878,0.72659844,0.0015249433,0.00010424789,0.000008572211,0.00000309106,0.000008265901,0.00005999908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755573,0.00059697486,0.0006550051,0.0006570291,0.00009487768,0.0004404057],"domain_scores_gemma":[0.9985262,0.00028888477,0.00020266842,0.0007553623,0.000033586613,0.00019327937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009081206,0.00022607238,0.0005342782,0.00012332173,0.000097414784,0.0000104857545,0.00047959734,0.00017505643,0.000016710212],"category_scores_gemma":[0.00012983166,0.0002014905,0.00011536134,0.00011461702,0.000077945886,0.000087677574,0.00013083254,0.00021862693,0.0000066838456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031415115,0.00019669236,0.002269271,0.000029717168,0.00012291965,0.000035182034,0.0011733985,0.08438227,0.097602494,0.05239705,0.0007186205,0.761041],"study_design_scores_gemma":[0.00021870059,0.00017611348,0.003440442,0.000011708403,0.000026569069,0.00019180418,0.000004614883,0.79287684,0.004215631,0.19811164,0.0004988526,0.00022711794],"about_ca_topic_score_codex":0.000026685006,"about_ca_topic_score_gemma":0.000003094273,"teacher_disagreement_score":0.76081383,"about_ca_system_score_codex":0.000029547791,"about_ca_system_score_gemma":0.00003495846,"threshold_uncertainty_score":0.8216544},"labels":[],"label_agreement":null},{"id":"W2033713899","doi":"10.1002/sta4.43","title":"A mixture of common skew‐t factor analysers","year":2014,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Component (thermodynamics); Maximization; Factor (programming language); Correlation clustering","score_opus":0.012682161023882794,"score_gpt":0.27602934686355024,"score_spread":0.26334718583966743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033713899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01173439,0.00007004057,0.98287547,0.00037493155,0.00015324133,0.000049997685,0.000005722618,0.000042069263,0.0046941447],"genre_scores_gemma":[0.56183314,0.0000048926677,0.43768442,0.00025737236,0.00002437776,0.0000013316704,0.0000010582098,0.0000042657134,0.00018915127],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992107,0.00013241533,0.00014542583,0.00019502219,0.00015467739,0.0001617201],"domain_scores_gemma":[0.99923855,0.000087235996,0.00007435858,0.00048430258,0.000041385912,0.000074186915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002151734,0.00008728879,0.00018838666,0.00006082019,0.000033175813,0.000029120449,0.00046862705,0.000048105354,0.000016147145],"category_scores_gemma":[0.000024915622,0.00006811344,0.00007319985,0.00020448344,0.000030387533,0.00012556641,0.000088466884,0.00009039418,0.0000077202],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007799024,0.00007033981,0.0013256675,0.000046013512,0.00004263963,0.0000048819315,0.0019979058,0.000014416346,0.0076763486,0.3416377,0.0033322051,0.64384407],"study_design_scores_gemma":[0.0013063553,0.00059009925,0.016854152,0.00009055112,0.000051036965,0.000017218536,0.000032346135,0.16025996,0.0637313,0.68687505,0.0693025,0.0008894436],"about_ca_topic_score_codex":0.000028122056,"about_ca_topic_score_gemma":0.000015786214,"teacher_disagreement_score":0.64295465,"about_ca_system_score_codex":0.000008970695,"about_ca_system_score_gemma":0.00001933492,"threshold_uncertainty_score":0.27775854},"labels":[],"label_agreement":null},{"id":"W2033839360","doi":"10.1016/j.jmva.2007.01.009","title":"Nonparametric tests of independence between random vectors","year":2007,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Mathematics; Multivariate random variable; Independence (probability theory); Nonparametric statistics; Marginal distribution; Random variable; Univariate; Joint probability distribution; Distance correlation; Multivariate normal distribution; Asymptotic distribution; Applied mathematics; Statistics; Multivariate statistics","score_opus":0.020653926818142224,"score_gpt":0.3207989578959037,"score_spread":0.30014503107776147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033839360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122081794,0.00026743067,0.8771097,0.00008069789,0.00013634557,0.000050027153,0.0000014366398,0.000009599956,0.00026298536],"genre_scores_gemma":[0.625094,0.000020988227,0.3747475,0.000022295124,0.00008449915,1.7359699e-7,2.8266862e-7,0.0000043234613,0.000025946027],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9973174,0.00026945036,0.00110144,0.00022805983,0.0008003127,0.00028334462],"domain_scores_gemma":[0.99603456,0.0013920363,0.0012973225,0.00044026072,0.00062050554,0.00021531453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058544986,0.00016206836,0.00087556447,0.0019471104,0.000055806344,0.000056966743,0.0010416975,0.00014433096,0.000014042274],"category_scores_gemma":[0.00071865885,0.00012034774,0.00067099195,0.004825599,0.000039779603,0.00046561714,0.00011627095,0.0003848172,0.0000021946503],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035920122,0.0007057206,0.36535472,0.00005924588,0.010811164,0.00039466986,0.0032659932,0.0040521026,0.025056966,0.008890607,0.00013201273,0.5809176],"study_design_scores_gemma":[0.0035927475,0.00036647567,0.9371275,0.00006777331,0.0030123843,0.000045511657,0.000030763425,0.02500591,0.019908974,0.010206496,0.00020378146,0.00043169266],"about_ca_topic_score_codex":0.00012485373,"about_ca_topic_score_gemma":0.000016313179,"teacher_disagreement_score":0.5804859,"about_ca_system_score_codex":0.000054228407,"about_ca_system_score_gemma":0.00010381357,"threshold_uncertainty_score":0.4907638},"labels":[],"label_agreement":null},{"id":"W2033996602","doi":"10.1016/j.compeleceng.2015.03.018","title":"A hierarchical Dirichlet process mixture of generalized Dirichlet distributions for feature selection","year":2015,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"King Abdulaziz City for Science and Technology","keywords":"Hierarchical Dirichlet process; Dirichlet process; Generalized Dirichlet distribution; Dirichlet distribution; Cluster analysis; Computer science; Feature (linguistics); Feature selection; Artificial intelligence; Hierarchical clustering; Pattern recognition (psychology); Mixture model; Latent Dirichlet allocation; Model selection; Data mining; Algorithm; Mathematics; Bayesian probability; Topic model; Dirichlet's energy","score_opus":0.014811587014575469,"score_gpt":0.2659668732039385,"score_spread":0.25115528618936306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033996602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026373728,0.0005406321,0.994836,0.00085590006,0.00039845667,0.0003691276,0.000014872045,0.00031139015,0.000036251196],"genre_scores_gemma":[0.16978405,0.0000071366594,0.82962704,0.0001398966,0.00028186152,0.000064367014,0.00003309587,0.000023965073,0.000038583363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828625,0.00007188982,0.0003072586,0.00048589715,0.000310441,0.0005382433],"domain_scores_gemma":[0.9987918,0.00020024451,0.0000979661,0.00030091245,0.00028838712,0.00032066618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035824484,0.0002654337,0.0004487852,0.00020948505,0.00008072092,0.00008763509,0.0006765105,0.00019813082,4.9293374e-7],"category_scores_gemma":[0.00025073986,0.00024044469,0.00017139381,0.0014462981,0.000023899009,0.00023348273,0.000101125916,0.0003981835,8.328918e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015917537,0.0005433363,0.00018453969,0.0002813181,0.0002815609,0.000023869778,0.0010884712,0.042690597,0.016819887,0.7514175,0.041036144,0.14547358],"study_design_scores_gemma":[0.00079070154,0.00025529793,0.0001769328,0.00002642815,0.000024397825,0.000049048915,4.651518e-7,0.9761686,0.006386603,0.010585671,0.00523206,0.00030383636],"about_ca_topic_score_codex":0.0000036610002,"about_ca_topic_score_gemma":3.8452382e-7,"teacher_disagreement_score":0.93347794,"about_ca_system_score_codex":0.00012163979,"about_ca_system_score_gemma":0.00015931665,"threshold_uncertainty_score":0.980505},"labels":[],"label_agreement":null},{"id":"W2034224025","doi":"10.1016/j.insmatheco.2010.09.002","title":"Distributional analysis of a generalization of the Polya process","year":2010,"lang":"en","type":"article","venue":"Insurance Mathematics and Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Infinite divisibility; Geometric distribution; Negative binomial distribution; Generalization; Poisson distribution; Compound Poisson distribution; Exponential distribution; Distribution (mathematics); Compound Poisson process; Applied mathematics; Mathematical analysis; Pure mathematics; Probability distribution; Poisson process; Statistics; Poisson regression","score_opus":0.008771929261194198,"score_gpt":0.23856473010758694,"score_spread":0.22979280084639275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034224025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5132619,0.000010990873,0.4864378,0.00006246166,0.000045575416,0.000028055183,0.00002373419,0.0000023040361,0.00012714446],"genre_scores_gemma":[0.8483709,0.000016574068,0.15157168,0.00002018483,0.000008192739,0.0000023756725,0.0000014932447,0.0000019010869,0.0000066792327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995768,0.000007096694,0.00022095733,0.00009566099,0.000040863495,0.000058624595],"domain_scores_gemma":[0.99941844,0.00003735385,0.00020692234,0.00026269566,0.000055424756,0.00001918058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020534243,0.00005033403,0.00016877291,0.00004269247,0.00003408179,0.000019656107,0.000256343,0.0000347844,0.000003261673],"category_scores_gemma":[0.000023013568,0.000035744648,0.000062252686,0.00019152988,0.000054497134,0.00008247997,0.000048916263,0.000043576783,1.3181432e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.703868e-7,0.000046169313,0.012007133,0.000047030848,0.000081354265,3.0037672e-8,0.00061471923,0.0005359745,0.0016358775,0.9805071,0.000003928815,0.00451985],"study_design_scores_gemma":[0.00010958552,0.0000075787607,0.04195911,0.000009947349,0.000057568755,0.0000033074602,0.000008379727,0.721027,0.009284455,0.22741634,0.000031833613,0.00008488874],"about_ca_topic_score_codex":0.000004625202,"about_ca_topic_score_gemma":0.000017999419,"teacher_disagreement_score":0.75309074,"about_ca_system_score_codex":0.0000031541933,"about_ca_system_score_gemma":0.000026194166,"threshold_uncertainty_score":0.14576244},"labels":[],"label_agreement":null},{"id":"W2034953682","doi":"10.1080/03610926.2010.547646","title":"Unification of Dirichlet Methodology","year":2012,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet distribution; Unification; Hypergeometric distribution; Sampling (signal processing); Mathematics; Object (grammar); Sample (material); Applied mathematics; Statistics; Computer science; Mathematical analysis; Artificial intelligence","score_opus":0.09267795470884393,"score_gpt":0.4420655647001156,"score_spread":0.34938760999127166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034953682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034332726,0.00456937,0.9917133,0.00014160572,0.0001385197,0.00012571884,0.000007238594,0.00002568743,0.002935227],"genre_scores_gemma":[0.09606812,0.0006738364,0.9029741,0.00013449248,0.000011625785,0.000024477027,0.0000061849464,0.0000068536365,0.000100280085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98603946,0.013136409,0.00038756,0.00016543246,0.0000742333,0.00019692087],"domain_scores_gemma":[0.9912487,0.007375317,0.00021317806,0.000997081,0.00008740999,0.00007830173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018738005,0.00010421462,0.0002576243,0.000146727,0.0000764304,0.000018004868,0.00062017556,0.00008826606,0.000014222303],"category_scores_gemma":[0.0016854882,0.00009701399,0.000022179178,0.00029574594,0.00020635535,0.00027269093,0.00028303565,0.00019075783,0.0000015380537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009369256,0.00003289246,0.00021920358,0.00001598037,0.0000052661535,6.614299e-8,0.0020450319,9.637943e-7,0.0016467628,0.6349503,0.000025233443,0.36104897],"study_design_scores_gemma":[0.0001743318,0.000021693166,0.008330961,0.000020337395,0.00001393364,0.000007941993,0.00009122607,0.0018696183,0.0041844747,0.98335046,0.0018220862,0.00011294273],"about_ca_topic_score_codex":0.0000135169885,"about_ca_topic_score_gemma":0.0000017387666,"teacher_disagreement_score":0.36093602,"about_ca_system_score_codex":0.000016797208,"about_ca_system_score_gemma":0.000026638856,"threshold_uncertainty_score":0.6494256},"labels":[],"label_agreement":null},{"id":"W2035595990","doi":"10.1007/s10260-013-0242-7","title":"Jointly modeling time-to-event and longitudinal data: a Bayesian approach","year":2013,"lang":"en","type":"article","venue":"Statistical Methods & Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of Mental Health","keywords":"Covariate; Event (particle physics); Bayesian probability; Econometrics; Statistics; Nonparametric statistics; Posterior probability; Computer science; Posterior predictive distribution; Parametric statistics; Bayesian inference; Mathematics; Bayesian linear regression","score_opus":0.05491215545635405,"score_gpt":0.37620565729921396,"score_spread":0.32129350184285993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035595990","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000055846544,0.0001343267,0.9927432,0.001511797,0.000031139243,0.0010853421,0.00007725372,0.00015284901,0.004258503],"genre_scores_gemma":[0.0027436765,0.000009064682,0.9955403,0.00041873805,0.000098010154,0.00085496146,0.000046865847,0.000024048697,0.00026432672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972129,0.0004907667,0.00043985687,0.0011615466,0.00024634507,0.00044861826],"domain_scores_gemma":[0.99686396,0.000680214,0.00006976729,0.0017130595,0.00013749705,0.0005354817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015638042,0.00023824882,0.00035354318,0.00011890562,0.0002557064,0.00033526478,0.0012054031,0.00009152747,0.00011951415],"category_scores_gemma":[0.0002443341,0.00021213188,0.00003458395,0.00048744358,0.00009456965,0.0004125455,0.00094949856,0.00026299324,0.00025672355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012663428,0.0000631705,0.000003237256,0.00001795618,0.000015438734,5.667586e-7,0.00006084353,0.00006839021,0.0004091176,0.39675486,0.0011920345,0.60141313],"study_design_scores_gemma":[0.0000776802,0.00002373184,0.00013744936,0.000005447435,0.0000220144,0.00001884198,0.000005470109,0.69126374,0.000020182477,0.30585063,0.0023870382,0.00018781619],"about_ca_topic_score_codex":0.000069097405,"about_ca_topic_score_gemma":9.329128e-7,"teacher_disagreement_score":0.6911953,"about_ca_system_score_codex":0.000030849158,"about_ca_system_score_gemma":0.000073805524,"threshold_uncertainty_score":0.8650487},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011520357196130747,"score_gpt":0.24963690029188826,"score_spread":0.2381165430957575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036312115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038352277,0.00037626614,0.9451465,0.00079645414,0.011047197,0.000086206244,8.1849714e-7,0.00006256452,0.004131724],"genre_scores_gemma":[0.8649027,0.000058550904,0.13405177,0.00033573352,0.0005568862,0.0000014195613,2.6773645e-7,0.00001657401,0.00007612728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982072,0.00034016074,0.0005778778,0.00017490707,0.00042276524,0.00027704999],"domain_scores_gemma":[0.99818367,0.0002742025,0.00055068504,0.0003500137,0.0004856842,0.00015576856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022151063,0.00018243828,0.00040296235,0.00017897792,0.0001674329,0.0002136652,0.00090063695,0.00011621094,0.000015745409],"category_scores_gemma":[0.00048539002,0.00014828805,0.0001971452,0.00034898217,0.00011146858,0.0013691538,0.0001352193,0.00039821427,0.0000056652225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013212473,0.000066868175,0.00001236331,0.000007734729,0.00004977201,0.000085430125,0.0010892601,0.000013311026,0.002477782,0.99092793,0.00012972542,0.0050077173],"study_design_scores_gemma":[0.0015805425,0.00044790897,0.000048569542,0.0000668979,0.000019169305,0.00027998784,0.000051845105,0.000009492752,0.016484959,0.9769621,0.0038762314,0.00017233037],"about_ca_topic_score_codex":0.0000025944948,"about_ca_topic_score_gemma":9.532142e-7,"teacher_disagreement_score":0.8265504,"about_ca_system_score_codex":0.000068434245,"about_ca_system_score_gemma":0.00029172597,"threshold_uncertainty_score":0.6047011},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.009405148207206006,"score_gpt":0.20642106155856108,"score_spread":0.19701591335135507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036631917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022264723,0.00035922122,0.9764444,0.00020626653,0.000042055322,0.00021929792,0.00016986359,0.000031346197,0.00026280456],"genre_scores_gemma":[0.16332655,0.0001275289,0.8355545,0.00021724102,0.00005046981,0.00002495318,0.00004052009,0.000007818362,0.0006504467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99906224,0.00005250546,0.00017106807,0.00036140147,0.000107540676,0.0002452237],"domain_scores_gemma":[0.9995899,0.00012952343,0.00004585765,0.00013531995,0.0000039289043,0.00009545517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017646927,0.00014590858,0.00019096545,0.000016353746,0.00018263001,0.00006467085,0.0001348982,0.00009584795,0.000050371294],"category_scores_gemma":[0.000010112292,0.000118941454,0.00002912392,0.000022578666,0.00015361595,0.00017668026,0.00018004772,0.00007465923,0.000010425204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062812054,0.00070132705,0.0025072838,0.00014556035,0.00008111083,0.00021587979,0.00028313097,0.0002455104,0.015121385,0.6728348,0.004392967,0.3034082],"study_design_scores_gemma":[0.00047151017,0.00031652316,0.02699726,0.0000032394203,0.0000248611,0.00005986236,0.0000070267492,0.24832202,0.00020070476,0.72036815,0.0029246968,0.00030413116],"about_ca_topic_score_codex":0.000005012299,"about_ca_topic_score_gemma":8.1130605e-7,"teacher_disagreement_score":0.30310407,"about_ca_system_score_codex":0.000026255457,"about_ca_system_score_gemma":0.0000051752663,"threshold_uncertainty_score":0.4850292},"labels":[],"label_agreement":null},{"id":"W2037535649","doi":"10.1016/j.spl.2009.04.011","title":"Modelling heavy-tailed count data using a generalised Poisson-inverse Gaussian family","year":2009,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University","funders":"","keywords":"Mathematics; Poisson distribution; Inverse Gaussian distribution; Count data; Statistics; Gaussian; Exponential family; Inverse; Applied mathematics; Probability density function; Statistical physics; Distribution (mathematics); Mathematical analysis","score_opus":0.0909370416795725,"score_gpt":0.30588854051005065,"score_spread":0.21495149883047815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037535649","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013828641,0.000059678565,0.9806839,0.0039122044,0.00037342124,0.0005465857,0.0003217522,0.00017792963,0.000095859206],"genre_scores_gemma":[0.014481301,0.000013505795,0.976779,0.008443088,0.00014358593,0.0000063253683,0.000098498596,0.000021312047,0.000013416474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964078,0.00041031252,0.000615628,0.0012633078,0.0005733988,0.0007295684],"domain_scores_gemma":[0.99664396,0.00014342825,0.00020639616,0.002591145,0.00014002349,0.00027502372],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013832671,0.00037460067,0.00044505394,0.00011019979,0.0002816224,0.00037396062,0.0018282053,0.0001095232,0.000008187327],"category_scores_gemma":[0.00009459725,0.00036211885,0.000072569455,0.0003821684,0.00014442588,0.0007637285,0.00033941076,0.00035642512,0.000010986181],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010314264,0.00037937707,0.0001518984,0.00015102628,0.000084849984,0.00021898215,0.0018383925,0.024671678,0.02365661,0.8946687,0.018368928,0.035706416],"study_design_scores_gemma":[0.0003021777,0.00003770655,0.00006271369,0.000024003384,0.000027096508,0.000008796767,0.000001040891,0.66803205,0.00008126479,0.3306699,0.00044372978,0.000309515],"about_ca_topic_score_codex":0.00033286592,"about_ca_topic_score_gemma":0.000027727185,"teacher_disagreement_score":0.6433604,"about_ca_system_score_codex":0.00023426028,"about_ca_system_score_gemma":0.0002478118,"threshold_uncertainty_score":0.99988306},"labels":[],"label_agreement":null},{"id":"W2037771381","doi":"10.1016/j.ecolmodel.2004.11.021","title":"On the use of stationary versus hidden Markov models to detect simple versus complex ecological dynamics","year":2005,"lang":"en","type":"article","venue":"Ecological Modelling","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Hidden Markov model; Ecological succession; Simple (philosophy); Computer science; Ecology; Markov chain; Dynamics (music); Markov model; Observable; Artificial intelligence; Machine learning; Biology; Physics","score_opus":0.19412874565898883,"score_gpt":0.3107221797292391,"score_spread":0.11659343407025027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037771381","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0897329,0.000014890683,0.9058801,0.002137241,0.00023806393,0.00042690017,0.000023161845,0.000116208124,0.0014305441],"genre_scores_gemma":[0.49247372,0.000012570863,0.5066417,0.00075417984,0.000043634725,0.000028560038,0.0000060589737,0.000008325936,0.000031238953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975876,0.0003944818,0.00047212356,0.0006255368,0.00039196567,0.00052828464],"domain_scores_gemma":[0.99424595,0.0046592057,0.00014400427,0.00062546,0.0001318655,0.0001935468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063930766,0.00026562405,0.0003646885,0.00009901175,0.0002650318,0.00011841474,0.001023429,0.00020248906,0.00014543845],"category_scores_gemma":[0.000220337,0.00017768133,0.00016816187,0.00035413387,0.00008851213,0.00037220112,0.0004325757,0.00035489417,0.00003868681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032700447,0.00011256084,0.0000014322861,0.0000023154134,0.000020709882,0.0000066996768,0.00009369631,0.6264185,0.000020046467,0.3132492,0.0007533332,0.058994554],"study_design_scores_gemma":[0.000569271,0.00073640724,0.000096453725,0.0000046829637,0.000010963368,0.0000013493172,0.000009282028,0.86223686,0.000033492404,0.13561562,0.0004824181,0.00020318701],"about_ca_topic_score_codex":0.000017309681,"about_ca_topic_score_gemma":0.00007441442,"teacher_disagreement_score":0.4027408,"about_ca_system_score_codex":0.00025753325,"about_ca_system_score_gemma":0.000060124446,"threshold_uncertainty_score":0.7245634},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09130992573247135,"score_gpt":0.3883450864695328,"score_spread":0.2970351607370615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039672920","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010214448,0.004545305,0.99066025,0.0007485422,0.0018702266,0.00085791654,0.0000031824468,0.0002043776,0.000088775916],"genre_scores_gemma":[0.0097835595,0.00007107371,0.9879334,0.0007482714,0.0012518173,0.00012575136,0.000026725347,0.000032402102,0.000026999716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694395,0.0006579212,0.0005501213,0.00073389645,0.00025167488,0.00086244225],"domain_scores_gemma":[0.99782485,0.0006234404,0.0001868255,0.0007620229,0.000109567016,0.00049332005],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005590823,0.00037972117,0.0006351658,0.00046491294,0.00015151016,0.00019403141,0.00076936383,0.00027057115,0.0000020750892],"category_scores_gemma":[0.00007948087,0.00029166974,0.00009963998,0.0014813615,0.0001443175,0.0010029804,0.0003250707,0.00036897016,7.1593803e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008846648,0.0001948131,0.00027883245,0.00012989176,0.000019190764,0.0000037749357,0.0023534133,0.000011013915,0.0002569379,0.036065325,0.00028268082,0.9603953],"study_design_scores_gemma":[0.0009479822,0.00060784887,0.00023129233,0.00015398604,0.00002922564,0.00008661386,0.000020814223,0.8723708,0.00023164124,0.118133664,0.0067790174,0.00040715392],"about_ca_topic_score_codex":0.000016827822,"about_ca_topic_score_gemma":0.0000010899986,"teacher_disagreement_score":0.9599881,"about_ca_system_score_codex":0.000035338362,"about_ca_system_score_gemma":0.00003544661,"threshold_uncertainty_score":0.99995357},"labels":[],"label_agreement":null},{"id":"W2040323067","doi":"10.1016/j.stamet.2010.01.003","title":"Inference from multiple imputation for missing data using mixtures of normals","year":2010,"lang":"en","type":"article","venue":"Statistical Methodology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Science Foundation; National Institutes of Health; National Cancer Institute; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Mathematics; Missing data; Inference; Statistics; Econometrics; Artificial intelligence; Computer science","score_opus":0.28388855350707864,"score_gpt":0.4631346471876172,"score_spread":0.17924609368053857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040323067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035475593,0.000059868114,0.9945123,0.00019618141,0.00085282867,0.000193793,0.00055888045,0.00003571812,0.00004283433],"genre_scores_gemma":[0.086695485,0.0000019215859,0.9129279,0.00015684316,0.00012182157,0.0000054162606,0.000077490186,0.000010114461,0.0000030015246],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977678,0.00085779483,0.00041368217,0.00054133934,0.00013245031,0.00028695635],"domain_scores_gemma":[0.97957075,0.019137662,0.00019587572,0.00083156023,0.00015065532,0.00011351975],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022282314,0.00013849456,0.00038752772,0.00007533028,0.00008599124,0.000046943056,0.0009564136,0.00016984987,0.000027316859],"category_scores_gemma":[0.0136563955,0.00012179516,0.00003470533,0.00012505734,0.00016713818,0.00026728987,0.00038195885,0.00023716084,0.0000012216808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028897375,0.000024232546,0.00014342536,0.000024299054,0.000020872913,0.0000028762204,0.00019739188,0.000015597441,0.24863459,0.2767994,0.00007131509,0.4740371],"study_design_scores_gemma":[0.00024038325,0.000041984797,0.000860672,0.000006967526,0.000029164947,0.000005986693,0.0000030954918,0.444353,0.016262144,0.53795546,0.00013910058,0.00010198783],"about_ca_topic_score_codex":0.00033265827,"about_ca_topic_score_gemma":0.000055917386,"teacher_disagreement_score":0.47393513,"about_ca_system_score_codex":0.0000058497812,"about_ca_system_score_gemma":0.00013710189,"threshold_uncertainty_score":0.994652},"labels":[],"label_agreement":null},{"id":"W2040735861","doi":"10.1002/for.1044","title":"On forecasting counts","year":2008,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Series (stratigraphy); Econometrics; Negative binomial distribution; Bayesian probability; Poisson distribution; Computer science; Probabilistic forecasting; Time series; Statistics; Mathematics; Probabilistic logic","score_opus":0.09448738222617091,"score_gpt":0.2687520753828352,"score_spread":0.17426469315666426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040735861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013303677,0.000105617066,0.95164955,0.000115407165,0.00054395816,0.000020489846,2.2590183e-7,0.000012498223,0.034248568],"genre_scores_gemma":[0.41595206,0.000008731113,0.5832328,0.00017955835,0.00026856962,2.4240907e-7,4.804937e-8,0.0000062671306,0.00035171225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992661,0.000034654833,0.0002445477,0.0000825084,0.00022507539,0.0001471399],"domain_scores_gemma":[0.9992935,0.00016369052,0.00025416067,0.00011042744,0.000110807465,0.00006739897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004956391,0.000068972564,0.00013322888,0.00009585077,0.00010124497,0.000027177319,0.00028609435,0.000032862128,0.000014317583],"category_scores_gemma":[0.00022874092,0.00005265733,0.00007983888,0.00014273942,0.000016134225,0.00021334743,0.0000357484,0.00019372281,0.00001055516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001696914,0.000050603758,0.00023718427,0.000015280524,0.000028895429,0.0008209439,0.00084574556,0.00027686454,0.00020711623,0.04869161,0.016256,0.93255275],"study_design_scores_gemma":[0.0015231849,0.0012117049,0.0006137889,0.00074921537,0.000029270923,0.024252076,0.000020006411,0.7203771,0.0031934665,0.22722927,0.020170024,0.00063092436],"about_ca_topic_score_codex":5.3263994e-7,"about_ca_topic_score_gemma":9.329468e-8,"teacher_disagreement_score":0.93192184,"about_ca_system_score_codex":0.000023835988,"about_ca_system_score_gemma":0.000059612583,"threshold_uncertainty_score":0.21473037},"labels":[],"label_agreement":null},{"id":"W2040845578","doi":"10.1007/s10260-013-0248-1","title":"Discussion of ‘Model-based clustering and classification with non-normal mixture distributions’ by Lee and McLachlan","year":2013,"lang":"en","type":"article","venue":"Statistical Methods & Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Computer science; Artificial intelligence","score_opus":0.017005651101725257,"score_gpt":0.32590135941116294,"score_spread":0.3088957083094377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040845578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011812493,0.000076226155,0.99669176,0.0018905338,0.0000137521665,0.00060373853,0.00014597365,0.000047768764,0.0004121119],"genre_scores_gemma":[0.09770471,0.000011457956,0.9016103,0.00009194745,0.000013250212,0.00044953945,0.000054384527,0.000011126531,0.00005325338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861705,0.00023184821,0.0002969797,0.0004719702,0.00015286989,0.00022927849],"domain_scores_gemma":[0.9985612,0.000493734,0.00012464923,0.0004742828,0.0001259125,0.0002202317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004741593,0.00016907546,0.0002362794,0.00005733327,0.00020386331,0.000104383456,0.00024591427,0.00009636949,0.000009373452],"category_scores_gemma":[0.00005980761,0.00011081384,0.000020593483,0.0002592333,0.000273161,0.00022260408,0.000110563684,0.00018029397,0.0000021236544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007289566,0.00007201834,0.00011343584,0.00006924392,0.000009983117,1.7105901e-7,0.000100098514,0.000018247243,0.024159623,0.2980371,0.00047349464,0.6769393],"study_design_scores_gemma":[0.0003090464,0.00007955388,0.0057367766,0.000023979268,0.000036361555,0.0000069257717,0.000016895352,0.86120546,0.002010479,0.12958935,0.00077989505,0.00020526267],"about_ca_topic_score_codex":0.00002033981,"about_ca_topic_score_gemma":0.0000026105695,"teacher_disagreement_score":0.8611872,"about_ca_system_score_codex":0.000021194666,"about_ca_system_score_gemma":0.00005677182,"threshold_uncertainty_score":0.45188573},"labels":[],"label_agreement":null},{"id":"W2040968446","doi":"10.1007/s11042-012-1191-0","title":"Variational learning for Dirichlet process mixtures of Dirichlet distributions and applications","year":2012,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hierarchical Dirichlet process; Overfitting; Dirichlet process; Computer science; Dirichlet distribution; Inference; Artificial intelligence; Markov chain Monte Carlo; Latent Dirichlet allocation; Machine learning; Mixture model; Mathematical optimization; Algorithm; Applied mathematics; Topic model; Bayesian probability; Mathematics; Artificial neural network; Boundary value problem","score_opus":0.022214400586985046,"score_gpt":0.30175076324217914,"score_spread":0.2795363626551941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040968446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042610263,0.0009614324,0.99630314,0.000578208,0.000028091292,0.0009940488,0.00020534021,0.00006709625,0.00043653994],"genre_scores_gemma":[0.35512242,0.000112190326,0.6403631,0.00008527549,0.0003377422,0.003645423,0.00021672342,0.000012404736,0.000104686624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902934,0.00003909802,0.0002537565,0.0002994714,0.00012744736,0.00025087554],"domain_scores_gemma":[0.99868315,0.0005784316,0.0001489009,0.00025687998,0.00016173713,0.0001708772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032800573,0.00013420761,0.0001817432,0.000059735965,0.000358331,0.00008056195,0.00023697171,0.00008469396,0.0000045773218],"category_scores_gemma":[0.00008730606,0.00012134133,0.000044267494,0.00030310467,0.00010132551,0.00036988556,0.0000882511,0.000118621305,0.000002502503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032806402,0.00019514372,0.0025554472,0.00008231852,0.000027230795,2.784787e-8,0.0005179753,0.000021425356,0.0019476382,0.60360545,0.00022557063,0.3908185],"study_design_scores_gemma":[0.002283956,0.00015360175,0.09364234,0.000063382875,0.0002866127,0.000045029796,0.00017921627,0.17082258,0.00923431,0.29111385,0.43080866,0.0013664578],"about_ca_topic_score_codex":0.000004440235,"about_ca_topic_score_gemma":7.446741e-7,"teacher_disagreement_score":0.43058312,"about_ca_system_score_codex":0.00001156843,"about_ca_system_score_gemma":0.000040075887,"threshold_uncertainty_score":0.49481556},"labels":[],"label_agreement":null},{"id":"W2041490883","doi":"10.1002/sim.6484","title":"A flexible mixed‐effect negative binomial regression model for detecting unusual increases in MRI lesion counts in individual multiple sclerosis patients","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Multiple Sclerosis Society of Canada","keywords":"Negative binomial distribution; Random effects model; Dirichlet process; Dirichlet distribution; Statistics; Bayesian probability; Parametric statistics; Mixed model; Conditional probability distribution; Mathematics; Computer science; Medicine; Poisson distribution; Meta-analysis; Pathology","score_opus":0.11343398538156718,"score_gpt":0.35615538315047834,"score_spread":0.24272139776891116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041490883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09827162,0.000076048615,0.9006887,0.00003911779,0.0002981946,0.00042417384,0.00007529229,0.000020372923,0.00010646221],"genre_scores_gemma":[0.57252824,0.000011971264,0.4272592,0.00006604986,0.00004447322,0.0000381948,0.00002564891,0.0000095750265,0.000016644964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983608,0.00028110924,0.00037254975,0.00034034072,0.0003639426,0.0002812246],"domain_scores_gemma":[0.99829787,0.0011781014,0.0001272211,0.00018899333,0.00010178293,0.00010601457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017399917,0.0001630962,0.00032996834,0.00033485083,0.000045231645,0.000020370286,0.0002850321,0.000097497345,0.0000016786661],"category_scores_gemma":[0.0029454418,0.00012693871,0.000015203359,0.00042199623,0.000071832284,0.00014090024,0.00013778865,0.00022647897,0.0000018350428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063179404,0.00043077354,0.052922674,0.00018204289,0.000016285356,0.00003947632,0.010406561,0.002518954,0.00031895968,0.011119076,0.011227428,0.910186],"study_design_scores_gemma":[0.006337611,0.00057219446,0.014179558,0.0006762967,0.000009864847,0.000001016699,0.00006955556,0.9315945,0.0007032327,0.04564896,0.000019410087,0.00018782188],"about_ca_topic_score_codex":0.00043152313,"about_ca_topic_score_gemma":0.00040452016,"teacher_disagreement_score":0.92907554,"about_ca_system_score_codex":0.000151165,"about_ca_system_score_gemma":0.000116946605,"threshold_uncertainty_score":0.51764107},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.1051308348991267,"score_gpt":0.3155985677931308,"score_spread":0.21046773289400408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042829929","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009002985,0.0001802376,0.98836434,0.00009781982,0.00034236704,0.00018992025,0.000045206514,0.00076199055,0.0010151597],"genre_scores_gemma":[0.4331763,0.000008377923,0.56646407,0.00018079339,0.00006584422,0.000006426005,0.000025609792,0.000020679703,0.000051867733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972288,0.0001765536,0.0006191282,0.00085000735,0.0005744555,0.0005510244],"domain_scores_gemma":[0.99668133,0.00022861239,0.00026994766,0.0024469136,0.00015249211,0.00022071053],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011105996,0.00029709534,0.0005229112,0.0005989323,0.00023424106,0.00007032152,0.0023395875,0.00017319454,0.000020181113],"category_scores_gemma":[0.00021811677,0.0002865846,0.00011369516,0.0024047047,0.00011410461,0.00082452287,0.0011547817,0.00028208148,0.000021689812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014421059,0.0013498024,0.008868182,0.0011558845,0.0004367235,0.00062795164,0.0027745492,0.6246839,0.06508062,0.0018843648,0.024269579,0.2687242],"study_design_scores_gemma":[0.0004927311,0.000049750342,0.0005493917,0.00007972748,0.000015401036,0.00007660861,0.0000032727105,0.9927831,0.0053230138,0.00019739456,0.00011403341,0.00031556116],"about_ca_topic_score_codex":0.000017477048,"about_ca_topic_score_gemma":0.000003675747,"teacher_disagreement_score":0.42417333,"about_ca_system_score_codex":0.00006320428,"about_ca_system_score_gemma":0.00019736473,"threshold_uncertainty_score":0.99995863},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.022333593211559196,"score_gpt":0.2780133281326238,"score_spread":0.2556797349210646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043122071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07930542,0.0010079609,0.9148044,0.004524796,0.00010160536,0.00014793822,0.000051048733,0.000012758434,0.00004406229],"genre_scores_gemma":[0.8415416,0.00008226124,0.15808143,0.000051531693,0.00018777553,0.000002331892,0.000009425784,0.000004835769,0.000038817405],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982408,0.0003374889,0.0004740862,0.00022120068,0.00048161647,0.00024480847],"domain_scores_gemma":[0.9986277,0.00019767953,0.00044459116,0.00023881996,0.00032522698,0.00016596702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008530124,0.00015731559,0.00036997366,0.00016820194,0.00017842838,0.00010820262,0.00048193472,0.00010738907,0.0000075859757],"category_scores_gemma":[0.00020767537,0.00007085786,0.00009662541,0.0020517183,0.00020095591,0.00027671416,0.00011712351,0.00031676926,6.846439e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005171751,0.0006359549,0.0035430007,0.000038702474,0.00017672416,0.000011832109,0.0008841428,0.000059732032,0.008257053,0.035290103,0.011644244,0.93894136],"study_design_scores_gemma":[0.017662691,0.0078108897,0.25324914,0.000581568,0.00057041895,0.0028459665,0.00022951709,0.21395546,0.35463363,0.021564452,0.124839745,0.0020565023],"about_ca_topic_score_codex":0.000039345257,"about_ca_topic_score_gemma":0.000002883762,"teacher_disagreement_score":0.9368848,"about_ca_system_score_codex":0.00009004782,"about_ca_system_score_gemma":0.000092166054,"threshold_uncertainty_score":0.28894997},"labels":[],"label_agreement":null},{"id":"W2043447175","doi":"10.1016/j.jmva.2013.09.003","title":"Marginal regression analysis of clustered failure time data with a cure fraction","year":2013,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Estimator; Statistics; Marginal model; Estimating equations; Fraction (chemistry); Regression; Proportional hazards model; Regression analysis; Hazard ratio; Applied mathematics; Survival function; Hazard; Confidence interval","score_opus":0.020037130000804627,"score_gpt":0.2987926363546233,"score_spread":0.2787555063538186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043447175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02082065,0.00011115491,0.97740084,0.0013908853,0.00003875203,0.00008461448,0.000011029514,0.00001344872,0.00012862308],"genre_scores_gemma":[0.38832414,0.000029601075,0.6113095,0.000059712027,0.000059749786,0.0000012567895,0.000022766633,0.000007638194,0.00018560379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735546,0.00046638682,0.0008110673,0.0004162699,0.00071816996,0.0002326526],"domain_scores_gemma":[0.99572927,0.00021886015,0.0017242549,0.001355476,0.0007896152,0.00018251697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013317007,0.00021877693,0.0010915815,0.0017348565,0.00008668291,0.00016883317,0.0015272686,0.00013166791,0.00029092137],"category_scores_gemma":[0.000091931535,0.00013294668,0.00051730464,0.0047016335,0.00003929355,0.0018718133,0.00028712134,0.00034952685,0.000008822464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013285913,0.0033069164,0.060332887,0.00020845713,0.26746494,0.00051730877,0.0061207665,0.069634005,0.13875368,0.0049537267,0.023365103,0.4240136],"study_design_scores_gemma":[0.00061573525,0.00013300167,0.031435587,0.00005809827,0.012081346,0.00001964745,0.00004426333,0.95407856,0.0003329317,0.00057660183,0.00043121638,0.00019302175],"about_ca_topic_score_codex":0.0003537039,"about_ca_topic_score_gemma":0.000056738787,"teacher_disagreement_score":0.88444453,"about_ca_system_score_codex":0.00005688212,"about_ca_system_score_gemma":0.000097549586,"threshold_uncertainty_score":0.5421408},"labels":[],"label_agreement":null},{"id":"W2043517840","doi":"10.1109/icassp.2013.6638725","title":"Multivariate Student's-t mixture model for bounded support data","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mixture model; Bounded function; Student's t-distribution; Gaussian; Computer science; Extension (predicate logic); Multivariate normal distribution; Distribution (mathematics); Gaussian process; Applied mathematics; Mathematics; Multivariate statistics; Artificial intelligence; Machine learning; Econometrics; Mathematical analysis; Autoregressive conditional heteroskedasticity; Physics","score_opus":0.07620409311385803,"score_gpt":0.35724642733450085,"score_spread":0.28104233422064284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043517840","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019693958,0.000023758568,0.9910567,0.0021845037,0.00028782993,0.0006909316,0.000017867898,0.00019068635,0.005350786],"genre_scores_gemma":[0.035696056,0.000004221848,0.950303,0.002114166,0.00007760064,0.00008448784,0.000032590982,0.000015641726,0.011672222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836236,0.00005034165,0.00025291,0.0007027875,0.00023065462,0.0004009624],"domain_scores_gemma":[0.99762243,0.00009607204,0.00006854815,0.0019186554,0.000133194,0.00016111197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000583016,0.00017881402,0.00021139251,0.000053144864,0.00012864737,0.0004333918,0.0027901575,0.00010242734,0.0000787239],"category_scores_gemma":[0.000041080555,0.00013463257,0.00006276627,0.00012311248,0.000025165848,0.0013759416,0.0009902912,0.000111802954,0.00007851842],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056845493,0.00021040364,0.000037779504,0.000026150208,0.00006882371,0.0000031993163,0.0013304207,0.00007237571,0.0030756516,0.6990791,0.15738963,0.13870078],"study_design_scores_gemma":[0.00040293226,0.0000294329,0.0001146536,0.0000029566147,0.000008504689,0.0000040099635,0.0000059608165,0.8367367,0.00022541556,0.15920664,0.00308268,0.00018009852],"about_ca_topic_score_codex":0.000060219274,"about_ca_topic_score_gemma":0.000016673883,"teacher_disagreement_score":0.8366643,"about_ca_system_score_codex":0.000016880578,"about_ca_system_score_gemma":0.00010969878,"threshold_uncertainty_score":0.5490157},"labels":[],"label_agreement":null},{"id":"W2043581384","doi":"10.1093/biomet/asp011","title":"Non-finite Fisher information and homogeneity: an EM approach","year":2009,"lang":"en","type":"article","venue":"Biometrika","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Chen; Mathematics; Homogeneity (statistics); Library science; Statistics; Demography; Computer science; Sociology","score_opus":0.01887520495701395,"score_gpt":0.25634109509093417,"score_spread":0.23746589013392022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043581384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017014202,0.00016852863,0.9777619,0.00019011491,0.00010556022,0.000121460056,0.000002206029,0.00008478492,0.0045512225],"genre_scores_gemma":[0.31233647,0.000025694428,0.68649346,0.0010122991,0.000052961816,0.0000034840004,0.00000843815,0.0000028042737,0.00006437959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920213,0.000037169295,0.00017226305,0.00021041725,0.00018407629,0.00019391975],"domain_scores_gemma":[0.9993239,0.000023106775,0.000063284766,0.00040139462,0.000052894546,0.00013542552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048726832,0.00011015579,0.00013023533,0.0005978879,0.00008255795,0.00034827754,0.00037292327,0.00008973357,0.00000262949],"category_scores_gemma":[0.000031409574,0.0000940985,0.00003139591,0.0015759905,0.000016575,0.0015114129,0.0000691987,0.00007428862,0.000011808773],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026378805,0.00004343801,0.00010388783,0.0000066543957,0.000003986772,0.0000010510863,0.00057690433,0.0000018198044,0.00027665452,0.008602633,0.000407695,0.98997265],"study_design_scores_gemma":[0.0030222428,0.0020124645,0.20314117,0.000040638275,0.00004629342,0.00016408552,0.000151434,0.6316044,0.01053088,0.06662427,0.08075665,0.0019054719],"about_ca_topic_score_codex":0.0000074425016,"about_ca_topic_score_gemma":4.3196547e-7,"teacher_disagreement_score":0.98806715,"about_ca_system_score_codex":0.0000135812315,"about_ca_system_score_gemma":0.000024356486,"threshold_uncertainty_score":0.38372254},"labels":[],"label_agreement":null},{"id":"W2043938177","doi":"10.1007/s10985-013-9259-3","title":"A copula model for marked point processes","year":2013,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Copula (linguistics); Censoring (clinical trials); Point process; Econometrics; Bivariate analysis; Event (particle physics); Multivariate statistics; Mathematics; Joint probability distribution; Marginal distribution; Computer science; Statistics; Random variable","score_opus":0.04005589111744818,"score_gpt":0.3040933451598307,"score_spread":0.26403745404238255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043938177","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010408272,0.00018341416,0.9963864,0.0021900511,0.00003059726,0.00030680205,0.00024510603,0.00010672684,0.00044679074],"genre_scores_gemma":[0.028597008,0.00003109186,0.96791893,0.00093202223,0.000054399094,0.000104194856,0.0005453722,0.0000119473325,0.001805011],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822193,0.00007715025,0.00032056184,0.0008149651,0.00023617374,0.0003292054],"domain_scores_gemma":[0.99680835,0.00018239305,0.00012912691,0.0024978041,0.00022170242,0.00016062411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067029847,0.00017608619,0.00038742443,0.00023842003,0.0001162255,0.00035636,0.0025522348,0.00007214374,0.00009368374],"category_scores_gemma":[0.00027434577,0.0001436366,0.00014116659,0.0014041994,0.000028767585,0.0013168834,0.00070657337,0.00007598274,0.00006147673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057266123,0.0007334246,0.0010821449,0.00061386183,0.0060462523,0.000012457826,0.0020514508,0.0077725067,0.0010446986,0.06755354,0.4598122,0.4532202],"study_design_scores_gemma":[0.0001447829,0.000012751268,0.0000955143,0.000006281004,0.0004275739,0.0000012835166,0.000004058959,0.96856624,0.00006263367,0.029316051,0.0011683896,0.00019441446],"about_ca_topic_score_codex":0.00016763741,"about_ca_topic_score_gemma":0.00005800344,"teacher_disagreement_score":0.96079373,"about_ca_system_score_codex":0.000013245635,"about_ca_system_score_gemma":0.000107861444,"threshold_uncertainty_score":0.58573306},"labels":[],"label_agreement":null},{"id":"W2045019767","doi":"10.1002/cjs.5540330108","title":"Modeling nonlinear time series with local mixtures of generalized linear models","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Estimator; Series (stratigraphy); Maximum likelihood; Statistics; Consistency (knowledge bases); Exponential family; Applied mathematics; Covariate; Combinatorics; Discrete mathematics","score_opus":0.01637837181776522,"score_gpt":0.23490111397287697,"score_spread":0.21852274215511175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045019767","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025284837,0.00035590146,0.99606633,0.0005320937,0.00009981433,0.000055203367,0.0001313667,0.0000061199894,0.00022466214],"genre_scores_gemma":[0.08296423,0.000020531708,0.91640466,0.00024475498,0.00017781125,4.7517364e-7,0.0000038781664,0.000016949583,0.0001667184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855435,0.000104507984,0.0005824254,0.0001571406,0.00029672505,0.00030484103],"domain_scores_gemma":[0.9982161,0.000052439937,0.00024326041,0.0002877885,0.0006673852,0.0005330302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049771223,0.0001622257,0.00039919734,0.0002169527,0.00008611463,0.000067840345,0.00057510857,0.00007596021,0.0000318912],"category_scores_gemma":[0.00004093997,0.00012647275,0.000062931336,0.00018439678,0.000121475416,0.00047627313,0.000020363846,0.00023611287,0.0000036778208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056496247,0.000025271214,0.0000107798605,0.000027040487,0.00009281071,0.00024096775,0.0015743476,0.73711026,0.00020515404,0.15722416,0.001860361,0.10157236],"study_design_scores_gemma":[0.00036503392,0.00022688635,0.0000022192103,0.000053585838,0.000026716189,0.00027747758,0.0000124287635,0.96524453,0.0007013499,0.03208938,0.0008493439,0.00015104395],"about_ca_topic_score_codex":0.000644562,"about_ca_topic_score_gemma":0.0025867498,"teacher_disagreement_score":0.22813429,"about_ca_system_score_codex":0.000073243486,"about_ca_system_score_gemma":0.0015049191,"threshold_uncertainty_score":0.5157409},"labels":[],"label_agreement":null},{"id":"W2045222793","doi":"10.1155/2007/37475","title":"An<mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" id=\"E1\"><mml:mi>M</mml:mi></mml:math>-Estimation-Based Procedure for Determining the Number of Regression Models in Regression Clustering","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Mathematics and Decision Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regression; Mathematics; Statistics; Algorithm; Cluster analysis; Regression analysis; Distribution (mathematics); Computer science; Artificial intelligence; Mathematical analysis","score_opus":0.03712785476299738,"score_gpt":0.3265171060414634,"score_spread":0.289389251278466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045222793","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45182723,0.000033858847,0.54757184,0.00004045753,0.00008484023,0.00003601006,8.4813445e-7,0.0000061808028,0.0003987306],"genre_scores_gemma":[0.46708545,0.000017815753,0.5327654,0.00008191483,0.00003262275,0.0000074789195,3.407651e-7,0.000008179667,8.243065e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979393,0.000013629618,0.0007527615,0.0002619622,0.00078267127,0.00024966817],"domain_scores_gemma":[0.9973122,0.0011768225,0.0009642247,0.000324782,0.00010729448,0.00011467619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004332662,0.0001451343,0.00020540075,0.00015799853,0.00034210517,0.00028770525,0.0007371262,0.00014808423,0.0000019432523],"category_scores_gemma":[0.00024031228,0.000097153905,0.000108988635,0.0003298683,0.00016056886,0.00055431406,0.00017971336,0.00018194802,0.0000020660534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073058065,0.000071912546,0.0000031741406,0.00010033023,0.00000543898,0.0000074849418,0.0013870082,0.0041090343,0.00071514683,0.9379383,0.000045785317,0.05554333],"study_design_scores_gemma":[0.00032760025,0.00013790684,0.000019054942,0.00064800895,0.000014624105,0.00007335429,0.00029745145,0.82220066,0.0042864676,0.17189501,0.000011346664,0.000088528395],"about_ca_topic_score_codex":0.0000020484615,"about_ca_topic_score_gemma":0.000003970849,"teacher_disagreement_score":0.81809163,"about_ca_system_score_codex":0.0000070694723,"about_ca_system_score_gemma":0.00021473212,"threshold_uncertainty_score":0.39618212},"labels":[],"label_agreement":null},{"id":"W2045248095","doi":"10.3166/isi.15.2.97-119","title":"Un graphe génératif pour la classification semi-supervisée","year":2010,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics","score_opus":0.022511980707438487,"score_gpt":0.2533479655261566,"score_spread":0.23083598481871814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045248095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017946932,0.0005402585,0.9070292,0.0030678085,0.0032246797,0.00040624203,0.00003211442,0.00024782724,0.06750494],"genre_scores_gemma":[0.5730556,0.00016054534,0.42422482,0.00067251606,0.0003717183,0.00006923699,0.00005741236,0.000024049068,0.001364106],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99710554,0.0004792827,0.0009956021,0.00035315004,0.00045925073,0.0006071832],"domain_scores_gemma":[0.99730986,0.0002800126,0.0005297762,0.00090827065,0.0006967954,0.00027526292],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021030053,0.0003949108,0.00035158097,0.00033206661,0.0005107244,0.001486182,0.00086112425,0.0006371549,0.00017982123],"category_scores_gemma":[0.00045746646,0.00040823733,0.00019750533,0.00095511106,0.0004153379,0.00859224,0.0001974009,0.00081190607,0.00052758335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056563604,0.000038559407,0.00015178438,0.00017440783,0.000024056963,0.0000032995015,0.006823083,0.0000092147175,0.0020390833,0.4687867,0.0015260867,0.5204181],"study_design_scores_gemma":[0.00093247084,0.000116188625,0.020549703,0.00041186568,0.00008636013,0.00068340637,0.00045865163,0.40129358,0.006156285,0.45250365,0.11580146,0.0010063683],"about_ca_topic_score_codex":0.00017917991,"about_ca_topic_score_gemma":0.000035258403,"teacher_disagreement_score":0.55510867,"about_ca_system_score_codex":0.00011911193,"about_ca_system_score_gemma":0.00038901315,"threshold_uncertainty_score":0.9998369},"labels":[],"label_agreement":null},{"id":"W2047306702","doi":"10.4134/bkms.2014.51.3.701","title":"KRUSKAL-WALLIS ONE-WAY ANALYSIS OF VARIANCE BASED ON LINEAR PLACEMENTS","year":2014,"lang":"en","type":"article","venue":"Bulletin of the Korean Mathematical Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Ministry of Education, Science and Technology; National Research Foundation of Korea; Yonsei University; National Research Foundation","keywords":"Mathematics; Infinity; Statistics; Variance (accounting); Null hypothesis; Sample (material); Analysis of variance; Kruskal's algorithm; Limiting; Kruskal–Wallis one-way analysis of variance; Sample size determination; Applied mathematics; Combinatorics; Mathematical analysis; Mann–Whitney U test","score_opus":0.01751268093591587,"score_gpt":0.2543350487374524,"score_spread":0.2368223678015365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047306702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001241563,0.0000069101266,0.98459446,0.0040629096,0.000048891954,0.00017434229,0.000009210901,0.00003366067,0.009828056],"genre_scores_gemma":[0.15706155,0.0000031059733,0.8408331,0.001398813,0.000031461022,0.000009017777,0.0000016298889,0.000011927604,0.00064937543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980421,0.00029616736,0.00047182557,0.00033635154,0.0006109342,0.00024263786],"domain_scores_gemma":[0.99741465,0.0008571311,0.00031630028,0.0012287033,0.00009684318,0.00008635468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018563372,0.00017407902,0.00053988874,0.000039713057,0.000095288204,0.000024779001,0.0011971386,0.000114465474,0.00026946823],"category_scores_gemma":[0.00033794803,0.00011463737,0.00074690103,0.00056361785,0.00015270636,0.000019299721,0.00025506256,0.00017426847,0.000021895345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033449658,0.001377472,0.00018430101,0.00043098044,0.0011036285,4.3577353e-7,0.0015428319,0.003954201,0.0008667617,0.96880525,0.01259454,0.009106151],"study_design_scores_gemma":[0.00046323094,0.000101578444,0.00067320507,0.00015330089,0.00037565647,3.3173265e-7,0.000008470608,0.92953134,0.0041739014,0.0619882,0.002348396,0.00018236546],"about_ca_topic_score_codex":0.000015235471,"about_ca_topic_score_gemma":4.4702048e-7,"teacher_disagreement_score":0.92557716,"about_ca_system_score_codex":0.000027034233,"about_ca_system_score_gemma":0.000024029572,"threshold_uncertainty_score":0.46747762},"labels":[],"label_agreement":null},{"id":"W2047584164","doi":"10.1080/02664763.2011.632404","title":"Two-step and likelihood methods for HIV viral dynamic models with covariate measurement errors and missing data","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Covariate; Missing data; Autocorrelation; Statistics; Econometrics; Computer science; Standard error; Mathematics","score_opus":0.09824906713412437,"score_gpt":0.3427253060192883,"score_spread":0.24447623888516393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047584164","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005226765,0.00033134123,0.99877113,0.000110124325,0.00010736735,0.00020503302,0.00005054721,0.000016855613,0.000355307],"genre_scores_gemma":[0.021170342,0.00005672181,0.97857034,0.00013827089,0.000030287329,0.000003231248,0.0000025628428,0.000024407711,0.0000038482362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858886,0.00010638945,0.00044040708,0.0003129789,0.00029583863,0.00025552767],"domain_scores_gemma":[0.99850714,0.00018155204,0.00044462318,0.00041533416,0.00024877637,0.00020259482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029508579,0.00018223145,0.00036959664,0.000097146,0.00010293989,0.00012578035,0.0005397526,0.000049928054,7.983296e-7],"category_scores_gemma":[0.00004656301,0.00013620593,0.000018957066,0.000080092344,0.00007040819,0.00035438803,0.00020432254,0.0002027952,9.731255e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020143375,0.000052752308,0.0000026312723,0.000061618885,0.00011345807,0.00001470017,0.001287966,0.0000468576,0.0012583603,0.42784712,0.00017935841,0.5689337],"study_design_scores_gemma":[0.000998392,0.00016167917,0.000034681063,0.00003285126,0.00011033689,0.000075046,0.000034122368,0.5216031,0.0001746453,0.47650638,0.00013704516,0.00013171448],"about_ca_topic_score_codex":0.0000062343534,"about_ca_topic_score_gemma":0.000008652536,"teacher_disagreement_score":0.568802,"about_ca_system_score_codex":0.00003646992,"about_ca_system_score_gemma":0.00018154604,"threshold_uncertainty_score":0.5554316},"labels":[],"label_agreement":null},{"id":"W2049916971","doi":"10.1002/cjs.5550340106","title":"Empirical likelihood tests for two-sample problems via nonparametric density estimation","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ministerio de Economía y Competitividad","keywords":"Mathematics; Empirical likelihood; Estimator; Statistics; Test statistic; Nonparametric statistics; Kernel density estimation; Statistical hypothesis testing","score_opus":0.029047465493427918,"score_gpt":0.29299536562211953,"score_spread":0.2639479001286916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049916971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012677276,0.00015030689,0.9973222,0.0004694648,0.00042439817,0.00016330302,0.00011920098,0.000009201909,0.000074218515],"genre_scores_gemma":[0.19423378,0.0000014401043,0.80538166,0.0002098201,0.00013247295,0.000002373233,0.00000886309,0.000009728826,0.000019846882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987563,0.000068978436,0.00044188232,0.0001634812,0.00019388842,0.0003754802],"domain_scores_gemma":[0.99782103,0.00067317113,0.00028305,0.00019917716,0.0005451336,0.00047843016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006331964,0.00012570234,0.00023422146,0.0003487158,0.00016605254,0.00018747868,0.00038992203,0.00006371919,0.0000062291233],"category_scores_gemma":[0.0006593418,0.000117165866,0.00006238738,0.00043058227,0.000048202823,0.00022208419,0.0000139694175,0.0001766043,0.0000034184495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011259132,0.00010133273,0.008404493,0.000103925435,0.000052009204,0.00025529577,0.00055064046,0.0061453516,0.0001883887,0.18978742,0.0648245,0.7295754],"study_design_scores_gemma":[0.0004672805,0.00020838648,0.006022038,0.000025060552,0.000030997435,0.00019146297,0.000001559402,0.31840828,0.00015196676,0.6723367,0.0019866931,0.00016954176],"about_ca_topic_score_codex":0.003610794,"about_ca_topic_score_gemma":0.013680572,"teacher_disagreement_score":0.7294058,"about_ca_system_score_codex":0.00016650023,"about_ca_system_score_gemma":0.0011195069,"threshold_uncertainty_score":0.763408},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.029067567471620568,"score_gpt":0.333769758462675,"score_spread":0.3047021909910544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050627451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035851053,0.00033752184,0.9981812,0.00036757864,0.000043528675,0.00015969799,0.00003196905,0.000034809425,0.0004851496],"genre_scores_gemma":[0.312583,0.000018044948,0.68726975,0.000056503428,0.000043469347,0.0000029165708,0.000009432907,0.0000052357623,0.000011668756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990912,0.000058903424,0.00027038023,0.00028154132,0.00013006275,0.00016788258],"domain_scores_gemma":[0.99878806,0.0007539222,0.00016083811,0.00016258455,0.00008732847,0.000047256297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002570776,0.00011172139,0.00016986129,0.000037549336,0.00018340843,0.000110503584,0.00010866806,0.00005498102,0.000001211947],"category_scores_gemma":[0.000063987594,0.000107242646,0.000015749261,0.00015821903,0.0000422574,0.00014521083,0.00013119307,0.00012370179,6.02352e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010491393,0.000020297679,0.000027558082,0.00005274521,0.0000064329056,0.000002273517,0.00019151437,0.00048251616,0.00008987442,0.8747104,0.000072326795,0.124343],"study_design_scores_gemma":[0.00011043023,0.000024413095,0.00044961073,0.000024272262,0.000014866786,0.000022756914,0.000005676688,0.73125345,0.00017086367,0.2674717,0.00035491513,0.00009703719],"about_ca_topic_score_codex":0.000029882302,"about_ca_topic_score_gemma":0.0000035603996,"teacher_disagreement_score":0.73077095,"about_ca_system_score_codex":0.0000064784545,"about_ca_system_score_gemma":0.00004024402,"threshold_uncertainty_score":0.43732283},"labels":[],"label_agreement":null},{"id":"W2051331323","doi":"10.1239/jap/1429282618","title":"Ergodic Inequality of a Two-Parameter Infinitely-Many-Alleles Diffusion Model","year":2015,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Ergodic theory; Allele; Pure mathematics; Statistical physics; Dominance (genetics); Biology; Genetics; Physics","score_opus":0.06735228294003268,"score_gpt":0.3055389314850028,"score_spread":0.2381866485449701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051331323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3609579,0.000055049222,0.6368367,0.00018411761,0.00010318281,0.00016779688,0.0000019418653,0.00001718418,0.001676144],"genre_scores_gemma":[0.5126435,0.000005406941,0.48717842,0.00011533614,0.000041704396,0.0000038815,2.63771e-7,0.000005466193,0.0000060297775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973078,0.00025378735,0.0011290197,0.00032724926,0.00070914614,0.0002730273],"domain_scores_gemma":[0.9972428,0.00027682647,0.0008494313,0.0007828747,0.000536326,0.00031173183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004758995,0.0002114134,0.00064219075,0.00014291905,0.00004557568,0.000059922248,0.0009885808,0.00013242576,0.00000493063],"category_scores_gemma":[0.00031113942,0.00015541453,0.00021729206,0.00034259303,0.0001350004,0.00037032596,0.00035742304,0.00043577442,0.000002529154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000841609,0.0015573932,0.0020104742,0.0002471495,0.00010221395,0.0000127869525,0.0070230635,0.0156642,0.0101589775,0.79819775,0.00072251895,0.16346186],"study_design_scores_gemma":[0.001203459,0.00019460713,0.00037067037,0.000025857571,0.000022169033,0.00001913798,0.000014554017,0.13553044,0.0037889674,0.858563,0.00010084677,0.00016630243],"about_ca_topic_score_codex":0.000010726904,"about_ca_topic_score_gemma":0.0000046155515,"teacher_disagreement_score":0.16329555,"about_ca_system_score_codex":0.000106912914,"about_ca_system_score_gemma":0.00043211,"threshold_uncertainty_score":0.63376206},"labels":[],"label_agreement":null},{"id":"W2051644092","doi":"10.1002/cjs.10082","title":"Model‐based linear clustering","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Humanities; Cluster analysis; Maximum likelihood; Mathematics; Statistics; Philosophy","score_opus":0.028865968275485633,"score_gpt":0.26412974094753433,"score_spread":0.2352637726720487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051644092","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053288013,0.000026421501,0.997364,0.0005127059,0.00085892796,0.000028348044,0.000042932246,0.000005623378,0.00062818994],"genre_scores_gemma":[0.17867479,0.0000015182334,0.8206097,0.00050646276,0.00011121313,2.670301e-7,6.332487e-7,0.0000076094116,0.0000877887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992637,0.000028374878,0.0002477892,0.00009320058,0.00013213676,0.00023481484],"domain_scores_gemma":[0.9986602,0.000070509,0.00013594201,0.00022907366,0.0002521488,0.0006521244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039591658,0.00008351754,0.00013774398,0.00017658508,0.000093089315,0.00010128989,0.0005527223,0.00005937096,0.000025345687],"category_scores_gemma":[0.00015232239,0.00007681734,0.000038319868,0.000110895715,0.000048939874,0.00015614004,0.0000139917665,0.0003866997,0.000004219299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057876723,0.000017170907,0.0002684744,0.00003316512,0.000024548186,0.00088497205,0.00083737256,0.011436072,0.0018566155,0.5958217,0.011491923,0.3773222],"study_design_scores_gemma":[0.00016664263,0.000040762123,0.000102662314,0.000013110064,0.0000070873143,0.000099239915,0.0000017644645,0.94954324,0.00017970834,0.04574053,0.004007528,0.000097715994],"about_ca_topic_score_codex":0.0002684134,"about_ca_topic_score_gemma":0.011581598,"teacher_disagreement_score":0.9381072,"about_ca_system_score_codex":0.00003094975,"about_ca_system_score_gemma":0.0017578322,"threshold_uncertainty_score":0.64628035},"labels":[],"label_agreement":null},{"id":"W2052085418","doi":"10.1016/j.eswa.2013.09.030","title":"Bayesian learning of finite generalized inverted Dirichlet mixtures: Application to object classification and forgery detection","year":2013,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Markov chain Monte Carlo; Gibbs sampling; Dirichlet process; Mixture model; Hierarchical Dirichlet process; Bayesian inference; Computer science; Latent Dirichlet allocation; Bayesian probability; Artificial intelligence; Mathematics; Pattern recognition (psychology); Algorithm; Topic model","score_opus":0.013788590419146152,"score_gpt":0.2535862511080923,"score_spread":0.23979766068894615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052085418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015824093,0.00043842598,0.9945584,0.00057752215,0.00005470003,0.002074306,0.0000021972412,0.0002020683,0.00050994847],"genre_scores_gemma":[0.7996556,0.000039058858,0.19408552,0.0001850257,0.0000924312,0.005755581,0.000013064135,0.000021421,0.00015226495],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983346,0.00019251043,0.000422464,0.000571564,0.00024289433,0.00023597087],"domain_scores_gemma":[0.9983505,0.00017246009,0.00028106326,0.00073672127,0.00027160358,0.00018764423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030609543,0.00019883816,0.00028267398,0.00023378686,0.00025090648,0.00014739126,0.00035161938,0.00012116204,0.0000024943172],"category_scores_gemma":[0.000035814533,0.00016446845,0.0000407203,0.0008462104,0.000046319536,0.00034840632,0.000066778084,0.00013191269,0.000022132275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026037384,0.0001470529,0.00091462984,0.00015280231,0.00008358377,4.1248248e-7,0.003650189,0.0010475141,0.5174214,0.105710566,0.0010882692,0.3697575],"study_design_scores_gemma":[0.0005114729,0.00015768112,0.0025650756,0.00007465959,0.000018207124,0.000028233371,0.00022853632,0.9595335,0.012842508,0.0034339456,0.020116478,0.00048966584],"about_ca_topic_score_codex":0.00056653714,"about_ca_topic_score_gemma":0.000016813028,"teacher_disagreement_score":0.958486,"about_ca_system_score_codex":0.000051384588,"about_ca_system_score_gemma":0.000045036642,"threshold_uncertainty_score":0.6706829},"labels":[],"label_agreement":null},{"id":"W2052694701","doi":"10.1063/1.3573633","title":"Multichannel SAR Image Classification by Finite Mixtures, Copula Theory and Markov Random Fields","year":2011,"lang":"en","type":"article","venue":"AIP conference proceedings","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency; Università degli Studi di Genova; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Synthetic aperture radar; Markov random field; Pattern recognition (psychology); Artificial intelligence; Contextual image classification; Computer science; Copula (linguistics); Radar imaging; Probability density function; Bayesian probability; Random field; Markov process; Markov chain; Mathematics; Radar; Machine learning; Image segmentation; Image (mathematics); Statistics","score_opus":0.030135946225188424,"score_gpt":0.2571386688680626,"score_spread":0.22700272264287416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052694701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003129061,0.00029293867,0.9832463,0.0005333489,0.00013747103,0.0002718282,0.0000052479572,0.00013957592,0.012244208],"genre_scores_gemma":[0.74784887,0.00015475828,0.25060183,0.00071814115,0.000034391032,0.000027540467,0.0000029751798,0.000011798571,0.0005997152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985615,0.000073398835,0.00026682962,0.00057600567,0.00018631166,0.0003359527],"domain_scores_gemma":[0.99895257,0.00018676893,0.00015374529,0.00023793262,0.00026520237,0.00020380145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010506844,0.00023289483,0.00025571804,0.00008594735,0.0001506051,0.0002581431,0.0006566297,0.00018813298,0.000060694863],"category_scores_gemma":[0.0003670674,0.00019821909,0.000052010233,0.00017061541,0.00014195904,0.0007470329,0.00018763442,0.0002706137,0.000013163668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034744837,0.00014739591,0.000815398,0.0001185948,0.00004949785,0.000007560255,0.01862182,9.904087e-9,0.05724793,0.7111921,0.009123717,0.20232856],"study_design_scores_gemma":[0.0028811982,0.00038260946,0.0018121123,0.00016156312,0.000072078146,0.00004880926,0.0004194654,0.16995084,0.026931757,0.7930065,0.0033045635,0.0010285327],"about_ca_topic_score_codex":0.000033315846,"about_ca_topic_score_gemma":0.0000012330127,"teacher_disagreement_score":0.7447198,"about_ca_system_score_codex":0.0000142665795,"about_ca_system_score_gemma":0.000051928124,"threshold_uncertainty_score":0.80831397},"labels":[],"label_agreement":null},{"id":"W2052915966","doi":"10.1089/106652704773416911","title":"Use of Runs Statistics for Pattern Recognition in Genomic DNA Sequences","year":2004,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; University of Manitoba; Manitoba Health Research Council","keywords":"Hidden Markov model; Bivariate analysis; Expectation–maximization algorithm; Mathematics; Statistic; Binary number; Statistics; Probabilistic logic; Sufficient statistic; Markov chain; Pattern recognition (psychology); Computer science; Algorithm; Artificial intelligence; Maximum likelihood","score_opus":0.0690596579144282,"score_gpt":0.3219836843225449,"score_spread":0.25292402640811673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052915966","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12463253,0.000050207494,0.8744353,0.0005328707,0.00022119026,0.00006571798,0.000053787888,0.0000026870973,0.0000056887643],"genre_scores_gemma":[0.35897267,0.000014350056,0.6407573,0.00019976996,0.000042122396,0.0000010328039,0.000009468201,0.0000020998393,0.0000011426514],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999165,0.00009958378,0.00045514264,0.000098058765,0.00007851277,0.000103725084],"domain_scores_gemma":[0.9986929,0.0005257292,0.0003916086,0.000051832805,0.0003026277,0.000035279314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040219506,0.00006317301,0.00019347471,0.0001732471,0.00002021394,0.000018674817,0.00019709245,0.00005228438,0.000003352113],"category_scores_gemma":[0.00008474629,0.000052796102,0.00005361653,0.00009258162,0.000046262245,0.00018485138,0.000023669068,0.00008424229,0.000001039073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008199548,0.00020773897,0.0018192127,0.00004650905,0.00008086998,0.000031196047,0.0008182788,0.053599786,0.009063936,0.1604799,0.00021663486,0.7735539],"study_design_scores_gemma":[0.0006643858,0.000428508,0.007787975,0.000036003494,0.0000068491086,0.000098751414,0.0000037535085,0.017131751,0.00075194135,0.9728899,0.00012645764,0.0000737412],"about_ca_topic_score_codex":0.00001686576,"about_ca_topic_score_gemma":0.0000104261935,"teacher_disagreement_score":0.81241,"about_ca_system_score_codex":0.000043268006,"about_ca_system_score_gemma":0.00022120714,"threshold_uncertainty_score":0.21529625},"labels":[],"label_agreement":null},{"id":"W2053843934","doi":"10.1002/sam.11149","title":"Nearest‐neighbors medians clustering","year":2012,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Mathematics; Median; Uniqueness; Partition (number theory); Univariate; Cluster analysis; Nonparametric statistics; Fixed point; Sample (material); Algorithm; Combinatorics; Statistics; Mathematical analysis","score_opus":0.09250896968680458,"score_gpt":0.3798075243016192,"score_spread":0.28729855461481457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053843934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012126851,0.00033425455,0.9957324,0.0015662195,0.00036048327,0.00003998605,0.00047185915,0.000018607578,0.00026349],"genre_scores_gemma":[0.19242038,0.00016350135,0.80666405,0.00037498353,0.00026209521,6.616156e-7,0.00009556146,0.0000047212748,0.0000140455095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970434,0.00023387992,0.00041562694,0.0007159078,0.000873646,0.0007175424],"domain_scores_gemma":[0.9951534,0.0006943943,0.00019651286,0.003222027,0.000088921304,0.0006447067],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.011844589,0.0001617286,0.00029638296,0.00028634447,0.0012068391,0.0017316729,0.0083623165,0.00003515855,0.00006132048],"category_scores_gemma":[0.0015942551,0.00009386941,0.000032178323,0.0019763869,0.0007154941,0.0057106344,0.006604244,0.00034703227,0.000008551951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009830228,0.00008470987,0.014402969,0.000008755048,0.00031284802,0.00004579725,0.0021282749,0.000022530487,0.00015405103,0.067818224,0.010048677,0.9049633],"study_design_scores_gemma":[0.00011932075,0.000030806717,0.036691222,0.000014340919,0.00044696673,0.00028430822,0.0002441824,0.95504993,0.000008263499,0.0032935538,0.003590835,0.00022628023],"about_ca_topic_score_codex":0.00007782133,"about_ca_topic_score_gemma":0.00007183079,"teacher_disagreement_score":0.9550274,"about_ca_system_score_codex":0.000022232216,"about_ca_system_score_gemma":0.00020138721,"threshold_uncertainty_score":0.99930465},"labels":[],"label_agreement":null},{"id":"W2053972562","doi":"10.1080/00949650903409999","title":"Evaluation of algorithms for generating Dirichlet random vectors","year":2010,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Algorithm; Dirichlet distribution; Sensitivity (control systems); Random number generation; Transformation (genetics); Goodness of fit; Statistics","score_opus":0.05694458435473418,"score_gpt":0.39265317507927683,"score_spread":0.3357085907245426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053972562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039345156,0.00005496331,0.9598975,0.00009135842,0.000388243,0.00017662476,0.00000554787,0.000006109645,0.00003449117],"genre_scores_gemma":[0.502837,0.0000013000694,0.49706626,0.000019298235,0.00006952448,0.0000010281101,0.0000022724573,0.0000023757837,9.222431e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998629,0.00022296308,0.00047068918,0.00010841675,0.00049049885,0.0000784606],"domain_scores_gemma":[0.9968589,0.0012825252,0.00037055314,0.00005879667,0.0013606694,0.00006856622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032723644,0.00006946405,0.00019031852,0.00010776453,0.00006972214,0.00006424639,0.00007942018,0.00005011106,0.0000056986746],"category_scores_gemma":[0.0011308627,0.000056699744,0.00004242863,0.000103052414,0.00002895362,0.0002581236,0.000014458521,0.000114792834,1.4366111e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030287876,0.000034260524,0.000035072342,0.000015427895,0.000020014279,5.4630647e-7,0.00030859443,0.20109294,0.002463496,0.027327092,0.000043115142,0.76862913],"study_design_scores_gemma":[0.0016051262,0.00013160784,0.0014513688,0.000009088389,0.00005651915,0.000007426541,0.000004916721,0.8836365,0.00021427928,0.11279866,0.00003134926,0.000053207503],"about_ca_topic_score_codex":0.000001387536,"about_ca_topic_score_gemma":0.0000011031877,"teacher_disagreement_score":0.76857597,"about_ca_system_score_codex":0.000014521673,"about_ca_system_score_gemma":0.00009460244,"threshold_uncertainty_score":0.23121484},"labels":[],"label_agreement":null},{"id":"W2054097821","doi":"10.1007/s13171-011-0011-3","title":"Methods of moments estimation in finite mixtures","year":2011,"lang":"en","type":"article","venue":"Sankhya A","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Estimator; Mathematics; Mixing (physics); Rate of convergence; Convergence (economics); Combinatorics; Distribution (mathematics); Estimation; Applied mathematics; Statistics; Mathematical analysis; Physics; Computer science","score_opus":0.04837055170223205,"score_gpt":0.34043029569930655,"score_spread":0.2920597439970745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054097821","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021150606,0.00016540558,0.98748344,0.00004717666,0.0001625381,0.00009049433,7.97916e-7,0.000029911444,0.009905165],"genre_scores_gemma":[0.19832724,0.000005713705,0.8014906,0.0000914081,0.0000056222652,0.000008287363,4.390413e-7,0.0000037399461,0.000066964756],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99910766,0.00023623423,0.00021108407,0.00019436365,0.00010290646,0.00014774606],"domain_scores_gemma":[0.9993975,0.000106932544,0.00008098381,0.00034657345,0.000028775956,0.000039229864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007385291,0.000081228056,0.00015246084,0.0001414116,0.000016287968,0.000011669459,0.00038923472,0.000056049816,0.000027291144],"category_scores_gemma":[0.00009220294,0.00006955656,0.000042699492,0.00030963492,0.00002428483,0.00021571277,0.00009533151,0.000078763514,0.0000060889483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000101544,0.000107215084,0.0005993171,0.00002871207,0.000014162702,0.0000084474295,0.0051534227,0.000045576493,0.0047419104,0.14620511,0.00012964645,0.8429563],"study_design_scores_gemma":[0.00038938373,0.00009492276,0.011231541,0.00005202504,0.000007738958,0.0000046209425,0.000008062505,0.17836085,0.09493945,0.7144757,0.00025075694,0.00018496778],"about_ca_topic_score_codex":0.00005766235,"about_ca_topic_score_gemma":0.000002940387,"teacher_disagreement_score":0.84277135,"about_ca_system_score_codex":0.000011377013,"about_ca_system_score_gemma":0.000025659716,"threshold_uncertainty_score":0.28364342},"labels":[],"label_agreement":null},{"id":"W2054765427","doi":"10.1007/s10115-011-0467-4","title":"A countably infinite mixture model for clustering and feature selection","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Mixture model; Cluster analysis; Model selection; Computer science; Artificial intelligence; Feature selection; Dirichlet process; Dirichlet distribution; Machine learning; Bayesian inference; Inference; Pattern recognition (psychology); Data mining; Mathematics; Bayesian probability","score_opus":0.028644784435366628,"score_gpt":0.25466713485173914,"score_spread":0.2260223504163725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054765427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044848878,0.0006697313,0.983844,0.00003446662,0.0002879308,0.0003435014,0.000007453755,0.0000810636,0.014283411],"genre_scores_gemma":[0.5823224,0.00015790867,0.4155915,0.00039338527,0.00014919639,0.00015249958,0.000012269414,0.00001141436,0.0012093772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939626,0.00003087386,0.00021854686,0.00012970761,0.000070458984,0.0001541486],"domain_scores_gemma":[0.99945915,0.000027392574,0.00010652881,0.0001321803,0.00019805052,0.000076724165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040311506,0.00011881401,0.0001515694,0.000126446,0.00015826603,0.00022365493,0.0001213337,0.00012883489,4.2281198e-7],"category_scores_gemma":[0.00001484988,0.00009857066,0.000024656249,0.00014444429,0.000014560534,0.0027501464,0.00006778618,0.00008676936,0.0000045450215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006700397,0.000036670037,0.00028484064,0.0014938479,0.000058549544,3.388237e-7,0.09350681,0.0002370422,0.00031088587,0.6711775,0.013733292,0.2190932],"study_design_scores_gemma":[0.00033839996,0.000044498658,0.0001425324,0.00005167727,0.0000069530884,0.000042600557,0.000057978647,0.9687272,0.00006251068,0.0011458519,0.029247742,0.0001320728],"about_ca_topic_score_codex":0.000008812988,"about_ca_topic_score_gemma":0.0000074603367,"teacher_disagreement_score":0.9684901,"about_ca_system_score_codex":0.000018271903,"about_ca_system_score_gemma":0.00004115783,"threshold_uncertainty_score":0.40195948},"labels":[],"label_agreement":null},{"id":"W2054890061","doi":"10.2307/3316000","title":"Optimal sampling for repeated binary measurements","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sequence (biology); Sampling (signal processing); Markov chain; Binary number; Pseudorandom binary sequence; Mathematics; Term (time); Dirichlet distribution; Nonparametric statistics; Computer science; Mathematical optimization; Statistics","score_opus":0.09253567411219904,"score_gpt":0.29953879241832526,"score_spread":0.20700311830612622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054890061","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012499355,0.00022247389,0.99717975,0.0004625137,0.0006086009,0.00008388349,0.0000675532,0.000005754542,0.000119564],"genre_scores_gemma":[0.05515504,0.000005879137,0.9444555,0.00024450445,0.00009287504,0.0000011519409,0.000002499648,0.000009650998,0.00003292231],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99909955,0.000030357707,0.00031450222,0.00011791482,0.00015686647,0.0002808219],"domain_scores_gemma":[0.9986312,0.000060808074,0.00018059631,0.00016398428,0.00045367912,0.0005097326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005913757,0.00009117419,0.00016193202,0.00017604306,0.00014540003,0.00011279208,0.00042536552,0.000045041794,0.0000061480305],"category_scores_gemma":[0.00026028042,0.00008593419,0.00005062639,0.00013851786,0.000033868255,0.00017388475,0.0000105719955,0.00012818835,0.0000017153876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049445287,0.00007130813,0.00048798093,0.00010679076,0.00024906002,0.0011153759,0.0034660802,0.026889203,0.0028301938,0.68333495,0.018233389,0.26316625],"study_design_scores_gemma":[0.0070542973,0.0027720253,0.005138481,0.0007250934,0.00023354685,0.0017134695,0.00012151402,0.026977185,0.0055246516,0.90970576,0.0386376,0.0013963688],"about_ca_topic_score_codex":0.00035474577,"about_ca_topic_score_gemma":0.00076658005,"teacher_disagreement_score":0.26176986,"about_ca_system_score_codex":0.00018359492,"about_ca_system_score_gemma":0.0017264107,"threshold_uncertainty_score":0.35042945},"labels":[],"label_agreement":null},{"id":"W2055479965","doi":"10.1111/j.0006-341x.2004.00189.x","title":"Assessing the Goodness‐of‐Fit of Hidden Markov Models","year":2004,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Goodness of fit; Univariate; Hidden Markov model; Mathematics; Statistics; Markov chain; Marginal distribution; Empirical distribution function; Markov model; Computer science; Econometrics; Multivariate statistics; Artificial intelligence; Random variable","score_opus":0.08768316276170808,"score_gpt":0.3412104473876531,"score_spread":0.25352728462594504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055479965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013153511,0.0010789585,0.981426,0.00037610074,0.00031387203,0.00009938351,0.0000032757405,0.00003134472,0.0035175774],"genre_scores_gemma":[0.49932224,0.00003770251,0.5005269,0.00005415593,0.000022411743,0.0000016846085,2.8895136e-7,0.000004868343,0.000029777448],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987889,0.00008162913,0.00030392077,0.00022743561,0.00039920062,0.00019891637],"domain_scores_gemma":[0.99869645,0.00023404034,0.00021556405,0.00064175966,0.00015434058,0.00005782354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009916606,0.00010751933,0.00021079648,0.0006499541,0.00006414959,0.0000985951,0.0010536489,0.00008467762,0.0000022554052],"category_scores_gemma":[0.00013340471,0.00007225028,0.00009905994,0.0053819423,0.00008134425,0.0005259585,0.00025058608,0.0000965983,0.0000018275259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001619274,0.000118565215,0.00009864931,0.000047567766,0.000022447603,0.0000043169393,0.00047157964,0.00011393834,0.0036572348,0.3154441,0.00009528163,0.6799247],"study_design_scores_gemma":[0.0013105728,0.0002509626,0.00730441,0.00016304517,0.000064398526,0.00004389003,0.00011697148,0.079957485,0.059422564,0.84981036,0.00094954896,0.00060576544],"about_ca_topic_score_codex":0.000052022573,"about_ca_topic_score_gemma":5.4967853e-7,"teacher_disagreement_score":0.67931896,"about_ca_system_score_codex":0.00003484062,"about_ca_system_score_gemma":0.00013519442,"threshold_uncertainty_score":0.29462808},"labels":[],"label_agreement":null},{"id":"W2056109357","doi":"10.1109/ijcnn.2013.6707025","title":"Variational learning of finite Beta-Liouville mixture models using component splitting","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Component (thermodynamics); Representation (politics); Inference; Computer science; Artificial intelligence; Selection (genetic algorithm); BETA (programming language); Model selection; Machine learning","score_opus":0.03200690153895129,"score_gpt":0.25855268370870316,"score_spread":0.22654578216975185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056109357","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005462536,0.000090277914,0.9861353,0.0003978793,0.00014068713,0.0001554882,9.309498e-7,0.000084183834,0.007532734],"genre_scores_gemma":[0.3705365,0.00000290747,0.62899274,0.00015191478,0.000041412226,0.0000040915315,0.0000017504341,0.0000071411678,0.00026154853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985664,0.00017901501,0.00035688025,0.00032764263,0.00030467496,0.00026537522],"domain_scores_gemma":[0.99895006,0.00025513198,0.0001828537,0.00032018716,0.00019868156,0.00009308638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052355626,0.00014736028,0.00024068056,0.00011642783,0.00013969566,0.00010793283,0.0004480696,0.00008937917,0.0001200032],"category_scores_gemma":[0.000033730197,0.00012321566,0.00009989373,0.00027672097,0.000027526263,0.0007186887,0.00025072988,0.0002076794,0.000011969347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016281931,0.000050638293,0.00014859525,0.000020464022,0.000040247374,0.0000015823168,0.00086245144,0.08158048,0.01124364,0.8810725,0.00013830297,0.02483944],"study_design_scores_gemma":[0.00014900714,0.000019007188,0.00019884764,0.000018995612,0.000007184841,0.000006242013,0.000014087462,0.9069618,0.0014515315,0.090946265,0.00009113458,0.00013587679],"about_ca_topic_score_codex":0.0002082819,"about_ca_topic_score_gemma":7.369462e-7,"teacher_disagreement_score":0.82538134,"about_ca_system_score_codex":0.00002464093,"about_ca_system_score_gemma":0.000057374167,"threshold_uncertainty_score":0.5024589},"labels":[],"label_agreement":null},{"id":"W2056439621","doi":"10.1111/j.1467-9892.2004.01874.x","title":"Bayesian Subset Model Selection for Time Series","year":2004,"lang":"en","type":"article","venue":"Journal of Time Series Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"SETAR; Autoregressive model; Series (stratigraphy); Bayesian probability; Nonlinear autoregressive exogenous model; Model selection; STAR model; Selection (genetic algorithm); Markov chain; Time series; Bilinear interpolation; Markov chain Monte Carlo; Econometrics; Mathematics; Computer science; Algorithm; Autoregressive integrated moving average; Statistics; Artificial intelligence","score_opus":0.008030792056920965,"score_gpt":0.24779198678748607,"score_spread":0.2397611947305651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056439621","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014251545,0.00011960036,0.9945813,0.0033149712,0.00006979218,0.00008602874,0.000009955632,0.00004008132,0.00035314506],"genre_scores_gemma":[0.019430352,0.000059146656,0.97598577,0.00018998793,0.00017237387,0.000004133545,0.0000047837375,0.000016518396,0.004136941],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984096,0.000082476305,0.0005935012,0.00026316108,0.000346089,0.0003051375],"domain_scores_gemma":[0.9984703,0.00004126696,0.0005151674,0.00031957877,0.00048293296,0.0001707338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008693392,0.00020354491,0.00062650157,0.0005134065,0.00021005512,0.00023465922,0.00061067933,0.000109492925,0.00006282676],"category_scores_gemma":[0.00006013974,0.00016781932,0.0007209729,0.0013291907,0.000045522553,0.0017582676,0.000065525,0.00017157895,0.000011856482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006929147,0.00041771273,0.00033545005,0.000084136285,0.0066925236,0.000052115283,0.002682804,0.8515381,0.029728068,0.06830773,0.008662157,0.030806273],"study_design_scores_gemma":[0.0006446338,0.00063655776,0.00008463266,0.000025161951,0.0013042771,0.00022745355,0.00001759869,0.82167584,0.009597955,0.1639903,0.0014283827,0.00036723813],"about_ca_topic_score_codex":0.000012905421,"about_ca_topic_score_gemma":0.00002670975,"teacher_disagreement_score":0.09568257,"about_ca_system_score_codex":0.000110094414,"about_ca_system_score_gemma":0.00021223322,"threshold_uncertainty_score":0.68434733},"labels":[],"label_agreement":null},{"id":"W2057665853","doi":"10.1239/aap/1214950212","title":"Using systematic sampling selection for Monte Carlo solutions of Feynman-Kac equations","year":2008,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Selection (genetic algorithm); Mathematics; Sampling (signal processing); Convergence (economics); Markov chain Monte Carlo; Monte Carlo method; Systematic sampling; Applied mathematics; Markov chain; Importance sampling; Slice sampling; Mathematical optimization; Statistical physics; Statistics; Computer science; Artificial intelligence","score_opus":0.14451347195259476,"score_gpt":0.3500001587873034,"score_spread":0.20548668683470864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057665853","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009087046,0.00074628403,0.987993,0.000026794107,0.00013223792,0.0015552675,0.0000044595236,0.00006564353,0.00038924182],"genre_scores_gemma":[0.46876335,0.000013358652,0.5309881,0.000010144775,0.000013246387,0.00020344574,4.440596e-7,0.00000427598,0.0000036621332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984814,0.00011694051,0.00054700393,0.00040596994,0.0001705597,0.00027811583],"domain_scores_gemma":[0.9986456,0.00053690077,0.00022790852,0.00042445885,0.00012277803,0.000042362946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011361131,0.00013189005,0.00035935917,0.000094477735,0.00024787744,0.000015181936,0.0003144357,0.000068912144,7.73569e-7],"category_scores_gemma":[0.00022943255,0.00012446847,0.000080107224,0.00053637335,0.00009163715,0.00036508005,0.000076332704,0.000110420886,5.0842976e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001549974,0.00014688096,0.00027216985,0.003407196,0.000012295863,1.4016759e-7,0.0009454796,0.07054777,0.0014900136,0.9161831,0.0000015366609,0.006977908],"study_design_scores_gemma":[0.00026053295,0.000030517363,0.00006761566,0.00022095014,0.000015903144,0.000006205388,0.00001695227,0.54460025,0.0010416455,0.4535647,0.000019494242,0.00015522949],"about_ca_topic_score_codex":0.000030298008,"about_ca_topic_score_gemma":0.00010240472,"teacher_disagreement_score":0.47405246,"about_ca_system_score_codex":0.0001563657,"about_ca_system_score_gemma":0.00010835114,"threshold_uncertainty_score":0.5075677},"labels":[],"label_agreement":null},{"id":"W2058356912","doi":"10.1239/jap/1276784897","title":"On the number of runs for Bernoulli arrays","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Mathematics; Multinomial distribution; Row; Bernoulli's principle; Independent and identically distributed random variables; Combinatorics; Bernoulli trial; Row and column spaces; Sampling (signal processing); Bernoulli process; Statistics; Random variable; Computer science","score_opus":0.019655331318162064,"score_gpt":0.279054144279261,"score_spread":0.25939881296109896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058356912","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14879115,0.0000031805093,0.84167093,0.0015460374,0.00032461536,0.00028090645,0.0000022539348,0.000007600502,0.0073733306],"genre_scores_gemma":[0.453985,9.0890757e-7,0.54571587,0.00018568616,0.00008791821,0.00000861472,6.594263e-8,0.0000039182387,0.000012015868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989391,0.00004942263,0.00042650333,0.00016478957,0.00026132306,0.00015887493],"domain_scores_gemma":[0.99808365,0.0006478586,0.00041062338,0.0005611574,0.00022116424,0.00007555198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028740312,0.000102184866,0.00024548318,0.000024775554,0.000073177114,0.000037760416,0.00083464757,0.00008249688,0.00003259563],"category_scores_gemma":[0.00017265274,0.000057496458,0.00017781879,0.00012683982,0.00009697429,0.00009211913,0.000060135586,0.00042174224,0.0000029649862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006568627,0.00013463691,0.000070865055,0.00002107891,0.00001675905,3.0055023e-7,0.00033656883,0.000018221263,0.0066272523,0.9663392,0.0005860733,0.025783379],"study_design_scores_gemma":[0.00026078924,0.00007036009,0.00031088048,0.000008080967,0.000010092106,0.000014013972,0.0000045926777,0.0008292469,0.017736545,0.9790881,0.0016019703,0.000065316075],"about_ca_topic_score_codex":0.0000011899385,"about_ca_topic_score_gemma":0.0000022862614,"teacher_disagreement_score":0.30519387,"about_ca_system_score_codex":0.000016288375,"about_ca_system_score_gemma":0.0001153745,"threshold_uncertainty_score":0.23446375},"labels":[],"label_agreement":null},{"id":"W2058367787","doi":"10.1016/j.imavis.2014.10.011","title":"Simultaneous high-dimensional clustering and feature selection using asymmetric Gaussian mixture models","year":2014,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Interpretability; Cluster analysis; Computer science; Outlier; Mahalanobis distance; Artificial intelligence; Gaussian; Feature selection; Feature (linguistics); Pattern recognition (psychology); Statistical model; Algorithm; Machine learning","score_opus":0.010881708267838295,"score_gpt":0.2862929925966823,"score_spread":0.275411284328844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058367787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036004808,0.00035570463,0.96250767,0.00039865173,0.00024979317,0.00011492179,8.495536e-7,0.00012679916,0.00024083548],"genre_scores_gemma":[0.50362664,0.000006326362,0.49593192,0.0002674803,0.00013212445,2.5130691e-7,8.9119305e-7,0.000010129524,0.000024222805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983844,0.00020360517,0.00021655086,0.0006198103,0.00023759122,0.00033802833],"domain_scores_gemma":[0.99900734,0.00036973078,0.00012249098,0.00022478204,0.000111623485,0.00016403735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063805335,0.00023100263,0.0002733972,0.00022523798,0.00049194164,0.00042749915,0.0001963889,0.00014650685,0.000001052607],"category_scores_gemma":[0.000083480685,0.00019758876,0.000043623746,0.0004668001,0.000040842348,0.00054581347,0.00044017794,0.0003106671,0.0000011119406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011731669,0.000027261754,0.000025325431,0.000054475116,0.000012933932,0.00002577258,0.00028010926,0.015266776,0.010123425,0.006412983,0.00015707006,0.96760213],"study_design_scores_gemma":[0.00037702036,0.00010095387,0.0001671379,0.00010761836,0.000012057648,0.00033713828,0.0000034232778,0.9889534,0.00065035495,0.008924964,0.00012299612,0.00024293528],"about_ca_topic_score_codex":0.00004177316,"about_ca_topic_score_gemma":0.0000033292104,"teacher_disagreement_score":0.97368664,"about_ca_system_score_codex":0.000025013,"about_ca_system_score_gemma":0.000020875119,"threshold_uncertainty_score":0.8057436},"labels":[],"label_agreement":null},{"id":"W2059098648","doi":"10.1017/s0004972712000421","title":"A NOTE CONCERNING THE DISTANCES OF UNIFORMLY DISTRIBUTED POINTS FROM THE CENTRE OF A RECTANGLE","year":2012,"lang":"en","type":"article","venue":"Bulletin of the Australian Mathematical Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Rectangle; Mathematics; Probability density function; Expression (computer science); Combinatorics; Function (biology); Cumulative distribution function; Closed-form expression; Geometry; Mathematical analysis; Statistics; Computer science","score_opus":0.028284503859335185,"score_gpt":0.26669667358047777,"score_spread":0.2384121697211426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059098648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02473969,0.0001632725,0.9317457,0.04193191,0.0001587336,0.00037930568,0.00014491922,0.000024540761,0.0007119358],"genre_scores_gemma":[0.73361856,0.000008871615,0.2655389,0.0002599114,0.00006115,0.000005283041,0.000002240502,0.000008999725,0.00049609377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983709,0.00030253676,0.0004631686,0.0001559946,0.00040311,0.00030428843],"domain_scores_gemma":[0.99743366,0.0011583604,0.00045120815,0.00081114564,0.000080025784,0.00006560802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012648988,0.00014940198,0.00032042357,0.0000035409876,0.00012760777,0.000025906655,0.0014831803,0.00009266711,0.00018270212],"category_scores_gemma":[0.00030950125,0.00006601413,0.00040974264,0.00021290075,0.00047563977,0.000046352397,0.00035109927,0.00022862718,0.0000087781145],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038856066,0.00063068146,0.0030677384,0.00045934215,0.00042291253,5.644487e-7,0.04044133,0.000023296756,0.004922919,0.7822879,0.16083424,0.006870237],"study_design_scores_gemma":[0.0021426072,0.00016324298,0.026968563,0.0024067392,0.000626247,0.0000270773,0.0059217415,0.0078263935,0.1058955,0.69652945,0.1504966,0.000995834],"about_ca_topic_score_codex":0.0000823223,"about_ca_topic_score_gemma":0.0000016101834,"teacher_disagreement_score":0.7088789,"about_ca_system_score_codex":0.000025030535,"about_ca_system_score_gemma":0.000029683863,"threshold_uncertainty_score":0.2756143},"labels":[],"label_agreement":null},{"id":"W2059439741","doi":"10.1177/0962280209344926","title":"Outlier detection for a hierarchical Bayes model in a study of hospital variation in surgical procedures","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Carleton University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Southern California","keywords":"Outlier; Bayes' theorem; Variation (astronomy); Computer science; Multilevel model; Statistics; Anomaly detection; Random effects model; Bayesian hierarchical modeling; Data mining; Bayesian probability; Artificial intelligence; Medicine; Machine learning; Mathematics","score_opus":0.056961056414367765,"score_gpt":0.4984115217864363,"score_spread":0.4414504653720685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059439741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06535888,0.000017990385,0.9320059,0.0007271104,0.00023701241,0.0013047996,0.0000071565078,0.000019419196,0.000321741],"genre_scores_gemma":[0.4542117,0.000006877548,0.5453468,0.000014151646,0.000045398123,0.0003541908,6.99978e-7,0.000009898068,0.0000102832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912995,0.0042944285,0.00096159894,0.0008969075,0.0017198197,0.000827757],"domain_scores_gemma":[0.98369414,0.015100935,0.0000681225,0.00048865005,0.00026254423,0.00038563067],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02813781,0.00017644005,0.0005510312,0.0008177569,0.0000666281,0.0000613482,0.00096394,0.0004060784,0.00004329629],"category_scores_gemma":[0.048269715,0.00014641507,0.000048417533,0.0014421107,0.00034223823,0.00017357545,0.00041228347,0.0025613823,0.0000010178425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023055126,0.002172618,0.0005428439,0.00009882604,0.000006759746,0.00011870692,0.0032864828,0.000031573873,0.0010373092,0.27423373,0.000012750979,0.71822786],"study_design_scores_gemma":[0.0014809744,0.0007479488,0.009437502,0.0000402645,0.0000017993235,0.000004207198,0.00005216481,0.5717137,0.0001387152,0.41625372,0.000022223572,0.00010681552],"about_ca_topic_score_codex":0.00030267477,"about_ca_topic_score_gemma":0.0018846742,"teacher_disagreement_score":0.71812105,"about_ca_system_score_codex":0.000087668406,"about_ca_system_score_gemma":0.0007276428,"threshold_uncertainty_score":0.99973977},"labels":[],"label_agreement":null},{"id":"W2059997481","doi":"10.1007/s12530-012-9047-4","title":"Online variational learning of finite Dirichlet mixture models","year":2012,"lang":"en","type":"article","venue":"Evolving Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Dirichlet distribution; Inference; Mixture model; Algorithm; Scale (ratio); Artificial intelligence; Machine learning; Mathematics","score_opus":0.025564127592940116,"score_gpt":0.2640638366494371,"score_spread":0.238499709056497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059997481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085957244,0.0032135716,0.99130684,0.00011141411,0.0010748623,0.00012474044,0.000007997726,0.00011119637,0.0031898036],"genre_scores_gemma":[0.6564979,0.000008717487,0.3422102,0.000040695428,0.0003690332,0.000006933216,0.000007209865,0.000010940061,0.00084834424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837744,0.00032994454,0.00035627536,0.00023589878,0.00036483616,0.00033560523],"domain_scores_gemma":[0.99872446,0.0003549253,0.0002380705,0.0003933853,0.00017031649,0.00011884362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011066885,0.00014752362,0.0002729695,0.00011617956,0.000099464996,0.000076167664,0.00047910304,0.00011373641,0.000010147064],"category_scores_gemma":[0.00017241613,0.0001275382,0.00008086832,0.00031316525,0.000017862478,0.0008569556,0.00014538346,0.0002289247,0.000010392649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003655559,0.00023424729,0.0026182327,0.00016158588,0.00006936704,0.0000028923955,0.0044894293,0.037504997,0.001464286,0.94565916,0.0022000414,0.0055921143],"study_design_scores_gemma":[0.00014475801,0.000025959906,0.0013354452,0.00009676769,0.000009401751,0.000016154429,0.00002255288,0.9910528,0.000050692048,0.005191092,0.0018916905,0.00016270205],"about_ca_topic_score_codex":0.00005567477,"about_ca_topic_score_gemma":5.9170605e-7,"teacher_disagreement_score":0.9535478,"about_ca_system_score_codex":0.000036821777,"about_ca_system_score_gemma":0.000053612683,"threshold_uncertainty_score":0.52008563},"labels":[],"label_agreement":null},{"id":"W2060003092","doi":"10.1016/j.knosys.2014.01.007","title":"Robust simultaneous positive data clustering and unsupervised feature selection using generalized inverted Dirichlet mixture models","year":2014,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Outlier; Artificial intelligence; Data mining; Pattern recognition (psychology); Latent Dirichlet allocation; Determining the number of clusters in a data set; Model selection; Machine learning; Dirichlet distribution; Clustering high-dimensional data; Correlation clustering; CURE data clustering algorithm; Mathematics; Topic model","score_opus":0.0613960326143573,"score_gpt":0.2785006054309159,"score_spread":0.21710457281655862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060003092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043210364,0.0021887908,0.9907524,0.00020580267,0.00092454604,0.0006386646,0.000042742922,0.00031867862,0.00060732034],"genre_scores_gemma":[0.6173545,0.000011998492,0.3814644,0.00025708828,0.0004499854,0.000018607276,0.00007678135,0.00005353357,0.00031310722],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618757,0.0012955295,0.0004236858,0.0012209043,0.00031959944,0.000552701],"domain_scores_gemma":[0.9973091,0.00047950467,0.00020315124,0.0013264687,0.00039407235,0.00028768755],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012060691,0.00046465386,0.00062899536,0.000261484,0.00044940738,0.00055028946,0.0011588912,0.00037418585,0.0000018284106],"category_scores_gemma":[0.0001374607,0.00041050935,0.00007981444,0.0007706894,0.000067979374,0.00074376195,0.0004754887,0.00038725854,0.0000054469733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024810943,0.00044388778,0.0002241702,0.0015176745,0.00038040458,0.000083055005,0.0039538043,0.8141393,0.057535138,0.022110362,0.005521259,0.09384284],"study_design_scores_gemma":[0.0012401231,0.00008397937,0.000010651652,0.0003073243,0.00006328391,0.00010270575,0.000012443812,0.99535704,0.0006448098,0.000541867,0.0011298386,0.00050594145],"about_ca_topic_score_codex":0.00025003662,"about_ca_topic_score_gemma":0.00016008595,"teacher_disagreement_score":0.6130335,"about_ca_system_score_codex":0.00014732084,"about_ca_system_score_gemma":0.00018860752,"threshold_uncertainty_score":0.99983466},"labels":[],"label_agreement":null},{"id":"W2060489239","doi":"10.1016/j.spl.2013.09.012","title":"Erratum to “Dimension reduction for model-based clustering via mixtures of shifted asymmetric Laplace distributions” [Statist. Probab. Lett. 83 (9) (2013) 2088–2093]","year":2013,"lang":"en","type":"erratum","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mathematics; Dimension (graph theory); Dimensionality reduction; Reduction (mathematics); Laplace transform; Applied mathematics; Statistics; Pure mathematics; Mathematical analysis; Geometry; Artificial intelligence; Computer science","score_opus":0.018228854741069663,"score_gpt":0.26842299238420114,"score_spread":0.2501941376431315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060489239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052571635,0.00027715246,0.9742105,0.0077824756,0.009678939,0.004554352,0.0030194153,0.0002512424,0.00017337696],"genre_scores_gemma":[0.00041316324,0.000022578792,0.992672,0.0011540704,0.00043714704,0.00086575095,0.0021948111,0.000120911944,0.0021195442],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99306005,0.000707125,0.0016784159,0.0021870898,0.0010939342,0.0012733868],"domain_scores_gemma":[0.99428725,0.00056324597,0.0010914224,0.0023017598,0.0012624173,0.00049391005],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017378137,0.0010647868,0.0014126402,0.00073596847,0.00042877448,0.00036763801,0.0016762449,0.00076509814,0.000013453353],"category_scores_gemma":[0.0008185758,0.0010583047,0.00035506368,0.0014015967,0.000343544,0.00044731,0.0004953926,0.0012847569,0.000019285726],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107712745,0.00024276954,0.0000018459245,0.0017747245,0.00009523167,0.000006493911,0.00027210332,0.0018280037,0.0024300665,0.04339827,0.9215211,0.028321633],"study_design_scores_gemma":[0.0007995946,0.0004592381,0.000047866124,0.0004429142,0.00021742674,0.000015799184,0.0000014112337,0.5532054,0.0011264909,0.43321046,0.009145371,0.001328062],"about_ca_topic_score_codex":0.00036147167,"about_ca_topic_score_gemma":0.00010511247,"teacher_disagreement_score":0.91237575,"about_ca_system_score_codex":0.0007654054,"about_ca_system_score_gemma":0.0007993894,"threshold_uncertainty_score":0.9991867},"labels":[],"label_agreement":null},{"id":"W2060556149","doi":"10.1007/s10044-008-0111-4","title":"On Bayesian analysis of a finite generalized Dirichlet mixture via a Metropolis-within-Gibbs sampling","year":2008,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Dirichlet distribution; Gibbs sampling; Conjugate prior; Mathematics; Hierarchical Dirichlet process; Metropolis–Hastings algorithm; Generalized Dirichlet distribution; Latent Dirichlet allocation; Kernel (algebra); Applied mathematics; Bayesian probability; Pattern recognition (psychology); Computer science; Artificial intelligence; Algorithm; Statistics; Posterior probability; Markov chain Monte Carlo; Topic model; Dirichlet's energy; Combinatorics; Mathematical analysis","score_opus":0.02449743636263198,"score_gpt":0.29227753959725356,"score_spread":0.2677801032346216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060556149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010341658,0.00019610253,0.9885517,0.00034040282,0.0000151008235,0.00017035492,0.00006227932,0.000052545107,0.0002698934],"genre_scores_gemma":[0.765613,0.000104937666,0.23325339,0.00071664905,0.00003925332,0.00008973679,0.00007052508,0.000009472137,0.00010302998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809474,0.00015225512,0.0005284224,0.00066930585,0.0003119336,0.00024337006],"domain_scores_gemma":[0.9980926,0.00023539516,0.00033097196,0.0010408186,0.00012554092,0.00017471057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034791182,0.00022651178,0.0007208004,0.0012376133,0.0002833618,0.000067715104,0.00053850847,0.000093740135,0.000050520877],"category_scores_gemma":[0.000019690584,0.00018786751,0.00054255564,0.0058547896,0.00008317703,0.00010080497,0.00011511987,0.0001526562,0.000004342291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036611178,0.0015408226,0.09275573,0.000109801906,0.034787375,0.000026751924,0.0065066684,0.036771234,0.008125968,0.3863713,0.00047086625,0.43249688],"study_design_scores_gemma":[0.00030182305,0.000040812854,0.020291528,0.0000071278087,0.0052171824,0.0000042821503,0.000012796656,0.9595532,0.0013455288,0.012156906,0.0006611017,0.0004077376],"about_ca_topic_score_codex":0.00043881751,"about_ca_topic_score_gemma":0.00020581672,"teacher_disagreement_score":0.92278194,"about_ca_system_score_codex":0.000022412496,"about_ca_system_score_gemma":0.00002451405,"threshold_uncertainty_score":0.7661015},"labels":[],"label_agreement":null},{"id":"W2060634510","doi":"10.1080/01431160802392646","title":"Finite Gamma mixture modelling using minimum message length inference: application to SAR image analysis","year":2009,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Sherbrooke","funders":"","keywords":"Computer science; Inference; Set (abstract data type); Image (mathematics); Segmentation; Data set; Synthetic aperture radar; Finite set; Artificial intelligence; Image segmentation; Unsupervised learning; Synthetic data; Pattern recognition (psychology); Algorithm; Data mining; Mathematics","score_opus":0.021962810220889247,"score_gpt":0.3197440377333011,"score_spread":0.2977812275124119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060634510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020098744,0.00008930872,0.9764761,0.002438617,0.0003659053,0.00007666064,0.0000022845786,0.000027350214,0.00042503406],"genre_scores_gemma":[0.41997325,0.00002277593,0.5791651,0.0005634418,0.00025009652,5.8483005e-9,0.0000013449408,0.000005797013,0.000018207933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979533,0.00013014188,0.0006329086,0.00030989118,0.000737897,0.00023585666],"domain_scores_gemma":[0.99771285,0.0001608754,0.0005418381,0.00033078942,0.0010808359,0.00017283742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008353481,0.00018945834,0.00035275889,0.0008416452,0.000084830404,0.00033699686,0.000814186,0.00009678073,0.0000040383306],"category_scores_gemma":[0.00013853869,0.00017334036,0.0002889698,0.0007827971,0.000019537927,0.00059927703,0.00009281319,0.0003233504,0.0000045868137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037405076,0.000024270206,0.0000072290936,0.000002510495,0.0002664043,0.0001429119,0.00092090614,0.15181491,0.025916507,0.001356897,0.000036815978,0.8194732],"study_design_scores_gemma":[0.00021566566,0.00004339286,0.000049280676,0.00008824803,0.000106171574,0.00015605497,0.000015898298,0.9706153,0.004032962,0.023953717,0.00054740196,0.00017588878],"about_ca_topic_score_codex":0.000034410325,"about_ca_topic_score_gemma":0.0000033163926,"teacher_disagreement_score":0.8192974,"about_ca_system_score_codex":0.0001445498,"about_ca_system_score_gemma":0.000102461454,"threshold_uncertainty_score":0.7068615},"labels":[],"label_agreement":null},{"id":"W2060679993","doi":"10.1239/jap/1245676095","title":"A Central Limit Theorem Associated with the Transformed Two-Parameter Poisson–Dirichlet Distribution","year":2009,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Dirichlet distribution; Poisson distribution; Central limit theorem; Limit (mathematics); Concentration parameter; Distribution (mathematics); Simplex; Applied mathematics; Pure mathematics; Mathematical analysis; Combinatorics; Statistics","score_opus":0.012979437113765806,"score_gpt":0.23696040582359254,"score_spread":0.22398096870982673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060679993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14333451,0.0000332311,0.84840184,0.0062026954,0.00007349967,0.00035978507,0.000005764335,0.00003432767,0.0015543664],"genre_scores_gemma":[0.90361506,0.000005253205,0.09562178,0.0006618926,0.000074529984,0.00000518637,0.0000026515513,0.0000053048348,0.000008327358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981095,0.00023915022,0.00046636333,0.00026142166,0.00049287704,0.00043065977],"domain_scores_gemma":[0.99843425,0.0003466547,0.00041522685,0.00042162635,0.00021831301,0.00016391944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002511761,0.00019889776,0.00035725944,0.00003201158,0.00015202224,0.00015674582,0.00079165667,0.00009390943,0.000006104417],"category_scores_gemma":[0.00011429639,0.000104298466,0.00018159418,0.00043652792,0.00011639932,0.00029651195,0.000026348256,0.00052578363,8.10327e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084018527,0.0008806288,0.00022165207,0.000016148051,0.00017168758,0.000021291446,0.0034436341,0.00061651325,0.0014195951,0.6440166,0.0013012363,0.3470508],"study_design_scores_gemma":[0.0019896852,0.0007852409,0.021075064,0.000045862966,0.00010518192,0.0000738528,0.000027991557,0.006016485,0.0049288603,0.9635739,0.0010639648,0.0003139463],"about_ca_topic_score_codex":0.0000013470985,"about_ca_topic_score_gemma":0.000007741871,"teacher_disagreement_score":0.76028055,"about_ca_system_score_codex":0.00019189261,"about_ca_system_score_gemma":0.00017306415,"threshold_uncertainty_score":0.42531678},"labels":[],"label_agreement":null},{"id":"W2060831937","doi":"10.1198/jasa.2010.tm09032","title":"Testing the Order of a Finite Mixture","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Homogeneity (statistics); Mathematics; Null hypothesis; Likelihood-ratio test; Applied mathematics; Statistical hypothesis testing; Limiting; Null (SQL); Statistics; Statistical power; Null distribution; Alternative hypothesis; Ratio test; Test statistic; Computer science; Data mining","score_opus":0.011810188231399895,"score_gpt":0.2762009980932988,"score_spread":0.2643908098618989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060831937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018301576,0.000009503836,0.97530645,0.005518217,0.0004151578,0.00004519005,0.00000841821,0.0000053920708,0.00039010946],"genre_scores_gemma":[0.4062132,0.0000017844242,0.59304243,0.0005629336,0.00012237045,5.605962e-7,8.866288e-8,0.0000035205026,0.000053101812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986546,0.00033452074,0.00033844815,0.00007801775,0.00045128184,0.00014313824],"domain_scores_gemma":[0.9943594,0.0033446376,0.0014863004,0.00022513875,0.00053672056,0.000047850335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014741325,0.00006869127,0.00021190236,0.000030471356,0.0000923019,0.000055239438,0.00066152075,0.000030688276,0.0000054476186],"category_scores_gemma":[0.008184294,0.000033869004,0.000071845716,0.00058514514,0.00009338275,0.00010383017,0.00009001162,0.00051976193,0.0000013937448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003264049,0.00016919055,0.02370782,0.000013792325,0.00017133029,0.00001005463,0.0011809797,0.00012578313,0.038382392,0.19100903,0.0119119175,0.73328507],"study_design_scores_gemma":[0.0005427203,0.0004603151,0.5975176,0.00005292873,0.00015615411,0.00009837337,0.000053692052,0.062072806,0.0015658233,0.33250666,0.004726647,0.0002462367],"about_ca_topic_score_codex":0.000030182222,"about_ca_topic_score_gemma":0.000006818644,"teacher_disagreement_score":0.73303884,"about_ca_system_score_codex":0.00003915568,"about_ca_system_score_gemma":0.00013124368,"threshold_uncertainty_score":0.9797956},"labels":[],"label_agreement":null},{"id":"W2061064612","doi":"10.2307/3315982","title":"Bayesian assessment of goodness of fit against nonparametric alternatives","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Goodness of fit; Nonparametric statistics; Chi-square test; Bayesian probability; Bayes factor; Parametric statistics; Statistical hypothesis testing; Mathematics; Statistics; Bayes' theorem; Computer science; Econometrics; Data mining","score_opus":0.024817650420694257,"score_gpt":0.2941580930083434,"score_spread":0.2693404425876491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061064612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007940093,0.0002420015,0.98741376,0.00012218473,0.00028334418,0.00006191235,0.00017002634,0.000002277777,0.0037643928],"genre_scores_gemma":[0.46862552,0.00006974075,0.53111047,0.00006692537,0.000026510019,3.242366e-7,8.929689e-7,0.000005703973,0.00009392768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856925,0.00013739095,0.0006204203,0.00012911776,0.00029929087,0.00024451065],"domain_scores_gemma":[0.9981913,0.000222151,0.0004723219,0.00026835618,0.00037330683,0.00047256387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005376068,0.000120833996,0.00037146395,0.00044134245,0.00005075204,0.000048452282,0.0007519061,0.000051600076,0.00012945748],"category_scores_gemma":[0.00010985888,0.00011018599,0.000075548094,0.00050743367,0.00011958965,0.00019756591,0.000013971898,0.00020377286,9.863883e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047551066,0.000056687466,0.0022043202,0.00006589904,0.00009354865,0.0002869489,0.00088057644,0.0013793922,0.00012499881,0.1291128,0.0014696321,0.86432046],"study_design_scores_gemma":[0.0040572393,0.0027998155,0.10408465,0.0011742413,0.00026927306,0.0005629643,0.00026781633,0.57538265,0.005263226,0.29033285,0.014268527,0.0015367427],"about_ca_topic_score_codex":0.0006991536,"about_ca_topic_score_gemma":0.0005471309,"teacher_disagreement_score":0.86278373,"about_ca_system_score_codex":0.000088201705,"about_ca_system_score_gemma":0.0015072982,"threshold_uncertainty_score":0.4493254},"labels":[],"label_agreement":null},{"id":"W2062898238","doi":"10.1080/00949650108812097","title":"A diagnostic tool for mixture models","year":2001,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"","keywords":"Mixture model; Mathematics; Mixture distribution; Representation (politics); Density estimation; Expectation–maximization algorithm; Nonparametric statistics; Scale (ratio); Maximum likelihood; Sample (material); Applied mathematics; Statistics; Probability density function","score_opus":0.030774683507232885,"score_gpt":0.3327422814412914,"score_spread":0.30196759793405853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062898238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040637376,0.00009887293,0.9949941,0.00043138297,0.00016351898,0.0001492585,0.0000052151013,0.000014438368,0.00007944294],"genre_scores_gemma":[0.4868214,0.000015857508,0.5129417,0.00014616568,0.00005897578,0.0000011040961,0.0000020392365,0.0000031200607,0.000009585848],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910855,0.00008841457,0.000369569,0.00012496994,0.000195182,0.0001133342],"domain_scores_gemma":[0.9966378,0.0026960094,0.0001848377,0.000059272556,0.00033434058,0.000087709515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004458609,0.00008304436,0.00017477944,0.000092300295,0.000078790676,0.00011814954,0.00009612483,0.00005103221,0.000003354803],"category_scores_gemma":[0.00049871404,0.00006799469,0.000043149867,0.00011328366,0.000020273696,0.00048599648,0.000019201505,0.00009304767,5.981499e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004510602,0.00003896882,0.00009658626,0.000018292609,0.0000121551775,0.000015739504,0.00025513573,0.3246618,0.000015299367,0.2740556,0.00019083328,0.40059447],"study_design_scores_gemma":[0.00041256525,0.00012186765,0.0012432985,0.000013232659,0.000011056205,0.000021179243,0.0000022240804,0.6067848,0.000002471031,0.3911247,0.00021147865,0.00005109388],"about_ca_topic_score_codex":7.759614e-7,"about_ca_topic_score_gemma":3.1161514e-7,"teacher_disagreement_score":0.48275766,"about_ca_system_score_codex":0.000018250497,"about_ca_system_score_gemma":0.000036241447,"threshold_uncertainty_score":0.2772743},"labels":[],"label_agreement":null},{"id":"W2063884065","doi":"10.1080/00207160701690425","title":"Testing the number of components of the mixture of two inverse Weibull distributions","year":2008,"lang":"en","type":"article","venue":"International Journal of Computer Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Memorial University of Newfoundland","keywords":"Mathematics; Weibull distribution; Likelihood-ratio test; Statistics; Maximization; Test statistic; Statistic; Applied mathematics; Inverse; Expectation–maximization algorithm; Score test; Maximum likelihood; Statistical hypothesis testing; Mathematical optimization","score_opus":0.0459856150671948,"score_gpt":0.3049401981709952,"score_spread":0.25895458310380043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063884065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18379721,0.000022577937,0.8146189,0.0005967397,0.00061943784,0.00005745019,0.000011490989,0.000004046119,0.00027215242],"genre_scores_gemma":[0.47554922,0.0000053274193,0.524278,0.000057493453,0.00009205324,3.459933e-7,4.1333632e-7,0.0000035077103,0.000013664777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99820787,0.0001219104,0.0007989156,0.0000786907,0.0006963779,0.00009624738],"domain_scores_gemma":[0.99662614,0.00057285215,0.0013178039,0.00032855582,0.0011164576,0.00003819064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005395591,0.00010440171,0.00027846277,0.000060995586,0.0000527703,0.00001901167,0.0019110224,0.00003572948,0.000006672883],"category_scores_gemma":[0.00013046498,0.00005858082,0.00022128574,0.00022977045,0.0001785095,0.0001632443,0.00037452293,0.00020265188,0.0000011317151],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036388767,0.0019653277,0.0151716,0.00021585768,0.0010926777,0.00008187293,0.013200598,0.0031129774,0.02498117,0.90951693,0.00694743,0.02367719],"study_design_scores_gemma":[0.0021864816,0.00015660873,0.027471745,0.00144136,0.00012451601,0.0056495643,0.000046377114,0.40746123,0.02532263,0.5289903,0.00084492244,0.0003042554],"about_ca_topic_score_codex":0.000011180212,"about_ca_topic_score_gemma":6.794672e-7,"teacher_disagreement_score":0.40434825,"about_ca_system_score_codex":0.000025870153,"about_ca_system_score_gemma":0.00010104293,"threshold_uncertainty_score":0.3551187},"labels":[],"label_agreement":null},{"id":"W2064014870","doi":"10.1016/j.jmva.2008.12.005","title":"Inference for multivariate normal mixtures","year":2008,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Science Foundation","keywords":"Mathematics; Likelihood function; Estimator; Multivariate statistics; Multivariate normal distribution; Inference; Maximum likelihood; Statistics; Statistical inference; Expectation–maximization algorithm; Mixing (physics); Restricted maximum likelihood; M-estimator; Applied mathematics; Maximum likelihood sequence estimation; Econometrics; Artificial intelligence; Computer science","score_opus":0.03310425386564551,"score_gpt":0.32219656686383497,"score_spread":0.28909231299818944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064014870","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008642885,0.00025437737,0.989859,0.00052839227,0.00031708527,0.0001098531,0.0000062307586,0.000028479106,0.00025372836],"genre_scores_gemma":[0.48503995,0.00005122244,0.5144058,0.00016009623,0.00014688396,0.000003408903,0.0000012582051,0.000007224212,0.0001841459],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774015,0.000263457,0.0008475251,0.00032153944,0.00045094726,0.00037638273],"domain_scores_gemma":[0.997023,0.0006369682,0.00085504784,0.00049385114,0.00075354264,0.00023759204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012864501,0.0002365823,0.0007508536,0.0007343039,0.0002462414,0.000099562814,0.0011189639,0.0001372881,0.000022340293],"category_scores_gemma":[0.0005188716,0.0001766054,0.00092291506,0.0012631085,0.000052857376,0.00082851993,0.00013553788,0.000295647,0.000003951487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013907647,0.0032696703,0.021621529,0.00019653238,0.03154721,0.0015501705,0.030063841,0.051076192,0.15153208,0.29333645,0.0047928686,0.4096227],"study_design_scores_gemma":[0.0044103623,0.00061046577,0.041809756,0.000058342404,0.0023794156,0.00028658958,0.00002643617,0.90145916,0.016066397,0.026286853,0.0056793806,0.0009268238],"about_ca_topic_score_codex":0.00010596421,"about_ca_topic_score_gemma":0.0000089227115,"teacher_disagreement_score":0.850383,"about_ca_system_score_codex":0.000046938294,"about_ca_system_score_gemma":0.00018882046,"threshold_uncertainty_score":0.7201759},"labels":[],"label_agreement":null},{"id":"W2064459221","doi":"10.1080/03461230701862889","title":"Modelling long-term investment returns via Bayesian infinite mixture time series models","year":2008,"lang":"en","type":"article","venue":"Scandinavian Actuarial Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Econometrics; Outlier; Bayesian average; Quantile; Bayesian econometrics; Series (stratigraphy); Variable-order Bayesian network; Computer science; Autoregressive model; Mathematics; Bayesian inference; Statistics","score_opus":0.02481877631996234,"score_gpt":0.24415639833189556,"score_spread":0.21933762201193321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064459221","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068297535,0.00042510513,0.9855783,0.0010952516,0.0014655289,0.0002862621,0.000008874398,0.00017660235,0.004134341],"genre_scores_gemma":[0.36268535,0.00048534633,0.63227075,0.0012587855,0.0017241725,0.00001211598,0.000012441189,0.0000644714,0.001486594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996301,0.00041753324,0.0007993376,0.0006899253,0.0008312261,0.000960974],"domain_scores_gemma":[0.99756026,0.00008054328,0.00044937525,0.00085603754,0.00022033941,0.0008334528],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080690085,0.00055425696,0.00064557884,0.00039028627,0.0010316162,0.00061363046,0.0015063372,0.000351361,0.00012888532],"category_scores_gemma":[0.000024233552,0.0004693114,0.0003719183,0.00053206435,0.00019566355,0.0027686777,0.00029012622,0.0011321518,0.000057248817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003463107,0.0027478766,0.006664031,0.0004519513,0.0031192694,0.027675051,0.09800481,0.21068141,0.015270128,0.3283181,0.04446094,0.25914335],"study_design_scores_gemma":[0.002361364,0.0005668108,0.00041633565,0.0003335113,0.000094080555,0.016814603,0.000012481479,0.5764312,0.0014727728,0.39962426,0.0005253556,0.0013472053],"about_ca_topic_score_codex":0.00002318363,"about_ca_topic_score_gemma":0.000003746043,"teacher_disagreement_score":0.3657498,"about_ca_system_score_codex":0.00023735347,"about_ca_system_score_gemma":0.0003646545,"threshold_uncertainty_score":0.9997759},"labels":[],"label_agreement":null},{"id":"W2065708566","doi":"10.1007/s11634-013-0155-1","title":"A LASSO-penalized BIC for mixture model selection","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Lasso (programming language); Model selection; Selection (genetic algorithm); Mathematics; Computer science; Artificial intelligence; Statistics","score_opus":0.04016452122136844,"score_gpt":0.34145722688980523,"score_spread":0.3012927056684368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065708566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079216156,0.00088069675,0.9967263,0.0009735966,0.00003280981,0.00024586823,0.0000205581,0.000035524503,0.00029248325],"genre_scores_gemma":[0.20538168,0.0010255753,0.79286,0.0001544141,0.000024712845,0.00012991848,0.00019651755,0.0000051974284,0.0002220124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988203,0.000078456156,0.0002639868,0.0005404883,0.0001249416,0.00017182995],"domain_scores_gemma":[0.9988116,0.00010074643,0.00014535026,0.0007928432,0.000096694814,0.000052774016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004847892,0.00011085458,0.00022455551,0.00024499153,0.000090681206,0.00016532137,0.00064924447,0.000067737084,0.0000068584873],"category_scores_gemma":[0.00007043732,0.000091741254,0.000050713108,0.0010864557,0.000026353737,0.0022163533,0.00011330469,0.00007946464,0.000003091581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010541607,0.0000832943,0.0028854616,0.00003118517,0.00011202732,1.2609871e-7,0.0001732927,0.0010339442,0.005025663,0.1659119,0.0008085767,0.823924],"study_design_scores_gemma":[0.0001841632,0.000010222973,0.0029944885,0.00000501982,0.00008944958,4.1583718e-7,0.000011481892,0.91570276,0.0001237894,0.07753825,0.0032299014,0.00011005527],"about_ca_topic_score_codex":0.00002667621,"about_ca_topic_score_gemma":0.00028912665,"teacher_disagreement_score":0.9146688,"about_ca_system_score_codex":0.00002299475,"about_ca_system_score_gemma":0.000025159128,"threshold_uncertainty_score":0.37410995},"labels":[],"label_agreement":null},{"id":"W2066380414","doi":"10.1007/s11222-010-9204-1","title":"Flexible mixture modeling via the multivariate t distribution with the Box-Cox transformation: an alternative to the skew-t distribution","year":2010,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Outlier; Mixture model; Power transform; Cluster analysis; Skewness; Transformation (genetics); Multivariate statistics; Mathematics; Data transformation; Expectation–maximization algorithm; Multivariate normal distribution; Skew; Computer science; Model selection; Algorithm; Data mining; Artificial intelligence; Statistics; Consistency (knowledge bases)","score_opus":0.012783736768222673,"score_gpt":0.27568036138187646,"score_spread":0.26289662461365376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066380414","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006125862,0.000026950174,0.988108,0.004746877,0.00030812793,0.00035713005,0.00021187068,0.00005125836,0.00006394674],"genre_scores_gemma":[0.7446383,0.0000032940231,0.25473902,0.00034219882,0.00017505258,0.000009421159,0.00007704686,0.000006634616,0.000008983687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877703,0.00018140419,0.00020709627,0.00029316352,0.00026120734,0.00028006727],"domain_scores_gemma":[0.9989659,0.00023083972,0.00010256337,0.00041467295,0.00019729626,0.00008873618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009918873,0.00016922192,0.00012483077,0.000013138648,0.0011974826,0.0004688871,0.00059966603,0.000048290385,0.0000014442173],"category_scores_gemma":[0.000034195746,0.000077901146,0.000025076011,0.00024067654,0.00007591419,0.00020357121,0.00012219867,0.00043996423,0.0000018836292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012584061,0.000018389126,0.0000045876754,0.0000068863637,0.000017779554,0.0000020632701,0.005761362,0.008427161,0.0001875969,0.7047727,0.00022281885,0.28056607],"study_design_scores_gemma":[0.00016688583,0.000073501535,0.00027670042,0.000014129901,0.000017959846,0.000029450313,0.000086255954,0.9473038,0.00029119747,0.04999432,0.0016109938,0.00013480557],"about_ca_topic_score_codex":0.00018200117,"about_ca_topic_score_gemma":0.00012169632,"teacher_disagreement_score":0.9388766,"about_ca_system_score_codex":0.000017757611,"about_ca_system_score_gemma":0.00004081225,"threshold_uncertainty_score":0.9210189},"labels":[],"label_agreement":null},{"id":"W2068057588","doi":"10.1016/j.jmva.2014.11.009","title":"A sufficient condition for the convergence of the mean shift algorithm with Gaussian kernel","year":2014,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics; Mean-shift; Algorithm; Kernel (algebra); Convergence (economics); Probability density function; Gaussian; Cluster analysis; Kernel density estimation; Gaussian function; Variable kernel density estimation; Kernel method; Applied mathematics; Segmentation; Artificial intelligence; Combinatorics; Statistics; Computer science; Support vector machine","score_opus":0.011481741174644263,"score_gpt":0.27170689462041747,"score_spread":0.2602251534457732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068057588","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005559838,0.00006565501,0.99234384,0.0016389933,0.00020284163,0.00012432634,0.0000057524035,0.000005054486,0.000053673277],"genre_scores_gemma":[0.7040495,0.0000082361485,0.29570252,0.00012676558,0.00006428304,0.000002901049,3.8845675e-7,0.000004388747,0.000040952895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984348,0.00031603294,0.0004655903,0.00017557056,0.00043589302,0.0001721348],"domain_scores_gemma":[0.9977026,0.00047241556,0.00089941063,0.0005055173,0.00034713425,0.00007294047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020200661,0.00012233832,0.00036256554,0.00015643048,0.0001667414,0.000066847184,0.0009734553,0.000045977118,0.000010434011],"category_scores_gemma":[0.000093293515,0.00005324785,0.0004629148,0.000888156,0.0000840326,0.00018538436,0.00007302785,0.00016486511,5.1576865e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037151863,0.0013256605,0.005634913,0.00011921961,0.014981692,0.000022828901,0.030150287,0.09305265,0.008064737,0.5026222,0.0008071671,0.3428471],"study_design_scores_gemma":[0.00069446873,0.00019059257,0.024533998,0.000033982607,0.0012820887,0.000013270782,0.00006579479,0.9643967,0.0024638982,0.0057989955,0.0004169439,0.00010924785],"about_ca_topic_score_codex":0.00009331996,"about_ca_topic_score_gemma":0.00004125835,"teacher_disagreement_score":0.8713441,"about_ca_system_score_codex":0.000025379799,"about_ca_system_score_gemma":0.00007866506,"threshold_uncertainty_score":0.21713844},"labels":[],"label_agreement":null},{"id":"W2068406209","doi":"10.1016/j.patcog.2008.06.022","title":"Discrete data clustering using finite mixture models","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Automatic summarization; Computer science; Robustness (evolution); Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Dirichlet distribution; Algorithm; Data mining; Mathematics","score_opus":0.18375514752137545,"score_gpt":0.31410763867963526,"score_spread":0.1303524911582598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068406209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008617554,0.000112798836,0.989397,0.00020611718,0.00038942776,0.00014835951,0.00006197329,0.00014052683,0.0009262408],"genre_scores_gemma":[0.37783098,0.00008531745,0.62101823,0.0006917504,0.00020707282,0.0000064624433,0.000104512765,0.00001853678,0.000037123835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848586,0.00014887308,0.00024258529,0.00059447327,0.00022914511,0.0002990329],"domain_scores_gemma":[0.99869514,0.00007948957,0.000107313754,0.0009531822,0.00006432794,0.00010057231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003161053,0.00017606675,0.00017955217,0.00009723824,0.00020784786,0.0000989122,0.000864499,0.00009643199,0.000018185074],"category_scores_gemma":[0.000025742427,0.00016564895,0.000053691518,0.00019255304,0.000031246695,0.0015873102,0.00061574765,0.00019412453,0.00003407901],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000077007335,0.000042176856,0.00018474058,0.00004696879,0.000027678238,0.00010808229,0.0009952293,0.0006686983,0.0008986818,0.000068828944,0.0003444266,0.99660677],"study_design_scores_gemma":[0.00023107839,0.00001895444,0.000111430374,0.00008086656,0.000013319325,0.00018635468,0.0000040085015,0.98072535,0.00055661163,0.017700547,0.0001173282,0.0002541456],"about_ca_topic_score_codex":0.00007376144,"about_ca_topic_score_gemma":0.000014516303,"teacher_disagreement_score":0.9963526,"about_ca_system_score_codex":0.000024610667,"about_ca_system_score_gemma":0.0000351683,"threshold_uncertainty_score":0.6754968},"labels":[],"label_agreement":null},{"id":"W2069386154","doi":"10.1002/env.922","title":"Model clustering and its application to water quality monitoring","year":2008,"lang":"en","type":"article","venue":"Environmetrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Pairwise comparison; Cluster analysis; Similarity (geometry); Data mining; Set (abstract data type); Computer science; Partition (number theory); Artificial intelligence; Mathematics; Pattern recognition (psychology); Machine learning; Image (mathematics)","score_opus":0.06763186470929634,"score_gpt":0.29871337482570787,"score_spread":0.23108151011641154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069386154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1331841,0.00016340357,0.8659357,0.00018781437,0.0000678,0.00011297001,7.074244e-7,0.000047417398,0.0003001233],"genre_scores_gemma":[0.58212185,0.000078868696,0.41743943,0.000071546914,0.000038569786,0.000011776627,2.9302674e-7,0.0000056515287,0.0002320003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990588,0.000043747277,0.00015674472,0.0003390149,0.00019317494,0.00020851001],"domain_scores_gemma":[0.99944144,0.00004221318,0.000026544752,0.00034855108,0.000010702825,0.00013054236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040127712,0.00009738511,0.000116860545,0.00014441524,0.00013849873,0.000026335849,0.00028840342,0.000058866313,8.6979867e-7],"category_scores_gemma":[0.000031994834,0.00008133301,0.000023852452,0.0002550617,0.000011888595,0.00023358666,0.00034525007,0.00009421791,0.00003724261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012731916,0.00013825047,0.0051257894,0.00006104649,0.000019137857,0.000016842689,0.007386482,0.029383833,0.27390206,0.026265293,0.000089577814,0.657599],"study_design_scores_gemma":[0.00021266151,0.000034621087,0.014932022,0.0000050368185,0.0000043551177,0.000022379772,0.000004409387,0.90313226,0.07503514,0.004569514,0.0016847675,0.0003628155],"about_ca_topic_score_codex":0.0000058760206,"about_ca_topic_score_gemma":2.1340426e-7,"teacher_disagreement_score":0.8737484,"about_ca_system_score_codex":0.000035319707,"about_ca_system_score_gemma":0.000004997606,"threshold_uncertainty_score":0.3316664},"labels":[],"label_agreement":null},{"id":"W2069467329","doi":"10.1002/cjs.5550350406","title":"A family of power‐divergence diagnostics for goodness‐of‐fit","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Goodness of fit; Dirichlet process; Divergence (linguistics); Context (archaeology); Dirichlet distribution; Multinomial distribution; Mathematics; Bayesian probability; Nonparametric statistics; Econometrics; Applied mathematics; Calibration; Statistics; Computer science; Geography; Mathematical analysis","score_opus":0.036241690699789324,"score_gpt":0.2804894193102464,"score_spread":0.24424772861045707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069467329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031707664,0.0008383195,0.99413973,0.000078361416,0.0009531756,0.00009200837,0.00038598586,0.0000021107826,0.00033955526],"genre_scores_gemma":[0.28345138,0.000074016774,0.7162772,0.00011634485,0.000043109765,3.6665665e-7,8.4674343e-7,0.000007097288,0.000029644258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874014,0.000033772754,0.00060959737,0.000107338674,0.00020719647,0.0003019437],"domain_scores_gemma":[0.9972273,0.0007309393,0.0004979975,0.00021567535,0.0008296329,0.0004984591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009702465,0.00010314532,0.00028912083,0.00024534983,0.000057322162,0.000023955341,0.0006459016,0.000065960056,0.000010566415],"category_scores_gemma":[0.0008070227,0.00009772534,0.000075939264,0.00024781053,0.00011188059,0.00012005777,0.00002017929,0.00012876358,6.9950147e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019531984,0.000038456266,0.0033818295,0.00010048793,0.00006314152,0.00030061282,0.0016043079,0.000063159205,0.00061294425,0.84370685,0.018264089,0.13184462],"study_design_scores_gemma":[0.0031692889,0.0041195867,0.13017587,0.0008766669,0.00032912602,0.00048050826,0.00068154174,0.010048853,0.015318292,0.7843163,0.049198933,0.0012850127],"about_ca_topic_score_codex":0.0006172123,"about_ca_topic_score_gemma":0.0015804287,"teacher_disagreement_score":0.2802806,"about_ca_system_score_codex":0.00005351921,"about_ca_system_score_gemma":0.0012149455,"threshold_uncertainty_score":0.39851236},"labels":[],"label_agreement":null},{"id":"W2069469628","doi":"10.1109/tgrs.2013.2281854","title":"Synthetic Aperture Radar Image Segmentation by Modified Student's t-Mixture Model","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Sandia National Laboratories; Priority Academic Program Development of Jiangsu Higher Education Institutions; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canada Research Chairs","keywords":"Pixel; Mixture model; Computer science; Synthetic aperture radar; Outlier; Artificial intelligence; Image segmentation; Expectation–maximization algorithm; Pattern recognition (psychology); Noise (video); Segmentation; Spatial analysis; Computer vision; Image (mathematics); Mathematics; Statistics; Maximum likelihood","score_opus":0.01053707082113745,"score_gpt":0.2564184147047885,"score_spread":0.24588134388365104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069469628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003167553,0.000041692325,0.99409115,0.0012977968,0.00037683043,0.00018655366,0.0000050000026,0.00013326875,0.0007001505],"genre_scores_gemma":[0.22691025,0.000073320836,0.77117217,0.0011815625,0.00002034018,2.6704421e-7,7.1409653e-7,0.000012445046,0.0006289313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982315,0.00015835845,0.00021685327,0.00068268034,0.00035254876,0.00035806483],"domain_scores_gemma":[0.9990755,0.00014353212,0.000075927244,0.00047350326,0.000063521125,0.0001680512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050783786,0.00022967231,0.00020802821,0.00013924357,0.0005967021,0.00029800067,0.00032522023,0.00012255262,0.0000011440873],"category_scores_gemma":[0.000010270313,0.00018928427,0.00007827278,0.00034994358,0.00015671772,0.0005518636,0.0000063187254,0.00029053685,0.0000056064355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058677433,0.000032223186,2.0652676e-8,0.000010049435,0.000006355015,0.0000024014585,0.00074540614,0.00060340797,0.11140562,0.00035727306,0.000059099835,0.8867723],"study_design_scores_gemma":[0.00026755256,0.00006580182,0.0000033789172,0.000048228696,0.000017870703,0.00005405937,0.000033029995,0.9695613,0.024709648,0.0048612216,0.00013709876,0.00024084748],"about_ca_topic_score_codex":0.000047936363,"about_ca_topic_score_gemma":0.000009239005,"teacher_disagreement_score":0.96895784,"about_ca_system_score_codex":0.00003774612,"about_ca_system_score_gemma":0.000040198513,"threshold_uncertainty_score":0.7718789},"labels":[],"label_agreement":null},{"id":"W2070831629","doi":"10.1081/sac-100107783","title":"ROBUSTNESS OF PROCEDURES FOR THE BEHRENS-FISHER PROBLEMS: EXTENSION TO BIVARIATE NORMAL MIXTURES","year":2001,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Extension (predicate logic); Robustness (evolution); Bivariate analysis; Mathematics; Statistics; Econometrics; Computer science; Chemistry; Programming language","score_opus":0.12027347678153441,"score_gpt":0.4138780509261474,"score_spread":0.29360457414461294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070831629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013481755,0.0003301897,0.9960433,0.0012817783,0.00010471165,0.0007396633,0.000016441945,0.000033957764,0.00010173175],"genre_scores_gemma":[0.48854032,0.000072779396,0.5111627,0.000114524104,0.000012120743,0.000049750903,0.000021603331,0.000005911435,0.000020316646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989267,0.00016472679,0.00040620024,0.0002175961,0.0001447407,0.00014003638],"domain_scores_gemma":[0.9971795,0.0015950239,0.00016875764,0.00061129313,0.00040036553,0.00004506168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056150503,0.00011126177,0.00015162828,0.00015649147,0.00025186577,0.00010139991,0.0005330182,0.000054361335,0.000001671338],"category_scores_gemma":[0.00028968413,0.000092418224,0.000023230567,0.0004507118,0.000070473514,0.00020526742,0.00021859093,0.00009871843,4.8310335e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016896547,0.00006105836,0.00013186412,0.000029983035,0.0000073531974,1.4291408e-7,0.0009733185,0.7565175,0.000050635717,0.075427875,0.00016379259,0.16661957],"study_design_scores_gemma":[0.00036382955,0.000054910146,0.0065539894,0.00004701959,0.000013875229,0.0000030383892,0.000026145319,0.9506772,0.000012905734,0.04159272,0.0005478448,0.00010649644],"about_ca_topic_score_codex":0.000029552008,"about_ca_topic_score_gemma":0.00010461754,"teacher_disagreement_score":0.48719212,"about_ca_system_score_codex":0.000020702624,"about_ca_system_score_gemma":0.000054576285,"threshold_uncertainty_score":0.37687057},"labels":[],"label_agreement":null},{"id":"W2070920564","doi":"10.1006/jmva.2001.2027","title":"Principal Component Analysis from the Multivariate Familial Correlation Matrix","year":2002,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Principal component analysis; Covariance matrix; Eigenvalues and eigenvectors; Estimator; Statistics; Multivariate statistics; Monte Carlo method; Applied mathematics; Matrix (chemical analysis); Multivariate normal distribution","score_opus":0.02680036171768103,"score_gpt":0.2925175668576886,"score_spread":0.2657172051400076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070920564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040688552,0.0005037631,0.95660675,0.0014202109,0.00042324644,0.00010905153,0.000017412118,0.000032778156,0.00019822031],"genre_scores_gemma":[0.6845947,0.00007759648,0.314658,0.00017486847,0.0002491902,0.0000020227342,0.0000072272746,0.000009321562,0.00022705742],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99600077,0.001044903,0.0012390912,0.00045423835,0.0009005563,0.00036041756],"domain_scores_gemma":[0.99608314,0.0009277124,0.0013951315,0.0009298788,0.0004383265,0.00022578485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018428218,0.00030016192,0.0009868786,0.0008716634,0.00028389812,0.00030037665,0.0015051167,0.00016465664,0.00021784556],"category_scores_gemma":[0.0002294945,0.00019002544,0.001635209,0.0041295406,0.000055165106,0.0006423998,0.00023505287,0.00055692566,0.000029553454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037287534,0.0023377747,0.080557294,0.000018138413,0.11854673,0.00052708434,0.028246846,0.55922323,0.01625597,0.041073848,0.0018352347,0.15100498],"study_design_scores_gemma":[0.00079076336,0.000043351112,0.13305637,0.0000092843275,0.00794324,0.0000066333123,0.000029041388,0.85570943,0.00008247215,0.0014710925,0.00065228547,0.00020600333],"about_ca_topic_score_codex":0.0012627335,"about_ca_topic_score_gemma":0.0001118708,"teacher_disagreement_score":0.6439062,"about_ca_system_score_codex":0.00011826662,"about_ca_system_score_gemma":0.000037364527,"threshold_uncertainty_score":0.7749013},"labels":[],"label_agreement":null},{"id":"W2070925289","doi":"10.3934/amc.2014.8.119","title":"Nearest-neighbor entropy estimators with weak metrics","year":2014,"lang":"en","type":"preprint","venue":"Advances in Mathematics of Communications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Estimator; Mathematics; Entropy estimation; Entropy (arrow of time); Upper and lower bounds; Minimax estimator; Ergodic theory; k-nearest neighbors algorithm; Bounded function; Applied mathematics; Maximum entropy probability distribution; Minimum-variance unbiased estimator; Nonparametric statistics; Statistics; Principle of maximum entropy; Computer science; Artificial intelligence; Mathematical analysis; Physics","score_opus":0.0255040991783082,"score_gpt":0.3320897558339155,"score_spread":0.3065856566556073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070925289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016430841,0.0064623286,0.97640353,0.00066965155,0.00012510298,0.00043395584,0.0000102974445,0.00008748541,0.015643306],"genre_scores_gemma":[0.078484856,0.004863725,0.91639864,0.000034370783,0.00001354492,0.000118926524,0.00001092231,0.000025876983,0.00004914572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796593,0.00027097642,0.000752282,0.00036328478,0.0003947366,0.00025277567],"domain_scores_gemma":[0.99122214,0.0016868364,0.00082248804,0.005936141,0.00025031983,0.000082084],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009331371,0.0002931856,0.0006765083,0.00039003446,0.00009606483,0.000099301455,0.005806468,0.00017203132,0.000003537178],"category_scores_gemma":[0.0004277089,0.0002466554,0.00010799581,0.0006832788,0.00029073883,0.00035781105,0.002797359,0.000725485,0.000005751851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018229559,0.00024764307,0.0001539213,0.0004105779,0.000025144425,6.961291e-7,0.0007326956,0.0021919478,0.000009546513,0.9760787,0.00003082488,0.020116488],"study_design_scores_gemma":[0.0001634229,0.00003766573,0.00003719768,0.00057794753,0.00002792633,0.0000050370427,0.000023055152,0.3263482,0.00013189664,0.66959,0.0028265505,0.00023109914],"about_ca_topic_score_codex":0.000012005228,"about_ca_topic_score_gemma":0.000039841332,"teacher_disagreement_score":0.32415622,"about_ca_system_score_codex":0.00005697088,"about_ca_system_score_gemma":0.00017289349,"threshold_uncertainty_score":0.99999857},"labels":[],"label_agreement":null},{"id":"W2071558725","doi":"10.1214/12-ba719","title":"Simulation-based Regularized Logistic Regression","year":2012,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"Engineering and Physical Sciences Research Council","keywords":"Mathematics; Logistic regression; Estimator; Markov chain Monte Carlo; Regularization (linguistics); Maximum a posteriori estimation; Computer science; Statistics; Maximum likelihood; Artificial intelligence; Monte Carlo method","score_opus":0.03629584693375288,"score_gpt":0.3235307993996509,"score_spread":0.28723495246589803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071558725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000261133,0.00018058969,0.99726796,0.00043293438,0.00014249752,0.000097640914,0.0000021831058,0.00017412998,0.001440946],"genre_scores_gemma":[0.54700994,0.0000010565102,0.45232266,0.00028304136,0.00006506569,0.0000055680866,0.000008034243,0.000006685078,0.00029795145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810314,0.00035448791,0.00032311937,0.0004055223,0.00036743938,0.00044627584],"domain_scores_gemma":[0.997807,0.0005488578,0.00017461478,0.0010988975,0.00009128287,0.00027933603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000863629,0.00020600023,0.00039665352,0.0004954059,0.00016835719,0.000118513824,0.00058203307,0.00012638328,0.00013856923],"category_scores_gemma":[0.00027060293,0.00016177093,0.0003889855,0.0021710685,0.000044394154,0.00038930215,0.0000846284,0.00012751145,0.00003997318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007544621,0.00090574904,0.038536694,0.00008020579,0.0019224989,0.0000648953,0.0013919779,0.2342683,0.0017967419,0.41988897,0.0010419962,0.30002654],"study_design_scores_gemma":[0.00022395547,0.000012461721,0.002878271,0.000008267373,0.00039902984,6.2677395e-7,0.0000021191054,0.98829895,0.00031996568,0.0071558272,0.0004753205,0.00022523222],"about_ca_topic_score_codex":0.000016963068,"about_ca_topic_score_gemma":0.0000033918275,"teacher_disagreement_score":0.75403064,"about_ca_system_score_codex":0.000050955547,"about_ca_system_score_gemma":0.0000489229,"threshold_uncertainty_score":0.65968275},"labels":[],"label_agreement":null},{"id":"W2072863153","doi":"10.1002/sim.2108","title":"Application of hidden Markov models to multiple sclerosis lesion count data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Actua; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Markov chain; Markov model; Multiple sclerosis; Perspective (graphical); Count data; Clinical trial; Artificial intelligence; Machine learning; Hidden Markov model; Data mining; Medicine; Statistics; Mathematics; Pathology","score_opus":0.10554507787332336,"score_gpt":0.3455094780797473,"score_spread":0.23996440020642396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072863153","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024975868,0.00020087154,0.99671113,0.00168972,0.000114557595,0.00028411797,0.00014256421,0.000024582794,0.000582692],"genre_scores_gemma":[0.23923203,0.00010374556,0.7599942,0.00047881212,0.00007803779,0.00001282195,0.000052789706,0.00000751415,0.00004004745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985204,0.00007945218,0.00040622495,0.00041804535,0.00038711756,0.00018876068],"domain_scores_gemma":[0.9981852,0.00033193847,0.00010937668,0.0011582045,0.00011160078,0.0001036813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011711325,0.000112936876,0.00025755464,0.00014017698,0.00003290945,0.0000107710075,0.0010780597,0.000049917577,0.000009975435],"category_scores_gemma":[0.0002209106,0.00009546077,0.000007978349,0.00033882758,0.000060048213,0.00020712159,0.000350991,0.00011538669,0.00000700995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011061543,0.00004298527,0.00007729342,0.000025220836,0.0000038872636,0.0000015595216,0.0008104415,0.00022745662,0.0024008155,0.13349232,0.009375954,0.853531],"study_design_scores_gemma":[0.0005128515,0.00006812921,0.0017300224,0.00010167681,0.000008902905,0.0000016723345,0.00001684528,0.9361797,0.00021605015,0.05931197,0.0017462615,0.00010591461],"about_ca_topic_score_codex":0.00034855728,"about_ca_topic_score_gemma":0.00026452617,"teacher_disagreement_score":0.93595225,"about_ca_system_score_codex":0.00005151103,"about_ca_system_score_gemma":0.000043665157,"threshold_uncertainty_score":0.38927773},"labels":[],"label_agreement":null},{"id":"W2073724362","doi":"10.1177/0141076815578597","title":"The impact of E.F. Lindquist's text on cluster randomisation","year":2015,"lang":"en","type":"article","venue":"Journal of the Royal Society of Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Cluster (spacecraft); Computer science; Text mining; World Wide Web; Information retrieval; Data science; Natural language processing; Operating system","score_opus":0.02657730332539639,"score_gpt":0.3148389513184571,"score_spread":0.28826164799306075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073724362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019999368,0.0010880184,0.95083,0.025773559,0.0007877965,0.00013300606,5.714507e-7,0.0000036709812,0.0013840287],"genre_scores_gemma":[0.9544917,0.00010885792,0.043044712,0.0008174503,0.00080576935,7.093469e-7,1.0574677e-7,0.0000076659335,0.00072305964],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836385,0.00029892102,0.0004983582,0.00007263803,0.0006404862,0.00012572689],"domain_scores_gemma":[0.9978452,0.0005136518,0.00084355567,0.00033018843,0.00036372282,0.0001037328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049444735,0.000096106996,0.000334107,0.000019699455,0.00007451365,0.000012324876,0.00082056964,0.000064166175,0.0000053588747],"category_scores_gemma":[0.0004770076,0.000035670924,0.0004887855,0.00014768315,0.00022462248,0.00006700652,0.00008536883,0.00028301656,4.939569e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015572641,0.00025111652,0.0006515862,0.000053255797,0.0006871753,0.0000022561933,0.021236934,0.010924726,0.0015121595,0.0049901516,0.72445405,0.23367935],"study_design_scores_gemma":[0.06421549,0.00998698,0.021516884,0.0021201617,0.00045033573,0.00020768693,0.001386026,0.6813683,0.0072896373,0.19709545,0.013843669,0.00051938236],"about_ca_topic_score_codex":0.00004635024,"about_ca_topic_score_gemma":5.981285e-7,"teacher_disagreement_score":0.9344923,"about_ca_system_score_codex":0.000076282646,"about_ca_system_score_gemma":0.0001783756,"threshold_uncertainty_score":0.17136657},"labels":[],"label_agreement":null},{"id":"W2073745063","doi":"10.1002/cjs.5550360402","title":"Testing for two states in a hidden Markov model","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hidden Markov model; Likelihood-ratio test; Mathematics; Inference; Marginal likelihood; Test statistic; Marginal distribution; Statistic; Applied mathematics; Statistical hypothesis testing; Markov model; Hidden semi-Markov model; Statistics; Chen; Markov chain; Computer science; Variable-order Markov model; Maximum likelihood; Artificial intelligence; Random variable","score_opus":0.04713047351454562,"score_gpt":0.27587495095429015,"score_spread":0.22874447743974452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073745063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034064683,0.00016237302,0.99548036,0.00027538996,0.00017144103,0.00007940759,0.00011057398,0.000004007086,0.0003099819],"genre_scores_gemma":[0.09253488,0.00000662497,0.90700024,0.00028975564,0.000056864723,0.0000018972387,0.0000014673474,0.000009641147,0.00009862588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990537,0.000043423202,0.0003502516,0.00011617653,0.00011515373,0.0003212565],"domain_scores_gemma":[0.9986243,0.00033805074,0.0001633582,0.0001373908,0.00031834753,0.00041852437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045938452,0.000093261195,0.00019415011,0.00024317572,0.0001100804,0.000055807326,0.00041650928,0.000031562602,0.0000030704905],"category_scores_gemma":[0.00041734907,0.00008907624,0.00003092621,0.00020486629,0.000051462892,0.00018868182,0.000013137746,0.00016277199,7.483682e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016628388,0.000030301393,0.0051974403,0.000057071953,0.00003324877,0.0022975062,0.005162485,0.004977651,0.00021566074,0.17237213,0.037381858,0.77225804],"study_design_scores_gemma":[0.0005436998,0.000116706404,0.0014331947,0.00004558664,0.000006732054,0.0003868269,0.00001235612,0.75417393,0.0000350142,0.24281861,0.00028807798,0.00013927232],"about_ca_topic_score_codex":0.0012262402,"about_ca_topic_score_gemma":0.005517995,"teacher_disagreement_score":0.77211875,"about_ca_system_score_codex":0.000111310546,"about_ca_system_score_gemma":0.002023811,"threshold_uncertainty_score":0.36324236},"labels":[],"label_agreement":null},{"id":"W2074057014","doi":"10.1016/j.camwa.2010.08.008","title":"Generalized Laguerre expansions of multivariate probability densities with moments","year":2010,"lang":"en","type":"article","venue":"Computers & Mathematics with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Laguerre polynomials; Mathematics; Multivariate statistics; Univariate; Probability density function; Applied mathematics; Edgeworth series; Series (stratigraphy); Log-normal distribution; Gaussian; Multivariate normal distribution; Statistical physics; Mathematical analysis; Statistics; Physics; Quantum mechanics","score_opus":0.018500943210932454,"score_gpt":0.26632791158691194,"score_spread":0.24782696837597948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074057014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039927643,0.000010443657,0.95804024,0.0003175434,0.00005550795,0.0009210485,0.0000060008515,0.00014928263,0.00057227403],"genre_scores_gemma":[0.11778986,0.000002069049,0.88169205,0.00006580003,0.000027925935,0.00032551194,0.00000516468,0.000016523962,0.00007508122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99871814,0.000045309058,0.00033248978,0.00040094342,0.0002690171,0.00023407431],"domain_scores_gemma":[0.99785835,0.00018704848,0.00025222718,0.0013083846,0.0002577285,0.0001362884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027465724,0.00020636451,0.0003213376,0.000087708366,0.00016207442,0.0000770418,0.00075235043,0.00006947047,0.0000038851003],"category_scores_gemma":[0.000010381682,0.0001431136,0.000053174983,0.00040206575,0.00018059285,0.00018335928,0.00017553625,0.0001961483,0.0000048425813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061261626,0.0003953381,0.00006420581,0.0001111967,0.000053311367,0.0000015574296,0.002045764,0.00019927614,0.0053613484,0.97906953,0.000070117676,0.012622222],"study_design_scores_gemma":[0.0019941712,0.00023587442,0.0009889572,0.00020938105,0.00011821111,0.00015460588,0.000077444856,0.38292563,0.009780829,0.60099816,0.0017108608,0.0008058629],"about_ca_topic_score_codex":0.000013916284,"about_ca_topic_score_gemma":0.00002294044,"teacher_disagreement_score":0.38272634,"about_ca_system_score_codex":0.000015050742,"about_ca_system_score_gemma":0.000110572495,"threshold_uncertainty_score":0.58360034},"labels":[],"label_agreement":null},{"id":"W207560109","doi":"10.1007/978-3-642-21881-1_42","title":"Learning Inverted Dirichlet Mixtures for Positive Data Clustering","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Dirichlet distribution; Expectation–maximization algorithm; Maximization; Model selection; Selection (genetic algorithm); Algorithm; Minimum description length; Latent Dirichlet allocation; Artificial intelligence; Data mining; Pattern recognition (psychology); Maximum likelihood; Mathematical optimization; Topic model; Mathematics; Statistics","score_opus":0.048641573033388764,"score_gpt":0.288367066147882,"score_spread":0.23972549311449323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W207560109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000030543345,0.0006318737,0.9920489,0.00054693304,0.0016663526,0.00066269236,0.000029331426,0.00020775791,0.0042031077],"genre_scores_gemma":[0.0105957035,0.000067317655,0.9861576,0.0018317626,0.0005509696,0.000014529308,0.000046387107,0.00006035864,0.00067538366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99525833,0.00009992693,0.000556309,0.0024784373,0.0006492542,0.0009577193],"domain_scores_gemma":[0.99581873,0.000768151,0.00037637877,0.002509653,0.00029805914,0.0002290183],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002003851,0.00066467095,0.0007108958,0.0006960565,0.00046090275,0.0005722473,0.006991436,0.0004567101,0.00001230368],"category_scores_gemma":[0.00026115202,0.00059449824,0.00014579165,0.0004477001,0.00060699676,0.0010161598,0.005015346,0.0010959146,0.000013051636],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014690432,0.000018986288,0.000008447308,0.00005147229,0.000026328073,0.000042672797,0.0011857501,0.0013969104,0.00017654101,0.02594396,0.000078174,0.97105604],"study_design_scores_gemma":[0.00026421048,0.00022083159,0.000025527816,0.00033278283,0.000018708015,0.000057915015,7.465492e-8,0.6684594,0.00086653326,0.32714826,0.0019363621,0.0006693626],"about_ca_topic_score_codex":0.00004604113,"about_ca_topic_score_gemma":0.00008035868,"teacher_disagreement_score":0.9703867,"about_ca_system_score_codex":0.00015919755,"about_ca_system_score_gemma":0.0004440512,"threshold_uncertainty_score":0.99965066},"labels":[],"label_agreement":null},{"id":"W2075711194","doi":"10.1007/s00357-013-9139-2","title":"Variable Selection for Clustering and Classification","year":2013,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Feature selection; Variable (mathematics); Computer science; Selection (genetic algorithm); Data mining; Artificial intelligence; Clustering high-dimensional data; Machine learning; Pattern recognition (psychology); Subspace topology; Mathematics","score_opus":0.041396182228672196,"score_gpt":0.2910300057636183,"score_spread":0.24963382353494612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075711194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020145224,0.00006972812,0.99424326,0.0023559737,0.0002580519,0.00019500282,2.720282e-7,0.000019069748,0.0008441006],"genre_scores_gemma":[0.24790847,0.000021542854,0.75164086,0.00009746139,0.00013481545,0.00001813907,5.2613694e-7,0.0000052043742,0.00017298477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992038,0.000069475,0.00034381254,0.00013896756,0.00013094724,0.000112984555],"domain_scores_gemma":[0.99883235,0.0001118957,0.00040765127,0.0001368922,0.00043881926,0.000072418145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000704496,0.0000701527,0.0001256638,0.0001235963,0.00008875782,0.00018865659,0.00020144535,0.00007039843,0.0000053935632],"category_scores_gemma":[0.000096123826,0.000058737332,0.00003867103,0.00018009804,0.000015326346,0.0010104377,0.000018681038,0.000101870166,0.0000032745206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010358867,0.000037916758,0.00024814988,0.000029570974,0.000015699858,6.8388964e-8,0.00017617119,0.000020623653,0.18399602,0.43486783,0.002414632,0.37818295],"study_design_scores_gemma":[0.00036191105,0.00014172698,0.021294802,0.00002768415,0.000015990376,0.00007206561,0.000025033487,0.80933774,0.0013749086,0.16157229,0.005679195,0.000096647134],"about_ca_topic_score_codex":0.00000340306,"about_ca_topic_score_gemma":8.3700263e-7,"teacher_disagreement_score":0.8093171,"about_ca_system_score_codex":0.00005022326,"about_ca_system_score_gemma":0.00006278161,"threshold_uncertainty_score":0.23952389},"labels":[],"label_agreement":null},{"id":"W2076102233","doi":"10.1117/12.641257","title":"Iterative Markovian estimation of mass functions in Dempster Shafer evidence theory: application to multisensor image segmentation","year":2006,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"","keywords":"Dempster–Shafer theory; Artificial intelligence; Computer science; Context (archaeology); Bayesian probability; Noise (video); Segmentation; Pattern recognition (psychology); Inference; Sensor fusion; Markov process; Image segmentation; Bayesian inference; Computer vision; Image (mathematics); Mathematics; Statistics","score_opus":0.010750950473168881,"score_gpt":0.25800892011342674,"score_spread":0.24725796964025787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076102233","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5440068,0.000022249507,0.45362037,0.0013019835,0.00006673832,0.0005180942,0.000013242646,0.000030808755,0.00041967208],"genre_scores_gemma":[0.32541656,0.0000067304,0.67411584,0.000063273255,0.00008008212,0.00019790903,0.000004645793,0.00001743417,0.00009753253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817115,1.1018779e-7,0.00067152973,0.00041454064,0.00048834353,0.0002543369],"domain_scores_gemma":[0.99815196,0.00024997626,0.00035171883,0.00008481331,0.00109221,0.000069313144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010059639,0.00022515914,0.000298007,0.00017534388,0.000055234483,0.00011950326,0.0007548077,0.0001194347,0.0000041249505],"category_scores_gemma":[0.00037117905,0.00019461551,0.0002580689,0.0005393582,0.00009672273,0.0012008044,0.00012368626,0.00017426694,0.0000015870752],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005181167,0.00006331335,0.00020485207,0.00015532246,0.00004231423,3.6444202e-8,0.00029652135,0.00090749806,0.55451685,0.44053543,0.00032717575,0.0028989143],"study_design_scores_gemma":[0.000859402,0.00025211676,0.0043867487,0.00051890605,0.00007666746,0.000006875864,0.00032828507,0.60804844,0.34371677,0.041329283,0.00010921249,0.00036729345],"about_ca_topic_score_codex":0.000019728583,"about_ca_topic_score_gemma":4.619949e-7,"teacher_disagreement_score":0.60714096,"about_ca_system_score_codex":0.00016263213,"about_ca_system_score_gemma":0.000025841884,"threshold_uncertainty_score":0.79361904},"labels":[],"label_agreement":null},{"id":"W2076179404","doi":"10.1111/j.1751-5823.2001.tb00468.x","title":"The History of the Dirichlet and Liouville Distributions","year":2001,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Dirichlet distribution; Mathematics; Scrutiny; Concentration parameter; Latent Dirichlet allocation; Generalized Dirichlet distribution; Dirichlet integral; Statistics; Probability distribution; Applied mathematics; Subject (documents); Statistical physics; Econometrics; Dirichlet series; Mathematical analysis; Physics; Computer science; Philosophy; Topic model; Information retrieval","score_opus":0.020368712982852404,"score_gpt":0.30296831148524866,"score_spread":0.28259959850239624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076179404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051843886,0.038733695,0.94063663,0.011139,0.00058475224,0.00008947435,0.000023788423,0.0000074399463,0.0087800585],"genre_scores_gemma":[0.0541279,0.3348366,0.5807421,0.010872525,0.0002692206,0.00013799277,0.00002548499,0.000021518625,0.018966643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992936,0.000107684755,0.00019152153,0.000116501025,0.00020797699,0.00008270443],"domain_scores_gemma":[0.99909127,0.00048589782,0.00007155428,0.00022312545,0.00008886334,0.000039278973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035991645,0.00005191773,0.00009214337,0.000007069589,0.000057426325,0.000019688714,0.0005393132,0.000013085824,0.000053606956],"category_scores_gemma":[0.0007203867,0.000026158245,0.000038572398,0.000075759395,0.00013834995,0.000053495078,0.00016938073,0.0000791647,0.000005515577],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.515524e-7,0.000008082792,0.000032572825,0.000014749175,0.0000057164852,0.0000012209476,0.0000067043784,3.2687435e-8,0.0000040235395,0.7491501,0.03382643,0.21694979],"study_design_scores_gemma":[0.000037458205,0.0000070061797,0.0023131368,0.0001572908,0.000008617885,0.000023146604,2.3639443e-7,0.0015236742,0.0000021531855,0.09104332,0.90484846,0.00003547029],"about_ca_topic_score_codex":0.000014071481,"about_ca_topic_score_gemma":0.0000054036186,"teacher_disagreement_score":0.87102205,"about_ca_system_score_codex":0.00007031289,"about_ca_system_score_gemma":0.00005632124,"threshold_uncertainty_score":0.10667022},"labels":[],"label_agreement":null},{"id":"W2078912995","doi":"10.1016/j.jmva.2013.05.008","title":"Minimum distance estimation in a finite mixture regression model","year":2013,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Hellinger distance; Estimator; Asymptotic distribution; Applied mathematics; Consistency (knowledge bases); Regression analysis; Statistics; Discrete mathematics","score_opus":0.015296478272484244,"score_gpt":0.2928723231808457,"score_spread":0.27757584490836146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078912995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012991123,0.00019947806,0.98515266,0.0012956844,0.00008120968,0.00007654294,0.000001118432,0.000011611553,0.00019054774],"genre_scores_gemma":[0.5000067,0.000024316243,0.49969834,0.00009706157,0.000017809349,0.0000024735916,7.710338e-7,0.0000039079932,0.00014863929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983017,0.00019951923,0.00067534816,0.00023547049,0.00037103,0.00021696488],"domain_scores_gemma":[0.9983484,0.00020434364,0.0006457848,0.0003874618,0.00028442414,0.00012954701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084416626,0.0001601003,0.00048642184,0.0006730331,0.000054350385,0.00014911398,0.000608503,0.00011045505,0.000018141784],"category_scores_gemma":[0.0002214493,0.0001093472,0.0003171561,0.0014321965,0.00001807499,0.0011108491,0.0000796197,0.0002991324,0.0000057978527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006956978,0.0004484091,0.0019927786,0.000036216345,0.00087031594,0.000104357,0.004992787,0.75600624,0.01238091,0.0144310165,0.0010120011,0.2076554],"study_design_scores_gemma":[0.00041915927,0.000026316087,0.0033238293,0.000060907012,0.0001399773,0.000005061074,0.00000869784,0.9594053,0.0002809801,0.036179837,0.000027866514,0.00012205816],"about_ca_topic_score_codex":0.000064312684,"about_ca_topic_score_gemma":0.000016822516,"teacher_disagreement_score":0.48701558,"about_ca_system_score_codex":0.00006473761,"about_ca_system_score_gemma":0.00006736028,"threshold_uncertainty_score":0.44590494},"labels":[],"label_agreement":null},{"id":"W2079361683","doi":"10.1007/s00184-006-0027-1","title":"Bayesian Analysis in the L 1-Norm of the Mixing Proportion Using Discriminant Analysis","year":2006,"lang":"en","type":"article","venue":"Metrika","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Mathematics; Linear discriminant analysis; Mixing (physics); Bayesian probability; Statistics; Discriminant; Posterior probability; Beta distribution; Norm (philosophy); Applied mathematics; Pattern recognition (psychology); Artificial intelligence; Computer science","score_opus":0.02036564289871512,"score_gpt":0.27764735813779534,"score_spread":0.2572817152390802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079361683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09361949,0.0002399516,0.9050117,0.0003329616,0.00006023619,0.00013683041,0.0000017253082,0.000011132332,0.0005859431],"genre_scores_gemma":[0.81839436,0.0000032242328,0.18146081,0.000056946647,0.000026164375,0.000004069936,0.0000017080966,0.0000033678375,0.000049350987],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981491,0.00042385602,0.00042909928,0.00030734882,0.00046115904,0.00022945547],"domain_scores_gemma":[0.9986832,0.000103767896,0.0002629911,0.0008673015,0.000061114435,0.00002162904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018710849,0.00012016437,0.0003307596,0.00090853986,0.00011930614,0.00008135865,0.0009085684,0.000052631625,0.000005639099],"category_scores_gemma":[0.000059236103,0.00006162653,0.00044090673,0.013923673,0.00004994389,0.00018302504,0.00012321548,0.00013118378,2.9804121e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019016594,0.00083844893,0.54835236,0.000084203995,0.0021493305,0.000052459287,0.0054888637,0.046197783,0.011911414,0.17788652,0.00013864071,0.20688097],"study_design_scores_gemma":[0.000118582364,0.000014859112,0.40517595,0.000010517322,0.0017401912,0.0000034139498,0.000052503394,0.5743581,0.0048702615,0.013455746,0.000054457865,0.00014543666],"about_ca_topic_score_codex":0.002112896,"about_ca_topic_score_gemma":0.0011400627,"teacher_disagreement_score":0.72477484,"about_ca_system_score_codex":0.000049475853,"about_ca_system_score_gemma":0.000038879207,"threshold_uncertainty_score":0.6689863},"labels":[],"label_agreement":null},{"id":"W2079937366","doi":"10.1239/jap/1197908815","title":"A Class of Infinite-Dimensional Diffusion Processes with Connection to Population Genetics","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Sobolev space; Pure mathematics; Entropy (arrow of time); Connection (principal bundle); Class (philosophy); Sobolev inequality; Diffusion process; Measure (data warehouse); Combinatorics; Geometry","score_opus":0.016499827131433577,"score_gpt":0.2607131689329453,"score_spread":0.24421334180151175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079937366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46364412,0.000016275313,0.535779,0.000113365044,0.000056212186,0.00015122264,3.9355595e-7,0.000007713691,0.00023166383],"genre_scores_gemma":[0.5550387,0.0000017099879,0.44483733,0.000077128105,0.00003817543,0.0000012840555,3.142891e-7,0.000003259472,0.0000020930559],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986361,0.000039809307,0.00054859597,0.00019228406,0.00043017627,0.00015303293],"domain_scores_gemma":[0.99839455,0.00022943533,0.00046055572,0.0002376823,0.00055183505,0.00012595503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016564217,0.00010775766,0.00024401711,0.000137793,0.0000530409,0.0000246105,0.00024688832,0.00007312721,0.000003008914],"category_scores_gemma":[0.00011371137,0.000075618635,0.000041843956,0.00052163756,0.000032126412,0.00013988644,0.00007017162,0.00015327072,5.383595e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054672896,0.0023558124,0.038833622,0.0013263526,0.0001587543,0.0000266818,0.005911984,0.02605022,0.10366807,0.21888386,0.00026788245,0.5970495],"study_design_scores_gemma":[0.0027172817,0.0025129637,0.16752017,0.00034812672,0.000088850895,0.00022272585,0.00006680781,0.007587267,0.14032502,0.67691797,0.0010370358,0.00065576227],"about_ca_topic_score_codex":0.000004949719,"about_ca_topic_score_gemma":0.00005237572,"teacher_disagreement_score":0.5963937,"about_ca_system_score_codex":0.00006375013,"about_ca_system_score_gemma":0.00017015757,"threshold_uncertainty_score":0.30836385},"labels":[],"label_agreement":null},{"id":"W2080104526","doi":"10.1109/tnnls.2013.2268461","title":"Online Learning of a Dirichlet Process Mixture of Beta-Liouville Distributions Via Variational Inference","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Mixture model; Cluster analysis; Dirichlet process; Inference; Computer science; Artificial intelligence; Bayesian inference; Dirichlet distribution; Machine learning; Pattern recognition (psychology); Mathematics; Data mining; Bayesian probability; Artificial neural network","score_opus":0.012436914879867188,"score_gpt":0.2551443564361672,"score_spread":0.24270744155629997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080104526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02980118,0.00027669003,0.9689915,0.00018115762,0.00036075411,0.00025659296,0.000010500369,0.00007763105,0.00004397863],"genre_scores_gemma":[0.98953354,0.000043390224,0.010052677,0.000020731,0.00006927607,0.000041685445,0.000010233919,0.000012379351,0.00021609671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982742,0.00044306542,0.00045299585,0.00032883597,0.00025131262,0.0002495986],"domain_scores_gemma":[0.99866396,0.00044969225,0.00030708432,0.00020638571,0.00026582996,0.00010706502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031943724,0.00019018502,0.00036317052,0.00011865324,0.00030091984,0.000085525106,0.0002605089,0.0001443754,0.000015966161],"category_scores_gemma":[0.000019587298,0.00015860442,0.00009781107,0.0005238242,0.00007081009,0.0003290278,0.0000054637367,0.0007725438,0.0000011359404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008003794,0.00012968411,0.0003101775,0.00008125662,0.000046531015,9.728496e-7,0.00040111772,0.95398647,0.00041151833,0.0018268606,0.000018204799,0.042779207],"study_design_scores_gemma":[0.00022523478,0.00022914445,0.0013892145,0.00010777114,0.000025776899,0.000020297415,0.000047005127,0.99742424,0.000117235846,0.0001791749,0.00007956471,0.00015531259],"about_ca_topic_score_codex":0.00018571636,"about_ca_topic_score_gemma":0.000005146798,"teacher_disagreement_score":0.95973235,"about_ca_system_score_codex":0.000014429234,"about_ca_system_score_gemma":0.000027610698,"threshold_uncertainty_score":0.64677006},"labels":[],"label_agreement":null},{"id":"W2080503784","doi":"10.1016/s0895-7177(00)00177-1","title":"Extremal problems on probability distributions","year":2000,"lang":"en","type":"article","venue":"Mathematical and Computer Modelling","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mathematics; Probability distribution; Monotonic function; Probability density function; Applied mathematics; Convolution of probability distributions; Interval (graph theory); Probability measure; Location parameter; Set (abstract data type); Probability mass function; Statistical physics; Mathematical analysis; Statistics; Combinatorics; Computer science; Physics","score_opus":0.04023099274977665,"score_gpt":0.23893921648743194,"score_spread":0.1987082237376553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080503784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013467576,0.00004308786,0.9818709,0.0005500128,0.00003779427,0.00021165598,0.0000022941147,0.00016205138,0.0036546425],"genre_scores_gemma":[0.11100567,0.000013163793,0.88843286,0.00018305,0.00007514863,0.000022373808,0.0000014600023,0.000006999641,0.0002592965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874294,0.00007542493,0.00026556136,0.0004497275,0.00018343111,0.00028290428],"domain_scores_gemma":[0.999247,0.00012429105,0.000028168928,0.00042402183,0.00002950552,0.00014701711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033398927,0.00016803367,0.00022278441,0.000027824744,0.0001640603,0.00018431524,0.0003190071,0.00006674076,0.000053721895],"category_scores_gemma":[0.0000030341323,0.00012525095,0.00007116963,0.0001302051,0.000055484783,0.00018021613,0.00009338958,0.00016389872,0.00005832162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025096429,0.0001461725,0.0000016173929,0.00004280417,0.000005765328,0.0000026802898,0.0002658811,0.006007205,0.0000031118425,0.80648166,0.0000377048,0.18700288],"study_design_scores_gemma":[0.0000707804,0.000041243562,0.0000045057704,0.000040272014,0.000002761519,0.000013860061,1.7897759e-7,0.53259754,0.000020402722,0.46679977,0.0003222651,0.000086438515],"about_ca_topic_score_codex":0.0000018337695,"about_ca_topic_score_gemma":1.3128657e-7,"teacher_disagreement_score":0.5265903,"about_ca_system_score_codex":0.0000142585,"about_ca_system_score_gemma":0.000013042735,"threshold_uncertainty_score":0.5107585},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.026056546071332128,"score_gpt":0.3550975326748263,"score_spread":0.3290409866034942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080972498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075478584,0.0005908089,0.9968912,0.001351629,0.00013055153,0.00011966213,0.000049318598,0.0000137733905,0.000098276156],"genre_scores_gemma":[0.017723335,0.00011490999,0.9812755,0.0006920618,0.00013100162,0.0000044980934,0.0000068138506,0.000009536401,0.0000423416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861145,0.00017554774,0.00050958944,0.00020398265,0.00029553342,0.00020387913],"domain_scores_gemma":[0.9975937,0.0014225312,0.00022253502,0.000085766005,0.00047874294,0.00019670697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545322,0.00014907985,0.00031741703,0.0001293733,0.00015778778,0.00012993516,0.00031630762,0.00008485125,0.000012552368],"category_scores_gemma":[0.00010241538,0.00011488226,0.000096546326,0.00027524686,0.00007231227,0.0002832073,0.00002537238,0.00024619457,2.5069468e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004749068,0.000050016657,0.000008689816,0.000038013568,0.000036414007,0.000005503342,0.00019992213,0.010335753,0.000009194619,0.38175908,0.0004257402,0.60708416],"study_design_scores_gemma":[0.00029778449,0.000112482005,0.00028479283,0.000018467159,0.000016064141,0.00009059925,0.0000020837076,0.42082125,0.000005446339,0.5772555,0.0010092694,0.00008626935],"about_ca_topic_score_codex":9.2706875e-7,"about_ca_topic_score_gemma":3.06515e-7,"teacher_disagreement_score":0.6069979,"about_ca_system_score_codex":0.000010358478,"about_ca_system_score_gemma":0.00009096467,"threshold_uncertainty_score":0.46847627},"labels":[],"label_agreement":null},{"id":"W2081839654","doi":"10.1109/iccitechnol.2012.6285806","title":"A variational component splitting approach for finite generalized Dirichlet mixture models","year":2012,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Component (thermodynamics); Selection (genetic algorithm); Dirichlet distribution; Categorization; Feature selection; Model selection; Computer science; Artificial intelligence; Feature (linguistics); Mathematics; Algorithm; Mathematical optimization; Mixture model; Pattern recognition (psychology); Applied mathematics; Mathematical analysis","score_opus":0.04784302812778942,"score_gpt":0.2790166263666431,"score_spread":0.23117359823885367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081839654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012633111,0.0002907603,0.9876653,0.0005322998,0.00029653954,0.00039249737,0.000010040579,0.0001521016,0.010534107],"genre_scores_gemma":[0.057170935,0.0000047770213,0.93983364,0.0015083475,0.00040432753,0.00011384571,0.00003408104,0.000014809359,0.0009152284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846196,0.000141681,0.0002777164,0.00036851584,0.0002544952,0.00049564475],"domain_scores_gemma":[0.99896705,0.00022123431,0.00009985031,0.00042906558,0.00009750168,0.0001853034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011161042,0.0001864643,0.0002358718,0.000078206554,0.00016901779,0.000117726544,0.0005237827,0.00011114508,0.00001355429],"category_scores_gemma":[0.00003665923,0.00014714796,0.00014158955,0.0002042884,0.00001656656,0.00071427465,0.00017810038,0.00011477862,0.0000044889657],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072862636,0.00012383364,0.000028302751,0.000019079596,0.000025030642,1.8605367e-7,0.00056586997,0.0025635841,0.0004254588,0.98611015,0.0018096092,0.008321625],"study_design_scores_gemma":[0.00045904156,0.000013618998,0.00006353424,0.0000035361495,0.000011183663,0.000007720351,0.0000036777167,0.9001587,0.00028597115,0.096212246,0.0025784217,0.00020236867],"about_ca_topic_score_codex":0.000011523808,"about_ca_topic_score_gemma":2.1299748e-7,"teacher_disagreement_score":0.8975951,"about_ca_system_score_codex":0.000031012987,"about_ca_system_score_gemma":0.000039057937,"threshold_uncertainty_score":0.60005194},"labels":[],"label_agreement":null},{"id":"W2082905687","doi":"10.1007/s11634-013-0152-4","title":"Infinite Dirichlet mixture models learning via expectation propagation","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet process; Mixture model; Model selection; Dirichlet distribution; Computer science; Hierarchical Dirichlet process; Inference; Automatic summarization; Cluster analysis; Bayesian inference; Minimum description length; Artificial intelligence; Latent Dirichlet allocation; Data mining; Selection (genetic algorithm); Synthetic data; Machine learning; Bayesian probability; Topic model; Mathematics","score_opus":0.030519176843317914,"score_gpt":0.3035554330616236,"score_spread":0.2730362562183057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082905687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028994011,0.00094516005,0.9942775,0.0007521331,0.00003784075,0.00017448538,0.0000033205147,0.000051610925,0.0008585696],"genre_scores_gemma":[0.7322728,0.0012033697,0.26600772,0.000062633466,0.000023430954,0.000052195912,0.00030074417,0.0000047919802,0.00007230122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984538,0.00021206788,0.0003290991,0.0006346769,0.00020828363,0.00016205321],"domain_scores_gemma":[0.9986732,0.000101413316,0.00022397809,0.0008443799,0.00010234444,0.000054669097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047124628,0.00012593545,0.0002050678,0.00032476344,0.00011167833,0.00020101987,0.0005820705,0.00006993581,0.000010117777],"category_scores_gemma":[0.0000681405,0.00010805596,0.000033337237,0.0014377735,0.00003613518,0.0051659183,0.00016533573,0.00015754381,0.0000071105183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034931825,0.000053131524,0.0051106797,0.000020073687,0.000056836492,6.623452e-7,0.00073769846,0.002407475,0.0042549805,0.0422409,0.00008301425,0.94503105],"study_design_scores_gemma":[0.00009620409,0.000012068764,0.017642634,0.0000082707875,0.00005359066,9.184558e-7,0.000058504804,0.9432251,0.00008765981,0.037646797,0.0010331814,0.00013508557],"about_ca_topic_score_codex":0.000040251725,"about_ca_topic_score_gemma":0.000103381455,"teacher_disagreement_score":0.944896,"about_ca_system_score_codex":0.00002418815,"about_ca_system_score_gemma":0.000014959085,"threshold_uncertainty_score":0.4406394},"labels":[],"label_agreement":null},{"id":"W2084043122","doi":"10.48550/arxiv.0906.2217","title":"Asymptotic Results for the Two-parameter Poisson-Dirichlet Distribution","year":2009,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Dirichlet distribution; Mathematics; Poisson distribution; Distribution (mathematics); Generalized Dirichlet distribution; Applied mathematics; Concentration parameter; Gamma distribution; Mathematical analysis; Combinatorics; Dirichlet's principle; Statistics","score_opus":0.05478481210760605,"score_gpt":0.31741056800479805,"score_spread":0.262625755897192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084043122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012667635,0.00066569063,0.972983,0.009990985,0.0016756845,0.00095894764,0.00015542915,0.00021769344,0.00068490324],"genre_scores_gemma":[0.62472177,0.00012712028,0.3711095,0.0019160712,0.0008481761,0.0001889105,0.0002243943,0.00003119068,0.0008328885],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99708754,0.0002889393,0.00057707913,0.0011265739,0.00032494575,0.0005949319],"domain_scores_gemma":[0.9960285,0.0010336107,0.0003865453,0.0021889927,0.0002198764,0.00014246542],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017523944,0.00043083442,0.00045656663,0.000063395615,0.00028562118,0.00032130253,0.002153926,0.00033224912,0.0000026095925],"category_scores_gemma":[0.0006216107,0.00030124525,0.0003901712,0.00025863104,0.00007856288,0.00019165568,0.00089528336,0.00076335797,0.000042282012],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037784054,0.00059237215,0.003228623,0.00029669728,0.00060872314,0.00006644041,0.0019807604,0.002595845,0.0007354963,0.22863309,0.10401028,0.6568738],"study_design_scores_gemma":[0.0033489948,0.00046152767,0.092033714,0.00049074646,0.00040611826,0.000056402616,0.000012769796,0.28688782,0.0049145864,0.54240364,0.066851586,0.0021320686],"about_ca_topic_score_codex":0.000052474465,"about_ca_topic_score_gemma":0.000009545602,"teacher_disagreement_score":0.65474176,"about_ca_system_score_codex":0.00012213286,"about_ca_system_score_gemma":0.00016017322,"threshold_uncertainty_score":0.999944},"labels":[],"label_agreement":null},{"id":"W2085825224","doi":"10.1109/lsp.2012.2190280","title":"Simultaneous Feature and Model Selection for Continuous Hidden Markov Models","year":2012,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Hidden Markov model; Feature selection; Artificial intelligence; Markov model; Pattern recognition (psychology); Model selection; Selection (genetic algorithm); Maximum-entropy Markov model; Feature (linguistics); Markov process; Data modeling; Markov chain; Machine learning; Variable-order Markov model; Mathematics; Statistics","score_opus":0.017139816809225668,"score_gpt":0.2578869165525539,"score_spread":0.24074709974332825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085825224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01000152,0.00059511233,0.98649025,0.002110869,0.00016102454,0.0002850577,0.0000036488404,0.00017866929,0.00017384897],"genre_scores_gemma":[0.4980132,0.0000025853067,0.49930692,0.0022595811,0.00020668616,0.000022123659,9.4135856e-7,0.00001731013,0.00017065318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856365,0.00006353409,0.00017657725,0.00042231602,0.00021715285,0.00055678026],"domain_scores_gemma":[0.99930197,0.00015098069,0.0001197842,0.00015425823,0.00010193483,0.0001710849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045247647,0.00023251936,0.0002425508,0.0000953525,0.00027455232,0.000266529,0.0003105311,0.00013505171,6.68931e-7],"category_scores_gemma":[0.000015459716,0.0002087698,0.00006645268,0.00018190268,0.00005253816,0.0011813003,0.0000425102,0.0002256112,9.870448e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056431905,0.000059040754,0.000035002427,0.0001604815,0.000027222737,0.000004151256,0.0019913574,0.010755955,0.114225656,0.0025560048,0.0056969086,0.8644318],"study_design_scores_gemma":[0.00030273647,0.000035980673,0.0000031693362,0.000040840172,0.000025069086,0.00006318814,0.000004477784,0.98169374,0.004246459,0.013124624,0.0001744082,0.00028529504],"about_ca_topic_score_codex":0.000004501204,"about_ca_topic_score_gemma":7.658583e-7,"teacher_disagreement_score":0.9709378,"about_ca_system_score_codex":0.000045320947,"about_ca_system_score_gemma":0.00005358182,"threshold_uncertainty_score":0.8513385},"labels":[],"label_agreement":null},{"id":"W2086229908","doi":"10.1080/10485252.2014.941364","title":"Switching nonparametric regression models","year":2014,"lang":"en","type":"article","venue":"Journal of nonparametric statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Frequentist inference; Mathematics; Covariate; Nonparametric statistics; Nonparametric regression; Econometrics; Sequence (biology); Regression; Regression analysis; Statistics; Bayesian probability; Bayesian inference","score_opus":0.023662881517720318,"score_gpt":0.2958462564397692,"score_spread":0.27218337492204886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086229908","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015022302,0.0006260744,0.993939,0.00018623534,0.0012601938,0.000095344956,0.0000057136845,0.00003708494,0.002348111],"genre_scores_gemma":[0.24933255,0.00017387376,0.74989134,0.00027885236,0.00021163328,0.0000010816672,5.537845e-7,0.000017841816,0.00009230517],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968278,0.00041817958,0.0010049691,0.00031944393,0.0009992732,0.00043033602],"domain_scores_gemma":[0.9946394,0.0025668642,0.0011620681,0.00062838366,0.00064899545,0.00035427755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026809748,0.0002678982,0.00063782407,0.0015480337,0.0001439439,0.00028011538,0.001348791,0.00015045909,0.000010311509],"category_scores_gemma":[0.0027400663,0.00019929356,0.00017217034,0.0027310066,0.000036210222,0.00079738745,0.00019000685,0.0006662081,0.000015160995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012784224,0.00010980811,0.000094498995,0.000024492847,0.00003524408,0.00004613312,0.00017182385,0.0011270558,0.00011609186,0.26946935,0.0051093358,0.72368336],"study_design_scores_gemma":[0.0005977358,0.00038864004,0.0005158958,0.00006789174,0.000040815965,0.00026674947,0.0000051505344,0.5706552,0.00022844267,0.42551434,0.0014914245,0.00022769994],"about_ca_topic_score_codex":0.0000097697175,"about_ca_topic_score_gemma":4.9139055e-7,"teacher_disagreement_score":0.72345567,"about_ca_system_score_codex":0.000103674,"about_ca_system_score_gemma":0.00017039236,"threshold_uncertainty_score":0.8126955},"labels":[],"label_agreement":null},{"id":"W2089059576","doi":"10.1007/s10463-014-0490-9","title":"Parameterizing mixture models with generalized moments","year":2014,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mixing (physics); Mathematics; Moment (physics); Space (punctuation); Parameter space; Distribution (mathematics); Curse of dimensionality; Applied mathematics; Generalized method of moments; Mixture model; Dimensionality reduction; Second moment of area; Statistical physics; Mathematical analysis; Statistics; Geometry; Computer science; Classical mechanics; Physics","score_opus":0.061794282657489374,"score_gpt":0.31015294677653404,"score_spread":0.24835866411904467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089059576","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008855085,0.000028255014,0.9874761,0.0007946749,0.00014628808,0.00017536811,0.00002263509,0.000022559352,0.0024790515],"genre_scores_gemma":[0.22159615,0.000012485927,0.77799714,0.00030861594,0.000014141224,0.0000057234292,0.000001060535,0.0000087229655,0.000055988086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986181,0.000095763164,0.0004343194,0.00020812836,0.00042421775,0.00021945928],"domain_scores_gemma":[0.9984619,0.00021726885,0.00029993936,0.0007643695,0.00016876118,0.0000877726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005262879,0.0001641299,0.00041332302,0.000046234632,0.00006533995,0.000036679296,0.0008993867,0.00006226825,0.0000031723175],"category_scores_gemma":[0.00021318512,0.0000950251,0.00008009865,0.00021095741,0.0002459406,0.00027346762,0.00021498998,0.00011045796,0.0000014024406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008261947,0.00010349129,0.0000027601068,0.00017178782,0.000041898118,0.0000014822336,0.00030090776,0.0007739961,0.00068646274,0.98774207,0.00033704174,0.00982984],"study_design_scores_gemma":[0.00019976706,0.00009291608,0.00002098598,0.00017114524,0.000020887166,0.0000094898,0.0000026086254,0.19496734,0.0073131924,0.79682237,0.00026696545,0.000112310234],"about_ca_topic_score_codex":0.000015311565,"about_ca_topic_score_gemma":0.0000024057363,"teacher_disagreement_score":0.21274106,"about_ca_system_score_codex":0.000004778114,"about_ca_system_score_gemma":0.00004815677,"threshold_uncertainty_score":0.3875011},"labels":[],"label_agreement":null},{"id":"W2089952084","doi":"10.1007/s10260-015-0298-7","title":"Cluster-weighted $$t$$ t -factor analyzers for robust model-based clustering and dimension reduction","year":2015,"lang":"en","type":"article","venue":"Statistical Methods & Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"","keywords":"Cluster analysis; Covariate; Outlier; Expectation–maximization algorithm; Dimension (graph theory); Maximization; Mathematics; Cluster (spacecraft); Computer science; Statistics; Artificial intelligence; Pattern recognition (psychology); Data mining; Maximum likelihood; Mathematical optimization; Combinatorics","score_opus":0.07114175890775135,"score_gpt":0.3829113868634449,"score_spread":0.3117696279556935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089952084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038234608,0.00010246803,0.9972166,0.0010513107,0.00013997908,0.0009363922,0.000079664045,0.00016939109,0.00026595604],"genre_scores_gemma":[0.0056112255,0.000006018502,0.9933842,0.0002200874,0.00007843091,0.0005812497,0.00003157154,0.0000242226,0.00006300176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805367,0.00039002497,0.00036109643,0.0006804347,0.0001911845,0.00032356154],"domain_scores_gemma":[0.99776214,0.00086734287,0.00011825362,0.0005965677,0.0002518379,0.00040384175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012030263,0.00020435569,0.00028858602,0.00013367551,0.00021949282,0.00012837826,0.00031278437,0.00012083373,0.0000039522206],"category_scores_gemma":[0.00022408439,0.00018732983,0.000053404485,0.0003580635,0.00012363151,0.00020371204,0.00013526213,0.0001583776,0.0000029750486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031781827,0.000064208376,0.0000028188274,0.000041368326,0.000016219516,3.4193138e-7,0.00019311889,0.0034240005,0.002650287,0.30647552,0.00060277875,0.68649757],"study_design_scores_gemma":[0.00038616604,0.000058170463,0.000018320143,0.0000072381163,0.000032061253,0.00000627277,0.000008990853,0.7389997,0.0009196186,0.25846568,0.00092834147,0.00016940178],"about_ca_topic_score_codex":0.000011353018,"about_ca_topic_score_gemma":0.0000025667425,"teacher_disagreement_score":0.73557574,"about_ca_system_score_codex":0.00008239663,"about_ca_system_score_gemma":0.00014465844,"threshold_uncertainty_score":0.7639089},"labels":[],"label_agreement":null},{"id":"W2090512127","doi":"10.1016/j.spl.2014.03.023","title":"On testing the coefficient of variation in an inverse Gaussian population","year":2014,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Inverse Gaussian distribution; Statistic; Inverse; Gaussian; Statistics; Test statistic; Coefficient of variation; Invariant (physics); Applied mathematics; Transformation (genetics); Mathematical analysis; Statistical hypothesis testing; Geometry","score_opus":0.02996091269570892,"score_gpt":0.27108413949007304,"score_spread":0.24112322679436413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090512127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14271383,6.0754905e-7,0.85594976,0.0008586607,0.00012476851,0.00023923884,0.0000074952336,0.000024723266,0.00008092902],"genre_scores_gemma":[0.42001572,5.487974e-8,0.5792796,0.00067649723,0.00001372842,0.000006150569,0.00000414511,0.0000033624153,7.075374e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983673,0.00059882575,0.00030789568,0.0003149867,0.00023715617,0.00017381928],"domain_scores_gemma":[0.9985384,0.00063955603,0.00015271716,0.0005602703,0.000065711516,0.000043389988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015858862,0.00009964551,0.00013348363,0.00006496358,0.00007392931,0.000053543474,0.0003380276,0.00003454211,0.000001994088],"category_scores_gemma":[0.00081427675,0.000075400756,0.000017648323,0.0002967506,0.000060628863,0.00013224456,0.000050522587,0.0001371457,0.0000017093971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061548444,0.000076623786,0.002351379,0.000027080336,0.000001733315,7.148269e-7,0.001050359,0.0021731479,0.0025578507,0.9544353,0.000061001156,0.037258666],"study_design_scores_gemma":[0.00011157648,0.000079536185,0.10352128,0.000014478231,0.0000031072123,4.8067295e-7,4.0717254e-7,0.34495363,0.000047269514,0.5511983,0.0000046603454,0.00006525884],"about_ca_topic_score_codex":0.0002541272,"about_ca_topic_score_gemma":0.0001533473,"teacher_disagreement_score":0.403237,"about_ca_system_score_codex":0.000070143135,"about_ca_system_score_gemma":0.000023675828,"threshold_uncertainty_score":0.30747536},"labels":[],"label_agreement":null},{"id":"W2091522639","doi":"10.1109/iccspa.2013.6487242","title":"An online approach for learning non-Gaussian mixture models with localized feature selection","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Computer science; Mixture model; Artificial intelligence; Feature selection; Cluster analysis; Inference; Online model; Machine learning; Bayesian inference; Pattern recognition (psychology); Model selection; Unsupervised learning; Feature (linguistics); Bayesian probability; Mathematics; Artificial neural network","score_opus":0.019885044477786728,"score_gpt":0.2587987072127342,"score_spread":0.23891366273494746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091522639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00071705075,0.000034382763,0.9937346,0.00084838003,0.00005059935,0.0007671334,0.0000016126038,0.00032735305,0.003518878],"genre_scores_gemma":[0.10385869,0.000003895573,0.89192325,0.00056766614,0.00014228567,0.00012031193,0.00003703148,0.00002797933,0.0033188693],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984296,0.00012595288,0.00015666793,0.0006561907,0.00021462128,0.00041696],"domain_scores_gemma":[0.999051,0.000034430497,0.000086310036,0.0004151916,0.00020532137,0.00020779159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027171645,0.0002514219,0.00027460716,0.0001038767,0.00022705736,0.00031461922,0.00054867164,0.00021619433,0.000012166107],"category_scores_gemma":[0.0000074323098,0.0001651821,0.000073686584,0.00041966676,0.000028928098,0.001252102,0.000048474853,0.0003847808,0.0000025691377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014399824,0.0009528128,0.00023683754,0.00018206601,0.00015477724,0.0000039740403,0.0026494013,0.16588801,0.008867287,0.25065517,0.011284091,0.5589816],"study_design_scores_gemma":[0.0006513693,0.00039792972,0.00005318111,0.000011266774,0.000012716247,0.000030835094,0.000044558372,0.981087,0.0007226957,0.015925739,0.00078063447,0.0002820472],"about_ca_topic_score_codex":0.00010784227,"about_ca_topic_score_gemma":0.000017489558,"teacher_disagreement_score":0.815199,"about_ca_system_score_codex":0.000029497389,"about_ca_system_score_gemma":0.00007290558,"threshold_uncertainty_score":0.67359304},"labels":[],"label_agreement":null},{"id":"W2091723435","doi":"10.1016/j.stamet.2010.07.004","title":"An odd property of sample median from odd sample sizes","year":2010,"lang":"en","type":"article","venue":"Statistical Methodology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Sample (material); Counterexample; Sample size determination; Statistics; Sample mean and sample covariance; Closeness; Property (philosophy); Distribution (mathematics); Population; Large sample; Probabilistic logic; Combinatorics; Demography; Mathematical analysis","score_opus":0.0930813728022253,"score_gpt":0.3770364275727918,"score_spread":0.28395505477056654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091723435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019761333,0.000028138204,0.9946506,0.00082100695,0.0012067782,0.0001789826,0.00064495485,0.00009900263,0.00039438478],"genre_scores_gemma":[0.02819949,0.000007452047,0.9709492,0.0005135844,0.00022643771,0.000019192881,0.00004798372,0.000019246098,0.000017414472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99565446,0.002419417,0.00048105515,0.0007104777,0.00025778599,0.00047681975],"domain_scores_gemma":[0.97792864,0.020399394,0.00014189695,0.0010229959,0.00014986953,0.00035722763],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024140915,0.0002186446,0.0006213267,0.000094437026,0.000089241985,0.000048427042,0.001098792,0.00026037663,0.00083102833],"category_scores_gemma":[0.0120543195,0.00014720843,0.00006608794,0.00021264654,0.00043012737,0.00019900367,0.00021164028,0.0005080473,0.0000144506985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024283812,0.00006231422,0.0002448605,0.000010363703,0.000016740196,0.000007959854,0.00042680663,6.890018e-7,0.027007854,0.50578564,0.00020758732,0.4662049],"study_design_scores_gemma":[0.00029949733,0.00030617008,0.004282139,0.0000054022803,0.000024202474,0.000010348875,0.000014335441,0.016907295,0.009731036,0.9658348,0.00235738,0.00022736788],"about_ca_topic_score_codex":0.0037052736,"about_ca_topic_score_gemma":0.00080612727,"teacher_disagreement_score":0.46597755,"about_ca_system_score_codex":0.000010352531,"about_ca_system_score_gemma":0.00015496636,"threshold_uncertainty_score":0.99626756},"labels":[],"label_agreement":null},{"id":"W2092208443","doi":"10.1006/jmva.2001.2016","title":"Moment Properties of the Multivariate Dirichlet Distributions","year":2002,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Mathematics; Dirichlet distribution; Combinatorics; Joint probability distribution; Distribution (mathematics); Identity matrix; Multivariate statistics; Multivariate normal distribution; Matrix (chemical analysis); Marginal distribution; Random variable; Mathematical analysis; Statistics; Eigenvalues and eigenvectors","score_opus":0.03500292979712245,"score_gpt":0.26514511015245096,"score_spread":0.23014218035532852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092208443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019979069,0.00055125507,0.9763892,0.002572182,0.00019700981,0.000083779014,0.0000075430016,0.000010639386,0.00020931219],"genre_scores_gemma":[0.8607894,0.00005857102,0.13867281,0.00007180991,0.000056903322,0.0000023401244,2.7576144e-7,0.0000052680534,0.0003426239],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978492,0.0004390742,0.0007758305,0.00019503704,0.0005126252,0.00022823566],"domain_scores_gemma":[0.99785244,0.000084180596,0.0008957825,0.00061811035,0.00044022323,0.000109269815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009047422,0.00016016352,0.00051699637,0.00028935503,0.00015708256,0.000078379104,0.0011171644,0.000069285714,0.00003830174],"category_scores_gemma":[0.00018399284,0.000086602595,0.00075500057,0.0017679271,0.00006917488,0.00036884454,0.00022543379,0.00025738904,0.0000030709436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015668664,0.005500866,0.010994149,0.00017949367,0.025500877,0.000121604986,0.026048021,0.025035992,0.4632235,0.22372065,0.003985706,0.21553245],"study_design_scores_gemma":[0.0018450982,0.00018190924,0.039262325,0.00018562762,0.0032783176,0.000054604963,0.00006506472,0.8891018,0.054749224,0.00662505,0.004147173,0.0005038054],"about_ca_topic_score_codex":0.000100060104,"about_ca_topic_score_gemma":0.00000684054,"teacher_disagreement_score":0.8640658,"about_ca_system_score_codex":0.000068837646,"about_ca_system_score_gemma":0.000038715825,"threshold_uncertainty_score":0.35315514},"labels":[],"label_agreement":null},{"id":"W2093178418","doi":"10.1002/cjs.10112","title":"Current status observation of a three‐state counting process with application to simultaneous accurate and diluted HIV test data","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Estimator; Event (particle physics); Nonparametric statistics; Statistics; Current (fluid); Counting process; Parametric statistics; Econometrics; Hazard; Computer science; Event data; Estimation; Mathematics; Engineering","score_opus":0.07427766836367777,"score_gpt":0.280791684716111,"score_spread":0.20651401635243322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093178418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012237722,0.00017563885,0.9866711,0.00007744196,0.000069299946,0.00015685265,0.0005855045,0.000004701007,0.000021732561],"genre_scores_gemma":[0.4366446,0.000019360097,0.5632504,0.00004394465,0.000017803877,0.0000013017662,0.000012266252,0.0000072480657,0.0000030675565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903005,0.000026351225,0.00034943983,0.00018591815,0.00017422956,0.0002340305],"domain_scores_gemma":[0.99792516,0.00019786034,0.00041922217,0.00031818406,0.0007005022,0.00043906708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003491602,0.0001037876,0.00017512905,0.00013127657,0.000072560426,0.00007584396,0.0005477636,0.000022002387,0.0000020890782],"category_scores_gemma":[0.00044260843,0.0000868991,0.000006661055,0.00029749033,0.00005417723,0.00037296867,0.0000363439,0.0001372144,6.830568e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045376713,0.00005920548,0.0419808,0.00025044696,0.000042696232,0.0001672556,0.0069685844,0.0010801648,0.00015514476,0.018336812,0.0005121358,0.9304014],"study_design_scores_gemma":[0.00077474467,0.0005870817,0.050819546,0.0003413824,0.000095804295,0.00016063261,0.00009081432,0.8921181,0.00024505839,0.05102259,0.003295806,0.0004484488],"about_ca_topic_score_codex":0.0010632611,"about_ca_topic_score_gemma":0.01303466,"teacher_disagreement_score":0.9299529,"about_ca_system_score_codex":0.00004280364,"about_ca_system_score_gemma":0.0010170044,"threshold_uncertainty_score":0.7273646},"labels":[],"label_agreement":null},{"id":"W2094029434","doi":"10.1155/2012/537474","title":"Testing Homogeneity in a Semiparametric Two-Sample Problem","year":2012,"lang":"en","type":"article","venue":"Journal of Probability and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Algorithm; Materials science; Computer science","score_opus":0.05258564447556148,"score_gpt":0.30650445305168084,"score_spread":0.25391880857611937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094029434","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029162733,0.00047937996,0.96985346,0.00008126484,0.00013089014,0.00011411247,0.000016284586,0.000007829977,0.00015402504],"genre_scores_gemma":[0.18853657,0.000009964433,0.8113412,0.00004617907,0.000057385074,0.0000016393473,3.048953e-7,0.000003186956,0.0000035754197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986385,0.00025842985,0.0004923987,0.00013005489,0.00020861588,0.0002720102],"domain_scores_gemma":[0.99781644,0.001343273,0.0002684802,0.00017406092,0.00022289417,0.0001748404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030491098,0.000099425655,0.00025201097,0.00013444555,0.00005696924,0.00006822104,0.00023972889,0.000045522254,0.0000029657397],"category_scores_gemma":[0.0020365694,0.00007962378,0.00002592888,0.0004958901,0.000052244053,0.0004268796,0.0000976189,0.00027090547,5.9159373e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011794717,0.00030748354,0.11901049,0.00012190387,0.000012224553,0.000013055566,0.0011190422,0.00009847283,0.00017660401,0.44661787,0.00013019802,0.43238086],"study_design_scores_gemma":[0.00045935385,0.00019610158,0.051307842,0.000041180374,0.000015446501,0.00017619506,0.000009225645,0.020235827,0.00009632555,0.92706114,0.00025583865,0.00014552785],"about_ca_topic_score_codex":0.000056024262,"about_ca_topic_score_gemma":0.00001708831,"teacher_disagreement_score":0.48044327,"about_ca_system_score_codex":0.000056987254,"about_ca_system_score_gemma":0.000111917405,"threshold_uncertainty_score":0.32469636},"labels":[],"label_agreement":null},{"id":"W2094293694","doi":"10.1139/f04-049","title":"A model for categorical length data from groundfish surveys","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"European Commission","keywords":"Multinomial distribution; Overdispersion; Statistics; Dirichlet distribution; Markov chain Monte Carlo; Categorical variable; Econometrics; Mathematics; Bayesian probability; Computer science; Count data; Poisson distribution","score_opus":0.11921040693540823,"score_gpt":0.2937061177372341,"score_spread":0.17449571080182585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094293694","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017469393,0.0006371798,0.97476715,0.00639777,0.00039146404,0.000068207744,0.000020741909,0.0000048364977,0.0002432376],"genre_scores_gemma":[0.5258171,0.000027594308,0.47363812,0.0003902638,0.00008222103,0.0000010226706,0.0000018040989,0.0000033363565,0.000038532005],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988154,0.00008775776,0.00029209116,0.00028932063,0.00020631548,0.00030906798],"domain_scores_gemma":[0.99880445,0.0002204746,0.00015094246,0.0003057099,0.00005408842,0.0004643468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002284867,0.00010763182,0.0002217977,0.000114157265,0.00037616506,0.0006414138,0.0015729069,0.000048877926,0.000005250924],"category_scores_gemma":[0.00032903766,0.00008140873,0.00004210645,0.00025875203,0.00032929744,0.0013335105,0.000062997875,0.00010386468,5.859146e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000138287005,0.00007500318,0.008421923,0.000034813216,0.00012221845,0.00017756618,0.0120825535,0.0005390483,0.000105119325,0.32683602,0.015882306,0.6357096],"study_design_scores_gemma":[0.00033633222,0.00016304944,0.0011418493,0.000023477807,0.000014358053,0.000061061895,0.0001120007,0.4391115,0.000012899265,0.55776995,0.0011030512,0.00015047459],"about_ca_topic_score_codex":0.0095402505,"about_ca_topic_score_gemma":0.031255513,"teacher_disagreement_score":0.63555914,"about_ca_system_score_codex":0.000042337466,"about_ca_system_score_gemma":0.002160408,"threshold_uncertainty_score":0.9970553},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.021128729276938034,"score_gpt":0.28424745489681436,"score_spread":0.2631187256198763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094952625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036026314,0.000041556887,0.99350816,0.0015462275,0.00014414263,0.00030523713,0.0000030456954,0.000097979595,0.00075101916],"genre_scores_gemma":[0.7504133,0.000054352182,0.24853729,0.00086782477,0.000025740661,0.000069192385,0.000001254748,0.000012966482,0.000018101598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979221,0.00013769208,0.00029901922,0.0005013475,0.0008571801,0.00028262282],"domain_scores_gemma":[0.99919933,0.00008216698,0.000063287756,0.00023594305,0.000063891435,0.0003553587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007013482,0.00018248605,0.00019639058,0.00016716876,0.00011074901,0.00004954415,0.00042491246,0.00012384717,0.000107270025],"category_scores_gemma":[0.000014647314,0.0001510427,0.000035180696,0.00025102898,0.00020723765,0.00047657161,0.000007402326,0.00055905036,0.000007715746],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034429217,0.00040885064,0.000105491774,0.000030713763,0.00002301575,0.00014966352,0.0027119028,0.00034129134,0.0012456181,0.0025597936,0.00002170667,0.9923675],"study_design_scores_gemma":[0.0011785824,0.000037912752,0.0002538952,0.00011028987,0.00001830912,0.00014906412,0.00007006172,0.9910765,0.0056142397,0.001289337,0.0000036238473,0.00019815288],"about_ca_topic_score_codex":0.000068021334,"about_ca_topic_score_gemma":0.00013968768,"teacher_disagreement_score":0.9921694,"about_ca_system_score_codex":0.000043646705,"about_ca_system_score_gemma":0.00018350611,"threshold_uncertainty_score":0.6159342},"labels":[],"label_agreement":null},{"id":"W2095051119","doi":"10.1002/cjs.10143","title":"Constrained nonparametric maximum likelihood estimation of stochastically ordered survivor functions","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Estimator; Nonparametric statistics; Uniqueness; Constraint (computer-aided design); Maximum likelihood; Consistency (knowledge bases); Statistics; Applied mathematics; Combinatorics; Discrete mathematics; Mathematical analysis","score_opus":0.017680067553879162,"score_gpt":0.24624716413287326,"score_spread":0.2285670965789941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095051119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077143556,0.00025755525,0.9968911,0.0002238072,0.0009981162,0.00007957499,0.00018317049,0.000005873763,0.0005893992],"genre_scores_gemma":[0.40492195,0.0000030826918,0.59493417,0.00005813599,0.000053688356,6.1137445e-7,0.0000029439354,0.0000058925875,0.000019532547],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987054,0.000102191094,0.0004960381,0.000092948074,0.0002236292,0.00037980438],"domain_scores_gemma":[0.9976943,0.00039449858,0.0003340605,0.00020518966,0.00051529333,0.000856655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007628287,0.00011421826,0.00025711016,0.00046112388,0.0000915834,0.00006404362,0.00033711593,0.00007151834,0.0000662251],"category_scores_gemma":[0.0009634016,0.0001066344,0.000053356496,0.00054912025,0.00011406226,0.00030447694,0.00001502451,0.00020696856,0.000008712757],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009208764,0.00007052688,0.0006744849,0.000045143337,0.000080174694,0.00004902637,0.0008033445,0.0005719867,0.00009254314,0.36119142,0.00487387,0.6315383],"study_design_scores_gemma":[0.0028483102,0.0017193389,0.025444087,0.0002857571,0.0004415446,0.0017528732,0.00025873116,0.3467252,0.00046930995,0.6145316,0.0043864995,0.0011367885],"about_ca_topic_score_codex":0.0005510138,"about_ca_topic_score_gemma":0.0009065154,"teacher_disagreement_score":0.6304015,"about_ca_system_score_codex":0.00007807427,"about_ca_system_score_gemma":0.0014809374,"threshold_uncertainty_score":0.43484247},"labels":[],"label_agreement":null},{"id":"W2096198554","doi":"10.7551/mitpress/1120.003.0097","title":"Fast, Large-Scale Transformation-Invariant Clustering","year":2002,"lang":"en","type":"book-chapter","venue":"The MIT Press eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Transformation (genetics); Scale invariance; Invariant (physics); Computer science; Scale (ratio); Mathematics; Artificial intelligence; Geography; Statistics; Cartography; Mathematical physics; Biology","score_opus":0.035341955376401384,"score_gpt":0.24160839654926075,"score_spread":0.20626644117285936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096198554","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6826682e-7,0.00034853304,0.50955355,0.00012195255,0.00021868816,0.00027078736,0.000018155704,0.00010951497,0.48935866],"genre_scores_gemma":[0.00021726378,0.00010115679,0.1092407,0.00068562204,0.00034569102,0.0000446507,0.000004683007,0.00006399203,0.88929623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981606,0.000091261754,0.00044321286,0.0004804597,0.00039433874,0.0004301555],"domain_scores_gemma":[0.9982067,0.00009143544,0.00019682515,0.0013205714,0.000064367814,0.000120140045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054344063,0.00041291723,0.00040286835,0.000079376645,0.00027051076,0.00026519634,0.0016904237,0.00030455922,0.00005301631],"category_scores_gemma":[0.0000029393893,0.00029383894,0.00025291095,0.000009358069,0.0000771306,0.00017124046,0.00038975524,0.0005976939,0.000052919357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004696733,0.0000070422925,1.0311311e-8,0.000053309006,0.00006066049,0.000013594801,0.0061319345,0.00002315238,0.000021389447,0.8652803,0.0009608593,0.12744309],"study_design_scores_gemma":[0.00048772583,0.000051942105,6.951782e-7,0.00027062756,0.00011902448,0.00009415325,0.0000050535346,0.114859104,0.0005423571,0.13389036,0.74899065,0.0006883177],"about_ca_topic_score_codex":0.000019867806,"about_ca_topic_score_gemma":0.000023224877,"teacher_disagreement_score":0.74802977,"about_ca_system_score_codex":0.000034053515,"about_ca_system_score_gemma":0.00003190272,"threshold_uncertainty_score":0.99995136},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015525361883031955,"score_gpt":0.27029117910126044,"score_spread":0.2547658172182285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096784803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020310603,0.00005636992,0.9790038,0.00028352457,0.000081381186,0.0001486111,0.00004145832,0.000051641688,0.000022616883],"genre_scores_gemma":[0.76546293,0.000050329825,0.23386553,0.000527448,0.000009125491,0.000008462421,0.00000861118,0.000009987315,0.0000575995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982287,0.00014908554,0.0004659922,0.00056722964,0.00035750287,0.00023147176],"domain_scores_gemma":[0.9989521,0.00029584134,0.00014907027,0.00035668386,0.00010486698,0.00014147519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066930056,0.00026579408,0.0004084686,0.00072611205,0.0001771576,0.000061388004,0.00020634953,0.00012361519,0.000046372603],"category_scores_gemma":[0.000009429482,0.00022264702,0.00018762705,0.0009953924,0.00005245326,0.00017213555,0.0000049523387,0.0002621909,0.0000017293181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055240158,0.00015133903,0.000024658848,0.000017860875,0.00012721411,0.000002793861,0.0001357116,0.58876604,0.001765587,0.0005046509,0.0000027713863,0.4084461],"study_design_scores_gemma":[0.00022747045,0.00015124425,0.0001650407,0.000026156356,0.00025839306,0.000003123486,0.0000022952868,0.86080045,0.13701162,0.0011641519,0.0000018094337,0.00018827275],"about_ca_topic_score_codex":0.00034373562,"about_ca_topic_score_gemma":0.000389992,"teacher_disagreement_score":0.7451523,"about_ca_system_score_codex":0.000022794828,"about_ca_system_score_gemma":0.000029883535,"threshold_uncertainty_score":0.9079282},"labels":[],"label_agreement":null},{"id":"W2096936651","doi":"10.1002/cjs.5550360308","title":"Nonparametric adaptive likelihood weights","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Mathematics; Nonparametric statistics; Maximization; Statistics; Convergence (economics); Expectation–maximization algorithm; Population; Entropy (arrow of time); Maximum likelihood; Applied mathematics; Computer science; Mathematical optimization; Artificial intelligence; Demography","score_opus":0.025630252514085558,"score_gpt":0.22864857257298676,"score_spread":0.2030183200589012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096936651","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010420514,0.00065819814,0.9953371,0.00020551893,0.00067295256,0.000043473192,0.00004527852,0.0000056025483,0.0019897711],"genre_scores_gemma":[0.17597415,0.00006244983,0.82340276,0.00028648617,0.00012154996,3.9126715e-7,5.429192e-7,0.000007622531,0.00014403248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989094,0.00008376644,0.00032288325,0.00012703879,0.00021921395,0.00033770828],"domain_scores_gemma":[0.9980936,0.00017525835,0.00021161664,0.00021426883,0.00040806658,0.0008971985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028452458,0.00011183663,0.00021913319,0.0004677572,0.00018194219,0.00005937392,0.00061047275,0.000058870704,0.00003064046],"category_scores_gemma":[0.00017252527,0.000097646844,0.000057993802,0.00049609836,0.00008947073,0.000241599,0.000015680343,0.00026634792,0.000020410676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062225718,0.000026420395,0.00071192253,0.000007984464,0.00006355498,0.0048659192,0.00206889,0.000027407095,0.000012493311,0.7132908,0.054028787,0.22488962],"study_design_scores_gemma":[0.0012963044,0.0012432509,0.018788276,0.000105702085,0.00006882559,0.0068591475,0.000048336267,0.03522532,0.000446415,0.8921879,0.04294388,0.0007866307],"about_ca_topic_score_codex":0.0007219736,"about_ca_topic_score_gemma":0.0013565349,"teacher_disagreement_score":0.22410299,"about_ca_system_score_codex":0.00011229229,"about_ca_system_score_gemma":0.0022470925,"threshold_uncertainty_score":0.39862457},"labels":[],"label_agreement":null},{"id":"W2097433879","doi":"10.2202/1557-4679.1223","title":"A Pseudo-EM Algorithm for Clustering Incomplete Longitudinal Data","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Cholesky decomposition; Expectation–maximization algorithm; Covariance; Computer science; Focus (optics); Missing data; Data mining; Multivariate statistics; Algorithm; Multivariate normal distribution; Determining the number of clusters in a data set; CURE data clustering algorithm; Mathematics; Correlation clustering; Statistics; Artificial intelligence; Maximum likelihood; Machine learning","score_opus":0.05577961052628969,"score_gpt":0.3465629364035154,"score_spread":0.29078332587722566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097433879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052023283,0.000033057193,0.9925877,0.0028237386,0.0036493319,0.00007697929,0.00023439672,0.000010393346,0.00006416052],"genre_scores_gemma":[0.02878991,0.00002078977,0.96969277,0.000477237,0.0009508662,0.0000012470605,0.000010885412,0.000008661152,0.000047611902],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988093,0.000041116637,0.00039141366,0.0001623825,0.0004498362,0.0001459517],"domain_scores_gemma":[0.99796146,0.0005337615,0.00037399502,0.0004791998,0.0005790018,0.00007256059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013311061,0.000100440455,0.00014558705,0.000091819165,0.00008486264,0.00029996716,0.003872291,0.000037285874,0.000009670836],"category_scores_gemma":[0.0003143762,0.000067509485,0.000058615682,0.000070820686,0.000053543266,0.00034546538,0.0006666946,0.00029764898,0.000003088172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020812304,0.00003880471,0.00002608369,0.000003994109,0.000117574535,0.000060185484,0.00023353484,0.0000125510915,0.0018872563,0.06987952,0.006347589,0.9213721],"study_design_scores_gemma":[0.0006111206,0.00010582324,0.0005270713,0.00003033645,0.000031879066,0.0013942326,0.000017225022,0.8710575,0.000545651,0.11416264,0.011382232,0.0001342627],"about_ca_topic_score_codex":0.000009613008,"about_ca_topic_score_gemma":0.000038604852,"teacher_disagreement_score":0.9212378,"about_ca_system_score_codex":0.000021645374,"about_ca_system_score_gemma":0.00012276981,"threshold_uncertainty_score":0.71957445},"labels":[],"label_agreement":null},{"id":"W2097834860","doi":"","title":"A recursive method for functionals of Poisson processes","year":2002,"lang":"en","type":"article","venue":"Project Euclid (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Toronto","funders":"","keywords":"Mathematics; Nonparametric statistics; Poisson distribution; Prior probability; Applied mathematics; Constructive; Exponential family; Compound Poisson process; Bayesian probability; Simple (philosophy); Random variable; Statistics; Poisson process; Process (computing); Computer science","score_opus":0.08832111591084192,"score_gpt":0.2604121607848866,"score_spread":0.1720910448740447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097834860","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038416628,0.00016566772,0.98720866,0.00020350685,0.00014749498,0.00047246556,0.000017804508,0.00009335261,0.011306905],"genre_scores_gemma":[0.021143086,0.00019774854,0.97217005,0.00017919746,0.0000636829,0.000005387071,0.0000027294668,0.000013912678,0.0062242076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998791,0.00015678046,0.00016421135,0.00050847675,0.00011572048,0.00026381493],"domain_scores_gemma":[0.9985901,0.00039090254,0.00018715557,0.00036464568,0.0003994914,0.00006766495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037528534,0.0001549554,0.00025355758,0.00030985835,0.000104562925,0.0000308913,0.00065963896,0.00009497737,0.00002656155],"category_scores_gemma":[0.00017996508,0.00015313129,0.00013225079,0.0012218244,0.00004086354,0.0004589058,0.00012914387,0.000098539276,0.000007300288],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021848884,0.0006517035,0.00022840007,0.00073655095,0.00022513203,0.000050082304,0.004682882,0.00025939284,0.0013103326,0.81933737,0.014544415,0.15775527],"study_design_scores_gemma":[0.005383647,0.0024237377,0.00027273124,0.00033735862,0.00038916353,0.000117537944,0.00064675056,0.30957273,0.043900356,0.46506488,0.16999304,0.0018980632],"about_ca_topic_score_codex":0.000048632162,"about_ca_topic_score_gemma":0.00001175758,"teacher_disagreement_score":0.35427245,"about_ca_system_score_codex":0.00004889322,"about_ca_system_score_gemma":0.00010815885,"threshold_uncertainty_score":0.6244513},"labels":[],"label_agreement":null},{"id":"W2097973007","doi":"10.1142/s0219691314500027","title":"STUDENTIZED PARTIAL SCORE TESTS FOR VARIANCES IN LONGITUDINAL DATA","year":2013,"lang":"en","type":"article","venue":"International Journal of Wavelets Multiresolution and Information Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Studentized range; Mathematics; Statistics; Studentized residual; Population; Statistic; Nonparametric statistics; Test statistic; Econometrics; Statistical hypothesis testing; Standard error; Medicine","score_opus":0.06546592658279668,"score_gpt":0.3543173010230344,"score_spread":0.2888513744402377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097973007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014242185,0.00019029816,0.9829319,0.0018263388,0.0004872365,0.00016284549,0.0000058206706,0.000012730462,0.0001406329],"genre_scores_gemma":[0.69671756,0.00006022256,0.30275598,0.0003184856,0.00011864857,0.000006758487,0.000011014881,0.0000023700163,0.000008970244],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986944,0.00003637915,0.00063917745,0.000117345655,0.00037360797,0.00013908929],"domain_scores_gemma":[0.9985247,0.00007271887,0.0005338956,0.00012485927,0.00067898736,0.000064829175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000819703,0.000090208116,0.00014390868,0.0002790073,0.00007426276,0.0006221255,0.0008166621,0.00004773801,0.0000073596116],"category_scores_gemma":[0.00027351023,0.00007395603,0.000030691295,0.00010857962,0.00003258401,0.012181388,0.00018785872,0.000118276745,0.0000030422095],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004941921,0.000059843012,0.001690033,0.00003488065,0.000025548321,0.0000030931665,0.0009953636,0.000091225775,0.00023041962,0.009359721,0.000565132,0.9868953],"study_design_scores_gemma":[0.00237086,0.00006697422,0.049460504,0.00021815562,0.000008095273,0.00015557365,0.00006905915,0.9373041,0.000202526,0.0052490993,0.0047436357,0.00015141728],"about_ca_topic_score_codex":0.000019277715,"about_ca_topic_score_gemma":0.0000035657474,"teacher_disagreement_score":0.9867439,"about_ca_system_score_codex":0.00004643349,"about_ca_system_score_gemma":0.00012729605,"threshold_uncertainty_score":0.88312125},"labels":[],"label_agreement":null},{"id":"W2098269566","doi":"10.1111/j.1755-0998.2010.02902.x","title":"Distance‐based population classification software using mean‐field annealing","year":2010,"lang":"en","type":"article","venue":"Molecular Ecology Resources","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Biology; Software; Population; Statistics; Evolutionary biology; Demography; Computer science; Mathematics","score_opus":0.019550064904245483,"score_gpt":0.2860991544047112,"score_spread":0.2665490895004657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098269566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38783944,0.000037204954,0.6110864,0.00046373886,0.0002512464,0.000089563924,6.4492394e-7,0.00009576847,0.00013596487],"genre_scores_gemma":[0.56568456,3.6739212e-7,0.43357575,0.0006676282,0.000038871312,0.000007744699,0.0000040802083,0.000008762657,0.000012211175],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871206,0.00019340072,0.00022654401,0.00043533088,0.00015812973,0.00027453052],"domain_scores_gemma":[0.99898905,0.00014085125,0.00014962413,0.00056566636,0.000070332455,0.000084502644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004194244,0.00014045634,0.00017567312,0.00012582657,0.00022069429,0.000107028325,0.00049744226,0.00022953001,0.000014199395],"category_scores_gemma":[0.0001665202,0.00013784006,0.00007893227,0.00024258975,0.000044505923,0.00014720346,0.00008087682,0.0002832791,0.000004371583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006089409,0.00022073893,0.13567959,0.00009431475,0.00008002435,0.0001787192,0.0017277817,0.0034220344,0.4395957,0.20023547,0.00021744905,0.21848728],"study_design_scores_gemma":[0.00061969215,0.00014459097,0.05628628,0.00002957593,0.000046715097,0.00004476152,0.000019177794,0.86217076,0.030779999,0.046034858,0.0032103385,0.0006132525],"about_ca_topic_score_codex":0.000046847825,"about_ca_topic_score_gemma":0.00012293486,"teacher_disagreement_score":0.85874873,"about_ca_system_score_codex":0.000025925876,"about_ca_system_score_gemma":0.000035065943,"threshold_uncertainty_score":0.56209546},"labels":[],"label_agreement":null},{"id":"W2098555101","doi":"10.1002/bimj.200410103","title":"Fisher Information Matrix of the Dirichlet-multinomial Distribution","year":2005,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multinomial distribution; Mathematics; Dirichlet distribution; Fisher information; Statistics; Negative multinomial distribution; Applied mathematics; Econometrics; Beta-binomial distribution; Negative binomial distribution; Mathematical analysis; Poisson distribution","score_opus":0.008645270941456831,"score_gpt":0.2580979848942987,"score_spread":0.24945271395284185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098555101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005169402,0.0001368044,0.99123675,0.0023966066,0.0004950325,0.00005971997,0.00000786315,0.000016180235,0.00048164083],"genre_scores_gemma":[0.5937468,0.000020382677,0.40568796,0.00018983913,0.00027696896,9.4681667e-7,0.0000014398532,0.000002242109,0.00007343192],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988718,0.00011266364,0.00036654336,0.00007574242,0.00039716047,0.00017611367],"domain_scores_gemma":[0.99921054,0.00008479594,0.00024536796,0.00021057247,0.00015067575,0.000098059325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006329006,0.00007556732,0.00011438855,0.00025268216,0.00012551948,0.00016313266,0.00067804474,0.00007549562,0.000019960502],"category_scores_gemma":[0.0002584412,0.000044730346,0.0001334057,0.0020308585,0.00002782504,0.00086424086,0.00015083831,0.00021300133,0.000017953997],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006768855,0.000038341783,0.00043741005,0.0000036001445,0.000009142915,5.907749e-7,0.000071976196,0.000015483449,0.00044617688,0.014833193,0.0106120175,0.9735253],"study_design_scores_gemma":[0.0027425122,0.0002885698,0.15883723,0.000059268612,0.000050065915,0.0007012752,0.000015222399,0.116500184,0.020979883,0.011121712,0.688125,0.00057905266],"about_ca_topic_score_codex":0.0000033132615,"about_ca_topic_score_gemma":1.4666223e-7,"teacher_disagreement_score":0.9729462,"about_ca_system_score_codex":0.000093274735,"about_ca_system_score_gemma":0.000059376267,"threshold_uncertainty_score":0.18240505},"labels":[],"label_agreement":null},{"id":"W2098878547","doi":"10.1093/molbev/msp248","title":"A Dirichlet Process Covarion Mixture Model and Its Assessments Using Posterior Predictive Discrepancy Tests","year":2009,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Génome Québec; Genome Canada","keywords":"Dirichlet process; Dirichlet distribution; Biology; Probabilistic logic; Phylogenetic tree; Sequence (biology); Biological system; Bayesian probability; Statistical physics; Mathematics; Evolutionary biology; Statistics; Genetics; Physics","score_opus":0.014235130349692177,"score_gpt":0.338292050934288,"score_spread":0.3240569205845958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098878547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33119053,0.001166931,0.6670832,0.00027368192,0.00004207046,0.00014201996,0.0000052586247,0.000035831832,0.000060508144],"genre_scores_gemma":[0.8426098,0.000020407233,0.15700057,0.00032074595,0.000016753422,0.000006200624,0.0000062641507,0.0000041811245,0.000015083891],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989681,0.00013948345,0.00013976071,0.00044771176,0.00007466433,0.00023027077],"domain_scores_gemma":[0.99959004,0.0000121180765,0.00007611909,0.00016551421,0.00007609298,0.00008012317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019493274,0.00015246512,0.00016671375,0.000076178265,0.000151514,0.000039857267,0.00014381915,0.00018872414,3.1407183e-7],"category_scores_gemma":[0.00002870434,0.00012918576,0.0000267848,0.00015399074,0.0000404371,0.00027370625,0.000084643354,0.00013379598,3.3713127e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015096385,0.00021492815,0.0041597704,0.00007097927,0.00007944918,0.000042346608,0.0012417601,0.0009133304,0.65907496,0.28595617,0.000019000325,0.04807637],"study_design_scores_gemma":[0.0002545544,0.00023815993,0.010965535,0.00003119091,0.000022163042,0.0000807302,0.0000028582892,0.8025213,0.0009490013,0.1847867,0.0000023820705,0.00014542692],"about_ca_topic_score_codex":0.0000049817445,"about_ca_topic_score_gemma":0.0000015449083,"teacher_disagreement_score":0.80160797,"about_ca_system_score_codex":0.00003098498,"about_ca_system_score_gemma":0.000060118764,"threshold_uncertainty_score":0.5268042},"labels":[],"label_agreement":null},{"id":"W2099384681","doi":"10.1109/cec.2008.4631256","title":"Model order selection for multiple cooperative swarms clustering using stability analysis","year":2008,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Stability (learning theory); Selection (genetic algorithm); Data mining; Swarm behaviour; Consensus clustering; Swarm intelligence; Artificial intelligence; Machine learning; Correlation clustering; CURE data clustering algorithm; Particle swarm optimization","score_opus":0.11213185795814502,"score_gpt":0.3204921821225822,"score_spread":0.20836032416443717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099384681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046563648,0.000011205717,0.9526936,0.000066425186,0.000055095996,0.00025625998,0.000003032498,0.00010852905,0.0002422519],"genre_scores_gemma":[0.44644985,0.0000016770986,0.5532978,0.000095365154,0.000014695445,0.000011694401,0.0000011285339,0.0000041524213,0.00012362702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891144,0.00008155023,0.0002074903,0.00043747117,0.00012622152,0.0002358058],"domain_scores_gemma":[0.99916077,0.00010002555,0.00005156362,0.00028525532,0.00033084312,0.00007153933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003683529,0.00012668005,0.0002315639,0.000113130125,0.000317654,0.000055347944,0.00021954844,0.00006234249,0.000010256656],"category_scores_gemma":[0.00006866782,0.000104440514,0.00011883856,0.0010278733,0.000029009207,0.00044532632,0.00009348178,0.00007558719,7.3600404e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035513105,0.00013939972,0.0034584966,0.00001919747,0.00026437917,9.675349e-7,0.003109443,0.9540237,0.022053167,0.008256939,0.00007979139,0.008558966],"study_design_scores_gemma":[0.0002418813,0.000026986898,0.00009509769,0.000001294147,0.00004017314,0.0000050670233,0.000008660472,0.9891436,0.008927768,0.0013510311,0.000012745625,0.00014569634],"about_ca_topic_score_codex":0.00015468083,"about_ca_topic_score_gemma":0.00039607374,"teacher_disagreement_score":0.3998862,"about_ca_system_score_codex":0.00007001251,"about_ca_system_score_gemma":0.00011214013,"threshold_uncertainty_score":0.42589608},"labels":[],"label_agreement":null},{"id":"W2100113682","doi":"10.1111/rssb.12022","title":"Non-Parametric Identification and Estimation of the Number of Components in Multivariate Mixtures","year":2013,"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":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Identifiability; Mathematics; Random variate; Multivariate statistics; Parametric statistics; Component (thermodynamics); Statistics; Applied mathematics; Multivariate normal distribution; Rank (graph theory); Identification (biology); Nonparametric statistics; Random variable; Combinatorics","score_opus":0.040905743568594596,"score_gpt":0.3263296163851893,"score_spread":0.2854238728165947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100113682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03836571,0.00005010161,0.95943546,0.0013440398,0.0004655912,0.0002575301,0.000035255667,0.0000043936734,0.000041889056],"genre_scores_gemma":[0.38516024,0.000009583132,0.6146711,0.000097506614,0.00001629699,0.0000043038567,7.172572e-7,0.0000058319633,0.000034397865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99642205,0.0015666859,0.0010728085,0.00022660641,0.00046139577,0.00025045726],"domain_scores_gemma":[0.99381953,0.004575683,0.000843115,0.00034161203,0.00030962593,0.000110449655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025367676,0.0001716451,0.0005783427,0.000043273572,0.00010831832,0.000058447895,0.0007576598,0.00016085319,0.000039322622],"category_scores_gemma":[0.0050173756,0.00009791819,0.00016024371,0.000464549,0.0006657029,0.00022436099,0.00032707152,0.0005018987,0.000001815618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016294362,0.00042102285,0.007003001,0.00040972067,0.00024601206,0.0000063495227,0.0021030493,0.0020502713,0.010137694,0.8501355,0.0032143649,0.12411006],"study_design_scores_gemma":[0.00041493052,0.00006884331,0.37187353,0.00005086557,0.000058913443,0.000033516342,0.000031056104,0.1884865,0.002029106,0.4368431,0.0000150375145,0.00009459136],"about_ca_topic_score_codex":0.00029399217,"about_ca_topic_score_gemma":0.0000021782596,"teacher_disagreement_score":0.4132924,"about_ca_system_score_codex":0.000050720988,"about_ca_system_score_gemma":0.00007980646,"threshold_uncertainty_score":0.60066295},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.013516255470009486,"score_gpt":0.25161436386545444,"score_spread":0.23809810839544496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100163972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027943172,0.00008931469,0.9489827,0.0017444825,0.00017429564,0.00013671692,2.779517e-7,0.00039369985,0.020535309],"genre_scores_gemma":[0.509741,0.000013011341,0.48893535,0.00055166776,0.000033980283,0.000010635383,0.0000010219048,0.000010111157,0.00070321106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861175,0.00003798707,0.00024614722,0.0005354283,0.00022254036,0.00034614874],"domain_scores_gemma":[0.99918294,0.00006246905,0.00005521892,0.00048079382,0.00005568044,0.0001628994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003518295,0.00015424758,0.00016881012,0.00010079432,0.00012490399,0.00019453201,0.0009244811,0.000104122744,0.00001572787],"category_scores_gemma":[0.000079836,0.00012085189,0.00005720155,0.00065400155,0.00007161883,0.00069956196,0.0003745174,0.00025217418,0.000029423434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005439698,0.0001035604,0.0009980056,0.000065317356,0.000028895183,0.00007058447,0.0025660836,0.00039272232,0.00018988454,0.9626735,0.00022177421,0.03268427],"study_design_scores_gemma":[0.0009398107,0.00010537005,0.003230894,0.00011597019,0.000011588898,0.0000728511,0.000020259944,0.03075473,0.0021150613,0.96173656,0.00040513588,0.00049174746],"about_ca_topic_score_codex":0.000041894047,"about_ca_topic_score_gemma":0.000025720741,"teacher_disagreement_score":0.48179784,"about_ca_system_score_codex":0.000042035757,"about_ca_system_score_gemma":0.00008158496,"threshold_uncertainty_score":0.4928197},"labels":[],"label_agreement":null},{"id":"W2100656889","doi":"10.1109/aps.2004.1330331","title":"GA optimization of terminal antennas by the estimation of the population density of probability using dependency trees","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Crossover; UMTS frequency bands; Population; Computer science; Tree (set theory); Mathematical optimization; Genetic algorithm; Algorithm; Estimation of distribution algorithm; Antenna (radio); Convergence (economics); GSM; Probability density function; Mathematics; Statistics; Telecommunications; Artificial intelligence; Combinatorics","score_opus":0.022802231997373672,"score_gpt":0.2723282766672649,"score_spread":0.24952604466989123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100656889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31171325,0.000012177988,0.6879186,0.000117288255,0.000035491692,0.00015245026,0.0000010459116,0.000006868296,0.000042846896],"genre_scores_gemma":[0.53181297,7.310061e-7,0.46816918,0.000008493157,0.0000023460577,5.841746e-7,5.690174e-7,0.0000012588994,0.0000038811304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991599,0.00013557156,0.00028919787,0.00013648195,0.00020836126,0.00007052966],"domain_scores_gemma":[0.9991709,0.00003792135,0.00026933246,0.00038544467,0.00012309436,0.00001330107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048577273,0.00006358338,0.00012438481,0.000024174633,0.000059876347,0.0000111635,0.00030206927,0.0000425217,0.000002106497],"category_scores_gemma":[0.000079301004,0.00003502887,0.00005747814,0.00023941779,0.00006427514,0.000245502,0.000078602956,0.00004535807,3.6360117e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001861429,0.00023191806,0.0131249735,0.00009285778,0.000014930958,2.470249e-7,0.0009966429,0.7843216,0.020603303,0.11842504,0.000004839918,0.062165055],"study_design_scores_gemma":[0.00012763524,0.000027243392,0.022487186,0.000036080764,0.000013763622,0.000008785434,0.000005053332,0.85573065,0.04253366,0.07898848,5.8242442e-8,0.000041417443],"about_ca_topic_score_codex":0.0006442993,"about_ca_topic_score_gemma":0.00006628665,"teacher_disagreement_score":0.22009973,"about_ca_system_score_codex":0.000022558479,"about_ca_system_score_gemma":0.000051173072,"threshold_uncertainty_score":0.14284359},"labels":[],"label_agreement":null},{"id":"W2101504623","doi":"10.2307/3315938","title":"The use of the weighted likelihood in the natural exponential families with quadratic variance","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Exponential family; Mathematics; Natural exponential family; Variance (accounting); Statistics; Quadratic equation; Exponential function; Applied mathematics; Maximum likelihood; Econometrics; Mathematical analysis; Economics; Geometry","score_opus":0.017140805984802488,"score_gpt":0.21533619209035568,"score_spread":0.19819538610555318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101504623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010008941,0.00035392185,0.98632604,0.002610969,0.0005278365,0.00010764551,0.000025950903,0.0000014276711,0.000037263035],"genre_scores_gemma":[0.5796266,0.000032020056,0.4198418,0.00042995476,0.000044075678,0.0000011483646,3.0936687e-7,0.000004976549,0.000019094277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881464,0.00023966911,0.00032391262,0.00008752131,0.00027939252,0.00025488177],"domain_scores_gemma":[0.9986946,0.00037905498,0.00026161523,0.0003446556,0.00020218892,0.00011787896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004947055,0.00009897251,0.00014255659,0.00007226671,0.00023317787,0.00021779146,0.0010245694,0.000030791063,0.0000013434],"category_scores_gemma":[0.0001748949,0.000042805816,0.000040062616,0.00036556498,0.00020832945,0.00021630591,0.000018957384,0.0003620429,4.3130268e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024777719,0.000028844752,0.0005691687,0.000017356371,0.000058686608,0.0003719616,0.009571828,0.00062813074,0.000094966934,0.9231421,0.0025848185,0.062907375],"study_design_scores_gemma":[0.00372946,0.00094179827,0.09085303,0.000879573,0.00019148509,0.0020049457,0.001401477,0.03280996,0.0008781345,0.8428416,0.02269308,0.00077541417],"about_ca_topic_score_codex":0.0026422946,"about_ca_topic_score_gemma":0.061692264,"teacher_disagreement_score":0.5696177,"about_ca_system_score_codex":0.00006909571,"about_ca_system_score_gemma":0.001653629,"threshold_uncertainty_score":0.95542943},"labels":[],"label_agreement":null},{"id":"W2102416536","doi":"10.1145/1143844.1143953","title":"An investigation of computational and informational limits in Gaussian mixture clustering","year":2006,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Computer science; Mixture model; Gaussian; Artificial intelligence; Physics","score_opus":0.01263397822533737,"score_gpt":0.25080274972281363,"score_spread":0.23816877149747626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102416536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09361356,0.000018492077,0.9037374,0.00038818855,0.000027474463,0.000057199104,0.0000010493877,0.000023312523,0.0021333038],"genre_scores_gemma":[0.51943874,4.0767134e-7,0.48037732,0.00014451318,0.00001195469,0.0000013870992,0.0000070213805,0.0000012480795,0.000017412009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941385,0.00004533349,0.00021262601,0.00011634096,0.00012933044,0.00008249541],"domain_scores_gemma":[0.99972415,0.00004089853,0.000059622427,0.00009721321,0.00004015509,0.00003794766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023083246,0.000059916314,0.00007950295,0.00011890838,0.000027080878,0.000048324022,0.00013186812,0.000043762393,0.0000037473073],"category_scores_gemma":[0.0000037029936,0.00005318993,0.000010959881,0.00017663915,0.0000291939,0.00073026575,0.000030275223,0.000052751857,5.9731707e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043529094,0.000028131964,0.006772197,0.00003797718,0.0000027648339,0.0000016647413,0.001491968,0.018421018,0.0016908797,0.92373055,0.00018519907,0.047633287],"study_design_scores_gemma":[0.00019086931,0.0000224422,0.11113922,0.0000129478,6.4759325e-7,0.000009552625,0.0000064980823,0.72275615,0.00067230366,0.16511191,0.000011952847,0.00006551274],"about_ca_topic_score_codex":0.000061476494,"about_ca_topic_score_gemma":0.00008518248,"teacher_disagreement_score":0.75861865,"about_ca_system_score_codex":0.000009474844,"about_ca_system_score_gemma":0.00003620813,"threshold_uncertainty_score":0.21690224},"labels":[],"label_agreement":null},{"id":"W2102502626","doi":"10.1109/glocom.2009.5426029","title":"Fitting the Modified-Power-Lognormal to the Sum of Independent Lognormals Distribution","year":2009,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Log-normal distribution; Matching (statistics); Mathematics; Applied mathematics; Distribution (mathematics); Simple (philosophy); Moment (physics); Random variable; Function (biology); Power (physics); Moment-generating function; Distribution fitting; Mathematical optimization; Probability distribution; Statistics; Mathematical analysis; Physics","score_opus":0.016858720782783262,"score_gpt":0.2672526613254208,"score_spread":0.2503939405426375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102502626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008596807,0.00007317474,0.9708049,0.012123004,0.00021154754,0.00024389206,0.0000052326936,0.00005213992,0.007889277],"genre_scores_gemma":[0.9545429,0.0000049319583,0.042877804,0.0022428439,0.00005701736,0.0000068978707,0.0000016175595,0.0000026364876,0.00026337832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986609,0.00017950886,0.00028416124,0.0002451372,0.0003238209,0.00030642116],"domain_scores_gemma":[0.9989114,0.0001457626,0.000097871794,0.0006763877,0.000094875446,0.000073748815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016489767,0.00011874764,0.0001404949,0.000028127166,0.00020303384,0.00011068869,0.0012611552,0.000060008715,0.000011442908],"category_scores_gemma":[0.00008805169,0.000058078997,0.000085633925,0.00039159783,0.000031688523,0.00023586128,0.00024337972,0.0001795239,0.000008351254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063394546,0.00003897599,0.000045208675,0.0000018038332,0.000007267792,0.000002045297,0.0006993741,0.00065427803,0.00059756683,0.80312204,0.0027049293,0.19212018],"study_design_scores_gemma":[0.001714216,0.0018249901,0.13755597,0.0001329235,0.00007995109,0.00023488434,0.00050434517,0.4027709,0.119152226,0.30337873,0.031048832,0.0016020125],"about_ca_topic_score_codex":0.000038379017,"about_ca_topic_score_gemma":0.000011159047,"teacher_disagreement_score":0.94594604,"about_ca_system_score_codex":0.000019431269,"about_ca_system_score_gemma":0.000040182167,"threshold_uncertainty_score":0.23683928},"labels":[],"label_agreement":null},{"id":"W2102723201","doi":"10.1007/s11634-013-0124-8","title":"Clustering and classification via cluster-weighted factor analyzers","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Pattern recognition (psychology); Covariance matrix; Covariance; Latent variable; Ranking (information retrieval); Fuzzy clustering","score_opus":0.03672495443431135,"score_gpt":0.317044713978554,"score_spread":0.28031975954424265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102723201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00826274,0.0012823791,0.9885162,0.0011922547,0.00006116848,0.00020300556,0.000016070924,0.00004590951,0.00042026024],"genre_scores_gemma":[0.6973604,0.0024368668,0.29979756,0.00012181905,0.000024814304,0.000033326,0.00016209098,0.000006581074,0.000056537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805456,0.00018715094,0.00043363028,0.000901372,0.00020025592,0.00022300241],"domain_scores_gemma":[0.9980693,0.00014173605,0.000239924,0.0013605742,0.000076024306,0.00011248118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044628515,0.0001754733,0.0003039362,0.00041051683,0.000120995726,0.00029751836,0.0007499901,0.00009093597,0.000020960268],"category_scores_gemma":[0.000043814234,0.00015049441,0.000039944596,0.001275117,0.00008412595,0.0032797635,0.0003473224,0.00013516628,0.000009083876],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003864309,0.000037963255,0.013361536,0.000022338945,0.000076498225,4.911369e-7,0.00018569393,0.00001813141,0.0038194186,0.005668062,0.000060021728,0.97674596],"study_design_scores_gemma":[0.00015118535,0.00001068125,0.17107995,0.00000904,0.00007561298,0.0000018818112,0.000040695715,0.8215444,0.00005147794,0.0056193224,0.0012525495,0.00016321716],"about_ca_topic_score_codex":0.00006510895,"about_ca_topic_score_gemma":0.00042499215,"teacher_disagreement_score":0.97658277,"about_ca_system_score_codex":0.00003582383,"about_ca_system_score_gemma":0.000015064449,"threshold_uncertainty_score":0.61369836},"labels":[],"label_agreement":null},{"id":"W2103225616","doi":"10.1109/tip.2006.877522","title":"Fusion of Hidden Markov Random Field Models and Its Bayesian Estimation","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Markov random field; Bayesian probability; Computer science; Artificial intelligence; Markov process; Hidden Markov model; Random field; Markov model; Pattern recognition (psychology); Field (mathematics); Estimation; Markov chain; Mathematics; Machine learning; Statistics; Image segmentation; Image (mathematics); Engineering","score_opus":0.012418922205753214,"score_gpt":0.26291081348713896,"score_spread":0.25049189128138577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103225616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015993329,0.00032647693,0.9958301,0.00045298005,0.000110284214,0.00017761617,0.0000029455944,0.00010062192,0.0013995995],"genre_scores_gemma":[0.53187895,0.000017057098,0.4679142,0.000053148513,0.000012890195,0.000010135087,3.4154132e-7,0.000007119895,0.00010620095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895334,0.00005672496,0.00028533113,0.00031621222,0.00020641519,0.00018196618],"domain_scores_gemma":[0.9994192,0.000109729364,0.00011092283,0.0001987094,0.00010697415,0.00005442311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002750597,0.0001487708,0.00020171056,0.00016855342,0.00021480712,0.0001368506,0.0002015781,0.00008850428,0.00000949201],"category_scores_gemma":[0.000005506093,0.00013677096,0.000060643237,0.00028037347,0.000029388362,0.001164524,0.0000034544653,0.0001614911,0.0000013594696],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004939782,0.00008265238,5.19297e-7,0.00012723249,0.0000051642437,0.0000037154607,0.00032956887,0.0018503766,0.026283914,0.00081247074,0.00003062818,0.97042435],"study_design_scores_gemma":[0.00056286465,0.000042387037,0.00000666158,0.000104792074,0.000017754553,0.000016478736,0.0000045030433,0.7945266,0.17632318,0.028270354,0.0000024467427,0.00012199659],"about_ca_topic_score_codex":0.000031598654,"about_ca_topic_score_gemma":0.0000065176782,"teacher_disagreement_score":0.97030234,"about_ca_system_score_codex":0.000016664142,"about_ca_system_score_gemma":0.000053161963,"threshold_uncertainty_score":0.5577358},"labels":[],"label_agreement":null},{"id":"W2103605202","doi":"10.1109/cvpr.2005.493","title":"MML-Based Approach for High-Dimensional Unsupervised Learning Using the Generalized Dirichlet Mixture","year":2006,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hierarchical Dirichlet process; Dirichlet distribution; Generalized Dirichlet distribution; Minimum description length; Cluster analysis; Pattern recognition (psychology); Mathematics; Expectation–maximization algorithm; Latent Dirichlet allocation; Dimensionality reduction; Computer science; Concentration parameter; Artificial intelligence; Algorithm; Applied mathematics; Topic model; Statistics; Dirichlet's principle; Maximum likelihood","score_opus":0.023036023963940062,"score_gpt":0.25688604639629975,"score_spread":0.2338500224323597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103605202","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068364344,0.00017552075,0.99052495,0.00087288773,0.0001552869,0.0002636883,0.000002239859,0.00014022869,0.0010287738],"genre_scores_gemma":[0.16758554,4.3252368e-7,0.83019197,0.0012865738,0.00018789018,0.000030288917,0.000021556178,0.000015891917,0.00067986513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985413,0.00024222402,0.00021082204,0.00041797632,0.00025542435,0.00033225594],"domain_scores_gemma":[0.99920666,0.0001583739,0.00007685274,0.0004065523,0.00009821313,0.00005334887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006316898,0.00017421786,0.00017909743,0.000060941267,0.00039775405,0.00016493119,0.0005263058,0.00010322781,0.00002033137],"category_scores_gemma":[0.000022595348,0.00011088944,0.00013195735,0.00029523685,0.00004466855,0.00014061785,0.00009419721,0.00016826471,0.0000013304914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031338597,0.000112847665,0.000059548976,0.000026342686,0.00002538126,0.0000036943686,0.00007325617,0.1212638,0.021366216,0.8423642,0.005223293,0.009450063],"study_design_scores_gemma":[0.0007600602,0.000030633706,0.00004894448,0.0000048638776,0.000016257769,0.0000072560183,0.0000023513796,0.973636,0.009176267,0.014887033,0.0012467138,0.00018362518],"about_ca_topic_score_codex":0.000197556,"about_ca_topic_score_gemma":0.000003907015,"teacher_disagreement_score":0.85237217,"about_ca_system_score_codex":0.000020689535,"about_ca_system_score_gemma":0.00008486215,"threshold_uncertainty_score":0.45219404},"labels":[],"label_agreement":null},{"id":"W2104680430","doi":"10.1016/j.tpb.2005.02.004","title":"Ewens’ sampling formula and related formulae: combinatorial proofs, extensions to variable population size and applications to ages of alleles","year":2005,"lang":"en","type":"article","venue":"Theoretical Population Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Sequence (biology); Population; Random variable; Connection (principal bundle); Distribution (mathematics); Mathematical proof; Population size; Sampling (signal processing); Constant (computer programming); Combinatorics; Allele; Statistics; Biology; Genetics; Mathematical analysis; Gene; Demography; Geometry; Computer science","score_opus":0.013133037785403399,"score_gpt":0.3058212339849155,"score_spread":0.2926881961995121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104680430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08565121,0.00007284716,0.9114157,0.001688369,0.00010393579,0.00060531934,0.00000791391,0.0000695718,0.00038515963],"genre_scores_gemma":[0.6160672,0.000006121695,0.3836309,0.00018208922,0.000052495387,0.000027449656,0.000017270208,0.0000063258967,0.000010155588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872565,0.00015068303,0.00040383998,0.00039636804,0.00008909545,0.0002343408],"domain_scores_gemma":[0.99891233,0.0004117863,0.0000912992,0.0003140272,0.000096467826,0.00017407902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005766768,0.00013545463,0.00027317414,0.000107773965,0.00015884556,0.000030953415,0.00017543562,0.00017685138,0.000016219386],"category_scores_gemma":[0.00038407304,0.00011512687,0.000027980197,0.00028911643,0.000084744446,0.00014188408,0.00020476074,0.00010186971,0.000002996543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020794594,0.000027988508,0.0006041736,0.000007772986,0.000006861521,8.4433715e-8,0.00012675636,0.00007879677,0.0036633245,0.9354972,0.000007961691,0.059958246],"study_design_scores_gemma":[0.00029857724,0.00013611025,0.020366823,0.00001692533,0.00001385549,0.000011180639,0.000002863071,0.009221917,0.00021370166,0.9691309,0.0004420464,0.00014512383],"about_ca_topic_score_codex":0.000033639735,"about_ca_topic_score_gemma":0.0000036196907,"teacher_disagreement_score":0.53041595,"about_ca_system_score_codex":0.00002353906,"about_ca_system_score_gemma":0.000009951401,"threshold_uncertainty_score":0.46947378},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.015527838056783252,"score_gpt":0.2711309065625086,"score_spread":0.25560306850572534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105787212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011039294,0.00011176243,0.9978187,0.00040269503,0.00013285114,0.00007879104,0.00005481712,0.00005748868,0.00023893798],"genre_scores_gemma":[0.93872094,0.00013040612,0.060815714,0.00019457127,0.000012509867,0.0000098363835,0.000004297276,0.0000065081404,0.00010518542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985159,0.00020278523,0.00038121684,0.000446557,0.0002422009,0.00021133567],"domain_scores_gemma":[0.9987311,0.0003195851,0.00012866627,0.0005898837,0.00009429403,0.00013651076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004603666,0.00019167797,0.00037172073,0.00058513106,0.00015038831,0.0000719019,0.0004684505,0.00007940357,0.00005343341],"category_scores_gemma":[0.000017078757,0.00015802466,0.00028083147,0.0019206464,0.000075311254,0.00014783414,0.0000065894924,0.000226956,0.0000072545467],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005710248,0.00013921162,0.00022381813,0.000013106866,0.00027466286,0.0000012626516,0.00010397306,0.0008653497,0.00034488013,0.00838962,0.000009174374,0.9896292],"study_design_scores_gemma":[0.00017111666,0.00027140178,0.0021989613,0.000029999941,0.00070760626,0.000011411961,0.0000085129695,0.5001582,0.48093826,0.014856009,0.00022431705,0.00042419124],"about_ca_topic_score_codex":0.0005190182,"about_ca_topic_score_gemma":0.00024044278,"teacher_disagreement_score":0.98920506,"about_ca_system_score_codex":0.000016110609,"about_ca_system_score_gemma":0.000013902615,"threshold_uncertainty_score":0.6444059},"labels":[],"label_agreement":null},{"id":"W2105934955","doi":"","title":"An Infinite Factor Model Hierarchy Via a Noisy-Or Mechanism","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Latent variable; Computer science; Generative model; Latent variable model; Factor analysis; Generative grammar; Factor (programming language); Conditional probability distribution; Hierarchy; Factorial; Artificial intelligence; Bayesian probability; Layer (electronics); Machine learning; Mathematics; Econometrics","score_opus":0.031398412049453414,"score_gpt":0.29528499871180036,"score_spread":0.26388658666234693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105934955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037684867,0.0000470234,0.9934989,0.00035464996,0.00032293983,0.0003115948,0.0000059186177,0.0004863841,0.0012041054],"genre_scores_gemma":[0.8153741,0.0000028378915,0.18251114,0.0018672534,0.00007632085,0.00002032431,0.000008694994,0.0000067134347,0.00013267009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982871,0.00009483152,0.00060581364,0.00023102925,0.00043420884,0.00034704473],"domain_scores_gemma":[0.9987591,0.00002115161,0.0003376668,0.00044898107,0.0002448793,0.0001882375],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00035709993,0.00022512003,0.0002473201,0.00024886566,0.00027079723,0.0012676384,0.00072466454,0.0001382276,0.000002264059],"category_scores_gemma":[0.000024319193,0.000168113,0.000050723953,0.000441298,0.000016303668,0.0098100975,0.00004242819,0.00021279014,0.000020685278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026439997,0.00004023771,0.0000029517953,0.00016784202,0.000004585594,0.000003741764,0.007695881,0.0077065052,0.0033306598,0.08857919,0.0001306047,0.89231133],"study_design_scores_gemma":[0.0002437896,0.00017135369,0.000027808193,0.000052493517,0.0000031644688,0.00007194201,0.00002401556,0.9847783,0.0007237761,0.01331835,0.0003490588,0.00023593471],"about_ca_topic_score_codex":0.000010433759,"about_ca_topic_score_gemma":6.9045274e-7,"teacher_disagreement_score":0.9770718,"about_ca_system_score_codex":0.000048273512,"about_ca_system_score_gemma":0.00014266097,"threshold_uncertainty_score":0.99976915},"labels":[],"label_agreement":null},{"id":"W2107143106","doi":"10.5539/mas.v7n7p1","title":"A Simulation Study of a Parametric Mixture Model of Three Different Distributions to Analyze Heterogeneous Survival Data","year":2013,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Parametric statistics; Weibull distribution; Consistency (knowledge bases); Expectation–maximization algorithm; Mixture model; Estimator; Parametric model; Statistics; Mathematics; Applied mathematics; Stability (learning theory); Population; Maximum likelihood; Computer science","score_opus":0.06642196893052241,"score_gpt":0.3148735748608626,"score_spread":0.24845160593034019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107143106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3628682,0.000011678923,0.6362807,0.000039145863,0.000045466997,0.00062665367,0.000029050765,0.000029273962,0.0000698653],"genre_scores_gemma":[0.8242843,6.4405117e-7,0.1756226,0.000023710878,0.00000972541,0.000042149113,0.000004348675,0.0000067556807,0.0000057675734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971403,0.00005650136,0.00046733048,0.0009653452,0.00096751936,0.00040299466],"domain_scores_gemma":[0.99666387,0.00020112342,0.00020640767,0.0024242252,0.00027911438,0.00022527792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008127865,0.00020619086,0.00039784607,0.00035446062,0.00018523795,0.00014016758,0.00344195,0.000056916506,0.0000035371097],"category_scores_gemma":[0.0001343739,0.00016364604,0.000045842127,0.0020737874,0.00015847465,0.00043697428,0.0016267014,0.00012957279,0.000003959358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016830296,0.0012266028,0.0006389168,0.000020525891,0.000031138057,8.4140805e-7,0.0016719964,0.76082647,0.14204319,0.014787454,0.000012839865,0.0787232],"study_design_scores_gemma":[0.00023930793,0.000098793986,0.0024833416,0.0000052454816,0.00001685318,4.2643927e-7,0.000012674423,0.9526761,0.0027671508,0.04153788,6.6112153e-7,0.00016156008],"about_ca_topic_score_codex":0.00009296526,"about_ca_topic_score_gemma":0.00007289995,"teacher_disagreement_score":0.46141613,"about_ca_system_score_codex":0.000051826122,"about_ca_system_score_gemma":0.00011583238,"threshold_uncertainty_score":0.6673292},"labels":[],"label_agreement":null},{"id":"W2107674477","doi":"10.1093/sysbio/syr131","title":"Phylogenetic Inference via Sequential Monte Carlo","year":2012,"lang":"en","type":"article","venue":"Systematic Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health; U.S. Department of Energy","keywords":"Biology; Inference; Phylogenetic tree; Monte Carlo method; Evolutionary biology; Phylogenetics; Markov chain Monte Carlo; Statistical inference; Statistical physics; Computational biology; Statistics; Artificial intelligence; Mathematics; Computer science; Genetics; Physics","score_opus":0.034380203956319605,"score_gpt":0.3100114945688999,"score_spread":0.2756312906125803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107674477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029423371,0.0017501033,0.9667212,0.00009365875,0.0010368815,0.00040207023,0.0000012959047,0.00008744969,0.0004840071],"genre_scores_gemma":[0.8085758,0.0000032661712,0.19103147,0.00016775283,0.00011091614,0.00006661633,3.9015853e-7,0.0000054788347,0.00003832203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801856,0.00078994676,0.00039427294,0.00026357593,0.00009378567,0.0004398621],"domain_scores_gemma":[0.9987684,0.00016947516,0.00016970946,0.0006977724,0.000056964534,0.00013769703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009915485,0.00016258069,0.00042351658,0.00007567293,0.00006289754,0.000038959857,0.00067507784,0.00015422962,0.000009890611],"category_scores_gemma":[0.00009572833,0.0001156948,0.000083547755,0.00014807812,0.000055736313,0.00013346349,0.00028547022,0.00011374677,0.00008828475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005164251,0.00015784292,0.0126342615,0.010656023,0.00021484257,0.000010179378,0.005335906,0.000036700192,0.04577077,0.910476,0.000065109925,0.014637176],"study_design_scores_gemma":[0.0021711846,0.000933368,0.013365955,0.0045216726,0.0004155578,0.0012422581,0.00014529044,0.45272392,0.0237231,0.49723053,0.00024707717,0.003280103],"about_ca_topic_score_codex":0.000036168494,"about_ca_topic_score_gemma":0.0000036732397,"teacher_disagreement_score":0.7791524,"about_ca_system_score_codex":0.00002680141,"about_ca_system_score_gemma":0.00003400845,"threshold_uncertainty_score":0.4717897},"labels":[],"label_agreement":null},{"id":"W2107710520","doi":"10.1142/s021800141350016x","title":"VARIATIONAL BAYES AND LOCALIZED FEATURE SELECTION FOR STUDENT'S t-MIXTURE MODELS","year":2013,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Robustness (evolution); Mixture model; Feature selection; Artificial intelligence; Pattern recognition (psychology); Gaussian; Bayes' theorem; Feature (linguistics); Bayesian probability; Computer science; Bayesian inference; Student's t-distribution; Model selection; Prior probability; Algorithm; Mathematics","score_opus":0.05910588778361101,"score_gpt":0.32403670522780414,"score_spread":0.2649308174441931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107710520","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015544749,0.00013747255,0.9788026,0.0044842544,0.00073080545,0.00019522096,0.0000141799355,0.000017286658,0.00007343097],"genre_scores_gemma":[0.6826509,0.00020286888,0.3152763,0.0012128248,0.0005643599,0.000023289633,0.0000101708765,0.0000099441595,0.000049300033],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987922,0.00008630193,0.00042043283,0.00022620044,0.0003374311,0.00013747785],"domain_scores_gemma":[0.9982528,0.00020345525,0.00029648974,0.00006025798,0.0010774765,0.00010953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004288724,0.00013270242,0.0001694493,0.00019502778,0.00008609841,0.00048430008,0.0003261884,0.00009307623,0.00006104115],"category_scores_gemma":[0.00007141831,0.00011225954,0.000080297716,0.000090053254,0.000042417647,0.0010575172,0.00006772982,0.00018541607,0.000007510678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031326887,0.00008216786,0.0001512711,0.000008840305,0.00007810979,0.000003414406,0.0005880813,0.000074095275,0.0012924336,0.019423146,0.00029551703,0.9779716],"study_design_scores_gemma":[0.0001682269,0.00015547393,0.0004142958,0.000084829226,0.00001926076,0.00021598615,0.00009551132,0.2684943,0.0044316105,0.7255111,0.0002475161,0.00016189726],"about_ca_topic_score_codex":0.000021091748,"about_ca_topic_score_gemma":0.000012367564,"teacher_disagreement_score":0.9778097,"about_ca_system_score_codex":0.000028541182,"about_ca_system_score_gemma":0.00004071091,"threshold_uncertainty_score":0.4670117},"labels":[],"label_agreement":null},{"id":"W2108268423","doi":"10.1002/sim.745","title":"Logistic discrimination of mixtures of M. tuberculosis and non‐specific tuberculin reactions","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"International Union Against Tuberculosis and Lung Disease","keywords":"Homogeneity (statistics); Tuberculin; Tuberculosis; Logistic regression; Goodness of fit; Tuberculin test; Medicine; Statistics; Mathematics; Pathology","score_opus":0.03422861188760234,"score_gpt":0.32867853000775166,"score_spread":0.2944499181201493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108268423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035715336,0.0006472949,0.9922944,0.0007387587,0.00021239126,0.00011769442,0.00002010359,0.000009461635,0.0023884056],"genre_scores_gemma":[0.519528,0.0013950352,0.4789219,0.00004137913,0.00003621572,0.000004187847,0.000008232653,0.0000046413697,0.00006047926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886024,0.00009479763,0.00044516046,0.00022312716,0.00023995448,0.00013670446],"domain_scores_gemma":[0.9988678,0.00050111226,0.00014213288,0.00030050654,0.00013104203,0.000057389636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006108692,0.00010440136,0.0002958765,0.00021375193,0.000028665067,0.000006400819,0.00019823121,0.000054943874,0.000024742149],"category_scores_gemma":[0.00038106224,0.00008337008,0.0000148887075,0.0003680145,0.00025175526,0.0000802758,0.000051570256,0.00013128662,5.980343e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001884958,0.00010902512,0.0007810204,0.00021777512,0.000018091465,0.000037043897,0.002463696,0.000035645826,0.011649377,0.7325504,0.0020267835,0.2500923],"study_design_scores_gemma":[0.0015717119,0.00059593935,0.07634159,0.0007348145,0.00007774016,0.00008248766,0.000254053,0.061673354,0.0030199103,0.8540999,0.0012389922,0.0003094956],"about_ca_topic_score_codex":0.00026516055,"about_ca_topic_score_gemma":0.00006611496,"teacher_disagreement_score":0.5159564,"about_ca_system_score_codex":0.000021022162,"about_ca_system_score_gemma":0.000019115996,"threshold_uncertainty_score":0.33997336},"labels":[],"label_agreement":null},{"id":"W2108408304","doi":"","title":"Learning mixture models with the latent maximum entropy principle","year":2003,"lang":"en","type":"article","venue":"Journal of Bioresource Management","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Principle of maximum entropy; Latent variable; Inference; Maximum entropy spectral estimation; Maximum likelihood; Expectation–maximization algorithm; Mixture model; Entropy (arrow of time); Maximum likelihood sequence estimation; Estimation theory; Latent variable model; Computer science; Maximum principle; Mathematics; Algorithm; Statistics; Artificial intelligence; Mathematical optimization","score_opus":0.011151578920080226,"score_gpt":0.2257308560792277,"score_spread":0.21457927715914746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108408304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071701836,0.00036640326,0.9843279,0.0021819859,0.00014490922,0.00018285512,1.658065e-7,0.000026536662,0.0055990433],"genre_scores_gemma":[0.30151457,0.00012229137,0.6954105,0.0007789008,0.00011529275,0.000005825589,1.7935689e-7,0.000019701916,0.002032766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822664,0.0003236781,0.0003164439,0.00022676672,0.00058411685,0.00032234323],"domain_scores_gemma":[0.9989073,0.000045063884,0.00039163584,0.00042249318,0.000107406166,0.0001260877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013901097,0.00018212436,0.00022271753,0.00014552906,0.00019154252,0.00020813162,0.0008525585,0.00004657777,0.000011686901],"category_scores_gemma":[0.000009033679,0.000096839576,0.00013953159,0.00033787763,0.000044987024,0.00021640441,0.00017174639,0.00040677548,0.0000051041325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000763315,0.00019452335,0.0003239353,0.000056056026,0.00042024214,0.0005185415,0.00259508,0.053848643,0.0001948624,0.79010236,0.0038281588,0.14784127],"study_design_scores_gemma":[0.0033211948,0.0019449334,0.001493119,0.00027099386,0.00032339324,0.0008799446,0.0005399944,0.117789425,0.0014490159,0.08974101,0.78140944,0.00083753275],"about_ca_topic_score_codex":0.0000010863708,"about_ca_topic_score_gemma":5.1451764e-7,"teacher_disagreement_score":0.7775813,"about_ca_system_score_codex":0.000055624314,"about_ca_system_score_gemma":0.000027095042,"threshold_uncertainty_score":0.39490032},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04733484034962512,"score_gpt":0.320574049874947,"score_spread":0.2732392095253219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108884300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033773598,0.00009992366,0.99703276,0.0020103997,0.00016550066,0.00017766574,0.00006217485,0.00008073885,0.000033094686],"genre_scores_gemma":[0.64595866,0.00017834383,0.35253093,0.00096338574,0.00006212848,0.00002827739,0.000007854842,0.000009935928,0.0002604735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985635,0.000072182476,0.00038387688,0.00056121487,0.00018026115,0.00023895786],"domain_scores_gemma":[0.9990808,0.00013456,0.00010124252,0.00048757816,0.000076419834,0.00011940482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003212591,0.00020627919,0.0002854686,0.00036996076,0.00019137262,0.00012613833,0.00039007684,0.0000792863,0.00003959184],"category_scores_gemma":[0.0000030800359,0.00017789128,0.0002618614,0.0005553485,0.00003632512,0.00027149022,0.0000051316256,0.00019626268,0.000008337287],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056728923,0.00015258077,0.000019010966,0.000010051121,0.00017108893,0.0000010005107,0.00020617501,0.0030220088,0.0004688417,0.00016527255,0.000012979367,0.9957653],"study_design_scores_gemma":[0.00010968858,0.00007250744,0.0002808992,0.000012344547,0.0002351166,0.000009613113,0.0000137787765,0.95828867,0.039756037,0.0005081812,0.0004903215,0.00022286548],"about_ca_topic_score_codex":0.00013005226,"about_ca_topic_score_gemma":0.0006893582,"teacher_disagreement_score":0.99554247,"about_ca_system_score_codex":0.000036779995,"about_ca_system_score_gemma":0.000013964735,"threshold_uncertainty_score":0.72541964},"labels":[],"label_agreement":null},{"id":"W2109450366","doi":"10.1109/icdm.2006.94","title":"Latent Dirichlet Co-Clustering","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Latent Dirichlet allocation; Cluster analysis; Document clustering; Computer science; Correlation clustering; Markov chain Monte Carlo; Dirichlet distribution; Biclustering; Canopy clustering algorithm; CURE data clustering algorithm; Topic model; Hierarchical Dirichlet process; Mixture model; Artificial intelligence; Brown clustering; Data mining; Mathematics; Bayesian probability","score_opus":0.013792331415250342,"score_gpt":0.25279123536545856,"score_spread":0.2389989039502082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109450366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064822068,0.000091036694,0.9163938,0.00079278543,0.000121548364,0.00008220125,4.2387657e-7,0.00022868066,0.075807296],"genre_scores_gemma":[0.48763326,0.0000062962313,0.5103897,0.00035869278,0.0001801952,0.000013290247,5.8156456e-7,0.000010109838,0.0014078605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991176,0.0000044641756,0.00014814317,0.00029453574,0.00017121446,0.00026405687],"domain_scores_gemma":[0.9997018,0.000011488566,0.000055802197,0.00010832272,0.00006518663,0.00005741185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025290422,0.000109867426,0.000116489224,0.000065758184,0.00008740604,0.00020878356,0.00043693456,0.000048258982,0.00000765606],"category_scores_gemma":[0.000009509675,0.00009554563,0.00004427547,0.00021237323,0.00001845014,0.00039348408,0.00013614635,0.0000943603,0.000038852864],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065213158,0.00008662887,0.004393112,0.00008313142,0.000012148704,0.000015223417,0.000802771,0.000009119257,0.027282584,0.8062359,0.032177698,0.12889513],"study_design_scores_gemma":[0.0013000065,0.00020942696,0.020375952,0.00013921018,0.000027003018,0.00025345344,0.000018379982,0.26579824,0.07336018,0.47560462,0.16148235,0.0014311754],"about_ca_topic_score_codex":0.000021810227,"about_ca_topic_score_gemma":8.934014e-7,"teacher_disagreement_score":0.48115104,"about_ca_system_score_codex":0.000025057432,"about_ca_system_score_gemma":0.000011150878,"threshold_uncertainty_score":0.38962376},"labels":[],"label_agreement":null},{"id":"W2109542479","doi":"10.1007/s10651-006-0007-7","title":"Cluster detection using Bayes factors from overparameterized cluster models","year":2007,"lang":"en","type":"article","venue":"Environmental and Ecological Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; University of Minnesota Duluth; University of Waterloo; University of Wisconsin-Madison","keywords":"Reversible-jump Markov chain Monte Carlo; Bayes' theorem; Markov chain Monte Carlo; Partition (number theory); Cluster (spacecraft); Inference; Jump; Mathematics; Statistics; Computer science; Data mining; Bayesian probability; Econometrics; Artificial intelligence; Combinatorics","score_opus":0.02467204485053945,"score_gpt":0.24250598085473477,"score_spread":0.21783393600419532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109542479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4444176,0.000024303108,0.55519515,0.000010861497,0.00013134014,0.00008732584,0.00005273019,0.000021053298,0.000059614915],"genre_scores_gemma":[0.5533706,0.000019545321,0.44626695,0.00027714056,0.000026222518,0.000001501007,0.000009241875,0.000004985712,0.00002381016],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998772,0.00009858064,0.00025159484,0.0003988263,0.00016762801,0.00031137388],"domain_scores_gemma":[0.99911404,0.00047510455,0.000082490806,0.00016540442,0.0000030920644,0.00015985512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025660062,0.00017629395,0.0002042225,0.000031917432,0.0001816536,0.00008516204,0.00016672183,0.00014570447,0.00008960721],"category_scores_gemma":[0.00002021854,0.00013679915,0.0000397805,0.000037496913,0.0001035739,0.00025854236,0.00028600942,0.00015615045,0.00000984307],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048354085,0.001441175,0.022692962,0.00004138844,0.00023727622,0.00022712341,0.0036383749,0.0021744315,0.103095,0.033798397,0.00029059892,0.83187973],"study_design_scores_gemma":[0.0007014563,0.00024648494,0.104295805,0.000004251022,0.000027626616,0.000014857482,0.000040457977,0.6766947,0.0020814647,0.21530262,0.00022236264,0.0003679429],"about_ca_topic_score_codex":0.00004794916,"about_ca_topic_score_gemma":0.000024486708,"teacher_disagreement_score":0.8315118,"about_ca_system_score_codex":0.00008970529,"about_ca_system_score_gemma":0.000003714319,"threshold_uncertainty_score":0.5578507},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.016269489474038484,"score_gpt":0.2627838807639077,"score_spread":0.2465143912898692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109904733","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025928584,0.000066510926,0.99322796,0.0005631827,0.00031716403,0.000025922494,0.000023378296,0.0000016870292,0.0031813185],"genre_scores_gemma":[0.11569555,0.000004386557,0.8836773,0.00033501224,0.00006959558,1.858312e-7,2.518827e-7,0.0000043445452,0.00021338531],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992975,0.00007443649,0.00027966444,0.00005773209,0.00012779397,0.00016285364],"domain_scores_gemma":[0.99915916,0.00013966062,0.00015510629,0.00017478643,0.0001355378,0.00023577079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042668745,0.000058732083,0.00012463998,0.000042000727,0.00008740363,0.000060503233,0.00052111584,0.000024787849,0.00019835599],"category_scores_gemma":[0.00008647767,0.000041033592,0.00003403552,0.00013063333,0.00007866458,0.000111085224,0.000007258458,0.00014614144,0.000007479269],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002296043,0.0000049577384,0.00044824986,0.000013973795,0.00002465161,0.00014657612,0.0018999046,0.0011624044,0.0000057655425,0.13325603,0.0139649175,0.84907025],"study_design_scores_gemma":[0.00069770013,0.00015915325,0.0053042844,0.00022341557,0.00007421098,0.002103501,0.000066218825,0.43057618,0.000111689544,0.53999996,0.020325363,0.0003583523],"about_ca_topic_score_codex":0.0007854907,"about_ca_topic_score_gemma":0.00068028586,"teacher_disagreement_score":0.8487119,"about_ca_system_score_codex":0.000030129306,"about_ca_system_score_gemma":0.0005896848,"threshold_uncertainty_score":0.2171859},"labels":[],"label_agreement":null},{"id":"W2110147390","doi":"10.1002/sim.1266","title":"Binary partitioning for continuous longitudinal data: categorizing a prognostic variable","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Population Health Research Institute; University of Toronto","funders":"","keywords":"Permutation (music); Statistics; Confidence interval; Statistic; Binary data; Binary number; Continuous variable; Variable (mathematics); Test statistic; Mathematics; Interval (graph theory); Set (abstract data type); Computer science; Data set; Statistical hypothesis testing; Combinatorics","score_opus":0.0849101194140717,"score_gpt":0.3404597345364128,"score_spread":0.2555496151223411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110147390","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005455721,0.000948204,0.9958007,0.00088131044,0.0006520023,0.00033322274,0.00007634285,0.000054506396,0.0011991718],"genre_scores_gemma":[0.037132137,0.0000756321,0.96175843,0.0002644472,0.00027541808,0.00005241839,0.000086580025,0.000012769863,0.00034214082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849415,0.00008687391,0.00035835354,0.00047656026,0.00022076849,0.00036326595],"domain_scores_gemma":[0.99815977,0.00091595,0.000103980434,0.00061857066,0.000108600834,0.00009315326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011577393,0.00013745941,0.00030249008,0.00011160656,0.00011738224,0.000050511706,0.00064858526,0.000052080646,0.00005945861],"category_scores_gemma":[0.0013226453,0.00011826371,0.00000980732,0.00034517588,0.00009195604,0.00025034344,0.00017372017,0.0001818083,0.0000064210217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007142792,0.000095530326,0.0015785452,0.00012613121,0.000020668393,0.00015278278,0.0007918238,0.00004198825,0.00015182419,0.8819156,0.044143844,0.070974104],"study_design_scores_gemma":[0.0010447362,0.00036136227,0.00094436074,0.00021379974,0.00004133334,0.00004069153,0.000027592505,0.7072869,0.000010371285,0.28209287,0.0077368123,0.00019915737],"about_ca_topic_score_codex":0.000059541304,"about_ca_topic_score_gemma":0.000020267678,"teacher_disagreement_score":0.70724493,"about_ca_system_score_codex":0.000031623436,"about_ca_system_score_gemma":0.000034937377,"threshold_uncertainty_score":0.4822654},"labels":[],"label_agreement":null},{"id":"W2110162240","doi":"10.2307/3315900","title":"A fast distance‐based approach for determining the number of components in mixtures","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Bayes' theorem; Bayesian probability; Algorithm; Software; Mathematics; Artificial intelligence","score_opus":0.04590796759457682,"score_gpt":0.27772275911419736,"score_spread":0.23181479151962053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110162240","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014159888,0.00007521815,0.99748605,0.000060221297,0.00018565785,0.000098213146,0.00008649067,0.0000010715512,0.00059109234],"genre_scores_gemma":[0.4226462,0.0000010412111,0.5772114,0.0001093941,0.000011981677,0.0000015779501,0.0000014897378,0.000004555156,0.000012382911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909323,0.00012810764,0.0003345125,0.00009443699,0.00012837324,0.00022134077],"domain_scores_gemma":[0.99895847,0.00025910375,0.00023081734,0.00016398035,0.00019485886,0.00019276222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005680498,0.000085698826,0.00019743264,0.00009171281,0.00007119278,0.000054062042,0.00042649987,0.00003678183,0.000004635338],"category_scores_gemma":[0.0002403004,0.000063005806,0.00004666843,0.00015438611,0.0000751341,0.00007575647,0.000005279843,0.00014198472,1.6575072e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019580031,0.000081558,0.0293286,0.000117551346,0.000038706545,0.00008774111,0.0019565371,0.0011203351,0.000084041116,0.9032962,0.0036824131,0.060186785],"study_design_scores_gemma":[0.00757605,0.00048172317,0.050426446,0.000410997,0.00013566719,0.0003848287,0.0002843877,0.48967332,0.0017209371,0.42843157,0.019375227,0.0010988433],"about_ca_topic_score_codex":0.00015164152,"about_ca_topic_score_gemma":0.0007241372,"teacher_disagreement_score":0.488553,"about_ca_system_score_codex":0.000056001878,"about_ca_system_score_gemma":0.0006172577,"threshold_uncertainty_score":0.2569302},"labels":[],"label_agreement":null},{"id":"W2110615995","doi":"10.1007/s00180-009-0165-9","title":"Penalized multinomial mixture logit model","year":2009,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; McMaster University","funders":"","keywords":"Multinomial logistic regression; Linear discriminant analysis; Multinomial probit; Statistics; Mathematics; Mixture model; Logistic regression; Discriminant; Pattern recognition (psychology); Logit; Artificial intelligence; Optimal discriminant analysis; Feature (linguistics); Dimensionality reduction; Multivariate normal distribution; Multivariate statistics; Computer science","score_opus":0.02147472188777151,"score_gpt":0.2951340797064518,"score_spread":0.2736593578186803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110615995","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012317706,0.00006562531,0.99636745,0.0009703377,0.0001705821,0.00013190442,0.00008245987,0.00013353351,0.0019549192],"genre_scores_gemma":[0.106156476,0.0000043909686,0.8913186,0.0020565125,0.000081215425,0.000003326938,0.00005433787,0.00000713586,0.00031798435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986714,0.00008016314,0.00028058275,0.00036637962,0.00034319397,0.00025825726],"domain_scores_gemma":[0.99905235,0.00024312927,0.00010423543,0.00024526526,0.00021825571,0.00013675157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000206128,0.000171577,0.0001981266,0.00007063044,0.00015343561,0.00014996876,0.0005261879,0.000075676944,0.00001739237],"category_scores_gemma":[0.00008857641,0.000161332,0.000053512056,0.00017057752,0.00003810993,0.00019272929,0.000071417766,0.00016662969,0.000036751513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008364494,0.000052795076,0.000004368,0.0000038064281,0.0000067298733,0.000018655572,0.0001844675,0.06984536,0.00005550552,0.7919468,0.011806802,0.12606631],"study_design_scores_gemma":[0.00026681117,0.000030420808,0.00044363082,0.0000032581145,0.0000037786524,0.000010558841,4.4885806e-7,0.5284014,0.000015918069,0.47043,0.000283823,0.000109993205],"about_ca_topic_score_codex":0.0000024054275,"about_ca_topic_score_gemma":7.631217e-7,"teacher_disagreement_score":0.45855603,"about_ca_system_score_codex":0.000040911666,"about_ca_system_score_gemma":0.00015419592,"threshold_uncertainty_score":0.6578928},"labels":[],"label_agreement":null},{"id":"W2112014249","doi":"10.1016/j.jmva.2005.03.011","title":"The likelihood ratio test for homogeneity in bivariate normal mixtures","year":2005,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Mathematics; Likelihood-ratio test; Bivariate analysis; Statistics; Homogeneity (statistics); Econometrics","score_opus":0.01343905847443759,"score_gpt":0.2904631597269461,"score_spread":0.2770241012525085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112014249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004407907,0.00070371066,0.9902625,0.004175889,0.00017680082,0.00012369006,0.0000057729085,0.0000116748515,0.00013203641],"genre_scores_gemma":[0.54365253,0.00008933287,0.45564502,0.00021560474,0.00028747058,0.0000059618023,7.528024e-7,0.000006820566,0.00009648349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997889,0.00028011933,0.0008621189,0.00024290648,0.0003404736,0.00038541795],"domain_scores_gemma":[0.9972427,0.0011320362,0.0006526696,0.00045299897,0.00037852812,0.00014107155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033101928,0.00017911695,0.00047292793,0.00046399148,0.00023945255,0.0002712334,0.001090609,0.000098344324,0.0000062159006],"category_scores_gemma":[0.00055210723,0.00011081438,0.00058791623,0.0012783823,0.000030502062,0.0006126165,0.00010692496,0.00028535526,0.0000024297476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027322076,0.0012323115,0.008426757,0.000025646372,0.0038929535,0.000070205715,0.0037482115,0.023432657,0.041284934,0.05948558,0.001227263,0.8569003],"study_design_scores_gemma":[0.0020833819,0.00023179695,0.029466577,0.000023692965,0.00085729675,0.00003360382,0.000026864269,0.9325833,0.010372662,0.018026216,0.005946825,0.0003477968],"about_ca_topic_score_codex":0.00008494417,"about_ca_topic_score_gemma":0.00035432877,"teacher_disagreement_score":0.90915066,"about_ca_system_score_codex":0.000075560405,"about_ca_system_score_gemma":0.00015175047,"threshold_uncertainty_score":0.4518879},"labels":[],"label_agreement":null},{"id":"W2112924360","doi":"10.1007/s13171-013-0033-0","title":"On simulations from the two-parameter Poisson-Dirichlet process and the normalized inverse-Gaussian process","year":2013,"lang":"en","type":"article","venue":"Sankhya A","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet process; Applied mathematics; Poisson distribution; Inverse; Mathematics; Gaussian process; Simple (philosophy); Process (computing); Inverse Gaussian distribution; Gaussian; Dirichlet distribution; Poisson process; Statistical physics; Mathematical analysis; Statistics; Computer science; Physics; Geometry; Bayesian probability","score_opus":0.013839572028423315,"score_gpt":0.28367124683135003,"score_spread":0.2698316748029267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112924360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21079266,0.00017866242,0.7691097,0.014712964,0.00020412248,0.0009395036,0.0000118642565,0.0001144999,0.003935975],"genre_scores_gemma":[0.9484575,0.0000053822387,0.044851582,0.0062986063,0.00010214732,0.000112558635,0.0000036353645,0.000013339312,0.0001552397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998495,0.00030769312,0.0002199681,0.0004031047,0.00028529466,0.0002889332],"domain_scores_gemma":[0.9978485,0.0011491107,0.00011659592,0.0006867245,0.00010223665,0.000096829936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037733602,0.0001952372,0.00021555185,0.000041330506,0.0003397613,0.0004167469,0.00088053226,0.00006581648,0.00008668299],"category_scores_gemma":[0.00021604165,0.000093810195,0.000065694076,0.00035870235,0.00019032134,0.0004909194,0.00012471835,0.00025752423,0.00005172302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031057786,0.00039112064,0.0042750756,0.000101624864,0.00040819217,0.000019486526,0.07658606,0.0033024126,0.00078532327,0.69358045,0.016853163,0.20338649],"study_design_scores_gemma":[0.0015834221,0.0000312381,0.0017462622,0.000034065564,0.000026188693,0.000005038126,0.0000824497,0.36584368,0.0003255587,0.6297276,0.00039860385,0.00019591187],"about_ca_topic_score_codex":0.00030815863,"about_ca_topic_score_gemma":0.000060453996,"teacher_disagreement_score":0.7376648,"about_ca_system_score_codex":0.000011727821,"about_ca_system_score_gemma":0.00005766188,"threshold_uncertainty_score":0.40186998},"labels":[],"label_agreement":null},{"id":"W2113884043","doi":"10.1109/tnn.2004.839356","title":"Mixtures-of-Experts of Autoregressive Time Series: Asymptotic Normality and Model Specification","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Autoregressive model; Estimator; Series (stratigraphy); Asymptotic distribution; Conditional probability distribution; Mathematics; Covariate; Applied mathematics; Conditional expectation; Multinomial distribution; Model selection; Time series; Linear model; Computer science; Econometrics; Statistics","score_opus":0.014191435877500097,"score_gpt":0.2465642726845874,"score_spread":0.23237283680708729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113884043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063924924,0.00019386396,0.99215657,0.0005299848,0.00020936849,0.00017072634,0.000008022643,0.00006368115,0.00027529913],"genre_scores_gemma":[0.82813996,0.000092810806,0.17131004,0.00012688627,0.000055817,0.00001024842,8.653165e-7,0.000010097033,0.0002532843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988333,0.000117201635,0.0003382245,0.00032210807,0.00018319751,0.00020598483],"domain_scores_gemma":[0.9991006,0.000106037696,0.0001561244,0.000459061,0.000082750776,0.00009542547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017604786,0.00016935928,0.00025564525,0.00008647851,0.00009659427,0.000028785567,0.00030112045,0.0001237207,0.0000127726535],"category_scores_gemma":[0.0000024668402,0.00014701349,0.00010183655,0.0001949649,0.00010430364,0.0004914491,0.0000041346957,0.00019033527,0.0000011733779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006451915,0.00014261568,0.0000035941134,0.000017332408,0.000027343865,0.0000017028631,0.0006191174,0.73851156,0.003903084,0.0021508327,0.00020253319,0.25435573],"study_design_scores_gemma":[0.00020818008,0.00009943367,0.000055281365,0.000027222277,0.000016802056,0.000018252693,0.0000022332463,0.9812207,0.017348513,0.0008376999,0.00003157343,0.00013409663],"about_ca_topic_score_codex":0.0000057661614,"about_ca_topic_score_gemma":0.000005177401,"teacher_disagreement_score":0.8217475,"about_ca_system_score_codex":0.000022481772,"about_ca_system_score_gemma":0.000023742294,"threshold_uncertainty_score":0.59950364},"labels":[],"label_agreement":null},{"id":"W2114442655","doi":"10.1007/s00500-014-1242-8","title":"A hierarchical nonparametric Bayesian approach for medical images and gene expressions classification","year":2014,"lang":"en","type":"article","venue":"Soft Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Interpretability; Mixture model; Artificial intelligence; Machine learning; Model selection; Markov chain Monte Carlo; Feature selection; Outlier; Feature (linguistics); Dirichlet process; Data mining; Generative model; Gaussian process; Bayesian probability; Gaussian; Generative grammar","score_opus":0.02183240981667998,"score_gpt":0.29293820430738976,"score_spread":0.27110579449070976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114442655","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013017268,0.0001405815,0.99574417,0.0009861906,0.00014974498,0.00023235868,0.0000012915758,0.00017275318,0.0012711755],"genre_scores_gemma":[0.40300044,0.0000036346414,0.5964795,0.0002884024,0.00018387877,0.000011564332,0.0000035805192,0.000008815445,0.000020186204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817336,0.00026533214,0.00029657406,0.0005955532,0.0003169685,0.00035218993],"domain_scores_gemma":[0.99802804,0.001108743,0.000103979175,0.00041788004,0.000066798304,0.00027456952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017197009,0.00015369721,0.00023912654,0.00015891274,0.00031708708,0.00016654024,0.0006146083,0.00014777477,0.0000017589223],"category_scores_gemma":[0.0008955529,0.00012928281,0.00007137167,0.00036763508,0.0000922062,0.00013643305,0.0003237479,0.00025861376,0.0000011364687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039724455,0.000066275956,0.00018055672,0.00004051604,0.0000090230415,0.0000011877523,0.00027295382,0.000039266615,0.0015437505,0.10197974,0.0003583798,0.89550436],"study_design_scores_gemma":[0.00036399884,0.000045989556,0.0011854796,0.000024636933,0.0000063341868,0.000040623378,0.000005392805,0.97231275,0.000459173,0.024952663,0.00043940582,0.00016358233],"about_ca_topic_score_codex":0.000003326358,"about_ca_topic_score_gemma":1.4552906e-7,"teacher_disagreement_score":0.97227347,"about_ca_system_score_codex":0.000014600311,"about_ca_system_score_gemma":0.000061907645,"threshold_uncertainty_score":0.5272},"labels":[],"label_agreement":null},{"id":"W2115192403","doi":"10.1111/sjos.12140","title":"Mixture Model Analysis of Partially Rank‐Ordered Set Samples: Age Groups of Fish from Length‐Frequency Data","year":2015,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Mathematics; Estimator; Statistics; Rank (graph theory); Maximization; Simple random sample; Expectation–maximization algorithm; Sample (material); Sampling (signal processing); Set (abstract data type); Sample size determination; Population; Maximum likelihood; Combinatorics; Mathematical optimization; Computer science","score_opus":0.10578928929426698,"score_gpt":0.3274315611435327,"score_spread":0.22164227184926574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115192403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065722708,0.0004283903,0.98537785,0.00021901214,0.00030069222,0.0000873671,0.006890931,0.000009576701,0.00011391917],"genre_scores_gemma":[0.3203612,0.00009784277,0.6791479,0.00009715596,0.00006484783,5.1577234e-7,0.00020128304,0.000011639868,0.000017592936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698,0.0003421361,0.0012169861,0.00035915335,0.0008038618,0.0002978336],"domain_scores_gemma":[0.9959774,0.00036569074,0.0013261253,0.001222093,0.0007483522,0.00036031796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015103461,0.00023383326,0.0010137738,0.00038606956,0.000049279264,0.00008489768,0.0021927822,0.0001245622,0.000024651346],"category_scores_gemma":[0.00052955997,0.00019901223,0.00017165713,0.00087891804,0.00015864936,0.0005703009,0.00027631893,0.0003247555,5.8097584e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011157297,0.0017171614,0.03825684,0.0005354297,0.01497896,0.0023292098,0.051311467,0.041850835,0.008762449,0.41813856,0.1448095,0.27619386],"study_design_scores_gemma":[0.0019226775,0.00048374914,0.0057304413,0.00021284021,0.0022641898,0.00003637565,0.00019921549,0.5781992,0.00038174374,0.40992182,0.00022204377,0.0004256646],"about_ca_topic_score_codex":0.00022193334,"about_ca_topic_score_gemma":0.00027904488,"teacher_disagreement_score":0.5363484,"about_ca_system_score_codex":0.00005395179,"about_ca_system_score_gemma":0.00042888906,"threshold_uncertainty_score":0.8115483},"labels":[],"label_agreement":null},{"id":"W2116501114","doi":"10.7202/602194ar","title":"Échantillonnage de Gibbs et autres applications économétriques des chaînes markoviennes","year":2009,"lang":"fr","type":"article","venue":"L Actualité économique","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université Laval","funders":"","keywords":"Markov chain Monte Carlo; Mathematics; Monte Carlo method; Statistics","score_opus":0.055821021591349634,"score_gpt":0.3105426650046177,"score_spread":0.2547216434132681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116501114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011533781,0.007612958,0.92668366,0.028465534,0.00040243746,0.00075111375,0.000057412355,0.00034835853,0.024144726],"genre_scores_gemma":[0.16483365,0.0052033253,0.7956701,0.0098952,0.00088105135,0.0002290323,0.000014772634,0.000051964133,0.023220921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962072,0.0008925921,0.00073160394,0.0010337043,0.000078538484,0.0010564029],"domain_scores_gemma":[0.99721646,0.00062188675,0.0003302129,0.0011544102,0.00017483781,0.0005022124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001883506,0.00058129005,0.0006712973,0.00024108871,0.0003501721,0.00082128425,0.0012743429,0.00048103457,0.00019214401],"category_scores_gemma":[0.00014889952,0.0006086979,0.00034770695,0.0004123629,0.00036162333,0.0016988731,0.00024782505,0.00048746812,0.00010473314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011115126,0.00016797171,0.00008006012,0.00007712274,0.0000331863,0.00001075138,0.0035979536,0.00002257066,0.00058985804,0.5634187,0.0006584426,0.43133226],"study_design_scores_gemma":[0.0003197753,0.00022150295,0.0027090427,0.00020503854,0.00004127581,0.00015479181,0.00005960983,0.01337105,0.005164554,0.732188,0.24489348,0.0006718937],"about_ca_topic_score_codex":0.00054572267,"about_ca_topic_score_gemma":0.0004566469,"teacher_disagreement_score":0.43066037,"about_ca_system_score_codex":0.00024595403,"about_ca_system_score_gemma":0.00046784643,"threshold_uncertainty_score":0.9996364},"labels":[],"label_agreement":null},{"id":"W2116651711","doi":"10.1080/02331880701829948","title":"Mixture inverse Gaussian distributions and its transformations, moments and applications","year":2009,"lang":"en","type":"article","venue":"Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Inverse Gaussian distribution; Mixture model; Mathematics; Parametric statistics; Gaussian; Inverse; Probabilistic logic; Parametric model; Applied mathematics; Inverse distribution; Transformation (genetics); Statistical model; Distribution (mathematics); Mixture distribution; Probability distribution; Computer science; Heavy-tailed distribution; Statistics; Random variable; Mathematical analysis","score_opus":0.011101108292120713,"score_gpt":0.27139796125992693,"score_spread":0.26029685296780625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116651711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000087760774,0.00030673266,0.99662215,0.0013845843,0.000029321887,0.00020437066,0.00042465076,0.00004336582,0.0008970705],"genre_scores_gemma":[0.0667757,0.00040413783,0.93212575,0.00041015478,0.000029637617,0.000022328624,0.0000633692,0.0000034135053,0.00016551788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994391,0.000032382926,0.00013262057,0.00016784265,0.00008854073,0.00013950604],"domain_scores_gemma":[0.99960107,0.00004127311,0.000034762827,0.00015511339,0.00004440084,0.00012336163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009473553,0.00008527974,0.000086953245,0.000041251318,0.0001936794,0.000087824796,0.0001252265,0.00004242938,0.0000035994185],"category_scores_gemma":[0.000015844147,0.00007893972,0.0000096482145,0.00015284077,0.00002612625,0.00021331562,0.000021599666,0.0000872289,0.0000045367965],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.6946106e-7,0.000017514429,0.000007342465,0.000009820212,0.000003347941,0.0000013553617,0.00023244103,6.0455915e-7,0.000099592835,0.84819394,0.0019206732,0.14951277],"study_design_scores_gemma":[0.0003977943,0.00008046428,0.0042379578,0.000014763402,0.000029547798,0.00003636682,0.00001587838,0.05479115,0.00029649818,0.91081285,0.029042047,0.00024467745],"about_ca_topic_score_codex":0.0000013094772,"about_ca_topic_score_gemma":0.0000034409284,"teacher_disagreement_score":0.14926809,"about_ca_system_score_codex":0.000012551813,"about_ca_system_score_gemma":0.000025303232,"threshold_uncertainty_score":0.32190686},"labels":[],"label_agreement":null},{"id":"W2116719857","doi":"10.1002/cjs.10120","title":"Modal simulation and visualization in finite mixture models","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confidence interval; Statistics; Inference; Modal; Humanities; Mathematics; Statistical inference; Computer science; Algorithm; Artificial intelligence; Philosophy","score_opus":0.05037443672395695,"score_gpt":0.2753435346034728,"score_spread":0.22496909787951583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116719857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015403385,0.00014682084,0.99753016,0.00004388398,0.00016550695,0.00004278311,0.000022317663,0.0000024037113,0.00050580036],"genre_scores_gemma":[0.5343639,0.000008954082,0.46548042,0.00010653957,0.00001841355,1.9171839e-7,9.189878e-7,0.0000039280653,0.000016695602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992461,0.00009251544,0.00030681543,0.00009734284,0.000105618376,0.00015159298],"domain_scores_gemma":[0.99916613,0.000104053695,0.00015766721,0.00010906894,0.00019034895,0.00027274006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040121432,0.00007373053,0.00013804673,0.00026559265,0.00004380861,0.00006220918,0.00019130285,0.000058313057,0.000013526545],"category_scores_gemma":[0.00013278367,0.00006849758,0.00001565835,0.00017086022,0.00003026555,0.00038897252,0.000010300749,0.00012241068,6.607204e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063486864,0.00001080117,0.0011588862,0.000013584894,0.00000879477,0.0002302705,0.0067706276,0.020372173,0.0000072799944,0.9010776,0.0003741165,0.0699695],"study_design_scores_gemma":[0.000135122,0.000044672903,0.0022586756,0.000017643437,0.000004026388,0.000018286186,0.000009016572,0.6612559,0.0000112325215,0.33605158,0.00013460855,0.000059258306],"about_ca_topic_score_codex":0.0006132526,"about_ca_topic_score_gemma":0.0031081713,"teacher_disagreement_score":0.6408837,"about_ca_system_score_codex":0.000041781852,"about_ca_system_score_gemma":0.0003493844,"threshold_uncertainty_score":0.27932504},"labels":[],"label_agreement":null},{"id":"W2116854856","doi":"10.1109/ccece.2009.5090159","title":"Estimation of boundary properties using stochastic differential equations","year":2009,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Stochastic differential equation; Boundary (topology); Brownian motion; Fokker–Planck equation; Dispersion (optics); Applied mathematics; Computer science; Boundary value problem; Differential equation; Stochastic process; Inverse problem; Mathematics; Diffusion; Mathematical optimization; Statistical physics; Algorithm; Mathematical analysis; Physics; Statistics","score_opus":0.047216470950666306,"score_gpt":0.29249720301731097,"score_spread":0.24528073206664466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116854856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013920785,0.00004844593,0.9852472,0.00017613536,0.00009872273,0.000091436494,3.1724983e-7,0.000052334697,0.00036463697],"genre_scores_gemma":[0.58175826,1.7823285e-7,0.41812885,0.000040713858,0.0000119099395,7.0369464e-7,3.059258e-7,0.0000012063066,0.00005787453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994614,0.00003799777,0.0001480333,0.00012376679,0.00013047013,0.00009831485],"domain_scores_gemma":[0.9996612,0.000022144253,0.000048686295,0.00019870617,0.000039814837,0.00002944352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089093126,0.000060870825,0.00009396467,0.000061811974,0.00007534155,0.000066098604,0.00018656894,0.00002645681,0.000008607132],"category_scores_gemma":[0.00003410475,0.00004571694,0.000031824864,0.00012374888,0.000024549927,0.00029760646,0.000032375185,0.00003985254,0.0000017992492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044126546,0.000083174345,6.503843e-7,0.000010072231,0.000007132935,4.679219e-7,0.00071030617,0.013403657,0.039485693,0.49563175,0.000019945444,0.45064273],"study_design_scores_gemma":[0.00007674708,0.000040544375,0.00008051189,0.000017838513,0.0000059179015,0.0000025067288,0.0000019786783,0.9353409,0.0062630787,0.05811197,0.0000011744901,0.00005686974],"about_ca_topic_score_codex":0.000010867591,"about_ca_topic_score_gemma":7.050675e-7,"teacher_disagreement_score":0.9219372,"about_ca_system_score_codex":0.000012973294,"about_ca_system_score_gemma":0.000060530634,"threshold_uncertainty_score":0.18642828},"labels":[],"label_agreement":null},{"id":"W2116887614","doi":"10.1093/biostatistics/kxq079","title":"A particular diffusion model for incomplete longitudinal data: application to the multicenter AIDS cohort study","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Missing data; Covariate; Bayesian probability; Gibbs sampling; Longitudinal data; Multicenter AIDS Cohort Study; Statistics; Sampling (signal processing); Computer science; Econometrics; Mathematics; Medicine; Data mining; Human immunodeficiency virus (HIV)","score_opus":0.09837403590722711,"score_gpt":0.33226683152782255,"score_spread":0.23389279562059545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116887614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003874804,0.000014673783,0.9936572,0.00016497145,0.00017211377,0.0018573597,0.00017248176,0.000047293965,0.000039153812],"genre_scores_gemma":[0.4472567,0.0000018544865,0.55229706,0.0002063234,0.00003551471,0.00014725994,0.000019734776,0.000007566211,0.00002796068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862635,0.00009298721,0.00025656415,0.0005550499,0.00022765493,0.00024141744],"domain_scores_gemma":[0.9980541,0.00011413332,0.000083653984,0.001510293,0.00013225993,0.000105598156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008270429,0.00014007806,0.0001628853,0.000039007922,0.00019323592,0.00008175383,0.001212801,0.0000334014,0.0000018611638],"category_scores_gemma":[0.0001170452,0.00009580039,0.000026482236,0.00015767434,0.000028142033,0.00014895023,0.00065837655,0.00007067902,0.000016832566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020414297,0.0024932802,0.11710702,0.0000840053,0.0002656516,0.000025585268,0.016071232,0.0005396048,0.0011462268,0.4976882,0.013964294,0.35041076],"study_design_scores_gemma":[0.00030850281,0.00015611156,0.04151784,0.000004681583,0.000058506626,0.0000016146703,0.000020173069,0.949558,0.00004837927,0.0074508493,0.0007363123,0.00013901234],"about_ca_topic_score_codex":0.00007477395,"about_ca_topic_score_gemma":0.00009678097,"teacher_disagreement_score":0.9490184,"about_ca_system_score_codex":0.00002154401,"about_ca_system_score_gemma":0.00002953429,"threshold_uncertainty_score":0.39066264},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.040024863115407754,"score_gpt":0.28380174681585485,"score_spread":0.2437768837004471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118036030","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012637307,0.0008613637,0.99591744,0.0023020436,0.00022236364,0.00010589041,0.000084520994,0.0000029741825,0.0003770213],"genre_scores_gemma":[0.1297271,0.00011311586,0.86927795,0.00042627062,0.00011051638,0.0000057203924,9.1154567e-7,0.000008662861,0.0003297623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941486,0.000033632077,0.00018971186,0.0000903016,0.00009235777,0.00017916114],"domain_scores_gemma":[0.99887985,0.00034901244,0.00013163105,0.00015256116,0.00021575687,0.00027117028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030443366,0.00006317952,0.000102849306,0.00007824734,0.00021338668,0.00017521555,0.00032778762,0.000023240547,0.00001621999],"category_scores_gemma":[0.00025671025,0.000043918695,0.000022721142,0.00012257266,0.00006918139,0.0001631905,0.000008341436,0.000105245264,6.4257404e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035784271,0.000016682076,0.0006596954,0.00007004567,0.000068407804,0.00012662711,0.0060405387,0.00021107761,0.000014808743,0.55654454,0.09335211,0.34289187],"study_design_scores_gemma":[0.00068797066,0.00019213837,0.0026103165,0.00004915339,0.000087919056,0.0005655567,0.0002307988,0.5847171,0.00009044166,0.3839567,0.026549742,0.00026215133],"about_ca_topic_score_codex":0.00014585005,"about_ca_topic_score_gemma":0.00084689585,"teacher_disagreement_score":0.58450603,"about_ca_system_score_codex":0.000019452129,"about_ca_system_score_gemma":0.00016914088,"threshold_uncertainty_score":0.17909524},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03295265194356398,"score_gpt":0.34019338394351684,"score_spread":0.30724073199995283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118846274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1529135,0.00009256522,0.84521395,0.0010442463,0.0002815804,0.00039122807,0.000025681313,0.000028841829,0.000008398919],"genre_scores_gemma":[0.60787034,0.000016396474,0.39195392,0.000041849697,0.000079612946,0.000018411674,0.0000040779178,0.000009844076,0.0000055378723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973204,0.00052201544,0.00071828155,0.00050073944,0.00046108302,0.00047748923],"domain_scores_gemma":[0.9893811,0.0095755,0.00027115014,0.00037689944,0.00019493158,0.00020041822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032214313,0.00027669896,0.00040753416,0.0001661405,0.0007432176,0.00044317587,0.0004896882,0.00010507108,0.000013712279],"category_scores_gemma":[0.0031278105,0.00018026934,0.00018263052,0.00042819747,0.00006103428,0.00056034955,0.00018347356,0.00041442367,7.226458e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005536952,0.00013290095,0.031674184,0.00012193797,0.0006891673,0.000018692825,0.0060354983,0.5483811,0.006600622,0.030348541,0.000039383318,0.37540427],"study_design_scores_gemma":[0.0012019854,0.00042881016,0.012342917,0.000023868002,0.00014322202,0.000023619881,0.000030081406,0.84401435,0.000056754598,0.14153948,0.0000011128517,0.00019377591],"about_ca_topic_score_codex":0.000043096214,"about_ca_topic_score_gemma":0.000043442393,"teacher_disagreement_score":0.45495686,"about_ca_system_score_codex":0.000097864715,"about_ca_system_score_gemma":0.00008321444,"threshold_uncertainty_score":0.735117},"labels":[],"label_agreement":null},{"id":"W2119053066","doi":"10.1109/icassp.2004.1327162","title":"Dirichlet-based probability model applied to human skin detection [image skin detection]","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Dirichlet distribution; Latent Dirichlet allocation; Probabilistic logic; Artificial intelligence; Pattern recognition (psychology); Computer science; Generalization; Statistical model; Mixture model; Probability model; Topic model; Mathematics; Statistics","score_opus":0.01788572812261474,"score_gpt":0.2649211283766104,"score_spread":0.24703540025399567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119053066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021641938,0.0000036840167,0.9690582,0.0004700315,0.00012876962,0.00071551214,0.0000014095984,0.0005242804,0.00745617],"genre_scores_gemma":[0.5107933,1.3613945e-7,0.48840117,0.00056346186,0.00004064816,0.000099111414,5.349147e-7,0.000011838986,0.00008975768],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978931,0.00008824433,0.00035505614,0.00087467156,0.0003463329,0.0004425741],"domain_scores_gemma":[0.9985331,0.000036699133,0.00008196458,0.000989719,0.000120989556,0.00023749263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075012725,0.0002688224,0.00025497872,0.00019671545,0.00033638702,0.00020775021,0.0006543941,0.00014683069,0.000011662315],"category_scores_gemma":[0.000032039083,0.00023128215,0.00013227761,0.0007141618,0.000051577408,0.00031692893,0.00017198152,0.00023897285,0.000061436614],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036331876,0.0003857163,0.0000027585972,0.000050191986,0.000015964459,0.0000039224656,0.0006819755,0.037425805,0.39428338,0.12935044,0.000054046064,0.43770948],"study_design_scores_gemma":[0.0006099492,0.00012412506,0.00024259303,0.000006884579,0.000007710446,0.0000038686444,0.0000036417737,0.16748387,0.5819167,0.24912874,0.00012739367,0.00034451045],"about_ca_topic_score_codex":0.00016034968,"about_ca_topic_score_gemma":0.000592359,"teacher_disagreement_score":0.4891514,"about_ca_system_score_codex":0.0002561421,"about_ca_system_score_gemma":0.000101182486,"threshold_uncertainty_score":0.9431412},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08795022052045552,"score_gpt":0.3292867301058385,"score_spread":0.24133650958538294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121034387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024464968,0.00009481388,0.9968132,0.0013495514,0.0005396464,0.0003224388,0.00015990969,0.000033867127,0.00044195767],"genre_scores_gemma":[0.011160701,0.0000038289304,0.9870731,0.0013065274,0.00012132328,0.000017797163,0.0000026111065,0.000034017117,0.00028005385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956539,0.0017738935,0.0008434337,0.00045210193,0.00058159325,0.0006950518],"domain_scores_gemma":[0.9840247,0.013983509,0.0005692849,0.00045108024,0.0005941371,0.00037730506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038279155,0.0003651433,0.0008314525,0.000033748027,0.00046491978,0.00015779151,0.0010053406,0.00019191077,0.000023653283],"category_scores_gemma":[0.0110698175,0.00021610285,0.00028310972,0.0003507345,0.000587829,0.0002202779,0.00018439618,0.0008720869,0.0000016706116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023123749,0.0001277249,0.00015574347,0.000089234614,0.000196594,0.00003375056,0.0003915115,0.0066346927,0.000578999,0.9683393,0.0051728548,0.018048303],"study_design_scores_gemma":[0.0012363071,0.0007174589,0.0007042033,0.00005746749,0.00017997304,0.00022554831,0.00002883649,0.35502288,0.0003026618,0.6397171,0.0015186375,0.0002889274],"about_ca_topic_score_codex":0.000010925416,"about_ca_topic_score_gemma":0.000003130108,"teacher_disagreement_score":0.34838817,"about_ca_system_score_codex":0.00009788113,"about_ca_system_score_gemma":0.0003468573,"threshold_uncertainty_score":0.99726033},"labels":[],"label_agreement":null},{"id":"W2121475256","doi":"10.6000/1929-6029.2012.01.02.05","title":"Two-Part Pattern-Mixture Model for Longitudinal Incomplete Semi-Continuous Toenail Data","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of New Brunswick; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Longitudinal data; Mixture model; Binary data; Logistic regression; Statistics; Mathematics; Computer science; Longitudinal study; Continuous modelling; Dropout (neural networks); Mixed model; Binary number; Econometrics; Data mining; Machine learning","score_opus":0.18374716977075786,"score_gpt":0.48186322428504275,"score_spread":0.2981160545142849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121475256","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006788277,0.0003660277,0.9923705,0.0042517167,0.0015125397,0.00013480852,0.00028498576,0.000007293644,0.0003933421],"genre_scores_gemma":[0.30328283,0.00027663077,0.6940346,0.00052732683,0.0016546872,0.000009505726,0.000037146656,0.000015536052,0.0001617599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942951,0.00040541711,0.0008014582,0.00031447256,0.0035603675,0.0006231489],"domain_scores_gemma":[0.9946236,0.0025848786,0.0002383923,0.00052049814,0.0015209621,0.0005116646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01273235,0.00014010408,0.00031744136,0.00041409497,0.000075627235,0.0001870821,0.004697016,0.000117527015,0.000099750076],"category_scores_gemma":[0.0061583584,0.000113667826,0.000059106726,0.00021476693,0.00017449592,0.0007197596,0.0012807193,0.00120891,0.000008524542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010521499,0.0004067265,0.0028187777,0.000036796144,0.0001185069,0.0004866991,0.0007378757,0.00011732849,0.00006396284,0.2112479,0.07286297,0.7109972],"study_design_scores_gemma":[0.0012879596,0.00010391698,0.0007221134,0.00023501132,0.000007764047,0.0003151853,0.00002108648,0.8689084,0.00004089995,0.11875268,0.009463063,0.00014193727],"about_ca_topic_score_codex":0.000046096124,"about_ca_topic_score_gemma":0.000070392176,"teacher_disagreement_score":0.86879104,"about_ca_system_score_codex":0.0001743709,"about_ca_system_score_gemma":0.0006638481,"threshold_uncertainty_score":0.8728303},"labels":[],"label_agreement":null},{"id":"W2121665983","doi":"10.1007/978-3-642-24965-5_58","title":"Spatial Finite Non-gaussian Mixture for Color Image Segmentation","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Mixture model; Image segmentation; Pattern recognition (psychology); Segmentation; Computer vision; Expectation–maximization algorithm; Scale-space segmentation; Maximization; Pixel; Gaussian; Image (mathematics); Maximum likelihood; Mathematics; Mathematical optimization; Statistics","score_opus":0.01966009758619449,"score_gpt":0.2684416241560063,"score_spread":0.2487815265698118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121665983","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006359151,0.0001465744,0.9907213,0.00066868035,0.0026039844,0.0011587624,0.000027947917,0.00013101792,0.0045353654],"genre_scores_gemma":[0.010309841,0.000029430721,0.9862833,0.0017921748,0.00073321804,0.000055765086,0.000017117287,0.000052649993,0.0007265108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960658,0.000051663694,0.0005994379,0.0018093468,0.0006738531,0.0007999025],"domain_scores_gemma":[0.99712455,0.0005530943,0.00042388227,0.0013246455,0.00033020912,0.0002435992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010725376,0.0006750393,0.0006622756,0.00068324816,0.00033543794,0.00055546296,0.0029241133,0.0005286374,0.000034523928],"category_scores_gemma":[0.000092882285,0.0005925288,0.0002447573,0.0003873993,0.0005138184,0.00076542964,0.00079346396,0.0006993196,0.00003309866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023669963,0.000033117693,0.000003756873,0.00007369736,0.000016215963,0.00005304472,0.0013411483,0.00044905054,0.0010540049,0.027047997,0.0000991577,0.9698051],"study_design_scores_gemma":[0.00060192804,0.00039328804,0.000033811837,0.0002450495,0.000022966771,0.00004171391,9.273654e-8,0.49939376,0.008955447,0.48829013,0.0011931241,0.00082869205],"about_ca_topic_score_codex":0.00004422144,"about_ca_topic_score_gemma":0.00008922633,"teacher_disagreement_score":0.96897644,"about_ca_system_score_codex":0.00021251726,"about_ca_system_score_gemma":0.00056466245,"threshold_uncertainty_score":0.9996526},"labels":[],"label_agreement":null},{"id":"W2121713677","doi":"10.1093/biostatistics/kxq067","title":"Functional mixture regression","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Regression; Functional principal component analysis; Regression analysis; Computer science; Principal component analysis; Functional data analysis; Scalar (mathematics); Linear regression; Artificial intelligence; Machine learning; Econometrics; Mathematics; Statistics","score_opus":0.015400804457123302,"score_gpt":0.2671184447815994,"score_spread":0.2517176403244761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121713677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036985628,0.000035296533,0.99342406,0.0010153805,0.0019285121,0.00004919361,0.000016308672,0.000089579524,0.0030718173],"genre_scores_gemma":[0.04736201,0.0000062676263,0.9507889,0.0004961089,0.0002177587,0.0000029207868,0.000009022011,0.000006441692,0.0011105554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993039,0.000033599885,0.000110270834,0.00022327348,0.00017440964,0.00015454233],"domain_scores_gemma":[0.9992948,0.00010432858,0.00004901352,0.00037724143,0.00007813203,0.00009644566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017397254,0.00009409017,0.00008218046,0.000041843417,0.00009947536,0.00007572865,0.00028935933,0.00009242862,0.00007460444],"category_scores_gemma":[0.00011597344,0.000070519425,0.000027721922,0.00013099417,0.000037973256,0.0001056461,0.000088409695,0.00023436887,0.000064401254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020108582,0.000016641681,0.00006017929,0.000003951957,0.000002671268,0.000012452653,0.000046232737,2.203669e-7,0.011973201,0.77519184,0.050330747,0.16235985],"study_design_scores_gemma":[0.0006090283,0.00010173925,0.01710529,0.000027796888,0.00001625632,0.0001754477,0.0000047379035,0.03474798,0.017222308,0.70572364,0.22368376,0.0005820002],"about_ca_topic_score_codex":0.000002801586,"about_ca_topic_score_gemma":0.000005601333,"teacher_disagreement_score":0.17335302,"about_ca_system_score_codex":0.0000056378585,"about_ca_system_score_gemma":0.000052296684,"threshold_uncertainty_score":0.28756985},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.037330696542404354,"score_gpt":0.3100610288616286,"score_spread":0.2727303323192243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123094878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014673691,0.000044103326,0.9944399,0.0005430471,0.0017299937,0.00036991143,0.000026850095,0.00023137711,0.0011474658],"genre_scores_gemma":[0.60355043,5.0269267e-7,0.39561713,0.00037597885,0.00028778872,0.00003141219,0.000071290924,0.0000074815753,0.000057994588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986669,0.000045310277,0.00048371145,0.00024851476,0.00027976005,0.00027579226],"domain_scores_gemma":[0.99857795,0.00009548951,0.00028665035,0.0007376051,0.00019700605,0.00010531085],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00066921965,0.00015045748,0.00018948785,0.00011974561,0.00027214267,0.0012033855,0.0013459979,0.00012581272,0.0000016562446],"category_scores_gemma":[0.00019869137,0.00011869318,0.000034563807,0.000234063,0.0000387472,0.0052841324,0.00021484007,0.00028829178,0.0000055662676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008552557,0.0000062452455,0.000016647244,0.00025167273,0.0000046287523,5.2392886e-7,0.0010006508,0.00005574284,0.0012700028,0.046111964,0.0013686792,0.9499047],"study_design_scores_gemma":[0.00029661617,0.000022480786,0.00013264421,0.000034029294,0.000006430737,0.000105632455,0.000019047337,0.9771347,0.00023193208,0.003097704,0.01875703,0.00016172322],"about_ca_topic_score_codex":0.000016504384,"about_ca_topic_score_gemma":0.000008229025,"teacher_disagreement_score":0.977079,"about_ca_system_score_codex":0.000010036752,"about_ca_system_score_gemma":0.00011589984,"threshold_uncertainty_score":0.99983346},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.029084159447461153,"score_gpt":0.2861228390117631,"score_spread":0.25703867956430193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123782934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021811429,0.00010815488,0.99887586,0.00023720489,0.0002176104,0.00013274941,0.000013715365,0.000047936494,0.00014868719],"genre_scores_gemma":[0.8214547,0.00015242066,0.17777926,0.00051560154,0.000011614255,0.0000111370455,6.965864e-7,0.000008231679,0.000066318265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985626,0.00023826893,0.00035521374,0.00037325616,0.00022997582,0.00024068155],"domain_scores_gemma":[0.9991659,0.0001149367,0.00007931972,0.00048628534,0.000052543488,0.00010102717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059513096,0.00020159458,0.00024770814,0.00027946764,0.00040334737,0.00023221808,0.00037611797,0.00005954918,0.0000643755],"category_scores_gemma":[0.000002754563,0.0001393182,0.0002348133,0.0009781569,0.000042787033,0.00028803,0.0000029602415,0.00026410227,0.0000054251536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014889641,0.000045727505,0.000007702791,0.000006682381,0.00022293186,0.0000042322463,0.001386561,0.022800252,0.00012788341,0.0011818826,7.296e-7,0.9742139],"study_design_scores_gemma":[0.00006331199,0.00003396813,0.000022970242,0.000012329797,0.00027791265,0.000046783796,0.00008598133,0.9546159,0.043058097,0.0015239598,0.000068785106,0.00018998311],"about_ca_topic_score_codex":0.00036657695,"about_ca_topic_score_gemma":0.0005305489,"teacher_disagreement_score":0.97402394,"about_ca_system_score_codex":0.000026489532,"about_ca_system_score_gemma":0.000024245246,"threshold_uncertainty_score":0.5681231},"labels":[],"label_agreement":null},{"id":"W2124310882","doi":"10.48550/arxiv.1206.3294","title":"Flexible Priors for Exemplar-based Clustering","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Prior probability; Cluster analysis; Dirichlet process; Computer science; Dirichlet distribution; Similarity (geometry); Data mining; Artificial intelligence; Pairwise comparison; Machine learning; Mathematics; Bayesian probability","score_opus":0.1067688121327724,"score_gpt":0.2170292362896167,"score_spread":0.11026042415684431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124310882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0132417455,0.00003984815,0.9831911,0.000120313765,0.00036367343,0.00018971923,0.0000019429574,0.00018221835,0.0026694757],"genre_scores_gemma":[0.7550093,0.0000028904924,0.24362735,0.00023008422,0.00006339465,9.219979e-7,9.571073e-7,0.0000089972955,0.0010561063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903774,0.00006405103,0.00009118802,0.00034129852,0.00004201067,0.00042370034],"domain_scores_gemma":[0.99911773,0.000096328746,0.000061771265,0.00048813314,0.00004999063,0.00018604778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038179793,0.00012992296,0.00013804308,0.00011143796,0.00015528216,0.00004243418,0.00059029576,0.00007733478,0.000011138495],"category_scores_gemma":[0.000018798492,0.000137855,0.00011188072,0.00036358854,0.000025283618,0.00064660533,0.00014875976,0.00008362432,0.000024915811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047559362,0.00012681911,0.0019769415,0.000052446885,0.00002680054,0.000015771913,0.00034257816,0.0060421233,0.0013320267,0.97518533,0.000716581,0.014135021],"study_design_scores_gemma":[0.0014433414,0.00012810795,0.00087208505,0.000034341014,0.00004531828,0.000006753546,0.0000332377,0.931705,0.010723599,0.035697594,0.018740144,0.0005704659],"about_ca_topic_score_codex":0.000009314744,"about_ca_topic_score_gemma":0.0000036487756,"teacher_disagreement_score":0.93948776,"about_ca_system_score_codex":0.000057923382,"about_ca_system_score_gemma":0.00004647667,"threshold_uncertainty_score":0.5621564},"labels":[],"label_agreement":null},{"id":"W2125501900","doi":"10.5705/ss.2010.062","title":"Semiparametric mixture of binomial regression with a degenerate component","year":2011,"lang":"en","type":"article","venue":"Statistica Sinica","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Component (thermodynamics); Semiparametric regression; Binomial regression; Econometrics; Mathematics; Statistics; Binomial (polynomial); Regression; Negative binomial distribution; Regression analysis; Poisson distribution; Physics","score_opus":0.03833413702423937,"score_gpt":0.26995462710201973,"score_spread":0.23162049007778035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125501900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003786053,0.00013183759,0.991529,0.000089574874,0.00018763707,0.00014974677,0.000030701303,0.000054053577,0.004041437],"genre_scores_gemma":[0.3858595,0.000015820768,0.6139235,0.000072174014,0.000019476607,0.000005887294,0.0000029021458,0.000008244857,0.00009253266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985525,0.00020450432,0.00032082337,0.00039982036,0.00026031927,0.0002620115],"domain_scores_gemma":[0.99863213,0.00025006634,0.00021055821,0.00063764356,0.00011874656,0.00015085473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032688177,0.00017198334,0.00031739977,0.00014091992,0.00006849972,0.00002920412,0.00056820695,0.00007984159,0.000043938624],"category_scores_gemma":[0.0000869539,0.00011449928,0.000047651232,0.0005114761,0.00013213597,0.00012029302,0.00014215078,0.00016551263,0.00000738095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034703015,0.0006329985,0.0010074616,0.0001138257,0.00012856601,0.00017374972,0.0026634196,0.000014624529,0.0067905337,0.75973064,0.010749355,0.21764779],"study_design_scores_gemma":[0.009879994,0.008179362,0.07146094,0.0012996973,0.00052821886,0.0005826106,0.00007611207,0.24608544,0.23053107,0.41617987,0.011240881,0.003955816],"about_ca_topic_score_codex":0.00006844839,"about_ca_topic_score_gemma":0.0000075444386,"teacher_disagreement_score":0.38207343,"about_ca_system_score_codex":0.000016342676,"about_ca_system_score_gemma":0.00012352783,"threshold_uncertainty_score":0.4669145},"labels":[],"label_agreement":null},{"id":"W2126417106","doi":"","title":"Bias of the Maximum Likelihood Estimators of the Two-Parameter Gamma Distribution Revisited","year":2009,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Estimator; Statistics; Mathematics; Maximum likelihood; Distribution (mathematics); Gamma distribution; Econometrics; Mathematical analysis","score_opus":0.03583690011623096,"score_gpt":0.3191019341904841,"score_spread":0.28326503407425313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126417106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42155686,0.00075071555,0.5408598,0.0039450387,0.0020964383,0.0039806888,0.0003445133,0.000096127354,0.026369795],"genre_scores_gemma":[0.87545985,0.0012102872,0.122755215,0.00015505,0.000121806326,0.00006364325,0.000016537002,0.000034506964,0.00018312054],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960273,0.001293736,0.0008876418,0.0007758561,0.00043513972,0.00058034784],"domain_scores_gemma":[0.99538743,0.00074103585,0.0005912293,0.0029557867,0.00021611663,0.00010838442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003981954,0.00028155727,0.0006029685,0.00017054101,0.00012408342,0.00012765003,0.003330625,0.0003307226,0.0000064538062],"category_scores_gemma":[0.0011847827,0.00018549319,0.00044327902,0.00046497938,0.00038312428,0.000111215224,0.002870295,0.0014900177,0.0000011352112],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003198342,0.00014952316,0.0039332337,0.0002214013,0.000071500996,0.000004130843,0.00035517814,0.0021658582,0.00033645792,0.02156825,0.00016291831,0.97099954],"study_design_scores_gemma":[0.0011888633,0.0001886632,0.049473688,0.0021073825,0.000048760907,0.00003706634,0.000046441222,0.25968447,0.015651625,0.666717,0.0039999466,0.00085608306],"about_ca_topic_score_codex":0.00006117611,"about_ca_topic_score_gemma":0.00002863652,"teacher_disagreement_score":0.9701435,"about_ca_system_score_codex":0.00035606298,"about_ca_system_score_gemma":0.00065024075,"threshold_uncertainty_score":0.75641924},"labels":[],"label_agreement":null},{"id":"W2127310938","doi":"10.6000/1929-6029.2014.03.02.10","title":"Testing the Equivalence of Survival Distributions using PP- and PPP-Plots","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Mathematics; Wilcoxon signed-rank test; Equivalence (formal languages); Null hypothesis; Hazard ratio; Log-rank test; Plot (graphics); Survival analysis; Population; Hazard; Mann–Whitney U test; Demography; Discrete mathematics; Confidence interval; Biology","score_opus":0.17419176540506606,"score_gpt":0.4780635370323231,"score_spread":0.3038717716272571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127310938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013060817,0.00014166057,0.98402494,0.0019636548,0.00039384628,0.00003586755,0.000016825772,0.000002076818,0.00036029224],"genre_scores_gemma":[0.5566262,0.00012831253,0.44304153,0.00003871537,0.0001560801,6.0019477e-7,4.585251e-7,0.0000029217815,0.00000519087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961916,0.00069906644,0.0004737117,0.0001187614,0.0023158044,0.00020105261],"domain_scores_gemma":[0.9907352,0.0072833584,0.00017567755,0.00013874333,0.0015166434,0.00015043082],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010453185,0.000055946985,0.00015301703,0.00014774522,0.00007108467,0.00008381902,0.0013356865,0.00004805111,0.000015843523],"category_scores_gemma":[0.02276293,0.000037578575,0.000021530783,0.00030048302,0.00039465178,0.00012707578,0.00042502672,0.00066394906,5.9241705e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012239611,0.000054334603,0.0017932248,0.000013100199,0.000017090058,0.00009521311,0.00017719711,0.000024900755,0.0007695328,0.6372554,0.00019317633,0.35959464],"study_design_scores_gemma":[0.00051028,0.00016289028,0.017709455,0.00043958565,0.0000045799607,0.00026484227,0.000035981793,0.4556212,0.00025607125,0.5242517,0.0006722731,0.0000711175],"about_ca_topic_score_codex":0.00008477766,"about_ca_topic_score_gemma":0.000011824319,"teacher_disagreement_score":0.5435654,"about_ca_system_score_codex":0.00006397399,"about_ca_system_score_gemma":0.00038492377,"threshold_uncertainty_score":0.98546875},"labels":[],"label_agreement":null},{"id":"W2127538895","doi":"10.1109/bsc.2010.5473011","title":"A Bayesian approach for SAR images segmentation and changes detection","year":2010,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Mixture model; Synthetic aperture radar; Computer science; Outlier; Segmentation; Image segmentation; Pattern recognition (psychology); Speckle noise; Context (archaeology); Gaussian; Gaussian noise; Noise (video); Computer vision; Gaussian process; Radar imaging; Scale-space segmentation; Speckle pattern; Image (mathematics); Radar; Geography","score_opus":0.0140290451191239,"score_gpt":0.265875286648329,"score_spread":0.2518462415292051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127538895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008125907,0.000023331817,0.9963058,0.00048839167,0.00016303947,0.00026896433,0.0000011667071,0.00008927962,0.0018474257],"genre_scores_gemma":[0.15955226,0.0000053276326,0.8398536,0.00020196073,0.00007707163,0.00003282159,0.000001255133,0.0000047375247,0.0002710028],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99948144,0.00002470829,0.00006301554,0.00024486057,0.000062312654,0.00012365429],"domain_scores_gemma":[0.99967855,0.00003606483,0.00002994867,0.00017073198,0.00003245421,0.000052238775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029879512,0.00007263655,0.00007196532,0.000056521647,0.00009513863,0.000111675465,0.00012583763,0.00005374589,0.0000030355648],"category_scores_gemma":[0.000014115591,0.000058339218,0.000019477246,0.000081307786,0.000019923244,0.00022568632,0.000039952556,0.00006809465,4.5540324e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025749166,0.000012764009,0.000013397282,0.000015192533,0.0000035633643,1.349003e-7,0.00019083677,4.4693888e-7,0.18142654,0.01907444,0.00009079904,0.7991693],"study_design_scores_gemma":[0.0004889436,0.00014665285,0.0003774121,0.0000023379173,0.00001119139,0.000036982285,0.000036284535,0.43259403,0.5227532,0.042136163,0.0011895758,0.00022725893],"about_ca_topic_score_codex":0.000012224788,"about_ca_topic_score_gemma":0.000029946455,"teacher_disagreement_score":0.798942,"about_ca_system_score_codex":0.000004148606,"about_ca_system_score_gemma":0.000007236876,"threshold_uncertainty_score":0.23790042},"labels":[],"label_agreement":null},{"id":"W2127722563","doi":"10.5539/jmr.v3n1p27","title":"Quasi-Stationary Distributions in Linear Birth and Death Processes","year":2011,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Birth–death process; Stationary distribution; Stationary process; Distribution (mathematics); Applied mathematics; Statistics; Mathematical analysis; Demography; Markov chain; Population","score_opus":0.20834616666002373,"score_gpt":0.4179441258010022,"score_spread":0.20959795914097848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127722563","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032382544,0.000380346,0.96584666,0.00033187572,0.000031567197,0.000079738405,0.0000024993644,0.000005656215,0.0009390944],"genre_scores_gemma":[0.19582973,0.0002723385,0.8037305,0.000008390646,0.000028880564,0.0000032483952,1.7619371e-7,0.0000047109475,0.00012204834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987326,0.0001632936,0.00034367497,0.00010019388,0.00045866013,0.00020154758],"domain_scores_gemma":[0.9985279,0.000490442,0.00011940659,0.0001727091,0.00057994854,0.00010960417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030885772,0.000061142535,0.00016018945,0.00030648615,0.00007613152,0.00005480711,0.00045552413,0.00004218026,0.000011054116],"category_scores_gemma":[0.00078830065,0.00004438588,0.000025825853,0.0004918722,0.00004782427,0.0003492646,0.0001333225,0.00035045124,0.0000039613956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028963175,0.002408333,0.0024118416,0.0008628039,0.000040551724,0.00029738838,0.01928876,0.0000050489666,0.000384973,0.94788265,0.00069982145,0.025688859],"study_design_scores_gemma":[0.0003662055,0.00046569802,0.0018612919,0.00024170356,0.000003964658,0.00033229016,0.00031723682,0.02030418,0.0014547539,0.97413963,0.00041271216,0.000100361074],"about_ca_topic_score_codex":0.0000075908465,"about_ca_topic_score_gemma":0.0000059413674,"teacher_disagreement_score":0.16344719,"about_ca_system_score_codex":0.00003080227,"about_ca_system_score_gemma":0.0002933754,"threshold_uncertainty_score":0.18100037},"labels":[],"label_agreement":null},{"id":"W2127756818","doi":"10.1002/047134608x.w8248","title":"Recognition and Clustering of Dirichlet Mixtures","year":2015,"lang":"en","type":"other","venue":"Wiley Encyclopedia of Electrical and Electronics Engineering","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Cluster analysis; Mixture model; Categorization; Dirichlet series; Generalized Dirichlet distribution; Latent Dirichlet allocation; Series (stratigraphy); Mathematics; Hierarchical Dirichlet process; Mixing (physics); Computer science; Artificial intelligence; Pattern recognition (psychology); Applied mathematics; Topic model; Mathematical analysis; Physics","score_opus":0.009800599907814121,"score_gpt":0.2153075056016622,"score_spread":0.20550690569384808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127756818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000204264,0.04315867,0.91463256,0.000028609033,0.00009501689,0.00012738873,0.0000068545696,0.00010242849,0.04164421],"genre_scores_gemma":[0.011101026,0.08646422,0.8871398,0.00008098435,0.0005184647,0.000035229135,0.000024691062,0.000350161,0.014285432],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901104,0.000029028904,0.0002246064,0.00027679285,0.00015586842,0.00030266203],"domain_scores_gemma":[0.9994927,0.00006441818,0.000109149565,0.00017908587,0.00003845126,0.00011621475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020927064,0.00019495584,0.0003513248,0.00025341637,0.000012297824,0.000014605676,0.0001875747,0.00016783594,0.000005270772],"category_scores_gemma":[0.00006916534,0.00018099399,0.0000347404,0.00035089045,0.000022818325,0.000077681674,0.00008864381,0.00022047866,5.0981134e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023888737,0.00009359348,0.000039729966,0.0005599908,0.00016576803,0.0000104351275,0.0003750438,0.000057226913,0.003970698,0.0257267,0.026766822,0.9422101],"study_design_scores_gemma":[0.002199733,0.0019821944,0.00013869061,0.001311741,0.00025906207,0.0002862656,0.000003984961,0.30692402,0.0043511754,0.061103575,0.6190932,0.0023464118],"about_ca_topic_score_codex":0.000023582645,"about_ca_topic_score_gemma":0.0000054892585,"teacher_disagreement_score":0.9398637,"about_ca_system_score_codex":0.000017602448,"about_ca_system_score_gemma":0.000062157786,"threshold_uncertainty_score":0.7380721},"labels":[],"label_agreement":null},{"id":"W2127940039","doi":"10.1016/s0019-0578(00)00016-1","title":"Probability density estimation using incomplete data","year":2000,"lang":"en","type":"article","venue":"ISA Transactions","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Expectation–maximization algorithm; Probability density function; Density estimation; Missing data; Mixture model; Unsupervised learning; Likelihood function; Data set; Function (biology); Convergence (economics); Mathematics; Probability mass function; Maximization; Artificial intelligence; Computer science; Estimation theory; Statistics; Maximum likelihood; Mathematical optimization","score_opus":0.132970531699671,"score_gpt":0.32065288459172264,"score_spread":0.18768235289205165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127940039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011525707,0.00001858274,0.9868212,0.00043129062,0.00014070624,0.000157158,0.0000196872,0.00015915105,0.0007265611],"genre_scores_gemma":[0.2941275,0.000004112603,0.7056682,0.000094195355,0.000018788243,0.0000027345902,0.0000048849365,0.0000040076948,0.00007557756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989903,0.00012211439,0.00017222227,0.0004031055,0.00014181738,0.00017044776],"domain_scores_gemma":[0.9986579,0.0000509373,0.00002641469,0.0011571569,0.000033632245,0.000073989875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036295122,0.0000951834,0.00011584374,0.000036930134,0.00025791864,0.000090250745,0.0006304304,0.000052203017,0.00017426646],"category_scores_gemma":[0.000007849162,0.00009264271,0.000041094674,0.0002703071,0.00004347923,0.00095590093,0.000019009043,0.00013530033,0.00003115249],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004636794,0.00008908207,0.000011496388,0.000012997602,0.000013578371,0.0000027392987,0.00031221882,0.0062374882,0.0007293515,0.0039427076,0.000050612387,0.9885931],"study_design_scores_gemma":[0.000112234804,0.0000100728685,0.0005793565,0.000008923266,0.000018442963,0.00004165154,0.0000010325178,0.94999725,0.0004251533,0.047535226,0.0011544506,0.00011622749],"about_ca_topic_score_codex":0.00018022985,"about_ca_topic_score_gemma":0.00007120749,"teacher_disagreement_score":0.9884769,"about_ca_system_score_codex":0.00003776523,"about_ca_system_score_gemma":0.00006821362,"threshold_uncertainty_score":0.377786},"labels":[],"label_agreement":null},{"id":"W2128053994","doi":"10.1093/jhered/ess038","title":"FLOCK Provides Reliable Solutions to the “Number of Populations” Problem","year":2012,"lang":"en","type":"article","venue":"Journal of Heredity","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Flock; Markov chain Monte Carlo; Partition (number theory); Biology; Genotype; Markov chain; Statistics; Amplified fragment length polymorphism; Computer science; Genetic diversity; Mathematics; Monte Carlo method; Combinatorics; Genetics; Ecology","score_opus":0.05820788907426431,"score_gpt":0.32329572724729544,"score_spread":0.2650878381730311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128053994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012796655,0.0002886239,0.97977954,0.00460115,0.0010371242,0.000110523775,0.0000018612557,0.000009448995,0.0013750654],"genre_scores_gemma":[0.38329726,0.000005308845,0.6158783,0.00013396316,0.00047729764,0.0000021779872,9.6113936e-8,0.000003401518,0.00020221059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99894327,0.00012314685,0.00036417396,0.000070552625,0.000278325,0.00022052732],"domain_scores_gemma":[0.99901056,0.00005812676,0.0002713158,0.00028346147,0.0002476297,0.00012889352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017381962,0.00006834414,0.00015527067,0.000044385928,0.00012717888,0.000036496782,0.0004907905,0.000041591924,0.000018696412],"category_scores_gemma":[0.00010321714,0.00004093373,0.00009662002,0.0002596446,0.000020685484,0.00061469484,0.00012639783,0.00018435591,0.000012479428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037509628,0.000699394,0.040911686,0.000080348465,0.000095559444,0.000006620626,0.0038107266,0.0015643463,0.001700437,0.4513854,0.40120825,0.0984997],"study_design_scores_gemma":[0.0011896486,0.00051758427,0.13074888,0.0004302578,0.0001901066,0.0012238256,0.000188177,0.016301947,0.00427911,0.54882616,0.29538718,0.00071715476],"about_ca_topic_score_codex":0.000035053592,"about_ca_topic_score_gemma":0.000011282788,"teacher_disagreement_score":0.3705006,"about_ca_system_score_codex":0.000033321336,"about_ca_system_score_gemma":0.00009505906,"threshold_uncertainty_score":0.16692291},"labels":[],"label_agreement":null},{"id":"W2128212246","doi":"10.1002/sim.4098","title":"Mixture cure model with random effects for the analysis of a multi‐center tonsil cancer study","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Statistics; Maximum likelihood; Covariate; Random effects model; Mathematics; Gaussian; Cure rate; Mixture model; Correlation; Medicine; Surgery; Internal medicine","score_opus":0.01772856284049867,"score_gpt":0.3572900698339538,"score_spread":0.3395615069934551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128212246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024893617,0.00024723003,0.99516535,0.0006526038,0.00040913105,0.00090359605,0.000090617075,0.00001218005,0.000029948622],"genre_scores_gemma":[0.25792265,0.000038063652,0.7413609,0.0003138295,0.00006878013,0.00015830656,0.0000065227573,0.0000094783045,0.00012146114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988105,0.00010650851,0.0002759326,0.00030411396,0.00030308592,0.00019984103],"domain_scores_gemma":[0.9975397,0.0014010927,0.00013488976,0.0005661706,0.0002965218,0.0000616558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096597575,0.00015262836,0.0005088664,0.00018282938,0.000064065214,0.000013917103,0.0004958856,0.000051403145,0.00000780944],"category_scores_gemma":[0.00045734222,0.000076754564,0.00004066333,0.0006528827,0.00013864506,0.000044954922,0.00005596762,0.00029469773,9.511354e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014495188,0.003136103,0.036356173,0.0006760939,0.006179634,0.00013135307,0.0651672,0.027076684,0.0040880134,0.28450432,0.025029248,0.54620564],"study_design_scores_gemma":[0.0064994926,0.00019602128,0.0043175723,0.000045532375,0.00082263857,7.9937905e-7,0.000052312236,0.9820235,0.00005775229,0.005745001,0.00013457282,0.00010481399],"about_ca_topic_score_codex":0.0002164241,"about_ca_topic_score_gemma":0.004497073,"teacher_disagreement_score":0.9549468,"about_ca_system_score_codex":0.0000117195605,"about_ca_system_score_gemma":0.00006984876,"threshold_uncertainty_score":0.31299603},"labels":[],"label_agreement":null},{"id":"W2128540811","doi":"10.1109/tpami.2011.199","title":"Model-Based Learning Using a Mixture of Mixtures of Gaussian and Uniform Distributions","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Mixture model; Expectation–maximization algorithm; Multivariate statistics; Cluster analysis; Artificial intelligence; Multivariate normal distribution; Computer science; Mixture distribution; Focus (optics); Gaussian; Data modeling; Pattern recognition (psychology); Estimation theory; Unsupervised learning; Machine learning; Mathematics; Probability density function; Algorithm; Statistics; Maximum likelihood","score_opus":0.03703425116683462,"score_gpt":0.28339577880663447,"score_spread":0.24636152763979985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128540811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008919434,0.00013295983,0.99064714,0.000046770616,0.00003468584,0.0000772966,0.000053953634,0.000023459277,0.000064309155],"genre_scores_gemma":[0.82167166,0.0000875833,0.17817022,0.00003859677,0.0000028998438,0.0000034272905,0.00000225187,0.000005985225,0.000017351882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988614,0.00009634692,0.00037121357,0.00034031825,0.00016250202,0.00016825434],"domain_scores_gemma":[0.9992205,0.00006569064,0.00017997893,0.00033565122,0.000092813214,0.000105368454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000265626,0.00017904585,0.00036180587,0.00040198793,0.00013891506,0.00002506086,0.00025101897,0.00008386892,0.000026063766],"category_scores_gemma":[0.0000048054458,0.00014752371,0.0001996716,0.0007477706,0.00012708327,0.00014114355,0.000006515466,0.00023880358,2.3823415e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042616386,0.00039270596,0.0015134643,0.00012102749,0.0006334746,0.0000064235383,0.0021154867,0.082949094,0.008374374,0.0040743314,0.0000010171884,0.899776],"study_design_scores_gemma":[0.00006073846,0.000085836546,0.0002581164,0.00003192339,0.00033753616,0.000004295435,0.000012079424,0.74799454,0.24890508,0.0021854902,0.0000015318909,0.00012283552],"about_ca_topic_score_codex":0.000803063,"about_ca_topic_score_gemma":0.00023300093,"teacher_disagreement_score":0.89965314,"about_ca_system_score_codex":0.0000123373975,"about_ca_system_score_gemma":0.000033238503,"threshold_uncertainty_score":0.60158426},"labels":[],"label_agreement":null},{"id":"W2128898088","doi":"10.1111/biom.12296","title":"Multivariate longitudinal data analysis with mixed effects hidden Markov models","year":2015,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Yale University","keywords":"Bivariate analysis; Univariate; Multivariate statistics; Bayesian probability; Random effects model; Statistics; Markov chain Monte Carlo; Multivariate analysis; Hidden Markov model; Computer science; Econometrics; Mixed model; Markov chain; Mathematics; Artificial intelligence; Medicine; Meta-analysis","score_opus":0.1268934855015197,"score_gpt":0.3224489525178476,"score_spread":0.19555546701632792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128898088","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081922853,0.0008981183,0.99643373,0.00015395186,0.00033661682,0.00013663946,0.000028016217,0.0001405175,0.0010531718],"genre_scores_gemma":[0.27798438,0.000016252032,0.72163725,0.0000789327,0.00005700303,0.000006395262,0.000035264835,0.000011786799,0.00017272691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748814,0.000249074,0.00024111079,0.0009113879,0.0007048694,0.00040544214],"domain_scores_gemma":[0.996558,0.0003438575,0.00015311595,0.0023269106,0.00023730822,0.0003807916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014999504,0.00023477411,0.0004201497,0.0022539438,0.00007714321,0.0002898787,0.0022975767,0.000116660885,0.0000018467936],"category_scores_gemma":[0.0002632161,0.00017412969,0.000080065154,0.016877156,0.000047616228,0.0009759368,0.0010796499,0.00012268838,0.000011249297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005840099,0.000333514,0.00395997,0.000046621186,0.0012527129,0.00023719767,0.00029705223,0.00013008981,0.00010737128,0.06183411,0.0069604646,0.9247825],"study_design_scores_gemma":[0.0009655251,0.00019702052,0.0071288813,0.00001270398,0.0004588882,0.000018074566,0.000004449286,0.9740404,0.00026274388,0.015661282,0.00081846514,0.0004315703],"about_ca_topic_score_codex":0.00027698043,"about_ca_topic_score_gemma":0.000018703948,"teacher_disagreement_score":0.97391033,"about_ca_system_score_codex":0.000069039765,"about_ca_system_score_gemma":0.00012123773,"threshold_uncertainty_score":0.81089133},"labels":[],"label_agreement":null},{"id":"W2129813332","doi":"10.1080/00031305.2014.904250","title":"On a Simple Construction of a Bivariate Probability Function With a Common Marginal","year":2014,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Bivariate analysis; Simple (philosophy); Mathematics; Statistics; Econometrics; Function (biology); Biology","score_opus":0.009802170898168941,"score_gpt":0.2512180360990115,"score_spread":0.24141586520084257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129813332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05920851,0.0000018200562,0.9382883,0.000351201,0.000051872074,0.0001563055,0.000011057928,0.000043751963,0.0018872105],"genre_scores_gemma":[0.5726255,5.1671344e-7,0.4269993,0.00033876367,0.0000167887,0.0000086859945,0.0000012827384,0.000004329223,0.000004821723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99878305,0.00044801563,0.00016727932,0.00023307417,0.00019734712,0.00017124624],"domain_scores_gemma":[0.99866515,0.000415527,0.00028516,0.00052166503,0.00006325087,0.00004927103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004942711,0.000107814434,0.0002347513,0.000046769088,0.00009903138,0.000032593405,0.00027749123,0.0000118371945,0.000006099558],"category_scores_gemma":[0.00005796387,0.00006584241,0.00002532908,0.00036259845,0.00040060584,0.000063695836,0.000042874035,0.000111194444,0.0000041376975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012005097,0.000025086583,0.00022067365,0.000006991475,0.000011404668,5.501463e-7,0.00013142206,0.000028612661,0.00008114501,0.67228264,0.00006594848,0.32702547],"study_design_scores_gemma":[0.0002584222,0.0017517661,0.029782554,0.000017444712,0.00002897906,0.00001502242,0.000028107032,0.030610034,0.00013434465,0.9369582,0.00028966146,0.0001254663],"about_ca_topic_score_codex":0.0005425708,"about_ca_topic_score_gemma":0.000073202194,"teacher_disagreement_score":0.513417,"about_ca_system_score_codex":0.000021884525,"about_ca_system_score_gemma":0.000041152674,"threshold_uncertainty_score":0.26849756},"labels":[],"label_agreement":null},{"id":"W2131672785","doi":"","title":"Non-Local Manifold Parzen Windows","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Curse of dimensionality; Tangent space; Nonlinear dimensionality reduction; Estimator; Manifold (fluid mechanics); Parametric statistics; Mathematics; Tangent; Gaussian; Probability density function; Kernel density estimation; Applied mathematics; Computer science; Artificial intelligence; Mathematical analysis; Dimensionality reduction; Geometry; Statistics; Physics","score_opus":0.011743896249141116,"score_gpt":0.25175582659942525,"score_spread":0.24001193035028412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131672785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002448277,0.000043239954,0.8791464,0.002376088,0.0001304567,0.000078314675,2.1686482e-7,0.00012995527,0.11785053],"genre_scores_gemma":[0.2899203,0.000004579234,0.70322144,0.002246443,0.00014365543,0.000005331473,2.2882418e-7,0.000005033678,0.004452983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991348,0.000027330561,0.00014141001,0.00028955794,0.00015239333,0.00025455045],"domain_scores_gemma":[0.99933606,0.000025455309,0.000025333575,0.0004742323,0.000024292962,0.00011461315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002592668,0.000103580096,0.000117528616,0.000042921154,0.000055755256,0.00008095747,0.0006156394,0.000059314538,0.000098740595],"category_scores_gemma":[0.0000031869263,0.000080509264,0.00005863674,0.00013931056,0.00001531784,0.00034583668,0.00016116652,0.0000975008,0.0003635066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010912929,0.000026072312,0.00002622032,0.0000018433765,0.000004773409,0.000007108192,0.0001262145,0.000030440362,0.00022948482,0.42647418,0.008868782,0.5642038],"study_design_scores_gemma":[0.0007119686,0.0000978681,0.0013570631,0.0000138900605,0.000008280455,0.000080669066,0.000011720331,0.748471,0.021022368,0.05735855,0.1703511,0.00051548297],"about_ca_topic_score_codex":0.000018567063,"about_ca_topic_score_gemma":0.000017662032,"teacher_disagreement_score":0.7484406,"about_ca_system_score_codex":0.000021184032,"about_ca_system_score_gemma":0.000029701512,"threshold_uncertainty_score":0.46722633},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01302649663491802,"score_gpt":0.28260567903664,"score_spread":0.269579182401722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135194391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039614104,0.00019888839,0.99081945,0.0028618847,0.0004851263,0.00026228666,0.0000012109247,0.0003611529,0.0010486089],"genre_scores_gemma":[0.2371298,0.0000062712675,0.7592789,0.00046249942,0.00044388717,0.000034149285,0.000016198726,0.000034794015,0.0025935178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978321,0.0006021866,0.00024277478,0.00068865577,0.00019737592,0.00043689596],"domain_scores_gemma":[0.99903995,0.00011527274,0.000102081176,0.00045151688,0.00008654518,0.00020462772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017823628,0.00021483876,0.0002451608,0.0001878252,0.0004685462,0.0002113337,0.00044762195,0.00007874475,0.000057352514],"category_scores_gemma":[0.0007210961,0.00020101549,0.00008723621,0.00042302054,0.000014513309,0.0003948959,0.00007923493,0.0004847009,0.000022902897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042402167,0.00011033206,0.0046632537,0.000040608218,0.00003135214,0.00000774934,0.0022243226,0.030692954,0.019413956,0.29246175,0.00077391166,0.6495374],"study_design_scores_gemma":[0.00045211843,0.00058635464,0.00022344677,0.000007592253,0.0000114811,0.000040581115,0.000015560801,0.5805165,0.0031747778,0.0075212116,0.40709925,0.00035110864],"about_ca_topic_score_codex":0.000041682415,"about_ca_topic_score_gemma":0.000019997608,"teacher_disagreement_score":0.6491863,"about_ca_system_score_codex":0.000042663087,"about_ca_system_score_gemma":0.000030838517,"threshold_uncertainty_score":0.81971735},"labels":[],"label_agreement":null},{"id":"W2136167681","doi":"10.1139/x11-101","title":"Two-stage sector sampling for estimating small woodlot attributes","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sampling (signal processing); Statistics; Estimator; Sampling design; Sample (material); Systematic sampling; Stage (stratigraphy); Variance (accounting); Population; Econometrics; Mathematics; Computer science; Economics; Biology","score_opus":0.3207347847784709,"score_gpt":0.39004451686901703,"score_spread":0.06930973209054614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136167681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043285787,0.00035983665,0.9537145,0.00039013225,0.00048721363,0.00022189421,0.000015148903,0.000010068215,0.0015154347],"genre_scores_gemma":[0.21271019,0.0000026504285,0.7866334,0.0000620985,0.00032995993,0.000008359583,8.6473017e-7,0.000016481192,0.00023602712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99792814,0.00021597852,0.0003976003,0.00024094523,0.0003083375,0.00090897596],"domain_scores_gemma":[0.9968706,0.0005491807,0.00015519727,0.00038496839,0.000960655,0.0010794364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004791863,0.00012943815,0.00024671303,0.0006712684,0.00043697673,0.0002928767,0.001490255,0.00007924136,0.000046414556],"category_scores_gemma":[0.001086771,0.00011193912,0.00013854346,0.00049123826,0.00012513314,0.00035808005,0.0000735003,0.0005851469,0.0000063320085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006363456,0.00006458063,0.03014073,0.0001994254,0.00013312692,0.0006266719,0.0064332355,0.0006634249,0.0006954127,0.7760134,0.0032522762,0.18171413],"study_design_scores_gemma":[0.0036723947,0.0028439774,0.034000713,0.0009786247,0.000043360793,0.00090177904,0.00038395755,0.13154694,0.0068393094,0.7951537,0.022459827,0.00117545],"about_ca_topic_score_codex":0.0052597136,"about_ca_topic_score_gemma":0.039439153,"teacher_disagreement_score":0.18053868,"about_ca_system_score_codex":0.00018340819,"about_ca_system_score_gemma":0.002338739,"threshold_uncertainty_score":0.97808856},"labels":[],"label_agreement":null},{"id":"W2136541992","doi":"10.1080/00949655.2011.614245","title":"Estimation of a discriminant function from a mixture of two inverse Weibull distributions","year":2011,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia; King Saud University","keywords":"Weibull distribution; Statistics; Mathematics; Discriminant function analysis; Monte Carlo method; Linear discriminant analysis; Inverse; Applied mathematics; Econometrics","score_opus":0.037985775528850727,"score_gpt":0.3179157665814056,"score_spread":0.27992999105255484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136541992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051665742,0.000039752045,0.94791174,0.00004540145,0.00015403943,0.00007346789,0.000038448114,0.000007173773,0.00006422865],"genre_scores_gemma":[0.54022586,0.0000030707943,0.4597305,0.000012532935,0.000013177807,2.808238e-7,0.000011436769,0.0000019864663,0.0000011386571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988384,0.0001576204,0.00057911867,0.00011490706,0.00023391334,0.00007602145],"domain_scores_gemma":[0.9985438,0.00041734264,0.00054864364,0.000084568135,0.00032541563,0.00008022998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033191172,0.00008472265,0.00023183344,0.00011663533,0.000044755674,0.000020464366,0.00008889282,0.0000486589,0.0000148787085],"category_scores_gemma":[0.00017303281,0.000068962436,0.000048846545,0.00016386998,0.00006403386,0.00037759606,0.000029091409,0.000105589905,5.7403116e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025727222,0.00029520082,0.0005397514,0.000071746894,0.00007057213,0.000009157343,0.0031107713,0.0950164,0.0011673818,0.42681506,0.000113310445,0.47253338],"study_design_scores_gemma":[0.00047093193,0.0002244945,0.017079867,0.000037822065,0.000054142612,0.0000043891987,0.000016338648,0.6837041,0.00029150432,0.2980642,0.0000055681453,0.000046682962],"about_ca_topic_score_codex":0.000039844595,"about_ca_topic_score_gemma":0.0000037389539,"teacher_disagreement_score":0.58868766,"about_ca_system_score_codex":0.000018501027,"about_ca_system_score_gemma":0.000048477646,"threshold_uncertainty_score":0.28122064},"labels":[],"label_agreement":null},{"id":"W2137399261","doi":"10.2307/3316097","title":"Estimating the order of a hidden markov model","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Identifiability; Hidden Markov model; Hidden semi-Markov model; Markov model; Context (archaeology); Variable-order Markov model; Computer science; Markov chain; Forward algorithm; Set (abstract data type); Machine learning; Mathematics; Algorithm; Econometrics; Artificial intelligence; Geography","score_opus":0.02937672770005426,"score_gpt":0.247198568872805,"score_spread":0.21782184117275075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137399261","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034954966,0.00031744147,0.99654317,0.0009450413,0.00027089455,0.000038267208,0.000038862287,0.0000023285743,0.0014944755],"genre_scores_gemma":[0.089829184,0.00000771202,0.90956366,0.00029910626,0.00005826459,3.8976e-7,2.0081472e-7,0.0000064256906,0.00023508404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915755,0.00006630699,0.00032704198,0.000076613054,0.0001704142,0.00020209054],"domain_scores_gemma":[0.9987642,0.00014310729,0.0002539731,0.0002288032,0.00033652887,0.0002733573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043158387,0.000077183395,0.00015806765,0.00010418836,0.00010256695,0.00007182563,0.0006424382,0.00003327094,0.000050430084],"category_scores_gemma":[0.00029863554,0.000054631633,0.000034749813,0.00020313135,0.00007757261,0.00013057739,0.000018992954,0.0001896322,0.0000022499794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012778416,0.000010916246,0.0000947305,0.000024297959,0.00003488581,0.00015690246,0.0033534418,0.00316719,0.00002996428,0.18559195,0.0430423,0.76449215],"study_design_scores_gemma":[0.000107141575,0.00003723163,0.000084708336,0.000029621962,0.0000138131145,0.00012088243,0.000008583036,0.9178213,0.000013754221,0.08143284,0.0002676508,0.00006251268],"about_ca_topic_score_codex":0.0003238259,"about_ca_topic_score_gemma":0.00083381496,"teacher_disagreement_score":0.9146541,"about_ca_system_score_codex":0.000038181992,"about_ca_system_score_gemma":0.00047696132,"threshold_uncertainty_score":0.22278133},"labels":[],"label_agreement":null},{"id":"W2138565270","doi":"10.1111/j.0006-341x.2001.00518.x","title":"Bayesian Nonparametric Modeling Using Mixtures of Triangular Distributions","year":2001,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Queensland University of Technology","keywords":"Markov chain Monte Carlo; Nonparametric statistics; Computer science; Bayesian probability; Context (archaeology); Mathematical optimization; Mathematics; Parametric statistics; Markov chain; Piecewise; Nonparametric regression; Algorithm; Focus (optics); Flexibility (engineering); Applied mathematics; Machine learning; Econometrics; Statistics; Artificial intelligence","score_opus":0.05482695784796059,"score_gpt":0.3136258099905117,"score_spread":0.2587988521425511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138565270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014402006,0.0022517738,0.98204535,0.00011044151,0.00038261252,0.00015831711,0.000018452738,0.000086936,0.000544126],"genre_scores_gemma":[0.47931015,0.00009237584,0.5204717,0.000031893087,0.000052887797,0.0000021014803,0.0000037612917,0.000008039462,0.000027080847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817485,0.0001242703,0.0004549065,0.00041163526,0.00043823617,0.00039609004],"domain_scores_gemma":[0.9985035,0.00019764357,0.00017277144,0.00071677146,0.00023625337,0.00017307478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083304784,0.00018366783,0.00032998025,0.0025116235,0.0001413979,0.00010704362,0.0008343147,0.00016391632,0.000010244987],"category_scores_gemma":[0.00060213427,0.00016842874,0.0001819486,0.017507127,0.000045312652,0.00031416543,0.00019592838,0.0001442006,0.00000380324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035194556,0.00080154533,0.0016439859,0.0001023841,0.0001556065,0.00011576652,0.00032902567,0.0050642635,0.030470738,0.19298118,0.00047630505,0.767824],"study_design_scores_gemma":[0.000356907,0.000060017162,0.00009093779,0.000017233855,0.000028478991,0.000046161367,0.00000443787,0.9731759,0.0040098163,0.021189444,0.0007858966,0.00023481433],"about_ca_topic_score_codex":0.000083823536,"about_ca_topic_score_gemma":7.1119894e-7,"teacher_disagreement_score":0.9681116,"about_ca_system_score_codex":0.00008524678,"about_ca_system_score_gemma":0.00010323011,"threshold_uncertainty_score":0.84115934},"labels":[],"label_agreement":null},{"id":"W2139695751","doi":"10.2307/3314762","title":"Estimation in an empirical bayes model for longitudinal and cross‐sectionally clustered binary data","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Acadia University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayes' theorem; Estimation; Binary data; Generalized estimating equation; Statistics; Random effects model; Longitudinal data; Binary number; Mathematics; Econometrics; Computer science; Psychology; Bayesian probability; Data mining; Medicine; Engineering","score_opus":0.13059642039162533,"score_gpt":0.3654678434181196,"score_spread":0.23487142302649427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139695751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018129691,0.000118958815,0.9807065,0.0004090104,0.00010879938,0.00007583015,0.00041311735,0.0000033890879,0.0000346614],"genre_scores_gemma":[0.22636634,0.000011573708,0.77330583,0.00017726624,0.00004230398,0.0000010146375,0.000024549772,0.0000062592153,0.00006485102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990926,0.00005596204,0.00032404542,0.00020628297,0.00011657262,0.00020453811],"domain_scores_gemma":[0.99899316,0.000121604186,0.000092681556,0.00026215825,0.0001424942,0.000387905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005784583,0.00008836285,0.00015219342,0.0001695774,0.00012117882,0.00023414019,0.00050189183,0.00005716894,0.000017751147],"category_scores_gemma":[0.00011612445,0.00008517152,0.000014888176,0.000107329455,0.0000654344,0.00080568093,0.000021990074,0.00014262069,5.7082616e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008330172,0.000059204736,0.011932916,0.000055843913,0.000028115895,0.00031656786,0.001762253,0.07221421,0.0000134521615,0.030972647,0.010132414,0.8724291],"study_design_scores_gemma":[0.00033827475,0.000116222844,0.021114318,0.000019972891,0.000008288459,0.00014901579,0.0000024608082,0.90527076,0.0000011364999,0.07271399,0.00017828147,0.00008730406],"about_ca_topic_score_codex":0.00023407537,"about_ca_topic_score_gemma":0.0107395835,"teacher_disagreement_score":0.87234175,"about_ca_system_score_codex":0.00006493009,"about_ca_system_score_gemma":0.0010096681,"threshold_uncertainty_score":0.599294},"labels":[],"label_agreement":null},{"id":"W2139830934","doi":"10.1139/f99-275","title":"Untangling the confusion surrounding the estimation of gillnet selectivity","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confusion; Fishery; Estimation; Biology; Environmental science; Geography; Ecology; Economics; Psychology","score_opus":0.021281880098243222,"score_gpt":0.24563101048906846,"score_spread":0.22434913039082524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139830934","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4996015,0.0006232105,0.49059597,0.0070059653,0.00022576378,0.00006103957,5.286761e-7,0.0000023647453,0.0018836284],"genre_scores_gemma":[0.96236175,0.000043745797,0.037237763,0.00026018545,0.000033338132,4.637614e-7,3.7627345e-8,0.0000014644354,0.00006127608],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922115,0.00014493868,0.00020225206,0.000088591645,0.00018701816,0.00015606564],"domain_scores_gemma":[0.9992834,0.00032595682,0.0001469338,0.00010707864,0.000033354772,0.00010329766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020518594,0.00005865795,0.00011350429,0.000058985428,0.0006381804,0.0003011262,0.0005115864,0.000020608988,0.000030294552],"category_scores_gemma":[0.0001600476,0.000029164576,0.00003249386,0.0004036136,0.00046088395,0.00046006896,0.000010830953,0.00009646194,2.9398507e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002353811,0.000003646358,0.002188904,0.0000056248577,0.000008507838,0.0000056176877,0.005435313,0.00031983946,0.00006419423,0.025640354,0.00041704607,0.9659086],"study_design_scores_gemma":[0.00035105663,0.0006062071,0.01805695,0.00025632468,0.000043771866,0.00061406626,0.0014352201,0.7518556,0.0011425129,0.21584986,0.009491469,0.00029697744],"about_ca_topic_score_codex":0.002499398,"about_ca_topic_score_gemma":0.0028954998,"teacher_disagreement_score":0.96561164,"about_ca_system_score_codex":0.000016546877,"about_ca_system_score_gemma":0.00048191726,"threshold_uncertainty_score":0.4908432},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.046528837673892244,"score_gpt":0.19329409256850758,"score_spread":0.14676525489461534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140574335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17505436,0.000020628855,0.8198949,0.0006817736,0.00027624663,0.00020945059,8.6077466e-7,0.00017669205,0.003685099],"genre_scores_gemma":[0.95959795,0.000018497996,0.03722296,0.00045885294,0.00006264989,0.0000012486453,7.643713e-7,0.000011050961,0.0026260274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985817,0.00028175995,0.0001251385,0.00054743775,0.00009093465,0.00037300246],"domain_scores_gemma":[0.9984572,0.00015041408,0.00012044888,0.00093764556,0.00014455356,0.0001897312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023110311,0.00018990181,0.00018273522,0.00007814523,0.00037724344,0.00016409821,0.0013564796,0.00009402305,0.000043657656],"category_scores_gemma":[0.00004071348,0.00014161911,0.000119698496,0.00043905518,0.00014955868,0.00075430697,0.00039040993,0.00025826998,0.000196718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070665205,0.000034774017,0.0013990197,0.000006504394,0.000032762277,0.00019826525,0.00035775674,0.0010266431,0.0004184602,0.9860439,0.0032427844,0.007232107],"study_design_scores_gemma":[0.00032149398,0.000044000735,0.011076265,0.000011918021,0.000026189527,0.000024190182,0.000038565286,0.87839586,0.00043883768,0.10911271,0.00025635312,0.00025362946],"about_ca_topic_score_codex":0.00036597424,"about_ca_topic_score_gemma":0.000018582201,"teacher_disagreement_score":0.8773692,"about_ca_system_score_codex":0.000060211696,"about_ca_system_score_gemma":0.00006876988,"threshold_uncertainty_score":0.57750595},"labels":[],"label_agreement":null},{"id":"W2140803050","doi":"10.5267/j.ijiec.2013.03.003","title":"Modeling quality control data using mixture of parametrical distributions","year":2013,"lang":"en","type":"article","venue":"International Journal of Industrial Engineering Computations","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Control (management); Computer science; Control theory (sociology); Econometrics; Environmental science; Statistics; Mathematics; Artificial intelligence; Physics","score_opus":0.10879204527241201,"score_gpt":0.3538619163339961,"score_spread":0.2450698710615841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140803050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024881873,0.00009283968,0.972026,0.0011111213,0.0016712471,0.000106362444,0.000074669624,0.000022798096,0.000013112898],"genre_scores_gemma":[0.62154573,0.0000034078184,0.37808508,0.000023185377,0.0003256344,9.051503e-7,0.000009966664,0.0000049395185,0.0000011690538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981632,0.00011058134,0.00087775127,0.00017003111,0.00052673725,0.00015166543],"domain_scores_gemma":[0.9975621,0.00054887054,0.0003669749,0.00031564027,0.001082029,0.00012439785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007718871,0.00012126193,0.00028998996,0.0003471999,0.00004121895,0.00015732682,0.0016175536,0.000111582856,0.0000088749275],"category_scores_gemma":[0.0014146477,0.00011049163,0.00012214153,0.00040900943,0.00002224316,0.00090771983,0.0002059123,0.00040352877,0.0000013862788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008968017,0.00009742362,0.00011439263,0.0000034463988,0.00022460481,0.000007368902,0.00006048732,0.94010735,0.0012160318,0.033705324,0.00025970553,0.024194872],"study_design_scores_gemma":[0.0008433287,0.000028027118,0.00013429234,0.00007688773,0.000024125702,0.0000739947,0.0000059600343,0.99407077,0.00012698598,0.0044341995,0.00007968209,0.000101744416],"about_ca_topic_score_codex":0.00011145937,"about_ca_topic_score_gemma":4.6994475e-7,"teacher_disagreement_score":0.59666383,"about_ca_system_score_codex":0.000092992515,"about_ca_system_score_gemma":0.00023417918,"threshold_uncertainty_score":0.45057178},"labels":[],"label_agreement":null},{"id":"W2141439367","doi":"10.1109/tmi.2007.896934","title":"Bayesian Kernel Methods for Analysis of Functional Neuroimages","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health","keywords":"Overfitting; Computer science; Kernel (algebra); Artificial intelligence; Maximum a posteriori estimation; Pattern recognition (psychology); Bayesian probability; Algorithm; Machine learning; Mathematics; Artificial neural network; Statistics","score_opus":0.03230083951881568,"score_gpt":0.36931926466898596,"score_spread":0.3370184251501703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141439367","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006573209,0.00008235293,0.99664223,0.0016095903,0.00091183436,0.0001318057,0.00000698803,0.00010869188,0.00044078493],"genre_scores_gemma":[0.1904187,0.000015226374,0.8081823,0.0011657504,0.000055736935,0.000015194291,0.0000016406505,0.000012695649,0.00013275938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980632,0.0001936773,0.00045861205,0.00046052432,0.00047419395,0.00034976532],"domain_scores_gemma":[0.9975893,0.0014421255,0.0001021094,0.00044160977,0.00013932718,0.00028556323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002930031,0.00016226203,0.00035189535,0.00068664574,0.00015471123,0.000041979627,0.00047523325,0.00008404857,0.00013014095],"category_scores_gemma":[0.00008766452,0.00014534309,0.00041470653,0.0013224235,0.00012599114,0.0002461904,0.0000040362142,0.00030888832,0.0000017961034],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022333228,0.00013149934,0.000019181696,0.000013579298,0.00022489064,0.000008136358,0.00015653823,0.00077418453,0.003515858,0.002939263,0.000104201106,0.99209034],"study_design_scores_gemma":[0.00042070283,0.000035700654,0.0006054767,0.000019248739,0.000364116,0.000019196237,0.000014241085,0.97137743,0.021273967,0.00486548,0.0008288051,0.00017560937],"about_ca_topic_score_codex":0.00001978858,"about_ca_topic_score_gemma":0.000011914153,"teacher_disagreement_score":0.99191475,"about_ca_system_score_codex":0.0000313347,"about_ca_system_score_gemma":0.000093544404,"threshold_uncertainty_score":0.5926919},"labels":[],"label_agreement":null},{"id":"W2142256070","doi":"10.1007/978-3-642-34487-9_4","title":"Nonparametric Localized Feature Selection via a Dirichlet Process Mixture of Generalized Dirichlet Distributions","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Dirichlet process; Hierarchical Dirichlet process; Feature selection; Cluster analysis; Dirichlet distribution; Artificial intelligence; Nonparametric statistics; Computer science; Pattern recognition (psychology); Feature (linguistics); Model selection; Mixture model; Bayesian inference; Selection (genetic algorithm); Generalized Dirichlet distribution; Inference; Bhattacharyya distance; Latent Dirichlet allocation; Bayesian probability; Mathematics; Topic model; Dirichlet's principle; Statistics; Artificial neural network","score_opus":0.014398182293352314,"score_gpt":0.2728300052774227,"score_spread":0.25843182298407036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142256070","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008355907,0.003362249,0.9925222,0.0007461673,0.0013867782,0.0008050873,0.000042264346,0.00021786778,0.0008338436],"genre_scores_gemma":[0.07737458,0.00014282201,0.92063284,0.00070308166,0.0006360256,0.000037743735,0.00003929818,0.000060531296,0.00037308846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448013,0.00018095507,0.0008450704,0.0018665559,0.0014598957,0.0011673825],"domain_scores_gemma":[0.9959827,0.000458089,0.0007959966,0.0015432707,0.00082113117,0.00039880918],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015152186,0.0009351794,0.0012591103,0.0015095819,0.0003667313,0.00033693362,0.0033139042,0.0009792362,0.000036965645],"category_scores_gemma":[0.0002188055,0.0007936475,0.00035984843,0.003759426,0.00073731894,0.0008534662,0.00083313603,0.001578605,0.000014885575],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004300048,0.00022322426,0.00018064039,0.00026581515,0.00007968054,0.00003462132,0.0008507668,0.004564283,0.0014837258,0.06463409,0.00030992887,0.9273302],"study_design_scores_gemma":[0.0011063064,0.0003450808,0.00023011671,0.0005334944,0.000120570316,0.00034665357,1.359646e-7,0.5436729,0.015401032,0.43044537,0.0059714722,0.0018268551],"about_ca_topic_score_codex":0.00003137556,"about_ca_topic_score_gemma":0.00003359341,"teacher_disagreement_score":0.9255034,"about_ca_system_score_codex":0.00039788475,"about_ca_system_score_gemma":0.0007010955,"threshold_uncertainty_score":0.99945146},"labels":[],"label_agreement":null},{"id":"W2143310476","doi":"","title":"Exact Nonparametric Two-Sample Homogeneity Tests for Possibly Discrete Distributions","year":2001,"lang":"en","type":"article","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Canada Council for the Arts; Université de Montréal; Natural Sciences and Engineering Research Council of Canada; Mitacs; Killam Trusts","keywords":"Nonparametric statistics; Monte Carlo method; Homogeneity (statistics); Statistical hypothesis testing; Sample size determination; Mathematics; Statistics; Statistical power; Probability distribution; Empirical distribution function; Applied mathematics; Econometrics","score_opus":0.020963864104438026,"score_gpt":0.27639983972944243,"score_spread":0.2554359756250044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143310476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0324576,0.0009980983,0.96178806,0.00062863773,0.0003196531,0.00052653893,0.0014473272,0.00010407346,0.0017300337],"genre_scores_gemma":[0.7214492,0.0016961944,0.27384314,0.00007067611,0.0001590755,0.000004863175,0.0006429862,0.000022108532,0.0021117749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761117,0.00017621997,0.00038026363,0.0010330403,0.00032757636,0.00047173572],"domain_scores_gemma":[0.9964328,0.0007320312,0.00040545713,0.0018867578,0.000211322,0.00033163143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046838704,0.0002954029,0.0004731465,0.00020452817,0.00082890363,0.00016620957,0.001648368,0.00012400278,0.000012229232],"category_scores_gemma":[0.00022289407,0.0003012831,0.0001397169,0.0005137724,0.00025289413,0.0013789013,0.0010104653,0.00015573094,0.0000030037852],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011402195,0.002199044,0.0791079,0.0004519898,0.0019241711,0.0019004414,0.00061852636,0.00014426769,0.006001134,0.12701826,0.10143561,0.67805845],"study_design_scores_gemma":[0.018312829,0.0018599431,0.14373878,0.00050850236,0.0020761895,0.0015782373,0.0003336391,0.07263241,0.003769213,0.061457243,0.68969023,0.00404277],"about_ca_topic_score_codex":0.007485802,"about_ca_topic_score_gemma":0.0025251114,"teacher_disagreement_score":0.68899155,"about_ca_system_score_codex":0.0001661917,"about_ca_system_score_gemma":0.00013890814,"threshold_uncertainty_score":0.9999439},"labels":[],"label_agreement":null},{"id":"W2143618849","doi":"","title":"Non-linear CCA and PCA by Alignment of Local Models","year":2003,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Canonical correlation; Dimensionality reduction; Nonlinear dimensionality reduction; Curse of dimensionality; Laplace operator; Manifold (fluid mechanics); Computer science; Linear model; Artificial intelligence; Mathematics; Principal component analysis; Algorithm; Pattern recognition (psychology); Applied mathematics; Mathematical optimization; Machine learning; Mathematical analysis","score_opus":0.012478967264110215,"score_gpt":0.2059051960134653,"score_spread":0.19342622874935508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143618849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023726847,0.0001721081,0.9691795,0.00027988834,0.00007511154,0.000120019555,0.00001683426,0.00002237049,0.006407326],"genre_scores_gemma":[0.66002387,0.000050807932,0.33913007,0.00008449011,0.0000050498134,1.2144292e-7,0.0000021284113,0.0000058497462,0.0006976519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898815,0.00008969488,0.00013430712,0.00034085993,0.00023823549,0.00020877931],"domain_scores_gemma":[0.9991978,0.000038345777,0.00012526376,0.00041865025,0.00008753343,0.00013240287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027550838,0.00013495285,0.00028554955,0.00008871037,0.00009470817,0.000012180887,0.000472907,0.00009468207,0.000023872459],"category_scores_gemma":[0.0000032210792,0.00015198349,0.00008274188,0.00019138103,0.00017809954,0.00042323692,0.00022846405,0.00009275216,0.0000034090076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016378317,0.00091222214,0.0005597787,0.000543639,0.0003571352,0.0001523456,0.021887926,0.001288203,0.015987346,0.55995107,0.022918018,0.37527853],"study_design_scores_gemma":[0.008237086,0.0017371951,0.0011592876,0.00047271245,0.000227309,0.00011119443,0.0054952223,0.77400523,0.050794873,0.12153683,0.03430452,0.0019185176],"about_ca_topic_score_codex":0.00013781109,"about_ca_topic_score_gemma":0.000012595115,"teacher_disagreement_score":0.77271706,"about_ca_system_score_codex":0.000029792343,"about_ca_system_score_gemma":0.00005788392,"threshold_uncertainty_score":0.61977065},"labels":[],"label_agreement":null},{"id":"W2143710665","doi":"10.1002/sim.5529","title":"Mixture distributions in multi‐state modelling: Some considerations in a study of psoriatic arthritis","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Medical Research Council","keywords":"Mixture model; Econometrics; Poisson distribution; Psoriatic arthritis; Computer science; Population; Inverse Gaussian distribution; Statistics; Mathematics; Arthritis; Medicine","score_opus":0.05109171537922794,"score_gpt":0.3417578543330217,"score_spread":0.2906661389537938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143710665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018739318,0.0011214868,0.97883755,0.00035485168,0.00036055475,0.0004543272,0.00007314997,0.000013858945,0.00004493075],"genre_scores_gemma":[0.5826842,0.0001231193,0.4170566,0.00005380343,0.000028120206,0.000029222869,0.000008999167,0.0000050869994,0.0000108499835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980452,0.00035148108,0.00072942016,0.00025412347,0.0002650949,0.0003546856],"domain_scores_gemma":[0.99868596,0.00064624095,0.00012843114,0.00035759225,0.00007878582,0.00010298797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012718725,0.00014859397,0.0004344502,0.00031752663,0.000040111612,0.000012492826,0.00019450825,0.00005670391,0.0000127133335],"category_scores_gemma":[0.0006086196,0.00013396538,0.000013050234,0.0005348259,0.00009133639,0.00022798155,0.000068382295,0.0003435831,0.0000015653578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000110580995,0.0021714775,0.010942001,0.00006640417,0.000020785303,0.00019045266,0.046270996,0.005818693,0.00010896684,0.90455985,0.0006110539,0.02922827],"study_design_scores_gemma":[0.0045365924,0.0002731058,0.018289065,0.00027871388,0.000013786277,0.000013349116,0.00042959274,0.3918795,0.00004648928,0.5839676,0.000038357834,0.00023382979],"about_ca_topic_score_codex":0.00062970584,"about_ca_topic_score_gemma":0.0018882719,"teacher_disagreement_score":0.5639449,"about_ca_system_score_codex":0.00006737747,"about_ca_system_score_gemma":0.000074635565,"threshold_uncertainty_score":0.546295},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06841040994015102,"score_gpt":0.30705565796956996,"score_spread":0.23864524802941894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144245426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011642717,0.00008017186,0.9868882,0.00030283572,0.00082282437,0.00011952088,0.00005894568,0.000059342223,0.00002544704],"genre_scores_gemma":[0.8444837,0.000059204744,0.15528621,0.000083718885,0.000059498783,0.000004302088,0.000008705058,0.000007716335,0.000006964681],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989723,0.000074322976,0.00024140801,0.00038332093,0.00013849714,0.00019017866],"domain_scores_gemma":[0.99874353,0.00015880314,0.000076847165,0.0008623133,0.00007226752,0.00008626264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002730863,0.00012942772,0.00014906196,0.000069354144,0.00022596426,0.00008242708,0.0005216588,0.00012464872,0.0000041374906],"category_scores_gemma":[0.0000066365014,0.00011734465,0.000043739466,0.00023094437,0.00006949506,0.00045811033,0.000009456883,0.0004742753,4.1503014e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021991396,0.00012524505,0.0000066706802,0.000014653169,0.000029083665,0.0000026020439,0.00009527194,0.70179915,0.02019012,0.010526487,0.000054329874,0.2671344],"study_design_scores_gemma":[0.00012566887,0.000022068842,0.000018091294,0.0000132274945,0.000026597749,0.00001760356,0.0000014595747,0.99735975,0.00081585394,0.0014460402,0.000039024082,0.00011459537],"about_ca_topic_score_codex":0.000026275846,"about_ca_topic_score_gemma":0.000031474443,"teacher_disagreement_score":0.832841,"about_ca_system_score_codex":0.0000094662155,"about_ca_system_score_gemma":0.000027308626,"threshold_uncertainty_score":0.4785176},"labels":[],"label_agreement":null},{"id":"W2144288553","doi":"10.1016/j.jmva.2006.01.007","title":"Densities for random balanced sampling","year":2006,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Polytope; Mathematics; Fractal; Sampling (signal processing); Combinatorics; Coupling (piping); Distribution (mathematics); Simple (philosophy); Simple random sample; Dimension (graph theory); Multivariate statistics; Variance (accounting); Fractal dimension; Statistical physics; Discrete mathematics; Mathematical analysis; Statistics; Physics; Materials science; Detector","score_opus":0.022029694868672352,"score_gpt":0.30428682646809746,"score_spread":0.2822571315994251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144288553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008297384,0.00026787838,0.99054015,0.00045585106,0.00019310409,0.00006376803,0.0000024141914,0.000015759366,0.00016371353],"genre_scores_gemma":[0.3675741,0.000010038724,0.63197404,0.00008174446,0.00020226894,0.0000015904541,0.000001055877,0.0000043889017,0.0001507823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987069,0.0001301989,0.0005586371,0.00016695715,0.00023446728,0.00020287711],"domain_scores_gemma":[0.9983184,0.00046823954,0.0005154287,0.00023556237,0.00039828965,0.00006413388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013273783,0.000118783435,0.00054213486,0.00041165648,0.00010253539,0.00014262738,0.0004209619,0.000059432045,0.0000054112597],"category_scores_gemma":[0.00010939265,0.000087976696,0.000676475,0.00061867834,0.000016159069,0.00033338022,0.000039647697,0.00011118993,7.2947483e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013511197,0.000889698,0.006121526,0.00012775967,0.013999379,0.0001779324,0.0036870555,0.17700213,0.1283419,0.42334032,0.003735997,0.24122515],"study_design_scores_gemma":[0.0050495383,0.00012254815,0.010802347,0.00003835158,0.002060118,0.000042886437,0.00002940373,0.8546497,0.0047614803,0.11927375,0.0028040872,0.00036575046],"about_ca_topic_score_codex":0.00007536589,"about_ca_topic_score_gemma":0.000016166301,"teacher_disagreement_score":0.6776476,"about_ca_system_score_codex":0.000034046734,"about_ca_system_score_gemma":0.00005051079,"threshold_uncertainty_score":0.35875854},"labels":[],"label_agreement":null},{"id":"W2144832675","doi":"10.1080/10618600.2013.844700","title":"Bayesian Estimation of Discrete Multivariate Latent Structure Models With Structural Zeros","year":2013,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Memorial University of Newfoundland; National Science Foundation","keywords":"Categorical variable; Local independence; Conditional independence; Latent class model; Mathematics; Posterior probability; Bayesian probability; Latent variable; Econometrics; Computer science; Latent variable model; Statistics","score_opus":0.008773760577415121,"score_gpt":0.2503721420045232,"score_spread":0.24159838142710804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144832675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03648087,0.000056529127,0.96277034,0.00044228332,0.000075600874,0.000105229425,0.000054060947,0.0000068412573,0.000008250144],"genre_scores_gemma":[0.49946895,0.0000036647757,0.5004547,0.00004722048,0.000015053617,4.7758004e-7,0.0000043874475,0.0000034450895,0.0000021011924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986929,0.0000944288,0.00048081533,0.00014344932,0.00044929344,0.00013906677],"domain_scores_gemma":[0.998563,0.0002671989,0.00042364362,0.000089684836,0.0004972904,0.00015921744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001376353,0.00013939782,0.00027994532,0.00012274325,0.00007884826,0.00010327775,0.0002091145,0.000058503923,0.000010250838],"category_scores_gemma":[0.00002821515,0.00008804619,0.000046071167,0.00019244086,0.00011474527,0.00053234556,0.00004559337,0.00021397237,1.7085722e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033170254,0.000020545427,0.00026454488,0.000036885656,0.000072400464,0.000011015623,0.00031250532,0.25344223,0.00010955992,0.65710175,0.00006054361,0.088534854],"study_design_scores_gemma":[0.00029423583,0.00013971943,0.016081033,0.000020787127,0.0000128450165,0.00007519321,0.000001747942,0.4970749,0.000018295033,0.48622087,8.5991286e-7,0.000059525417],"about_ca_topic_score_codex":0.00002273609,"about_ca_topic_score_gemma":0.0000013923841,"teacher_disagreement_score":0.46298808,"about_ca_system_score_codex":0.000010027448,"about_ca_system_score_gemma":0.00006325052,"threshold_uncertainty_score":0.35904193},"labels":[],"label_agreement":null},{"id":"W2144837664","doi":"10.1007/s10044-011-0256-4","title":"Expectation-maximization algorithms for inference in Dirichlet processes mixture","year":2011,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Markov chain Monte Carlo; Computer science; Mixture model; Expectation–maximization algorithm; Algorithm; Inference; Dirichlet distribution; Bayes' theorem; Model selection; Artificial intelligence; Pattern recognition (psychology); Machine learning; Mathematics; Maximum likelihood; Bayesian probability","score_opus":0.03564797153838353,"score_gpt":0.30369508603931766,"score_spread":0.2680471145009341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144837664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006604475,0.00014517413,0.9984118,0.00017757856,0.000008423762,0.00028138148,0.000011444715,0.000035226338,0.00026855923],"genre_scores_gemma":[0.66423917,0.00008867033,0.33478352,0.00015116375,0.000025293895,0.00063922576,0.000028266786,0.0000044381964,0.000040264273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992263,0.000028427461,0.00019635189,0.0003472795,0.0000763661,0.00012530533],"domain_scores_gemma":[0.99932545,0.00012941536,0.0000921759,0.00027309207,0.00012857112,0.000051300616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013632097,0.00009308243,0.0001657396,0.00022606632,0.000087187254,0.000065009386,0.00025732702,0.000044387987,0.000010221974],"category_scores_gemma":[0.000030555944,0.0000819688,0.00004773494,0.001349798,0.000019101763,0.00018976105,0.00004063888,0.000045532048,0.0000017208824],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022675965,0.0002081592,0.057348367,0.00007053511,0.00013415601,6.520544e-7,0.0039211484,0.00008269483,0.00012158289,0.030439273,0.000029749732,0.9076414],"study_design_scores_gemma":[0.0008895488,0.00009637821,0.17954133,0.00004346821,0.0006461685,0.0000028790457,0.00021902786,0.6122115,0.0055080713,0.19756405,0.0022856835,0.0009918314],"about_ca_topic_score_codex":0.00008423576,"about_ca_topic_score_gemma":0.00024449185,"teacher_disagreement_score":0.9066496,"about_ca_system_score_codex":0.000008363189,"about_ca_system_score_gemma":0.000024528983,"threshold_uncertainty_score":0.33425906},"labels":[],"label_agreement":null},{"id":"W2145915577","doi":"10.2307/3315857","title":"A geometric approach to transdimensional markov chain monte carlo","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Markov chain Monte Carlo; Markov chain; Monte Carlo method; Linear subspace; Computer science; Markov chain mixing time; Subspace topology; Statistical physics; Hybrid Monte Carlo; Dimension (graph theory); Mathematical optimization; Applied mathematics; Mathematics; Markov model; Algorithm; Variable-order Markov model; Artificial intelligence; Combinatorics; Statistics; Machine learning; Pure mathematics; Physics","score_opus":0.019290967290907977,"score_gpt":0.2211869549461648,"score_spread":0.20189598765525682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145915577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006369204,0.0005210419,0.9946575,0.00028075973,0.0005119966,0.00009132042,0.00007665792,0.0000042611073,0.003219505],"genre_scores_gemma":[0.1471273,0.00000888024,0.851789,0.0007001349,0.00004683984,0.0000013842761,5.159167e-7,0.000010584209,0.00031534114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998647,0.00015780292,0.00035026693,0.0001778537,0.00027555245,0.00039154102],"domain_scores_gemma":[0.99799794,0.00012151511,0.00011730755,0.00022739984,0.0002986867,0.0012371425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089300756,0.00013321136,0.00024717627,0.0006933037,0.00011447918,0.000111090616,0.00049328525,0.000059479586,0.00002258063],"category_scores_gemma":[0.00033401622,0.00012121706,0.00006203586,0.0008104393,0.000035744677,0.000130266,0.0000085943075,0.00024321169,0.0000047834224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075083312,0.00004868982,0.00019958035,0.000029477444,0.000068160734,0.00067787315,0.0020782473,0.0012334466,0.000045818957,0.7715603,0.059683885,0.164367],"study_design_scores_gemma":[0.0063506914,0.0028432996,0.019226223,0.00039814058,0.0003542701,0.011267231,0.00055150816,0.14098237,0.0011081126,0.33345026,0.4795318,0.003936119],"about_ca_topic_score_codex":0.00047,"about_ca_topic_score_gemma":0.00070845784,"teacher_disagreement_score":0.43811005,"about_ca_system_score_codex":0.00012481751,"about_ca_system_score_gemma":0.0013996953,"threshold_uncertainty_score":0.49430883},"labels":[],"label_agreement":null},{"id":"W2147030611","doi":"10.1109/tnn.2004.828755","title":"Learning Mixture Models With the Regularized Latent Maximum Entropy Principle","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Principle of maximum entropy; Computer science; Entropy (arrow of time); Mixture model; Artificial intelligence; Statistical physics; Mathematics; Physics; Thermodynamics","score_opus":0.013973562342100943,"score_gpt":0.23080299245883956,"score_spread":0.2168294301167386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147030611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039725197,0.00008035199,0.9904511,0.0042003873,0.0004983089,0.00036578442,0.0000011293719,0.00028650387,0.00014390831],"genre_scores_gemma":[0.85335845,0.000051085182,0.1450062,0.0009021601,0.00008795919,0.00005113906,9.4524614e-7,0.000027582017,0.0005144729],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982495,0.00022048384,0.00020805055,0.0005068102,0.00032836923,0.000486809],"domain_scores_gemma":[0.9989633,0.000090889385,0.00009528597,0.00064082374,0.000066713525,0.0001430025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025653467,0.0002764841,0.00023078482,0.00006741354,0.0005655685,0.00019702653,0.00065229484,0.00014597023,0.0000080577765],"category_scores_gemma":[0.0000010485012,0.00016919595,0.00016344246,0.0004856174,0.00008134442,0.00040885515,0.0000064421656,0.001038597,0.000004874359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006811162,0.000060213682,6.5900053e-7,0.0000030768028,0.000033590273,0.000024912564,0.00028400245,0.945117,0.00023834313,0.011438393,0.00002375344,0.04270794],"study_design_scores_gemma":[0.00092456123,0.00031172181,0.0000125305405,0.000030067293,0.00003460162,0.00009177977,0.000006180913,0.98602444,0.0012446116,0.010802665,0.00026787943,0.00024894188],"about_ca_topic_score_codex":0.000017860792,"about_ca_topic_score_gemma":0.000024898309,"teacher_disagreement_score":0.8493859,"about_ca_system_score_codex":0.00006160658,"about_ca_system_score_gemma":0.000042022075,"threshold_uncertainty_score":0.6899611},"labels":[],"label_agreement":null},{"id":"W2147157387","doi":"","title":"Hermite Regression Analysis of Multi-Modal Count Data","year":2010,"lang":"en","type":"article","venue":"Economics bulletin","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Negative binomial distribution; Count data; Poisson regression; Quasi-likelihood; Poisson distribution; Econometrics; Statistics; Hermite polynomials; Mathematics; Modal; Binomial distribution; Regression analysis; Covariate; Population","score_opus":0.033812130121541564,"score_gpt":0.29187420330062,"score_spread":0.2580620731790785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147157387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063678466,0.00006542134,0.9326457,0.0015483784,0.00047198927,0.00007344016,0.000055796547,0.000033345837,0.0014274749],"genre_scores_gemma":[0.1600441,0.000052018204,0.8389561,0.00033300364,0.00006575129,0.000002934919,0.00003137135,0.000009350726,0.0005053373],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988976,0.00005398232,0.00030982602,0.0005079776,0.00005664647,0.00017395715],"domain_scores_gemma":[0.99762195,0.00010171805,0.00020753655,0.0019408853,0.000041170813,0.000086761065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093067175,0.00011965524,0.0003152768,0.00016294478,0.000052327603,0.0000723004,0.001653048,0.00009979872,0.0001824198],"category_scores_gemma":[0.00005152136,0.00010591756,0.00009665597,0.00018163507,0.00004969692,0.00012879529,0.00064161286,0.00019178908,0.000042800657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004683393,0.00055380585,0.004790554,0.00004081716,0.0012420684,0.000021061942,0.0011221406,0.0011617623,0.012066795,0.34032744,0.01766379,0.6209629],"study_design_scores_gemma":[0.00033804803,0.00001628198,0.00421548,0.00000696833,0.00010666444,0.0000045209454,0.000004132586,0.8526978,0.001468821,0.0013746818,0.13953732,0.00022929904],"about_ca_topic_score_codex":0.0000745427,"about_ca_topic_score_gemma":0.00012391005,"teacher_disagreement_score":0.85153604,"about_ca_system_score_codex":0.000012536645,"about_ca_system_score_gemma":0.000048556303,"threshold_uncertainty_score":0.43191928},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.012802119347311845,"score_gpt":0.3132920961572663,"score_spread":0.30048997680995443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147307434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16682811,0.0009367353,0.8307969,0.0010422344,0.00005404756,0.00027821297,0.000009108783,0.000023226741,0.00003143571],"genre_scores_gemma":[0.8451821,0.000011359621,0.15378621,0.00086495426,0.000017723349,0.00011162879,0.000010682326,0.0000045099428,0.000010810947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902266,0.00010197031,0.00015419893,0.0003655739,0.00006348455,0.00029210048],"domain_scores_gemma":[0.99958223,0.000014605669,0.000050788516,0.00028239138,0.000037604867,0.000032357773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051928445,0.00012662739,0.00012851389,0.000043618595,0.0001628736,0.000043248194,0.0002692591,0.0001487123,1.8135303e-7],"category_scores_gemma":[0.000022399805,0.00009057364,0.00005112054,0.00012984323,0.00008366698,0.00010776341,0.00006092794,0.00010567704,5.6213355e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018241133,0.00019242142,0.0027795807,0.00012546442,0.00004978067,0.000018720419,0.015378209,0.006632899,0.09026554,0.86949664,0.00005645108,0.014821894],"study_design_scores_gemma":[0.0009935946,0.00028508093,0.0009391639,0.000024032604,0.000009929678,0.000060677427,0.00006299694,0.2841346,0.010928872,0.7022768,0.00006131285,0.00022293617],"about_ca_topic_score_codex":0.000015587339,"about_ca_topic_score_gemma":0.000055998764,"teacher_disagreement_score":0.678354,"about_ca_system_score_codex":0.000035243615,"about_ca_system_score_gemma":0.000043354135,"threshold_uncertainty_score":0.36934856},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.043337857943991,"score_gpt":0.30385368442812677,"score_spread":0.2605158264841358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147357149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056945,0.00023701084,0.9928307,0.0034513336,0.0018919344,0.0001687603,0.00016199294,0.0000469827,0.0006418273],"genre_scores_gemma":[0.01861012,0.00001928015,0.97912997,0.0009496762,0.0005735142,0.0000056665217,0.0000023733453,0.000027049442,0.00068233773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944029,0.0024796226,0.0011439881,0.00044677185,0.0007965683,0.00073014974],"domain_scores_gemma":[0.99361974,0.004599482,0.0005765222,0.00052873074,0.00035411352,0.00032141458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003415614,0.00035788564,0.00083994336,0.000041113228,0.0003948078,0.00021262732,0.0014643746,0.0002781624,0.00015810186],"category_scores_gemma":[0.002537944,0.00023267974,0.00051636866,0.00034041275,0.0008886755,0.000281169,0.00047697304,0.0010372354,0.000007957679],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011111826,0.00010112015,0.00015886732,0.000043478154,0.00015081471,0.00009797193,0.00024213517,0.0007967676,0.00032287076,0.91317695,0.05644052,0.028357375],"study_design_scores_gemma":[0.00095764303,0.00052151456,0.010959531,0.000040189923,0.0002565462,0.00041271304,0.00006481581,0.03624003,0.00060071785,0.9316776,0.017781287,0.00048744344],"about_ca_topic_score_codex":0.00028722957,"about_ca_topic_score_gemma":0.00002546448,"teacher_disagreement_score":0.038659234,"about_ca_system_score_codex":0.00017293254,"about_ca_system_score_gemma":0.0002668441,"threshold_uncertainty_score":0.94884044},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02437224421377677,"score_gpt":0.35123408429174074,"score_spread":0.326861840077964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148178414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039609214,0.000009452252,0.9954791,0.000057912737,0.00015281256,0.00017218309,0.000016588463,0.000043160897,0.00010787377],"genre_scores_gemma":[0.49688202,1.6074814e-7,0.5028064,0.00027260848,0.000019143736,7.128949e-7,0.000008473411,0.00000333478,0.0000070952074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992528,0.000028337485,0.00020455474,0.0002113318,0.00011648961,0.00018651616],"domain_scores_gemma":[0.99722964,0.0023913025,0.00009390586,0.00013610885,0.00008748206,0.00006155332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054333877,0.0000869306,0.00010211982,0.0000651029,0.0001650676,0.000094164614,0.000106883024,0.000029529841,0.0000011469069],"category_scores_gemma":[0.0002690718,0.00008199173,0.000013909147,0.00010480389,0.000010498285,0.000046499074,0.000027210348,0.000057671507,6.615288e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006880323,0.000010120998,0.0001636079,0.000018843859,0.0000021847686,0.0000014538969,0.00008389113,0.019537093,0.0000058333744,0.62229073,0.000037312762,0.35784206],"study_design_scores_gemma":[0.00026563037,0.00007269792,0.0037352524,0.000017618006,0.000002834749,2.684552e-7,0.0000015754866,0.7447798,0.000020242915,0.25098532,0.000039545746,0.000079150064],"about_ca_topic_score_codex":0.000015378304,"about_ca_topic_score_gemma":0.000005656918,"teacher_disagreement_score":0.72524273,"about_ca_system_score_codex":0.000016960985,"about_ca_system_score_gemma":0.000027841015,"threshold_uncertainty_score":0.33435258},"labels":[],"label_agreement":null},{"id":"W2148197091","doi":"10.1109/crv.2007.7","title":"A Robust Video Foreground Segmentation by Using Generalized Gaussian Mixture Modeling","year":2007,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Segmentation; Computer science; Artificial intelligence; Gaussian; Computer vision; Image segmentation; Gaussian process; Bayesian probability; Gaussian network model; Pattern recognition (psychology); Flexibility (engineering); Mathematics; Statistics","score_opus":0.050854797955194334,"score_gpt":0.3001486095525238,"score_spread":0.2492938115973295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148197091","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016741129,0.00027888454,0.9794321,0.00032053704,0.0002630231,0.00019373494,0.0000013724084,0.0001538093,0.002615415],"genre_scores_gemma":[0.10768913,0.000009999833,0.8906329,0.0010199755,0.000106596905,0.0000035076014,0.0000064057463,0.000015712627,0.00051572674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844146,0.000079353216,0.00032011038,0.00045577894,0.00027723162,0.00042607743],"domain_scores_gemma":[0.99926037,0.000037300473,0.00008146631,0.00039401185,0.000067908026,0.00015895073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008952864,0.0001902749,0.0001848395,0.0001115967,0.00018730045,0.00022687072,0.000412872,0.00012641562,0.000022774091],"category_scores_gemma":[0.000010442109,0.00015792421,0.00008418364,0.0003450166,0.000017638187,0.0007073913,0.00010089463,0.00013721248,0.000004054472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005593141,0.000176878,0.0001155463,0.000053449105,0.00009559878,0.000053514003,0.002403632,0.03248098,0.27238572,0.33202562,0.005594052,0.3545591],"study_design_scores_gemma":[0.0004181701,0.000019956105,0.0000033395852,0.000013158786,0.000010803033,0.000029708503,0.000027350576,0.96851283,0.013477309,0.017049046,0.00020900399,0.00022934916],"about_ca_topic_score_codex":0.00020516191,"about_ca_topic_score_gemma":0.00004199131,"teacher_disagreement_score":0.9360318,"about_ca_system_score_codex":0.0000899644,"about_ca_system_score_gemma":0.00004152086,"threshold_uncertainty_score":0.64399624},"labels":[],"label_agreement":null},{"id":"W2148555051","doi":"10.1002/cjs.5550350111","title":"Cramér‐von Mises statistics for discrete distributions with unknown parameters","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"von Mises distribution; Statistics; Mathematics; von Mises yield criterion; Distribution (mathematics); Sample (material); Applied mathematics; Econometrics; Mathematical analysis; Engineering; Physics","score_opus":0.02201752458171307,"score_gpt":0.2689067726721805,"score_spread":0.24688924809046742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148555051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003013734,0.00013227043,0.9960447,0.00042180615,0.0004900313,0.00015299277,0.0022675367,0.000007844135,0.00018147196],"genre_scores_gemma":[0.046118103,0.000013653944,0.95336837,0.00020419624,0.00008504482,0.0000019596046,0.00003305922,0.000015882511,0.00015975696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985707,0.000049254944,0.00045843673,0.00017390942,0.00021466518,0.00053307205],"domain_scores_gemma":[0.9971849,0.000661126,0.00031416066,0.00025088512,0.0006218543,0.0009670752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070438016,0.00016573194,0.00026254926,0.00019613931,0.0002469573,0.00021349353,0.000504611,0.00006373482,0.000009304054],"category_scores_gemma":[0.0004243057,0.00013523165,0.000051686628,0.00023920332,0.00017483202,0.00020733067,0.000012742152,0.00022111973,0.0000015125541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026877638,0.000014216213,0.00033814428,0.00003219963,0.00006476036,0.00046638388,0.00038560998,0.00008384951,0.000021023188,0.86507463,0.020708958,0.11278332],"study_design_scores_gemma":[0.002808423,0.0028168808,0.0083358055,0.0003316364,0.00040923926,0.0012399978,0.00020428575,0.022631759,0.0014113374,0.80329907,0.15519162,0.00131998],"about_ca_topic_score_codex":0.00053729606,"about_ca_topic_score_gemma":0.012742361,"teacher_disagreement_score":0.13448265,"about_ca_system_score_codex":0.00016438517,"about_ca_system_score_gemma":0.001365617,"threshold_uncertainty_score":0.71105367},"labels":[],"label_agreement":null},{"id":"W2149940508","doi":"10.1109/tit.2007.909168","title":"Information conversion, effective samples, and parameter size","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute","keywords":"Principle of maximum entropy; Kullback–Leibler divergence; Sample size determination; Mathematics; Entropy (arrow of time); Bayesian probability; Independence (probability theory); Posterior probability; Sample (material); Statistics; Computer science","score_opus":0.007705106554193773,"score_gpt":0.2319841043563846,"score_spread":0.22427899780219085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149940508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025763358,0.000009404203,0.99323136,0.00011764386,0.00055387797,0.00037390247,0.0000133459225,0.00016816464,0.0029559399],"genre_scores_gemma":[0.84201324,0.000021270012,0.15513387,0.002716499,0.000014991862,0.000031344734,0.0000034844825,0.000004258766,0.00006103527],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990041,0.000118428805,0.00035769682,0.0000919987,0.00021504183,0.00021268666],"domain_scores_gemma":[0.9980909,0.0012447701,0.00013376237,0.0002908579,0.00012518882,0.000114523325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014915182,0.00014584577,0.0001314475,0.0002618424,0.00023629506,0.00017112552,0.00020289602,0.000116196825,0.000036533784],"category_scores_gemma":[0.000055494085,0.00012879279,0.00006448241,0.00027700042,0.00006586296,0.0049463846,0.0000035861376,0.00021481549,0.00012319852],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009774047,0.00001813979,0.0000025661182,0.00003185202,0.000022996364,4.3848732e-7,0.0044604237,0.00012149966,0.00004000278,0.08583068,0.00013529371,0.90923834],"study_design_scores_gemma":[0.009564523,0.0017913567,0.007582599,0.0002818144,0.00020514676,0.0005068175,0.003135444,0.07440827,0.23914981,0.5720378,0.088539146,0.0027972267],"about_ca_topic_score_codex":0.000010006035,"about_ca_topic_score_gemma":0.0000010594737,"teacher_disagreement_score":0.90644115,"about_ca_system_score_codex":0.000058169444,"about_ca_system_score_gemma":0.000028784072,"threshold_uncertainty_score":0.52520174},"labels":[],"label_agreement":null},{"id":"W2150355686","doi":"10.1002/cjs.11253","title":"Bayesian nonparametric multivariate ordinal regression","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multivariate probit model; Multivariate statistics; Mathematics; Statistics; Probit model; Probit; Ordinal data; Multivariate analysis; Econometrics","score_opus":0.04249451254297744,"score_gpt":0.28740137176267133,"score_spread":0.2449068592196939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150355686","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021379982,0.0003875092,0.99604994,0.0005364152,0.0012189248,0.0000488943,0.00003311467,0.000007268231,0.0015041451],"genre_scores_gemma":[0.17841646,0.000007376223,0.82099664,0.00021689074,0.0001387462,4.1074546e-7,0.0000011770261,0.000009581476,0.0002127041],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986704,0.000168063,0.00038394245,0.00014877989,0.00028968923,0.00033909868],"domain_scores_gemma":[0.997122,0.00014498823,0.00029757826,0.0002690777,0.0005834355,0.0015829077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090879615,0.00013316398,0.00024797593,0.00049472426,0.00009772682,0.00018332616,0.0006914707,0.00007665519,0.000020719783],"category_scores_gemma":[0.0008364897,0.00010628601,0.00004812232,0.00053834746,0.000057591038,0.00031147763,0.000028406252,0.00029612737,0.000012662372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001897647,0.00003426625,0.0012939931,0.000018455281,0.000048150952,0.002796232,0.0019223758,0.00019733052,0.00005107673,0.33403823,0.1121148,0.5474661],"study_design_scores_gemma":[0.002786749,0.0012778125,0.004821927,0.0002970989,0.00009272183,0.002554138,0.00013615668,0.17889947,0.00039933805,0.7317447,0.076111116,0.00087874656],"about_ca_topic_score_codex":0.0015891633,"about_ca_topic_score_gemma":0.0011642165,"teacher_disagreement_score":0.54658735,"about_ca_system_score_codex":0.00017960182,"about_ca_system_score_gemma":0.0024795032,"threshold_uncertainty_score":0.4398532},"labels":[],"label_agreement":null},{"id":"W2150388527","doi":"10.1109/tnn.2009.2016339","title":"A Hybrid Pareto Mixture for Conditional Asymmetric Fat-Tailed Distributions","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pareto principle; Computer science; Lomax distribution; Mathematics; Mathematical optimization","score_opus":0.015510991328141828,"score_gpt":0.2623983043234745,"score_spread":0.24688731299533268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150388527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003484356,0.00013490376,0.9947357,0.0026563169,0.00097647036,0.00050306413,0.00019365441,0.00027951162,0.00017193635],"genre_scores_gemma":[0.91055435,0.000026688833,0.08707193,0.001735173,0.00025845095,0.00010697196,0.00005740837,0.000013386762,0.00017561355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824995,0.00012113243,0.00031738463,0.00055365753,0.00023970468,0.0005181594],"domain_scores_gemma":[0.99874127,0.00032893062,0.000091854716,0.00048631034,0.00013152727,0.00022010999],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018189011,0.00027295435,0.00027493085,0.00018727225,0.00051722175,0.00016712578,0.0005310393,0.00014189586,0.000017086551],"category_scores_gemma":[0.000010004418,0.0002487049,0.00032947515,0.000701313,0.00004741219,0.00038342437,0.0000020465789,0.0004725703,0.000006662457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010542653,0.00050673756,0.0000031198729,0.000010112047,0.000072985735,0.000032798096,0.000045487926,0.09621127,0.00023989857,0.06194527,0.017832978,0.82299393],"study_design_scores_gemma":[0.00079973694,0.00045059307,0.00017469074,0.000015216311,0.000048696296,0.00007665025,0.0000012797199,0.9480962,0.00235801,0.04580636,0.0017968183,0.00037572123],"about_ca_topic_score_codex":0.000002133906,"about_ca_topic_score_gemma":0.0000035460719,"teacher_disagreement_score":0.91020596,"about_ca_system_score_codex":0.00006751851,"about_ca_system_score_gemma":0.000030524552,"threshold_uncertainty_score":0.99999654},"labels":[],"label_agreement":null},{"id":"W2150689251","doi":"10.1504/ijdmb.2013.054696","title":"A clustering approach for estimating parameters of a profile hidden Markov model","year":2013,"lang":"en","type":"article","venue":"International Journal of Data Mining and Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"University of Waterloo; University of Tehran; Iran National Science Foundation","keywords":"Hidden Markov model; Cluster analysis; Pattern recognition (psychology); Computer science; Markov chain Monte Carlo; Markov chain; Artificial intelligence; Markov model; Bayesian probability; Mathematics; Algorithm; Machine learning","score_opus":0.06555281677021664,"score_gpt":0.31880183367583853,"score_spread":0.2532490169056219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150689251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028859559,0.000032255106,0.99616355,0.00022135275,0.00018076593,0.00011484412,0.000047522542,0.0000071269415,0.00034664737],"genre_scores_gemma":[0.010582195,0.000011262551,0.9891937,0.000109880224,0.000054905307,0.0000038527933,0.00002055429,0.000004312176,0.000019337385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989329,0.000016767712,0.0005808762,0.00009021727,0.00026771726,0.00011153379],"domain_scores_gemma":[0.9986558,0.00015187025,0.00057830446,0.00023107402,0.00032224398,0.000060738854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075424154,0.0000844429,0.00017737325,0.00013590674,0.000031222942,0.00019134014,0.0011903042,0.000037847276,0.000001075126],"category_scores_gemma":[0.00020217469,0.00006352737,0.00004266548,0.00005228075,0.000030245094,0.0018065847,0.00045245784,0.00007280089,2.0560933e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008674156,0.000018430443,0.000019757925,0.00006409115,0.0000564154,5.107701e-7,0.0011011559,0.00006509409,0.00006322383,0.000036342706,0.001090254,0.99747604],"study_design_scores_gemma":[0.0003518705,0.00006417711,0.000009927744,0.00011661915,0.000012623047,0.0001306572,0.00015958275,0.9986648,0.00008132104,0.0003333163,0.0000038474245,0.000071270326],"about_ca_topic_score_codex":0.0000040420223,"about_ca_topic_score_gemma":1.9297023e-7,"teacher_disagreement_score":0.9985997,"about_ca_system_score_codex":0.000012548374,"about_ca_system_score_gemma":0.000067432535,"threshold_uncertainty_score":0.25905707},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2150812226","doi":"10.1002/9780470284704.app1","title":"Appendix A: Probability Tables","year":2008,"lang":"en","type":"other","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Appendix; Statistics; Computer science; Mathematics; Geology; Paleontology","score_opus":0.023327380225042254,"score_gpt":0.2572862195845337,"score_spread":0.23395883935949144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150812226","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1511178e-8,0.00040974037,0.50734884,0.000089605746,0.00019224134,0.0001362266,0.0000032830803,0.00033153355,0.49148852],"genre_scores_gemma":[8.8638046e-7,0.000093369286,0.50916094,0.00014288128,0.00009332033,0.00000844371,0.000003655244,0.0000575145,0.490439],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987835,0.00008607388,0.00013855798,0.00055223843,0.00018960437,0.00024997594],"domain_scores_gemma":[0.9987735,0.000022705159,0.000083358536,0.0010156215,0.000016208365,0.00008856919],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017137555,0.00021500248,0.0002859303,0.00010458493,0.000036361733,0.000048875136,0.0009127383,0.00024364097,0.0024111916],"category_scores_gemma":[0.000012345033,0.00016109944,0.0000869371,0.0001655377,0.000052515064,0.00007083431,0.00023102576,0.00014986597,0.0007336554],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7913872e-7,0.00002021539,0.0000037245832,0.000020480527,0.000008844823,0.0000072622324,0.000016983327,6.692604e-8,0.0000017375025,0.21755213,0.7447542,0.037614204],"study_design_scores_gemma":[0.00006637724,0.000011596141,0.0000030750543,0.000026343532,0.0000026430835,0.000020507761,1.7183866e-7,0.0003408845,0.000038398106,0.044844817,0.9544289,0.0002162525],"about_ca_topic_score_codex":0.00022694046,"about_ca_topic_score_gemma":0.00007850299,"teacher_disagreement_score":0.20967476,"about_ca_system_score_codex":0.00001819167,"about_ca_system_score_gemma":0.00010181201,"threshold_uncertainty_score":0.99850076},"labels":[],"label_agreement":null},{"id":"W2152164727","doi":"","title":"Nonparametric Identification of Multivariate Mixtures","year":2010,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Japan Society for the Promotion of Science; Social Sciences and Humanities Research Council of Canada; Royal Bank of Canada","keywords":"Nonparametric statistics; Multivariate statistics; Mathematics; Component (thermodynamics); Random variate; Parametric statistics; Statistics; Mixture model; Distribution (mathematics); Econometrics; Random variable; Physics; Mathematical analysis","score_opus":0.03392551006500434,"score_gpt":0.3462154774138904,"score_spread":0.3122899673488861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152164727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12809464,0.0004163952,0.8264787,0.0007206389,0.00293538,0.0017360834,0.000054913093,0.00012493384,0.03943827],"genre_scores_gemma":[0.6662214,0.0016873193,0.33084613,0.00003644492,0.0001474717,0.00013275414,0.000014031111,0.0000352997,0.0008791708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645185,0.00055449817,0.0009376849,0.0011385202,0.000344614,0.0005728568],"domain_scores_gemma":[0.99600315,0.0008104506,0.00047124818,0.002296079,0.00025801177,0.0001610888],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0048520206,0.00026764112,0.0005578143,0.0011544015,0.00009163816,0.0002569098,0.002565059,0.0007120659,0.000011016983],"category_scores_gemma":[0.0010456141,0.00027389932,0.00020320757,0.00043354987,0.0002234031,0.00019096227,0.002035373,0.0023822833,0.0000058563946],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017360884,0.00017785895,0.00017933658,0.00015655695,0.000047038222,0.000009878105,0.00047039406,0.0013628949,0.0123324795,0.03243388,0.000019700634,0.95279264],"study_design_scores_gemma":[0.0008952597,0.000109389104,0.012046848,0.00023934722,0.000016300515,0.000017584092,0.000026566333,0.6749251,0.043552313,0.26258776,0.004598118,0.0009854111],"about_ca_topic_score_codex":0.00011051804,"about_ca_topic_score_gemma":0.00004854126,"teacher_disagreement_score":0.9518072,"about_ca_system_score_codex":0.0002092274,"about_ca_system_score_gemma":0.00052070996,"threshold_uncertainty_score":0.99997133},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06075234635197555,"score_gpt":0.3189824197277949,"score_spread":0.2582300733758193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152173558","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003106367,0.00025677172,0.99308157,0.004484224,0.00079675205,0.00043560943,0.0003208593,0.000031908523,0.00028164778],"genre_scores_gemma":[0.029740108,0.00009613239,0.96812856,0.0014407558,0.00027794164,0.000032915676,0.0000054435336,0.000029889483,0.00024822314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99516946,0.0016693434,0.001236014,0.00052779546,0.0005605113,0.00083685236],"domain_scores_gemma":[0.98203784,0.016103152,0.0005116477,0.0005347194,0.00042745835,0.00038516792],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0046913475,0.0003876604,0.0009881558,0.000063829306,0.00031695983,0.00016772709,0.0013976218,0.00038073974,0.000040445957],"category_scores_gemma":[0.00976174,0.00026228072,0.00044786723,0.0005040288,0.000468673,0.00038291852,0.00034893065,0.001048768,0.000002221831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041005164,0.0003821512,0.00026339502,0.00009853433,0.00014088114,0.0001056255,0.00089835684,0.0069715357,0.0003013212,0.9127663,0.009396788,0.06826508],"study_design_scores_gemma":[0.000879304,0.00045295962,0.0016623178,0.000033832875,0.00007817283,0.00010806151,0.000038158185,0.36527988,0.00013793237,0.63024014,0.00085471495,0.00023453317],"about_ca_topic_score_codex":0.00004183346,"about_ca_topic_score_gemma":0.00003542259,"teacher_disagreement_score":0.35830835,"about_ca_system_score_codex":0.00016179957,"about_ca_system_score_gemma":0.00034376956,"threshold_uncertainty_score":0.99998295},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011329849681937863,"score_gpt":0.22191598189564,"score_spread":0.21058613221370212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152298208","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17590165,0.0005762912,0.82209265,0.00013877185,0.0000859822,0.0009506887,0.0000013229399,0.000019784042,0.00023283792],"genre_scores_gemma":[0.629857,0.0000114708255,0.36983857,0.00003274267,0.000010216051,0.00023540878,6.580859e-7,0.000003672391,0.000010280032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983173,0.00056020555,0.00050207565,0.00031377716,0.00008800294,0.00021863976],"domain_scores_gemma":[0.99900824,0.00013494061,0.00029430864,0.00048361122,0.000033769087,0.000045128043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000388725,0.00015447292,0.0004838354,0.00013445716,0.00002329249,0.000022908165,0.00036416002,0.00012096591,0.000020022595],"category_scores_gemma":[0.000029879062,0.00009709443,0.000044277822,0.00013706688,0.0001180128,0.00008734352,0.000098167715,0.0000913467,0.00001767327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000669699,0.0006301562,0.12627278,0.045112938,0.0005871805,0.000024171093,0.00875141,0.0010842939,0.19528618,0.5137557,0.00007509468,0.10835315],"study_design_scores_gemma":[0.0029745009,0.001977353,0.05667921,0.009489769,0.000102075,0.00067141315,0.0004839793,0.11995126,0.022790318,0.7834322,0.000012384241,0.0014355223],"about_ca_topic_score_codex":0.0000649772,"about_ca_topic_score_gemma":0.0000065446093,"teacher_disagreement_score":0.45395535,"about_ca_system_score_codex":0.000020547486,"about_ca_system_score_gemma":0.000029831974,"threshold_uncertainty_score":0.39593962},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014210250749412177,"score_gpt":0.2553749113308786,"score_spread":0.2411646605814664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152594362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001909945,0.000078116595,0.9960406,0.001484249,0.000026900829,0.000221656,0.000013495167,0.00009428993,0.00013077882],"genre_scores_gemma":[0.852046,0.000012881939,0.14758763,0.0002578177,0.000009408475,0.00005017927,0.0000026912276,0.000010376879,0.000022994842],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990277,0.00008138143,0.00018453061,0.0003211839,0.00021653404,0.0001686467],"domain_scores_gemma":[0.9993622,0.00012088294,0.00009845414,0.00023520441,0.00012971087,0.000053594802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032419537,0.00014698591,0.00013313821,0.00007449997,0.00037498627,0.00010298723,0.00023986775,0.00007517565,0.0000015933962],"category_scores_gemma":[0.000019228359,0.000110228255,0.00005634189,0.00044028283,0.00005028451,0.0003612473,0.0000023334103,0.00033219001,0.00000237718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051910927,0.00026365247,0.0000012260032,0.00015642375,0.000010710467,0.0000017795629,0.0012697049,0.5259038,0.064277545,0.006384107,0.0000053530416,0.40167376],"study_design_scores_gemma":[0.000321152,0.000052511383,0.000007706667,0.00009902601,0.000015436795,0.0000022333516,0.000008751651,0.8963209,0.09646642,0.00658583,0.000011881256,0.00010815225],"about_ca_topic_score_codex":0.0000051054285,"about_ca_topic_score_gemma":0.0000011147025,"teacher_disagreement_score":0.8501361,"about_ca_system_score_codex":0.000039524377,"about_ca_system_score_gemma":0.00010031669,"threshold_uncertainty_score":0.44949776},"labels":[],"label_agreement":null},{"id":"W2152675118","doi":"10.1002/cjs.11131","title":"Regression analysis for a summed missing data problem under an outcome‐dependent sampling scheme","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Missing data; Outcome (game theory); Estimator; Simple random sample; Unobservable; Statistics; Sampling design; Stratified sampling; Covariate; Econometrics; Computer science; Sampling (signal processing); Sample size determination; Regression analysis; Data set; Mathematics; Medicine","score_opus":0.2368295715483372,"score_gpt":0.3906280965375512,"score_spread":0.153798524989214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152675118","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000487342,0.00048157224,0.99758583,0.0005749911,0.000408451,0.00009724107,0.00031179504,0.0000063432794,0.000046404297],"genre_scores_gemma":[0.09792903,0.000006683399,0.9014731,0.00029561264,0.0001843256,9.490222e-7,0.000041588784,0.000012786511,0.000055912013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984129,0.000121302866,0.00053145795,0.00021215739,0.0002371634,0.00048499854],"domain_scores_gemma":[0.9972673,0.00022525816,0.00040306637,0.0006433926,0.00028944146,0.001171548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019749014,0.00014056127,0.00033325434,0.00040019612,0.00023210577,0.00026960866,0.0010908725,0.0000736746,0.00001714992],"category_scores_gemma":[0.0002804942,0.00011528135,0.00006574865,0.00033987913,0.00003718587,0.0008612678,0.00006021619,0.00021306708,8.675377e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027395241,0.000121303274,0.054033305,0.0001484022,0.0009513094,0.000118607975,0.0030708378,0.0008228366,0.0006220901,0.4439173,0.0073896516,0.48877695],"study_design_scores_gemma":[0.0027878878,0.00051822216,0.047402713,0.00042056962,0.0025054142,0.0005518468,0.00058817246,0.60338056,0.00043312274,0.30874994,0.030769715,0.0018918677],"about_ca_topic_score_codex":0.00056463433,"about_ca_topic_score_gemma":0.004551489,"teacher_disagreement_score":0.6025577,"about_ca_system_score_codex":0.00013549402,"about_ca_system_score_gemma":0.0007770676,"threshold_uncertainty_score":0.47010368},"labels":[],"label_agreement":null},{"id":"W2152733965","doi":"10.1109/mlsp.2008.4685450","title":"A data-driven mixture kernel for count data classification using support vector machines","year":2008,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Support vector machine; Computer science; Kernel (algebra); Machine learning; Kernel method; Artificial intelligence; Context (archaeology); Structured support vector machine; Count data; Relevance vector machine; Pattern recognition (psychology); Data modeling; Least squares support vector machine; Dirichlet distribution; Data mining; Mathematics; Statistics","score_opus":0.20931614602714052,"score_gpt":0.3688335232462169,"score_spread":0.15951737721907636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152733965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063213246,0.00007631105,0.99616426,0.0011008019,0.0004023422,0.0003258085,0.0004732427,0.00013937669,0.00068569893],"genre_scores_gemma":[0.02908723,0.00002511379,0.9684286,0.0006926764,0.00026079602,0.000009146458,0.0007971133,0.000016715101,0.00068260985],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982918,0.0000697282,0.00026746717,0.00085913803,0.00024002777,0.00027184412],"domain_scores_gemma":[0.9963662,0.000107749314,0.0001178732,0.0032018954,0.00010453824,0.00010172706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057252205,0.00016518259,0.0002099231,0.00005882522,0.00021536558,0.00011009116,0.003171001,0.00009337967,0.00002555368],"category_scores_gemma":[0.000080044985,0.00013034987,0.000036502734,0.00019558135,0.00004868856,0.0012481529,0.000931165,0.00010907821,0.000011601032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065710716,0.00049655733,0.001662024,0.0001731334,0.00019138397,0.00007730874,0.0013439279,0.00008597064,0.025169985,0.3428838,0.42819688,0.19965333],"study_design_scores_gemma":[0.00024219688,0.000026581454,0.0008798043,0.000006594591,0.00001851889,0.00010207522,0.000003010028,0.9527619,0.0001286784,0.0022578076,0.043383963,0.00018889774],"about_ca_topic_score_codex":0.00005735719,"about_ca_topic_score_gemma":0.000037992188,"teacher_disagreement_score":0.9526759,"about_ca_system_score_codex":0.00003005696,"about_ca_system_score_gemma":0.00024600662,"threshold_uncertainty_score":0.58925617},"labels":[],"label_agreement":null},{"id":"W2153734993","doi":"","title":"Spatio-temporal object recognition using variational learning of an infinite statistical model","year":2013,"lang":"en","type":"article","venue":"European Signal Processing Conference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Inference; Artificial intelligence; Bayesian inference; Machine learning; Statistical model; Bayes' theorem; Object (grammar); Statistical inference; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Feature (linguistics); Activity recognition; Nonparametric statistics; Bayesian probability; Key (lock); Mathematics","score_opus":0.06534754987773936,"score_gpt":0.28984793455442154,"score_spread":0.22450038467668218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153734993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02311837,0.000018180886,0.97075003,0.0000318879,0.000032124295,0.0001195026,0.000006520918,0.00010722729,0.005816173],"genre_scores_gemma":[0.51104856,7.3168576e-7,0.4887945,0.000056480156,0.000036134505,0.0000019055011,0.000021146941,0.000011334256,0.000029217452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979164,0.0006557794,0.00041707107,0.00042469788,0.00033655317,0.00024952632],"domain_scores_gemma":[0.9987342,0.00009074823,0.00030571557,0.00018332335,0.0005486829,0.00013735933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008414881,0.00017560062,0.00020106,0.000117884876,0.00019169837,0.00040613321,0.0004446809,0.000045039185,0.00010633393],"category_scores_gemma":[0.00008627408,0.0001679372,0.000032417,0.00022426856,0.00008522079,0.0013892658,0.00013076399,0.0002844805,0.000033384382],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015972895,0.000090668655,0.00017270146,0.000076899596,0.000010341482,0.000011465916,0.0018340307,0.007275467,0.007461374,0.019069485,0.000018762788,0.96396285],"study_design_scores_gemma":[0.00019052549,0.00009933995,0.0007627788,0.00010832238,0.000009546175,0.000013034899,0.0000150149435,0.9415504,0.0004519337,0.056578994,0.000011837344,0.00020831263],"about_ca_topic_score_codex":0.000046077083,"about_ca_topic_score_gemma":0.0000012432342,"teacher_disagreement_score":0.96375453,"about_ca_system_score_codex":0.000020313739,"about_ca_system_score_gemma":0.0003536725,"threshold_uncertainty_score":0.68482804},"labels":[],"label_agreement":null},{"id":"W2153784930","doi":"10.1002/sim.1101","title":"Estimating cancer prevalence using mixture models for cancer survival","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Hazard; Hazard ratio; Cancer; Disease; Medicine; Population; Cancer survival; Proportional hazards model; Demography; Survival analysis; Environmental health; Internal medicine; Confidence interval; Biology","score_opus":0.10269196972644017,"score_gpt":0.39283956274252446,"score_spread":0.2901475930160843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153784930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017624743,0.003804722,0.9921877,0.0010978213,0.0017667057,0.00034031927,0.00014073588,0.00004222023,0.00044353897],"genre_scores_gemma":[0.010383759,0.000540559,0.9875093,0.0004904645,0.0005070103,0.00008345983,0.0000028893276,0.000020819014,0.00046174863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982766,0.00010800383,0.00038982337,0.00045980336,0.00035661404,0.0004091892],"domain_scores_gemma":[0.99871665,0.0004777276,0.00015462025,0.00036065426,0.00017780295,0.00011256447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007258106,0.00019705303,0.0003676098,0.00010903917,0.00011190824,0.000030390043,0.00051802036,0.00008075648,0.00011245392],"category_scores_gemma":[0.00028829413,0.00016398705,0.000024345467,0.0003221833,0.000105663,0.0002129173,0.00007956147,0.00022528443,6.884934e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000123004,0.00006194762,0.00040526586,0.00082490983,0.000037493028,0.000039952167,0.00545654,0.040674184,0.00067017914,0.39026323,0.008300226,0.55325377],"study_design_scores_gemma":[0.0004894111,0.000041519983,0.000050836818,0.00039983593,0.000026847181,0.0000038399544,0.0000076152273,0.8272811,0.000029495895,0.17130405,0.00020763492,0.00015779547],"about_ca_topic_score_codex":0.00043793215,"about_ca_topic_score_gemma":0.00015958342,"teacher_disagreement_score":0.78660697,"about_ca_system_score_codex":0.00011266331,"about_ca_system_score_gemma":0.00006411364,"threshold_uncertainty_score":0.66871977},"labels":[],"label_agreement":null},{"id":"W2153962481","doi":"10.1109/icassp.2006.1660735","title":"Maximum Likelihood Parameter Estimation for Latent Variable Models Using Sequential Monte Carlo","year":2006,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Monte Carlo method; Latent variable; Expectation–maximization algorithm; Algorithm; Computer science; Maximum likelihood sequence estimation; Estimation theory; Monte Carlo integration; Latent variable model; Mathematical optimization; Hybrid Monte Carlo; Mathematics; Applied mathematics; Markov chain Monte Carlo; Maximum likelihood; Statistics; Artificial intelligence","score_opus":0.03687190593152226,"score_gpt":0.27469221988053777,"score_spread":0.2378203139490155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153962481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017188593,0.00006677175,0.995853,0.00017784873,0.00036882868,0.00037883024,0.0000061565647,0.0001564976,0.001273189],"genre_scores_gemma":[0.11482677,0.000001100226,0.8844926,0.00022081303,0.00008931673,0.00002840619,0.0000032927235,0.0000144893565,0.00032323852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865365,0.000060151502,0.0002874593,0.00041764358,0.00018614065,0.0003949553],"domain_scores_gemma":[0.99924874,0.00007099432,0.00008440213,0.00040865867,0.000115255105,0.00007194062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042433734,0.00016616023,0.00019554944,0.000079475074,0.00012965186,0.00024671265,0.0003391349,0.000106225445,0.000007119298],"category_scores_gemma":[0.000011082981,0.00014316457,0.00010412139,0.00018114963,0.0000161187,0.0008088406,0.00010650844,0.00007567757,0.0000024629771],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013504623,0.000098486875,0.000014268459,0.00003548198,0.000027795506,0.0000044905746,0.000111799054,0.30030543,0.0032807074,0.6260167,0.0009919622,0.06909942],"study_design_scores_gemma":[0.00019337547,0.00001984156,0.0000026244388,0.000007313939,0.000012657476,0.0000074031914,4.136311e-7,0.5452584,0.0015140246,0.452822,0.00005398916,0.000107923006],"about_ca_topic_score_codex":0.0007288204,"about_ca_topic_score_gemma":0.000012557149,"teacher_disagreement_score":0.244953,"about_ca_system_score_codex":0.00006111231,"about_ca_system_score_gemma":0.00008106006,"threshold_uncertainty_score":0.5838082},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06584906040963906,"score_gpt":0.3317421120016123,"score_spread":0.26589305159197324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154036191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3437844,0.0002535867,0.65357155,0.00017711945,0.00024697906,0.00010321741,0.0000012147073,0.00013292466,0.0017289976],"genre_scores_gemma":[0.56000745,0.000008063153,0.4387996,0.00080469175,0.0002219374,0.0000025029635,0.000001131714,0.000016528364,0.00013811169],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822694,0.00006265631,0.00031525397,0.000543033,0.00030228647,0.0005498575],"domain_scores_gemma":[0.9988172,0.00008871638,0.000115144,0.0006414012,0.00014746102,0.00019007156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083512755,0.00022200706,0.00023820487,0.00013059823,0.00017866281,0.000081954764,0.000871208,0.00013835776,0.000007416011],"category_scores_gemma":[0.00004416251,0.00019016358,0.00009410369,0.0005564294,0.000055735032,0.0007275113,0.00018487635,0.0002530669,0.000019867397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023284616,0.0021238846,0.14784315,0.0006091644,0.00043273196,0.0013960991,0.020114837,0.008360011,0.17537765,0.22222362,0.0024102174,0.41887578],"study_design_scores_gemma":[0.0008295099,0.00013036716,0.005053224,0.0001081261,0.00004369495,0.00013264475,0.000046743622,0.77858436,0.11374672,0.09846864,0.0017689642,0.001087029],"about_ca_topic_score_codex":0.000030161556,"about_ca_topic_score_gemma":0.0000067003034,"teacher_disagreement_score":0.77022433,"about_ca_system_score_codex":0.000036228364,"about_ca_system_score_gemma":0.000090365684,"threshold_uncertainty_score":0.77546453},"labels":[],"label_agreement":null},{"id":"W2154185929","doi":"10.1109/cimca.2005.1631337","title":"A New Evolutionary Algorithm for Determining the Optimal Number of Clusters","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Evolutionary algorithm; Cluster analysis; Computer science; Benchmark (surveying); Determining the number of clusters in a data set; Evolutionary computation; Entropy (arrow of time); Fitness function; Set (abstract data type); Selection (genetic algorithm); Cluster (spacecraft); Genetic algorithm; Data mining; Algorithm; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning; Correlation clustering; Canopy clustering algorithm","score_opus":0.017367650353288733,"score_gpt":0.29642518313194044,"score_spread":0.2790575327786517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154185929","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015282015,0.00003617138,0.99393076,0.0014192332,0.0001183791,0.0001393106,0.0000013745135,0.000034080298,0.0041678553],"genre_scores_gemma":[0.0034680099,0.0000019898866,0.99313754,0.0006373452,0.00016487867,0.000006530999,4.9454144e-7,0.0000050071453,0.002578182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993758,0.000032143307,0.00014909875,0.0001681497,0.00011281396,0.00016198409],"domain_scores_gemma":[0.99944323,0.00014155616,0.000048813818,0.00026032978,0.000052930118,0.000053116208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022622591,0.000072597206,0.00009514783,0.000019172143,0.0000588125,0.000027286917,0.00046412964,0.000036440317,0.000028169949],"category_scores_gemma":[0.000011566757,0.00004661506,0.000079572885,0.000094518,0.000020926995,0.00024370005,0.00011771591,0.000047986443,0.000008699188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014485056,0.0000111364825,0.000022788534,0.0000015055942,0.000006379204,1.4818319e-7,0.00021638154,0.00004372449,0.000010232461,0.029827751,0.008307192,0.9615513],"study_design_scores_gemma":[0.00038349017,0.000033300985,0.00027974133,0.000006047471,0.00000657157,0.000017990315,0.000007440223,0.97951597,0.00042778038,0.0071065403,0.012123822,0.00009129861],"about_ca_topic_score_codex":0.00001017327,"about_ca_topic_score_gemma":0.0000015404601,"teacher_disagreement_score":0.9794723,"about_ca_system_score_codex":0.00001522431,"about_ca_system_score_gemma":0.00007106038,"threshold_uncertainty_score":0.1900907},"labels":[],"label_agreement":null},{"id":"W2154400783","doi":"10.1002/sim.821","title":"The use of mixture models for identifying high risks in disease mapping","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Overdispersion; Poisson distribution; Frequentist inference; Econometrics; Statistics; Autocorrelation; Parametric model; Computer science; Parametric statistics; Bayes' theorem; Random effects model; Mixture model; Bayesian probability; Population; Inference; Bayesian inference; Mathematics; Negative binomial distribution; Artificial intelligence; Medicine","score_opus":0.16375861163825192,"score_gpt":0.38095295121453415,"score_spread":0.21719433957628223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154400783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012292905,0.0006145094,0.99582213,0.001503344,0.00041120115,0.00032397918,0.00003947022,0.000013214217,0.00004284402],"genre_scores_gemma":[0.13617104,0.0005985732,0.8627002,0.00029261608,0.000074678916,0.000032528213,0.000009925851,0.000009700317,0.00011069628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985971,0.00015129751,0.00044461357,0.00026180138,0.0002674178,0.0002777869],"domain_scores_gemma":[0.9977051,0.0015307026,0.00013316823,0.00043628903,0.00010598541,0.00008874466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011296282,0.000117803305,0.00024915754,0.00015273086,0.00007415296,0.000035855024,0.00044629682,0.000043467975,0.0000030256924],"category_scores_gemma":[0.00091878546,0.0000804723,0.00002213162,0.00039351714,0.00011632599,0.00018881036,0.00008836517,0.00017939079,2.9493165e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042022693,0.00003246835,0.0006675113,0.00008295868,0.000009189377,0.000076209355,0.0016435715,0.0019260643,0.00007801434,0.8361197,0.0018461444,0.15747611],"study_design_scores_gemma":[0.0004828997,0.000023689465,0.0041305223,0.00016531517,0.000006774045,0.0000016276568,0.000019296247,0.41904944,0.000004820685,0.57492036,0.0011301482,0.00006511829],"about_ca_topic_score_codex":0.0003732572,"about_ca_topic_score_gemma":0.00018402316,"teacher_disagreement_score":0.41712338,"about_ca_system_score_codex":0.00003593862,"about_ca_system_score_gemma":0.00005396484,"threshold_uncertainty_score":0.3281565},"labels":[],"label_agreement":null},{"id":"W2155039816","doi":"10.1109/ccece.2014.6901122","title":"Model verification of GMM clustering based on signature testing","year":2014,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Mixture model; Computer science; Signature (topology); Robustness (evolution); Pattern recognition (psychology); Data mining; Statistic; Data modeling; Artificial intelligence; Statistics; Mathematics","score_opus":0.039803185819632284,"score_gpt":0.2653103332773539,"score_spread":0.22550714745772166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155039816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038472636,0.000004123687,0.97080374,0.00027469784,0.00005962642,0.000057915724,2.9995994e-7,0.00008275537,0.028332096],"genre_scores_gemma":[0.47539017,9.677982e-8,0.52414477,0.00036939338,0.000012452939,0.0000018250412,2.5485372e-7,0.000002905999,0.0000781524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993462,0.00006065672,0.00012798041,0.00021668764,0.00013750736,0.000110975234],"domain_scores_gemma":[0.9992384,0.00015526464,0.000062303145,0.00044132458,0.000064431246,0.000038314538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044027183,0.00007349511,0.00009579139,0.000056019646,0.000037888858,0.00002680088,0.00034287575,0.000055616347,0.0000021233109],"category_scores_gemma":[0.000104724146,0.00005970545,0.00002851433,0.00017332645,0.000010465988,0.00010884385,0.00004582468,0.00008646777,0.0000024227904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073586116,0.00005659335,0.0000430644,0.000042402753,0.000002710925,4.743578e-7,0.00016356412,0.2436723,0.08638907,0.2989211,0.00020611477,0.37049526],"study_design_scores_gemma":[0.00010737357,0.000047906946,0.00010675236,0.000022577386,0.0000014888345,4.7161316e-7,4.6845037e-7,0.9760803,0.0087923715,0.014738295,0.000031000625,0.00007102031],"about_ca_topic_score_codex":0.0000051193374,"about_ca_topic_score_gemma":0.0000017632889,"teacher_disagreement_score":0.732408,"about_ca_system_score_codex":0.00000932093,"about_ca_system_score_gemma":0.000025160816,"threshold_uncertainty_score":0.24347176},"labels":[],"label_agreement":null},{"id":"W2155485631","doi":"10.1139/f04-020","title":"Abundance of minke whales (<i>Balaenoptera acutorostrata</i>) in the Northeast Atlantic: variability in time and space","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Norges Forskningsråd","keywords":"Balaenoptera; Minke whale; Quantile; Abundance (ecology); Cetacea; Aerial survey; Environmental science; Whale; Statistics; Fishery; Physical geography; Geography; Biology; Mathematics; Cartography","score_opus":0.012955797912856667,"score_gpt":0.2227626247937783,"score_spread":0.20980682688092164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155485631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9403857,0.00051199,0.051923264,0.0065666456,0.00008331662,0.00007925898,0.0000019233862,0.0000011810051,0.0004467227],"genre_scores_gemma":[0.9365424,0.000047834183,0.06319235,0.00019087148,0.000017250743,6.513432e-7,8.926718e-8,0.000001488913,0.000007070788],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989487,0.00016268213,0.00030482278,0.00016347898,0.00020097844,0.00021932411],"domain_scores_gemma":[0.99930483,0.00023992386,0.00014166742,0.00013851831,0.000025544456,0.0001495102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026940834,0.000088652305,0.00021130715,0.00012821046,0.000113083915,0.00028596917,0.0006289415,0.000034229703,0.0000039879815],"category_scores_gemma":[0.00017878247,0.000056921894,0.000024523531,0.0004323126,0.0006376899,0.0005619276,0.000022150422,0.00012269657,2.0379542e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015785778,0.000080285696,0.8067105,0.00006665668,0.000015083955,0.0002651197,0.036847863,0.00006015209,0.0003292338,0.06813422,0.00010729395,0.087367795],"study_design_scores_gemma":[0.0014829865,0.0011248869,0.6660395,0.0009040591,0.000026021422,0.0012749088,0.0020223248,0.01088284,0.00029371702,0.31409287,0.001295763,0.0005600871],"about_ca_topic_score_codex":0.008379036,"about_ca_topic_score_gemma":0.031757537,"teacher_disagreement_score":0.24595866,"about_ca_system_score_codex":0.000023024148,"about_ca_system_score_gemma":0.00069965195,"threshold_uncertainty_score":0.99822426},"labels":[],"label_agreement":null},{"id":"W2156524460","doi":"10.1371/journal.pone.0118726","title":"Mixture Models for Distance Sampling Detection Functions","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Raincoast Conservation Foundation","keywords":"Sampling (signal processing); Computer science; Parametric statistics; Monotonic function; Set (abstract data type); Function (biology); Covariate; Sample size determination; Key (lock); Distance sampling; Selection (genetic algorithm); Model selection; Statistics; Data mining; Algorithm; Mathematics; Artificial intelligence; Machine learning; Transect; Biology","score_opus":0.14329120783688942,"score_gpt":0.2796155648453607,"score_spread":0.1363243570084713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156524460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014992214,0.00035892372,0.9958686,0.00053724746,0.00020435094,0.00026127815,0.000009130726,0.00019305923,0.0010681528],"genre_scores_gemma":[0.18947785,0.000007703448,0.8093593,0.00011485922,0.00015623019,0.000084671716,0.00000286647,0.000010863385,0.0007856547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907297,0.00003603058,0.00015682958,0.00030856894,0.00021375911,0.00021184488],"domain_scores_gemma":[0.9991508,0.00006214954,0.00006115981,0.0003887222,0.00020369391,0.00013345096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036173806,0.000101152844,0.0001482045,0.000038763457,0.00012309893,0.000087348606,0.00027574244,0.000073153926,0.0000011583672],"category_scores_gemma":[0.000053791857,0.00009487657,0.000050651794,0.00020476062,0.000014451134,0.00045318686,0.000055955894,0.0001109289,0.000009194633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016430294,0.002039907,0.000051518513,0.0003592483,0.00044211454,0.0000052391783,0.0028767919,0.002795385,0.05653655,0.55843204,0.0016368023,0.37466007],"study_design_scores_gemma":[0.00036004887,0.00011201381,0.0000093982035,0.00006656603,0.000043580403,0.0000024528294,0.000012798166,0.634489,0.012755349,0.35097906,0.0009857928,0.00018392649],"about_ca_topic_score_codex":0.0000054615075,"about_ca_topic_score_gemma":0.000010196922,"teacher_disagreement_score":0.6316936,"about_ca_system_score_codex":0.00005041762,"about_ca_system_score_gemma":0.00004316205,"threshold_uncertainty_score":0.38689542},"labels":[],"label_agreement":null},{"id":"W2156604399","doi":"","title":"Bayesian Nonparametric Modeling of Suicide Attempts","year":2012,"lang":"en","type":"article","venue":"Cambridge University Engineering Department Publications Database","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"","keywords":"Computer science; Nonparametric statistics; Generative model; Multinomial logistic regression; Multinomial distribution; Population; Econometrics; Sample (material); Gibbs sampling; Discrete choice; Laplace's method; Bayesian probability; Artificial intelligence; Machine learning; Data mining; Mathematics; Generative grammar","score_opus":0.0223815379823416,"score_gpt":0.23720323372443192,"score_spread":0.2148216957420903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156604399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007500955,0.00026410623,0.9895854,0.00024756644,0.00017612368,0.00019315274,0.00013137222,0.00022516532,0.0016761516],"genre_scores_gemma":[0.54448086,0.000035368193,0.4549687,0.000029475388,0.000035344812,0.0000030303984,0.00014424544,0.0000091104785,0.00029386554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885917,0.00005209358,0.00019758673,0.00029230912,0.00021100893,0.00038785406],"domain_scores_gemma":[0.9983915,0.000096510856,0.000081516664,0.0009977749,0.00013016244,0.00030249645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004433525,0.00015702094,0.00017900254,0.00064433913,0.00010059167,0.000042434152,0.00076068635,0.00005384408,0.000005148883],"category_scores_gemma":[0.000110934125,0.00018120774,0.000084021085,0.0014020726,0.000019893767,0.0017573581,0.00032220868,0.00010431805,0.000013775078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004667023,0.0003127355,0.0015820953,0.0000604863,0.000075127595,0.0000056660974,0.00007450324,0.0073500304,0.0011664744,0.98192775,0.0049827723,0.0024576904],"study_design_scores_gemma":[0.00028131934,0.000016072026,0.0009961275,0.000023236928,0.000039070015,0.000017263483,0.000010246867,0.9806098,0.0011616773,0.000009965708,0.016561083,0.0002741825],"about_ca_topic_score_codex":0.00003125159,"about_ca_topic_score_gemma":7.588305e-7,"teacher_disagreement_score":0.9819178,"about_ca_system_score_codex":0.00012887595,"about_ca_system_score_gemma":0.000070266506,"threshold_uncertainty_score":0.73894376},"labels":[],"label_agreement":null},{"id":"W2157288200","doi":"10.1016/j.tpb.2008.03.003","title":"Faà di Bruno’s formula and the distributions of random partitions in population genetics and physics","year":2008,"lang":"en","type":"article","venue":"Theoretical Population Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Dirichlet distribution; Sampling (signal processing); Population; Hypergeometric distribution; Population genetics; Statistical physics; Mathematics; Physics; Statistics; Mathematical analysis; Demography","score_opus":0.015244650660530693,"score_gpt":0.27740965619307684,"score_spread":0.2621650055325461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157288200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29597804,0.00014206693,0.702996,0.0005796084,0.00003420298,0.00013654516,0.00000747165,0.000012253522,0.00011377435],"genre_scores_gemma":[0.97343016,0.00013814594,0.026283968,0.00006123866,0.000028270755,0.000011304706,0.00004077319,0.0000030797635,0.0000030389322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990345,0.0003454572,0.00026015562,0.00017122137,0.00005441313,0.00013424014],"domain_scores_gemma":[0.9993408,0.00032613892,0.00007077953,0.00019116205,0.000032177802,0.00003895501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037361195,0.000079427344,0.00020391222,0.000026074054,0.0001228047,0.000010395808,0.000105429404,0.000080256,0.000004024836],"category_scores_gemma":[0.0001151319,0.000052541414,0.00003373622,0.00015301662,0.0006301114,0.00007348672,0.00008306688,0.000087461354,3.9968572e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003010531,0.000016797669,0.024876134,0.0000029403648,0.000003413219,2.361606e-7,0.00016060074,0.000019985422,0.00006801288,0.9611087,0.000001818824,0.013711272],"study_design_scores_gemma":[0.00090437673,0.000024597495,0.16742142,0.000004413569,0.0000070147194,0.0000102366575,0.0000013797313,0.05990577,0.000067920446,0.77159417,0.0000073160168,0.000051393705],"about_ca_topic_score_codex":0.000069153924,"about_ca_topic_score_gemma":0.000009982412,"teacher_disagreement_score":0.67745215,"about_ca_system_score_codex":0.000008959549,"about_ca_system_score_gemma":0.000007440742,"threshold_uncertainty_score":0.23216717},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.028275605383895706,"score_gpt":0.30047637550832457,"score_spread":0.27220077012442884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157487910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027748453,0.00006083906,0.9980765,0.0008782992,0.00020885562,0.00027553813,0.00008529455,0.00009191694,0.000045247278],"genre_scores_gemma":[0.66940546,0.000050547937,0.32979515,0.00045348448,0.000049579605,0.00001743213,0.00004834816,0.000008478099,0.00017153102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808556,0.000090430665,0.0003208734,0.00095188717,0.00025922686,0.00029201616],"domain_scores_gemma":[0.9988016,0.00008535276,0.00013190055,0.00075866585,0.000080279264,0.00014221325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004921359,0.00027411946,0.00036109585,0.00046193405,0.00035403032,0.00020599694,0.00059614604,0.00009762505,0.000017226235],"category_scores_gemma":[0.0000043081377,0.00023584311,0.00018010855,0.0006794218,0.000026374193,0.00057371316,0.000009525882,0.0003609981,0.0000024788242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031391766,0.00020186407,0.0000087196695,0.000015307003,0.0002255241,0.0000030661613,0.00006273248,0.027503103,0.001259149,0.00014369587,0.000074293814,0.97047114],"study_design_scores_gemma":[0.00013352046,0.00018213065,0.0003558447,0.000014201001,0.0003639947,0.00005449178,0.0000037718423,0.95717466,0.04027386,0.0011447308,0.00003693989,0.00026188308],"about_ca_topic_score_codex":0.0003111201,"about_ca_topic_score_gemma":0.00020988873,"teacher_disagreement_score":0.97020924,"about_ca_system_score_codex":0.000039022805,"about_ca_system_score_gemma":0.000026693993,"threshold_uncertainty_score":0.9617403},"labels":[],"label_agreement":null},{"id":"W2157859776","doi":"10.2307/3315930","title":"Bayesian identifiability and misclassification in multinomial data","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identifiability; Multinomial distribution; Dirichlet distribution; Gibbs sampling; Bayesian probability; Computer science; Prior information; Type (biology); Sampling (signal processing); Mathematics; Statistics; Econometrics; Algorithm; Artificial intelligence","score_opus":0.06701990393281865,"score_gpt":0.2768366024229348,"score_spread":0.20981669849011614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157859776","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033555548,0.00014930971,0.99498916,0.0009317223,0.00030489778,0.000054453172,0.00010289316,0.0000022588583,0.000109728106],"genre_scores_gemma":[0.41154492,0.000010864844,0.5883327,0.0000624641,0.000034445995,2.059011e-7,0.0000035846967,0.0000028916857,0.000007907371],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991503,0.000073292606,0.00032704353,0.00017429068,0.000101055164,0.00017401775],"domain_scores_gemma":[0.99891394,0.000077793644,0.00014087035,0.00039420486,0.00010193287,0.00037127893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000818007,0.000069020105,0.0001353662,0.00016327201,0.000059439197,0.00014119004,0.0006405279,0.00004386018,0.000005276032],"category_scores_gemma":[0.00036991676,0.00006677449,0.000010757636,0.00013641422,0.000078387886,0.0003847745,0.00003695579,0.00017411534,0.0000011110442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009455153,0.000050031573,0.007985794,0.000056546465,0.000022412563,0.00076491316,0.0027906457,0.00022837489,0.0003183768,0.4518792,0.0032007226,0.5326935],"study_design_scores_gemma":[0.001947135,0.00013535956,0.13869639,0.000139329,0.000029887931,0.000475915,0.00008595503,0.07410814,0.00019888266,0.7791373,0.004651542,0.00039413432],"about_ca_topic_score_codex":0.0030678601,"about_ca_topic_score_gemma":0.036178086,"teacher_disagreement_score":0.5322994,"about_ca_system_score_codex":0.000121803714,"about_ca_system_score_gemma":0.0011877931,"threshold_uncertainty_score":0.98140913},"labels":[],"label_agreement":null},{"id":"W2158389509","doi":"10.1371/journal.pone.0137278","title":"A Bayesian Alternative to Mutual Information for the Hierarchical Clustering of Dependent Random Variables","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Université de Montréal; Deutsche Forschungsgemeinschaft","keywords":"Mutual information; Cluster analysis; Hierarchical clustering; Bayes factor; Artificial intelligence; Curse of dimensionality; Bayes' theorem; Pattern recognition (psychology); Bayesian probability; Computer science; Mathematics; Bayesian hierarchical modeling; Dimensionality reduction; Data mining; Machine learning","score_opus":0.06195703519572359,"score_gpt":0.2702648390218102,"score_spread":0.2083078038260866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158389509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001383478,0.000026608308,0.9956644,0.0012926856,0.00010700572,0.0005879488,0.000008825575,0.000028856059,0.0009001718],"genre_scores_gemma":[0.2021345,0.0000039550746,0.7972242,0.00039853272,0.000085495405,0.00008634711,0.0000015004618,0.0000040991617,0.00006135279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990671,0.00008527546,0.00022788924,0.00012393501,0.00033485785,0.00016091827],"domain_scores_gemma":[0.99900156,0.00034717767,0.00008049854,0.00028830173,0.00017207258,0.00011041233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009223925,0.000079858495,0.00017660495,0.0000694419,0.000053948814,0.00007688006,0.00053063675,0.000035247336,0.000002146912],"category_scores_gemma":[0.00032785,0.00005481646,0.000036863275,0.00012634997,0.00001920366,0.00039401097,0.00021421276,0.000081817045,0.0000048915385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017869412,0.001237294,0.000112911526,0.00035859234,0.00092206395,0.0000049478585,0.06973304,0.008651806,0.007190498,0.42482644,0.0013119064,0.48386356],"study_design_scores_gemma":[0.0015144624,0.00020764962,0.00001988886,0.000059959682,0.00003167308,0.0000024770004,0.000043827513,0.95212126,0.011210458,0.03446454,0.00022547011,0.00009835572],"about_ca_topic_score_codex":0.00003769046,"about_ca_topic_score_gemma":0.0000117015725,"teacher_disagreement_score":0.9434694,"about_ca_system_score_codex":0.000027672044,"about_ca_system_score_gemma":0.000064094245,"threshold_uncertainty_score":0.22353505},"labels":[],"label_agreement":null},{"id":"W2160327809","doi":"10.1007/s11222-007-9037-8","title":"Particle methods for maximum likelihood estimation in latent variable models","year":2007,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Expectation–maximization algorithm; Latent variable; Monte Carlo method; Maximum likelihood sequence estimation; Latent variable model; Markov chain Monte Carlo; Particle filter; Maximum likelihood; Mathematics; Algorithm; Computer science; Estimation theory; Likelihood function; Statistics; Mathematical optimization","score_opus":0.026735168533815724,"score_gpt":0.3430897622378254,"score_spread":0.31635459370400965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160327809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043446483,0.00020941158,0.9985854,0.00007499186,0.00018803455,0.00019056707,0.000005747073,0.000042698906,0.00026866986],"genre_scores_gemma":[0.10026169,0.0000063638026,0.8995356,0.00014783451,0.000022404714,0.0000036012377,0.0000029549647,0.000007887227,0.000011693726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988686,0.000094469964,0.0003035949,0.00028384596,0.000081385384,0.00036810935],"domain_scores_gemma":[0.99884653,0.0007417419,0.000079686564,0.00016720418,0.000072434814,0.00009239038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031318404,0.00010332841,0.00016363247,0.000053841588,0.00011427338,0.000114192495,0.00016025003,0.000047043464,8.3619193e-7],"category_scores_gemma":[0.00009461955,0.00010050897,0.000016683201,0.00019909008,0.000017116226,0.00014307945,0.000117096,0.00008881458,4.6993955e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027233257,0.000014682416,0.00001779875,0.000015081358,0.0000029065422,0.0000019411193,0.00031042358,0.0013251358,0.00012150006,0.45494843,0.00001369469,0.5432257],"study_design_scores_gemma":[0.00017029289,0.000026804457,0.00011147567,0.0000123194695,0.0000032366984,0.0000038084595,0.0000044274,0.52395666,0.00024427153,0.47536352,0.00003591746,0.00006723077],"about_ca_topic_score_codex":0.000033699704,"about_ca_topic_score_gemma":0.0000057180678,"teacher_disagreement_score":0.5431585,"about_ca_system_score_codex":0.00002353942,"about_ca_system_score_gemma":0.000034724966,"threshold_uncertainty_score":0.4098637},"labels":[],"label_agreement":null},{"id":"W2160628682","doi":"10.1002/sim.5374","title":"A Bayesian method for estimating prevalence in the presence of a hidden sub‐population","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Posterior probability; Bayesian probability; Population; Sampling (signal processing); Markov chain Monte Carlo; Sample (material); Gibbs sampling; Computer science; Econometrics; Mathematics; Demography","score_opus":0.03508214765957837,"score_gpt":0.3825456648440279,"score_spread":0.34746351718444957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160628682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038890913,0.0003120461,0.9978408,0.00048380785,0.00030539682,0.00047313748,0.000014223841,0.00001004104,0.00017164367],"genre_scores_gemma":[0.18028511,0.000013056387,0.81938034,0.00013435508,0.000112987786,0.000051283714,0.0000046328787,0.000005347893,0.000012909654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983439,0.000446798,0.00042804275,0.00019799112,0.00030747234,0.00027579427],"domain_scores_gemma":[0.9967179,0.0026395551,0.0001722537,0.00036397143,0.000058970978,0.0000473951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004819502,0.000103282124,0.00024140488,0.00012244412,0.000035925117,0.000010447051,0.00052049675,0.000045196102,0.0000045000943],"category_scores_gemma":[0.0023150495,0.000069793314,0.000015787367,0.000375731,0.00005657019,0.00017924294,0.000055069475,0.00015151386,2.6427932e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010145504,0.000055416316,0.005506428,0.00038778124,0.0000039696697,0.000003586534,0.011613361,0.00008183571,0.00031395658,0.5573747,0.0005633028,0.42408547],"study_design_scores_gemma":[0.00035370924,0.00008912222,0.017814754,0.00023888303,0.000012701403,0.000009257713,0.000054012886,0.6848104,0.00008490676,0.29643264,0.000022578213,0.000077052006],"about_ca_topic_score_codex":0.00018717161,"about_ca_topic_score_gemma":0.000049675393,"teacher_disagreement_score":0.68472856,"about_ca_system_score_codex":0.00002597255,"about_ca_system_score_gemma":0.000026227613,"threshold_uncertainty_score":0.28460887},"labels":[],"label_agreement":null},{"id":"W2160798324","doi":"10.1002/asmb.463","title":"A generalized multinomial discriminant procedure with applications","year":2002,"lang":"en","type":"article","venue":"Applied Stochastic Models in Business and Industry","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Multinomial distribution; Discriminant; Classifier (UML); Linear discriminant analysis; Mathematics; Applied mathematics; Artificial intelligence; Computer science; Mathematical optimization; Pattern recognition (psychology); Statistics","score_opus":0.031449426706780595,"score_gpt":0.2408952657679715,"score_spread":0.2094458390611909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160798324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009983297,0.00017422289,0.985952,0.000670854,0.000039075807,0.0006280581,0.000003614148,0.00007213666,0.002476701],"genre_scores_gemma":[0.7536882,0.000017020393,0.2452342,0.00022652624,0.00008966677,0.0005950856,0.0000023433754,0.000017775892,0.0001291738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854493,0.000019664016,0.00026465973,0.0006132358,0.00019409726,0.00036341694],"domain_scores_gemma":[0.9992207,0.00003965463,0.00009398891,0.00044906297,0.00006821749,0.0001283367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013663479,0.00025081035,0.00029425177,0.00012805498,0.00014919971,0.000115801864,0.00039403446,0.00029033492,0.000009617984],"category_scores_gemma":[0.00000666269,0.00019256883,0.000018106824,0.000613059,0.00010391954,0.00029283846,0.00015668724,0.00043356247,0.0000027186652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024897163,0.00017397107,0.0000151024315,0.000053015883,0.000010685732,0.000007645481,0.00078681967,0.016612593,0.00022816201,0.89078456,0.00012795573,0.09117458],"study_design_scores_gemma":[0.0020742144,0.000026470414,0.00048298915,0.00008498338,0.00002245006,0.00007673432,0.000046651447,0.92754006,0.000048490892,0.06893911,0.00015031669,0.00050752173],"about_ca_topic_score_codex":0.00004184535,"about_ca_topic_score_gemma":0.000011390117,"teacher_disagreement_score":0.9109275,"about_ca_system_score_codex":0.000026739255,"about_ca_system_score_gemma":0.0000504926,"threshold_uncertainty_score":0.7852729},"labels":[],"label_agreement":null},{"id":"W2161202741","doi":"10.5555/1036843.1036873","title":"From fields to trees","year":2004,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gibbs sampling; Markov chain Monte Carlo; Graphical model; Tree (set theory); Sampling (signal processing); Computer science; Focus (optics); Markov chain; Importance sampling; Posterior probability; Algorithm; Mathematics; Belief propagation; Statistics; Artificial intelligence; Bayesian probability; Monte Carlo method; Machine learning; Combinatorics","score_opus":0.04739542792282484,"score_gpt":0.3219355585509258,"score_spread":0.27454013062810095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161202741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02321407,0.00005140634,0.9681598,0.006199467,0.00061251776,0.00018950923,0.0000042038623,0.00009956339,0.0014694381],"genre_scores_gemma":[0.68355876,0.0000077446675,0.3148934,0.0013154785,0.00015549504,0.000019054993,0.0000014397219,0.000005988549,0.00004262269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99836385,0.00007507892,0.00040080526,0.000549086,0.00022843397,0.00038272474],"domain_scores_gemma":[0.9989518,0.00016664286,0.000046453286,0.00061542675,0.000058101105,0.00016160327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037113132,0.00016981101,0.00021111949,0.00016761005,0.000070090544,0.00014906221,0.0010409734,0.00011305069,0.00005402944],"category_scores_gemma":[0.00018116295,0.00015785938,0.000071280774,0.0007039856,0.00004564588,0.00021873742,0.00018852162,0.00022350412,0.000271456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014134363,0.000071658644,0.000009125511,0.0000012705898,0.0000035709154,0.000029909766,0.0044996347,0.042433176,0.0010638203,0.49234366,0.000059702095,0.45947033],"study_design_scores_gemma":[0.000031346113,0.00008257264,0.00006229851,0.000045368106,0.0000018373273,0.0000019104332,0.00012716465,0.030478273,0.03197251,0.9363816,0.0005910659,0.00022405977],"about_ca_topic_score_codex":0.00386142,"about_ca_topic_score_gemma":0.004089796,"teacher_disagreement_score":0.6603447,"about_ca_system_score_codex":0.00010649533,"about_ca_system_score_gemma":0.000094543684,"threshold_uncertainty_score":0.6437319},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.011245201410113275,"score_gpt":0.2784303576061979,"score_spread":0.2671851561960846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162021827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044899206,0.000765975,0.9869781,0.007298457,0.00013934722,0.00020996947,0.000092845934,0.000011562371,0.00001378097],"genre_scores_gemma":[0.31129026,0.00006376345,0.6876686,0.00083046645,0.00010619623,0.000008544285,0.0000020192779,0.000007758885,0.000022398019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986659,0.000043074975,0.00043039402,0.00019399448,0.00045871406,0.00020788243],"domain_scores_gemma":[0.99829435,0.00053574867,0.0002871034,0.00009981736,0.0006210398,0.0001619088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000533215,0.0001602078,0.00025095118,0.000092942704,0.00023250075,0.00012463436,0.00040547265,0.00007843803,8.961514e-7],"category_scores_gemma":[0.00015470175,0.0000978698,0.00010298055,0.00027792208,0.00010354685,0.00019004165,0.000045864937,0.00030212736,1.5718317e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007410368,0.00010336055,0.00004695313,0.000090697315,0.00007770558,0.000018578694,0.0006759507,0.16432518,0.000007320963,0.8034155,0.001639788,0.029524885],"study_design_scores_gemma":[0.00045593275,0.00010783026,0.0009492292,0.000024135785,0.000024963576,0.00009606746,0.0000069239277,0.4646638,0.0000032814426,0.53348213,0.00010804754,0.00007762013],"about_ca_topic_score_codex":0.0000024836431,"about_ca_topic_score_gemma":0.0000044541025,"teacher_disagreement_score":0.30680034,"about_ca_system_score_codex":0.000017649432,"about_ca_system_score_gemma":0.00025149604,"threshold_uncertainty_score":0.39910147},"labels":[],"label_agreement":null},{"id":"W2162339969","doi":"10.1109/tip.2005.851710","title":"A stochastic method for Bayesian estimation of hidden Markov random field models with application to a color model","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Health and Medical Research Fund","keywords":"Maximum a posteriori estimation; Markov random field; Image segmentation; Mathematics; Pattern recognition (psychology); Random field; Artificial intelligence; Hidden Markov model; Expectation–maximization algorithm; Algorithm; Estimator; Segmentation; Computer science; Maximum likelihood; Statistics","score_opus":0.012764499005457546,"score_gpt":0.29953286071274227,"score_spread":0.2867683617072847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162339969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045371395,0.000024219657,0.99689096,0.0016992877,0.000029432058,0.0010253912,0.000010810543,0.00012412756,0.00015042559],"genre_scores_gemma":[0.3587546,8.79416e-7,0.6403991,0.00030984706,0.0000151519225,0.00043307652,6.466036e-7,0.000016406362,0.00007030956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867874,0.00004381714,0.00032812447,0.00046498855,0.00023569085,0.00024861124],"domain_scores_gemma":[0.99892354,0.00024648686,0.00014385841,0.00035310935,0.00021991086,0.00011309589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047247543,0.00019342388,0.00028469568,0.00022247856,0.00021039101,0.00011370905,0.0003427262,0.00008577319,0.0000019634476],"category_scores_gemma":[0.000011124811,0.00016994702,0.000084099636,0.00041056692,0.000023769284,0.0009399671,0.0000029212918,0.00014280903,0.0000013904734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019288326,0.000060477472,4.872572e-9,0.000048835424,0.000007781894,1.0860681e-7,0.0006430259,0.48088735,0.0038078632,0.00042796717,0.000011881547,0.51391184],"study_design_scores_gemma":[0.001034734,0.00016354868,1.02336905e-7,0.00009737791,0.000055082688,0.000010099655,0.000010763772,0.93180937,0.05209454,0.014537158,0.00000271814,0.00018450952],"about_ca_topic_score_codex":0.0000127696385,"about_ca_topic_score_gemma":0.000018583387,"teacher_disagreement_score":0.5137273,"about_ca_system_score_codex":0.000056869907,"about_ca_system_score_gemma":0.00016474907,"threshold_uncertainty_score":0.6930238},"labels":[],"label_agreement":null},{"id":"W2162435505","doi":"10.1002/cjs.11261","title":"Bayesian transformation family selection: Moving toward a transformed Gaussian universe","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Technical University of Athens","keywords":"Transformation (genetics); Mathematics; Skewness; Markov chain Monte Carlo; Posterior probability; Power transform; Applied mathematics; Bayesian probability; Markov chain; Statistical physics; Econometrics; Computer science; Statistics; Discrete mathematics; Physics","score_opus":0.0368886466207037,"score_gpt":0.2480021856097321,"score_spread":0.2111135389890284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162435505","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025700332,0.00013016896,0.9916986,0.0012624376,0.0005893786,0.00008720129,0.000043823926,0.000013704543,0.0059176423],"genre_scores_gemma":[0.37868726,0.000019938825,0.62084454,0.00027839353,0.00008965284,6.093579e-7,0.0000024124313,0.0000092875125,0.0000678927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876744,0.000113314585,0.00040133277,0.00011973575,0.00026404342,0.0003341551],"domain_scores_gemma":[0.99808556,0.00004160167,0.00015882756,0.00012017619,0.00041244828,0.0011813813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059188314,0.000135142,0.00021636348,0.00036748697,0.00012462707,0.00016860246,0.0004292302,0.00008213657,0.00001691787],"category_scores_gemma":[0.00006421469,0.00012847812,0.0000605737,0.0003966064,0.000052301355,0.0007789854,0.0000059510426,0.0002718277,0.0000048630304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000218763,0.000016706983,0.0000945026,0.000042909884,0.000055214114,0.00048985454,0.01999066,0.0004898834,0.000100391306,0.53529876,0.012767405,0.43063182],"study_design_scores_gemma":[0.0050695767,0.0018476817,0.0023457624,0.00032457203,0.00022115442,0.003097891,0.0039504035,0.31291077,0.0008592533,0.5363736,0.13160554,0.0013937558],"about_ca_topic_score_codex":0.0011124983,"about_ca_topic_score_gemma":0.0046289153,"teacher_disagreement_score":0.42923805,"about_ca_system_score_codex":0.00031378455,"about_ca_system_score_gemma":0.0034884026,"threshold_uncertainty_score":0.61882764},"labels":[],"label_agreement":null},{"id":"W2162721377","doi":"10.1109/icassp.2007.366870","title":"Bayesian Unsupervised Signal Classification by Dirichlet Process Mixtures of Gaussian Processes","year":2007,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dirichlet process; Cluster analysis; Mixture model; Dirichlet distribution; Pattern recognition (psychology); Hierarchical Dirichlet process; Computer science; A priori and a posteriori; Gibbs sampling; Bayesian probability; Markov chain Monte Carlo; Gaussian process; Algorithm; Artificial intelligence; Gaussian; Mathematics; Latent Dirichlet allocation; Topic model; Physics","score_opus":0.01779959529025576,"score_gpt":0.28940592958715267,"score_spread":0.2716063342968969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162721377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019391458,0.0003913294,0.9764449,0.0008732301,0.000071983224,0.00024136913,0.0000045437096,0.00016587721,0.019867636],"genre_scores_gemma":[0.7206324,0.000015671982,0.27854288,0.00035768378,0.00004698776,0.000011483879,0.000006744848,0.00001241162,0.00037374397],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99813443,0.00007440121,0.00045601669,0.0005120622,0.00042885958,0.00039423665],"domain_scores_gemma":[0.9987045,0.00016388268,0.00018332302,0.00047023475,0.00029446304,0.00018358305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008046857,0.00021242679,0.0002570606,0.00015613071,0.00009877594,0.00008626081,0.00094440696,0.00014336681,0.000051784984],"category_scores_gemma":[0.000064250664,0.00016495706,0.000059666174,0.0010068344,0.000081241036,0.00051426305,0.000060506056,0.00014531735,0.000004922034],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010205431,0.0010005556,0.0028486978,0.0010471428,0.00008925374,0.000020609905,0.004813355,0.000014475646,0.19607818,0.21668728,0.012022251,0.56527615],"study_design_scores_gemma":[0.00094603637,0.0003156973,0.002510854,0.000120952085,0.000033798013,0.00003089103,0.00022199118,0.03290011,0.8724024,0.08647071,0.003178235,0.000868275],"about_ca_topic_score_codex":0.000018694675,"about_ca_topic_score_gemma":0.000014861107,"teacher_disagreement_score":0.71869326,"about_ca_system_score_codex":0.00002084632,"about_ca_system_score_gemma":0.00017630047,"threshold_uncertainty_score":0.6726754},"labels":[],"label_agreement":null},{"id":"W2163124253","doi":"10.1214/ejp.v12-417","title":"Large Deviations for Dirichlet Processes and Poisson-Dirichlet Distribution with Two Parameters","year":2007,"lang":"en","type":"article","venue":"Electronic Journal of Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Concentration parameter; Dirichlet distribution; Poisson distribution; Dirichlet process; Generalized Dirichlet distribution; Distribution (mathematics); Dirichlet's principle; Applied mathematics; Hierarchical Dirichlet process; Infinity; Mathematical analysis; Statistics; Boundary value problem","score_opus":0.012735148290248875,"score_gpt":0.28026614893915686,"score_spread":0.267531000648908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163124253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100821584,0.0013044233,0.8963254,0.0011010972,0.000049295693,0.0003333951,0.00000871444,0.00002201802,0.00003406502],"genre_scores_gemma":[0.7795052,0.000055003005,0.22027266,0.00008941151,0.000047892445,0.000008545758,0.0000033164931,0.000006098123,0.000011878557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835974,0.00010568013,0.00040512273,0.00026646795,0.000239696,0.00062331394],"domain_scores_gemma":[0.9983369,0.00040105765,0.00034982574,0.00023267862,0.0005487242,0.00013082204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040720575,0.0001451071,0.0002530671,0.000059396047,0.000156043,0.000082774866,0.00033184636,0.000052273423,0.0000010116012],"category_scores_gemma":[0.00049928395,0.000103443024,0.00006739606,0.00044227886,0.000056475455,0.00051069463,0.000042287917,0.0002953549,2.2787754e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026582528,0.00041869123,0.004019485,0.00017346654,0.00011541573,0.000005710441,0.00071981427,0.000027488964,0.00032038923,0.9660374,0.00031471375,0.027581621],"study_design_scores_gemma":[0.0017263546,0.0013424236,0.0034095894,0.000052768508,0.00007147252,0.00025407388,0.000026761069,0.001094611,0.003686847,0.98379904,0.0042784186,0.0002576407],"about_ca_topic_score_codex":0.000003764621,"about_ca_topic_score_gemma":0.0001408666,"teacher_disagreement_score":0.6786836,"about_ca_system_score_codex":0.0002355008,"about_ca_system_score_gemma":0.0006350163,"threshold_uncertainty_score":0.42182842},"labels":[],"label_agreement":null},{"id":"W2163587445","doi":"10.1002/cjs.11133","title":"Nonparametric hierarchical Bayes analysis of binomial data via Bernstein polynomial priors","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Dirichlet process; Mathematics; Prior probability; Statistics; Markov chain Monte Carlo; Estimator; Dirichlet distribution; Bayes' theorem; Posterior probability; Bayesian probability; Econometrics","score_opus":0.03673095030733958,"score_gpt":0.28082459092127376,"score_spread":0.24409364061393418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163587445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011044667,0.00055319944,0.9864344,0.0001770493,0.0008316333,0.000054227145,0.00070722157,0.0000035850692,0.0001939934],"genre_scores_gemma":[0.4436541,0.00001547171,0.55601466,0.00008155164,0.00018340562,1.9126698e-7,0.000015508649,0.0000069854977,0.000028135137],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980954,0.00018614954,0.0006921441,0.00019844229,0.0003502958,0.00047758647],"domain_scores_gemma":[0.9968615,0.0005475045,0.00047633174,0.00073337485,0.00023566338,0.0011456305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014351174,0.00014814755,0.0005176732,0.0015088343,0.000089529705,0.00009375346,0.0016884159,0.00010789517,0.00006421629],"category_scores_gemma":[0.0006169311,0.0001336422,0.00011420306,0.0015592352,0.00014498319,0.0005067346,0.00011741683,0.00036093206,0.0000033585052],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004435674,0.00015970726,0.045821447,0.0000624128,0.002169904,0.00033193702,0.0033716597,0.0002988223,0.00037732197,0.15850918,0.028418614,0.7604346],"study_design_scores_gemma":[0.0033085004,0.0013625452,0.37743688,0.00018230933,0.007074125,0.000953677,0.0001446153,0.52435744,0.0012361748,0.032495502,0.049171463,0.0022767528],"about_ca_topic_score_codex":0.0026177785,"about_ca_topic_score_gemma":0.005776705,"teacher_disagreement_score":0.7581579,"about_ca_system_score_codex":0.0001099228,"about_ca_system_score_gemma":0.0014001863,"threshold_uncertainty_score":0.54497707},"labels":[],"label_agreement":null},{"id":"W2163654519","doi":"10.1002/sim.4321","title":"Bayesian inference on joint models of HIV dynamics for time‐to‐event and longitudinal data with skewness and covariate measurement errors","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Covariate; Skewness; Bayesian probability; Computer science; Event (particle physics); Econometrics; Random effects model; Bayesian inference; Statistics; Inference; Mathematics; Artificial intelligence; Medicine","score_opus":0.1320334529644685,"score_gpt":0.3338156581999011,"score_spread":0.2017822052354326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163654519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018443483,0.000056786335,0.99833655,0.0004856929,0.00006663584,0.00041042382,0.00017199325,0.00001677712,0.00027072948],"genre_scores_gemma":[0.26855335,0.000019635898,0.7312615,0.00008902454,0.000013368165,0.00001315952,0.000017473576,0.000011952774,0.00002056529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846715,0.0000804223,0.000355667,0.0004874415,0.0003904965,0.00021882151],"domain_scores_gemma":[0.9987145,0.00017399107,0.000137464,0.00063424645,0.00019421491,0.00014554824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016842356,0.00017157636,0.00038273504,0.00014571777,0.00003817459,0.000012873842,0.00041188006,0.00004161515,0.0000050380254],"category_scores_gemma":[0.00028232177,0.00012393208,0.000006250034,0.00015790122,0.00014858686,0.0001213279,0.00022880283,0.00011834497,3.9647566e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000160446,0.00011584914,0.00034409182,0.00021127825,0.000046558438,0.000027992182,0.0025588998,0.00024033041,0.0000628947,0.90991294,0.0004398616,0.085878834],"study_design_scores_gemma":[0.00078872574,0.0007125216,0.0027074935,0.00035543376,0.000034088716,0.000007320061,0.000020376581,0.7166032,0.00003464633,0.27858853,0.000015174231,0.00013244852],"about_ca_topic_score_codex":0.00012483349,"about_ca_topic_score_gemma":0.00026082553,"teacher_disagreement_score":0.7163629,"about_ca_system_score_codex":0.000044268105,"about_ca_system_score_gemma":0.000088698616,"threshold_uncertainty_score":0.50538033},"labels":[],"label_agreement":null},{"id":"W2164131589","doi":"10.1109/icip.2008.4712321","title":"Non-Gaussian mixture image models prediction","year":2008,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Clutter; Mixture model; Dirichlet distribution; Gaussian; Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Computer science; Texture (cosmology); Nonlinear system; Mathematics; Applied mathematics; Algorithm; Radar; Mathematical analysis; Physics","score_opus":0.018486709028401497,"score_gpt":0.24105979696580787,"score_spread":0.22257308793740638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164131589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064645184,0.000042201977,0.8780868,0.0008801709,0.00028959586,0.00012329863,0.0000023854154,0.00027425712,0.119654804],"genre_scores_gemma":[0.17010188,0.00004479687,0.8249388,0.0006692466,0.00012632483,0.000011776863,0.000002088966,0.000010028357,0.004095104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884874,0.000043376764,0.00018595916,0.00040760526,0.00023482674,0.0002795182],"domain_scores_gemma":[0.9991151,0.000018661107,0.000042488668,0.00061245984,0.00006388617,0.00014739513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019911562,0.0001488383,0.0001549426,0.0000848868,0.000183144,0.00006378713,0.00055977097,0.00010785851,0.00002887844],"category_scores_gemma":[0.0000055860623,0.00011609695,0.00008516591,0.00027442517,0.000047433336,0.0010857899,0.00013136757,0.00016738582,0.000051668172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011034931,0.00021532064,0.00019674248,0.000028819371,0.000044779325,0.0002149279,0.0037164327,0.00022898949,0.011948724,0.79592264,0.09862339,0.088848196],"study_design_scores_gemma":[0.00038417726,0.00007653264,0.0009767668,0.000011797245,0.0000057794946,0.00025450255,0.0000052082637,0.8337175,0.007682468,0.15467608,0.0019441602,0.00026499067],"about_ca_topic_score_codex":0.0000208183,"about_ca_topic_score_gemma":0.0000019916051,"teacher_disagreement_score":0.8334885,"about_ca_system_score_codex":0.0000218862,"about_ca_system_score_gemma":0.00006187622,"threshold_uncertainty_score":0.47342962},"labels":[],"label_agreement":null},{"id":"W2164798779","doi":"10.1080/15598608.2009.10411945","title":"Exact Conditional Tests and Approximate Bootstrap Tests for the von Mises Distribution","year":2009,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Practice","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Directorate for Biological Sciences; Simon Fraser University; Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Ciencia y Tecnología","keywords":"Mathematics; Statistics; Sampling distribution; Exact test; Test statistic; Exact statistics; Conditional probability distribution; F-test of equality of variances; Applied mathematics; Statistical hypothesis testing","score_opus":0.041094656889450944,"score_gpt":0.3741524462421269,"score_spread":0.33305778935267594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164798779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023981123,0.00095534546,0.9930271,0.0050921566,0.0000865946,0.00010780733,0.00007480228,0.000006794045,0.0004095948],"genre_scores_gemma":[0.48385003,0.0003326863,0.5143529,0.0012577778,0.00015614288,0.000002468177,0.0000053263434,0.0000034952186,0.000039155115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880767,0.0005173811,0.00024177159,0.00012634625,0.00016914643,0.00013769498],"domain_scores_gemma":[0.98020035,0.019172423,0.00024406431,0.000097424934,0.00017290712,0.00011283547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037789762,0.00009104777,0.00014730777,0.000020719173,0.00020371149,0.00019569637,0.00014796772,0.000042673888,0.0000087381495],"category_scores_gemma":[0.005201164,0.00005528159,0.00003077575,0.00006065907,0.00011820274,0.00072117883,0.000020957723,0.00020952435,5.434251e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003464411,0.000058838723,0.0000031199845,0.000010583229,0.00002313645,0.000022037117,0.00007688924,0.0000035668822,0.00021366459,0.87009037,0.001131365,0.12801997],"study_design_scores_gemma":[0.00042385157,0.00052748475,0.0049790507,0.00002277669,0.000096778946,0.0015242595,0.00004084033,0.0037464837,0.00009368243,0.9802361,0.008225189,0.00008346166],"about_ca_topic_score_codex":4.0948154e-7,"about_ca_topic_score_gemma":6.337362e-8,"teacher_disagreement_score":0.4836102,"about_ca_system_score_codex":0.000010026152,"about_ca_system_score_gemma":0.000047437683,"threshold_uncertainty_score":0.62266546},"labels":[],"label_agreement":null},{"id":"W2164907674","doi":"10.1145/1899396.1899398","title":"The double CFTP method","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Modeling and Computer Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Hungkuang University; Hong Kong University of Science and Technology; Research Grants Council, University Grants Committee","keywords":"Mathematics; Dirichlet distribution; Markov chain; Poisson distribution; Coalescence (physics); Combinatorics; Limit (mathematics); Poisson point process; Applied mathematics; Distribution (mathematics); Identity (music); Bessel function; Discrete mathematics; Mathematical analysis; Boundary value problem; Statistics; Physics","score_opus":0.07555412885911102,"score_gpt":0.31413135928981406,"score_spread":0.23857723043070306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164907674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005111603,0.00007044694,0.998111,0.00028841142,0.00039138983,0.00013443007,4.7247087e-7,0.0001602322,0.00033246388],"genre_scores_gemma":[0.39117995,0.000023397271,0.6085445,0.00015461218,0.00003372748,0.00000837873,2.680804e-7,0.000006399046,0.00004871053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897385,0.00011848826,0.00021161216,0.00035104825,0.00014980277,0.00019521808],"domain_scores_gemma":[0.99886245,0.00023988928,0.000042689568,0.0007004813,0.00008077588,0.0000737408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048847054,0.00013669694,0.00011418265,0.00007518135,0.0005555211,0.0001563457,0.0004969394,0.00007294344,0.000002737243],"category_scores_gemma":[0.0000030414765,0.000099449586,0.00006973812,0.00017029612,0.000017913137,0.0003252686,0.000023096614,0.00018233144,0.000005870225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018011366,0.00002060259,6.589339e-7,0.0000017548239,0.000011713973,4.5737406e-7,0.0006390781,0.43168104,0.0000036189927,0.016954191,0.0000018855935,0.550667],"study_design_scores_gemma":[0.00029630394,0.000064753076,0.000014789617,0.000009271189,0.000010808616,0.0000051639204,0.000004698082,0.8806073,0.00011721308,0.11860687,0.00015093738,0.00011185962],"about_ca_topic_score_codex":0.000041587013,"about_ca_topic_score_gemma":0.000004916181,"teacher_disagreement_score":0.55055517,"about_ca_system_score_codex":0.00001288905,"about_ca_system_score_gemma":0.000018532777,"threshold_uncertainty_score":0.42726752},"labels":[],"label_agreement":null},{"id":"W2165091599","doi":"10.48550/arxiv.1207.1375","title":"Nonparametric Bayesian Logic","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Syntax; Inference; Bayesian inference; Artificial intelligence; Dirichlet distribution; Matching (statistics); Dirichlet process; Generative model; Bayesian probability; Generative grammar; Machine learning; Latent Dirichlet allocation; Selection (genetic algorithm); Theoretical computer science; Data mining; Topic model; Mathematics","score_opus":0.07321097545028427,"score_gpt":0.203399019088266,"score_spread":0.13018804363798173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165091599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011248784,0.00012856378,0.96576554,0.00009650875,0.0003600972,0.000089456626,8.3545837e-7,0.00017240901,0.022137797],"genre_scores_gemma":[0.8561784,0.000028777786,0.14190523,0.00034472893,0.000075513635,2.3253988e-7,5.623875e-7,0.0000072641624,0.0014593068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987924,0.00015044054,0.0001025947,0.00040613426,0.00006269337,0.00048574054],"domain_scores_gemma":[0.99881047,0.00011090802,0.00007058789,0.0006729578,0.000047466358,0.00028758924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040012217,0.0001529569,0.00016283231,0.00023579846,0.00012794785,0.00004715996,0.00086177944,0.00010228034,0.000051258157],"category_scores_gemma":[0.00003658589,0.00015176616,0.00010820454,0.0015011701,0.000050904786,0.000905141,0.00024701073,0.00016368277,0.00021534624],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037237962,0.00007607934,0.0031036339,0.0000047172407,0.00001246868,0.00003683811,0.00009251775,0.00021793548,0.000050076447,0.9875515,0.0003451188,0.008505394],"study_design_scores_gemma":[0.0010317813,0.00016287416,0.009386369,0.000020114332,0.00006996468,0.00006705844,0.00004747262,0.43871456,0.0011181661,0.54072785,0.0076306695,0.0010230904],"about_ca_topic_score_codex":0.000017567814,"about_ca_topic_score_gemma":0.0000017667734,"teacher_disagreement_score":0.8449296,"about_ca_system_score_codex":0.00006476717,"about_ca_system_score_gemma":0.00003182126,"threshold_uncertainty_score":0.61888444},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.010797611166166439,"score_gpt":0.28848977053517044,"score_spread":0.277692159369004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165255548","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004492773,0.00054067216,0.993175,0.00019658271,0.0003307374,0.00031607843,0.0000040949367,0.000044880217,0.00089914567],"genre_scores_gemma":[0.32570693,0.00013324425,0.67390776,0.00017988775,0.000017821449,0.000008899141,0.000024690455,0.0000030227618,0.00001770744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988628,0.000032097018,0.00052676554,0.000163107,0.00017607588,0.00023913376],"domain_scores_gemma":[0.99934816,0.00008066665,0.00019299249,0.00030336576,0.000036580008,0.00003824731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005099905,0.00012035427,0.00017416247,0.00032233013,0.00005549847,0.00007738116,0.00040630717,0.00007637496,6.230386e-7],"category_scores_gemma":[0.00004634248,0.000114618044,0.000040936615,0.00061604445,0.00000985354,0.0020518266,0.000033662982,0.000116492745,0.000003829621],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012162929,0.00009236405,0.0011898217,0.00013457354,0.0000013546041,0.0000013524648,0.0014625324,0.0031967256,0.0007849854,0.025199434,0.000052476604,0.9678722],"study_design_scores_gemma":[0.0004928651,0.000037727455,0.008889678,0.00005923411,0.0000020756313,0.0000022467586,0.000023500748,0.9187962,0.0015130716,0.06925569,0.0007582684,0.0001694389],"about_ca_topic_score_codex":0.0000027363244,"about_ca_topic_score_gemma":0.000006570768,"teacher_disagreement_score":0.9677028,"about_ca_system_score_codex":0.000068710906,"about_ca_system_score_gemma":0.000010602407,"threshold_uncertainty_score":0.46739882},"labels":[],"label_agreement":null},{"id":"W2166329820","doi":"10.1109/tnn.2010.2054109","title":"An Extension of the Standard Mixture Model for Image Segmentation","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Artificial intelligence; Mixture model; Image segmentation; Pixel; Robustness (evolution); Computer science; Pattern recognition (psychology); Markov random field; Segmentation; Grayscale; Scale-space segmentation; Computer vision; Mathematics","score_opus":0.015014905269373057,"score_gpt":0.2822433391842295,"score_spread":0.26722843391485646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166329820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011088671,0.000008923623,0.9863969,0.00055618625,0.0014538204,0.0003882661,0.00002217435,0.000064692584,0.000020377218],"genre_scores_gemma":[0.6319228,0.0000049003484,0.36765033,0.000293652,0.000044880384,0.000022583305,7.68332e-7,0.00000979949,0.000050306808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990573,0.00008036769,0.00019223904,0.00030018398,0.00017710488,0.00019279335],"domain_scores_gemma":[0.9990021,0.0000818672,0.00008583773,0.00063484564,0.00012335413,0.00007201947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024747849,0.00013254143,0.0001396586,0.000042791642,0.00023375243,0.0000610979,0.00045459566,0.000119826145,0.000004465231],"category_scores_gemma":[0.0000025117238,0.00009134087,0.00014793551,0.00019394713,0.000057224293,0.000387235,0.000002243423,0.00038465805,2.2048715e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008424265,0.00009194595,0.000001029056,0.0000097880475,0.000009948801,7.181211e-7,0.00028726232,0.5197641,0.13923362,0.002290339,0.00028221615,0.33794475],"study_design_scores_gemma":[0.00028765603,0.00011275614,0.000015666854,0.0000079445,0.000017655015,0.000007874145,0.0000027839762,0.94741386,0.047662683,0.004360668,0.000013016652,0.00009742014],"about_ca_topic_score_codex":0.0000033319347,"about_ca_topic_score_gemma":0.000040840474,"teacher_disagreement_score":0.6208341,"about_ca_system_score_codex":0.000011097854,"about_ca_system_score_gemma":0.0000275295,"threshold_uncertainty_score":0.37247726},"labels":[],"label_agreement":null},{"id":"W2169097105","doi":"10.2307/3316071","title":"Blind nonparametric regression","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Nonparametric statistics; Nonparametric regression; Mathematics; Statistics; Regression; Econometrics; Computer science; Applied mathematics; Artificial intelligence","score_opus":0.03348599288132698,"score_gpt":0.280513925965992,"score_spread":0.24702793308466503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169097105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011126391,0.0005773451,0.994769,0.0005681759,0.00072276965,0.000033536588,0.000014359913,0.000004062506,0.0021981318],"genre_scores_gemma":[0.10282193,0.00009300933,0.89621174,0.00033841186,0.00012807327,2.5216602e-7,7.106063e-7,0.0000067216774,0.00039914527],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991067,0.00007234743,0.0002837616,0.0001017761,0.00018053586,0.0002548542],"domain_scores_gemma":[0.9984776,0.00013726961,0.00020133835,0.00021140176,0.00027986747,0.00069251866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004393547,0.00008740255,0.00016449514,0.0004533991,0.000101658596,0.00013699515,0.0005466752,0.000055427423,0.000056034936],"category_scores_gemma":[0.0003087886,0.00007010411,0.000039223247,0.00055218214,0.000041841005,0.0002077179,0.000014151942,0.0002208042,0.000012605293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008200672,0.000012772021,0.0010996262,0.0000070720102,0.000018210081,0.0022945483,0.00038309873,0.000029111452,0.000030851093,0.21560326,0.048225027,0.73228824],"study_design_scores_gemma":[0.0022903879,0.0007601042,0.01204466,0.00026351222,0.00007195273,0.005440788,0.000047821075,0.035610586,0.00034271783,0.65558296,0.2868103,0.000734187],"about_ca_topic_score_codex":0.00037257915,"about_ca_topic_score_gemma":0.0012011778,"teacher_disagreement_score":0.73155403,"about_ca_system_score_codex":0.00007721292,"about_ca_system_score_gemma":0.0009611224,"threshold_uncertainty_score":0.2858763},"labels":[],"label_agreement":null},{"id":"W2169714360","doi":"10.1109/tip.2006.877379","title":"A hybrid SEM algorithm for high-dimensional unsupervised learning using a finite generalized Dirichlet mixture","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"University of California, Irvine","keywords":"Generalized Dirichlet distribution; Algorithm; Hierarchical Dirichlet process; Pattern recognition (psychology); Mathematics; Dirichlet distribution; Image segmentation; Mixture model; Artificial intelligence; Latent Dirichlet allocation; Computer science; Dirichlet's principle; Topic model; Segmentation","score_opus":0.015440545693772616,"score_gpt":0.2634581740378422,"score_spread":0.2480176283440696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169714360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028555875,0.0003088146,0.99537665,0.0002755925,0.00040408527,0.00033599764,0.000033294855,0.00034880333,0.00006115167],"genre_scores_gemma":[0.14600992,0.0000041544126,0.8528509,0.0003515244,0.00017004971,0.00006372541,0.000009783456,0.00004761477,0.0004922901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978401,0.00017148275,0.00040491018,0.0007201637,0.0003536538,0.00050965714],"domain_scores_gemma":[0.99898493,0.00015208447,0.00015832786,0.00030720592,0.00028308202,0.00011435992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040174884,0.00034543397,0.00035503047,0.00027236537,0.0009205885,0.0004519299,0.00037152407,0.000114707625,0.000014558353],"category_scores_gemma":[0.000008884023,0.00032741812,0.00019464042,0.00048171394,0.00006920527,0.0008884955,0.0000058701985,0.0004248882,0.0000054056673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041570303,0.00025598166,6.353093e-7,0.000096046264,0.00003639268,0.000041626943,0.00018818896,0.04229329,0.06826574,0.00038623143,0.00014029953,0.888254],"study_design_scores_gemma":[0.0011633682,0.00006649565,0.0000029512667,0.00010109366,0.000055065164,0.00006629519,0.0000036806396,0.8916214,0.09891622,0.007449823,0.00018016013,0.0003734305],"about_ca_topic_score_codex":0.000083079925,"about_ca_topic_score_gemma":0.0000036338815,"teacher_disagreement_score":0.88788056,"about_ca_system_score_codex":0.000085311956,"about_ca_system_score_gemma":0.00019419567,"threshold_uncertainty_score":0.9999178},"labels":[],"label_agreement":null},{"id":"W2169962072","doi":"10.1109/icip.2005.1529754","title":"A probabilistic approach for shadows modeling and detection","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Probabilistic logic; Computer science; Statistical model; Artificial intelligence; Dirichlet distribution; Latent Dirichlet allocation; Mixture model; Pattern recognition (psychology); Computer vision; Topic model; Mathematics","score_opus":0.02972659222963302,"score_gpt":0.2631425982733436,"score_spread":0.23341600604371054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169962072","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084139354,0.00007491466,0.9952497,0.00022008226,0.000029719986,0.0002925222,2.7434237e-7,0.000100096295,0.003191321],"genre_scores_gemma":[0.360497,0.0000018346752,0.63913715,0.0001319503,0.00004951692,0.000042614767,2.0332222e-7,0.0000030659667,0.00013665401],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994203,0.000021123858,0.00009990095,0.00026606544,0.000056596677,0.00013604626],"domain_scores_gemma":[0.9996982,0.000026981745,0.00001602021,0.00017417548,0.000034692825,0.000049887192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031087434,0.00006709283,0.00007881052,0.00003522144,0.00007400236,0.00007670064,0.00013955394,0.000040336214,8.7734037e-7],"category_scores_gemma":[0.000022835427,0.000052917083,0.000026922193,0.000071436305,0.000008737697,0.00023448313,0.000049170358,0.000044454846,6.9245135e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036691035,0.00002443875,7.4126825e-7,0.000021636048,0.000003287523,5.9358523e-8,0.00021508183,0.005454483,0.00057848496,0.19486819,0.000020405367,0.7988095],"study_design_scores_gemma":[0.00013751542,0.000026699283,0.0000015586457,0.0000016198355,0.000003191788,0.000009342627,0.0000032037424,0.93807536,0.000443963,0.061032668,0.00019114865,0.00007370952],"about_ca_topic_score_codex":0.0000058819646,"about_ca_topic_score_gemma":0.000006561472,"teacher_disagreement_score":0.9326209,"about_ca_system_score_codex":0.0000138845135,"about_ca_system_score_gemma":0.000011751363,"threshold_uncertainty_score":0.2157896},"labels":[],"label_agreement":null},{"id":"W2170902875","doi":"10.1109/tnn.2009.2034851","title":"A Dirichlet Process Mixture of Generalized Dirichlet Distributions for Proportional Data Modeling","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Hierarchical Dirichlet process; Dirichlet process; Dirichlet distribution; Cluster analysis; Gibbs sampling; Concentration parameter; Latent Dirichlet allocation; Mixture model; Generalized Dirichlet distribution; Mathematics; Pattern recognition (psychology); Computer science; Algorithm; Artificial intelligence; Applied mathematics; Bayesian probability; Topic model; Dirichlet series; Mathematical analysis","score_opus":0.04578269611782361,"score_gpt":0.3189366009787135,"score_spread":0.2731539048608899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170902875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012266627,0.00025077493,0.9947136,0.0022736539,0.0005134922,0.000575154,0.00025470852,0.00015706623,0.000034885197],"genre_scores_gemma":[0.7946364,0.0000660504,0.20439434,0.0005381557,0.00014624209,0.000060045993,0.00008856377,0.000013274128,0.000056874982],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980525,0.00009940183,0.00047764427,0.00066340284,0.00029553988,0.0004115242],"domain_scores_gemma":[0.9984281,0.0000896938,0.0001496073,0.00097404816,0.00021711468,0.00014140653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034473444,0.00025150058,0.00033007702,0.0001005624,0.00030527406,0.00008166713,0.0010724737,0.00016224342,0.0000072231123],"category_scores_gemma":[0.000008304538,0.00021483938,0.00017312892,0.0005227831,0.000043871372,0.0005895107,0.0000064545516,0.00035174616,5.227436e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112907524,0.00040117893,0.0000012219555,0.000025954676,0.000046545196,0.000004212013,0.000077477314,0.8508575,0.00038787164,0.010365533,0.0011937842,0.13652581],"study_design_scores_gemma":[0.00051386387,0.0001667506,0.000006472836,0.000029662111,0.00005273393,0.000020824145,0.0000015655414,0.9872735,0.00082429795,0.010741117,0.00013827243,0.00023091646],"about_ca_topic_score_codex":0.000005192543,"about_ca_topic_score_gemma":0.0000050266067,"teacher_disagreement_score":0.79340976,"about_ca_system_score_codex":0.000026553767,"about_ca_system_score_gemma":0.00007327527,"threshold_uncertainty_score":0.8760896},"labels":[],"label_agreement":null},{"id":"W2171408965","doi":"10.1109/crv.2006.39","title":"Hierarchical Region Mean-Based Image Segmentation","year":2006,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Image segmentation; Computer science; Straddle; Block (permutation group theory); Segmentation; Potts model; Boundary (topology); Image (mathematics); Artificial intelligence; Hierarchy; Pattern recognition (psychology); Scale (ratio); Mean-shift; Algorithm; Mathematics; Statistical physics; Geometry; Cartography; Geography; Ising model","score_opus":0.014307126653162926,"score_gpt":0.26372546469943625,"score_spread":0.24941833804627334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171408965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085518335,0.000014769739,0.97354585,0.0023762668,0.00009416317,0.000085963,2.2815854e-7,0.00016741003,0.02286018],"genre_scores_gemma":[0.089896016,7.0604887e-7,0.9081852,0.0008353616,0.00006639714,0.0000067501132,0.0000028842412,0.0000045218,0.0010022074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992315,0.000097794866,0.00012606858,0.00023972052,0.00015120095,0.00015370424],"domain_scores_gemma":[0.99955094,0.000056208446,0.00003184297,0.0002840929,0.000033079643,0.000043814725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018090023,0.000076512624,0.00007454544,0.00005913104,0.00005970748,0.00009649659,0.00024823958,0.00003817589,0.000014252216],"category_scores_gemma":[0.0000050867666,0.000061432474,0.000046885852,0.00016682954,0.000026955258,0.00022922669,0.000032436375,0.00006867895,0.000022213817],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051794855,0.000068935326,0.000077613644,0.0000073258725,0.0000022235247,0.000026654665,0.00006495123,0.000025193845,0.020912277,0.8529846,0.0064706183,0.11935441],"study_design_scores_gemma":[0.0008987203,0.00009766491,0.0016972041,0.000013373206,0.0000073141878,0.000024846033,0.000003878598,0.29450062,0.18397355,0.5160582,0.0023742218,0.0003504291],"about_ca_topic_score_codex":0.000058453767,"about_ca_topic_score_gemma":0.000010986776,"teacher_disagreement_score":0.33692643,"about_ca_system_score_codex":0.000020503594,"about_ca_system_score_gemma":0.000031581854,"threshold_uncertainty_score":0.25051436},"labels":[],"label_agreement":null},{"id":"W2171491412","doi":"10.1007/11564126_16","title":"Support Vector Random Fields for Spatial Classification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Conditional random field; Support vector machine; Computer science; Discriminative model; Kernel (algebra); Artificial intelligence; Generalization; Pattern recognition (psychology); Random field; Multivariate random variable; Inference; Spatial analysis; Consistency (knowledge bases); Machine learning; Mathematics; Random variable; Statistics","score_opus":0.028772525054208544,"score_gpt":0.2823242950158188,"score_spread":0.2535517699616103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171491412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032178152,0.00016865555,0.9892769,0.0026096674,0.0023957477,0.0007800557,0.000010041735,0.00013674995,0.004618978],"genre_scores_gemma":[0.039547954,0.00003768003,0.9553996,0.0021549917,0.0015778985,0.000040390798,0.00001202815,0.000033890377,0.0011956177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965973,0.000044382552,0.0005689905,0.0015112557,0.00065522664,0.0006228743],"domain_scores_gemma":[0.9972624,0.00067380373,0.00030165055,0.0013196875,0.00026167036,0.00018079279],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013504128,0.0004741846,0.00058175734,0.00048879965,0.00023008135,0.00042215106,0.0025544644,0.0005023198,0.000041332725],"category_scores_gemma":[0.00011932045,0.00042181523,0.0002307159,0.00025925896,0.00031289482,0.00045716894,0.00046410083,0.0006053379,0.00002404654],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017690809,0.000017593677,0.0000026593611,0.000023262795,0.0000072169696,0.000008372657,0.0002984936,0.0006884002,0.000105609666,0.06612902,0.0001285576,0.93257314],"study_design_scores_gemma":[0.00089766504,0.0002461329,0.00005893476,0.000107439264,0.000014725789,0.00003680339,3.088029e-8,0.67495537,0.0012773762,0.30914047,0.012634027,0.0006310025],"about_ca_topic_score_codex":0.000013379368,"about_ca_topic_score_gemma":0.0000983634,"teacher_disagreement_score":0.9319421,"about_ca_system_score_codex":0.00019932988,"about_ca_system_score_gemma":0.0006334014,"threshold_uncertainty_score":0.9998234},"labels":[],"label_agreement":null},{"id":"W2171721967","doi":"","title":"A Bayesian Approach to Cluster Validation.","year":2008,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Cluster analysis; Bayesian probability; Computer science; Stability (learning theory); Matrix (chemical analysis); Baseline (sea); Algorithm; Cluster (spacecraft); Measure (data warehouse); Mathematical optimization; Mathematics; Data mining; Artificial intelligence; Machine learning","score_opus":0.031103402797769627,"score_gpt":0.25906226905608226,"score_spread":0.22795886625831263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171721967","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020433257,0.000009697642,0.82241356,0.0011691173,0.00009551247,0.00014123133,2.2914791e-7,0.00013757785,0.17582871],"genre_scores_gemma":[0.10701032,0.0000019272447,0.8837453,0.0033822737,0.000060467555,0.000019143456,7.1008856e-7,0.0000061112855,0.0057737436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990588,0.00007754491,0.00013546713,0.00034026598,0.0001786292,0.00020933808],"domain_scores_gemma":[0.99923545,0.000028662362,0.00002002927,0.0005146764,0.000043384433,0.00015778489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024669568,0.000096146774,0.00011177164,0.00008568001,0.000112304486,0.00005862561,0.0005486082,0.000044813434,0.000017063909],"category_scores_gemma":[0.000017562126,0.00007558486,0.00004819413,0.00034677342,0.000015133486,0.0002790578,0.00016586519,0.000065752094,0.00009718725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051286756,0.00016782442,0.00015718388,0.000009606115,0.000014503711,0.00000986048,0.0030897104,0.0002719436,0.000329259,0.853594,0.06764922,0.07470178],"study_design_scores_gemma":[0.0014011172,0.0002323343,0.0023218712,0.000018257295,0.000013236205,0.00084478356,0.000029806024,0.76991975,0.016814025,0.13055065,0.07639211,0.0014620671],"about_ca_topic_score_codex":0.000011550581,"about_ca_topic_score_gemma":4.29119e-7,"teacher_disagreement_score":0.7696478,"about_ca_system_score_codex":0.000014535226,"about_ca_system_score_gemma":0.000036830363,"threshold_uncertainty_score":0.3082261},"labels":[],"label_agreement":null},{"id":"W2172043318","doi":"10.1080/03610920701713286","title":"Gamma Mixture: Bimodality, Inflexions and L-Moments","year":2008,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Bimodality; Estimator; Method of moments (probability theory); Generalized method of moments; Statistical physics; Simple (philosophy); Parameter space; Mixture model; Mathematics; Applied mathematics; Density estimation; Gamma distribution; Biological system; Statistics; Physics; Biology","score_opus":0.03969086704750028,"score_gpt":0.39057022226538873,"score_spread":0.35087935521788843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172043318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016751706,0.0029641886,0.9924154,0.00039514896,0.00008892719,0.0001621862,0.0000138049445,0.000047199013,0.0022379337],"genre_scores_gemma":[0.069462135,0.0026960876,0.92702353,0.00044601338,0.000010544533,0.000032894783,0.000006518473,0.000008930559,0.00031332148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99466175,0.0044272672,0.0003220821,0.00028976158,0.0001032066,0.00019593566],"domain_scores_gemma":[0.9962831,0.002457561,0.000112282374,0.00095772796,0.0000689561,0.00012037177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004643939,0.00014608206,0.00023794365,0.00012973513,0.000319805,0.00006480184,0.0005834711,0.00009006948,0.000010102665],"category_scores_gemma":[0.0005811851,0.00013684544,0.000019503148,0.00025461064,0.0003699,0.0002568002,0.00057307,0.00027624622,0.0000017808914],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001205643,0.000028415687,0.00025297242,0.000013632503,0.000007411318,0.0000028837542,0.002021422,9.1435385e-7,0.00019736735,0.75186235,0.00009475781,0.24550584],"study_design_scores_gemma":[0.00036328146,0.000032601933,0.008488661,0.000032745178,0.0000086894115,0.000056074892,0.000030613704,0.003955563,0.0004162143,0.9834952,0.002949988,0.00017041295],"about_ca_topic_score_codex":0.00002085129,"about_ca_topic_score_gemma":0.0000058994046,"teacher_disagreement_score":0.24533543,"about_ca_system_score_codex":0.000019759796,"about_ca_system_score_gemma":0.000049969545,"threshold_uncertainty_score":0.5580395},"labels":[],"label_agreement":null},{"id":"W2175672038","doi":"10.1016/j.compbiomed.2015.11.008","title":"Oscillometric blood pressure estimation by combining nonparametric bootstrap with Gaussian mixture model","year":2015,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"National Research Foundation; Neurosciences Research Foundation","keywords":"Gaussian; Confidence interval; Mixture model; Standard deviation; Nonparametric statistics; Mathematics; Blood pressure; Statistics; Cluster analysis; Algorithm; Computer science; Pattern recognition (psychology); Artificial intelligence; Medicine; Chemistry; Internal medicine","score_opus":0.028749420155867164,"score_gpt":0.31507044570484216,"score_spread":0.286321025548975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2175672038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066425484,0.007133853,0.9828244,0.0018561101,0.00033847286,0.0001928837,0.000002476549,0.00007151834,0.00093777163],"genre_scores_gemma":[0.5187163,0.000090618654,0.48035714,0.00071069534,0.00003843589,0.000008026303,0.000011725441,0.000006180405,0.000060925075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857605,0.00016654031,0.0002639117,0.0005209677,0.00015585526,0.00031669156],"domain_scores_gemma":[0.9990114,0.00022649544,0.00011875829,0.00034216326,0.00006414818,0.0002370444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007859374,0.00021286959,0.00040618225,0.00055729307,0.00006782518,0.000025121251,0.000446731,0.00020198786,0.0000011004789],"category_scores_gemma":[0.00011821031,0.00014405166,0.000017593517,0.0012270404,0.00023460289,0.00018372519,0.00012849575,0.0003110316,7.3640774e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001718091,0.0005735951,0.010086446,0.00019210415,0.00035797802,0.00012324458,0.0061962083,0.006303709,0.0018606117,0.3743383,0.021201452,0.5785945],"study_design_scores_gemma":[0.0033061826,0.0011537651,0.00069880864,0.00013695883,0.000080846294,0.00013805187,0.000015491316,0.92862254,0.00012402522,0.06490222,0.0005477611,0.00027333773],"about_ca_topic_score_codex":0.00002640174,"about_ca_topic_score_gemma":0.000001598854,"teacher_disagreement_score":0.9223188,"about_ca_system_score_codex":0.000012697336,"about_ca_system_score_gemma":0.00006543212,"threshold_uncertainty_score":0.58742565},"labels":[],"label_agreement":null},{"id":"W2180453814","doi":"10.1609/aaai.v28i1.8980","title":"Learning the Structure of Probabilistic Graphical Models with an Extended Cascading Indian Buffet Process","year":2014,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Graphical model; Directed acyclic graph; Computer science; Artificial intelligence; Process (computing); Machine learning; Context (archaeology); Probabilistic logic; Theoretical computer science; Extension (predicate logic); Graph; Algorithm; Programming language","score_opus":0.03783105091268975,"score_gpt":0.2889702007784415,"score_spread":0.25113914986575175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180453814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39231628,0.0000076168717,0.60480624,0.0009802356,0.0000968939,0.0004454754,0.000002396995,0.000060526538,0.001284369],"genre_scores_gemma":[0.97099584,0.0000064346973,0.028781215,0.00010845658,0.000054413165,0.000013436008,4.0251345e-7,0.000017509761,0.000022283039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776727,0.00010841549,0.00050576293,0.00059950835,0.0006311424,0.00038791462],"domain_scores_gemma":[0.997914,0.00016845463,0.00053875975,0.00044167144,0.0008140736,0.0001230042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093187497,0.00028186865,0.00036799398,0.00012967753,0.0003151976,0.00022212083,0.0024364062,0.00013377285,0.000009836601],"category_scores_gemma":[0.0004168141,0.0001526416,0.000090254616,0.00085024425,0.0005326847,0.00059670035,0.00020502969,0.0006572201,0.0000011894482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071902505,0.000072166345,0.00006664302,0.000086304,0.000013583178,2.705888e-7,0.0055993805,0.0012844416,0.012167935,0.9191057,0.0000020195503,0.061529666],"study_design_scores_gemma":[0.000023891318,0.0004628985,0.0000582296,0.00016327552,0.000014540001,0.00001255797,0.00035682064,0.29166618,0.118318014,0.5887738,0.0000022053177,0.00014756959],"about_ca_topic_score_codex":0.000038099723,"about_ca_topic_score_gemma":0.000033103115,"teacher_disagreement_score":0.57867956,"about_ca_system_score_codex":0.00001930057,"about_ca_system_score_gemma":0.00012317902,"threshold_uncertainty_score":0.6224544},"labels":[],"label_agreement":null},{"id":"W2181556329","doi":"10.6339/jds.2004.02(1).135","title":"The Poisson Inverse Gaussian Regression Model in the Analysis of Clustered Counts Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; Western University","funders":"","keywords":"Poisson regression; Statistics; Mathematics; Covariate; Poisson distribution; Negative binomial distribution; Count data; Inverse Gaussian distribution; Regression analysis; Generalized linear model; Regression; Distribution (mathematics); Population","score_opus":0.14271075028666894,"score_gpt":0.3991228810900525,"score_spread":0.25641213080338354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181556329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017344581,0.00034055187,0.9936621,0.0032400773,0.00017695322,0.000026887014,0.000037116144,0.0000016578662,0.0007802075],"genre_scores_gemma":[0.26982984,0.00061326375,0.7287197,0.0006596601,0.000052257717,2.553277e-7,0.000012588888,0.0000030717015,0.00010935409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998357,0.00019007717,0.0003165695,0.0002591974,0.0007285899,0.00014853853],"domain_scores_gemma":[0.9967541,0.00016867107,0.00031473153,0.0025514376,0.00015762282,0.000053413267],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0066403393,0.00005603813,0.00015542268,0.00016554294,0.00013945352,0.00021011638,0.008004703,0.00002205919,0.0000036298266],"category_scores_gemma":[0.00043516792,0.000026368043,0.000034607085,0.002247252,0.00020502036,0.0020396756,0.0014957784,0.00018001696,8.720458e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055887882,0.0004171719,0.0009515773,0.000031946693,0.000273274,0.0003326146,0.0058833207,0.0034025365,0.016124416,0.10482712,0.07292892,0.7947712],"study_design_scores_gemma":[0.00008878438,0.000008989372,0.0009495883,0.000031967927,0.000051236282,0.000034728917,0.00007699144,0.99320066,0.00014991783,0.0035197514,0.0018475626,0.000039794442],"about_ca_topic_score_codex":0.0000075371745,"about_ca_topic_score_gemma":0.00006124757,"teacher_disagreement_score":0.9897981,"about_ca_system_score_codex":0.000018955157,"about_ca_system_score_gemma":0.00055228936,"threshold_uncertainty_score":0.9973625},"labels":[],"label_agreement":null},{"id":"W2181612026","doi":"10.1109/mmsp.2015.7340853","title":"Hybrid hidden Markov model for mixed continuous/continuous and discrete/continuous data modeling","year":2015,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hidden Markov model; Computer science; Gaussian; Data modeling; Pattern recognition (psychology); Mixture model; Gaussian process; Artificial intelligence; Algorithm","score_opus":0.05980609403456198,"score_gpt":0.3011596470116282,"score_spread":0.24135355297706618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181612026","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054153334,0.00093381864,0.98690504,0.0016245521,0.000490024,0.00078700803,0.00011253115,0.00036296697,0.0033687262],"genre_scores_gemma":[0.23521763,0.000038852286,0.76040447,0.0006206178,0.00016645304,0.000049734423,0.000051611656,0.00004378672,0.0034068597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965542,0.00016531986,0.000615445,0.0014428291,0.0004172351,0.0008049492],"domain_scores_gemma":[0.99651384,0.00016891585,0.00016997043,0.0022959525,0.00030843876,0.00054285204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002278782,0.00043551892,0.0007310037,0.00013503419,0.0001819182,0.0005770213,0.0024497518,0.00014391329,0.0000035753158],"category_scores_gemma":[0.00026370704,0.00036581286,0.00011252699,0.00012500667,0.00007725541,0.0015418765,0.0018259966,0.00023242302,0.000008016417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010159397,0.00011963978,0.00006353631,0.00006044073,0.00010146477,0.000033182518,0.00096823624,0.00053596013,0.00028499748,0.07167194,0.037503425,0.8885556],"study_design_scores_gemma":[0.0012780535,0.000099608944,0.0000026415116,0.000026913505,0.00004514063,0.00006512087,0.000048783768,0.90454257,0.00014804178,0.09187965,0.001363764,0.0004997172],"about_ca_topic_score_codex":0.000104244544,"about_ca_topic_score_gemma":0.000032686235,"teacher_disagreement_score":0.9040066,"about_ca_system_score_codex":0.000037453457,"about_ca_system_score_gemma":0.00020802098,"threshold_uncertainty_score":0.99987936},"labels":[],"label_agreement":null},{"id":"W2182753936","doi":"","title":"Asymptotic Theory for Linear-Chain Conditional Random Fields","year":2011,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; CRFS; Conditional random field; Sequence (biology); Hessian matrix; Ergodicity; Applied mathematics; Feature (linguistics); Consistency (knowledge bases); Exponential family; Ergodic theory; Inference; Discrete mathematics; Statistics; Computer science; Artificial intelligence; Mathematical analysis","score_opus":0.15941988105138544,"score_gpt":0.35806462897219055,"score_spread":0.1986447479208051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182753936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000086961474,0.00001378429,0.99021125,0.00069657754,0.0006906343,0.00019536061,0.00017671994,0.000039468465,0.007889267],"genre_scores_gemma":[0.47730908,0.00004308033,0.5214559,0.00061542355,0.00010561963,0.00003251324,0.000028953295,0.0000062371873,0.00040320455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881226,0.000111321795,0.00033098832,0.0003360445,0.00021821738,0.00019118325],"domain_scores_gemma":[0.9984843,0.00079917506,0.00010107193,0.0001810642,0.00033992852,0.000094425675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006152891,0.00014784312,0.00016007217,0.00010315579,0.000121032426,0.000119350945,0.00047117283,0.00008195821,0.00032225047],"category_scores_gemma":[0.0004277975,0.00013244762,0.000048467842,0.000060851202,0.00013780138,0.00016068216,0.00006638273,0.00014019472,0.00003724506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015128197,0.00005721356,0.000003991589,0.0000045809807,0.000022042132,0.0000069530647,0.0005955414,0.00001389183,0.00005895451,0.8003384,0.00013878346,0.19860838],"study_design_scores_gemma":[0.0000681511,0.0001613405,0.0000310489,0.000015856644,0.0000064643114,0.00000763156,0.00005621826,0.2600607,0.001885226,0.737448,0.0001376341,0.00012172469],"about_ca_topic_score_codex":0.000012137817,"about_ca_topic_score_gemma":0.000018392439,"teacher_disagreement_score":0.4772221,"about_ca_system_score_codex":0.000015609156,"about_ca_system_score_gemma":0.0000756301,"threshold_uncertainty_score":0.5401057},"labels":[],"label_agreement":null},{"id":"W2185425981","doi":"","title":"SERIES REPRESENTATIONS FOR MULTIVARIATE GENERALIZED GAMMA PROCESSES VIA A SCALE INVARIANCE PRINCIPLE","year":2009,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bivariate analysis; Multivariate statistics; Point process; Mathematics; Property (philosophy); Scale invariance; Scale (ratio); Invariance principle; Series (stratigraphy); Variance (accounting); Poisson distribution; Applied mathematics; Simple (philosophy); Econometrics; Statistics","score_opus":0.02917291344439188,"score_gpt":0.3296926725440741,"score_spread":0.3005197590996822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185425981","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006437397,0.00006701243,0.99007744,0.004494512,0.00013263576,0.00050453533,0.0000038802586,0.0002378218,0.0038384048],"genre_scores_gemma":[0.030598247,0.000012629955,0.96285355,0.0010650969,0.00009210368,0.000110064146,0.000003726276,0.0000075723383,0.0052569825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988262,0.000066938264,0.00023919031,0.00045624416,0.0001348686,0.0002765685],"domain_scores_gemma":[0.99900794,0.000082726925,0.00008578472,0.0005121645,0.00021483403,0.0000965494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002766162,0.00013854294,0.00018370588,0.000055710578,0.00018952426,0.00017684815,0.00051377877,0.00005874314,0.00001221556],"category_scores_gemma":[0.00012869794,0.00011389799,0.0000598473,0.00039642968,0.000024998273,0.00085782685,0.00007345702,0.00004906875,0.000005167854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042033476,0.00013137308,0.000046366527,0.00004640819,0.000015682745,0.0000039565566,0.0011741569,0.000112379494,0.020121137,0.9161425,0.0014162015,0.06074779],"study_design_scores_gemma":[0.0012712842,0.0002062497,0.0015055477,0.000026565598,0.00001564667,0.000043079468,0.000009721352,0.10185069,0.091931395,0.791343,0.011366623,0.00043023896],"about_ca_topic_score_codex":0.00002847725,"about_ca_topic_score_gemma":0.000051867304,"teacher_disagreement_score":0.12479956,"about_ca_system_score_codex":0.00001459102,"about_ca_system_score_gemma":0.000114484494,"threshold_uncertainty_score":0.46446252},"labels":[],"label_agreement":null},{"id":"W2185671880","doi":"10.2139/ssrn.2381838","title":"Fitting Mixtures of Erlangs to Censored and Truncated Data Using the EM Algorithm","year":2014,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Algorithm; Computer science; Statistics; Mathematics; Econometrics","score_opus":0.019170197289560466,"score_gpt":0.28440490421908377,"score_spread":0.2652347069295233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185671880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023063194,0.0013138843,0.97443706,0.00090894947,0.0001251505,0.00008086671,0.0000025234074,0.000018010187,0.000050361014],"genre_scores_gemma":[0.28494188,0.00017000959,0.7141351,0.00037353142,0.00026804776,7.527464e-7,0.0000013318435,0.000014101052,0.000095229254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980083,0.00027712955,0.00024665648,0.0002735663,0.00022120275,0.0009731201],"domain_scores_gemma":[0.9989478,0.00012047636,0.00016445809,0.0006033996,0.00007939024,0.0000844834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038384884,0.00012138342,0.0001881143,0.00007869172,0.00021287885,0.00013100958,0.0012909417,0.00004986163,0.0000011805255],"category_scores_gemma":[0.00014155511,0.00007866225,0.000038315327,0.00025263274,0.000029990804,0.0002603619,0.00032814627,0.00069887645,7.186883e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061881356,0.000013332816,0.00004431284,0.0000042742095,0.00005205872,0.0000011228353,0.00070472027,0.000022342121,0.003397199,0.10259849,0.00010595785,0.89305],"study_design_scores_gemma":[0.00063357444,0.0002931322,0.00036338868,0.000058766356,0.000056312434,0.0011216194,0.00033173742,0.4792698,0.0020221362,0.51427734,0.0012771679,0.00029503516],"about_ca_topic_score_codex":0.000054405744,"about_ca_topic_score_gemma":0.000052565574,"teacher_disagreement_score":0.892755,"about_ca_system_score_codex":0.000064555745,"about_ca_system_score_gemma":0.00037522218,"threshold_uncertainty_score":0.32077533},"labels":[],"label_agreement":null},{"id":"W2188150523","doi":"","title":"An Overview of the New Feature Selection Methods in Finite Mixture of Regression Models","year":2011,"lang":"en","type":"article","venue":"Journal of the Iranian Statistical Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Variable (mathematics); Computer science; Feature (linguistics); Variables; Regression analysis; Artificial intelligence; Machine learning; Statistical model; Function (biology); Model selection; Regression; Statistical learning; Mathematics; Statistics","score_opus":0.08225990530167471,"score_gpt":0.3787570082470074,"score_spread":0.2964971029453327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188150523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006420969,0.00077810005,0.99716705,0.00083732745,0.0003006931,0.0001077934,0.000009432337,0.0000047210438,0.00015281254],"genre_scores_gemma":[0.05352881,0.00013672035,0.94581425,0.00036943992,0.00006012206,4.5171433e-7,1.2145547e-7,0.000008725868,0.000081340586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771076,0.0010232927,0.000507296,0.00016238845,0.00041444713,0.00018183111],"domain_scores_gemma":[0.9983335,0.00032338852,0.00064347737,0.00040867986,0.00017846902,0.000112499256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001693831,0.00014041757,0.00038519755,0.000028175613,0.00007450468,0.000021368225,0.0011124414,0.00014876304,0.000017842747],"category_scores_gemma":[0.00017443075,0.00006787986,0.0003457661,0.0005604804,0.000096420335,0.0003077375,0.00014084867,0.00066946435,1.0075384e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020293648,0.0006373999,0.0013879593,0.00034794616,0.00021353675,0.000008743145,0.026257126,0.0011034899,0.031448558,0.5257464,0.018485798,0.3941601],"study_design_scores_gemma":[0.0007628006,0.00024210518,0.02270442,0.00056315475,0.000099766134,0.000074040785,0.00006992008,0.16564842,0.012194514,0.79705125,0.0004170864,0.00017251236],"about_ca_topic_score_codex":0.000052358053,"about_ca_topic_score_gemma":0.000012078929,"teacher_disagreement_score":0.39398757,"about_ca_system_score_codex":0.00004846258,"about_ca_system_score_gemma":0.00022352503,"threshold_uncertainty_score":0.29085267},"labels":[],"label_agreement":null},{"id":"W2189515485","doi":"","title":"Supplementary Appendix to \\Nonparametric Identication and Estimation of the Number of Components in Multivariate Mixtures\"","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate statistics; Contingency table; Quantile; Nonparametric statistics; Mathematics; Statistics; Econometrics; Table (database); Computer science; Data mining","score_opus":0.01855754715908091,"score_gpt":0.29597352618293804,"score_spread":0.2774159790238571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189515485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3197897,0.0000050614794,0.6791885,0.0005290329,0.000049735776,0.00027520838,0.0000028653435,0.0000036171139,0.00015625692],"genre_scores_gemma":[0.57273644,9.831209e-7,0.42713445,0.00008998852,0.0000017919015,0.000008290217,0.0000025242462,0.0000015709187,0.000023953848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992219,0.00010842265,0.00025190556,0.00015730476,0.00016119124,0.00009924499],"domain_scores_gemma":[0.99945074,0.00009275697,0.00008859834,0.0002899019,0.000042215393,0.00003580379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002829639,0.00006271826,0.00011752298,0.00010099051,0.00001917768,0.000024517747,0.0003227241,0.000027839782,0.000103700404],"category_scores_gemma":[0.00004098349,0.00004272943,0.000022484244,0.0004751348,0.00002066009,0.00019799954,0.00020439549,0.000045922323,0.0000111297495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018463481,0.0005079162,0.082685694,0.00016553655,0.0000482505,8.217083e-7,0.0038024664,0.0006857497,0.11731732,0.43108428,0.0020556557,0.36162785],"study_design_scores_gemma":[0.0004919032,0.000023645844,0.41068852,0.000041983065,0.0000084980975,0.000005245071,0.000013647599,0.43224427,0.049004577,0.10732731,0.000027199936,0.00012317834],"about_ca_topic_score_codex":0.0024915328,"about_ca_topic_score_gemma":0.000017802875,"teacher_disagreement_score":0.43155855,"about_ca_system_score_codex":0.000013155962,"about_ca_system_score_gemma":0.00000974906,"threshold_uncertainty_score":0.37664688},"labels":[],"label_agreement":null},{"id":"W2198679603","doi":"10.1016/j.spl.2015.12.008","title":"On nomenclature for, and the relative merits of, two formulations of skew distributions","year":2015,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Skew; Mathematics; Econometrics; Distribution (mathematics); Applied mathematics; Statistics; Calculus (dental); Mathematical economics; Statistical physics; Computer science; Mathematical analysis; Medicine","score_opus":0.029863568988561514,"score_gpt":0.30077697057140024,"score_spread":0.2709134015828387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198679603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028918276,0.0000378831,0.99199575,0.0037446464,0.0000922203,0.00056874484,0.00046006308,0.00001296168,0.00019587547],"genre_scores_gemma":[0.020142134,0.0000017517422,0.9795248,0.00025263117,0.000011606632,0.000034051358,0.000019403626,0.0000037659838,0.0000098759565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902165,0.00018396784,0.00027425462,0.00021147246,0.00016956529,0.00013910931],"domain_scores_gemma":[0.99800146,0.001176556,0.00015933701,0.00038246898,0.00021810604,0.000062085994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084237405,0.00009687953,0.00020563051,0.000029817978,0.00008684972,0.000021147385,0.00023362582,0.0000326214,7.931083e-7],"category_scores_gemma":[0.00071670127,0.00006640959,0.000047605106,0.0001672003,0.00036639447,0.00012959116,0.00007585899,0.00012090202,2.8288946e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029210643,0.000028935257,0.00006479105,0.000028771186,0.00001845427,1.8238494e-7,0.0012999251,9.3962825e-7,0.00008505599,0.9949356,0.0007028865,0.002805293],"study_design_scores_gemma":[0.00086086104,0.00008071915,0.0004994939,0.000015095362,0.000025667423,0.0000011300883,1.6131946e-7,0.002618298,0.00012961082,0.995589,0.00011151875,0.000068434616],"about_ca_topic_score_codex":0.000032705484,"about_ca_topic_score_gemma":0.00001679317,"teacher_disagreement_score":0.017250307,"about_ca_system_score_codex":0.000036871377,"about_ca_system_score_gemma":0.00006757209,"threshold_uncertainty_score":0.27081046},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2198702551","doi":"10.5539/ijsp.v5n1p90","title":"Asymptotic Distribution of Cramer-von Mises Statistic When Contamination Exists","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Estimator; Statistics; Statistic; Goodness of fit; Test statistic; von Mises yield criterion; Asymptotic distribution; Applied mathematics; Statistical hypothesis testing","score_opus":0.03212241523558035,"score_gpt":0.30634954764131234,"score_spread":0.274227132405732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198702551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01885949,0.00015039205,0.97936684,0.0005365659,0.00059195695,0.00008463994,0.00023895761,0.0000058284486,0.0001653223],"genre_scores_gemma":[0.5355534,0.000027986054,0.46430585,0.0000312647,0.0000437989,0.0000010098732,0.000016136182,0.0000024640324,0.000018081144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99850285,0.00017315957,0.0005468075,0.0001451226,0.00053361285,0.00009846755],"domain_scores_gemma":[0.9970466,0.00035854673,0.0005105637,0.00012864113,0.001824601,0.00013103086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011897399,0.00009438405,0.00020777146,0.00006401585,0.00002340334,0.0000933338,0.00037573333,0.000041136303,0.0000071413106],"category_scores_gemma":[0.0011180455,0.00007970262,0.000036051875,0.00005678675,0.00010694161,0.00031103095,0.000082172286,0.00011676505,7.094781e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008864565,0.0001737928,0.0031277945,0.00004585136,0.00006969817,0.000028374337,0.0008967955,0.00005299513,0.00008948741,0.72756815,0.0016463076,0.26621208],"study_design_scores_gemma":[0.0006868444,0.0003320639,0.02362773,0.000058911497,0.00002339807,0.000089411675,0.000014510412,0.014793363,0.00027905763,0.95906514,0.00093360676,0.00009596903],"about_ca_topic_score_codex":0.000036881847,"about_ca_topic_score_gemma":0.000008299738,"teacher_disagreement_score":0.5166939,"about_ca_system_score_codex":0.000108874345,"about_ca_system_score_gemma":0.00019772701,"threshold_uncertainty_score":0.32501787},"labels":[],"label_agreement":null},{"id":"W2204082285","doi":"10.1007/978-3-642-21786-9_59","title":"Simultaneous Non-gaussian Data Clustering, Feature Selection and Outliers Rejection","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Computer science; Cluster analysis; Pattern recognition (psychology); Mixture model; Artificial intelligence; Feature selection; Expectation–maximization algorithm; Feature (linguistics); Gaussian; Selection (genetic algorithm); Model selection; Maximization; Data mining; Maximum likelihood; Mathematics; Statistics; Mathematical optimization","score_opus":0.024897277439985387,"score_gpt":0.26769799672131944,"score_spread":0.24280071928133407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204082285","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011556107,0.0003988764,0.992489,0.0005138971,0.0019923334,0.0004514018,0.000009612397,0.00019357372,0.003939748],"genre_scores_gemma":[0.036314316,0.0001507209,0.96086925,0.0008578185,0.00058667944,0.0000049484674,0.0000124173375,0.000050064176,0.0011537817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995737,0.00006536848,0.00040433646,0.0024774086,0.0006353255,0.00068054],"domain_scores_gemma":[0.99682534,0.00028167613,0.00031425254,0.0021452801,0.0001728074,0.0002606681],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011948902,0.0006329823,0.00056954566,0.00073953404,0.00039564492,0.00063902646,0.0034239471,0.0006286459,0.00001009329],"category_scores_gemma":[0.000118814634,0.00056696474,0.0000725285,0.00054942834,0.00040704824,0.0010209557,0.002584547,0.0012612044,0.00001178071],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011986756,0.00001640109,0.000013644553,0.00004736548,0.000015574238,0.000074356474,0.0008433607,0.0024083024,0.000117616844,0.0036628623,0.00007663051,0.9927119],"study_design_scores_gemma":[0.00022103064,0.00021634623,0.00004345009,0.0002523468,0.000019281366,0.00037575647,1.180098e-7,0.90497977,0.00026031802,0.08991767,0.00303836,0.0006755521],"about_ca_topic_score_codex":0.000078263554,"about_ca_topic_score_gemma":0.00045933228,"teacher_disagreement_score":0.99203634,"about_ca_system_score_codex":0.00020641582,"about_ca_system_score_gemma":0.00036547158,"threshold_uncertainty_score":0.9996782},"labels":[],"label_agreement":null},{"id":"W2214473900","doi":"10.5539/ijsp.v5n1p61","title":"Recursive Deviance Information Criterion for the Hidden Markov Model","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Deviance information criterion; Deviance (statistics); Hidden Markov model; Likelihood function; Marginal likelihood; Bayesian information criterion; Computer science; Bayesian probability; Model selection; Algorithm; Mathematics; Machine learning; Artificial intelligence; Statistics; Bayesian inference; Estimation theory","score_opus":0.0357763876658552,"score_gpt":0.314657356918596,"score_spread":0.27888096925274075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2214473900","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060796447,0.00015513912,0.99442863,0.0037982648,0.00064514106,0.00013345268,0.00008483077,0.0000039400675,0.00014261],"genre_scores_gemma":[0.04711799,0.00007644098,0.9522688,0.00042487297,0.00008395167,0.000005317134,0.0000028463658,0.0000018639352,0.000017910674],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991998,0.000047861256,0.00031882146,0.00007095977,0.0002874788,0.00007505094],"domain_scores_gemma":[0.99773157,0.0002849121,0.0002639078,0.000107098866,0.001541235,0.00007125028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012390866,0.00006105357,0.000093521034,0.000038168662,0.000042757623,0.00018583587,0.00044769706,0.000027293958,0.000001236529],"category_scores_gemma":[0.0006359827,0.000040007144,0.000031605094,0.000035522928,0.000044577293,0.0006642778,0.0000751432,0.00009171012,4.543098e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007862956,0.000016413338,0.00006291073,0.000011004435,0.000025286832,0.000001283909,0.0009937932,0.00014397193,0.0000055682262,0.3331647,0.0039111846,0.6615853],"study_design_scores_gemma":[0.00029929748,0.00007527773,0.00037106217,0.000014147549,0.0000076235865,0.000035984845,0.00001146999,0.28552794,0.000024130557,0.7106147,0.0029757863,0.000042602216],"about_ca_topic_score_codex":0.000005723532,"about_ca_topic_score_gemma":0.0000029034918,"teacher_disagreement_score":0.66154265,"about_ca_system_score_codex":0.000056785644,"about_ca_system_score_gemma":0.00016406043,"threshold_uncertainty_score":0.17920196},"labels":[],"label_agreement":null},{"id":"W2217230608","doi":"10.2139/ssrn.1515271","title":"Diagnostic Analysis and Computational Strategies for Estimating Single Spell Discrete Time Duration Models – A Monte Carlo Study","year":2009,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Monte Carlo method; Duration (music); Spell; Econometrics; Computer science; Statistical physics; Statistics; Mathematics; Physics","score_opus":0.014252869782360048,"score_gpt":0.2781854925652918,"score_spread":0.2639326227829317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2217230608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044794448,0.00046138745,0.9537027,0.00048953784,0.0000615475,0.00031233183,0.0000023391551,0.00003934023,0.00013639513],"genre_scores_gemma":[0.6572774,0.000018511992,0.34245533,0.000042962467,0.00008165828,0.0000027612668,0.0000020013142,0.0000059848926,0.00011336969],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997932,0.00016524663,0.0003799749,0.00034131165,0.00027067534,0.0009107613],"domain_scores_gemma":[0.99905235,0.00031694846,0.00022632556,0.00017405432,0.00014209104,0.00008822318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015366911,0.00018073471,0.0002913146,0.00021944115,0.00024280719,0.00055692665,0.0003087438,0.00004513958,0.0000011841786],"category_scores_gemma":[0.00007677404,0.00015592664,0.00012839817,0.00040667263,0.000020148957,0.0010826276,0.000034387802,0.00041965462,0.000001409898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038858492,0.00031477213,0.00018115758,0.0000068948075,0.0007190917,0.000011662233,0.002773216,0.486292,0.0002675105,0.40237316,0.000035043777,0.10698661],"study_design_scores_gemma":[0.00028773764,0.00050818134,0.00020332105,0.0000054127445,0.00012551746,0.000047389753,0.00012468752,0.52718467,0.000003976036,0.4714116,7.033213e-7,0.00009683373],"about_ca_topic_score_codex":0.000025322925,"about_ca_topic_score_gemma":0.0001403914,"teacher_disagreement_score":0.61248296,"about_ca_system_score_codex":0.00018807354,"about_ca_system_score_gemma":0.00053994235,"threshold_uncertainty_score":0.63585037},"labels":[],"label_agreement":null},{"id":"W2247461623","doi":"","title":"Collaborative Mode Complex Assessment Tasks in Authentic Context: Theoretical Background, Internet Implementation and Validation","year":2010,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Context (archaeology); The Internet; Computer science; Psychology; World Wide Web; Geography","score_opus":0.019379336099336186,"score_gpt":0.36734070446926964,"score_spread":0.34796136836993347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2247461623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17918533,0.0000043798304,0.81631905,0.001029351,0.00015237657,0.0002624195,0.0000047317894,0.00003187303,0.0030104662],"genre_scores_gemma":[0.6576661,0.0000018924122,0.3419958,0.00025158233,0.000014465644,0.000020510543,0.000011505715,0.000004061307,0.000034069035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883616,0.00022510096,0.0002561072,0.0003298618,0.00016660255,0.00018617288],"domain_scores_gemma":[0.9994056,0.00012934417,0.00006745446,0.00023511841,0.00008487849,0.000077606994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006331654,0.000121351026,0.0001569325,0.000090582114,0.00004434471,0.0002638932,0.00024492777,0.000060602128,0.00027980786],"category_scores_gemma":[0.000010413587,0.00010033037,0.0000204098,0.00019972768,0.00010971161,0.00041031968,0.00014518038,0.00018510733,0.000005331936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003803073,0.000032696615,0.00083130004,0.000003757667,0.0000062180616,0.0000016701133,0.0011676933,9.318989e-7,0.004763862,0.9355854,0.00015498645,0.0574477],"study_design_scores_gemma":[0.0013131886,0.0001419414,0.01771002,0.000010711176,0.000010979092,0.000013776837,0.0008600957,0.44699183,0.0076907887,0.52446574,0.0005101782,0.00028079018],"about_ca_topic_score_codex":0.00013200477,"about_ca_topic_score_gemma":0.0006102386,"teacher_disagreement_score":0.4784808,"about_ca_system_score_codex":0.000033636614,"about_ca_system_score_gemma":0.000067632085,"threshold_uncertainty_score":0.4091354},"labels":[],"label_agreement":null},{"id":"W2250078330","doi":"10.1109/icdm.2015.70","title":"Two-Step Heterogeneous Finite Mixture Model Clustering for Mining Healthcare Databases","year":2015,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Institute of Genetics","keywords":"Categorical variable; Mixture model; Cluster analysis; Computer science; Data mining; Analytics; Hidden Markov model; Multinomial distribution; Data modeling; Gaussian; Database; Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.12000442692756026,"score_gpt":0.3529569684320728,"score_spread":0.23295254150451256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250078330","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029764994,0.00051883026,0.9950098,0.001594841,0.00041692855,0.0003156845,0.00003442341,0.00023322782,0.0015786099],"genre_scores_gemma":[0.06593066,0.000008449496,0.9301056,0.003018147,0.00014790795,0.000049016737,0.00001601672,0.000023247416,0.0007009554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833035,0.000095150535,0.00028534458,0.000579706,0.00023362493,0.00047580895],"domain_scores_gemma":[0.99843013,0.00018149569,0.00008637877,0.0007853482,0.00017197471,0.00034466505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005989042,0.0002181458,0.00026532216,0.000089377994,0.00012842746,0.00013183232,0.00067793246,0.000067024965,0.0000020886523],"category_scores_gemma":[0.00009289062,0.00018582554,0.000096349475,0.0001629342,0.000020679076,0.00043978295,0.0004202186,0.000109324115,0.000005277458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000130114,0.00014148495,0.000088207584,0.00029760262,0.00007739808,0.000078435405,0.0044464394,0.096181616,0.000675838,0.35598257,0.016877946,0.5250223],"study_design_scores_gemma":[0.00057353947,0.00008726838,4.178985e-7,0.000031996227,0.000006805787,0.00004482961,0.000027405895,0.9882343,0.0007748024,0.007171784,0.002801505,0.00024537294],"about_ca_topic_score_codex":0.00007380763,"about_ca_topic_score_gemma":0.00023639925,"teacher_disagreement_score":0.89205265,"about_ca_system_score_codex":0.000044515164,"about_ca_system_score_gemma":0.00017016649,"threshold_uncertainty_score":0.7577746},"labels":[],"label_agreement":null},{"id":"W2253505087","doi":"10.1002/sta4.136","title":"A second look at inference for bivariate Skellam distributions","year":2017,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Bivariate analysis; Inference; Computer science; Econometrics; Statistics; Mathematics; Artificial intelligence","score_opus":0.03388183594038812,"score_gpt":0.33514998219592507,"score_spread":0.30126814625553694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253505087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002233718,0.0000426053,0.98884195,0.0009448858,0.00039402873,0.00017896247,0.00013542552,0.000049451595,0.0071789944],"genre_scores_gemma":[0.3332473,0.0000124622175,0.6604844,0.00016019832,0.000077790464,0.000041066498,0.00001113911,0.000007161505,0.0059585036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99921197,0.000029947045,0.000118833836,0.0002927861,0.00008279612,0.00026364796],"domain_scores_gemma":[0.99868494,0.000118356234,0.000103753075,0.0009254083,0.00007019896,0.00009733719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025749134,0.00009760004,0.00012462669,0.000022333492,0.0006335624,0.00029829875,0.00082537625,0.00004771535,0.000053352698],"category_scores_gemma":[0.00013055795,0.00008371942,0.00006616246,0.000033957127,0.000063995474,0.00032935193,0.0003902619,0.00006437354,0.000038675604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006513295,0.000022992977,0.00016252733,0.000021526354,0.00001458672,0.000006855122,0.00027478774,9.845598e-7,0.0014035347,0.9047027,0.0059566167,0.087426364],"study_design_scores_gemma":[0.000692379,0.000102010345,0.0047484385,0.00002401765,0.000012337836,0.000011443667,0.0000024262638,0.023185588,0.008220507,0.85146725,0.11122126,0.00031234673],"about_ca_topic_score_codex":0.000011723327,"about_ca_topic_score_gemma":0.00007630933,"teacher_disagreement_score":0.3310136,"about_ca_system_score_codex":0.00003580568,"about_ca_system_score_gemma":0.00006811411,"threshold_uncertainty_score":0.48729137},"labels":[],"label_agreement":null},{"id":"W2260476998","doi":"","title":"On Model-Based Clustering, Classification, and Discriminant Analysis","year":2011,"lang":"en","type":"article","venue":"Journal of the Iranian Statistical Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Linear discriminant analysis; Discriminant; Multivariate statistics; Artificial intelligence; Selection (genetic algorithm); Focus (optics); Machine learning; Computer science; Data mining; Model selection; Mathematics; Pattern recognition (psychology)","score_opus":0.04877352564559086,"score_gpt":0.28526157596301027,"score_spread":0.23648805031741943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260476998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002077384,0.000023107226,0.9964796,0.00088055956,0.00010326301,0.000047627884,0.00000969296,0.000007419337,0.00037135778],"genre_scores_gemma":[0.463526,0.0000054283723,0.5358703,0.0005509447,0.0000132788855,5.519376e-7,1.2047853e-7,0.000003287946,0.000030049643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894696,0.00013527155,0.00031335116,0.00016268548,0.00028794017,0.00015377178],"domain_scores_gemma":[0.9990567,0.00016074137,0.00023481654,0.00031678934,0.000096790456,0.00013416153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064513535,0.00010293107,0.00022343484,0.00003475927,0.00013915998,0.00006253462,0.0005280054,0.00004507282,0.000011840144],"category_scores_gemma":[0.00007560695,0.00005819351,0.00025404032,0.00025510087,0.000114129594,0.0001061884,0.00007665863,0.00023296218,7.414512e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071856906,0.0003110018,0.0012991239,0.0000463252,0.00047337628,0.000014780759,0.005361471,0.0013493394,0.0004559914,0.9374213,0.0045481585,0.048647262],"study_design_scores_gemma":[0.00022315196,0.00006831058,0.037977204,0.000014983745,0.00021696952,0.000007995361,0.000019172163,0.8537965,0.000052580275,0.10750791,0.00003542423,0.00007980026],"about_ca_topic_score_codex":0.0000075251346,"about_ca_topic_score_gemma":0.000004698405,"teacher_disagreement_score":0.85244715,"about_ca_system_score_codex":0.000039439397,"about_ca_system_score_gemma":0.00006852111,"threshold_uncertainty_score":0.23730624},"labels":[],"label_agreement":null},{"id":"W2264689466","doi":"","title":"A Mixture-of-Normal Distribution Modeling Approach in Financial Econometrics: A Selected Review","year":2013,"lang":"en","type":"review","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Kurtosis; Econometrics; Financial econometrics; Distribution (mathematics); Normal distribution; Flexibility (engineering); Mixture model; Economics; Computer science; Finance; Mathematics; Statistics; Financial market","score_opus":0.03391737035817708,"score_gpt":0.2889121361373873,"score_spread":0.2549947657792102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2264689466","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.1449613e-7,0.5003935,0.4989247,0.000021100086,0.00010300185,0.00045093836,0.0000062394993,0.000017207944,0.0000828829],"genre_scores_gemma":[0.000020362446,0.9496461,0.049780834,0.000037193415,0.00022856292,0.00010025036,0.00007025486,0.00003514761,0.00008125894],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937278,0.0008709222,0.0017044336,0.00068588764,0.00038904857,0.002621901],"domain_scores_gemma":[0.9977435,0.00011124204,0.0010913857,0.0006042607,0.0002916912,0.00015794598],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0055849957,0.00058729923,0.0024158775,0.0006822831,0.000115336894,0.00012195422,0.0019157937,0.0004842868,0.0000062771414],"category_scores_gemma":[0.00038740368,0.00046700065,0.00072986924,0.0035449234,0.000028866527,0.00060383556,0.0002180059,0.0049617216,0.000011934782],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014117951,0.00006857636,5.8356505e-7,0.005683982,0.000066883505,0.0000022770732,0.000013536536,0.000013071388,4.9286633e-8,0.08526379,0.00009321831,0.9087926],"study_design_scores_gemma":[0.0015863124,0.00077563216,0.0000029326463,0.06462746,0.0015664311,0.0075365067,0.000016284826,0.11287181,0.0000010577654,0.38319454,0.4243719,0.0034491266],"about_ca_topic_score_codex":0.000032208205,"about_ca_topic_score_gemma":0.000009370272,"teacher_disagreement_score":0.9053435,"about_ca_system_score_codex":0.0016134826,"about_ca_system_score_gemma":0.00991868,"threshold_uncertainty_score":0.99977815},"labels":[],"label_agreement":null},{"id":"W2278730005","doi":"10.48550/arxiv.1508.02663","title":"Particle Gibbs Split-Merge Sampling for Bayesian Inference in Mixture Models","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Gibbs sampling; Merge (version control); Inference; Bayesian inference; Bayesian probability; Computer science; Econometrics; Statistics; Mathematics; Statistical physics; Artificial intelligence; Physics; Information retrieval","score_opus":0.17920494181217653,"score_gpt":0.259742621568692,"score_spread":0.08053767975651546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278730005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03127978,0.00023135576,0.96595746,0.00020385241,0.0004953732,0.0005898174,0.00003116727,0.00017525225,0.0010359606],"genre_scores_gemma":[0.7662602,0.000077711586,0.2329541,0.000121528494,0.000071607916,0.000006120426,0.000011090087,0.000022415838,0.0004752066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997251,0.00022359923,0.00033449123,0.0014278347,0.00011822102,0.00064486125],"domain_scores_gemma":[0.997478,0.0002903094,0.00022781917,0.0014072474,0.00026588578,0.000330756],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091899314,0.0004119067,0.0005422687,0.00022439759,0.00011004717,0.00016103075,0.0019281257,0.00047791094,0.000007587777],"category_scores_gemma":[0.000119150805,0.00045857774,0.00023220903,0.000636727,0.00007267887,0.00066298596,0.0014623278,0.00066943583,0.000009621345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035132776,0.00007954077,0.0003182601,0.0000828424,0.000027954951,0.000051061834,0.00062185846,0.26157156,0.000030408832,0.73239154,0.000100801626,0.0046890634],"study_design_scores_gemma":[0.0003405759,0.000025267178,0.000038670183,0.000067217974,0.00001884288,8.4579915e-7,0.000013314958,0.53177136,0.000060365455,0.46723935,0.00013459855,0.00028959065],"about_ca_topic_score_codex":0.00016333302,"about_ca_topic_score_gemma":0.0001346817,"teacher_disagreement_score":0.73498046,"about_ca_system_score_codex":0.00023952968,"about_ca_system_score_gemma":0.00046842074,"threshold_uncertainty_score":0.9997866},"labels":[],"label_agreement":null},{"id":"W2280270471","doi":"10.1007/s11222-016-9641-6","title":"Mixture models: building a parameter space","year":2016,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Space (punctuation); Parameter space; Mixture model; Mathematics; Computer science; Applied mathematics; Artificial intelligence; Statistics","score_opus":0.019367954638465253,"score_gpt":0.27145576422120066,"score_spread":0.2520878095827354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2280270471","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017825379,0.00022488396,0.9962482,0.00066843006,0.00022083857,0.00006923927,0.000013973341,0.00008304266,0.0006888727],"genre_scores_gemma":[0.2995619,0.00002646626,0.7000446,0.00019477565,0.00005608345,0.0000010112424,2.8982348e-7,0.000007751354,0.00010714137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890846,0.00007819918,0.00017640973,0.00038383945,0.00014695949,0.00030613478],"domain_scores_gemma":[0.9989184,0.0005389689,0.00008061268,0.0002818078,0.000063707535,0.00011645977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032621433,0.00014275685,0.00017033369,0.000052686442,0.00014621526,0.00015664934,0.0002847353,0.00005292424,0.0000027565275],"category_scores_gemma":[0.00007468563,0.00009541875,0.000026637512,0.00010932408,0.000045251043,0.00017521193,0.00027211997,0.000092266346,0.000002698441],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.604093e-7,0.000004463673,0.00001367189,0.000006514449,0.0000056128474,0.0000105794425,0.00015203006,0.000010897186,0.0003687446,0.5894294,0.00041861893,0.40957862],"study_design_scores_gemma":[0.00015949203,0.000028072387,0.00005880297,0.000050879866,0.0000044837075,0.00002586181,0.0000024916633,0.425355,0.00022308753,0.5733413,0.0006103512,0.00014017586],"about_ca_topic_score_codex":0.000009354204,"about_ca_topic_score_gemma":0.00000122973,"teacher_disagreement_score":0.4253441,"about_ca_system_score_codex":0.000014822082,"about_ca_system_score_gemma":0.000026999398,"threshold_uncertainty_score":0.3891064},"labels":[],"label_agreement":null},{"id":"W2287543214","doi":"10.1016/j.amar.2016.02.001","title":"Multilevel Dirichlet process mixture analysis of railway grade crossing crash data","year":2016,"lang":"en","type":"article","venue":"Analytic Methods in Accident Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Transport Canada","keywords":"Latent Dirichlet allocation; Outlier; Computer science; Parametric statistics; Bayesian probability; Dirichlet process; Crash; Multilevel model; Bayes' theorem; Probabilistic logic; Dirichlet distribution; Econometrics; Statistical model; Bayesian hierarchical modeling; Bayes factor; Data mining; Statistics; Machine learning; Mathematics; Artificial intelligence; Topic model","score_opus":0.28012428021635016,"score_gpt":0.5646036332053688,"score_spread":0.2844793529890186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287543214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009405101,0.00043628615,0.9873851,0.0015413866,0.00012499894,0.00032823367,0.000016069498,0.000044432858,0.00071837165],"genre_scores_gemma":[0.22109734,0.00012432164,0.77752835,0.000073822106,0.000058896854,0.000025332429,0.000007709166,0.00001931353,0.0010649534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99059266,0.0041658916,0.0010362237,0.0015942804,0.0015784485,0.0010324898],"domain_scores_gemma":[0.98826504,0.0064924466,0.00028587307,0.004018249,0.0006605304,0.00027787566],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.028178202,0.00029332406,0.0009785542,0.0027151487,0.00024849147,0.00045492098,0.0061142426,0.00023416855,0.00014739491],"category_scores_gemma":[0.0070571476,0.00019306429,0.00023864304,0.007988628,0.0004450819,0.0011721906,0.0023434828,0.00064747,0.000010982309],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028856804,0.00031403152,0.045674056,0.000092586546,0.0008100201,0.00007646523,0.0018724891,0.00008218809,0.02322611,0.014342089,0.0011837368,0.91229737],"study_design_scores_gemma":[0.001460772,0.00013195603,0.1022169,0.0004469693,0.00046728383,0.000015186389,0.00013431082,0.6643946,0.043012,0.18543582,0.0014571433,0.00082703773],"about_ca_topic_score_codex":0.00028116244,"about_ca_topic_score_gemma":0.00024192603,"teacher_disagreement_score":0.91147035,"about_ca_system_score_codex":0.00015425934,"about_ca_system_score_gemma":0.00050044927,"threshold_uncertainty_score":0.99926317},"labels":[],"label_agreement":null},{"id":"W2290362878","doi":"10.1162/neco_a_00938","title":"Maximum Pseudolikelihood Estimation for Model-Based Clustering of Time Series Data","year":2017,"lang":"en","type":"preprint","venue":"Neural Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire de Gériatrie de Montréal","funders":"","keywords":"Estimator; Series (stratigraphy); Cluster analysis; Expectation–maximization algorithm; Computer science; Maximum likelihood; Estimation; Algorithm; Mathematics; Estimation theory; Mathematical optimization; Applied mathematics; Statistics; Engineering","score_opus":0.07614330160407824,"score_gpt":0.3498403797478008,"score_spread":0.27369707814372257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290362878","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005723127,0.000061467625,0.99648404,0.000997088,0.00071419857,0.0007185998,0.00015427284,0.000156784,0.000141264],"genre_scores_gemma":[0.1260549,0.000003706289,0.87307477,0.000084149586,0.00008377284,0.000032887954,0.0006030732,0.000023452883,0.000039280625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981636,0.00011812271,0.00044677575,0.00077573804,0.0002783513,0.0002174176],"domain_scores_gemma":[0.9971974,0.00012841437,0.0006914267,0.0016582177,0.0002616073,0.00006297411],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059016515,0.00027034365,0.00042201503,0.00014031668,0.00017550736,0.00034428763,0.0020016178,0.00020649812,8.0107264e-7],"category_scores_gemma":[0.00012360384,0.00027566627,0.00011269351,0.000057412577,0.000049290044,0.0008287949,0.0015771991,0.00023410686,0.0000023099253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025291054,0.000020797645,0.0000012359905,0.00033205468,0.000011500608,9.489487e-7,0.00009936553,0.74608773,0.00022129562,0.00069354795,0.0003222232,0.25218403],"study_design_scores_gemma":[0.00027781018,0.00006095187,0.00002299155,0.00011594222,0.00002962356,0.000003955574,3.8605253e-7,0.80097085,0.00046662107,0.19784334,0.000008090928,0.00019940449],"about_ca_topic_score_codex":0.000016617189,"about_ca_topic_score_gemma":0.000004451283,"teacher_disagreement_score":0.25198463,"about_ca_system_score_codex":0.00003429768,"about_ca_system_score_gemma":0.00022764146,"threshold_uncertainty_score":0.99996954},"labels":[],"label_agreement":null},{"id":"W2291350422","doi":"10.48550/arxiv.1603.01527","title":"Random Locations of Periodic Stationary Processes","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Infimum and supremum; Mathematics; Focus (optics); Regular polygon; Convex hull; Path (computing); Joint probability distribution; Combinatorics; Set (abstract data type); Stochastic process; Statistical physics; Computer science; Physics; Geometry; Statistics","score_opus":0.05849889681558717,"score_gpt":0.20684395402504543,"score_spread":0.14834505720945826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291350422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060492754,0.00022932749,0.9889137,0.00021742,0.00023918893,0.00024078324,0.000034379267,0.00009746353,0.003978465],"genre_scores_gemma":[0.9249192,0.00029118636,0.07296772,0.000048826798,0.00004316267,0.0000019982215,0.000008723174,0.000010162493,0.0017090179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998743,0.00015683942,0.00019337329,0.0006417577,0.000081239144,0.00018379341],"domain_scores_gemma":[0.9981987,0.00022344924,0.00026602682,0.00082871265,0.00038780752,0.000095334486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023755973,0.00018850337,0.00028726135,0.00020638535,0.00009853717,0.000040879095,0.0011905363,0.00015988482,0.000026016187],"category_scores_gemma":[0.00007264198,0.00017276857,0.00011959321,0.00040035375,0.00013672211,0.00031815947,0.0006869039,0.00018797135,0.000017823622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006829279,0.00016068734,0.0006312187,0.0005787533,0.00013033759,0.000067022695,0.00095756276,0.011140348,0.00010960053,0.9750382,0.00066393765,0.010454094],"study_design_scores_gemma":[0.0014087174,0.000056997866,0.0004729183,0.00036032824,0.00009046518,0.000006307834,0.000036384197,0.08348253,0.00089598214,0.9114839,0.0011793438,0.000526132],"about_ca_topic_score_codex":0.000021208005,"about_ca_topic_score_gemma":0.000006787783,"teacher_disagreement_score":0.9188699,"about_ca_system_score_codex":0.00005801274,"about_ca_system_score_gemma":0.0007447376,"threshold_uncertainty_score":0.7045298},"labels":[],"label_agreement":null},{"id":"W2292733224","doi":"10.1515/sagmb-2014-0098","title":"Using informative Multinomial-Dirichlet prior in a t-mixture with reversible jump estimation of nucleosome positions for genome-wide profiling","year":2015,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Canadian Institutes of Health Research","keywords":"Multinomial distribution; Dirichlet distribution; Profiling (computer programming); Jump; Mathematics; Genome; Mixture model; Statistics; Computational biology; Biology; Econometrics; Computer science; Statistical physics; Genetics; Physics","score_opus":0.023026727306635755,"score_gpt":0.33038312067648096,"score_spread":0.3073563933698452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292733224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032298867,0.000145491,0.96647966,0.00009735275,0.0000102962895,0.000787913,0.00008437706,0.000007915529,0.00008811955],"genre_scores_gemma":[0.29796708,0.0000079867095,0.7018098,0.00006160942,0.0000036112451,0.00009557926,0.00004890861,0.0000043802875,0.0000010422672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992352,0.00006155129,0.0002598989,0.00022921043,0.000052419364,0.00016168269],"domain_scores_gemma":[0.99939513,0.00014314496,0.000089685935,0.00018731854,0.00011696547,0.00006776433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021415303,0.00009481222,0.00017251166,0.00013280631,0.000039774975,0.00001668006,0.00015120058,0.000080908176,2.9244026e-7],"category_scores_gemma":[0.000068642585,0.000082630984,0.000013447435,0.00026572606,0.00010351823,0.00004240124,0.000076126926,0.00007807074,2.440513e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034281664,0.00011505429,0.0013845727,0.00007525482,0.000017938944,0.000002128728,0.00078547327,0.0042284904,0.0144298365,0.96006465,0.0000052586506,0.01885709],"study_design_scores_gemma":[0.001159044,0.00031775545,0.0027033703,0.000025404619,0.000025635216,0.000009647087,0.00006597632,0.6737052,0.0075924895,0.31394738,0.00021799772,0.00023006994],"about_ca_topic_score_codex":0.00001404157,"about_ca_topic_score_gemma":0.0000070432175,"teacher_disagreement_score":0.66947675,"about_ca_system_score_codex":0.00003267294,"about_ca_system_score_gemma":0.000111560505,"threshold_uncertainty_score":0.33695936},"labels":[],"label_agreement":null},{"id":"W2293445795","doi":"10.1007/978-3-319-25040-3_62","title":"Computing Boundaries in Local Mixture Models","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Regular polygon; Polytope; Parameter space; Space (punctuation); Algorithm; Mathematical optimization; Theoretical computer science; Geometry; Mathematics","score_opus":0.03290359949436624,"score_gpt":0.27810936634850303,"score_spread":0.24520576685413678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293445795","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015195667,0.0024092125,0.98338896,0.0009270208,0.0023716476,0.0004470208,0.0000055575156,0.00020412156,0.010231238],"genre_scores_gemma":[0.0999923,0.000027108852,0.89758617,0.0015170957,0.00045016996,0.0000049939,0.000005049679,0.00005360448,0.00036351132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99410725,0.00012975563,0.000866645,0.0022561338,0.0014620794,0.0011781354],"domain_scores_gemma":[0.99669904,0.00041337032,0.00034179576,0.0017774394,0.00040910614,0.00035926636],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028051208,0.00084635953,0.0010425055,0.0012169669,0.00035182177,0.001399233,0.0043991264,0.000727967,0.000009041912],"category_scores_gemma":[0.00008958599,0.0007721333,0.00017593589,0.0010290305,0.0018285569,0.0011606053,0.002322424,0.001849556,0.000022601891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064132437,0.000022835244,0.0000055794135,0.000031017003,0.000006188257,0.00017635598,0.0019837918,0.07362176,0.000009220382,0.24272214,0.000088584835,0.68132615],"study_design_scores_gemma":[0.00022207484,0.000063776475,0.0000051138063,0.00027461967,0.0000033545382,0.00006998614,1.9626825e-7,0.5077969,0.00006965334,0.4893831,0.001628909,0.00048231098],"about_ca_topic_score_codex":0.00009499367,"about_ca_topic_score_gemma":0.00025443634,"teacher_disagreement_score":0.68084383,"about_ca_system_score_codex":0.0007086579,"about_ca_system_score_gemma":0.0022217906,"threshold_uncertainty_score":0.9996374},"labels":[],"label_agreement":null},{"id":"W2293591183","doi":"10.1155/2018/5372803","title":"Smooth Kernel Estimation of a Circular Density Function: A Connection to Orthogonal Polynomials on the Unit Circle","year":2018,"lang":"en","type":"article","venue":"Journal of Probability and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Kernel density estimation; Kernel (algebra); Unit circle; Estimator; Cauchy distribution; Fourier series; Multivariate kernel density estimation; Variable kernel density estimation; Orthogonal polynomials; Equivalence (formal languages); Mathematical analysis; Applied mathematics; Pure mathematics; Kernel method; Statistics","score_opus":0.034380695161354224,"score_gpt":0.2806247112904923,"score_spread":0.2462440161291381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2293591183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15243156,0.00001616898,0.84631217,0.0007999622,0.00023876742,0.00012603767,0.000010345789,0.000005091403,0.000059915954],"genre_scores_gemma":[0.5520998,0.0000023729363,0.44760108,0.00022760197,0.000060733364,8.751468e-7,2.653306e-7,0.0000019310028,0.0000053398003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988683,0.0002753019,0.0003700344,0.00013953097,0.00024585746,0.00010096968],"domain_scores_gemma":[0.9985277,0.00038207902,0.00028221493,0.00022440514,0.000497033,0.00008658921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018711331,0.00007537329,0.00018601853,0.000059204358,0.00013642182,0.00005703642,0.0001681825,0.000045575955,0.000012779468],"category_scores_gemma":[0.00074962876,0.000054573506,0.000039926326,0.00017854202,0.00011352498,0.00013336515,0.0000450444,0.00013773801,0.0000019859729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001531359,0.00011267091,0.00045744542,0.00004926075,0.00003283626,0.0000037771476,0.0007860667,0.0002515891,0.0008596412,0.79276454,0.0005603477,0.20396869],"study_design_scores_gemma":[0.00030734175,0.0016475813,0.058006726,0.000058937716,0.00004140759,0.00007464428,0.0000220363,0.04053884,0.0011703701,0.89779043,0.00024077114,0.000100921454],"about_ca_topic_score_codex":0.0000111202735,"about_ca_topic_score_gemma":0.000015908348,"teacher_disagreement_score":0.39966822,"about_ca_system_score_codex":0.000028597828,"about_ca_system_score_gemma":0.00012494747,"threshold_uncertainty_score":0.2225443},"labels":[],"label_agreement":null},{"id":"W2296528819","doi":"10.1109/icmla.2015.70","title":"Topic Novelty Detection Using Infinite Variational Inverted Dirichlet Mixture Models","year":2015,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Dirichlet process; Hierarchical Dirichlet process; Conjugate prior; Inference; Prior probability; Mixture model; Bayesian inference; Novelty; Bayes' theorem; Latent Dirichlet allocation; Computer science; Novelty detection; Mathematics; Artificial intelligence; Parametric model; Bayes factor; Parametric statistics; Bayesian probability; Pattern recognition (psychology); Topic model; Statistics; Boundary value problem; Mathematical analysis","score_opus":0.07779213641419455,"score_gpt":0.28592943684493033,"score_spread":0.20813730043073578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296528819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045256405,0.000042777327,0.9872925,0.0004209163,0.0005571207,0.000107618165,0.0000015169667,0.00016058954,0.0068912706],"genre_scores_gemma":[0.324139,0.0000013808221,0.67449397,0.0008804816,0.000119115655,0.0000040660248,0.0000017566792,0.0000063439343,0.00035389667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883324,0.00012066857,0.00020211018,0.0003241491,0.00030442866,0.00021541707],"domain_scores_gemma":[0.9991395,0.000049943217,0.00007154309,0.00036974065,0.00020763444,0.00016167527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004523881,0.00013653886,0.00014487105,0.000115450195,0.000084931016,0.00012874488,0.0003599219,0.00012873737,0.000010527166],"category_scores_gemma":[0.000052597807,0.00011531228,0.000051870036,0.00045815666,0.000016919215,0.00086959335,0.00015727423,0.00015152083,0.000011441063],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017753231,0.00011320824,0.0002299754,0.000014193732,0.000052590458,0.000008180557,0.0017340035,0.013645637,0.0051988587,0.8587766,0.0009882255,0.119220726],"study_design_scores_gemma":[0.0002638567,0.00002172742,0.00016964132,0.0000037219586,0.0000053304047,0.000019485955,0.0000030573583,0.7663777,0.00092045264,0.23141488,0.00067336357,0.00012680196],"about_ca_topic_score_codex":0.00013692438,"about_ca_topic_score_gemma":0.000026188658,"teacher_disagreement_score":0.75273204,"about_ca_system_score_codex":0.00007727116,"about_ca_system_score_gemma":0.00014761854,"threshold_uncertainty_score":0.47022983},"labels":[],"label_agreement":null},{"id":"W2296728097","doi":"","title":"Online Learning of a Dirichlet Process Mixture of Generalized Dirichlet Distributions for Simultaneous Clustering and Localized Feature Selection","year":2012,"lang":"en","type":"article","venue":"Asian Conference on Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Hierarchical Dirichlet process; Latent Dirichlet allocation; Dirichlet process; Mixture model; Dirichlet distribution; Computer science; Feature selection; Artificial intelligence; Pattern recognition (psychology); Nonparametric statistics; Mathematics; Data mining; Algorithm; Topic model; Bayesian probability; Statistics","score_opus":0.019111419161808352,"score_gpt":0.3050766169462291,"score_spread":0.28596519778442075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296728097","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02994608,0.00039494454,0.9678669,0.00087669195,0.00009315152,0.00034300252,0.00003541482,0.00011395945,0.0003298552],"genre_scores_gemma":[0.7728125,0.00004521516,0.22657911,0.0000496685,0.000077629185,0.000019398414,0.00007351706,0.000020617912,0.0003223264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812526,0.00038113087,0.00036543625,0.0004191645,0.00025331444,0.00045567405],"domain_scores_gemma":[0.99861574,0.00028693007,0.00041685582,0.00022104707,0.00029298145,0.000166466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055636646,0.00029038754,0.00052093057,0.00016091444,0.00025586959,0.000066662855,0.0003373981,0.00019305728,0.000012043096],"category_scores_gemma":[0.00069381355,0.0002525415,0.00010742401,0.00046904932,0.000074824224,0.00027372528,0.00012225518,0.000682822,5.911026e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005632557,0.00084288325,0.018682802,0.0011143716,0.00025605218,0.000008839215,0.009405619,0.015687514,0.030153813,0.14871678,0.00009847587,0.7744696],"study_design_scores_gemma":[0.0010775911,0.000489729,0.00091674196,0.00017930276,0.00005445963,0.00004077204,0.00010760443,0.9903859,0.0024931987,0.0016861552,0.0022424848,0.0003260825],"about_ca_topic_score_codex":0.000031767264,"about_ca_topic_score_gemma":0.000020982614,"teacher_disagreement_score":0.97469836,"about_ca_system_score_codex":0.000030321315,"about_ca_system_score_gemma":0.00006560462,"threshold_uncertainty_score":0.99999267},"labels":[],"label_agreement":null},{"id":"W2299360728","doi":"","title":"A Flexible Modeling Approach Using Dirichlet Process Mixtures: Application to Multi-Level Railway Grade Crossing Crash Data","year":2016,"lang":"en","type":"article","venue":"Transportation Research Board 95th Annual MeetingTransportation Research Board","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outlier; Latent Dirichlet allocation; Computer science; Parametric statistics; Dirichlet process; Bayesian probability; Data mining; Robustness (evolution); Probabilistic logic; Dirichlet distribution; Statistical model; Identification (biology); Econometrics; Machine learning; Topic model; Artificial intelligence; Statistics; Mathematics","score_opus":0.26860691910550444,"score_gpt":0.46273168886486066,"score_spread":0.19412476975935622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299360728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11026668,0.00017696836,0.8827783,0.0023342415,0.0001530758,0.0028888017,0.00068128156,0.0005096721,0.00021097389],"genre_scores_gemma":[0.53847647,0.00007652276,0.45977297,0.00013878799,0.00020836826,0.00052612956,0.00027091405,0.000108231485,0.0004216418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98427963,0.0020519984,0.0017651066,0.0034700376,0.0055599525,0.00287326],"domain_scores_gemma":[0.9890531,0.0012908161,0.00030119307,0.002937029,0.0049733613,0.0014445055],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0156166,0.00072122144,0.0008201097,0.002079949,0.002341417,0.0010681553,0.004990558,0.000524354,0.000030665324],"category_scores_gemma":[0.0011054842,0.00060092256,0.0002242518,0.0053181387,0.0007564804,0.0037380254,0.00017275944,0.001619924,0.00008242218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022042461,0.0049806996,0.028470397,0.0038005349,0.0007361662,0.00042507672,0.10717795,0.09223713,0.31535885,0.080843486,0.0067404187,0.35702506],"study_design_scores_gemma":[0.0054919403,0.00058054604,0.024473246,0.0013927523,0.00009553721,0.0000069716375,0.003947636,0.91733426,0.019060865,0.020533932,0.004580006,0.0025023015],"about_ca_topic_score_codex":0.003541287,"about_ca_topic_score_gemma":0.0019113102,"teacher_disagreement_score":0.82509714,"about_ca_system_score_codex":0.0003513415,"about_ca_system_score_gemma":0.0017089704,"threshold_uncertainty_score":0.9999688},"labels":[],"label_agreement":null},{"id":"W2300776220","doi":"10.71781/15571","title":"Mesures d'apparentement pour des modèles de sélection avec interactions dans une population structurée en groupes","year":2009,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Physics; Humanities; Art","score_opus":0.012682905183415676,"score_gpt":0.2408430876621742,"score_spread":0.22816018247875852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300776220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30948272,0.00357907,0.67523676,0.00050662446,0.0015385204,0.0003682497,0.00003082243,0.00016101533,0.009096179],"genre_scores_gemma":[0.8257162,0.0004992801,0.14313918,0.000084181396,0.000381132,0.0000308033,0.00039241524,0.000034850887,0.029721964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99634326,0.0007066038,0.0006423821,0.00096000073,0.0006986559,0.0006491204],"domain_scores_gemma":[0.9978973,0.00017192062,0.0005880272,0.0005230465,0.00042356885,0.00039609885],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004164336,0.000645394,0.00051475555,0.00050987734,0.007412763,0.0002781873,0.0007295424,0.000493059,0.000025181957],"category_scores_gemma":[0.000078280675,0.0007416392,0.0004475146,0.000669545,0.00018065644,0.00136887,0.00016448993,0.00065779686,0.000013241701],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006653229,0.0007080545,0.01940094,0.0003690161,0.0007966153,0.001160192,0.2257061,0.03486025,0.09990373,0.36660007,0.00054919586,0.24928053],"study_design_scores_gemma":[0.0011152523,0.00025334867,0.7460359,0.0008874706,0.0006821414,0.0024249663,0.013078065,0.14061807,0.02318889,0.06593252,0.004574556,0.0012088229],"about_ca_topic_score_codex":0.116340734,"about_ca_topic_score_gemma":0.07054449,"teacher_disagreement_score":0.726635,"about_ca_system_score_codex":0.009698885,"about_ca_system_score_gemma":0.0012110387,"threshold_uncertainty_score":0.9995035},"labels":[],"label_agreement":null},{"id":"W2303791683","doi":"10.1080/03610926.2014.983806","title":"Some contributions on the multivariate Poisson–Skellam probability distribution","year":2016,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Statistics Canada","funders":"","keywords":"Multivariate statistics; Poisson distribution; Compound Poisson distribution; Statistics; Zero-inflated model; Multivariate analysis; Distribution (mathematics); Mathematics; Poisson regression; Medicine; Mathematical analysis; Environmental health","score_opus":0.03513996025616692,"score_gpt":0.38282486072348937,"score_spread":0.3476849004673225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2303791683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043642757,0.0005765353,0.99283653,0.005082017,0.00012791406,0.00037577286,0.00020520714,0.00005604752,0.00030355883],"genre_scores_gemma":[0.17318776,0.0004177186,0.8257476,0.00032887637,0.000023004932,0.00010987599,0.0000143509205,0.000006706944,0.00016412059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9889512,0.010048847,0.00034573616,0.00031032026,0.000109359156,0.00023454457],"domain_scores_gemma":[0.98530424,0.012889595,0.0001547064,0.0014279832,0.00014421907,0.000079262296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012473367,0.00014792617,0.000202079,0.000042105148,0.00035903946,0.0000797007,0.00079729204,0.000089660425,0.000014943071],"category_scores_gemma":[0.0051433085,0.00008405082,0.000035308152,0.00019421308,0.00034928427,0.00023404854,0.00033257014,0.0002442289,0.0000070975034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025468147,0.000048256647,0.000018159168,0.0000047709136,0.000006954173,2.9555287e-7,0.00026550665,0.0000010068,0.0008234591,0.755498,0.0001245132,0.24318363],"study_design_scores_gemma":[0.00037926008,0.000039662966,0.0032386454,0.000071436414,0.000008921377,0.0000027044657,0.000012144239,0.0023968257,0.002467858,0.9886878,0.0025658943,0.0001288547],"about_ca_topic_score_codex":0.000013695411,"about_ca_topic_score_gemma":0.000003858902,"teacher_disagreement_score":0.24305478,"about_ca_system_score_codex":0.0000918673,"about_ca_system_score_gemma":0.00005515797,"threshold_uncertainty_score":0.6157392},"labels":[],"label_agreement":null},{"id":"W2307710747","doi":"","title":"THE NESTED DIRICHLET DISTRIBUTION AND INCOMPLETE CATEGORICAL DATA ANALYSIS","year":2009,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Dirichlet distribution; Frequentist inference; Categorical variable; Categorical distribution; Mathematics; Bayes factor; Likelihood function; Conjugate prior; Bayesian probability; Marginal likelihood; Latent Dirichlet allocation; Computer science; Statistics; Prior probability; Bayes' theorem; Bayesian inference; Artificial intelligence; Bayesian linear regression; Maximum likelihood; Topic model","score_opus":0.03312163371153608,"score_gpt":0.30227403107910467,"score_spread":0.2691523973675686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2307710747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037498766,0.00017902299,0.9911716,0.007245025,0.000042352265,0.000054469016,0.000007697108,0.000065324966,0.0008595158],"genre_scores_gemma":[0.7562049,0.00006175629,0.24281494,0.00059252855,0.000042270363,0.0000013886976,0.00007702491,0.0000016682561,0.00020350184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990607,0.00012772382,0.00014321772,0.00034919416,0.0001425207,0.00017666977],"domain_scores_gemma":[0.998583,0.0001491296,0.0000388475,0.0011156015,0.000034745302,0.00007865461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064416527,0.000079818594,0.00012834159,0.000030229188,0.00022685333,0.00026219783,0.0009660184,0.000033646764,0.0000019342458],"category_scores_gemma":[0.000051647236,0.000045163473,0.00003160503,0.0008286588,0.000031741012,0.00028132138,0.00032103594,0.0000794226,0.0000026859466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001864314,0.0000140797865,0.00016914292,4.4960473e-7,0.000033455966,0.0000034101947,0.000025930727,0.0000026379075,0.000035638284,0.6692755,0.0030124765,0.3274254],"study_design_scores_gemma":[0.00012525174,0.000041229938,0.056830566,7.6413426e-7,0.00009584223,0.000014205168,0.0000036789656,0.76575905,0.000037912618,0.15746325,0.01947805,0.00015020854],"about_ca_topic_score_codex":0.000039211,"about_ca_topic_score_gemma":0.00002734504,"teacher_disagreement_score":0.7657564,"about_ca_system_score_codex":0.000011538748,"about_ca_system_score_gemma":0.000016026763,"threshold_uncertainty_score":0.252838},"labels":[],"label_agreement":null},{"id":"W2316359013","doi":"10.1080/01966324.2007.10737689","title":"Bayesian Analysis of Dyadic Data","year":2007,"lang":"en","type":"article","venue":"American Journal of Mathematical and Management Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of Connecticut","keywords":"Computer science; Markov chain Monte Carlo; Missing data; Bayesian probability; Variety (cybernetics); Class (philosophy); Variable-order Bayesian network; Inference; Covariate; Data mining; Bayesian inference; Machine learning; Artificial intelligence; Econometrics; Mathematics","score_opus":0.03373646764183357,"score_gpt":0.33197570451469377,"score_spread":0.2982392368728602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316359013","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008642484,0.0001138197,0.98524165,0.0006983883,0.00004133222,0.000043705902,8.443738e-7,0.0000062566296,0.0052115456],"genre_scores_gemma":[0.37906498,0.00009585144,0.6206568,0.00014293531,0.000010789706,1.5692353e-7,1.0982036e-7,0.0000012648643,0.000027141108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99855685,0.00006260297,0.00048514895,0.0002175586,0.00048208682,0.00019573254],"domain_scores_gemma":[0.9987208,0.0002728824,0.0004441429,0.00038773206,0.00004493095,0.00012950283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045721973,0.000082602564,0.0003875774,0.00055317214,0.000066497945,0.00006524505,0.001473133,0.000010956172,0.000012098931],"category_scores_gemma":[0.00005081628,0.00005292947,0.00007679456,0.0018814899,0.0005657627,0.0004073641,0.0003987645,0.000060112583,6.6030753e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049939163,0.000076629796,0.00031298303,0.000028453805,0.00030268953,0.00002297541,0.0002978828,0.000014548489,0.000023736715,0.54300314,0.00009872345,0.45581323],"study_design_scores_gemma":[0.00060157635,0.0017614398,0.019742178,0.00027608345,0.0023164856,0.00018239205,0.0022350112,0.31512186,0.00033270495,0.6552508,0.0016062161,0.00057327567],"about_ca_topic_score_codex":0.0000045644065,"about_ca_topic_score_gemma":0.0000024480776,"teacher_disagreement_score":0.45523995,"about_ca_system_score_codex":0.0000056923595,"about_ca_system_score_gemma":0.000016713691,"threshold_uncertainty_score":0.2737472},"labels":[],"label_agreement":null},{"id":"W2339371659","doi":"10.1007/s13171-018-0143-9","title":"Inference on Covariance Operators via Concentration Inequalities: k-sample Tests, Classification, and Clustering via Rademacher Complexities","year":2018,"lang":"en","type":"article","venue":"Sankhya A","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Engineering and Physical Sciences Research Council","keywords":"Covariance; Inference; Cluster analysis; Mathematics; Classifier (UML); Maximization; Pattern recognition (psychology); Rational quadratic covariance function; Sample (material); Analysis of covariance; Covariance function; Artificial intelligence; Statistics; Computer science; Covariance intersection; Mathematical optimization","score_opus":0.06950374276023197,"score_gpt":0.32789190044147565,"score_spread":0.2583881576812437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339371659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005873894,0.00010768717,0.99077874,0.000815833,0.00031438828,0.00020899347,0.000009648311,0.00013022157,0.0017605749],"genre_scores_gemma":[0.6705554,0.000013548182,0.32800633,0.0011576012,0.00016835194,0.000020488204,0.000005451088,0.0000090302565,0.0000638052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854845,0.00021733432,0.00029818245,0.00045118202,0.00020277481,0.0002820778],"domain_scores_gemma":[0.99886215,0.00029265526,0.00011182287,0.0004760733,0.00014862083,0.00010867327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042685698,0.00018603934,0.00020517525,0.00005223305,0.0002566893,0.00023887552,0.00038457118,0.00009108232,0.000047224374],"category_scores_gemma":[0.0001524192,0.00016761733,0.000026870755,0.00023801987,0.0002251272,0.0004668592,0.00012348116,0.00013785128,0.000022761033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002003591,0.000058909656,0.001966964,0.00005474579,0.000026512475,0.0000025358713,0.007384927,0.000026313486,0.008213519,0.88044286,0.00049701205,0.10130567],"study_design_scores_gemma":[0.00062068936,0.00041699302,0.012513329,0.00013173527,0.000012574871,0.000019497595,0.00012309174,0.76222354,0.004195667,0.21371812,0.005430948,0.0005938091],"about_ca_topic_score_codex":0.00013630392,"about_ca_topic_score_gemma":0.00004691925,"teacher_disagreement_score":0.76219726,"about_ca_system_score_codex":0.000048117516,"about_ca_system_score_gemma":0.00007220041,"threshold_uncertainty_score":0.68352365},"labels":[],"label_agreement":null},{"id":"W2340675989","doi":"10.1002/cjs.11274","title":"Sample‐size calculation for tests of homogeneity","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Homogeneity (statistics); Sample size determination; Parametric statistics; Statistics; Econometrics; Statistical hypothesis testing; Parametric model; Computer science; Limiting; Simple (philosophy); Mathematics; Engineering","score_opus":0.029373134481366633,"score_gpt":0.27533956630554246,"score_spread":0.24596643182417582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340675989","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013006979,0.000072612056,0.99713683,0.0005239537,0.00033023904,0.00006200735,0.00052362593,0.0000020535601,0.000047961108],"genre_scores_gemma":[0.25309604,0.000006964573,0.7467166,0.00006981794,0.000058668702,5.757154e-7,4.3385091e-7,0.0000044508315,0.000046422432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929494,0.000043754044,0.00029946739,0.00008091877,0.00010640493,0.00017452576],"domain_scores_gemma":[0.9976333,0.0011692495,0.0002464604,0.00015943259,0.00046515613,0.00032643997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004170734,0.00006370688,0.00015759068,0.000095261,0.000051440788,0.00002446173,0.00030035258,0.0000394582,0.000014692861],"category_scores_gemma":[0.0018086741,0.000045197787,0.000047506695,0.000092789196,0.000052368647,0.00013003424,0.000007988726,0.000041870655,5.731785e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005792557,0.000007775419,0.002509999,0.000022910748,0.000025121504,0.0000237552,0.00021527622,0.000010356207,0.0014700132,0.5130782,0.007886436,0.47474435],"study_design_scores_gemma":[0.001038171,0.00041917816,0.05822451,0.00013849894,0.00004611958,0.000108348046,0.0000048722586,0.0039147604,0.0025324381,0.922361,0.010972741,0.00023935235],"about_ca_topic_score_codex":0.00054514303,"about_ca_topic_score_gemma":0.003608219,"teacher_disagreement_score":0.47450498,"about_ca_system_score_codex":0.00006834728,"about_ca_system_score_gemma":0.0009246919,"threshold_uncertainty_score":0.21652825},"labels":[],"label_agreement":null},{"id":"W2343187332","doi":"10.1155/2016/4037380","title":"Semisupervised Clustering by Iterative Partition and Regression with Neuroscience Applications","year":2016,"lang":"en","type":"review","venue":"Computational Intelligence and Neuroscience","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"School of Science, Monash University Malaysia; Universiteit van Amsterdam; University of Melbourne; Monash University","keywords":"Cluster analysis; Computer science; Artificial intelligence; Machine learning; Regression; Unsupervised learning; Regression analysis; Segmented regression; Pattern recognition (psychology); Consensus clustering; Data mining; Correlation clustering; Polynomial regression; Statistics; CURE data clustering algorithm; Mathematics","score_opus":0.07967677072065657,"score_gpt":0.36534808437397687,"score_spread":0.2856713136533203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343187332","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.8329425e-7,0.36042234,0.6388944,0.00011428461,0.00008786792,0.00036513683,0.00001990184,0.00004931111,0.00004618419],"genre_scores_gemma":[0.0004103131,0.95196366,0.046643186,0.00057243445,0.000041283976,0.00018037988,0.000007637044,0.00001843043,0.00016265018],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731976,0.00021094675,0.00041617875,0.0013093689,0.00040627617,0.00033749948],"domain_scores_gemma":[0.99860865,0.00039661877,0.00027985472,0.0003716991,0.00010346069,0.00023970613],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029017578,0.0003933256,0.00052079203,0.00017876622,0.0005038456,0.00053009944,0.00082928425,0.00010253601,0.0000019539734],"category_scores_gemma":[0.00004708887,0.0002462187,0.00006247,0.00075009494,0.0005489051,0.0008833906,0.00043313412,0.00024493106,0.0000036807805],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015610811,0.000023662542,0.0000014734726,0.000473284,0.00000144388,0.0000069802754,0.00007014371,0.00010400102,0.00003951842,0.010199889,0.00006996827,0.98900807],"study_design_scores_gemma":[0.00016514472,0.0005157907,0.000014374352,0.0096269315,0.00006670136,0.0011115681,0.000008624096,0.3209061,0.00018960789,0.029651344,0.6363345,0.0014092964],"about_ca_topic_score_codex":0.0000011070962,"about_ca_topic_score_gemma":3.586375e-7,"teacher_disagreement_score":0.9875988,"about_ca_system_score_codex":0.00002745184,"about_ca_system_score_gemma":0.00014324072,"threshold_uncertainty_score":0.999999},"labels":[],"label_agreement":null},{"id":"W2346128565","doi":"10.1007/s40304-015-0079-5","title":"Testing the Order of a Normal Mixture in Mean","year":2016,"lang":"en","type":"article","venue":"Communications in Mathematics and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Normal distribution; Mixture model; Applied mathematics; Order (exchange); Component (thermodynamics); Distribution (mathematics); Test (biology); Variance (accounting); Statistical hypothesis testing; Mathematical analysis; Physics; Thermodynamics","score_opus":0.06242051314097595,"score_gpt":0.32318934083510087,"score_spread":0.2607688276941249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2346128565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007452613,0.00023483761,0.99561274,0.0009754253,0.000015570322,0.000106720334,0.000014651748,0.000007971145,0.0022868377],"genre_scores_gemma":[0.094976485,0.00016607084,0.9047628,0.000035411405,0.0000027458518,0.000012196045,5.717884e-7,0.00000421666,0.000039526567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993079,0.000106079686,0.00030256403,0.00008947071,0.000085926295,0.00010807844],"domain_scores_gemma":[0.99662334,0.0020826457,0.00010834589,0.0010664136,0.000099116194,0.0000201629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007674048,0.00006640755,0.00013111568,0.00006279773,0.000061180646,0.000026694768,0.0009233348,0.00003227133,0.0000018296736],"category_scores_gemma":[0.00059948006,0.000037870606,0.000008445713,0.00033653932,0.00014103102,0.0000702041,0.00040747612,0.00010772737,8.53118e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.1315165e-7,0.000052989075,0.0003467487,0.00002187611,0.0000022395102,6.2933526e-7,0.0022387698,0.0000014839209,0.0002656513,0.8700787,0.000048691032,0.12694195],"study_design_scores_gemma":[0.00020619204,0.000018453607,0.0023074541,0.00016314331,0.000004223263,0.000008315359,0.00007083114,0.19147615,0.00004309898,0.8053906,0.00023095745,0.000080576254],"about_ca_topic_score_codex":0.000017286546,"about_ca_topic_score_gemma":0.00013830623,"teacher_disagreement_score":0.19147466,"about_ca_system_score_codex":0.000011305838,"about_ca_system_score_gemma":0.000039900315,"threshold_uncertainty_score":0.1715801},"labels":[],"label_agreement":null},{"id":"W2353061623","doi":"10.1007/s11634-016-0250-1","title":"Latent class model with conditional dependency per modes to cluster categorical data","year":2016,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Categorical variable; Conditional independence; Multinomial distribution; Independence (probability theory); Model selection; Latent class model; Mathematics; Local independence; Conditional probability distribution; Conditional probability; Mixture model; Latent variable; Class (philosophy); Expectation–maximization algorithm; Information Criteria; Dependency (UML); Statistics; Posterior probability; Algorithm; Latent variable model; Computer science; Artificial intelligence; Maximum likelihood; Bayesian probability","score_opus":0.06299037588866112,"score_gpt":0.3427291082985342,"score_spread":0.27973873240987307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2353061623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054088514,0.00027729647,0.9919681,0.006556516,0.000019624886,0.00011607788,0.00022144642,0.00002469476,0.00027536682],"genre_scores_gemma":[0.5925219,0.0005314207,0.40605778,0.00023792959,0.000021283759,0.000019152292,0.000443716,0.000005027733,0.00016176808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800974,0.00010366303,0.00028874626,0.001079557,0.0003113232,0.000206954],"domain_scores_gemma":[0.9971681,0.00012159301,0.00010664057,0.0024136913,0.00007590759,0.00011401863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005835284,0.00014228282,0.00023538037,0.00022413392,0.0000787901,0.00010434863,0.0017023431,0.00005680015,0.000008239428],"category_scores_gemma":[0.000045947676,0.00008562627,0.000022648219,0.0006098505,0.00006158741,0.0029942337,0.0007362182,0.00007947163,0.000009704541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044179797,0.00013428362,0.0069208625,0.000012005486,0.0001400111,0.0000039168867,0.000089621004,0.003805961,0.0013585672,0.60501724,0.0005383099,0.38193503],"study_design_scores_gemma":[0.00023058076,0.000017152512,0.0062610754,0.000008992351,0.00010536925,0.000003883767,0.0000076167635,0.918695,0.000030191086,0.07256088,0.0019103478,0.00016897057],"about_ca_topic_score_codex":0.000013259052,"about_ca_topic_score_gemma":0.00070031366,"teacher_disagreement_score":0.914889,"about_ca_system_score_codex":0.000039330233,"about_ca_system_score_gemma":0.00006707451,"threshold_uncertainty_score":0.3491738},"labels":[],"label_agreement":null},{"id":"W2360393060","doi":"10.1016/j.compmedimag.2016.05.001","title":"WITHDRAWN: Adaptive Swarm Balancing Algorithms for rare-event prediction in imbalanced healthcare data","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Event (particle physics); Rare events; Event data; Swarm behaviour; Algorithm; Artificial intelligence; Data mining; Mathematics; Statistics","score_opus":0.03440100624848556,"score_gpt":0.32043466044108965,"score_spread":0.28603365419260407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2360393060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008037099,0.0010243701,0.98025817,0.016349701,0.0009788427,0.00034181896,0.00006052803,0.00016628923,0.000016595919],"genre_scores_gemma":[0.23224162,0.00065673416,0.7636165,0.0028836057,0.00045315753,0.000056743625,0.000037419602,0.000024652854,0.000029574381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975718,0.00021767807,0.00043748596,0.0008645514,0.00042822526,0.00048026108],"domain_scores_gemma":[0.9981845,0.00045176904,0.000120763834,0.00075857586,0.000107582295,0.0003768038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016805445,0.00021841662,0.00038059612,0.00018013774,0.00014639486,0.00008879779,0.000964567,0.00012291524,0.0000015740741],"category_scores_gemma":[0.00018147271,0.00015411187,0.000058348844,0.00033400016,0.00017277358,0.00051760545,0.00063281954,0.0002626736,7.157879e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041230905,0.000060484974,0.0010336535,0.00006378864,0.00002088457,0.00004794179,0.0003002014,7.9537307e-7,0.00016942139,0.03141507,0.0014649779,0.96538156],"study_design_scores_gemma":[0.003044478,0.000109118904,0.0023905248,0.0007716043,0.000009951002,0.00010172866,0.000012206812,0.9339757,0.00006754637,0.056368265,0.0028915417,0.00025736584],"about_ca_topic_score_codex":0.00004386369,"about_ca_topic_score_gemma":0.000015124576,"teacher_disagreement_score":0.9651242,"about_ca_system_score_codex":0.000036666926,"about_ca_system_score_gemma":0.00020725865,"threshold_uncertainty_score":0.6284499},"labels":[],"label_agreement":null},{"id":"W2375394096","doi":"10.1016/j.spa.2018.03.009","title":"Process convergence for the complexity of Radix Selection on Markov sources","year":2018,"lang":"en","type":"preprint","venue":"Stochastic Processes and their Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fondation Sciences Mathématiques de Paris; Agence Nationale de la Recherche; Deutsche Forschungsgemeinschaft; Alexander von Humboldt-Stiftung","keywords":"Mathematics; Markov chain; Bernoulli's principle; Discrete mathematics; Independent and identically distributed random variables; Central limit theorem; Limit (mathematics); Normalization (sociology); Markov process; Combinatorics; Algorithm; Weak convergence; Bernoulli process; Statistics; Computer science; Random variable","score_opus":0.04184949113410392,"score_gpt":0.3050631965333336,"score_spread":0.26321370539922967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2375394096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023955987,0.00090060325,0.9957287,0.0009403219,0.00011732425,0.0017398153,0.00009893608,0.00008211781,0.00015267877],"genre_scores_gemma":[0.9041674,0.000040513485,0.09277162,0.00011425185,0.0002479468,0.0025843137,0.000014354754,0.000018349421,0.000041260253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874604,0.000030507246,0.00027825386,0.00059911923,0.00014018804,0.00020589409],"domain_scores_gemma":[0.9980059,0.00049147545,0.00032956575,0.00054492266,0.00056202494,0.00006608455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035661377,0.00024790628,0.0002916964,0.00006885659,0.00041410048,0.00009464324,0.0010149631,0.00012668748,0.000004153406],"category_scores_gemma":[0.000082168175,0.00015899734,0.000069499925,0.00033133072,0.0004946055,0.00006728534,0.00027846312,0.00021884858,0.0000011675958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007080351,0.00024173378,0.000006002809,0.0028658086,0.00018696,3.1179358e-8,0.0041723326,0.00039839488,0.00020128446,0.90158,0.00027066047,0.09000599],"study_design_scores_gemma":[0.00011498388,0.000092993134,0.00001917068,0.00011843712,0.000038809627,0.0000044443177,0.000049800736,0.12292847,0.0018649074,0.87440896,0.00017361519,0.00018543673],"about_ca_topic_score_codex":0.000017630393,"about_ca_topic_score_gemma":0.000013771687,"teacher_disagreement_score":0.9039278,"about_ca_system_score_codex":0.0000147357405,"about_ca_system_score_gemma":0.00034172,"threshold_uncertainty_score":0.64837235},"labels":[],"label_agreement":null},{"id":"W2402735257","doi":"10.2139/ssrn.2618265","title":"Multivariate Pascal Mixture Regression Models for Correlated Claim Frequencies","year":2015,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Statistics; Econometrics; Mathematics; Multivariate analysis; Regression; Bayesian multivariate linear regression; Regression analysis; Multivariate adaptive regression splines","score_opus":0.029481200521131613,"score_gpt":0.2881969412505078,"score_spread":0.2587157407293762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402735257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017787344,0.003841743,0.99007237,0.0022907169,0.0008801492,0.00024733783,0.0000028641925,0.000120586665,0.0007654752],"genre_scores_gemma":[0.48681653,0.0006629905,0.50867414,0.00040274012,0.0005130584,0.000024751758,0.000005986477,0.000044750566,0.0028550148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99630487,0.00028064795,0.00038834434,0.00042294752,0.00041016855,0.0021930255],"domain_scores_gemma":[0.9985497,0.00010835504,0.0002554316,0.00042159742,0.00036201844,0.00030288834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033937641,0.00027342534,0.00032235312,0.000143956,0.00028867915,0.00019084832,0.0010220843,0.00025684744,0.0000019010316],"category_scores_gemma":[0.00014156476,0.00019567327,0.00020498633,0.0002880242,0.000043024203,0.000934054,0.0001207745,0.0018009713,0.000008575925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007393641,0.000052479325,0.000012533856,0.000004155658,0.00007240456,0.000008013131,0.0009919861,0.00050070666,0.000730835,0.89923567,0.0012357531,0.09708153],"study_design_scores_gemma":[0.0011769397,0.0003103327,0.000006080783,0.000034143468,0.000020630952,0.0005084525,0.00011971655,0.21055822,0.00026807486,0.78591025,0.0008698215,0.00021731896],"about_ca_topic_score_codex":0.00003738375,"about_ca_topic_score_gemma":0.0000625275,"teacher_disagreement_score":0.4850378,"about_ca_system_score_codex":0.0006570662,"about_ca_system_score_gemma":0.002551776,"threshold_uncertainty_score":0.7979325},"labels":[],"label_agreement":null},{"id":"W2403069539","doi":"","title":"Learning finite Beta-Liouville mixture models via variational bayes for proportional data clustering","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Computer science; Inference; Bayesian inference; Artificial intelligence; Data point; Algorithm; Pattern recognition (psychology); Mathematics; Bayesian probability; Statistics","score_opus":0.16449539141737493,"score_gpt":0.3381483742376632,"score_spread":0.17365298282028827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403069539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000100272635,0.000019929545,0.98223567,0.010017593,0.001334659,0.00061687746,0.00006869724,0.00016846255,0.0054378533],"genre_scores_gemma":[0.47794962,0.00003418637,0.51994324,0.00065148104,0.0004151943,0.00017388207,0.0002042199,0.000021712613,0.00060645404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996754,0.00013921676,0.0008359174,0.0010594432,0.0007741168,0.00043731232],"domain_scores_gemma":[0.9972303,0.00042553415,0.0003643329,0.00076920487,0.0010350721,0.0001755645],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008707523,0.00032550437,0.0003017624,0.00027431978,0.000286276,0.0007748762,0.0021579207,0.0001597832,0.0006954233],"category_scores_gemma":[0.00033508817,0.00029981398,0.00013819637,0.00022402084,0.00009877857,0.0018108032,0.00070754386,0.00043404388,0.00027173755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022182328,0.00011126537,0.0000055145624,0.000009151901,0.000057055604,0.0000033966264,0.00027744833,0.020418456,0.001572972,0.70960426,0.0004646308,0.26745364],"study_design_scores_gemma":[0.00003651711,0.0000807416,0.000030019217,0.000038565035,0.000005747712,0.000008900915,0.000024180961,0.5929768,0.0017217826,0.404358,0.0005073812,0.00021132799],"about_ca_topic_score_codex":0.00010880064,"about_ca_topic_score_gemma":0.000034069155,"teacher_disagreement_score":0.5725584,"about_ca_system_score_codex":0.000087304354,"about_ca_system_score_gemma":0.00022459369,"threshold_uncertainty_score":0.9999454},"labels":[],"label_agreement":null},{"id":"W2403172445","doi":"10.1002/bimj.201500144","title":"Parsimonious mixtures of multivariate contaminated normal distributions","year":2016,"lang":"en","type":"preprint","venue":"Biometrical Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs","keywords":"Identifiability; Outlier; Covariance; Multivariate statistics; Cluster analysis; Expectation–maximization algorithm; Multivariate normal distribution; Mathematics; Mixture model; A priori and a posteriori; Principal component analysis; Applied mathematics; Statistics; Computer science; Maximum likelihood","score_opus":0.0271619678969238,"score_gpt":0.3071621179928542,"score_spread":0.2800001500959304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403172445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018025549,0.0017890264,0.99207664,0.0011464272,0.0021018684,0.00017278807,0.00016664376,0.00006881465,0.0006752641],"genre_scores_gemma":[0.60218805,0.00022731125,0.39698955,0.00005391647,0.00036375353,0.000007126404,0.000010299929,0.000015472737,0.00014450021],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99687177,0.0005181385,0.00087448955,0.00051007926,0.00067265076,0.00055286457],"domain_scores_gemma":[0.996905,0.00050247286,0.00084170274,0.0006992757,0.0006050998,0.0004464287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012303529,0.0003467918,0.0006833547,0.0014108913,0.00017848941,0.00027650266,0.002039425,0.00054018607,0.00002802535],"category_scores_gemma":[0.00073305,0.00023283927,0.00048190614,0.0017201278,0.00014604063,0.00021555915,0.0014616806,0.0010676065,0.0000097166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065762695,0.000698146,0.00043731413,0.00010292069,0.00053149764,0.00035295915,0.00021771192,0.000009076289,0.017789284,0.10999907,0.006479416,0.86331683],"study_design_scores_gemma":[0.0062937024,0.0012175696,0.03437175,0.0015566845,0.0004335321,0.0017494278,0.000008159681,0.021300068,0.102415785,0.80181414,0.025883967,0.0029552055],"about_ca_topic_score_codex":0.000022278877,"about_ca_topic_score_gemma":3.3585997e-7,"teacher_disagreement_score":0.86036164,"about_ca_system_score_codex":0.00017941128,"about_ca_system_score_gemma":0.00036728205,"threshold_uncertainty_score":0.94949096},"labels":[],"label_agreement":null},{"id":"W2403442979","doi":"10.1007/978-3-662-69359-9_143","title":"Cramér-Von Mises Statistics for Discrete Distributions","year":2025,"lang":"en","type":"book-chapter","venue":"International Encyclopedia of Statistical Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"von Mises distribution; Statistics; von Mises yield criterion; Mathematics; Engineering; Structural engineering","score_opus":0.015147596901596557,"score_gpt":0.3140875146387128,"score_spread":0.29893991773711626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403442979","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4493185e-7,0.000043828626,0.61687464,0.00045478952,0.0011214458,0.00022986451,0.0069222143,0.000029526038,0.37432355],"genre_scores_gemma":[0.00023455074,0.00032950478,0.85700464,0.0001134723,0.00014769302,0.000032184675,0.00024012603,0.000012417887,0.14188543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997074,0.000019266472,0.00067140977,0.0008367401,0.0010146725,0.00038389224],"domain_scores_gemma":[0.99645936,0.0014802822,0.0003273753,0.00051560544,0.0009895086,0.00022788884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058354886,0.00030658298,0.00040699355,0.00027555486,0.00019966875,0.000176496,0.0023162584,0.00014965369,0.0001637988],"category_scores_gemma":[0.0015572226,0.00027909415,0.00011382821,0.00014228796,0.0009698871,0.00035435197,0.0005600016,0.00026320614,0.000013715272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009170941,0.00002127702,0.0000027873461,0.000038096798,0.000023372493,0.000007517354,0.000022204222,0.0000026441046,0.000016439315,0.85090214,0.012049061,0.13690528],"study_design_scores_gemma":[0.00016501873,0.00007847721,0.000091293834,0.00012143451,0.000037121885,0.0000046215782,9.1959174e-7,0.01380906,0.0000479765,0.77342653,0.21195659,0.00026095056],"about_ca_topic_score_codex":0.000023064782,"about_ca_topic_score_gemma":0.000010388945,"teacher_disagreement_score":0.24012999,"about_ca_system_score_codex":0.00018529223,"about_ca_system_score_gemma":0.00095493835,"threshold_uncertainty_score":0.99996614},"labels":[],"label_agreement":null},{"id":"W2404343021","doi":"","title":"Visual scenes clustering using variational incremental learning of infinite generalized Dirichlet mixture models","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Generalization; Dirichlet process; Dirichlet distribution; Artificial intelligence; Computer science; Inference; Hierarchical Dirichlet process; Mixture model; Bayesian inference; Algorithm; Mathematics; Machine learning; Bayesian probability; Pattern recognition (psychology); Applied mathematics; Latent Dirichlet allocation; Topic model","score_opus":0.0321123560664235,"score_gpt":0.2891757801535304,"score_spread":0.2570634240871069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404343021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060162205,0.00006981362,0.93743837,0.00012678523,0.00015418675,0.00016539887,8.8768326e-7,0.00008460844,0.0017977237],"genre_scores_gemma":[0.3909125,0.000005913098,0.60863096,0.00022205256,0.000059348502,0.0000062993745,0.000002907674,0.000008766977,0.00015122115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851197,0.00021540522,0.00035581153,0.00032217836,0.0003232176,0.000271421],"domain_scores_gemma":[0.99930495,0.000071083145,0.0001598142,0.00021427026,0.0001573293,0.00009252491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004050983,0.00017101763,0.00024240199,0.00014554155,0.00013355234,0.00015092488,0.00038310772,0.00009518759,0.0001184899],"category_scores_gemma":[0.000023085333,0.00014660005,0.000083176354,0.0002917489,0.00002982023,0.001035967,0.00039734849,0.00015471783,0.000006843376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021415652,0.00018080123,0.0014687715,0.00008356962,0.00013978897,0.0000055469004,0.0020979173,0.13562651,0.27251118,0.52753484,0.00029584387,0.060033828],"study_design_scores_gemma":[0.0003475622,0.000035565976,0.0003075724,0.000021011687,0.000007483082,0.000011730939,0.000011498509,0.9751495,0.0037623714,0.020129977,0.000036935893,0.0001787853],"about_ca_topic_score_codex":0.0004134115,"about_ca_topic_score_gemma":0.0000043100545,"teacher_disagreement_score":0.839523,"about_ca_system_score_codex":0.00003366478,"about_ca_system_score_gemma":0.00006272045,"threshold_uncertainty_score":0.59781766},"labels":[],"label_agreement":null},{"id":"W2404383345","doi":"","title":"Random mappings with Ewens cycle structure","year":2013,"lang":"en","type":"article","venue":"Ars Combinatoria","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Combinatorics; Random permutation; Poisson distribution; Permutation (music); Order (exchange); Vertex (graph theory); Distribution (mathematics); Mathematical sciences; Dirichlet distribution; Discrete mathematics; Statistics; Symmetric group; Mathematical analysis","score_opus":0.005309925755462508,"score_gpt":0.20880699473674294,"score_spread":0.20349706898128042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404383345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23205796,0.00010472445,0.7593327,0.0013618481,0.0010843223,0.00038262503,0.0000013550539,0.00021797087,0.005456484],"genre_scores_gemma":[0.76222986,0.0000037754985,0.2369485,0.0004709226,0.000010938565,0.000020027039,0.0000011840973,0.000013204243,0.00030161612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875784,0.000097373035,0.00016421416,0.00038725254,0.00024932486,0.00034399558],"domain_scores_gemma":[0.99889517,0.00008029915,0.000082081504,0.00066231104,0.00012574172,0.00015442567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016013093,0.00018349537,0.0002355602,0.00006239919,0.00012624876,0.00023060855,0.00071749056,0.00008970822,0.00007031911],"category_scores_gemma":[0.000021089481,0.00013360432,0.0000509578,0.00032211817,0.000049887465,0.0005652004,0.00014705425,0.00020179049,0.0000679886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007362535,0.00002992857,0.00026241218,0.000009684143,0.000025444097,0.000010697505,0.0005004369,0.000007222561,0.0013282007,0.9720837,0.003690221,0.022044707],"study_design_scores_gemma":[0.0017579015,0.00008559195,0.0017104378,0.000019302352,0.0000071523173,0.000028218115,0.0000075755065,0.0058704875,0.0019985295,0.98685217,0.0014195438,0.00024310466],"about_ca_topic_score_codex":0.00006491943,"about_ca_topic_score_gemma":0.0000026276673,"teacher_disagreement_score":0.5301719,"about_ca_system_score_codex":0.000024106268,"about_ca_system_score_gemma":0.000047313602,"threshold_uncertainty_score":0.5448226},"labels":[],"label_agreement":null},{"id":"W2408131130","doi":"10.1609/aaai.v26i1.8397","title":"A Search Algorithm for Latent Variable Models with Unbounded Domains","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Latent variable; A priori and a posteriori; Latent variable model; Prior probability; Algorithm; Computer science; Probabilistic logic; Probabilistic latent semantic analysis; Domain (mathematical analysis); Variable (mathematics); Latent Dirichlet allocation; Dirichlet distribution; Mathematics; Machine learning; Artificial intelligence; Topic model; Bayesian probability","score_opus":0.09569180326638813,"score_gpt":0.30836496863901175,"score_spread":0.21267316537262362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408131130","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018935987,0.000030403264,0.9877954,0.002177425,0.00020622792,0.00047655407,0.000011631411,0.0000629869,0.0073457346],"genre_scores_gemma":[0.24658589,0.00002846286,0.752303,0.00028794832,0.000056106946,0.000059182254,8.094061e-7,0.000016093069,0.00066252373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99790835,0.000032371245,0.00040529526,0.0006630753,0.00051753625,0.0004733561],"domain_scores_gemma":[0.99759734,0.00013246413,0.00018537094,0.00041157776,0.0015486174,0.00012462375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078341394,0.00023332612,0.00032348392,0.00008323884,0.00026687127,0.00040454252,0.0014534367,0.00010563558,0.000022412458],"category_scores_gemma":[0.00009345582,0.0001609183,0.000119602824,0.00083408057,0.00018758865,0.00047459398,0.00035956234,0.00027667815,0.000007640793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003011606,0.000121605684,0.000003864721,0.000031108295,0.000024439476,0.0000010425867,0.0005977337,0.00015409318,0.010817959,0.830079,0.000044366607,0.15809466],"study_design_scores_gemma":[0.000034610184,0.000112673544,0.0000020240614,0.00009167406,0.000009928841,0.000009374044,0.00006753757,0.34503907,0.23211795,0.42235896,0.000041783125,0.00011440802],"about_ca_topic_score_codex":0.000028539374,"about_ca_topic_score_gemma":0.0000055566484,"teacher_disagreement_score":0.40772003,"about_ca_system_score_codex":0.000051500636,"about_ca_system_score_gemma":0.00041689043,"threshold_uncertainty_score":0.6562058},"labels":[],"label_agreement":null},{"id":"W241360418","doi":"10.1016/j.mcm.2005.12.006","title":"Exact sampling with highly uniform point sets","year":2006,"lang":"en","type":"article","venue":"Mathematical and Computer Modelling","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Pacific Railway (Canada); University of Calgary","funders":"","keywords":"Sampling (signal processing); Markov chain Monte Carlo; Markov chain; Coupling (piping); Mathematics; Gibbs sampling; Slice sampling; Importance sampling; Statistics; Computer science; Algorithm; Monte Carlo method; Bayesian probability; Applied mathematics; Engineering","score_opus":0.025239290214477073,"score_gpt":0.240086629953237,"score_spread":0.21484733973875994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W241360418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010975166,0.00008463804,0.9858562,0.00038956577,0.000050474322,0.00013541905,8.192146e-7,0.00018655164,0.0023211688],"genre_scores_gemma":[0.15808919,0.0000055118894,0.8415194,0.00018415516,0.00009833004,0.000006620821,0.0000013578307,0.000013666251,0.00008178445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986454,0.000038156813,0.00029576253,0.0004338438,0.00023648233,0.00035034446],"domain_scores_gemma":[0.99923503,0.00015112731,0.0000668602,0.00037630374,0.000050294402,0.00012035583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003274886,0.00022061019,0.000294811,0.00007123781,0.00014907256,0.00029942987,0.00032467133,0.00006884805,0.0000042850907],"category_scores_gemma":[0.0000011610019,0.00015140061,0.000055432247,0.000155207,0.000046190587,0.00032310525,0.00018319298,0.00015922879,0.000011849483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042314336,0.00006673702,0.0000055112114,0.000064406915,0.000010796846,0.000015565478,0.00024482017,0.014816035,0.000017097445,0.95760864,0.000038003473,0.027108157],"study_design_scores_gemma":[0.00013739114,0.000042928397,0.0000067180763,0.00006461329,0.0000060673647,0.00006482804,0.0000014161989,0.5792524,0.00008663222,0.4200904,0.00010506167,0.00014148524],"about_ca_topic_score_codex":0.0000143134075,"about_ca_topic_score_gemma":8.604146e-7,"teacher_disagreement_score":0.5644364,"about_ca_system_score_codex":0.00001533068,"about_ca_system_score_gemma":0.000019163443,"threshold_uncertainty_score":0.61739373},"labels":[],"label_agreement":null},{"id":"W2419445839","doi":"10.5539/ijsp.v5n4p9","title":"Gradient and Likelihood Ratio Tests in Cure Rate Models","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Likelihood-ratio test; Weibull distribution; Mathematics; Statistics; Statistic; Population; Sample size determination; Applied mathematics; Statistical hypothesis testing; Likelihood function; Score test; Sample (material); Maximum likelihood","score_opus":0.019637975377272573,"score_gpt":0.2815171617360204,"score_spread":0.26187918635874785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2419445839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022174237,0.00017959019,0.97403777,0.0030802616,0.00027684026,0.00006577421,0.00004220749,0.0000037843745,0.0001395343],"genre_scores_gemma":[0.5150366,0.00035655673,0.48443806,0.00010365592,0.00004182822,0.0000014880158,3.2322728e-7,0.0000024970225,0.000019006466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904776,0.000120829434,0.00035689436,0.00016295955,0.00020333233,0.00010822798],"domain_scores_gemma":[0.99893564,0.00032195388,0.00017656348,0.00009917581,0.0003718082,0.00009486804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010666238,0.00008096757,0.00014158494,0.0000835497,0.000021496806,0.00009153143,0.0002633251,0.00003213872,0.0000040671175],"category_scores_gemma":[0.00018489249,0.000051172545,0.00002031316,0.000047151025,0.00006167442,0.00042201357,0.00009826426,0.00009602086,3.212011e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002923082,0.00006182517,0.0026346543,0.000009452948,0.000018749457,0.000037421236,0.00028975387,0.00001670788,0.0004370119,0.565832,0.00016389204,0.43046927],"study_design_scores_gemma":[0.0005588465,0.000096544216,0.016136078,0.00006413976,0.0000036402412,0.00007588371,0.0000020934679,0.0161675,0.00011882868,0.9664749,0.00023040228,0.00007115151],"about_ca_topic_score_codex":0.000008649099,"about_ca_topic_score_gemma":0.00003000693,"teacher_disagreement_score":0.49286234,"about_ca_system_score_codex":0.000045735807,"about_ca_system_score_gemma":0.00008165792,"threshold_uncertainty_score":0.20867558},"labels":[],"label_agreement":null},{"id":"W24292542","doi":"10.1007/b101765_15","title":"Simulation of Bivariate Observations","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bivariate analysis; Computer science; Estimator; Monte Carlo method; Parametric statistics; Random variate; Statistics; Econometrics; Random variable; Mathematics; Machine learning","score_opus":0.06944740738588165,"score_gpt":0.2896931743211188,"score_spread":0.22024576693523715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W24292542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4913473e-7,0.00004741005,0.58033854,0.00018670838,0.000076585035,0.00007093456,0.0000018775839,0.000048798745,0.41922897],"genre_scores_gemma":[0.00051214243,0.000013851921,0.6133135,0.00028057577,0.000045315443,5.5516745e-7,0.000004340764,0.000007455513,0.38582224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999159,0.000014885399,0.00028677096,0.00026070292,0.00018385044,0.0000948004],"domain_scores_gemma":[0.9989148,0.00013711817,0.0001869431,0.000571479,0.00014730079,0.000042409138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017281306,0.00014919306,0.00023360831,0.000114272094,0.000031039257,0.000029897186,0.00042562807,0.00019267738,0.000060372204],"category_scores_gemma":[0.000018240888,0.00013052618,0.000109776156,0.00004467356,0.000015804759,0.00017317216,0.0000749714,0.000120476485,0.000016123788],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.9231846e-7,0.0000043597934,1.7982704e-7,0.000005017573,0.000008466594,9.216923e-7,0.000027187858,0.001318195,0.000020051984,0.8540179,0.0001485869,0.14444862],"study_design_scores_gemma":[0.00005496794,0.000028884842,0.000032964643,0.00003318235,0.000010998638,4.754941e-7,5.1322694e-8,0.18865357,0.00002955127,0.7756825,0.035343695,0.00012915864],"about_ca_topic_score_codex":0.000004544856,"about_ca_topic_score_gemma":0.000001843137,"teacher_disagreement_score":0.18733537,"about_ca_system_score_codex":0.000014765911,"about_ca_system_score_gemma":0.00005813345,"threshold_uncertainty_score":0.5322703},"labels":[],"label_agreement":null},{"id":"W245872649","doi":"10.22237/jmasm/1067646000","title":"A Note On MLEs For Normal Distribution Parameters Based On Disjoint Partial Sums Of A Random Sample","year":2003,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Mathematics; Statistics; Disjoint sets; Sample (material); Normal distribution; Sample mean and sample covariance; Distribution (mathematics); Combinatorics; Mathematical analysis","score_opus":0.03645416640176971,"score_gpt":0.35444432926145847,"score_spread":0.31799016285968873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W245872649","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014901535,0.000022727023,0.99842095,0.00021274817,0.0003198527,0.00036293673,0.00021912626,0.0000151101885,0.0002775503],"genre_scores_gemma":[0.20599948,0.000003531984,0.79367626,0.00022702126,0.000043205047,0.000026095224,0.000007861266,0.000014234495,0.000002296314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682194,0.0010338911,0.00088524615,0.0003424524,0.0005209887,0.00039545758],"domain_scores_gemma":[0.9889605,0.0096900705,0.000543813,0.00037635,0.00016247173,0.0002667962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004699042,0.000246459,0.00073233695,0.00011644286,0.00010009483,0.00007054526,0.00038100517,0.00012751886,0.000010792694],"category_scores_gemma":[0.002993592,0.00018573465,0.00025396698,0.00017288706,0.00010995127,0.00008808141,0.000029471974,0.00036006782,7.38801e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014756445,0.00020581516,0.0000031053326,0.000036823094,0.00003185962,0.0000052380506,0.00009619866,0.004125279,0.0033210372,0.54978645,0.00011212976,0.44080046],"study_design_scores_gemma":[0.002844099,0.00072835817,0.000057413137,0.000037402675,0.0000613885,0.000007912225,0.0000032154555,0.4981329,0.034091193,0.4632995,0.0005699207,0.00016667711],"about_ca_topic_score_codex":0.0000030202573,"about_ca_topic_score_gemma":4.6664465e-7,"teacher_disagreement_score":0.49400762,"about_ca_system_score_codex":0.000084603154,"about_ca_system_score_gemma":0.00018575184,"threshold_uncertainty_score":0.75740397},"labels":[],"label_agreement":null},{"id":"W2460913564","doi":"10.1037/met0000055","title":"A correction factor for the impact of cluster randomized sampling and its applications.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; University of Ottawa","funders":"","keywords":"Statistics; Spurious relationship; Cluster sampling; Sample size determination; Statistical power; Sampling (signal processing); Covariate; Cluster analysis; Variance (accounting); Population; Cluster (spacecraft); Mathematics; Standard error; Confidence interval; Sample (material); Population variance; Statistical hypothesis testing; Type I and type II errors; Econometrics; Computer science; Demography; Filter (signal processing)","score_opus":0.19036396902259523,"score_gpt":0.5067937905813413,"score_spread":0.3164298215587461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460913564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089048344,0.0010913257,0.99534863,0.000375958,0.0004883778,0.0011679194,0.0000035108671,0.000047577658,0.00058622437],"genre_scores_gemma":[0.067677,0.0000534992,0.93160814,0.00017226765,0.000081081635,0.00033477115,3.5870178e-7,0.000005202047,0.00006767327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810743,0.0010675957,0.000268586,0.00030900168,0.00008761894,0.00015974701],"domain_scores_gemma":[0.9926527,0.006627457,0.00014771741,0.00032341608,0.00014383758,0.00010488671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046554334,0.00011731175,0.00036375748,0.00004352433,0.00007413225,0.00005025749,0.00036399328,0.00010119265,0.0000058162864],"category_scores_gemma":[0.0019554158,0.00005651916,0.00019704206,0.00020932834,0.00007247985,0.00009692477,0.00008122711,0.00012997437,0.0000010290523],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001823138,0.00005381997,0.000008520891,0.0000047742997,0.00003701561,5.6186128e-8,0.00030396596,0.000045143974,0.0011448583,0.016008412,0.00021112098,0.9803592],"study_design_scores_gemma":[0.028932754,0.00041456756,0.0015875627,0.000013197124,0.000045873076,0.00004358957,0.000015942705,0.5523791,0.0011845538,0.41362995,0.0015175464,0.00023535428],"about_ca_topic_score_codex":0.0000062107733,"about_ca_topic_score_gemma":1.1558927e-7,"teacher_disagreement_score":0.9801238,"about_ca_system_score_codex":0.000015754486,"about_ca_system_score_gemma":0.000014988579,"threshold_uncertainty_score":0.23409566},"labels":[],"label_agreement":null},{"id":"W2470346259","doi":"10.1007/978-3-319-25388-6_1","title":"Order statistics and nearest neighbors","year":2015,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Order statistic; Statistics; Probability and statistics; Order (exchange); Mathematics; Statistical physics; Physics; Economics","score_opus":0.10905930463665656,"score_gpt":0.326035775456214,"score_spread":0.21697647081955743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470346259","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004214041,0.002427039,0.7990783,0.0015771287,0.0007157051,0.00020688937,0.0004007839,0.000040787345,0.19554919],"genre_scores_gemma":[0.0001435342,0.00089016126,0.973368,0.00054108835,0.00016686314,0.0000050734216,0.000051258685,0.000016946726,0.024817077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979028,0.00008593533,0.00026796607,0.0008204888,0.00061797915,0.00030481632],"domain_scores_gemma":[0.997674,0.00021019514,0.0001503821,0.0018041478,0.00008077018,0.00008053199],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0028190466,0.00025576103,0.00026825813,0.00012819789,0.00022882751,0.0006959179,0.005554659,0.00011783397,0.000025673271],"category_scores_gemma":[0.00018752324,0.00016579333,0.000013864813,0.00019154507,0.001030997,0.0011685957,0.0025885715,0.00034546523,0.000016690241],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018586628,0.0000038948538,0.000011919015,0.000012750168,0.0000045477555,0.00002704095,0.00041997136,0.000002383596,7.1093194e-7,0.94759184,0.0074623264,0.04446078],"study_design_scores_gemma":[0.00006337017,0.00008046217,0.00006173795,0.00005385424,0.000010757705,0.000050477905,0.000031332915,0.003364042,0.0000014496421,0.6048405,0.391164,0.00027799094],"about_ca_topic_score_codex":0.00006291814,"about_ca_topic_score_gemma":0.00026508974,"teacher_disagreement_score":0.38370168,"about_ca_system_score_codex":0.000016621963,"about_ca_system_score_gemma":0.00031514472,"threshold_uncertainty_score":0.9998258},"labels":[],"label_agreement":null},{"id":"W2471383395","doi":"10.37236/6225","title":"Large Deviations for Permutations Avoiding Monotone Patterns","year":2016,"lang":"en","type":"preprint","venue":"The Electronic Journal of Combinatorics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University; York University","funders":"","keywords":"Combinatorics; Physics; Permutation (music); Lambda; Sigma; Limiting; Monotone polygon; Limit (mathematics); Mathematics; Mathematical analysis; Quantum mechanics; Geometry","score_opus":0.016772908903515654,"score_gpt":0.2932536271257783,"score_spread":0.2764807182222626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471383395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029357423,0.0037122464,0.98654574,0.0046338546,0.001539378,0.0003923584,0.000021009813,0.0000327791,0.00018691472],"genre_scores_gemma":[0.99645317,0.0017128641,0.0009947435,0.00015840626,0.0003146039,0.00004036438,0.0000027962374,0.000028405966,0.00029466453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761295,0.0004213105,0.00062601356,0.00025332204,0.0003922555,0.00069411885],"domain_scores_gemma":[0.99689275,0.00073902775,0.00096091453,0.0006721909,0.0006344051,0.00010069044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003288037,0.0002497591,0.00043073762,0.00019566716,0.00041268373,0.00018163658,0.0020034336,0.00018167443,0.000003294334],"category_scores_gemma":[0.00025747778,0.00015892224,0.00039517207,0.00020433805,0.000021719496,0.00025340045,0.00044533916,0.0014617805,0.0000022257527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063188445,0.000074665906,0.000025526835,0.000028229957,0.00012911603,0.0000019374927,0.00079588644,0.00002273348,0.000068175745,0.9978518,0.00045542928,0.0005402029],"study_design_scores_gemma":[0.0006353561,0.00016634313,0.000058751008,0.000117746975,0.000099872595,0.00006211939,0.000027978194,0.003741049,0.00056013523,0.99135816,0.002976503,0.00019597399],"about_ca_topic_score_codex":0.0000015980637,"about_ca_topic_score_gemma":0.000003846252,"teacher_disagreement_score":0.9935174,"about_ca_system_score_codex":0.0004747376,"about_ca_system_score_gemma":0.0012264714,"threshold_uncertainty_score":0.6480661},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2479081199","doi":"10.1007/978-3-319-39378-0_54","title":"A Hidden Markov Model with Controlled Non-parametric Emissions","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Qualcomm (Canada)","funders":"","keywords":"Hidden Markov model; Computer science; Markov model; Set (abstract data type); Ergodic theory; Class (philosophy); Maximum-entropy Markov model; Nonparametric statistics; Markov chain; Algorithm; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Parametric model; Parametric statistics; Machine learning; Variable-order Markov model; Mathematics; Statistics; Programming language","score_opus":0.014409229795275398,"score_gpt":0.25529382841962767,"score_spread":0.24088459862435227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479081199","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014818983,0.0003620776,0.9723931,0.0015875011,0.00070087326,0.0009223467,0.000008165032,0.00017494126,0.023836195],"genre_scores_gemma":[0.023127966,0.00005813799,0.9697718,0.0014750176,0.0003137529,0.000038764334,0.0000011953936,0.000057059875,0.005156279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946499,0.000072968665,0.0006892984,0.0022073518,0.0013497464,0.0010307714],"domain_scores_gemma":[0.9953535,0.001060433,0.00046301095,0.0022771677,0.00038953632,0.0004563237],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014865563,0.00085065275,0.001268741,0.0015682827,0.00033603737,0.00056684326,0.0043153926,0.0005048333,0.000024597968],"category_scores_gemma":[0.00016074025,0.00052708306,0.00026659816,0.0010553865,0.0006706745,0.00066672056,0.0012751679,0.00095858827,0.000033657736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006162742,0.00003451787,0.0000063459147,0.000023193457,0.00003050283,0.00010826498,0.0002381762,0.0026492875,0.00015476542,0.03978435,0.00006546257,0.9568435],"study_design_scores_gemma":[0.001587091,0.0001742107,0.000007876459,0.0004811759,0.000020276342,0.00007896751,2.3880705e-8,0.69385326,0.00025180719,0.3027496,0.00012177545,0.00067394617],"about_ca_topic_score_codex":0.000005747289,"about_ca_topic_score_gemma":0.000012605365,"teacher_disagreement_score":0.95616955,"about_ca_system_score_codex":0.0002996399,"about_ca_system_score_gemma":0.0014792624,"threshold_uncertainty_score":0.99971807},"labels":[],"label_agreement":null},{"id":"W2486150254","doi":"10.4018/978-1-61692-811-7.ch001","title":"Stochastic Learning-based Weak Estimation and Its Applications","year":2010,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor; Carleton University","funders":"","keywords":"Computer science; Artificial intelligence; sort; Estimator; Field (mathematics); Cybernetics; Scheme (mathematics); Machine learning; Mathematics","score_opus":0.014287300412682185,"score_gpt":0.2612884256578926,"score_spread":0.24700112524521042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2486150254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011923338,0.00019586655,0.63893753,0.00008941459,0.00011276364,0.00033464457,0.000012317703,0.00015725712,0.360159],"genre_scores_gemma":[0.07711271,0.0000033514523,0.85515845,0.0006255202,0.00034269635,0.00018387471,0.000011842277,0.00006850416,0.066493034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986444,0.00002737317,0.00024912835,0.0005879603,0.0002614991,0.00022963677],"domain_scores_gemma":[0.99888295,0.000091336,0.00021142182,0.0005079063,0.000121627054,0.00018476981],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018934005,0.00031524154,0.00029186578,0.00007280778,0.00019598684,0.0001680613,0.00049549795,0.00042646183,0.000007238313],"category_scores_gemma":[0.00003096422,0.0003135855,0.00009057279,0.000023730066,0.00006757712,0.0000696913,0.00016260149,0.00054701365,0.00008137471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022738577,0.000003719349,9.1559585e-8,0.000021103006,0.000009985799,0.0000021772846,0.000014105867,0.0001390169,0.00004024967,0.8946698,0.000030696145,0.10506683],"study_design_scores_gemma":[0.00019260259,0.000055120472,0.0000027092728,0.00007464191,0.000040367235,0.000032153584,2.5309762e-7,0.12788111,0.000056977366,0.8583637,0.012950562,0.00034980167],"about_ca_topic_score_codex":0.000004970458,"about_ca_topic_score_gemma":0.0000103822595,"teacher_disagreement_score":0.29366598,"about_ca_system_score_codex":0.000053778185,"about_ca_system_score_gemma":0.00019629183,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"W2486583868","doi":"10.1142/9789812796707_0009","title":"EMPIRICAL LIKELIHOOD CONFIDENCE INTERVALS FOR THE DIFFERENCE OF TWO QUANTILES OF A POPULATION","year":2003,"lang":"en","type":"book-chapter","venue":"WORLD SCIENTIFIC eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Quantile; Statistics; Confidence interval; Empirical likelihood; Econometrics; Mathematics; Population; Demography; Sociology","score_opus":0.07338077653162715,"score_gpt":0.33464578563299374,"score_spread":0.2612650091013666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2486583868","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000077301884,0.0004483947,0.9093095,0.00018906413,0.0015106995,0.00069441803,0.00004001958,0.00003371444,0.087696895],"genre_scores_gemma":[0.076635286,0.0000036905058,0.18328167,0.000288852,0.00008313117,0.000046469213,0.000011699229,0.000039637,0.73960954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973517,0.00011311177,0.0008211026,0.00078632205,0.00060998753,0.00031778842],"domain_scores_gemma":[0.99651617,0.000776854,0.0007687594,0.0014562054,0.0003868222,0.00009516299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018999814,0.00031528788,0.0006295172,0.00038279608,0.00021496826,0.00019035251,0.0015546576,0.00012458178,0.000022601096],"category_scores_gemma":[0.000054481316,0.00022127737,0.00039489786,0.00011257993,0.0005268956,0.000073572126,0.00026120257,0.000268008,0.000003364273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008864594,0.000016722835,0.00002561659,0.00009291794,0.000038083075,9.924299e-7,0.0005100051,0.0000022075326,0.0011105677,0.9446469,0.002141143,0.051405996],"study_design_scores_gemma":[0.00030093046,0.000080310005,0.00011778082,0.0006731264,0.00009670229,0.000006320989,0.000003354766,0.0056333416,0.005445265,0.9605638,0.026724247,0.00035483015],"about_ca_topic_score_codex":0.000023080942,"about_ca_topic_score_gemma":0.0007573648,"teacher_disagreement_score":0.7260278,"about_ca_system_score_codex":0.000030725656,"about_ca_system_score_gemma":0.00013893614,"threshold_uncertainty_score":0.902343},"labels":[],"label_agreement":null},{"id":"W2503582921","doi":"10.1017/cbo9780511791260.014","title":"Dirichlet's Unit Theorem","year":2003,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Unit (ring theory); Mathematics; Dirichlet distribution; Mathematical analysis; Mathematics education","score_opus":0.02725816200755349,"score_gpt":0.2146235735349631,"score_spread":0.18736541152740963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2503582921","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.6113656e-7,0.00013623748,0.4701362,0.000033315508,0.00024027521,0.00016619849,0.000032598517,0.00014132133,0.5291131],"genre_scores_gemma":[0.000045600715,0.00010807107,0.04610204,0.00048703144,0.000085706946,5.038338e-7,0.0000105662875,0.00004375795,0.9531167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980841,0.00014722435,0.00020113742,0.00082782534,0.00033262622,0.00040706823],"domain_scores_gemma":[0.99779344,0.00010592795,0.00022997343,0.0014148785,0.00018231981,0.00027345194],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002724111,0.00048713648,0.00048478,0.00022918664,0.00023080123,0.00012749765,0.0017898884,0.00047859226,0.000006533179],"category_scores_gemma":[0.0000094191755,0.0005271548,0.00029492995,0.00002047887,0.00020829821,0.0001931025,0.00070098834,0.00063738506,0.000022921222],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009344511,0.0000065070367,1.7657244e-7,0.000026346883,0.0000718529,0.0003242292,0.000035760662,4.5368236e-7,0.0000108278155,0.9503757,0.035112936,0.014025914],"study_design_scores_gemma":[0.00033639342,0.000040055897,0.0000014568803,0.000081165104,0.000088525565,0.000042119133,0.0000023621517,0.0002563449,0.0002688411,0.003751671,0.9945314,0.0005996595],"about_ca_topic_score_codex":0.000025617246,"about_ca_topic_score_gemma":5.9912946e-7,"teacher_disagreement_score":0.9594185,"about_ca_system_score_codex":0.0001080918,"about_ca_system_score_gemma":0.00013001585,"threshold_uncertainty_score":0.999718},"labels":[],"label_agreement":null},{"id":"W2507984430","doi":"10.1109/ssp.2016.7551777","title":"Estimation of time-varying mixture models: An application to traffic estimation","year":2016,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Inference; Mixture model; Estimation; Data modeling; Data mining; Estimation theory; Algorithm; Artificial intelligence; Engineering","score_opus":0.0168446513445688,"score_gpt":0.27731396591374924,"score_spread":0.26046931456918043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507984430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053968546,0.000012967887,0.99122566,0.0011649524,0.000043217613,0.00029184448,0.0000020048772,0.00018917146,0.0016733403],"genre_scores_gemma":[0.4078906,0.000001398588,0.5917773,0.00011143394,0.000013954393,0.000011924772,0.0000025163627,0.000005822122,0.00018504681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989511,0.00007683376,0.00024886313,0.00035733008,0.00020776429,0.00015813914],"domain_scores_gemma":[0.99906766,0.00007276701,0.000093386974,0.0005703433,0.00008419164,0.00011163356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041439862,0.0001151314,0.00014740007,0.00012277614,0.000043014643,0.000041576986,0.0004377381,0.00007796853,0.000011940295],"category_scores_gemma":[0.000029506227,0.000078504156,0.000037617003,0.00029199358,0.000015550653,0.00115806,0.00005791445,0.000036667097,0.00007156831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040552472,0.000029387105,3.2646452e-7,0.000006582693,0.000002516266,1.2999008e-7,0.00027998802,0.09332292,0.014630297,0.077328846,0.00010695927,0.814288],"study_design_scores_gemma":[0.00013598481,0.00006023674,0.000012047503,0.000025493588,0.0000044231965,0.0000034340303,8.737801e-7,0.9090557,0.013525448,0.077037506,0.000026153324,0.000112700654],"about_ca_topic_score_codex":0.000008002458,"about_ca_topic_score_gemma":0.000001863862,"teacher_disagreement_score":0.8157328,"about_ca_system_score_codex":0.000032193817,"about_ca_system_score_gemma":0.000036045778,"threshold_uncertainty_score":0.32013065},"labels":[],"label_agreement":null},{"id":"W2511105687","doi":"10.1016/j.jspi.2016.08.002","title":"A central limit theorem for bootstrap sample sums from non-i.i.d. models","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Independent and identically distributed random variables; Central limit theorem; Random variable; Sequence (biology); Limit (mathematics); Combinatorics; Moment (physics); Sample (material); Class (philosophy); Statistics; Discrete mathematics; Mathematical analysis","score_opus":0.062310965185857395,"score_gpt":0.3307695592137837,"score_spread":0.2684585940279263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511105687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037593676,0.00016036953,0.9949469,0.0005007942,0.00020810303,0.00006119139,0.00016427564,0.000012028363,0.00018695263],"genre_scores_gemma":[0.48935515,0.000033996846,0.5104024,0.00010260707,0.00008996159,0.0000012010298,0.0000010170135,0.000003779596,0.0000099259005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998883,0.000059986607,0.0003650216,0.00019941009,0.0001939962,0.00029858146],"domain_scores_gemma":[0.9960421,0.0032431213,0.00018599232,0.00014375786,0.00013293899,0.00025210067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039559652,0.0001277575,0.00028216196,0.000056595953,0.00007593458,0.00012827534,0.00033449318,0.00006769282,0.000011429461],"category_scores_gemma":[0.000530824,0.00007501891,0.000052333915,0.000048373426,0.00008393329,0.0005011191,0.000057420573,0.00014631553,5.972219e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010088112,0.000038383627,0.00081700494,0.000013812966,0.000038323356,0.00003142134,0.00080372056,0.00009394625,0.000883483,0.6981294,0.0014318223,0.29761782],"study_design_scores_gemma":[0.00063044124,0.00033262587,0.0031994826,0.00021526414,0.000018941093,0.000021342019,0.00001225911,0.096613236,0.00030002455,0.8981611,0.00035867144,0.00013661149],"about_ca_topic_score_codex":0.000019360645,"about_ca_topic_score_gemma":9.3475325e-7,"teacher_disagreement_score":0.4855958,"about_ca_system_score_codex":0.000018304701,"about_ca_system_score_gemma":0.00010533097,"threshold_uncertainty_score":0.30591822},"labels":[],"label_agreement":null},{"id":"W2512718628","doi":"","title":"Hidden Markov models with discrete infinite logistic normal distribution priors","year":2016,"lang":"en","type":"article","venue":"International Conference on Information Fusion","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hidden Markov model; Prior probability; Pattern recognition (psychology); Bayesian probability; Computer science; Posterior probability; Artificial intelligence; Algorithm; Markov model; Mathematics; Stochastic matrix; Markov chain; Applied mathematics; Machine learning","score_opus":0.03193451441721599,"score_gpt":0.2764315793795729,"score_spread":0.24449706496235693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512718628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002086262,0.0000023224889,0.94554204,0.004239979,0.00039503563,0.00017262719,0.00009460325,0.00012661445,0.04734051],"genre_scores_gemma":[0.9138446,0.00005689289,0.084918216,0.0004840693,0.000055820434,0.00003218198,0.00013278291,0.000005214264,0.00047021476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984625,0.000063143445,0.0003882624,0.00022286901,0.00063630356,0.00022691344],"domain_scores_gemma":[0.9987151,0.000084048435,0.00026777305,0.00034930548,0.00047395044,0.00010982029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000313911,0.00018684707,0.00013374617,0.00016991846,0.00012066957,0.0003025797,0.0007388942,0.00009079025,0.00015629394],"category_scores_gemma":[0.00007434688,0.00011361795,0.00005053342,0.00016274604,0.00006627389,0.0039055499,0.00020550769,0.00013035556,0.00016664443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008051084,0.000012735515,0.00006119276,0.000004307842,0.000009458718,0.0000018564524,0.00019350267,0.00003853969,0.00012889472,0.7360094,0.00028474352,0.26317483],"study_design_scores_gemma":[0.003456549,0.00069768383,0.007391743,0.0007969032,0.000020703297,0.00008512625,0.00009729007,0.7327298,0.0024772934,0.23705955,0.014092134,0.0010952455],"about_ca_topic_score_codex":0.000021613048,"about_ca_topic_score_gemma":0.0000047520216,"teacher_disagreement_score":0.91175836,"about_ca_system_score_codex":0.00012265227,"about_ca_system_score_gemma":0.00013140045,"threshold_uncertainty_score":0.46332055},"labels":[],"label_agreement":null},{"id":"W2514369511","doi":"10.20982/tqmp.08.3.p127","title":"Le nombre de permutations dans les tests permutationnels; The number of permutations in permutation tests","year":2012,"lang":"fr","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Combinatorics; Permutation (music); Mathematics; Philosophy","score_opus":0.16558520353988432,"score_gpt":0.5306528493453669,"score_spread":0.3650676458054826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514369511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052805547,0.003982272,0.9251303,0.005990597,0.006218758,0.0014147717,0.00012194201,0.000043878386,0.004291936],"genre_scores_gemma":[0.32270384,0.000116424206,0.6754664,0.00026463656,0.0004172443,0.00053208857,0.000026177688,0.00005276991,0.00042043036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98610187,0.0099359285,0.0016585743,0.0008520488,0.00028280859,0.0011687673],"domain_scores_gemma":[0.9835008,0.014047645,0.00080797344,0.0007558943,0.00069559674,0.00019208956],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012862524,0.00050424115,0.00095258275,0.0004901838,0.00041909158,0.000103650964,0.0009307182,0.0005584977,0.000063265274],"category_scores_gemma":[0.0077060633,0.00047803044,0.0003248111,0.0018436426,0.0010329298,0.0011768143,0.0001238498,0.0006787059,0.000022911805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007999247,0.00082002266,0.012457021,0.00013033597,0.00006775303,0.0000047217354,0.09965342,0.00065948965,0.019387355,0.8223266,0.00015513449,0.04425816],"study_design_scores_gemma":[0.0027242883,0.00035562628,0.25293818,0.00023555633,0.00016232271,0.0002403008,0.0057252953,0.026022937,0.0016986713,0.7041847,0.00500643,0.00070566125],"about_ca_topic_score_codex":0.0012742784,"about_ca_topic_score_gemma":0.00073295576,"teacher_disagreement_score":0.2698983,"about_ca_system_score_codex":0.0002744002,"about_ca_system_score_gemma":0.00085266936,"threshold_uncertainty_score":0.9997671},"labels":[],"label_agreement":null},{"id":"W2515426017","doi":"10.1177/0008068320050504","title":"Symmetry and Bayesian Function Estimation <sup>1</sup>","year":2005,"lang":"en","type":"article","venue":"Calcutta Statistical Association Bulletin","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université de Montréal","funders":"","keywords":"Mathematics; Spectral geometry; Frequentist inference; Function (biology); Bayes estimator; Bayesian probability; Homogeneous space; Applied mathematics; Manifold (fluid mechanics); Statistical manifold; Bayes' theorem; Riemannian manifold; Estimator; Euclidean space; Bayesian inference; Pure mathematics; Information geometry; Statistics; Geometry; Scalar curvature; Curvature","score_opus":0.0069715522003412495,"score_gpt":0.24327191100104947,"score_spread":0.2363003588007082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515426017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033421785,0.00009935843,0.98149234,0.01427942,0.00011784284,0.00016603095,0.0000295133,0.00017744815,0.0033038186],"genre_scores_gemma":[0.16055995,0.000017166767,0.8350173,0.002156205,0.00020629633,0.000021459107,0.0000305345,0.000015422867,0.0019756542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801683,0.0003116709,0.00038024288,0.00048005953,0.00043194366,0.00037925958],"domain_scores_gemma":[0.9983927,0.00084013905,0.00016698852,0.0002544864,0.00013228541,0.00021341613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009879402,0.0001864798,0.00024379267,0.00009773256,0.0002063215,0.00026103723,0.00020581644,0.00019773137,0.0002714269],"category_scores_gemma":[0.0009841763,0.00018320796,0.000046273195,0.0002263186,0.00003496161,0.00021631017,0.000100376106,0.0002636332,0.00030103337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008240999,0.000051979627,0.00027462328,0.0000134043685,0.000023788754,0.0000030913354,0.00016480946,0.00013934748,0.000013633892,0.5430099,0.048519984,0.40777722],"study_design_scores_gemma":[0.0006212501,0.000104446655,0.0045474344,0.000018583385,0.00004670885,0.000011342385,0.000012019491,0.8214806,0.00005343008,0.07622616,0.09655624,0.00032179357],"about_ca_topic_score_codex":0.000014186602,"about_ca_topic_score_gemma":0.0000016995918,"teacher_disagreement_score":0.8213412,"about_ca_system_score_codex":0.00025400892,"about_ca_system_score_gemma":0.000040240124,"threshold_uncertainty_score":0.74710035},"labels":[],"label_agreement":null},{"id":"W2517722844","doi":"10.1371/journal.pone.0161112","title":"Performance Evaluation of Missing-Value Imputation Clustering Based on a Multivariate Gaussian Mixture Model","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National High-tech Research and Development Program; Priority Academic Program Development of Jiangsu Higher Education Institutions; Government of Jiangsu Province; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Missing data; Cluster analysis; Imputation (statistics); Expectation–maximization algorithm; Mixture model; Multivariate statistics; Computer science; Pattern recognition (psychology); Data mining; Gaussian; Artificial intelligence; Mathematics; Statistics; Machine learning; Maximum likelihood","score_opus":0.06995695490798276,"score_gpt":0.2934285494568177,"score_spread":0.22347159454883492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517722844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048084784,0.00001648388,0.94854665,0.0012155707,0.000040924748,0.0002856022,0.000003826896,0.000063398686,0.0017427715],"genre_scores_gemma":[0.5328688,0.000002104465,0.4669382,0.00010601684,0.00002321863,0.000015606687,9.24159e-7,0.000007811564,0.000037319925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821734,0.00024213688,0.00024693218,0.0003422187,0.00074848835,0.00020285937],"domain_scores_gemma":[0.99893975,0.00010007754,0.00016677559,0.00047820705,0.00024020414,0.000074976444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012763328,0.00013900372,0.00020118593,0.00012885722,0.0000743236,0.0000327826,0.00030979738,0.000087074484,0.000010388469],"category_scores_gemma":[0.00014270743,0.000097792574,0.00004690285,0.00017438327,0.000023624338,0.0003595159,0.000056090907,0.00008191441,0.000006999386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079356745,0.0007708157,0.00010087017,0.00014643601,0.000056096505,0.0000011145285,0.0008373328,0.047751483,0.26732433,0.0053670267,0.000016382259,0.67754877],"study_design_scores_gemma":[0.00085539516,0.00010922943,0.00078192994,0.00058052794,0.000049973452,5.8258394e-7,5.746077e-7,0.9351956,0.05311172,0.009180721,6.3281396e-7,0.00013307718],"about_ca_topic_score_codex":0.0000046688397,"about_ca_topic_score_gemma":0.0000014821326,"teacher_disagreement_score":0.88744414,"about_ca_system_score_codex":0.00008675852,"about_ca_system_score_gemma":0.00015096721,"threshold_uncertainty_score":0.39878654},"labels":[],"label_agreement":null},{"id":"W2518176102","doi":"10.1109/iscas.2016.7538965","title":"A novel 3D model recognition approach using Pitman-Yor process mixtures of Beta-Liouville Distributions","year":2016,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Generalization; Inference; Computer science; Artificial intelligence; Bayes' theorem; Process (computing); Bayesian inference; BETA (programming language); Applied mathematics; Algorithm; Machine learning; Pattern recognition (psychology); Mathematics; Bayesian probability","score_opus":0.07160166049523677,"score_gpt":0.30288617702560633,"score_spread":0.23128451653036958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518176102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028365345,0.000046000314,0.99147856,0.00029244483,0.00007001275,0.00021704941,0.00008249901,0.00010412998,0.0048727477],"genre_scores_gemma":[0.23554027,0.0000052051423,0.7641514,0.000070623624,0.000033153814,0.00002000035,0.0000060713246,0.000008745276,0.00016455268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986506,0.00006270943,0.00030642695,0.0004446086,0.00024541092,0.00029023876],"domain_scores_gemma":[0.99898434,0.000073832576,0.00014336324,0.0004458087,0.00025108914,0.000101544974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045949567,0.0001679343,0.0002380799,0.00010786567,0.0001164548,0.000046429643,0.0005040162,0.00010965134,0.000013415895],"category_scores_gemma":[0.000057237285,0.000105273444,0.00009945343,0.00036689453,0.000077760444,0.0005658389,0.00012876122,0.00008089733,0.0000036639003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026769892,0.0008568724,0.00003594461,0.0001599387,0.00008693343,0.0000016297233,0.00084077957,0.00056566676,0.20604776,0.43645224,0.00053740444,0.35438806],"study_design_scores_gemma":[0.0005525257,0.000036060756,0.00002390281,0.00007018667,0.000033768556,0.000032224878,0.000007820239,0.79437214,0.06607824,0.1384675,0.00003130441,0.0002943434],"about_ca_topic_score_codex":0.000022213218,"about_ca_topic_score_gemma":0.0000023798762,"teacher_disagreement_score":0.79380643,"about_ca_system_score_codex":0.000035820536,"about_ca_system_score_gemma":0.00012786445,"threshold_uncertainty_score":0.42929265},"labels":[],"label_agreement":null},{"id":"W2521468507","doi":"","title":"Loss modelling with mixtures of Erlang distributions","year":2014,"lang":"en","type":"article","venue":"Lirias (KU Leuven)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"KU Leuven; University of Toronto; Universiteit van Amsterdam","keywords":"Erlang (programming language); Computer science; Programming language","score_opus":0.015240964997891496,"score_gpt":0.23838087458759774,"score_spread":0.22313990958970625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521468507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008892109,0.0001245001,0.9868704,0.00084035326,0.00018678303,0.000098152064,0.000009973474,0.00008917012,0.0028885303],"genre_scores_gemma":[0.5281094,0.0000049939977,0.4715196,0.000106785694,0.00008117741,0.0000063094367,0.0000043383357,0.000007639278,0.0001598203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988236,0.00013262888,0.0002164781,0.00032456117,0.0002292645,0.0002735081],"domain_scores_gemma":[0.9989144,0.00013694509,0.00011404818,0.0006372537,0.00009446544,0.000102848535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041000196,0.00014907942,0.00024062186,0.00006379018,0.00010176047,0.000057827416,0.0005660902,0.00008205472,0.000007661877],"category_scores_gemma":[0.000021762406,0.00011335379,0.00007768436,0.0002929989,0.00007341822,0.00026002433,0.00010058081,0.00015834815,0.000010893698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013162785,0.000058024478,0.00011741594,0.000028415903,0.000025438738,0.000006919563,0.0004478336,0.0039830543,0.00047564,0.9587292,0.00038387827,0.035731018],"study_design_scores_gemma":[0.0009784091,0.00031240788,0.00032912617,0.00016906273,0.00004865758,0.00006243282,0.000011639036,0.63514185,0.018801374,0.32033896,0.023235468,0.00057061104],"about_ca_topic_score_codex":0.000050766277,"about_ca_topic_score_gemma":0.000007767581,"teacher_disagreement_score":0.63839024,"about_ca_system_score_codex":0.000018282677,"about_ca_system_score_gemma":0.00004766233,"threshold_uncertainty_score":0.46224332},"labels":[],"label_agreement":null},{"id":"W2525445790","doi":"10.1016/j.csda.2016.09.007","title":"Model selection for discrete regular vine copulas","year":2016,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Alexander von Humboldt-Stiftung","keywords":"Vine copula; Copula (linguistics); Bivariate analysis; Univariate; Multivariate statistics; Benchmark (surveying); Computer science; Joint probability distribution; Mathematics; Marginal distribution; Gaussian; Data mining; Algorithm; Mathematical optimization; Econometrics; Statistics; Random variable","score_opus":0.05648152366928197,"score_gpt":0.34696084512182107,"score_spread":0.2904793214525391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525445790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046340232,0.000036520003,0.99468815,0.0009009219,0.00006539609,0.00014211668,0.0040171673,0.000071050184,0.000032327454],"genre_scores_gemma":[0.042049587,0.000017272545,0.955074,0.00018251453,0.00006618137,0.000017127622,0.0021051792,0.000012454196,0.00047565377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816316,0.00009934231,0.00036750062,0.00073848525,0.00038036576,0.00025114868],"domain_scores_gemma":[0.99799275,0.0005448116,0.00017961726,0.0008023771,0.00035837793,0.00012206382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000592355,0.0001652824,0.00029635715,0.00023649003,0.00020529843,0.00014569277,0.0009447124,0.00005252281,0.000022300455],"category_scores_gemma":[0.00021306767,0.00012415813,0.00009518246,0.00075507234,0.000051737527,0.0005442261,0.0003239276,0.000051636056,0.000010426119],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013359711,0.000036482023,0.00032884133,0.000012324225,0.0005631025,0.0000014952936,0.00003272764,0.064113274,0.00011487957,0.8239916,0.016688792,0.09410311],"study_design_scores_gemma":[0.00018852575,0.000018237986,0.00048702155,0.0000041338303,0.000281758,0.0000014368333,2.2457019e-7,0.61592925,0.000013594769,0.38231128,0.00064203946,0.00012252106],"about_ca_topic_score_codex":0.0000372876,"about_ca_topic_score_gemma":0.000090230715,"teacher_disagreement_score":0.5518159,"about_ca_system_score_codex":0.000059421294,"about_ca_system_score_gemma":0.00012896684,"threshold_uncertainty_score":0.5063022},"labels":[],"label_agreement":null},{"id":"W2527129705","doi":"10.1016/j.ijar.2016.09.011","title":"Nonparametric adaptive Bayesian regression using priors with tractable normalizing constants and under qualitative assumptions","year":2016,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Prior probability; Nonparametric regression; Bayesian probability; Nonparametric statistics; Mathematics; Regression; Applied mathematics; Bayesian linear regression; Econometrics; Statistics; Computer science; Artificial intelligence; Bayesian inference","score_opus":0.03882337038694846,"score_gpt":0.34641687216811373,"score_spread":0.3075935017811653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527129705","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093174815,0.0002947052,0.90517044,0.0005340777,0.000213535,0.000073415315,0.0000064823926,0.000018443294,0.0005140715],"genre_scores_gemma":[0.48184252,0.00007342137,0.517974,0.00003555505,0.000046592686,9.61709e-7,1.9939135e-7,0.00000817383,0.000018554334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982493,0.0002525905,0.00042112495,0.00024256707,0.0006003152,0.00023410477],"domain_scores_gemma":[0.99789524,0.0005079385,0.00072043046,0.0001395441,0.00058854214,0.00014828879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012200068,0.00017058145,0.0002692235,0.00042320997,0.00011913864,0.0002006276,0.00046226228,0.00006624285,0.0000091597485],"category_scores_gemma":[0.00016617538,0.00009893848,0.00006743683,0.00028071366,0.000105809595,0.0016004478,0.000116101655,0.00019665368,7.472142e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007144053,0.00030644966,0.0032378158,0.000031283234,0.0009937952,0.0004997303,0.015440654,0.0005721456,0.028487965,0.62689567,0.000077235636,0.32274288],"study_design_scores_gemma":[0.0142222345,0.0017403481,0.010008973,0.01891457,0.00038777848,0.015421407,0.011048564,0.6273025,0.042029552,0.25571406,0.0005971389,0.0026128523],"about_ca_topic_score_codex":0.000018536826,"about_ca_topic_score_gemma":0.0000022356294,"teacher_disagreement_score":0.6267304,"about_ca_system_score_codex":0.00017786329,"about_ca_system_score_gemma":0.00018448432,"threshold_uncertainty_score":0.4034594},"labels":[],"label_agreement":null},{"id":"W2536231481","doi":"10.1109/mlsp.2004.1422956","title":"Improving content based image retrieval systems using finite multinomial dirichlet mixture","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Multinomial distribution; Computer science; Probabilistic logic; Artificial intelligence; Pattern recognition (psychology); Dirichlet distribution; Mixture model; Categorization; Latent Dirichlet allocation; Topic model; Mathematics; Statistics","score_opus":0.04347014978397442,"score_gpt":0.27183989864143876,"score_spread":0.22836974885746433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2536231481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006234647,0.00022486235,0.9908094,0.00053346856,0.0007137621,0.00032291046,0.0000068148647,0.00024307035,0.00091109093],"genre_scores_gemma":[0.16894424,0.0000014711381,0.8291111,0.0008750436,0.00042906648,0.0000036538847,0.0000018817063,0.000017511888,0.000616055],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802035,0.00022041144,0.0004060673,0.00056373555,0.0003184633,0.0004709535],"domain_scores_gemma":[0.9985663,0.00022969255,0.00017325446,0.0006625643,0.00017865261,0.00018949212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008297289,0.00024727825,0.0003065162,0.00012509056,0.0001684611,0.0004291327,0.00066282274,0.00015144632,0.000021960674],"category_scores_gemma":[0.00016083742,0.00019813984,0.00013877044,0.0002946328,0.000042655316,0.000650385,0.00019036182,0.00024711018,0.000024845973],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007887258,0.00017332398,0.00009642752,0.00010548252,0.000038200204,0.00007543206,0.00031434462,0.0011221571,0.92366433,0.023794707,0.00057798764,0.049958713],"study_design_scores_gemma":[0.0007468746,0.00003965782,0.000039868686,0.000028437993,0.0000130784665,0.000019467398,0.000009592214,0.93456113,0.06284877,0.000047910642,0.0013655064,0.0002796805],"about_ca_topic_score_codex":0.00016825128,"about_ca_topic_score_gemma":0.000004301555,"teacher_disagreement_score":0.933439,"about_ca_system_score_codex":0.00011633896,"about_ca_system_score_gemma":0.0001321331,"threshold_uncertainty_score":0.80799085},"labels":[],"label_agreement":null},{"id":"W2537444784","doi":"10.1109/codit.2016.7593572","title":"RJMCMC learning for clustering and feature selection of L&lt;inf&gt;2&lt;/inf&gt;-normalized vectors","year":2016,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Reversible-jump Markov chain Monte Carlo; Cluster analysis; Feature selection; Computer science; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Markov chain; Pattern recognition (psychology); Markov chain Monte Carlo; Bayesian probability; Machine learning","score_opus":0.012285796315086434,"score_gpt":0.25421669496089333,"score_spread":0.24193089864580689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537444784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0140874805,0.00015506354,0.9821467,0.0006860119,0.00027873123,0.00027013806,0.0000014917272,0.0001701017,0.002204311],"genre_scores_gemma":[0.38390806,0.000055248438,0.6103312,0.00011091135,0.00011228015,0.000022255168,9.4269984e-7,0.000019089284,0.005440036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986209,0.00013554737,0.00025274506,0.00043916795,0.00018896771,0.00036261973],"domain_scores_gemma":[0.99906564,0.00026259484,0.00015509862,0.0002583504,0.00014123609,0.00011706776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069054356,0.00019843159,0.000300659,0.00014101881,0.00016892252,0.000090185305,0.00030479,0.00016158193,0.000026934555],"category_scores_gemma":[0.00012843282,0.00013342689,0.00010310504,0.00026464113,0.00004364288,0.0005369956,0.0001874066,0.00012489212,0.000002691128],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010750543,0.000039258317,0.0011672402,0.00014171278,0.00006975708,0.000002349268,0.0008653497,0.000085474,0.42286685,0.06799546,0.0024094398,0.50424963],"study_design_scores_gemma":[0.007998877,0.0019455835,0.010623876,0.0005842068,0.00013223843,0.00025758336,0.000041571468,0.5401675,0.2730227,0.027002202,0.13630706,0.001916559],"about_ca_topic_score_codex":0.000010603218,"about_ca_topic_score_gemma":0.00004151377,"teacher_disagreement_score":0.54008204,"about_ca_system_score_codex":0.000036675698,"about_ca_system_score_gemma":0.000048947564,"threshold_uncertainty_score":0.5440991},"labels":[],"label_agreement":null},{"id":"W2540718312","doi":"10.1002/cjs.11331","title":"Switching nonparametric regression models for multi‐curve data","year":2017,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Frequentist inference; Covariate; Nonparametric statistics; Curve fitting; Nonparametric regression; Function (biology); Mathematics; Data set; Independent and identically distributed random variables; Computer science; Econometrics; Statistics; Bayesian probability; Bayesian inference","score_opus":0.22845851167192782,"score_gpt":0.3690791161144387,"score_spread":0.1406206044425109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2540718312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026016263,0.002259668,0.99043274,0.00041430962,0.0035611172,0.0002936002,0.0028202422,0.000009089763,0.00018324357],"genre_scores_gemma":[0.014460756,0.00022720087,0.9845081,0.00014326822,0.0003885304,0.0000037919683,0.00007938661,0.00003514654,0.0001538099],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977302,0.00015332551,0.0007386625,0.00054554816,0.0003303653,0.0005018766],"domain_scores_gemma":[0.9938295,0.00039495947,0.0016226589,0.0023348697,0.00082778273,0.0009902545],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00212203,0.0003210559,0.0006697987,0.0006640459,0.00041657663,0.0010149169,0.0060187755,0.00031819625,0.0000039531674],"category_scores_gemma":[0.0019074391,0.0002780644,0.00012459184,0.00010696633,0.000066077744,0.00065743923,0.00072700524,0.0011016567,0.0000015034326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010038747,0.000030055911,0.00008080201,0.00031519504,0.00017336439,0.00055034243,0.0009941556,0.002350427,0.0000074260297,0.13665447,0.055217117,0.8036166],"study_design_scores_gemma":[0.00030827886,0.000041690273,0.00008597164,0.00042502268,0.000063243046,0.000071279464,0.000004305376,0.6763117,0.000007473155,0.31977168,0.002661925,0.00024744816],"about_ca_topic_score_codex":0.0029421144,"about_ca_topic_score_gemma":0.006686785,"teacher_disagreement_score":0.80336916,"about_ca_system_score_codex":0.00020772523,"about_ca_system_score_gemma":0.005676403,"threshold_uncertainty_score":0.99996716},"labels":[],"label_agreement":null},{"id":"W2543456117","doi":"10.1109/icmla.2011.6174513","title":"Probabilistic clustering based on Langevin mixture","year":2011,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hypersphere; Cluster analysis; Computer science; Probabilistic logic; Artificial intelligence; Mixture model; Representation (politics); Categorization; Machine learning; Pattern recognition (psychology)","score_opus":0.041937194855617796,"score_gpt":0.25123156492399523,"score_spread":0.20929437006837742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2543456117","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001342292,0.00001001662,0.84649855,0.00027862965,0.0001671838,0.00010465759,4.3871682e-7,0.000165195,0.15264112],"genre_scores_gemma":[0.17953932,5.361226e-7,0.8176981,0.0017932389,0.000035096855,0.0000117535465,3.9169157e-7,0.000006929726,0.0009146055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923724,0.00007398939,0.00010253824,0.00027983345,0.0001213431,0.00018506683],"domain_scores_gemma":[0.9992946,0.000049844344,0.000026857171,0.000524134,0.000026558944,0.00007803733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025325696,0.000103625025,0.00010175759,0.000054149692,0.00004209691,0.000040343937,0.00047428382,0.000054567397,0.0001012882],"category_scores_gemma":[0.00002984939,0.00007473023,0.000045406647,0.00013895471,0.000015578333,0.00010588857,0.000080345264,0.000096571865,0.000055287463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026072834,0.00023510362,0.00014843106,0.00006527582,0.0000103559005,0.000060759117,0.001123167,0.0001268052,0.00041351357,0.7870159,0.0044181463,0.20635648],"study_design_scores_gemma":[0.0002923267,0.00020045594,0.0010612198,0.00004112142,0.0000055106952,0.000008790011,0.0000029232594,0.9331301,0.0019914065,0.060753025,0.0022342894,0.00027884892],"about_ca_topic_score_codex":0.000022912447,"about_ca_topic_score_gemma":0.000036257177,"teacher_disagreement_score":0.9330033,"about_ca_system_score_codex":0.00001533139,"about_ca_system_score_gemma":0.000026381362,"threshold_uncertainty_score":0.30474105},"labels":[],"label_agreement":null},{"id":"W2544994990","doi":"10.1109/icmla.2011.81","title":"Infinite Dirichlet Mixture Model and Its Application via Variational Bayes","year":2011,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet process; Hierarchical Dirichlet process; Dirichlet distribution; Generalized Dirichlet distribution; Latent Dirichlet allocation; Mixture model; Inference; Bayes' theorem; Mathematics; Artificial intelligence; Bayesian inference; Representation (politics); Categorization; Concentration parameter; Applied mathematics; Computer science; Pattern recognition (psychology); Dirichlet's principle; Bayesian probability; Topic model; Mathematical analysis; Boundary value problem","score_opus":0.025297484875917466,"score_gpt":0.246881730096876,"score_spread":0.22158424522095854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544994990","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000325887,0.000091328046,0.9813298,0.0004971871,0.000048174552,0.0001369202,0.0000024348824,0.00010801587,0.017460234],"genre_scores_gemma":[0.29837507,0.000012758075,0.7004085,0.00075031206,0.000028343638,0.000021606369,0.0000020262419,0.000004841159,0.00039656158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992162,0.00004040833,0.00014149107,0.00032000645,0.00013519789,0.00014671155],"domain_scores_gemma":[0.999465,0.000039346905,0.00005380509,0.0002725171,0.00008095293,0.00008838688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024967696,0.00010729739,0.000100718906,0.00006152954,0.000074465854,0.000037677193,0.0003153566,0.000083846775,0.000021939137],"category_scores_gemma":[0.00001210825,0.00008744867,0.000025575848,0.00016571696,0.000012982705,0.00041062036,0.00013507958,0.000085517444,0.000016027316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025173993,0.00002865316,0.000039569248,0.0000056392464,0.0000071415607,4.9515756e-7,0.00061851996,0.000031917145,0.0024642567,0.9595262,0.00026546157,0.037009656],"study_design_scores_gemma":[0.00007898906,0.000011289829,0.0008355472,0.0000015704533,0.000003544002,0.0000060957204,5.234099e-7,0.6933236,0.0006602672,0.30468485,0.00030095648,0.0000927242],"about_ca_topic_score_codex":0.000009785209,"about_ca_topic_score_gemma":0.0000039050788,"teacher_disagreement_score":0.6932917,"about_ca_system_score_codex":0.0000075627627,"about_ca_system_score_gemma":0.000029284325,"threshold_uncertainty_score":0.35660535},"labels":[],"label_agreement":null},{"id":"W2547113758","doi":"10.1002/cjs.11323","title":"A comparative review of variable selection techniques for covariate dependent Dirichlet process mixture models","year":2017,"lang":"en","type":"review","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Covariate; Latent variable; Mathematics; Dirichlet distribution; Dirichlet process; Feature selection; Statistics; Econometrics; Computer science; Artificial intelligence","score_opus":0.14056292487670474,"score_gpt":0.39800148614202485,"score_spread":0.2574385612653201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547113758","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1657079e-9,0.48756132,0.5107002,0.000023525232,0.00019838221,0.00051743456,0.00069143664,0.0000037234931,0.00030394632],"genre_scores_gemma":[5.7184434e-7,0.50198305,0.49770477,0.00007374737,0.00008508821,0.000026189276,0.00001915935,0.000015524902,0.00009191004],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971314,0.00037324967,0.0014747311,0.00031894923,0.0003353949,0.00036625075],"domain_scores_gemma":[0.99301136,0.0003340403,0.0035143003,0.00050808716,0.0021733604,0.000458848],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022988785,0.0003803715,0.0027618874,0.00038224025,0.00020857912,0.00018516213,0.0016634144,0.00026228174,0.000014220323],"category_scores_gemma":[0.00048434007,0.00029788452,0.0002948904,0.00030306083,0.000076856006,0.00037387235,0.00003234211,0.0005819858,7.564241e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025141203,0.000016730593,1.1863101e-7,0.05823259,0.00022657315,0.000035166897,0.0001515983,0.0000085756665,1.690313e-7,0.16264269,0.01994612,0.75873715],"study_design_scores_gemma":[0.00011284611,0.00021411752,1.094533e-7,0.0748503,0.0008517171,0.0004629327,0.0000015955776,0.0021915145,0.0000065918703,0.14671135,0.7742506,0.00034628712],"about_ca_topic_score_codex":0.000274165,"about_ca_topic_score_gemma":0.00048622,"teacher_disagreement_score":0.75839084,"about_ca_system_score_codex":0.00024747485,"about_ca_system_score_gemma":0.009311498,"threshold_uncertainty_score":0.9999473},"labels":[],"label_agreement":null},{"id":"W2551174787","doi":"10.1002/cjs.11308","title":"The multivariate leptokurtic‐normal distribution and its application in model‐based clustering","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Kurtosis; Multivariate statistics; Mathematics; Elliptical distribution; Multivariate normal distribution; Cluster analysis; Statistics; Distribution (mathematics); Normal distribution; Applied mathematics; Mixture model; Mathematical analysis","score_opus":0.01804132866093049,"score_gpt":0.25013991125605445,"score_spread":0.23209858259512395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551174787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001292275,0.00010572779,0.99713767,0.0012106416,0.000100056,0.000057369907,0.000070798254,0.0000024405415,0.000023042803],"genre_scores_gemma":[0.72089845,0.000016509524,0.2789848,0.000053861713,0.000020748406,0.0000016455407,7.7222666e-7,0.0000032976761,0.00001987804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934256,0.000061802304,0.00023000769,0.00008407687,0.00008626614,0.00019531412],"domain_scores_gemma":[0.99923444,0.00017485961,0.00012972904,0.000106537125,0.00012853347,0.00022591889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054011744,0.000060473223,0.0000821626,0.000055985096,0.00012267566,0.00007302429,0.00023505308,0.00003200831,7.5528914e-7],"category_scores_gemma":[0.00017232404,0.000037725094,0.000012881955,0.00008340511,0.000035069057,0.00017999018,0.000015265929,0.000089904825,7.6450385e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009428819,0.000004757539,0.00034270855,0.000008913903,0.0000062255485,0.000030939394,0.00022836808,0.0016590732,0.0009247713,0.34180024,0.00018866533,0.6547959],"study_design_scores_gemma":[0.00032657952,0.000024450444,0.0025816455,0.000038432132,0.000004530151,0.000019471214,0.000003205183,0.9629599,0.000234653,0.03318527,0.0005547349,0.00006716618],"about_ca_topic_score_codex":0.00024332665,"about_ca_topic_score_gemma":0.004611275,"teacher_disagreement_score":0.9613008,"about_ca_system_score_codex":0.00011067664,"about_ca_system_score_gemma":0.00042913164,"threshold_uncertainty_score":0.25731996},"labels":[],"label_agreement":null},{"id":"W2557218182","doi":"10.1101/085993","title":"Estimation of sub-epidemic dynamics by means of Sequential Monte Carlo Approximate Bayesian Computation: an application to the Swiss HIV Cohort Study","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Approximate Bayesian computation; Computer science; Bayesian probability; Monte Carlo method; Computation; Human immunodeficiency virus (HIV); Markov chain Monte Carlo; Particle filter; Transmission (telecommunications); Econometrics; Data mining; Statistics; Artificial intelligence; Algorithm; Biology; Mathematics; Virology","score_opus":0.01103724436488234,"score_gpt":0.25426844659032105,"score_spread":0.2432312022254387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557218182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14913087,0.00009507182,0.8470435,0.00045306073,0.00039212793,0.0024457087,0.0002523797,0.00018295398,0.000004324046],"genre_scores_gemma":[0.80497813,0.00001258212,0.19445524,0.000054805634,0.00009210122,0.00035055281,0.0000012313411,0.00005405829,0.0000012998495],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959332,0.0007067383,0.0010463608,0.0012383821,0.00067748886,0.00039785076],"domain_scores_gemma":[0.9956018,0.00011847653,0.001064382,0.0022915076,0.00068999146,0.00023388889],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026764164,0.000493682,0.00079653563,0.00024295555,0.00014869524,0.00014556096,0.0018075359,0.0003131414,0.0000011432566],"category_scores_gemma":[0.000096261145,0.0004061379,0.00014135081,0.0006451177,0.00010643551,0.0003445784,0.0006658608,0.0003869496,0.0000035515402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028680643,0.0040330384,0.067185715,0.002602478,0.0021224155,0.00003500279,0.001874942,0.22763911,0.5763477,0.108288646,0.002037929,0.0075462055],"study_design_scores_gemma":[0.00034198258,0.00010866854,0.014008802,0.00015326517,0.00013432749,3.427402e-8,0.0000045260845,0.95728385,0.027233802,0.00023465668,0.0000131115885,0.00048298438],"about_ca_topic_score_codex":0.00015382061,"about_ca_topic_score_gemma":0.000020771837,"teacher_disagreement_score":0.7296447,"about_ca_system_score_codex":0.0002864776,"about_ca_system_score_gemma":0.00033105194,"threshold_uncertainty_score":0.99983907},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2559900549","doi":"10.5351/csam.2016.23.6.445","title":"Nonparametric Bayesian methods: a gentle introduction and overview","year":2016,"lang":"en","type":"article","venue":"Communications for Statistical Applications and Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; Ohio State University; National Science Foundation","keywords":"Dirichlet process; Nonparametric statistics; Consistency (knowledge bases); Bayesian probability; Dirichlet distribution; Computer science; Econometrics; Bayesian statistics; Mathematics; Data mining; Machine learning; Bayesian inference; Artificial intelligence","score_opus":0.053213613811979865,"score_gpt":0.4345534778964141,"score_spread":0.3813398640844342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559900549","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017275613,0.0056889867,0.9819351,0.010779194,0.00006192482,0.00083632465,0.00006518809,0.00009771984,0.0005338346],"genre_scores_gemma":[0.0004339009,0.004342899,0.9931832,0.00023227598,0.000072674906,0.0014628713,0.000015797605,0.000017224585,0.00023918024],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781233,0.00087768806,0.00040038582,0.0005667846,0.000084294166,0.0002585302],"domain_scores_gemma":[0.99258983,0.004904069,0.00013022183,0.0019837178,0.00017324647,0.00021893317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002455859,0.00017503831,0.00029984664,0.00017878033,0.00045821271,0.00012422615,0.0008164724,0.00009492586,0.000014830406],"category_scores_gemma":[0.0006729685,0.00012851259,0.000051256196,0.00057899853,0.00034515822,0.00024020062,0.0005656271,0.00012478635,0.000004095178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014944465,0.000030226181,0.0000038629746,0.000016538168,0.00001005781,1.9310448e-8,0.000025397941,2.5803654e-8,0.0009496643,0.49516878,0.00023780671,0.50355613],"study_design_scores_gemma":[0.00024109315,0.000047943267,0.00024805512,0.000010061975,0.000044554297,0.00001841375,0.0000074381683,0.014981814,0.0004838014,0.60301286,0.38073856,0.00016540517],"about_ca_topic_score_codex":0.000008901972,"about_ca_topic_score_gemma":0.000002901006,"teacher_disagreement_score":0.5033907,"about_ca_system_score_codex":0.000037055554,"about_ca_system_score_gemma":0.00004809598,"threshold_uncertainty_score":0.5240591},"labels":[],"label_agreement":null},{"id":"W2560940630","doi":"10.1007/s00357-018-9280-z","title":"On Fractionally-Supervised Classification: Weight Selection and Extension to the Multivariate t-Distribution","year":2018,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Extension (predicate logic); Multivariate statistics; Selection (genetic algorithm); Cluster analysis; Gaussian; Artificial intelligence; Resolution (logic); Multivariate normal distribution; Model selection; Pattern recognition (psychology); Computer science; Machine learning; Mathematics; Chemistry","score_opus":0.053785955787808676,"score_gpt":0.32347412047800156,"score_spread":0.26968816469019286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560940630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013071592,0.00014034273,0.9597095,0.024275655,0.0020478512,0.0004086888,0.000012350795,0.00004343668,0.000290555],"genre_scores_gemma":[0.75311506,0.0002490286,0.24414209,0.000745769,0.0015224776,0.00003756497,0.000034238394,0.00002222484,0.00013157837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710065,0.00058785465,0.0008096846,0.00058483926,0.0007088319,0.00020811442],"domain_scores_gemma":[0.9960466,0.00031584024,0.0012523871,0.0007528038,0.0014473812,0.00018498894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022843024,0.0002767486,0.0003454133,0.00025027426,0.00033880427,0.00036754357,0.00081159506,0.00036222563,0.000014023086],"category_scores_gemma":[0.00048081164,0.00019101004,0.00016209038,0.00040157765,0.00004972462,0.00040111766,0.0002214328,0.0009337657,0.00002896159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000508017,0.0005548849,0.0001785831,0.000100813355,0.00023274284,0.000007322149,0.0013332835,0.00088555145,0.041804746,0.41497552,0.0637968,0.47562173],"study_design_scores_gemma":[0.00074771896,0.0005787878,0.17582136,0.0004895136,0.0001380101,0.0001920421,0.000033221568,0.64445615,0.0024980083,0.13806733,0.036458388,0.0005194351],"about_ca_topic_score_codex":0.0000073173896,"about_ca_topic_score_gemma":0.000004053704,"teacher_disagreement_score":0.74004346,"about_ca_system_score_codex":0.0003085084,"about_ca_system_score_gemma":0.0003185026,"threshold_uncertainty_score":0.7789163},"labels":[],"label_agreement":null},{"id":"W2563004743","doi":"10.1515/sagmb-2015-0096","title":"Statistical models and computational algorithms for discovering relationships in microbiome data","year":2016,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Microbiome; Human microbiome; Multinomial distribution; Computer science; Human Microbiome Project; Human health; Dirichlet distribution; Computational biology; Data science; Biology; Bioinformatics; Statistics; Mathematics","score_opus":0.05676287330995345,"score_gpt":0.3576809279288802,"score_spread":0.30091805461892673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563004743","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013963865,0.00038861728,0.99617046,0.00058890437,0.000018870805,0.00038798555,0.0010058242,0.000009972012,0.000032970012],"genre_scores_gemma":[0.2510066,0.000082357314,0.74857926,0.000059412785,0.0000074981976,0.00008761383,0.00016811957,0.0000061015858,0.0000030497422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998819,0.00011104142,0.00026172202,0.0005553656,0.000046333073,0.00020655988],"domain_scores_gemma":[0.9986857,0.00083137356,0.000035821773,0.00033794143,0.000031726122,0.00007741268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003526062,0.00010514058,0.00015348889,0.0000936872,0.000060603656,0.000033679207,0.0002837836,0.00008329635,0.0000010028206],"category_scores_gemma":[0.000074042524,0.00008249025,0.000007462055,0.00011829307,0.00019171798,0.000060179416,0.00031424177,0.00007832313,5.3810595e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027492474,0.000026362353,0.0004065837,0.000008871682,0.0000043487353,0.0000012325861,0.000028559416,0.000052001553,0.0016827994,0.89380866,0.000014219501,0.103963636],"study_design_scores_gemma":[0.00033232744,0.00003188368,0.0027462975,0.000006688565,0.0000045395605,0.0000056459526,0.0000029879618,0.23670302,0.000056452896,0.7594993,0.0005081121,0.00010275721],"about_ca_topic_score_codex":0.000011406249,"about_ca_topic_score_gemma":0.000021255933,"teacher_disagreement_score":0.24961022,"about_ca_system_score_codex":0.000016208984,"about_ca_system_score_gemma":0.000044713343,"threshold_uncertainty_score":0.3363855},"labels":[],"label_agreement":null},{"id":"W2563486537","doi":"10.1093/forestscience/56.4.379","title":"Two-Component Mixture Models for Diameter Distributions in Mixed-Species, Two-Age Cohort Stands","year":2010,"lang":"en","type":"article","venue":"Forest Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Component (thermodynamics); Cohort; Statistics; Geography; Age structure; Environmental science; Demography; Ecology; Mathematics; Biology; Population; Physics; Thermodynamics","score_opus":0.018576600560699475,"score_gpt":0.280084769329255,"score_spread":0.26150816876855554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563486537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05977995,0.00003692266,0.9357108,0.0005401662,0.0014038015,0.00059542403,0.00007728801,0.00009759727,0.0017580785],"genre_scores_gemma":[0.58577794,0.0000038332882,0.41377375,0.000101320526,0.000086197724,0.00009149742,0.00001089002,0.0000081795915,0.00014637811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970955,0.00006053316,0.0003783711,0.000960987,0.0006310316,0.0008735439],"domain_scores_gemma":[0.9980076,0.00021161929,0.000112439564,0.001142067,0.00020922578,0.0003170775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023039829,0.00025467275,0.0003065054,0.00027810593,0.0004681402,0.0004885065,0.0022571317,0.00009139292,0.000008921772],"category_scores_gemma":[0.00018640466,0.00021264753,0.00012592136,0.0013092934,0.0006665711,0.0013314467,0.00045595027,0.0004204433,0.0000066039825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005922316,0.000078103156,0.0010645085,0.000005372985,0.000003178201,0.00001158508,0.00019774163,0.0013326664,0.019003052,0.97527933,0.00029801312,0.0027205325],"study_design_scores_gemma":[0.00067856314,0.00006081887,0.009831214,0.000022568085,0.000007376471,0.0000213711,0.000006354722,0.434124,0.004297773,0.54862255,0.0019730416,0.00035435724],"about_ca_topic_score_codex":0.00009783107,"about_ca_topic_score_gemma":0.0010513891,"teacher_disagreement_score":0.525998,"about_ca_system_score_codex":0.00012568169,"about_ca_system_score_gemma":0.0003191597,"threshold_uncertainty_score":0.86715144},"labels":[],"label_agreement":null},{"id":"W2564000705","doi":"10.1109/dsaa.2016.22","title":"Infinite Langevin Mixture Modeling and Feature Selection","year":2016,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain Monte Carlo; Cluster analysis; Prior probability; Computer science; Feature selection; Mixture model; Model selection; Artificial intelligence; Bayesian probability; Bayesian inference; Feature (linguistics); Algorithm; Posterior probability; Pattern recognition (psychology); Machine learning","score_opus":0.015133384693952132,"score_gpt":0.24965388776670341,"score_spread":0.2345205030727513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564000705","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028272783,0.00015279723,0.98583466,0.006083007,0.00008955584,0.00005537139,6.369036e-7,0.00014938893,0.004807311],"genre_scores_gemma":[0.24605961,0.00006279868,0.7491759,0.00069343345,0.00008702548,0.0000038845883,1.989526e-7,0.000005842868,0.0039112815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993893,0.000049869996,0.00006818933,0.00025003153,0.00008860532,0.0001539887],"domain_scores_gemma":[0.99965,0.000042971835,0.000019557083,0.00017585319,0.0000435995,0.00006801724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019203966,0.000088068125,0.00008833784,0.0000539568,0.00005938027,0.000067821704,0.00016564071,0.00008895724,0.0000102929225],"category_scores_gemma":[0.000021256055,0.00004872775,0.00002384538,0.000141057,0.000010164684,0.00033413016,0.00007991719,0.00007771768,0.0000071632644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062857025,0.000014476899,0.00029985467,0.000012096857,0.000014612115,0.000003516287,0.000277606,0.000010717591,0.030403541,0.31836674,0.00857723,0.6420133],"study_design_scores_gemma":[0.0008784081,0.00012490558,0.00056249823,0.000106416286,0.000014732056,0.00015236148,0.000007387631,0.7500633,0.007238501,0.20846392,0.031792954,0.0005945958],"about_ca_topic_score_codex":0.000007535737,"about_ca_topic_score_gemma":0.000013005402,"teacher_disagreement_score":0.7500526,"about_ca_system_score_codex":0.000011207198,"about_ca_system_score_gemma":0.000017288989,"threshold_uncertainty_score":0.198706},"labels":[],"label_agreement":null},{"id":"W2565002883","doi":"10.1159/000450891","title":"Discrete Distribution Based on Compound Sum to Model Dental Caries Count Data","year":2016,"lang":"en","type":"article","venue":"Caries Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Count data; Negative binomial distribution; Binomial distribution; Statistics; Mathematics; Zero (linguistics); Overdispersion; Dentistry; Distribution (mathematics); Medicine; Econometrics; Poisson distribution","score_opus":0.15137069307489656,"score_gpt":0.4157701148788177,"score_spread":0.2643994218039212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565002883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020600662,0.00006877959,0.98748714,0.0076535107,0.0002298569,0.00031570197,0.00088416436,0.00007206727,0.0012287319],"genre_scores_gemma":[0.89087206,0.000017257995,0.10731739,0.00034498738,0.00012671371,0.000045960984,0.0001639475,0.000017627512,0.0010940252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996837,0.00038865505,0.00019756933,0.0007845617,0.0011056854,0.00068648875],"domain_scores_gemma":[0.99660397,0.0005776629,0.000028611055,0.002174396,0.00032309338,0.00029226067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020194228,0.00016271822,0.00020169161,0.00012741322,0.00047695832,0.00055549823,0.0024043135,0.000091082904,0.000011817602],"category_scores_gemma":[0.0005695426,0.00010778255,0.000043384156,0.00045028227,0.00037160583,0.0006010231,0.0016201648,0.00026316725,0.000061004077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002630014,0.00012661396,0.0006748013,0.000047556525,0.000032481734,0.00007785744,0.0006219332,0.0004760008,0.005468266,0.79457,0.12251704,0.07512444],"study_design_scores_gemma":[0.00056935754,0.00024082167,0.00047138156,0.000108478824,0.000006074863,0.000006182956,0.00003415688,0.92442995,0.0049641337,0.029334266,0.039500486,0.0003346815],"about_ca_topic_score_codex":0.0001584199,"about_ca_topic_score_gemma":0.00013353112,"teacher_disagreement_score":0.92395395,"about_ca_system_score_codex":0.0002755619,"about_ca_system_score_gemma":0.00043800258,"threshold_uncertainty_score":0.5356682},"labels":[],"label_agreement":null},{"id":"W2565954840","doi":"10.5539/ijsp.v6n1p13","title":"On Sequential Learning for Parameter Estimation in Particle Algorithms for State-Space Models","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Particle filter; Algorithm; State space; State-space representation; Bayesian inference; Computer science; Dirichlet distribution; Divergence (linguistics); Mathematical optimization; Nonlinear system; Deconvolution; Gaussian; Mathematics; Inference; Bayesian probability; Artificial intelligence; Kalman filter","score_opus":0.04495860266039764,"score_gpt":0.3347120087617904,"score_spread":0.2897534061013928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565954840","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018986218,0.000018742945,0.9790392,0.0014047247,0.0002838334,0.00019132049,0.00006266072,0.0000052871533,0.000007997731],"genre_scores_gemma":[0.38461295,0.0000145061085,0.61527514,0.00003903931,0.00002152624,0.000009994763,0.0000010055613,0.0000031144784,0.00002273855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99909836,0.00007873905,0.00034001452,0.00015824004,0.00020146133,0.00012318073],"domain_scores_gemma":[0.9979462,0.0012799377,0.00020657665,0.0000725787,0.00043768072,0.000057001977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010804537,0.000073472605,0.00013151238,0.000055310116,0.00003157718,0.000088925204,0.00020133582,0.000028577648,0.0000022799259],"category_scores_gemma":[0.0007578228,0.000050046237,0.000041310355,0.00003159204,0.000035148816,0.00034066252,0.00003342624,0.00007071726,2.2567411e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018054836,0.00006322286,0.00012678106,0.000013133408,0.000023267143,0.0000033912597,0.0002614082,0.006581045,0.00023774765,0.5017164,0.00007222602,0.49072087],"study_design_scores_gemma":[0.0005887975,0.0002008362,0.00017498105,0.000027026595,0.0000027586018,0.000005101022,8.792781e-7,0.4392875,0.0005383142,0.5590797,0.00005501837,0.00003909392],"about_ca_topic_score_codex":0.0000056313233,"about_ca_topic_score_gemma":0.0000053718336,"teacher_disagreement_score":0.4906818,"about_ca_system_score_codex":0.00007170057,"about_ca_system_score_gemma":0.00006297505,"threshold_uncertainty_score":0.20408264},"labels":[],"label_agreement":null},{"id":"W2566526665","doi":"10.1002/cjs.11310","title":"A new method for robust mixture regression","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Natural Science Foundation of China","keywords":"Outlier; Robust regression; Computation; Mixture model; Expectation–maximization algorithm; Contrast (vision); Regression analysis; Regression; Computer science; Robust statistics; Mathematics; Algorithm; Maximum likelihood; Statistics; Artificial intelligence","score_opus":0.029812526993604406,"score_gpt":0.2932130286168522,"score_spread":0.2634005016232478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566526665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000033304466,0.00033869172,0.99419963,0.0042391294,0.0008363949,0.00007309846,0.00010607402,0.0000052253163,0.00019843811],"genre_scores_gemma":[0.00033782775,0.000021094245,0.9972911,0.00042833472,0.0002898855,8.1916016e-7,6.135083e-7,0.000011682729,0.0016186348],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905646,0.00009230732,0.0002874369,0.0001404494,0.00013503947,0.00028831649],"domain_scores_gemma":[0.9979113,0.0004200211,0.00023558938,0.00022309073,0.00032008303,0.00088992465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006071923,0.00010997369,0.0002092214,0.0001729077,0.00009484975,0.00008664739,0.00056217477,0.00007797457,0.0000456147],"category_scores_gemma":[0.00045750555,0.00006561734,0.00006767791,0.00012350295,0.000022540795,0.00020776755,0.0000141920145,0.00011082545,0.0000027641677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041560484,0.0000014663544,0.00001643776,0.000005738504,0.000010910965,0.000065050546,0.00014472227,0.000004455109,0.00018864986,0.19534881,0.18000026,0.62420934],"study_design_scores_gemma":[0.0012939703,0.00035592815,0.0003000952,0.00034220013,0.000048728267,0.0005330923,0.000010238596,0.007957017,0.0012127033,0.767284,0.2203508,0.00031127981],"about_ca_topic_score_codex":0.00031487804,"about_ca_topic_score_gemma":0.0019776972,"teacher_disagreement_score":0.623898,"about_ca_system_score_codex":0.00009154357,"about_ca_system_score_gemma":0.0019834389,"threshold_uncertainty_score":0.35185355},"labels":[],"label_agreement":null},{"id":"W2568188511","doi":"10.1016/j.jda.2011.10.002","title":"Indexability, concentration, and VC theory","year":2011,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Search engine indexing; Histogram; Measure (data warehouse); Dimension (graph theory); Similarity (geometry); Similarity measure; Statistical analysis","score_opus":0.025446906063955575,"score_gpt":0.2651457390474658,"score_spread":0.23969883298351022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568188511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005721329,0.00078403245,0.9896167,0.0002730578,0.0003369655,0.000054504533,0.0000012003053,0.000011373751,0.003200835],"genre_scores_gemma":[0.3334849,0.000093248585,0.666035,0.00020588998,0.00011840997,6.7469404e-7,1.1083873e-7,0.0000047784165,0.000056992045],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989542,0.00021377581,0.0003322,0.0001418961,0.00020519295,0.00015275196],"domain_scores_gemma":[0.9991623,0.000084516774,0.00023371789,0.00021755775,0.00015304418,0.00014882028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001336821,0.000095448435,0.0001865277,0.00003544967,0.000056483623,0.00006983573,0.0004179185,0.00005439171,0.000023639941],"category_scores_gemma":[0.00006590241,0.000066974775,0.00007296098,0.000116176896,0.000087600696,0.00065734074,0.00009513786,0.00019065879,0.0000014779879],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034043645,0.00007375014,0.0021414126,0.000014077707,0.00007580574,0.0000622523,0.004958413,7.0959675e-7,0.00039776383,0.49588436,0.00036412122,0.49599332],"study_design_scores_gemma":[0.0006634151,0.0004167293,0.022450715,0.000039619616,0.00003218763,0.00039882207,0.00007156155,0.004794446,0.004034993,0.96628505,0.000614646,0.00019783685],"about_ca_topic_score_codex":0.0000051610855,"about_ca_topic_score_gemma":6.001929e-7,"teacher_disagreement_score":0.49579546,"about_ca_system_score_codex":0.000014380353,"about_ca_system_score_gemma":0.00007049488,"threshold_uncertainty_score":0.27311522},"labels":[],"label_agreement":null},{"id":"W2569400434","doi":"10.71781/10441","title":"Étude de la médiane de permutations sous la distance de Kendall-Tau","year":2015,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Philosophy; Humanities","score_opus":0.041498546157117316,"score_gpt":0.37581481818713264,"score_spread":0.33431627203001535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569400434","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033414554,0.0013367627,0.8833106,0.0005465286,0.00038065165,0.00046152627,0.00009812413,0.000008353275,0.08044285],"genre_scores_gemma":[0.13469262,0.00017309256,0.83668214,0.00018857971,0.00019962204,0.000098799115,0.0001621193,0.00005757485,0.027745448],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960024,0.0015562407,0.00045714382,0.00084561436,0.00035954834,0.00077907887],"domain_scores_gemma":[0.9974946,0.0006411658,0.00033092021,0.000698934,0.0002697253,0.0005646955],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0033735032,0.00044493386,0.00050677796,0.000115565934,0.00035430805,0.0017615643,0.0022234106,0.00064673147,0.00033846893],"category_scores_gemma":[0.00041431078,0.00048379932,0.00016237328,0.00041076922,0.00019299632,0.00061529997,0.00025413785,0.00075686845,0.00019955171],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082541206,0.00040454607,0.00057104963,0.00011554136,0.0001280778,0.0007665035,0.09330329,0.0009629038,0.0030300578,0.070734106,0.0030999435,0.8268014],"study_design_scores_gemma":[0.003769511,0.00047086322,0.026979933,0.0021221375,0.0008874808,0.0023311675,0.0053539644,0.22637926,0.010104895,0.302127,0.41573134,0.0037424334],"about_ca_topic_score_codex":0.0011128243,"about_ca_topic_score_gemma":0.0018992592,"teacher_disagreement_score":0.823059,"about_ca_system_score_codex":0.00038903437,"about_ca_system_score_gemma":0.0038374441,"threshold_uncertainty_score":0.99976134},"labels":[],"label_agreement":null},{"id":"W2572140284","doi":"","title":"On hyper-parameter estimation in empirical Bayes: a revisit of the MacKay algorithm","year":2016,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bayes' theorem; Algorithm; Heuristic; Computer science; Gaussian; Estimation theory; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Bayesian probability","score_opus":0.05027605717255774,"score_gpt":0.33621117325410327,"score_spread":0.28593511608154554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2572140284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019763375,0.000030379804,0.97623396,0.003033797,0.0003167732,0.00028909292,0.0000042921274,0.000025125013,0.00030321485],"genre_scores_gemma":[0.7300455,0.00001779032,0.26925218,0.0005654122,0.000028104116,0.000023881528,3.1544297e-7,0.000008011084,0.000058835358],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99785095,0.0003799379,0.0006354963,0.0004759963,0.00033331072,0.000324281],"domain_scores_gemma":[0.9978941,0.0011074421,0.0001422851,0.0007238946,0.0000747625,0.000057506302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001050989,0.00017120929,0.00026568433,0.00018853197,0.00004437579,0.000045329394,0.00094153406,0.00011501794,0.000039541756],"category_scores_gemma":[0.0009550345,0.00009700697,0.000104992614,0.00084189005,0.00015385155,0.00020033511,0.00016267039,0.00021581494,0.000047710953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017581104,0.000092969116,0.00015289389,0.0000058748246,0.0000022717088,0.0000031777047,0.00058552914,0.0019688322,0.00047338803,0.13952558,0.000041041745,0.8571309],"study_design_scores_gemma":[0.00004184158,0.00007222609,0.00028074038,0.00023681611,0.000001937423,0.0000026417642,0.000012952516,0.43938422,0.018180415,0.5415896,0.00007127251,0.00012528643],"about_ca_topic_score_codex":0.00012040035,"about_ca_topic_score_gemma":0.00011612526,"teacher_disagreement_score":0.8570056,"about_ca_system_score_codex":0.00013653732,"about_ca_system_score_gemma":0.00008972989,"threshold_uncertainty_score":0.39558294},"labels":[],"label_agreement":null},{"id":"W2583613911","doi":"10.1002/env.2437","title":"Model‐based clustering for spatiotemporal data on air quality monitoring","year":2017,"lang":"en","type":"article","venue":"Environmetrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cluster analysis; Data mining; Computer science; Autoregressive model; Mixture model; Identifiability; Expectation–maximization algorithm; Information Criteria; Model selection; Bayesian information criterion; Air quality index; Statistics; Mathematics; Maximum likelihood; Artificial intelligence; Machine learning; Geography; Meteorology","score_opus":0.24795205905250364,"score_gpt":0.39951383188801604,"score_spread":0.1515617728355124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583613911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034915244,0.000052754196,0.9942664,0.0007039867,0.0005362049,0.00020074764,0.000042619275,0.0000611806,0.00064458407],"genre_scores_gemma":[0.43469402,0.000008888369,0.5649123,0.000089601184,0.00012243117,0.0000080979835,0.0000064865676,0.000010951308,0.00014722958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847925,0.00006789779,0.00023423744,0.00062530924,0.00031345309,0.000279862],"domain_scores_gemma":[0.9957119,0.00027246092,0.00023935194,0.003651262,0.000015095246,0.00010988479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014641933,0.0001579609,0.00020088613,0.00013903709,0.00048200085,0.00021769246,0.0027904129,0.00010286529,0.0000010689271],"category_scores_gemma":[0.00058860146,0.00015243431,0.00006586794,0.00010084554,0.000044115688,0.0006894196,0.0008698982,0.0001608176,0.000008197715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032269316,0.00016853603,0.003869197,0.00006788194,0.000019302868,0.000006892888,0.00013364575,0.022108262,0.00072837377,0.014928897,0.00051066844,0.9574261],"study_design_scores_gemma":[0.00039338082,0.000048128255,0.011365494,0.000014432212,0.000006032098,3.4908183e-7,0.0000010352626,0.97839576,0.002804777,0.005054754,0.0017019085,0.00021395399],"about_ca_topic_score_codex":0.00003093611,"about_ca_topic_score_gemma":0.0000028542001,"teacher_disagreement_score":0.9572121,"about_ca_system_score_codex":0.00005771013,"about_ca_system_score_gemma":0.000036774938,"threshold_uncertainty_score":0.6216091},"labels":[],"label_agreement":null},{"id":"W2592316541","doi":"","title":"Trans-dimensional Bayesian inference for large sequential data sets","year":2015,"lang":"en","type":"article","venue":"2015 AGU Fall Meeting","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Bayesian probability; Computer science; Inference; Bayesian inference; Artificial intelligence; Data mining; Econometrics; Mathematics","score_opus":0.09047351892089694,"score_gpt":0.355440478570817,"score_spread":0.26496695964992006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592316541","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001969673,0.00037086997,0.9929263,0.0014666837,0.0007899462,0.00029925123,0.00008707609,0.00016535168,0.0019248532],"genre_scores_gemma":[0.24552558,0.00000353059,0.75342005,0.00055712287,0.00022094305,0.000017159566,0.000076062424,0.000019387426,0.00016017642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765784,0.00022309984,0.0003497435,0.00075379026,0.00043225364,0.0005832971],"domain_scores_gemma":[0.997919,0.00023693377,0.00013000716,0.0011550048,0.00022513364,0.00033387667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029863676,0.00022169082,0.00027450346,0.00008100051,0.00017064903,0.00018308051,0.001751853,0.00013331743,0.000002967176],"category_scores_gemma":[0.00040539124,0.00020046064,0.00007070815,0.00019325929,0.000027638573,0.000793535,0.00066257775,0.00018863619,0.000015129614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024539803,0.0008762792,0.00515027,0.0003539053,0.00032621273,0.00018285941,0.010382436,0.0009529078,0.010627691,0.41219977,0.2573116,0.30139068],"study_design_scores_gemma":[0.0016885145,0.00012767562,0.000087621636,0.00010886948,0.000034924808,0.000032318072,0.00002933309,0.8920003,0.00055004616,0.05914607,0.045649,0.0005452865],"about_ca_topic_score_codex":0.00019797076,"about_ca_topic_score_gemma":0.00040046577,"teacher_disagreement_score":0.8910474,"about_ca_system_score_codex":0.000037707356,"about_ca_system_score_gemma":0.00032603965,"threshold_uncertainty_score":0.81745476},"labels":[],"label_agreement":null},{"id":"W2593332226","doi":"10.1002/bimj.201600137","title":"Mixture Markov regression model with application to mosquito surveillance data analysis","year":2017,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Public Health; Public Health Agency of Canada; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Series (stratigraphy); Markov chain; Mixture model; Regression analysis; Markov model; Statistics; Time series; Expectation–maximization algorithm; Computer science; Mathematics; Maximum likelihood; Econometrics","score_opus":0.042777864680130416,"score_gpt":0.3494344604817212,"score_spread":0.3066565958015908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593332226","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009726577,0.00022257777,0.99296963,0.00498447,0.00013433918,0.000116053605,0.000022735727,0.000036801768,0.0005407606],"genre_scores_gemma":[0.32419294,0.00005276184,0.6751772,0.00021307994,0.0001672051,0.0000034787556,0.0000066570174,0.0000078498015,0.00017880478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978344,0.00012944799,0.00029368143,0.00069090805,0.0007015882,0.00035000648],"domain_scores_gemma":[0.99566394,0.00009399097,0.0003863727,0.0031528783,0.00023093131,0.00047186052],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017038807,0.00018282347,0.0003544895,0.001119055,0.0006404405,0.0010701097,0.0047074985,0.00011469819,0.00000481867],"category_scores_gemma":[0.0003666104,0.0001144764,0.00009735358,0.0033719882,0.000046555346,0.00078246964,0.0010656742,0.00029814764,0.000009541515],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058019054,0.0001032057,0.005495216,0.000006432622,0.00019864262,0.000040192146,0.00005675644,0.0004365253,0.0014538807,0.0024339142,0.008530354,0.98118687],"study_design_scores_gemma":[0.00038323988,0.000099011544,0.035928223,0.000020565825,0.0000849411,0.0000916086,0.0000016505552,0.95441014,0.00020280926,0.004134172,0.004324136,0.00031953392],"about_ca_topic_score_codex":0.000016877677,"about_ca_topic_score_gemma":0.000013103062,"teacher_disagreement_score":0.9808673,"about_ca_system_score_codex":0.000060999668,"about_ca_system_score_gemma":0.000094730494,"threshold_uncertainty_score":0.99996686},"labels":[],"label_agreement":null},{"id":"W2593882186","doi":"10.5539/ijsp.v6n2p134","title":"On Some Mixture Models for Over-dispersed Binary Data","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Applied mathematics; Binary number; Binomial (polynomial); Covariate; Quasi-likelihood; Mixture model; Computation; Binary data; Range (aeronautics); Count data; Statistics; Algorithm","score_opus":0.06257641469814794,"score_gpt":0.3540193746940929,"score_spread":0.29144295999594494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593882186","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004168557,0.00010160112,0.9910556,0.002626625,0.0010410806,0.000118872216,0.0006900289,0.000004924889,0.00019271181],"genre_scores_gemma":[0.22303359,0.000090066256,0.77635294,0.0003018766,0.00016870651,0.0000017838398,0.0000117380305,0.000004937171,0.00003437779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989534,0.000048946247,0.0003048223,0.00024734903,0.00033464437,0.000110816305],"domain_scores_gemma":[0.9980611,0.00034251146,0.00041951652,0.0006575368,0.00042797602,0.00009131999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010264359,0.000098985765,0.00017208759,0.000051951927,0.00014730921,0.00038590698,0.0019712106,0.000048584712,0.000005466323],"category_scores_gemma":[0.00058979023,0.00007626786,0.00004341486,0.000011927411,0.000084106614,0.0009983925,0.00038493378,0.00014970583,3.349491e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009957637,0.00008716577,0.000062634565,0.000016803077,0.00005365047,0.000021292168,0.00008999057,0.000082828796,0.00006289569,0.8948758,0.0035597114,0.100987606],"study_design_scores_gemma":[0.00049719156,0.00014228618,0.0013637263,0.00003167707,0.00000926023,0.000018024415,9.02249e-7,0.21862112,0.000025802618,0.77843195,0.0007898862,0.00006818991],"about_ca_topic_score_codex":0.000012384906,"about_ca_topic_score_gemma":0.0000051671277,"teacher_disagreement_score":0.21886504,"about_ca_system_score_codex":0.000033073196,"about_ca_system_score_gemma":0.00010873908,"threshold_uncertainty_score":0.372131},"labels":[],"label_agreement":null},{"id":"W2594897147","doi":"10.1016/j.csda.2018.08.016","title":"Mixtures of generalized hyperbolic distributions and mixtures of skew-t distributions for model-based clustering with incomplete data","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Missing data; Skew; Imputation (statistics); Cluster analysis; Mixture model; Mathematics; Multivariate statistics; Expectation–maximization algorithm; Applied mathematics; Statistics; Algorithm; Computer science; Maximum likelihood","score_opus":0.0639664086196896,"score_gpt":0.34615312516069463,"score_spread":0.282186716541005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594897147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007434064,0.0001451047,0.9127948,0.00020815466,0.000032742908,0.00018715346,0.08585597,0.000023895684,0.000008733645],"genre_scores_gemma":[0.24824314,0.000010179345,0.724441,0.00005284924,0.000035635665,0.000008708591,0.02719633,0.00000815012,0.000004038713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798834,0.00013234523,0.00054551853,0.00072748883,0.00036811407,0.00023817246],"domain_scores_gemma":[0.9965102,0.0006356025,0.00036964135,0.0016638811,0.00069783174,0.00012284369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053791935,0.00020539503,0.0005175046,0.00022352334,0.00028595421,0.00010443593,0.0015143456,0.00005776604,0.000007657991],"category_scores_gemma":[0.00024220867,0.0001785368,0.000060968694,0.0009005922,0.0003917813,0.00031262217,0.00088025734,0.00007995407,3.5313394e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013307456,0.0003232309,0.0012573563,0.00022304775,0.0021547268,0.0000034219202,0.00018798248,0.08890806,0.000654414,0.8706842,0.007186172,0.028284295],"study_design_scores_gemma":[0.00048455273,0.0000675603,0.0024169201,0.000017755261,0.00088646123,0.0000024556543,7.7140214e-7,0.8750671,0.0001372934,0.12051386,0.00023079531,0.00017447765],"about_ca_topic_score_codex":0.00024962833,"about_ca_topic_score_gemma":0.00033309753,"teacher_disagreement_score":0.78615904,"about_ca_system_score_codex":0.000021840879,"about_ca_system_score_gemma":0.00024892643,"threshold_uncertainty_score":0.7280519},"labels":[],"label_agreement":null},{"id":"W2595579230","doi":"10.1214/17-aos1676","title":"Think globally, fit locally under the manifold setup: Asymptotic analysis of locally linear embedding","year":2018,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Mathematics; Manifold (fluid mechanics); Embedding; Applied mathematics; Regularization (linguistics); Nonlinear dimensionality reduction; Laplace transform; Kernel (algebra); Markov chain; Mathematical analysis; Statistics; Pure mathematics; Dimensionality reduction; Artificial intelligence; Computer science","score_opus":0.07745280808389232,"score_gpt":0.36894931015097293,"score_spread":0.2914965020670806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2595579230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002124621,0.00019141204,0.9936551,0.002233869,0.00014271375,0.00014191344,0.00014815503,0.000030549138,0.0013316638],"genre_scores_gemma":[0.45112303,0.000116100295,0.54562235,0.0027901502,0.000095223615,0.000001597784,0.0000053849594,0.000012856533,0.00023331103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979211,0.0002998337,0.0005408539,0.00029374706,0.0006005603,0.0003438731],"domain_scores_gemma":[0.9968412,0.00082826347,0.0003887848,0.0011429643,0.00071480527,0.00008398333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001797531,0.00019130894,0.00042191998,0.00012033699,0.00017815319,0.00008371286,0.0018694949,0.00007880525,0.00005055424],"category_scores_gemma":[0.00016909848,0.000111489295,0.00016423552,0.0010828595,0.00035476687,0.00012343617,0.00040989398,0.00016990933,0.000015668515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027686296,0.000072882474,0.000029548357,0.000030181722,0.00093540654,0.000006248455,0.0019078335,0.0052862144,0.00013685379,0.9621399,0.0064227837,0.023004472],"study_design_scores_gemma":[0.00012692023,0.00024372591,0.0025377346,0.00004241396,0.00041447056,0.000005312629,0.00011213793,0.7919691,0.0009112308,0.2031276,0.00033918614,0.00017015084],"about_ca_topic_score_codex":0.00012328767,"about_ca_topic_score_gemma":0.00007866245,"teacher_disagreement_score":0.7866829,"about_ca_system_score_codex":0.000012196621,"about_ca_system_score_gemma":0.00012824638,"threshold_uncertainty_score":0.45464015},"labels":[],"label_agreement":null},{"id":"W2597718168","doi":"10.1109/tsp.2017.2684747","title":"Time-Varying Mixtures of Markov Chains: An Application to Road Traffic Modeling","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain; Computer science; Markov process; Road traffic; Markov model; Algorithm; Mathematics; Statistics; Transport engineering; Engineering; Machine learning","score_opus":0.025900503285736624,"score_gpt":0.29939482234440695,"score_spread":0.27349431905867033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597718168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0148931965,0.00006720985,0.9838645,0.0002932422,0.0000879269,0.00025350708,0.0000038002265,0.00014192978,0.000394706],"genre_scores_gemma":[0.7367366,0.0000035131527,0.2629573,0.0001291802,0.00005102633,0.000034515364,5.2112233e-7,0.000016826476,0.000070510534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984897,0.00007746309,0.00031565595,0.0005359181,0.00030741794,0.0002738798],"domain_scores_gemma":[0.99877435,0.000026131247,0.00017767474,0.00070992927,0.00014936358,0.00016255413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005096928,0.00019663642,0.00024721381,0.00019534225,0.0008451035,0.00031159437,0.0009767631,0.0001095226,0.0000070846786],"category_scores_gemma":[0.000004320574,0.000188511,0.00009190481,0.00019291832,0.000054038483,0.0010917637,0.0000056004988,0.00022369214,0.000009343665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002449117,0.000087239045,1.0459097e-7,0.000030784606,0.0000074871805,0.0000010974501,0.00079049217,0.18838641,0.03261488,0.000051857824,0.0000019310191,0.7780032],"study_design_scores_gemma":[0.00019898528,0.000092998045,0.000003951568,0.00012218767,0.000016918319,0.0000073787414,0.000011329979,0.95558643,0.04296732,0.00077912176,0.00000728807,0.00020607252],"about_ca_topic_score_codex":0.000024965113,"about_ca_topic_score_gemma":0.0000058935084,"teacher_disagreement_score":0.77779716,"about_ca_system_score_codex":0.00003411614,"about_ca_system_score_gemma":0.00009908548,"threshold_uncertainty_score":0.7687256},"labels":[],"label_agreement":null},{"id":"W2600919970","doi":"10.5539/jmr.v9n2p65","title":"Asymptotic Properties of Longitudinal Weighted Averages for Strongly Mixing Data","year":2017,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Mixing (physics); Consistency (knowledge bases); Asymptotic distribution; Covariance; Random variable; Statistics; Normality; Variable (mathematics); Strong consistency; Applied mathematics; Mathematical analysis; Discrete mathematics; Estimator","score_opus":0.36781006797563237,"score_gpt":0.451736657608668,"score_spread":0.08392658963303562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600919970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036575988,0.00046029428,0.9611239,0.0009903951,0.00016467852,0.00020409317,0.00000503093,0.0000049194787,0.00047072684],"genre_scores_gemma":[0.3933467,0.000054355653,0.6062544,0.0000022246754,0.000117473355,0.0000021039873,2.1231133e-7,0.00000860159,0.00021393682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978136,0.00016042654,0.00055960094,0.00019452424,0.0009480186,0.00032383788],"domain_scores_gemma":[0.9960884,0.0004570379,0.00062655174,0.0016578552,0.0010576247,0.00011253164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008139506,0.000101078,0.00037452846,0.00023294016,0.00036052018,0.0004603151,0.0045439135,0.000060612925,0.000005271988],"category_scores_gemma":[0.0017069953,0.000066927634,0.00009510122,0.00008609229,0.00017083564,0.0009713228,0.0010692558,0.00035877668,0.0000021926594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000298213,0.002834961,0.0014408892,0.0069547165,0.0012301268,0.00024694754,0.010378698,0.0000742184,0.09697041,0.61839086,0.015335936,0.24584402],"study_design_scores_gemma":[0.0019686965,0.0010619868,0.0010571731,0.0025734967,0.000076382195,0.0003678891,0.00028279042,0.6033909,0.06923261,0.31867424,0.0009606745,0.00035320089],"about_ca_topic_score_codex":0.000006622115,"about_ca_topic_score_gemma":0.0000031526502,"teacher_disagreement_score":0.60331666,"about_ca_system_score_codex":0.00003249221,"about_ca_system_score_gemma":0.00028943727,"threshold_uncertainty_score":0.8443797},"labels":[],"label_agreement":null},{"id":"W2602475131","doi":"10.5539/ijsp.v6n3p9","title":"Convergence of the Nelson-Aalen Estimator in Competing Risks","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Convergence (economics); CONTEST; Mathematics; Simple (philosophy); Nonparametric statistics; Applied mathematics; Statistics; Econometrics; Mathematical economics; Economics","score_opus":0.04605266826985577,"score_gpt":0.34808468228733663,"score_spread":0.30203201401748087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602475131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076850496,0.000052091375,0.92099524,0.0010202426,0.0006981306,0.000052460462,0.00002801908,0.0000012650203,0.00030206115],"genre_scores_gemma":[0.5989231,0.000025644935,0.40099958,0.00002305047,0.00002297143,3.5911364e-7,8.339944e-8,0.0000011133342,0.000004070385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99910825,0.00009363488,0.00036319802,0.00009745709,0.00026728882,0.00007018743],"domain_scores_gemma":[0.99852586,0.00021694227,0.00059347827,0.00023118523,0.00039405865,0.000038495004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011070427,0.0000557027,0.00013620219,0.000029285535,0.00007363886,0.00010204371,0.0010688336,0.00002401999,0.0000062266354],"category_scores_gemma":[0.00082147575,0.000037547852,0.000034652734,0.00002286507,0.00014642744,0.00020393383,0.00025355653,0.00014851331,1.8905948e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029487344,0.000080884056,0.18701519,0.00003496259,0.00003163226,0.00002198894,0.0005410804,0.00009845216,0.00024149651,0.6716751,0.000083137995,0.14014663],"study_design_scores_gemma":[0.00028483948,0.000030444142,0.45269036,0.00008763838,0.000004264863,0.000036204096,0.0000045561883,0.03238985,0.00037536913,0.5139397,0.00010997534,0.000046832887],"about_ca_topic_score_codex":0.0000917125,"about_ca_topic_score_gemma":0.000021073032,"teacher_disagreement_score":0.5220726,"about_ca_system_score_codex":0.000023986153,"about_ca_system_score_gemma":0.00009684088,"threshold_uncertainty_score":0.19861767},"labels":[],"label_agreement":null},{"id":"W2602801322","doi":"10.1007/978-3-319-41573-4_18","title":"A Mixture of Variance-Gamma Factor Analyzers","year":2017,"lang":"en","type":"book-chapter","venue":"Contributions to statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"","keywords":"Bayesian information criterion; Mixture model; Generalized gamma distribution; Gamma distribution; Expectation–maximization algorithm; Mathematics; Variance (accounting); Inverse-gamma distribution; Statistics; Conditional variance; Cluster analysis; Conditional probability distribution; Normal-inverse Gaussian distribution; Gaussian; Applied mathematics; Inverse-chi-squared distribution; Probability distribution; Econometrics; Gaussian process; Maximum likelihood; Distribution fitting; Gaussian random field; Physics","score_opus":0.02107266566919008,"score_gpt":0.3120185771714803,"score_spread":0.2909459115022902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602801322","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.22077e-7,0.0003697046,0.9169121,0.00062589307,0.00065704715,0.0003800947,0.01973577,0.000057074467,0.061262242],"genre_scores_gemma":[0.00055138214,0.00012456244,0.80141014,0.00019314466,0.00019887795,0.000013848819,0.00015331274,0.00003064438,0.19732408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981422,0.000050043564,0.00050721783,0.0005658644,0.00036751837,0.00036716767],"domain_scores_gemma":[0.99611944,0.00030420616,0.0005543241,0.0016696103,0.0010536074,0.00029878612],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002730526,0.00037211776,0.0007311559,0.00021786291,0.00025633982,0.00016901174,0.0013737001,0.0003947661,0.00015275502],"category_scores_gemma":[0.0006768165,0.000361337,0.00016942377,0.000047195765,0.00013994076,0.00012621375,0.0003277397,0.0004214605,0.00008645756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005267521,0.0000118787575,0.0000010130877,0.000026784237,0.00009733783,0.000041388834,0.00008367611,0.000002968279,0.000050893017,0.8944821,0.02501254,0.080184154],"study_design_scores_gemma":[0.00029040416,0.00010946729,0.00007963167,0.00017256005,0.00011516948,0.000011788796,3.424477e-7,0.001818006,0.00012589808,0.5842114,0.41260725,0.00045806362],"about_ca_topic_score_codex":0.000017408345,"about_ca_topic_score_gemma":0.000028375403,"teacher_disagreement_score":0.3875947,"about_ca_system_score_codex":0.00014131962,"about_ca_system_score_gemma":0.0004948223,"threshold_uncertainty_score":0.99988383},"labels":[],"label_agreement":null},{"id":"W2603922505","doi":"","title":"Mixed-Effects Regression Trees for Clustered Data","year":2008,"lang":"fr","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Multivariate statistics; Tree (set theory); Computer science; Covariate; Regression; Expectation–maximization algorithm; Statistics; Regression analysis; Mathematics; Data mining; Maximum likelihood","score_opus":0.2157929693191104,"score_gpt":0.3500391561485351,"score_spread":0.13424618682942469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603922505","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027374804,0.009873436,0.971841,0.00821033,0.005144705,0.0006505272,0.00004541466,0.00012037765,0.0038405077],"genre_scores_gemma":[0.008787228,0.0005833823,0.9346217,0.001171675,0.00068466365,0.000024256258,0.000027898617,0.000025374653,0.05407382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974325,0.00037910594,0.0003339372,0.0009918638,0.0002709756,0.00059162325],"domain_scores_gemma":[0.9964295,0.0007327229,0.00012854818,0.00234232,0.00011561585,0.00025131067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000819865,0.00029825832,0.000395467,0.00007578287,0.00036697526,0.00013268311,0.002013799,0.00025040636,0.00003880908],"category_scores_gemma":[0.0002636569,0.00023139158,0.00013011268,0.00027308072,0.00016445077,0.0011874697,0.001194474,0.0001815076,0.00005574358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016530521,0.00011096342,0.00001817123,0.00011200124,0.00002158246,0.000056599474,0.0003492665,0.0000026082437,0.00028171038,0.1522086,0.23032342,0.61649853],"study_design_scores_gemma":[0.0015647879,0.00038530875,0.0009915086,0.00041406392,0.0000604903,0.0003669625,0.000008404156,0.6329661,0.005847329,0.059722427,0.29710653,0.00056609925],"about_ca_topic_score_codex":0.00009871302,"about_ca_topic_score_gemma":0.00007723273,"teacher_disagreement_score":0.6329635,"about_ca_system_score_codex":0.000029996912,"about_ca_system_score_gemma":0.00016537853,"threshold_uncertainty_score":0.9435874},"labels":[],"label_agreement":null},{"id":"W2604188292","doi":"10.1002/sim.7289","title":"Correcting covariate‐dependent measurement error with non‐zero mean","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Biotechnology Research Institute; McGill University","funders":"","keywords":"Covariate; Statistics; Observational error; Extrapolation; Regression; Imputation (statistics); Econometrics; Calibration; Standard error; Mathematics; Computer science; Missing data","score_opus":0.07450561637566287,"score_gpt":0.3482761329384653,"score_spread":0.27377051656280244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604188292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022540806,0.00006293228,0.9893817,0.0010431723,0.0012128985,0.00023385473,0.0000069460284,0.00003333508,0.0077997963],"genre_scores_gemma":[0.40224364,0.0000087428125,0.5971445,0.00024740925,0.00009111748,0.000011565094,0.0000016213412,0.0000109995635,0.00024039147],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979015,0.00011465624,0.00033437123,0.00044341266,0.00085587794,0.00035016015],"domain_scores_gemma":[0.99812835,0.00014562496,0.0002830374,0.0010442255,0.0002552414,0.0001434927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028198091,0.0001922254,0.00035840392,0.00010190757,0.00029917576,0.00010512158,0.0009891471,0.000054393506,0.000027670618],"category_scores_gemma":[0.0007565232,0.00013697312,0.000013441244,0.000094838004,0.00016175091,0.0001599963,0.00017868479,0.00031347232,0.000007799933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000790219,0.00013920642,0.0023433494,0.00012877813,0.00008475825,0.00088461215,0.008792831,0.00010565214,0.00092760794,0.34637877,0.0087878425,0.6313476],"study_design_scores_gemma":[0.012894093,0.0024698323,0.04454056,0.0026213957,0.00021221238,0.00043398503,0.00047874136,0.27560815,0.0025289669,0.654564,0.0019885716,0.0016594598],"about_ca_topic_score_codex":0.00069058244,"about_ca_topic_score_gemma":0.0010345057,"teacher_disagreement_score":0.62968814,"about_ca_system_score_codex":0.00011501832,"about_ca_system_score_gemma":0.00013759293,"threshold_uncertainty_score":0.55856013},"labels":[],"label_agreement":null},{"id":"W2604726822","doi":"10.1007/s10489-017-0909-0","title":"Proportional data modeling via entropy-based variational bayes learning of mixture models","year":2017,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Bayes' theorem; Entropy (arrow of time); Machine learning; Artificial intelligence; Applied mathematics; Bayesian probability; Thermodynamics; Mathematics","score_opus":0.06701788626964093,"score_gpt":0.3102828004910845,"score_spread":0.24326491422144353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604726822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000116026415,0.000108592685,0.99579835,0.0004928436,0.0001702321,0.00021878368,0.00001246338,0.000076959084,0.0030057284],"genre_scores_gemma":[0.50896174,0.000020173633,0.49078584,0.00009125309,0.00006290171,0.000012761923,0.000026294343,0.000008865175,0.000030200517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787056,0.000064328306,0.0004656254,0.0007477642,0.0005486886,0.00030304084],"domain_scores_gemma":[0.9971615,0.00011908977,0.00042403376,0.0019900643,0.00020269098,0.00010262783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001085117,0.0002071287,0.0002664193,0.000086163935,0.00044939647,0.00020768995,0.0033372866,0.00012548525,0.000039368733],"category_scores_gemma":[0.00009052706,0.00018860157,0.00006596653,0.00009880952,0.000110891386,0.00081636803,0.0008150493,0.00033148608,0.000015564494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014821567,0.00005438469,0.00001794977,0.000021520415,0.000019346548,0.0000021081053,0.00013185672,0.16261317,0.0020594073,0.7540583,0.000038623926,0.08096853],"study_design_scores_gemma":[0.000061732215,0.00001613248,0.000010502116,0.000019108422,0.000008645371,0.0000027567144,0.0000025067432,0.6866,0.0045885383,0.30845186,0.000093972274,0.00014420871],"about_ca_topic_score_codex":0.00004520974,"about_ca_topic_score_gemma":0.000001951115,"teacher_disagreement_score":0.5239869,"about_ca_system_score_codex":0.000024692557,"about_ca_system_score_gemma":0.00023682034,"threshold_uncertainty_score":0.7690949},"labels":[],"label_agreement":null},{"id":"W2610828927","doi":"","title":"Bivariate Asymptotics for Striped Plane Partitions","year":2009,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo; Carleton University","funders":"","keywords":"Mathematics; Colored; Partition (number theory); Multivariate normal distribution; Plane (geometry); Combinatorics; Bivariate analysis; Gaussian; Standard deviation; Equivalence (formal languages); Discrete mathematics; Geometry; Multivariate statistics; Statistics; Physics","score_opus":0.022499835173827677,"score_gpt":0.28729518463338855,"score_spread":0.26479534945956085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610828927","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001288463,0.00002055468,0.98317325,0.0039421236,0.00017672725,0.00014894598,0.000005304277,0.00015755574,0.012246712],"genre_scores_gemma":[0.094815396,0.0000051084457,0.90223604,0.0016823583,0.00007426224,0.0000065646623,0.000003850336,0.0000026896478,0.0011737279],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993674,0.000026040912,0.0001279117,0.00019605385,0.000078730336,0.0002038385],"domain_scores_gemma":[0.999468,0.00007709945,0.000029304385,0.0003046659,0.00004168105,0.0000792067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019601459,0.00007489055,0.000097751916,0.000041440893,0.00008385656,0.00008892326,0.00030439592,0.00004521446,0.0000142107865],"category_scores_gemma":[0.000025217128,0.000060752667,0.000049450096,0.0001352911,0.000007604793,0.00016750011,0.000022168715,0.000046359528,0.000013615144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018089916,0.000031887037,0.0000022085444,0.0000013825936,0.0000036052363,0.0000011181943,0.000045637244,0.000015294061,0.0005914185,0.9262857,0.0050684153,0.06795153],"study_design_scores_gemma":[0.0004005083,0.00020107518,0.0004164889,0.0000056792337,0.000008464461,0.00000812478,0.0000019584575,0.06626053,0.0046034446,0.9152988,0.012629087,0.0001658224],"about_ca_topic_score_codex":0.000002337841,"about_ca_topic_score_gemma":0.0000017972902,"teacher_disagreement_score":0.094686545,"about_ca_system_score_codex":0.000008112834,"about_ca_system_score_gemma":0.000031136748,"threshold_uncertainty_score":0.24774218},"labels":[],"label_agreement":null},{"id":"W2612127537","doi":"10.71781/15059","title":"Probabilité de fixation dans des modèles de sélection avec consanguinité","year":2006,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Mathematics","score_opus":0.06243754209634114,"score_gpt":0.3402262050977441,"score_spread":0.2777886630014029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612127537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21687369,0.00033070776,0.7296565,0.00012090844,0.0004557857,0.0008207196,0.000021823436,0.000007918395,0.051711902],"genre_scores_gemma":[0.053097367,0.000029920562,0.8986474,0.00005015196,0.00021653109,0.00013600453,0.00025021654,0.00004024235,0.04753215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996795,0.00076704234,0.00058651395,0.00092765514,0.00027700907,0.00064678007],"domain_scores_gemma":[0.998213,0.00021414943,0.0004335471,0.00059234747,0.00034672322,0.00020025641],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015668046,0.00043325862,0.0004422316,0.00014850151,0.0005311474,0.0011694118,0.0012209592,0.00058023026,0.0002899938],"category_scores_gemma":[0.00024491095,0.0004590225,0.00016791595,0.0005139394,0.00017694721,0.00087595003,0.0001533822,0.0004195799,0.000099336256],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006114853,0.00029712045,0.0013441019,0.00015638921,0.000054345706,0.00004076945,0.0433786,0.000982548,0.025368834,0.017760117,0.00028225378,0.9102738],"study_design_scores_gemma":[0.0013161212,0.0005357082,0.04349471,0.0014583326,0.00040935894,0.00039300672,0.0011812958,0.36439463,0.28195933,0.2926177,0.010476029,0.0017637499],"about_ca_topic_score_codex":0.004072898,"about_ca_topic_score_gemma":0.009663725,"teacher_disagreement_score":0.90851,"about_ca_system_score_codex":0.0005089021,"about_ca_system_score_gemma":0.0012796769,"threshold_uncertainty_score":0.9998675},"labels":[],"label_agreement":null},{"id":"W2612562696","doi":"10.1109/icit.2017.7915513","title":"Unsupervised learning of finite mixtures using scaled dirichlet distribution and its application to software modules categorization","year":2017,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet distribution; Mixture model; Computer science; Expectation–maximization algorithm; Latent Dirichlet allocation; Artificial intelligence; Flexibility (engineering); Machine learning; Dirichlet process; Data mining; Pattern recognition (psychology); Algorithm; Topic model; Mathematics; Maximum likelihood; Statistics","score_opus":0.021673674061033862,"score_gpt":0.28504438282013955,"score_spread":0.2633707087591057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612562696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054784298,0.00007783601,0.94450206,0.00023335028,0.0000524122,0.0002059264,0.0000058941887,0.00006348812,0.00007473082],"genre_scores_gemma":[0.7034687,0.000011277218,0.29638746,0.00003253493,0.00002537142,0.00000743314,0.000013689159,0.0000048896673,0.00004866615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991543,0.00007157757,0.00018538276,0.0003048034,0.0001409798,0.00014295045],"domain_scores_gemma":[0.9991505,0.00005979156,0.00015778071,0.00039161934,0.00016055725,0.0000797095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030642026,0.000103919214,0.00015027984,0.000048549977,0.00036600765,0.00015115079,0.00037424732,0.000070864175,0.000001781739],"category_scores_gemma":[0.00031850406,0.00009170837,0.000027216518,0.00011922357,0.000023246332,0.0004325535,0.000211825,0.000070820395,0.0000018273134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022827237,0.00006559285,0.0054674824,0.00011773968,0.000023627197,0.000001683745,0.00081672275,0.006531163,0.14956717,0.25506955,0.000053096337,0.58226335],"study_design_scores_gemma":[0.00021890644,0.00003690677,0.011304842,0.000027251119,0.000011466995,0.0000024270867,0.000003859838,0.930183,0.046151124,0.011722599,0.0001738202,0.00016378978],"about_ca_topic_score_codex":0.000066036264,"about_ca_topic_score_gemma":0.0000044987337,"teacher_disagreement_score":0.9236518,"about_ca_system_score_codex":0.000017694398,"about_ca_system_score_gemma":0.000018706192,"threshold_uncertainty_score":0.37397587},"labels":[],"label_agreement":null},{"id":"W2612605702","doi":"10.1016/j.ecosta.2017.05.001","title":"A mixture of SDB skew- t factor analyzers","year":2017,"lang":"en","type":"article","venue":"Econometrics and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Mixture model; Factor (programming language); sort; Extension (predicate logic); Expectation–maximization algorithm","score_opus":0.0412038798764564,"score_gpt":0.28932226152436197,"score_spread":0.24811838164790556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612605702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002817596,0.00032649457,0.9931357,0.00016424173,0.00025720877,0.00005450006,0.00025865753,0.00000993819,0.0029756823],"genre_scores_gemma":[0.31593156,0.00020597804,0.6835509,0.000046776033,0.000022215578,0.0000010663375,0.000001995254,0.0000042306983,0.00023528491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992978,0.000021760252,0.00020266588,0.000235874,0.00008744016,0.00015444995],"domain_scores_gemma":[0.99879694,0.00018307264,0.00024824098,0.00058379455,0.000073517374,0.00011444626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022829574,0.00009747255,0.00022768181,0.00023238845,0.00017317184,0.00026219853,0.0005563623,0.000057999052,0.000027257247],"category_scores_gemma":[0.00036704214,0.00008773669,0.000032895518,0.00015554704,0.000074546464,0.00020780253,0.00017996486,0.00008721758,0.0000022097017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013056831,0.000019015786,0.0050466494,0.000026622076,0.000023699353,0.000007056499,0.00017232388,8.2991e-7,0.00001861713,0.5926077,0.00097531325,0.40110087],"study_design_scores_gemma":[0.0008197933,0.0002690033,0.22568755,0.000022905575,0.000035266363,0.000011813047,0.000010905748,0.12094932,0.0004048699,0.63155806,0.019655066,0.0005754693],"about_ca_topic_score_codex":0.000024684437,"about_ca_topic_score_gemma":0.000006566241,"teacher_disagreement_score":0.4005254,"about_ca_system_score_codex":0.000011098034,"about_ca_system_score_gemma":0.00003577576,"threshold_uncertainty_score":0.35777986},"labels":[],"label_agreement":null},{"id":"W2613072333","doi":"10.1016/j.spl.2018.08.012","title":"Three skewed matrix variate distributions","year":2018,"lang":"en","type":"preprint","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs","keywords":"Random variate; Skewness; Matrix (chemical analysis); Skew; Mathematics; Heavy-tailed distribution; Applied mathematics; Multivariate statistics; Work (physics); Statistics; Probability distribution; Computer science; Random variable; Physics; Materials science","score_opus":0.02665790199049816,"score_gpt":0.2976564342735646,"score_spread":0.2709985322830664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613072333","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005802489,0.000050415387,0.98689795,0.0062524825,0.0020633934,0.0010826506,0.0024419639,0.00037443102,0.0002564925],"genre_scores_gemma":[0.0011420283,0.00001312598,0.99707985,0.00094198575,0.00035725036,0.0001507791,0.00024928403,0.000033439355,0.000032230546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958311,0.00048901205,0.0007676086,0.0016188285,0.00055225746,0.0007411949],"domain_scores_gemma":[0.99588835,0.0004609105,0.00038492822,0.002704618,0.00030034865,0.00026083682],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001334742,0.00056180975,0.0006294747,0.00011098625,0.00029438682,0.0005642823,0.0021547123,0.00034579472,0.00006350872],"category_scores_gemma":[0.0006084168,0.0005496725,0.00021150001,0.0002715455,0.0004361492,0.00016384556,0.0023876282,0.0010204162,0.00011024804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008548309,0.000093851435,0.00007083379,0.0002573377,0.000057876146,0.000026057474,0.00019595867,0.000006479974,0.00032450617,0.96319747,0.024053179,0.011707888],"study_design_scores_gemma":[0.0001919019,0.000040752915,0.0011552379,0.00006484767,0.00006495595,0.0000085172305,5.5571963e-8,0.0150434,0.00018092358,0.9812911,0.0013895836,0.0005686861],"about_ca_topic_score_codex":0.00016442391,"about_ca_topic_score_gemma":0.00007531078,"teacher_disagreement_score":0.022663595,"about_ca_system_score_codex":0.0003367074,"about_ca_system_score_gemma":0.00039740262,"threshold_uncertainty_score":0.9996955},"labels":[],"label_agreement":null},{"id":"W2614013743","doi":"10.1080/00031305.2018.1459315","title":"Simple Measures of Individual Cluster-Membership Certainty for Hard Partitional Clustering","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simple (philosophy); Cluster (spacecraft); Cluster analysis; Mathematics; Certainty; Econometrics; Statistics; Computer science; Philosophy; Epistemology","score_opus":0.07860951827381393,"score_gpt":0.33514756504687654,"score_spread":0.2565380467730626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614013743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004583224,0.000014739172,0.9932465,0.0007873701,0.0001559372,0.0002375694,0.00018618812,0.000044368557,0.00074411085],"genre_scores_gemma":[0.53527075,0.0000014170022,0.46313074,0.0013576833,0.00016560941,0.000025687084,0.000007043264,0.00000917378,0.00003188822],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853355,0.0002621711,0.00026998174,0.00027269518,0.0003251782,0.00033643137],"domain_scores_gemma":[0.9982967,0.0007203399,0.0002762167,0.00044240043,0.00017869016,0.00008566432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097247295,0.00013447419,0.000263083,0.000058769587,0.00020610809,0.00007880863,0.00082801015,0.000019851346,0.000018791286],"category_scores_gemma":[0.00020710762,0.000099265024,0.00006830096,0.00025866958,0.00055607565,0.00010013545,0.00018402512,0.00008262629,0.0000067628785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015472523,0.00005784723,0.00024239915,0.000033403503,0.000119746255,0.0000021389612,0.0038214917,0.000088534776,0.00069430546,0.28449425,0.014631437,0.69565976],"study_design_scores_gemma":[0.0012451089,0.0019983447,0.037733957,0.00006376797,0.00015187876,0.00003101851,0.0005653207,0.22243766,0.0036291075,0.71727884,0.014110774,0.00075419195],"about_ca_topic_score_codex":0.0001747403,"about_ca_topic_score_gemma":0.00019098756,"teacher_disagreement_score":0.6949055,"about_ca_system_score_codex":0.000022168451,"about_ca_system_score_gemma":0.000082638006,"threshold_uncertainty_score":0.40479103},"labels":[],"label_agreement":null},{"id":"W2616848787","doi":"","title":"An Affine-Invariant Multivariate Sign Test for Cluster Correlated Data","year":2002,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Mathematics; Test statistic; Sign test; Statistic; Statistics; Multivariate statistics; Univariate; F-test; Affine transformation; Invariant (physics); Multivariate normal distribution; Chi-square test; Statistical hypothesis testing; Mann–Whitney U test; Wilcoxon signed-rank test; Geometry","score_opus":0.0732033049180199,"score_gpt":0.31192257388022704,"score_spread":0.23871926896220713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616848787","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003367783,0.000045897606,0.99120635,0.0019653246,0.00037410998,0.00041402926,0.00003504214,0.00028257314,0.0056430176],"genre_scores_gemma":[0.06181124,0.000006643105,0.932545,0.0016208047,0.00014092427,0.000017096381,0.00002639415,0.000018305373,0.003813579],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983602,0.00012374691,0.00026523962,0.0007418278,0.00014740443,0.00036153704],"domain_scores_gemma":[0.99715084,0.0005230471,0.00007410764,0.0020029375,0.000080878024,0.00016817631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007696955,0.00017940275,0.00019722697,0.00006689496,0.00013486393,0.00023583077,0.0020358663,0.0001214452,0.00016189231],"category_scores_gemma":[0.00020983949,0.0001380158,0.00004259264,0.00023963096,0.000023174158,0.0010259454,0.0003888471,0.0001275739,0.00007688126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002172698,0.0009617563,0.00006561375,0.000026814809,0.00005690116,0.000025575211,0.0012333804,0.00017185246,0.009047374,0.23243472,0.102776416,0.65317786],"study_design_scores_gemma":[0.00081671553,0.0001561523,0.00008098224,0.0000088078,0.000013183398,0.000018952915,0.0000030115043,0.9840271,0.00042265168,0.006742493,0.0074750697,0.00023490342],"about_ca_topic_score_codex":0.000046817135,"about_ca_topic_score_gemma":0.00001720105,"teacher_disagreement_score":0.98385525,"about_ca_system_score_codex":0.000014361193,"about_ca_system_score_gemma":0.000022184022,"threshold_uncertainty_score":0.5628121},"labels":[],"label_agreement":null},{"id":"W2619498682","doi":"10.5539/jmr.v9n3p80","title":"Minimum Hellinger Distance Estimation of a Univariate GARCH Process","year":2017,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Hellinger distance; Estimator; Autoregressive conditional heteroskedasticity; Asymptotic distribution; Univariate; Minimum-variance unbiased estimator; Applied mathematics; Statistics; Convergence (economics); Mixing (physics); Process (computing); Econometrics; Mathematical optimization; Volatility (finance); Computer science","score_opus":0.12927333386195844,"score_gpt":0.45988664460803064,"score_spread":0.3306133107460722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619498682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027817555,0.00014225839,0.96853805,0.00093193346,0.000111253124,0.00011603373,9.4208866e-7,0.0000047052927,0.002337247],"genre_scores_gemma":[0.45374075,0.00004680456,0.54585475,0.0000037238058,0.000046077792,0.0000015463856,5.0805554e-8,0.000006529429,0.00029979358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774563,0.00017675974,0.00054162054,0.0001322947,0.0011418636,0.00026182595],"domain_scores_gemma":[0.9967761,0.00047005914,0.00074693613,0.00078496436,0.0011036104,0.00011834202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006641544,0.000086070904,0.00030241613,0.0002424249,0.00024522335,0.00029263014,0.0020977727,0.0000642679,0.000007750206],"category_scores_gemma":[0.0012430045,0.00006327248,0.0000851442,0.0001800211,0.00015653222,0.00058577413,0.00021340253,0.00042431947,0.0000051008237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009493754,0.0012776526,0.00011148507,0.002511388,0.00015078312,0.00018046546,0.01857346,0.0010548554,0.009204558,0.78798485,0.0011770858,0.17767847],"study_design_scores_gemma":[0.00031634944,0.00015748797,0.000081333565,0.00047754296,0.0000070278415,0.000056776993,0.000067862034,0.33170387,0.009738149,0.6572245,0.00009477005,0.000074331976],"about_ca_topic_score_codex":0.00000351961,"about_ca_topic_score_gemma":0.0000010880553,"teacher_disagreement_score":0.4259232,"about_ca_system_score_codex":0.000035486482,"about_ca_system_score_gemma":0.00027608918,"threshold_uncertainty_score":0.38982186},"labels":[],"label_agreement":null},{"id":"W2624988516","doi":"10.22237/jmasm/1241136240","title":"Quantifying Bimodality Part 2: A Likelihood Ratio Test for the Comparison of a Unimodal Normal Distribution and a Bimodal Mixture of Two Normal Distributions. Bruno D. Zumbo is","year":2009,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Dalhousie University","funders":"","keywords":"Bimodality; Mathematics; Statistics; Maximum likelihood; Distribution (mathematics); Normal distribution; Mathematical analysis; Physics","score_opus":0.045293750402697536,"score_gpt":0.3878912138193276,"score_spread":0.3425974634166301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624988516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020043617,0.00059760583,0.9945928,0.0012523882,0.00017833347,0.0004213684,0.0008716243,0.00001675069,0.00006478498],"genre_scores_gemma":[0.47897696,0.00002164011,0.5208223,0.000072372546,0.0000790729,0.0000073561346,0.000012403108,0.0000064377195,0.0000014541544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965639,0.0005287099,0.0014893675,0.00037576284,0.00057283003,0.00046940925],"domain_scores_gemma":[0.99348134,0.004161502,0.0011031115,0.00045800387,0.0005378781,0.0002581372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042262427,0.00030229113,0.0009622812,0.00009489862,0.00026932269,0.00011941922,0.00068336213,0.00017418757,0.000007807213],"category_scores_gemma":[0.0008745553,0.00021555404,0.00021998961,0.0004041339,0.00027380555,0.0002713928,0.00013646354,0.000593707,2.0875402e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027513833,0.00041720417,0.00035196304,0.00007853633,0.00008242799,0.000002362749,0.0005575657,0.00010179692,0.020975586,0.43637678,0.0003392382,0.5404414],"study_design_scores_gemma":[0.0018560556,0.0007723923,0.009063369,0.00007252396,0.00028238425,0.000060985683,0.000047930378,0.5657012,0.03045633,0.39112082,0.00028516108,0.00028084777],"about_ca_topic_score_codex":0.000014353769,"about_ca_topic_score_gemma":0.0000045208208,"teacher_disagreement_score":0.5655994,"about_ca_system_score_codex":0.0000627687,"about_ca_system_score_gemma":0.0002917174,"threshold_uncertainty_score":0.8790039},"labels":[],"label_agreement":null},{"id":"W2625544043","doi":"10.46298/dmtcs.2429","title":"A product formula for the TASEP on a ring","year":2014,"lang":"fr","type":"article","venue":"Discrete Mathematics & Theoretical Computer Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Vetenskapsrådet","keywords":"Mathematics; Combinatorics; Conjecture; Permutation (music); Order (exchange); Product (mathematics); Ring (chemistry); Geometry; Physics","score_opus":0.027018339656616354,"score_gpt":0.29958761489255353,"score_spread":0.27256927523593716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625544043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022485112,0.0004065538,0.9672396,0.018827073,0.002884056,0.0013091728,0.000016482121,0.00012570927,0.008966503],"genre_scores_gemma":[0.21129149,0.000018269693,0.7855946,0.001741333,0.0009195594,0.00008275462,0.0000010928785,0.00003847417,0.00031242744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99482924,0.00032955548,0.0007238693,0.001429978,0.001208822,0.0014785569],"domain_scores_gemma":[0.99258655,0.0036949497,0.000277337,0.0025429612,0.0004293206,0.00046885214],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.009394513,0.0005648665,0.00059792475,0.00017087224,0.0014726283,0.0018738052,0.004355552,0.00012370695,0.0000411226],"category_scores_gemma":[0.001307157,0.00035638802,0.00035881117,0.0011294755,0.0047351304,0.0006845501,0.0013659797,0.00052653736,0.00008744209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010736637,0.00013045463,4.5006948e-7,0.00016652515,0.000018615558,0.000002541814,0.002260938,0.00018476944,0.000104496874,0.7930097,0.00032135253,0.20378943],"study_design_scores_gemma":[0.0002183094,0.00032074263,0.0000065879244,0.00024949873,0.000041533138,0.000042422704,0.000008814356,0.52092355,0.0011317016,0.4740181,0.0027626168,0.00027614334],"about_ca_topic_score_codex":0.0000044894696,"about_ca_topic_score_gemma":0.0000011547709,"teacher_disagreement_score":0.5207388,"about_ca_system_score_codex":0.00007851642,"about_ca_system_score_gemma":0.00020626141,"threshold_uncertainty_score":0.99988884},"labels":[],"label_agreement":null},{"id":"W2626895545","doi":"10.1111/rssc.12226","title":"Pattern–Mixture Models with Incomplete Informative Cluster Size: Application to a Repeated Pregnancy Study","year":2017,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute; National Institutes of Health","keywords":"Mixture model; Parity (physics); Cluster (spacecraft); Pregnancy; Latent variable; Statistics; Statistical model; Gestational age; Sample size determination; Mathematics; Computer science; Biology","score_opus":0.011031979333497833,"score_gpt":0.25961999533179203,"score_spread":0.2485880159982942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626895545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055421435,0.000013081732,0.99551606,0.0012766325,0.0002152412,0.0010548228,0.00028050016,0.000033226315,0.0010562482],"genre_scores_gemma":[0.38891175,0.000004897188,0.6101544,0.0005910681,0.00007360308,0.000047423535,0.0000026262503,0.000021461728,0.00019278297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971149,0.00019061408,0.000865937,0.0004047671,0.00095763226,0.0004661422],"domain_scores_gemma":[0.99621916,0.0004949352,0.001209697,0.0012256767,0.00052485446,0.0003257053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007796566,0.00037039132,0.00061515777,0.000026721063,0.0010517879,0.00071108463,0.002184027,0.00011614658,0.000016362797],"category_scores_gemma":[0.00024583278,0.00022657236,0.00012608335,0.00016321859,0.0002657649,0.0005724863,0.00083411403,0.0006841824,0.000007216177],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008531529,0.0008451721,0.00078742835,0.0002697202,0.00097455364,0.000092598006,0.029774133,0.010095905,0.00011111919,0.60265064,0.027438024,0.32610753],"study_design_scores_gemma":[0.0061293617,0.0032386752,0.05367469,0.00047229588,0.00051780685,0.00013277185,0.0013449676,0.45642367,0.00021327063,0.474367,0.001959177,0.0015263223],"about_ca_topic_score_codex":0.00006338656,"about_ca_topic_score_gemma":0.00005652397,"teacher_disagreement_score":0.44632778,"about_ca_system_score_codex":0.00014600769,"about_ca_system_score_gemma":0.00017802327,"threshold_uncertainty_score":0.9239353},"labels":[],"label_agreement":null},{"id":"W2646223782","doi":"10.1177/0962280217712088","title":"Functional principal component analysis of glomerular filtration rate curves after kidney transplant","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Functional principal component analysis; Renal function; Principal component analysis; Functional data analysis; Filtration (mathematics); Kidney transplant; Kidney transplantation; Function (biology); Kidney; Urology; Medicine; Internal medicine; Mathematics; Biology; Statistics","score_opus":0.11661366098704007,"score_gpt":0.494865302077494,"score_spread":0.37825164109045395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2646223782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065423985,0.00027530084,0.9920177,0.0051200488,0.00024929247,0.00022881507,0.000098771074,0.000015988624,0.001339886],"genre_scores_gemma":[0.08078938,0.00041546364,0.9180234,0.0004792407,0.000058587608,0.00008889962,0.000033551925,0.00000859421,0.00010284513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9898252,0.0060743648,0.0006855,0.0006595016,0.0021544087,0.00060106255],"domain_scores_gemma":[0.9916241,0.0061497013,0.00011384129,0.001053274,0.00029690852,0.000762172],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02684355,0.00015994576,0.0006110585,0.00052142097,0.00021887664,0.0001212154,0.001366159,0.00018998208,0.001552734],"category_scores_gemma":[0.01971471,0.00012691507,0.00013301248,0.0008217989,0.00088518724,0.00021588341,0.0003801362,0.0009575878,0.000008727785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022537482,0.0003517053,0.0025505784,0.00039526436,0.0003203244,0.0004270367,0.00029384278,0.000008623108,0.0016701156,0.49723294,0.0011106706,0.4954135],"study_design_scores_gemma":[0.00079132925,0.0001840287,0.3904789,0.000548959,0.0001522636,0.000008778088,0.000006380311,0.45690313,0.0015752849,0.14752534,0.0015446618,0.00028094798],"about_ca_topic_score_codex":0.00018525493,"about_ca_topic_score_gemma":0.00005653537,"teacher_disagreement_score":0.49513257,"about_ca_system_score_codex":0.00005959673,"about_ca_system_score_gemma":0.000542489,"threshold_uncertainty_score":0.99935997},"labels":[],"label_agreement":null},{"id":"W2669206880","doi":"10.1080/01621459.2018.1505626","title":"MCMC for Imbalanced Categorical Data","year":2018,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Computer science; Markov chain Monte Carlo; Bayesian probability; Approximate Bayesian computation; Computational complexity theory; Computation; Sample size determination; Sample (material); Bayesian inference; Logarithm; Machine learning; Data mining; Algorithm; Artificial intelligence; Mathematics; Statistics","score_opus":0.03988550071863376,"score_gpt":0.3559444286280251,"score_spread":0.31605892790939133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2669206880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046786113,0.000043773056,0.9901397,0.0065884967,0.0020924723,0.00019947495,0.0003308585,0.000016422217,0.000120933575],"genre_scores_gemma":[0.041989848,0.000046745987,0.9557546,0.00081476156,0.0011782659,0.000005989661,0.000020650574,0.000015813253,0.00017336858],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973801,0.00057078263,0.00067085074,0.00036700827,0.0007104604,0.00030081708],"domain_scores_gemma":[0.9934195,0.0015432396,0.0032497204,0.0010166899,0.0006470789,0.00012376689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025642894,0.0001827402,0.00065218436,0.0000628395,0.00011022261,0.00021593942,0.003181599,0.000116369745,0.0000038753155],"category_scores_gemma":[0.0037485175,0.000119502154,0.00018656136,0.00021799732,0.00009684758,0.00017028359,0.0015918124,0.0006836356,0.0000035987673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017948801,0.00031803866,0.0031354483,0.00010561083,0.0008172795,0.000014718891,0.0004263587,0.00007693718,0.00027320578,0.12617615,0.5332782,0.33519858],"study_design_scores_gemma":[0.00048080657,0.00037593336,0.024920631,0.00006267231,0.00028794014,0.000029516843,0.0000080657865,0.10376327,0.00007183424,0.8581315,0.011532544,0.00033523812],"about_ca_topic_score_codex":0.00003314348,"about_ca_topic_score_gemma":0.000004604166,"teacher_disagreement_score":0.7319554,"about_ca_system_score_codex":0.00049089355,"about_ca_system_score_gemma":0.00048088678,"threshold_uncertainty_score":0.59122556},"labels":[],"label_agreement":null},{"id":"W2679995671","doi":"10.1109/ccece.2017.7946595","title":"Spatially constrained non-Gaussian mixture model for image segmentation","year":2017,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Mitacs; Concordia University","keywords":"Image segmentation; Mixture model; Artificial intelligence; Pattern recognition (psychology); Markov random field; Expectation–maximization algorithm; Computer science; Scale-space segmentation; Pixel; Dirichlet distribution; Segmentation-based object categorization; Segmentation; Computer vision; Mathematics; Maximum likelihood; Statistics","score_opus":0.024063150813009422,"score_gpt":0.31349590563093477,"score_spread":0.28943275481792535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2679995671","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016004013,0.0000052694113,0.9722112,0.0036724284,0.00024281612,0.0004110886,0.000011509158,0.00007792657,0.023207752],"genre_scores_gemma":[0.14901696,0.0000028713714,0.8476709,0.00060569344,0.00007452106,0.00003680538,0.000004489878,0.000009138993,0.0025786094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906033,0.000021783339,0.00017277322,0.00036134,0.00013601845,0.0002477495],"domain_scores_gemma":[0.9988078,0.000035861805,0.00014511675,0.00080952654,0.00009602237,0.000105697625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034878834,0.00014157695,0.00016138134,0.00004114428,0.00041690975,0.000545616,0.0009059553,0.000083663464,0.000012191948],"category_scores_gemma":[0.000045331697,0.000114199756,0.000091247,0.00002715007,0.00006942046,0.0008173004,0.000134232,0.00007438985,0.0000081857825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017683444,0.0000609177,0.000021981621,0.000043565884,0.000030168236,0.000010592697,0.0011412244,0.00010849672,0.057084203,0.50904894,0.0049666846,0.42746553],"study_design_scores_gemma":[0.0005990942,0.000036810714,0.000091154485,0.000008884714,0.000007718591,0.0000052513983,0.0000035410253,0.88809425,0.012650962,0.098264344,0.000080639344,0.00015737579],"about_ca_topic_score_codex":0.000023148412,"about_ca_topic_score_gemma":0.000036790418,"teacher_disagreement_score":0.8879857,"about_ca_system_score_codex":0.00001659151,"about_ca_system_score_gemma":0.00011078275,"threshold_uncertainty_score":0.5261388},"labels":[],"label_agreement":null},{"id":"W2720946861","doi":"10.1007/s13571-017-0136-z","title":"Symmetrizing and Variance Stabilizing Transformations of Sample Coefficient of Variation from Inverse Gaussian Distribution","year":2017,"lang":"en","type":"article","venue":"Sankhya B","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Transformation (genetics); Gaussian; Variance (accounting); Inverse Gaussian distribution; Mathematics; Distribution (mathematics); Inverse; Normal-inverse Gaussian distribution; Applied mathematics; Sample (material); Variation (astronomy); Coefficient of variation; Normal distribution; Power (physics); Statistics; Mathematical analysis; Gaussian function; Physics; Geometry; Gaussian random field; Chemistry; Computational chemistry; Thermodynamics","score_opus":0.023160861039339325,"score_gpt":0.27091705871905053,"score_spread":0.24775619767971122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2720946861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024258386,0.00010025726,0.97438306,0.00024097993,0.00015798747,0.00012659842,0.00017406103,0.000017391809,0.0005412772],"genre_scores_gemma":[0.7297958,0.000032172575,0.27012217,0.000012444728,0.000014071678,0.000002570731,0.00001577416,0.0000024811004,0.0000025249678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992004,0.00007564363,0.00025917348,0.00018722394,0.00015619445,0.00012136946],"domain_scores_gemma":[0.99891484,0.00017737779,0.00026932938,0.00050776143,0.000079723875,0.000050965038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047583782,0.00007732496,0.00016805678,0.000048604048,0.00020128053,0.00007625579,0.00033370254,0.00005860496,0.0000062871018],"category_scores_gemma":[0.00025358336,0.00007269704,0.000040137304,0.00012601259,0.00007544381,0.00053109025,0.00007894647,0.00007128065,6.7749966e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002725708,0.00019905013,0.0052524526,0.0001719165,0.00006863773,0.000001884647,0.007821388,0.00022016572,0.021088038,0.7289207,0.0001242946,0.23610425],"study_design_scores_gemma":[0.0014654533,0.00015097567,0.26604506,0.00027578996,0.000079844394,0.000003577294,0.000072089766,0.5097606,0.042851508,0.17819026,0.0007317382,0.00037307272],"about_ca_topic_score_codex":0.00065398036,"about_ca_topic_score_gemma":0.000045553585,"teacher_disagreement_score":0.7055374,"about_ca_system_score_codex":0.000023270637,"about_ca_system_score_gemma":0.0000468027,"threshold_uncertainty_score":0.29644993},"labels":[],"label_agreement":null},{"id":"W2728522405","doi":"10.1016/j.jmva.2017.07.008","title":"Hidden truncation hyperbolic distributions, finite mixtures thereof, and their application for clustering","year":2017,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Truncation (statistics); Identifiability; Cluster analysis; Applied mathematics; Distribution (mathematics); Representation (politics); Convexity; Statistical physics; Mathematical optimization; Statistics; Mathematical analysis","score_opus":0.022795380687726845,"score_gpt":0.307280768250595,"score_spread":0.2844853875628682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728522405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007664583,0.00023593445,0.99049807,0.0013040715,0.0000836069,0.00011187299,0.000011875875,0.000010140744,0.00007985158],"genre_scores_gemma":[0.6991936,0.00007227809,0.30052158,0.00003660316,0.00011835421,0.000007536158,0.0000038919698,0.000004367833,0.00004179532],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991056,0.00009727285,0.00035000851,0.00019276139,0.00011547526,0.0001389189],"domain_scores_gemma":[0.99811625,0.0002290533,0.00078292814,0.00053227926,0.0002556326,0.00008383579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009672348,0.00011817017,0.00032817482,0.00018560115,0.00040251252,0.00031045545,0.00065491826,0.00006992003,0.0000017789871],"category_scores_gemma":[0.0002563174,0.00008147953,0.00025545567,0.00016767104,0.000031903688,0.0005297449,0.000112335685,0.00010656186,6.0506534e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006948643,0.00012852019,0.0017415236,0.00003180563,0.0017507444,0.0000028060724,0.0017901703,0.00051481754,0.052240912,0.027289089,0.000086121676,0.914354],"study_design_scores_gemma":[0.0008881655,0.000074040545,0.035287913,0.000026664642,0.0006566994,0.000016337604,0.000024222636,0.89034224,0.0056698895,0.06457296,0.0022288375,0.00021204236],"about_ca_topic_score_codex":0.0000838111,"about_ca_topic_score_gemma":0.000027927177,"teacher_disagreement_score":0.91414195,"about_ca_system_score_codex":0.00002829251,"about_ca_system_score_gemma":0.00003512758,"threshold_uncertainty_score":0.3322639},"labels":[],"label_agreement":null},{"id":"W2729038276","doi":"10.3103/s106653071702003x","title":"A unified approach to estimation of noncentrality parameters, the multiple correlation coefficient, and mixture models","year":2017,"lang":"en","type":"article","venue":"Mathematical Methods of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; Simons Foundation","keywords":"Mathematics; Estimator; Mean squared error; Statistics; Correlation coefficient; Constraint (computer-aided design); Applied mathematics; Mixing (physics)","score_opus":0.0657157664099738,"score_gpt":0.3546420469726016,"score_spread":0.2889262805626278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2729038276","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005474105,0.000022436367,0.997618,0.0002545657,0.000083859595,0.0004927521,0.000056836394,0.000017882845,0.00090621994],"genre_scores_gemma":[0.13442492,0.0000045658544,0.8654704,0.000042908152,0.000005379091,0.000013683423,0.0000025649122,0.00000759098,0.000027945669],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983224,0.00044821337,0.00047305741,0.00027962978,0.00028588128,0.0001907941],"domain_scores_gemma":[0.99625146,0.002091423,0.00041413592,0.0009784717,0.0001553499,0.00010914557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023524885,0.0001473811,0.00038928824,0.000044610097,0.00018594769,0.00011773226,0.0007214922,0.000087976645,0.0000012553159],"category_scores_gemma":[0.0027281074,0.0000905856,0.00004567676,0.00010787057,0.0002635908,0.00019114417,0.00026878598,0.0001417187,6.810111e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013216141,0.000104209386,0.000011001419,0.00018068319,0.00001561343,3.1247689e-7,0.001591984,0.005753251,0.00014537264,0.83182216,0.00006338645,0.16029884],"study_design_scores_gemma":[0.00011851558,0.0000365758,0.00022533421,0.00003065567,0.000021732265,0.0000028123,0.000013969776,0.5594884,0.0008388941,0.4391583,0.0000043642144,0.00006047014],"about_ca_topic_score_codex":0.000019581406,"about_ca_topic_score_gemma":7.0720637e-7,"teacher_disagreement_score":0.55373514,"about_ca_system_score_codex":0.000013027536,"about_ca_system_score_gemma":0.000030500118,"threshold_uncertainty_score":0.36939734},"labels":[],"label_agreement":null},{"id":"W2730102021","doi":"","title":"Multivariate Forests with Missing Mixed Outcomes","year":2013,"lang":"en","type":"article","venue":"Les Cahiers du GERAD","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Missing data; Multivariate statistics; Imputation (statistics); Multivariate analysis; Statistics; Random forest; Sample (material); Computer science; Econometrics; Mathematics; Artificial intelligence","score_opus":0.010695181670737778,"score_gpt":0.23141159970339228,"score_spread":0.22071641803265452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2730102021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107274584,0.00005751558,0.8873553,0.00359042,0.00023533402,0.00020413953,6.7999423e-7,0.00016735136,0.0011146225],"genre_scores_gemma":[0.35800874,0.0000011253388,0.64089364,0.0006190409,0.00003745015,0.000017099823,6.658753e-7,0.00001268329,0.0004095183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998751,0.00012478013,0.00017626301,0.00037850853,0.00020916607,0.00036026922],"domain_scores_gemma":[0.9989797,0.00016037344,0.000085570944,0.00053476985,0.000072707764,0.00016686985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020810883,0.000200885,0.00023961658,0.000084583226,0.00024161811,0.00027839356,0.0005344249,0.000115023075,0.00001830626],"category_scores_gemma":[0.00004587843,0.00013604791,0.000074212745,0.00019359238,0.000081797196,0.00054242794,0.000074811374,0.00021962893,0.000039709303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071740787,0.000058977083,0.014468801,0.000018496463,0.00006902418,0.00003755835,0.0022205627,0.000013448463,0.0010364709,0.60190207,0.0011701554,0.37899724],"study_design_scores_gemma":[0.0017658866,0.00011593382,0.4891545,0.00004955899,0.000027967699,0.00005201838,0.000037414327,0.03778762,0.0018779071,0.46611753,0.0021881757,0.00082549255],"about_ca_topic_score_codex":0.00017846428,"about_ca_topic_score_gemma":0.000019776717,"teacher_disagreement_score":0.4746857,"about_ca_system_score_codex":0.000042224987,"about_ca_system_score_gemma":0.000036923826,"threshold_uncertainty_score":0.5547873},"labels":[],"label_agreement":null},{"id":"W2731694362","doi":"","title":"Development and Application of Hidden Markov Models in the Bayesian Framework","year":2012,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Variable-order Bayesian network; Hidden Markov model; Computer science; Markov model; Artificial intelligence; Markov chain; Machine learning; Data science; Bayesian inference","score_opus":0.013666628543196394,"score_gpt":0.25625939198285824,"score_spread":0.24259276343966185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731694362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011522361,0.0012819736,0.95880985,0.00016359513,0.00007430232,0.00025844667,0.0000016237058,0.00001423551,0.027873589],"genre_scores_gemma":[0.43866223,0.000107829524,0.5607615,0.000010478563,0.000010492681,9.920451e-7,0.000011566081,0.000004805161,0.00043010295],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99910396,0.00010454904,0.00012417808,0.0002610186,0.00024464642,0.00016162002],"domain_scores_gemma":[0.9991156,0.00007383069,0.00026048732,0.00043936662,0.000058928377,0.000051807852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044978352,0.00014343762,0.00026667205,0.0000549666,0.00008081267,0.000012138316,0.000793546,0.00024321441,0.0000699568],"category_scores_gemma":[0.000005372592,0.00014172612,0.00005290702,0.00009627273,0.000032918237,0.00044855566,0.00008708908,0.00016197632,8.4648656e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023929644,0.00004709792,0.000049289087,0.00011793699,0.000021470249,0.0000013360125,0.09649052,0.0000014112607,0.0001062415,0.11320733,0.00002971759,0.7899037],"study_design_scores_gemma":[0.00146828,0.00018717867,0.78003424,0.0010879672,0.0002932948,0.000012969444,0.06368512,0.06909257,0.000720194,0.07901426,0.0026065016,0.0017974176],"about_ca_topic_score_codex":0.011087642,"about_ca_topic_score_gemma":0.021325935,"teacher_disagreement_score":0.7881063,"about_ca_system_score_codex":0.00008878757,"about_ca_system_score_gemma":0.00009710745,"threshold_uncertainty_score":0.9965323},"labels":[],"label_agreement":null},{"id":"W2732028845","doi":"","title":"MODIFIED LIKELIHOOD RATIO TEST FOR HOMOGENEITY IN A TWO-SAMPLE PROBLEM","year":2009,"lang":"en","type":"article","venue":"Statistica Sinica","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; York University","funders":"","keywords":"Homogeneity (statistics); Likelihood-ratio test; Statistics; Statistic; Mathematics; Null hypothesis; Limiting; Test statistic; Null distribution; Applied mathematics; Statistical hypothesis testing; Asymptotic distribution; Score test; Computer science; Estimator","score_opus":0.027275126479994912,"score_gpt":0.33271468729070847,"score_spread":0.30543956081071355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732028845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014110151,0.00005450278,0.99459016,0.0018425409,0.000090985755,0.0005945344,0.00020972168,0.00009534548,0.0023811324],"genre_scores_gemma":[0.28759384,0.0000069759453,0.7116314,0.000600736,0.00004832983,0.000052608506,0.000013119214,0.000007693392,0.000045321798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99827576,0.00011351015,0.00042247618,0.00054196833,0.000176277,0.00047002782],"domain_scores_gemma":[0.9973603,0.0017251108,0.00010229829,0.00056219945,0.00010153214,0.00014858719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070867833,0.00017632401,0.0002946645,0.00008687425,0.000108472195,0.00013712248,0.0005755568,0.0000553647,0.000008008287],"category_scores_gemma":[0.0008696197,0.00016418952,0.00006327007,0.00031630578,0.000039796312,0.00019813952,0.0000669911,0.00014774004,0.0000073094784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014885422,0.00021307077,0.00004952336,0.000012684924,0.0000046721034,0.000007974627,0.00021904732,0.000033390384,0.0006999246,0.7119522,0.0013397739,0.28545287],"study_design_scores_gemma":[0.0010440577,0.00035392857,0.0019116258,0.000021418708,0.000009401468,0.0000047703547,0.0000026711898,0.15719292,0.0003972092,0.8379772,0.00085060985,0.00023424905],"about_ca_topic_score_codex":0.00006248969,"about_ca_topic_score_gemma":0.00011275383,"teacher_disagreement_score":0.28745273,"about_ca_system_score_codex":0.00003977894,"about_ca_system_score_gemma":0.00021008757,"threshold_uncertainty_score":0.6695454},"labels":[],"label_agreement":null},{"id":"W2739069932","doi":"10.1002/sim.7397","title":"Dynamic classification using credible intervals in longitudinal discriminant analysis","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Belgian Federal Science Policy Office; Institut National de la Santé et de la Recherche Médicale; Medical Research Council; National Institute for Health and Care Research","keywords":"Linear discriminant analysis; False positive paradox; Bayesian probability; Multivariate statistics; Context (archaeology); Time point; Discriminant; Computer science; Confidence interval; Bayes' theorem; Statistics; Data mining; Set (abstract data type); Data set; Artificial intelligence; Machine learning; Mathematics","score_opus":0.10170984138903208,"score_gpt":0.42324950014943274,"score_spread":0.3215396587604007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739069932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008819102,0.000114518065,0.9889868,0.000955573,0.0003605447,0.00010368023,0.0000132838395,0.000011781351,0.00063474337],"genre_scores_gemma":[0.50864744,0.00004873907,0.49118853,0.000031510095,0.000019753228,0.000003842767,0.0000071495015,0.0000039934102,0.000049074835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853075,0.00012830546,0.00042678913,0.0003981151,0.0002643542,0.0002516773],"domain_scores_gemma":[0.99854445,0.00015528395,0.0002513126,0.000908399,0.00007014612,0.0000704116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013308435,0.00012952446,0.0003958727,0.00046615128,0.00012223845,0.0000830653,0.00080680195,0.00005444393,0.000020242345],"category_scores_gemma":[0.0006065754,0.00010445652,0.000029826373,0.0004065167,0.0001862979,0.00022945643,0.00016869941,0.00020140164,0.0000018595928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025412804,0.00015139488,0.09679378,0.00011338865,0.00011688525,0.00039257845,0.003729735,0.00031597473,0.0025324796,0.6537408,0.00038178536,0.24170578],"study_design_scores_gemma":[0.00025855008,0.0000323311,0.3293081,0.00008657495,0.000058930043,0.0000032808782,0.000033349374,0.5999577,0.000009926328,0.07015875,0.000013267615,0.00007927174],"about_ca_topic_score_codex":0.0008287589,"about_ca_topic_score_gemma":0.0017777983,"teacher_disagreement_score":0.5996417,"about_ca_system_score_codex":0.00012012026,"about_ca_system_score_gemma":0.000049060185,"threshold_uncertainty_score":0.42596135},"labels":[],"label_agreement":null},{"id":"W2739929871","doi":"10.1016/j.patcog.2018.02.025","title":"Finite mixtures of skewed matrix variate distributions","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random variate; Cluster analysis; Expectation–maximization algorithm; Mathematics; Data Matrix; Matrix (chemical analysis); Statistics; Multivariate normal distribution; Multivariate statistics; Applied mathematics; Algorithm; Random variable; Maximum likelihood; Chemistry","score_opus":0.02757265643079578,"score_gpt":0.2929697497666989,"score_spread":0.2653970933359031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739929871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007500691,0.00003675741,0.98968357,0.00034873726,0.00044908735,0.00011512681,0.000084828214,0.00008345328,0.0016977541],"genre_scores_gemma":[0.7353749,0.000014232571,0.26408288,0.00020184678,0.0002002634,0.000014285397,0.000044019558,0.0000070250107,0.000060514252],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99901277,0.00014841558,0.00023573871,0.00026130423,0.00014473319,0.00019703542],"domain_scores_gemma":[0.99916255,0.00011877041,0.00012518061,0.00032098612,0.00020906226,0.0000634376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032050986,0.00010856422,0.0001427367,0.000084478444,0.00009385949,0.000052959018,0.00029850646,0.000076161494,0.000113788024],"category_scores_gemma":[0.0000706972,0.000098865545,0.00007540127,0.0002474256,0.000056832934,0.00022341308,0.00009247369,0.00009022009,0.00016564426],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008713604,0.0000983907,0.0002988028,0.000034215223,0.000029116612,0.0000049630544,0.0004149765,5.0879896e-7,0.006452599,0.0041896687,0.000888044,0.98758],"study_design_scores_gemma":[0.0012143748,0.00050913275,0.011132265,0.0002538328,0.00008747959,0.000048792645,0.000007832075,0.05207835,0.25052926,0.6810327,0.0024037948,0.0007021697],"about_ca_topic_score_codex":0.000045269382,"about_ca_topic_score_gemma":0.0000075004914,"teacher_disagreement_score":0.98687786,"about_ca_system_score_codex":0.0000138150735,"about_ca_system_score_gemma":0.000024590798,"threshold_uncertainty_score":0.40316197},"labels":[],"label_agreement":null},{"id":"W2742228879","doi":"10.5539/ijsp.v6n5p53","title":"A Log-Density Estimation Methodology Applicable to Massive Bivariate Data","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Mathematics; Logarithm; Univariate; Applied mathematics; Polynomial; Density estimation; Probability density function; Function (biology); Marginal distribution; Random variable; Mathematical optimization; Statistics; Multivariate statistics; Mathematical analysis; Estimator","score_opus":0.11549405466960827,"score_gpt":0.39568903044678566,"score_spread":0.2801949757771774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742228879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023901854,0.000020168569,0.99157625,0.0049221497,0.00071269704,0.000107434986,0.00012548688,0.0000059048984,0.00013970697],"genre_scores_gemma":[0.10677877,0.000022236922,0.89285856,0.00021212315,0.00009962681,0.0000015202671,0.000004698219,0.000003028448,0.000019419489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988073,0.00017585489,0.00035429295,0.00026366184,0.00028651912,0.0001123526],"domain_scores_gemma":[0.99763477,0.00039993768,0.00049604836,0.00069658103,0.0006492894,0.00012339548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025586996,0.00008686276,0.00020993287,0.00006281533,0.00013383574,0.00037609914,0.0018923461,0.00004537121,0.000008162814],"category_scores_gemma":[0.0021415222,0.000071287206,0.000022862323,0.000027134989,0.00007949882,0.0005178578,0.000936844,0.00015097641,0.000002642764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053702915,0.00004604313,0.0008154593,0.0000113381075,0.000057728474,0.000039595736,0.00019758256,0.000090157715,0.00022968533,0.5386083,0.0008571942,0.4589932],"study_design_scores_gemma":[0.00025113617,0.000079224505,0.0166145,0.00001831915,0.000014314957,0.00008547122,0.0000016655035,0.082256734,0.00016754874,0.89956814,0.0008651432,0.00007777501],"about_ca_topic_score_codex":0.00011430253,"about_ca_topic_score_gemma":0.000029422778,"teacher_disagreement_score":0.4589154,"about_ca_system_score_codex":0.00003719183,"about_ca_system_score_gemma":0.00010687253,"threshold_uncertainty_score":0.36267325},"labels":[],"label_agreement":null},{"id":"W2744811808","doi":"10.2139/ssrn.1153335","title":"A Powerful Test of the Autoregressive Unit Root Hypothesis Based on a Tuning Parameter Free Statistic","year":2008,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Autoregressive model; Mathematics; Unit root; Augmented Dickey–Fuller test; Nonparametric statistics; Unit root test; Statistic; Test statistic; Statistics; Asymptotic distribution; Applied mathematics; Nuisance parameter; Distribution (mathematics); Statistical hypothesis testing; Econometrics; Mathematical analysis; Cointegration","score_opus":0.020176858817157268,"score_gpt":0.25646364223067963,"score_spread":0.23628678341352236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2744811808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004471983,0.0008324163,0.9911068,0.0013823914,0.0006348069,0.00029828344,0.000036347516,0.000045178174,0.0011917917],"genre_scores_gemma":[0.7122262,0.00054293283,0.28560436,0.00041772777,0.00028351278,0.00001944402,0.000002176986,0.000067866065,0.000835746],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953024,0.0008116251,0.0006071249,0.00060053344,0.0008196955,0.0018586578],"domain_scores_gemma":[0.99498427,0.0017494432,0.0010428249,0.0018349567,0.00024876185,0.00013975803],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0019688995,0.0004663311,0.00059379445,0.00029429738,0.00026752424,0.00016443364,0.0037840283,0.00028935974,0.000012175303],"category_scores_gemma":[0.0017922523,0.00031369206,0.00044651856,0.0003031974,0.000156136,0.00011283667,0.00075776037,0.00543199,0.0000053111903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023083217,0.0012581724,0.003497785,0.00024235382,0.0012111177,0.00026603037,0.0026342638,0.012242101,0.00077207707,0.40689516,0.0032856748,0.5674644],"study_design_scores_gemma":[0.0006831405,0.00048019434,0.0017678336,0.0005303644,0.00008521383,0.00043294957,0.000017724225,0.105832376,0.00044077125,0.88913596,0.00017084219,0.00042263983],"about_ca_topic_score_codex":0.000063971886,"about_ca_topic_score_gemma":0.0001427105,"teacher_disagreement_score":0.70775425,"about_ca_system_score_codex":0.00065264927,"about_ca_system_score_gemma":0.0075340387,"threshold_uncertainty_score":0.9999315},"labels":[],"label_agreement":null},{"id":"W2746526488","doi":"10.5539/ijsp.v6n5p119","title":"Correcting for Non-Sum to 1 Estimated Probabilities in Applications of Discrete Probability Models to Count Data","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Count data; Mathematics; Negative binomial distribution; Poisson distribution; Trinomial; Binomial distribution; Binomial (polynomial); Quasi-likelihood; Exponential family; Statistics; Sample size determination; Multinomial distribution; Exponential function; Applied mathematics; Combinatorics; Mathematical analysis","score_opus":0.09327166732444458,"score_gpt":0.3796261676091319,"score_spread":0.28635450028468734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2746526488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01887992,0.000021578122,0.97725606,0.0015755183,0.00032855367,0.0009933383,0.000839177,0.0000060115253,0.000099815006],"genre_scores_gemma":[0.38125563,0.0000056074978,0.61859125,0.000045124307,0.000041381103,0.000041017705,0.0000069789794,0.000004409632,0.000008593904],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982277,0.00006541295,0.0007708975,0.00039131742,0.00036971123,0.00017496991],"domain_scores_gemma":[0.9965484,0.0004983673,0.00054055837,0.0008663146,0.0013997521,0.0001465744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026848689,0.00013121899,0.00032554325,0.00011387801,0.0001145835,0.0002614238,0.0020603894,0.00004697022,0.000002064048],"category_scores_gemma":[0.001423995,0.00011248201,0.000038866692,0.000076397104,0.00011018467,0.00064913864,0.0007149687,0.00013870177,2.7829233e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000357031,0.00040536636,0.008811052,0.00034529218,0.00009323291,0.000005815335,0.003232243,0.0043924735,0.00024975205,0.40739837,0.0005133668,0.574196],"study_design_scores_gemma":[0.00037075288,0.00017376411,0.0077588223,0.00014276101,0.000011310235,0.0000190527,0.000017158976,0.18741135,0.00018153338,0.8035813,0.00021041321,0.00012176429],"about_ca_topic_score_codex":0.00019709385,"about_ca_topic_score_gemma":0.00027447322,"teacher_disagreement_score":0.57407427,"about_ca_system_score_codex":0.000104030456,"about_ca_system_score_gemma":0.00024842555,"threshold_uncertainty_score":0.45868835},"labels":[],"label_agreement":null},{"id":"W2748082833","doi":"10.1049/iet-ipr.2017.0407","title":"Image segmentation using a hierarchical student's‐ <i>t</i> mixture model","year":2017,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Qinglan Project of Jiangsu Province of China; Health and Medical Research Fund; Government of Jiangsu Province; National Natural Science Foundation of China","keywords":"Image segmentation; Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Computer vision; Image (mathematics); Scale-space segmentation","score_opus":0.0314236445247262,"score_gpt":0.3583204385572944,"score_spread":0.3268967940325682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748082833","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011467845,0.00021614686,0.9831904,0.0011354533,0.00017520125,0.00019963352,0.0000033308993,0.00015768742,0.0034542917],"genre_scores_gemma":[0.16319793,0.000009403897,0.83598006,0.00048058078,0.00013564141,0.000012096438,0.0000017664632,0.00002458548,0.00015791754],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981089,0.00009433503,0.00029051327,0.0006228377,0.00043537098,0.00044800492],"domain_scores_gemma":[0.9984437,0.000024704686,0.0003126061,0.00087428134,0.00018613528,0.00015852874],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00058898045,0.00025023532,0.00025702224,0.000086921005,0.0011810212,0.0031039626,0.0015252108,0.00010628331,0.000003896428],"category_scores_gemma":[0.00007015796,0.00022600366,0.00009558025,0.00012005512,0.00017586653,0.0039443867,0.0005642311,0.00038828945,0.000008674182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002081977,0.00019211296,0.00028744375,0.00020492896,0.000024222494,0.0001173818,0.004694908,0.00012653074,0.58534515,0.003008955,0.00047919454,0.40549833],"study_design_scores_gemma":[0.0004943134,0.000018821824,0.00024183761,0.00010392691,0.000024288207,0.000049837236,0.000022523462,0.9438202,0.012953189,0.04191846,0.000031232154,0.00032138056],"about_ca_topic_score_codex":0.00001236108,"about_ca_topic_score_gemma":0.0000024057658,"teacher_disagreement_score":0.94369364,"about_ca_system_score_codex":0.000057048554,"about_ca_system_score_gemma":0.00022169526,"threshold_uncertainty_score":0.9979309},"labels":[],"label_agreement":null},{"id":"W2750145144","doi":"10.48550/arxiv.1708.07804","title":"BAMBI: An R package for Fitting Bivariate Angular Mixture Models","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Univariate; Bivariate analysis; von Mises distribution; Bayesian probability; Bivariate data; Statistical inference; Statistics; Mathematics; Goodness of fit; Multivariate statistics; Computer science; von Mises yield criterion; Physics","score_opus":0.12094187546883035,"score_gpt":0.2356435467770471,"score_spread":0.11470167130821675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750145144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008542937,0.00015497065,0.98584616,0.00019398172,0.00095708034,0.00065221445,0.000078822755,0.00032223255,0.0032515908],"genre_scores_gemma":[0.6667782,0.000100679244,0.3307167,0.00016761248,0.00024718366,0.0000037170641,0.000036247435,0.00004192505,0.0019077015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967653,0.0002953042,0.0002648105,0.0019125777,0.0001194414,0.0006425338],"domain_scores_gemma":[0.99515337,0.00013067988,0.00052264973,0.0035643373,0.00028479547,0.0003441927],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007472573,0.00052165927,0.00061019836,0.0002468449,0.00059085846,0.00054988306,0.00417015,0.000692318,0.000007647713],"category_scores_gemma":[0.00007347839,0.0005708291,0.0004472826,0.0001787495,0.00008583199,0.0012719504,0.0021181873,0.00072661834,0.000010176219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003366283,0.00009873823,0.000059697308,0.00015440333,0.0001228312,0.00025670993,0.0005785801,0.02268974,0.00019737723,0.9662767,0.00037287816,0.009158659],"study_design_scores_gemma":[0.0003266877,0.00004192434,0.000046163565,0.000072430965,0.0000632443,0.000003397261,0.0000067330616,0.5042359,0.00022179271,0.49430183,0.00028008674,0.00039976058],"about_ca_topic_score_codex":0.00015982515,"about_ca_topic_score_gemma":0.00002644135,"teacher_disagreement_score":0.6582353,"about_ca_system_score_codex":0.00011763267,"about_ca_system_score_gemma":0.00026697412,"threshold_uncertainty_score":0.9996743},"labels":[],"label_agreement":null},{"id":"W2752903275","doi":"","title":"Convergence rates of a partition based Bayesian multivariate density estimation method.","year":2017,"lang":"en","type":"article","venue":"PubMed","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"","keywords":"Estimator; Density estimation; Rate of convergence; Bayesian probability; Smoothness; Mathematics; Multivariate kernel density estimation; Parametric statistics; Partition (number theory); Multivariate statistics; Applied mathematics; Bayes estimator; Mathematical optimization; Convergence (economics); Prior probability; Statistics; Algorithm; Computer science; Artificial intelligence; Variable kernel density estimation","score_opus":0.05028770916655146,"score_gpt":0.32337173532257024,"score_spread":0.2730840261560188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752903275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028344642,0.000014095316,0.9947062,0.00097636593,0.0003433751,0.00036382102,0.0000027764688,0.00005465182,0.00070424844],"genre_scores_gemma":[0.5098567,0.0000011592581,0.48989958,0.00007296311,0.000014780318,0.00011143774,9.1507087e-7,0.0000032467663,0.000039257764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987727,0.00026293696,0.0002222675,0.0003124543,0.00017921253,0.00025043447],"domain_scores_gemma":[0.99845773,0.00014629119,0.00031737564,0.0008488345,0.00011560508,0.000114187875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016061385,0.00011063988,0.00019813444,0.00005964529,0.00022111081,0.0001393828,0.00064576854,0.00006839275,0.0000057544917],"category_scores_gemma":[0.00053502404,0.0000998055,0.000070039605,0.000084076135,0.00005992849,0.0006033599,0.00012041419,0.00008031692,0.0000033415254],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018455863,0.00005750154,0.0020842534,0.00003824627,0.000016749706,0.0000059240997,0.0001309462,0.00023963994,0.0010683927,0.059599087,0.00009486235,0.9366459],"study_design_scores_gemma":[0.00028033718,0.000008457563,0.25094008,0.000009633428,0.000010674107,0.0000016119434,5.914594e-7,0.6364613,0.06529127,0.046852663,0.000037408143,0.00010594793],"about_ca_topic_score_codex":0.00015341138,"about_ca_topic_score_gemma":0.000012116526,"teacher_disagreement_score":0.93654,"about_ca_system_score_codex":0.000021330165,"about_ca_system_score_gemma":0.00003779207,"threshold_uncertainty_score":0.406995},"labels":[],"label_agreement":null},{"id":"W2756751105","doi":"10.1109/mwscas.2017.8052880","title":"Spatially constrained Generalized Dirichlet mixture model for image segmentation","year":2017,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Image segmentation; Dirichlet distribution; Markov random field; Expectation–maximization algorithm; Artificial intelligence; Mixture model; Computer science; Pattern recognition (psychology); Segmentation; Maximization; Mathematics; Computer vision; Algorithm; Mathematical optimization; Maximum likelihood; Statistics","score_opus":0.032984089151819634,"score_gpt":0.32302343615509427,"score_spread":0.2900393470032746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756751105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005026474,0.000017196433,0.98762435,0.0030560498,0.0002443103,0.00041372384,0.00001652155,0.000109774504,0.008015429],"genre_scores_gemma":[0.03628128,0.000008166967,0.9590375,0.0010865383,0.00008928803,0.000054109165,0.000008753937,0.000010784088,0.0034235818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901366,0.000041776457,0.00018666727,0.00036663417,0.00014687497,0.00024435783],"domain_scores_gemma":[0.99878764,0.000036676152,0.00015744839,0.00079464307,0.00012864257,0.000094973766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037870219,0.00014643856,0.00018312996,0.00003918767,0.00039475123,0.0005359865,0.0008753837,0.00007879362,0.000016238657],"category_scores_gemma":[0.000068927344,0.000117869735,0.00010199075,0.00002927192,0.000064670145,0.00069574703,0.00014347251,0.00006185698,0.000005378004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016439315,0.00004259524,0.00001401772,0.00002324795,0.00002766849,0.000006121755,0.00050410035,0.00015937063,0.067419074,0.77233094,0.0070957947,0.1523606],"study_design_scores_gemma":[0.00086541404,0.000025637542,0.000035948597,0.0000046761415,0.000009498714,0.0000036781394,0.0000013694261,0.86660206,0.013928794,0.11814978,0.00021418817,0.00015896595],"about_ca_topic_score_codex":0.000022770791,"about_ca_topic_score_gemma":0.000027173648,"teacher_disagreement_score":0.8664427,"about_ca_system_score_codex":0.00001679123,"about_ca_system_score_gemma":0.00008850725,"threshold_uncertainty_score":0.51685303},"labels":[],"label_agreement":null},{"id":"W2758319537","doi":"10.1177/0013164417719111","title":"Recommendations on the Sample Sizes for Multilevel Latent Class Models","year":2017,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Latent class model; Sample size determination; Statistics; Sample (material); Rule of thumb; Nested set model; Computer science; Model selection; Econometrics; Data mining; Mathematics; Algorithm","score_opus":0.4657980968857349,"score_gpt":0.4110614061339838,"score_spread":0.05473669075175114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758319537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00090321485,0.00006229416,0.8258319,0.16864838,0.00068179396,0.00029396,0.000015385918,0.000014341689,0.003548719],"genre_scores_gemma":[0.6427089,0.000034681107,0.35352576,0.0030580235,0.0001857965,0.00026979804,0.0000032732685,0.0000036718354,0.0002101295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903244,0.00008753361,0.00014969266,0.00033682943,0.00023256535,0.00016091237],"domain_scores_gemma":[0.9986386,0.00050821464,0.00009706865,0.00051846396,0.00015595816,0.0000817043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009958328,0.000103753126,0.00009412987,0.000019593515,0.0008100831,0.00021982667,0.0005848045,0.000046488407,0.000055202883],"category_scores_gemma":[0.00046604022,0.00005898724,0.0000568991,0.000021782655,0.00006113881,0.0001328984,0.00005893615,0.00010074649,0.0000065701706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009863841,0.00025237058,0.000034567678,0.0000022970842,0.000011634513,4.1167418e-8,0.00012069426,0.0000063449143,0.0000720485,0.8193682,0.01352469,0.16659723],"study_design_scores_gemma":[0.00026966288,0.00012984339,0.025609717,0.000023633886,0.000005034115,0.000001867537,0.0000050695603,0.008538443,0.00006374146,0.95115304,0.014083711,0.000116213196],"about_ca_topic_score_codex":0.000009636351,"about_ca_topic_score_gemma":0.0000037386503,"teacher_disagreement_score":0.64180565,"about_ca_system_score_codex":0.000027519074,"about_ca_system_score_gemma":0.000030499,"threshold_uncertainty_score":0.6230586},"labels":[],"label_agreement":null},{"id":"W2764305583","doi":"10.1002/jae.2685","title":"Bayesian parametric and semiparametric factor models for large realized covariance matrices","year":2019,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Parametric statistics; Wishart distribution; Covariance; Dirichlet process; Factor analysis; Dirichlet distribution; Nonparametric statistics; Inverse; Computer science; Applied mathematics; Semiparametric model; Mathematics; Bayesian probability; Econometrics; Statistics","score_opus":0.027752645643149672,"score_gpt":0.26035996120055255,"score_spread":0.23260731555740288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2764305583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01216165,0.0021626144,0.98145455,0.00014020967,0.000536717,0.0005291556,0.00003100979,0.000031318632,0.0029527633],"genre_scores_gemma":[0.46881294,0.00073991774,0.53003365,0.0002315646,0.00008291589,0.000008479637,0.0000010285244,0.000018395704,0.00007109068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772805,0.000045147466,0.00090776983,0.00048946484,0.00032255772,0.0005069888],"domain_scores_gemma":[0.9964847,0.0013813914,0.0010970813,0.0005069158,0.00022381812,0.00030608548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019840419,0.0002669959,0.0008164712,0.0030532759,0.00009648271,0.0003564054,0.0009728689,0.00020901457,0.00002264078],"category_scores_gemma":[0.00020812209,0.0002327734,0.00021598773,0.004363919,0.000018748631,0.00096366345,0.00016975736,0.00032825288,0.000009221741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019263079,0.00027031443,0.00088560145,0.0002282958,0.00021814961,0.00000879789,0.0004880127,0.0034572408,0.00011484659,0.78305376,0.0011094104,0.20997296],"study_design_scores_gemma":[0.0046650055,0.0005860606,0.001045906,0.000034295237,0.00007419309,0.00009441204,0.000044712677,0.5919171,0.0005514637,0.38858548,0.01171564,0.0006857258],"about_ca_topic_score_codex":0.0000023288628,"about_ca_topic_score_gemma":3.458798e-7,"teacher_disagreement_score":0.58845985,"about_ca_system_score_codex":0.0001202559,"about_ca_system_score_gemma":0.0001374613,"threshold_uncertainty_score":0.9492224},"labels":[],"label_agreement":null},{"id":"W2765657020","doi":"10.1007/s00180-017-0771-x","title":"Efficient computation of multivariate empirical distribution functions at the observed values","year":2017,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Empirical distribution function; Cumulative distribution function; Mathematics; F-distribution; Merge (version control); Computation; Multivariate normal distribution; Monte Carlo method; Algorithm; Multivariate stable distribution; Applied mathematics; Multivariate statistics; Computer science; Statistics; Probability distribution; Probability density function; Normal-Wishart distribution; Parallel computing","score_opus":0.08551688271772234,"score_gpt":0.3594477272368043,"score_spread":0.27393084451908195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765657020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013467086,0.000050881445,0.98413604,0.0010265189,0.00052711036,0.0001820781,0.0003866874,0.000041046067,0.0001825348],"genre_scores_gemma":[0.54176843,0.0000010314545,0.45782474,0.0000606972,0.00003805403,0.00000541162,0.00015997869,0.000005265851,0.0001363781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857783,0.00019630238,0.0003421561,0.00029196878,0.00041364797,0.00017808627],"domain_scores_gemma":[0.9979676,0.00070356834,0.00039530947,0.0004340988,0.0004262877,0.000073141724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048331922,0.00013179368,0.00017243047,0.000026085852,0.0011290273,0.00017865923,0.0005516374,0.000051378396,0.000008478588],"category_scores_gemma":[0.00037892562,0.00009941232,0.00006524093,0.00010054543,0.00024239693,0.00008507433,0.00035515847,0.00011242106,0.00002263561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026227432,0.00019246241,0.0009781481,0.000031961004,0.000059648773,0.000007356581,0.0007199837,0.43462083,0.00009001883,0.47698733,0.010155315,0.07613072],"study_design_scores_gemma":[0.0002813833,0.000034889177,0.12798491,0.000011933966,0.000015439797,0.0000060643774,0.0000041863923,0.75232756,0.00003433501,0.11900501,0.00020498747,0.00008931298],"about_ca_topic_score_codex":0.000035649355,"about_ca_topic_score_gemma":0.00000791512,"teacher_disagreement_score":0.52830136,"about_ca_system_score_codex":0.00008589828,"about_ca_system_score_gemma":0.00010214186,"threshold_uncertainty_score":0.8683679},"labels":[],"label_agreement":null},{"id":"W2766846309","doi":"10.1002/cjs.11345","title":"A two‐level directional model for dependence in circular data","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"von Mises distribution; Cluster analysis; Pooling; Hierarchical clustering; Statistics; Population; Statistical hypothesis testing; Mathematics; Computer science; Variation (astronomy); Data mining; von Mises yield criterion; Econometrics; Artificial intelligence; Engineering; Finite element method; Physics","score_opus":0.21770144183683135,"score_gpt":0.343091410151785,"score_spread":0.12538996831495366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766846309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010366756,0.00014361857,0.9974868,0.0005412745,0.00047838408,0.00006697789,0.0008551994,0.0000018120595,0.0003222073],"genre_scores_gemma":[0.13398318,0.000012486715,0.86562324,0.00014867168,0.00008387557,0.0000012516488,0.0000049255113,0.0000065385593,0.0001358045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991197,0.00003239487,0.0002655342,0.00017982174,0.00015494802,0.00024760683],"domain_scores_gemma":[0.99832976,0.00010691727,0.00025269564,0.00070705154,0.00023521454,0.0003683866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089926715,0.00008140554,0.00016504254,0.00014573819,0.00025354713,0.00028663452,0.0020491625,0.000039483617,0.000004077809],"category_scores_gemma":[0.00077091705,0.0000804593,0.00002649359,0.000042507934,0.00006277325,0.0006071378,0.00007249708,0.00017219043,8.548665e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009061273,0.00002045379,0.0017700829,0.00003284003,0.00003933347,0.00062471203,0.0005694029,0.0023449957,0.000083656865,0.59950656,0.0071847867,0.38781413],"study_design_scores_gemma":[0.00034539352,0.000017964647,0.0022845932,0.000030200597,0.000008691412,0.00011791664,0.0000028059478,0.7463322,0.000011782874,0.24975589,0.0010014577,0.00009109421],"about_ca_topic_score_codex":0.0016614256,"about_ca_topic_score_gemma":0.05374716,"teacher_disagreement_score":0.7439872,"about_ca_system_score_codex":0.00008651653,"about_ca_system_score_gemma":0.0023537755,"threshold_uncertainty_score":0.9635195},"labels":[],"label_agreement":null},{"id":"W2767631755","doi":"10.1007/s00357-019-9309-y","title":"Mixtures of Hidden Truncation Hyperbolic Factor Analyzers","year":2019,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Truncation (statistics); Cluster analysis; Factor (programming language); Gaussian; Applied mathematics; Computer science; Mixture model; Process (computing); Mathematics; Statistics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Physics","score_opus":0.05285534351087375,"score_gpt":0.3160797611992984,"score_spread":0.2632244176884247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767631755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03608747,0.00094007625,0.95881265,0.0014980682,0.0014858098,0.00019443569,0.000008430769,0.000017497683,0.00095554313],"genre_scores_gemma":[0.6941253,0.00032542986,0.30509079,0.000058031408,0.00024857343,0.0000028400166,0.000005381241,0.000012144702,0.00013148335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976392,0.00031643172,0.0009873605,0.00030531967,0.00059826614,0.00015345355],"domain_scores_gemma":[0.99541634,0.00015370447,0.0027112735,0.0008699754,0.0007480906,0.000100631216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087005354,0.00020966888,0.00058306614,0.0004726166,0.000030024896,0.000114937364,0.0013598935,0.00033747696,0.00001348668],"category_scores_gemma":[0.00016273466,0.00017018135,0.0003554904,0.0002492623,0.000041113042,0.0003699029,0.00017769133,0.00062503124,0.000006058878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077424935,0.0003152455,0.0018173935,0.0005119159,0.00040261634,0.0000061440874,0.0032151595,0.00048656994,0.17102072,0.05721246,0.003765258,0.7611691],"study_design_scores_gemma":[0.0022490644,0.00073491834,0.34636486,0.0016131904,0.00061362545,0.00018687063,0.00014321873,0.18028267,0.11934217,0.33827105,0.008574242,0.0016241033],"about_ca_topic_score_codex":0.000008159918,"about_ca_topic_score_gemma":8.07471e-7,"teacher_disagreement_score":0.75954497,"about_ca_system_score_codex":0.00012527856,"about_ca_system_score_gemma":0.0005506697,"threshold_uncertainty_score":0.6939794},"labels":[],"label_agreement":null},{"id":"W2768638255","doi":"10.1920/wp.cem.2019.1319","title":"Minimalist G-modelling: A comment on Efron","year":2019,"lang":"en","type":"report","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Economic and Social Research Council","keywords":"Computer science","score_opus":0.09588854122459677,"score_gpt":0.33411288515569804,"score_spread":0.23822434393110126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768638255","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000118272,0.00024113609,0.5879679,0.0027813732,0.0017011298,0.00023857756,0.0000066871016,0.00011279374,0.40694925],"genre_scores_gemma":[0.0006510905,0.00060910615,0.88862914,0.008306947,0.000509646,0.000032546017,0.000032015232,0.000054101514,0.10117541],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968693,0.00013557944,0.0004659079,0.0009765579,0.0011244445,0.00042817267],"domain_scores_gemma":[0.9973365,0.00016815319,0.0002712433,0.001830368,0.00023683421,0.00015688603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012656169,0.00043434007,0.000646351,0.0001947487,0.00007121406,0.00022240348,0.0014076796,0.00041592118,0.000073906136],"category_scores_gemma":[0.000023204548,0.00033625634,0.00028473418,0.00016038775,0.000025280051,0.0001152291,0.00039244213,0.00055237894,0.00029446767],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063080897,0.00011664444,0.000003620369,0.00013057681,0.00005592602,0.0000354716,0.00009573212,0.00011961698,0.0000056534054,0.1815753,0.7563522,0.061502934],"study_design_scores_gemma":[0.00015767459,0.00018189049,0.0000038940134,0.00016649769,0.000019883008,0.00002847372,0.0000012366262,0.054114684,0.00010206366,0.007607533,0.9371654,0.00045077712],"about_ca_topic_score_codex":0.00033132132,"about_ca_topic_score_gemma":0.000004294719,"teacher_disagreement_score":0.30577385,"about_ca_system_score_codex":0.0002612777,"about_ca_system_score_gemma":0.0007588529,"threshold_uncertainty_score":0.9999089},"labels":[],"label_agreement":null},{"id":"W2770641088","doi":"10.6084/m9.figshare.7859750","title":"Incremental Mixture Importance Sampling With Shotgun Optimization","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Shotgun; Sampling (signal processing); Computer science; Environmental science; Chemistry; Computer vision; Biochemistry","score_opus":0.04034452851986339,"score_gpt":0.28374037233654387,"score_spread":0.24339584381668047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770641088","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.36131e-8,0.0005673206,0.29272237,0.000047990965,0.00008894053,0.00017572213,0.70622724,0.000060471702,0.00010992873],"genre_scores_gemma":[3.3568202e-7,0.000018984849,0.34000134,0.000576113,0.00017158658,0.000083139385,0.65910465,0.000015733298,0.000028097831],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980677,0.0000941475,0.00026732497,0.0008067269,0.000424009,0.00034010282],"domain_scores_gemma":[0.99813795,0.00006493665,0.00028231295,0.0011970386,0.0001829824,0.00013477803],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009093659,0.00037018166,0.00035887485,0.000095622345,0.0001356682,0.00041423022,0.0012212665,0.0003420453,0.034691703],"category_scores_gemma":[0.00018423394,0.00031526835,0.00009383873,0.00044179393,0.000005803174,0.00035468242,0.00052272115,0.00052364386,0.00012349666],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023180546,0.000022339142,4.1120254e-7,0.00018800347,0.000026845568,0.00012211647,0.000010770902,0.00034883755,0.0000015536857,0.000013131866,0.9979082,0.0013554852],"study_design_scores_gemma":[0.000170462,0.000038500108,0.000006127338,0.0019791946,0.000019718733,0.00008267409,0.0000020448504,0.003359804,0.000050898314,0.000052691084,0.993748,0.0004898647],"about_ca_topic_score_codex":0.0000071398294,"about_ca_topic_score_gemma":0.000036033987,"teacher_disagreement_score":0.047278974,"about_ca_system_score_codex":0.00007200298,"about_ca_system_score_gemma":0.00030262393,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W2771761215","doi":"10.1186/s12859-019-2916-0","title":"A multivariate Poisson-log normal mixture model for clustering transcriptome sequencing data","year":2019,"lang":"en","type":"preprint","venue":"BMC Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Cluster analysis; Mixture model; Overdispersion; Markov chain Monte Carlo; Computer science; Multivariate statistics; Expectation–maximization algorithm; Context (archaeology); Poisson distribution; Count data; Data mining; Mathematics; Statistics; Biology; Artificial intelligence; Machine learning; Bayesian probability","score_opus":0.11826977902242625,"score_gpt":0.3252396361446816,"score_spread":0.20696985712225535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771761215","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004650167,0.0002085917,0.99317044,0.00025206746,0.0020066428,0.0017464933,0.0009964986,0.00034110763,0.0012316657],"genre_scores_gemma":[0.002961421,0.00004230287,0.9947747,0.00075554405,0.00020908151,0.00007713256,0.00048659625,0.00005697077,0.0006362276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964255,0.00009627538,0.001185022,0.00090190663,0.0005214958,0.00086976134],"domain_scores_gemma":[0.99438155,0.00021953681,0.00067049277,0.0042767334,0.00021394342,0.000237763],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019004537,0.00068677077,0.0008601139,0.00028436672,0.00019994781,0.00074937165,0.005640457,0.00081115356,0.0000028908282],"category_scores_gemma":[0.00014374327,0.0006177741,0.00032582387,0.00020585729,0.000050844068,0.0017920096,0.004693283,0.0009795094,0.000022042665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012937919,0.00012190324,0.000025747073,0.014960274,0.00035058497,0.000008203289,0.0358384,0.806761,0.0006531903,0.025637345,0.006349297,0.10916464],"study_design_scores_gemma":[0.00078510185,0.000035801746,0.000007149933,0.00039363542,0.00008050828,0.000028093464,0.000045737565,0.98728275,0.00006433005,0.01000346,0.00048577652,0.0007876818],"about_ca_topic_score_codex":0.000043768287,"about_ca_topic_score_gemma":0.00004809812,"teacher_disagreement_score":0.18052168,"about_ca_system_score_codex":0.00019117308,"about_ca_system_score_gemma":0.0012362436,"threshold_uncertainty_score":0.9997395},"labels":[],"label_agreement":null},{"id":"W2775197842","doi":"10.48550/arxiv.1712.02750","title":"A Convergence Diagnostic for Bayesian Clustering","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain Monte Carlo; Cluster analysis; Bayesian probability; Markov chain; Computer science; Posterior probability; Gibbs sampling; Convergence (economics); State space; Sampling (signal processing); Mathematical optimization; Mathematics; Machine learning; Artificial intelligence; Statistics","score_opus":0.09424591298712023,"score_gpt":0.2295658257888058,"score_spread":0.13531991280168557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775197842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018219464,0.00012412784,0.99292487,0.0002274845,0.0017999563,0.000621811,0.00002698714,0.00020229028,0.002250513],"genre_scores_gemma":[0.81700945,0.00023027569,0.18051013,0.00012222308,0.00015431587,0.0000066628977,0.0000070641654,0.000023608745,0.0019362482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777925,0.00012743777,0.00020231963,0.001338723,0.00007471622,0.00047757966],"domain_scores_gemma":[0.9965734,0.00049271586,0.00035122724,0.0021794604,0.00016278923,0.00024044512],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046126632,0.0003615078,0.00043915922,0.00016052225,0.0003741224,0.00028134618,0.0033006696,0.00034657912,0.000014497774],"category_scores_gemma":[0.00030001916,0.00041494702,0.00032305083,0.00012949496,0.00011272591,0.0004178021,0.00246853,0.0004234361,0.000022630646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052123185,0.000121054356,0.0011312588,0.00059123826,0.00020136348,0.0006657973,0.00058876426,0.031628378,0.00005511325,0.9337465,0.0017659672,0.02945243],"study_design_scores_gemma":[0.00033539423,0.00003867481,0.00022253674,0.00014985059,0.000055321892,0.000005455512,0.0000043730856,0.7030864,0.00008496672,0.29467517,0.0009192681,0.00042262403],"about_ca_topic_score_codex":0.00009540814,"about_ca_topic_score_gemma":0.00006127707,"teacher_disagreement_score":0.8151875,"about_ca_system_score_codex":0.00011527729,"about_ca_system_score_gemma":0.0002381634,"threshold_uncertainty_score":0.99983025},"labels":[],"label_agreement":null},{"id":"W2780489948","doi":"","title":"Ottawa Bayesian inference workshop","year":2017,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Inference; Bayesian probability; Bayesian inference; Computer science; Artificial intelligence","score_opus":0.025840794011842763,"score_gpt":0.3053321987844826,"score_spread":0.27949140477263984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780489948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009602117,0.000001156332,0.56724936,0.0012450628,0.00043746404,0.00027427464,0.0000018171609,0.00016012201,0.42967057],"genre_scores_gemma":[0.44959664,0.000056949735,0.37503922,0.00042865842,0.00015237424,0.000120988836,0.0000021555027,0.000035775236,0.17456722],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99481547,0.0006221664,0.0005858649,0.0027438088,0.0005123722,0.0007202923],"domain_scores_gemma":[0.98526025,0.0005879818,0.0005015601,0.013022928,0.00018793912,0.00043932107],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0058518513,0.0004024239,0.00048739108,0.0001483113,0.0008867833,0.0013313704,0.007570833,0.0003114436,0.06325893],"category_scores_gemma":[0.00525769,0.0004147578,0.0002495059,0.00017283666,0.0002703299,0.0014418004,0.005094341,0.00068605336,0.34505844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025283789,0.0002620715,0.011683049,0.000055805776,0.000107500266,0.00010444137,0.0017080151,0.0001381771,0.00201121,0.31615153,0.020743972,0.64700896],"study_design_scores_gemma":[0.0016076467,0.0000033518384,0.061091214,0.00033153797,0.000076838274,0.00013906421,0.000039383725,0.06035991,0.018529247,0.63077086,0.22509278,0.0019581793],"about_ca_topic_score_codex":0.0001882524,"about_ca_topic_score_gemma":0.00010123853,"teacher_disagreement_score":0.64505076,"about_ca_system_score_codex":0.00011495178,"about_ca_system_score_gemma":0.00023375466,"threshold_uncertainty_score":0.9998304},"labels":[],"label_agreement":null},{"id":"W2785374143","doi":"10.1002/cjs.11795","title":"Clustering and semi‐supervised classification for clickstream data via mixture models","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Clickstream; Computer science; Mixture model; Cluster analysis; Machine learning; Artificial intelligence; Unsupervised learning; Data mining; Markov chain; Web page","score_opus":0.09815003102868965,"score_gpt":0.2989763110525442,"score_spread":0.20082628002385455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785374143","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002534778,0.00016146233,0.99713326,0.0011979511,0.0004039794,0.0001114107,0.00061608135,0.000011081159,0.00011132032],"genre_scores_gemma":[0.07648467,0.00007803053,0.92285585,0.00025257294,0.00014175958,0.0000020432392,0.000062169274,0.000014301638,0.00010862118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989425,0.00006502788,0.00036592167,0.0002202143,0.00013897671,0.00026734232],"domain_scores_gemma":[0.99840325,0.00022647632,0.00018262255,0.00048853585,0.00023546946,0.0004636342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008860772,0.00010554269,0.00019887455,0.00021583904,0.00014634094,0.00019168276,0.00081808877,0.00007167948,0.0000036283752],"category_scores_gemma":[0.00017654218,0.00009686126,0.000025514179,0.00022473061,0.000043235796,0.0004504837,0.00006696701,0.00014783253,0.0000017577521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008622288,0.0000073281312,0.00014263346,0.00009080673,0.000049170827,0.00012986934,0.0014553192,0.000579775,0.00039727901,0.09709099,0.07956646,0.8204818],"study_design_scores_gemma":[0.00022743162,0.000049642287,0.00050368154,0.000027871123,0.000018338387,0.000083870094,0.000029177629,0.89047277,0.000013493168,0.104479395,0.0039930134,0.000101312806],"about_ca_topic_score_codex":0.00019462855,"about_ca_topic_score_gemma":0.0023363058,"teacher_disagreement_score":0.889893,"about_ca_system_score_codex":0.000043890515,"about_ca_system_score_gemma":0.0005396147,"threshold_uncertainty_score":0.39498875},"labels":[],"label_agreement":null},{"id":"W2786105260","doi":"10.1109/ascc.2017.8287319","title":"Simultaneous estimation of sub-model number and parameters for mixture probability principal component regression","year":2017,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Principal component analysis; Probabilistic logic; Maximum a posteriori estimation; Computer science; Expectation–maximization algorithm; Statistical model; A priori and a posteriori; Principal component regression; Maximization; Component (thermodynamics); Algorithm; Artificial intelligence; Data mining; Mathematical optimization; Mathematics; Statistics; Maximum likelihood","score_opus":0.034181110933353444,"score_gpt":0.3202447601942225,"score_spread":0.286063649260869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786105260","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20344476,0.000010267654,0.7952536,0.0004144908,0.00009209381,0.00040059522,0.000004053276,0.000033770506,0.0003464057],"genre_scores_gemma":[0.48262912,0.0000025979953,0.51726264,0.000029440287,0.000005079278,0.000011248825,0.0000010178018,0.0000032479322,0.00005561366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990449,0.000050497707,0.0002189566,0.0003618906,0.00015408131,0.00016969793],"domain_scores_gemma":[0.9985709,0.00024026375,0.00021263912,0.0007892116,0.000102690894,0.00008427724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004976332,0.00012915605,0.00021828954,0.000018442886,0.00021565171,0.0001181544,0.00045172556,0.00009486245,9.95562e-7],"category_scores_gemma":[0.00031483293,0.00009112293,0.0000613495,0.000023359496,0.00010353811,0.00030952826,0.00021144762,0.00007425608,6.8213865e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009863404,0.00018447608,0.0005829331,0.00027682306,0.00002362593,0.000003945841,0.0007405192,0.014183764,0.0058677644,0.2478001,0.00016055554,0.73007685],"study_design_scores_gemma":[0.0002764832,0.00003698677,0.0002530886,0.000034722623,0.00000738945,0.000003440313,6.5537273e-7,0.8344972,0.012048135,0.15271749,0.000025560597,0.000098816345],"about_ca_topic_score_codex":0.000020403779,"about_ca_topic_score_gemma":0.000007837169,"teacher_disagreement_score":0.82031345,"about_ca_system_score_codex":0.000018016059,"about_ca_system_score_gemma":0.000035967594,"threshold_uncertainty_score":0.37158853},"labels":[],"label_agreement":null},{"id":"W2790407909","doi":"10.1002/sam.11373","title":"Building cancer prognosis systems with survival function clusters","year":2018,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneous; Cluster analysis; Computer science; Cancer; Lung cancer; Cluster (spacecraft); Population; Medicine; Covariate; Demographics; Survival analysis; Data mining; Oncology; Internal medicine; Artificial intelligence; Mathematics; Machine learning; Demography","score_opus":0.08062547735272997,"score_gpt":0.3739859447699232,"score_spread":0.29336046741719324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790407909","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036227505,0.00018984335,0.9941517,0.000922389,0.0004934278,0.00007640523,0.00044069334,0.000019996003,0.00008275997],"genre_scores_gemma":[0.26729268,0.000078524274,0.7320957,0.00015007456,0.00032217673,0.0000026867936,0.00004061478,0.000005178605,0.000012322748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969363,0.0002537567,0.0003668352,0.0010009896,0.0009641102,0.00047797887],"domain_scores_gemma":[0.9966519,0.00038035613,0.00026942685,0.0021155023,0.00027843015,0.00030439222],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0082692355,0.00016422027,0.0003091211,0.00026586818,0.0014563008,0.0026880496,0.0052089123,0.000030389025,0.000021236474],"category_scores_gemma":[0.0004043923,0.000086548986,0.000020611553,0.0023980315,0.0010383128,0.0033080347,0.0026922163,0.00024353276,0.0000019488932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010923487,0.000089618625,0.020952849,0.000025903557,0.0012097794,0.000047325993,0.0007872939,0.00013628101,0.00034313512,0.115311675,0.009287972,0.85169894],"study_design_scores_gemma":[0.00015998771,0.00014906142,0.014719465,0.000046224766,0.0007983599,0.00009477927,0.00019675471,0.98084515,0.000008775661,0.0012244236,0.0015658978,0.00019112737],"about_ca_topic_score_codex":0.0003732977,"about_ca_topic_score_gemma":0.00024106582,"teacher_disagreement_score":0.98070884,"about_ca_system_score_codex":0.000031481704,"about_ca_system_score_gemma":0.00031936844,"threshold_uncertainty_score":0.99984366},"labels":[],"label_agreement":null},{"id":"W2790828348","doi":"","title":"Mixture Model Averaging for Clustering and Classification","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Computer science; Bayesian information criterion; Model selection; Data mining; Rand index; Artificial intelligence; Bayesian inference; Bayesian probability; Pattern recognition (psychology); Mathematics; Machine learning","score_opus":0.10815239210930831,"score_gpt":0.21518328028726946,"score_spread":0.10703088817796115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790828348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020411443,0.000058661084,0.97760606,0.00012219159,0.00011828956,0.00012170523,0.0000015535471,0.00007365498,0.0014864318],"genre_scores_gemma":[0.7614637,0.000020439718,0.23773117,0.00012810454,0.00003803691,6.0021364e-7,8.3785807e-7,0.0000054924317,0.00061161007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993385,0.00003675537,0.0000664752,0.00029020873,0.00002673393,0.0002413277],"domain_scores_gemma":[0.99945474,0.000054019874,0.00004857929,0.00028330553,0.000038597045,0.00012078331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025686243,0.0000943015,0.000093047245,0.00006852702,0.00013584238,0.0000415544,0.00026050638,0.000065236774,0.000001124891],"category_scores_gemma":[0.0000113275555,0.00009940095,0.000042540956,0.000160063,0.000024177149,0.00074057496,0.00012802615,0.000074609,0.0000033985916],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000099690105,0.00002423539,0.0007094599,0.00002220319,0.000010642848,0.0000016993899,0.00056133117,0.0047536897,0.0012159654,0.9793377,0.00016659866,0.013186494],"study_design_scores_gemma":[0.00022190678,0.000009809183,0.00046939292,0.000007181456,0.000012174118,0.000003998441,0.000013845818,0.9520972,0.00014647795,0.046487074,0.00040774082,0.00012322931],"about_ca_topic_score_codex":0.000002291554,"about_ca_topic_score_gemma":0.00000183442,"teacher_disagreement_score":0.94734347,"about_ca_system_score_codex":0.000034619836,"about_ca_system_score_gemma":0.000017051298,"threshold_uncertainty_score":0.40534532},"labels":[],"label_agreement":null},{"id":"W2790993801","doi":"10.1002/sta4.177","title":"Flexible clustering of high‐dimensional data via mixtures of joint generalized hyperbolic distributions","year":2018,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"Canada Research Chairs","keywords":"Identifiability; Cluster analysis; Bayesian information criterion; Computer science; Joint (building); Limiting; Mixture model; Determining the number of clusters in a data set; Mathematics; Selection (genetic algorithm); Subspace topology; Applied mathematics; Algorithm; Data mining; Statistics; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Engineering","score_opus":0.056894550683767954,"score_gpt":0.31125728618629717,"score_spread":0.2543627355025292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790993801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0136026265,0.00020036398,0.9848913,0.00034204155,0.00038068258,0.00008586918,0.00020012406,0.000037822014,0.00025919787],"genre_scores_gemma":[0.35714403,0.000008962154,0.64256614,0.000083783125,0.00007506033,0.0000018738367,0.00004288326,0.000005128463,0.00007213062],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888223,0.00009656085,0.00028943454,0.00031774284,0.00021202474,0.00020201158],"domain_scores_gemma":[0.99853307,0.00004115816,0.00012615934,0.0010847922,0.00014328324,0.00007151663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000364858,0.00010459072,0.00024261774,0.000063828214,0.00007513689,0.000018859915,0.00073548773,0.00004668534,0.00004036517],"category_scores_gemma":[0.00003876594,0.00008606713,0.00004589537,0.00022897871,0.00014072325,0.00021691529,0.0008330572,0.00006637229,0.000005916944],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062072824,0.00023862506,0.000052329273,0.000106600644,0.00012246947,0.000008807391,0.0006524777,0.00014565278,0.43805653,0.3324248,0.015036093,0.21309355],"study_design_scores_gemma":[0.0009879387,0.00025251938,0.0016713577,0.00008772891,0.000039551735,0.0000410508,0.0000033607475,0.31001344,0.49729598,0.18594216,0.0033289406,0.00033595215],"about_ca_topic_score_codex":0.00025565253,"about_ca_topic_score_gemma":0.000023739856,"teacher_disagreement_score":0.34354138,"about_ca_system_score_codex":0.0000127075145,"about_ca_system_score_gemma":0.00007207675,"threshold_uncertainty_score":0.35097158},"labels":[],"label_agreement":null},{"id":"W2793872545","doi":"10.1016/j.csda.2018.01.012","title":"Prediction with a flexible finite mixture-of-regressions","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Jenny ja Antti Wihurin Rahasto; Natural Sciences and Engineering Research Council of Canada; Magnus Ehrnroothin Säätiö","keywords":"Covariate; Linear regression; Regression; Mathematics; Regression analysis; Random forest; Predictive power; Nonlinear system; Generalized linear model; Statistics; Linear model; Econometrics; Computer science; Applied mathematics; Artificial intelligence","score_opus":0.053367042984998246,"score_gpt":0.32417006742643023,"score_spread":0.270803024441432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793872545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008912103,0.000059350674,0.99604625,0.00016530181,0.00009229668,0.000078646466,0.003029594,0.000064553904,0.00037491173],"genre_scores_gemma":[0.08193006,0.000011217166,0.915294,0.00012586135,0.000080763595,0.0000042159,0.0024123897,0.000007755098,0.00013377178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982527,0.00013599887,0.0003530341,0.00056388526,0.00050641457,0.00018797161],"domain_scores_gemma":[0.9975164,0.00052018935,0.00023902388,0.0010786214,0.0005315337,0.00011422414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042436577,0.00014815561,0.00028737207,0.0003391629,0.00020532528,0.0001182321,0.00096272444,0.000047493806,0.00007235765],"category_scores_gemma":[0.0001350292,0.00011722459,0.00004854772,0.0018514476,0.0001739863,0.00043123725,0.00037855364,0.00010241051,0.000015672616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057034573,0.0002824112,0.009043006,0.000044782966,0.0025067793,0.000024586261,0.00068388873,0.050865915,0.00003834018,0.76158273,0.03016816,0.14470235],"study_design_scores_gemma":[0.00017948847,0.00009190576,0.013129634,0.000017252081,0.00048950175,0.0000040239574,0.0000018562703,0.89906687,0.000030019699,0.08541395,0.0014524428,0.0001230491],"about_ca_topic_score_codex":0.00008967027,"about_ca_topic_score_gemma":0.00006872013,"teacher_disagreement_score":0.848201,"about_ca_system_score_codex":0.000017702232,"about_ca_system_score_gemma":0.00016643871,"threshold_uncertainty_score":0.47802803},"labels":[],"label_agreement":null},{"id":"W2795506808","doi":"10.1007/978-3-319-89656-4_17","title":"MML-Based Approach for Determining the Number of Topics in EDCM Mixture Models","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Multinomial distribution; Expectation–maximization algorithm; Exponential family; Dirichlet distribution; Simulated annealing; Mixture model; Exponential function; Algorithm; Artificial intelligence; Heuristic; Machine learning; Maximum likelihood; Mathematics; Statistics","score_opus":0.03514417107977675,"score_gpt":0.2857522084889811,"score_spread":0.25060803740920434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795506808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008356184,0.00010851901,0.9937212,0.00036331563,0.0006810782,0.0005114599,0.0000069740286,0.00003616407,0.0044877413],"genre_scores_gemma":[0.03314834,0.000005793023,0.9649134,0.0013054551,0.00040458067,0.000027618593,0.000004306747,0.00002789357,0.0001625989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712396,0.00006840661,0.00053473294,0.0011257143,0.0006003845,0.00054682285],"domain_scores_gemma":[0.9973298,0.0005995697,0.0003141022,0.0013799039,0.00029111045,0.00008552909],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014832129,0.00040635365,0.00051290187,0.0003208622,0.0001525112,0.00021248653,0.0033489089,0.00040961197,0.000008092262],"category_scores_gemma":[0.00009049056,0.0003017601,0.0001882079,0.00045149538,0.0006384288,0.0003403848,0.00062839786,0.0005731986,0.0000015838914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002153227,0.0000810583,0.000110191155,0.00018709681,0.000014103382,0.000009618369,0.002571747,0.04574142,0.000022661983,0.16150934,0.00009028815,0.78964096],"study_design_scores_gemma":[0.0002973513,0.000058802187,0.000016527662,0.00013584942,0.0000057399543,0.000007853953,1.04322076e-7,0.6672879,0.00056012085,0.33115056,0.0002283774,0.00025081667],"about_ca_topic_score_codex":0.000008836205,"about_ca_topic_score_gemma":0.000016346694,"teacher_disagreement_score":0.78939015,"about_ca_system_score_codex":0.000091281625,"about_ca_system_score_gemma":0.0004682217,"threshold_uncertainty_score":0.99994344},"labels":[],"label_agreement":null},{"id":"W2797508735","doi":"10.1109/wsc.2018.8632422","title":"ON A GENERALIZED SPLITTING METHOD FOR SAMPLING FROM A CONDITIONAL DISTRIBUTION","year":2018,"lang":"en","type":"article","venue":"2018 Winter Simulation Conference (WSC)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Conditional probability distribution; Mathematics; Event (particle physics); Estimator; Sampling distribution; Rare events; Statistics; Distribution (mathematics); Sampling (signal processing); Applied mathematics; Combinatorics; Computer science; Mathematical analysis; Physics","score_opus":0.08858667748422848,"score_gpt":0.38399534558622134,"score_spread":0.29540866810199284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797508735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056391116,0.00000929065,0.99173015,0.0006208211,0.00072652975,0.00036642214,0.0002168948,0.00014329625,0.00054747897],"genre_scores_gemma":[0.47853634,4.2000073e-7,0.52004164,0.0006363942,0.00040502948,0.000027516357,0.00020416366,0.000009134981,0.00013938431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981499,0.00021391912,0.00039398382,0.00066129875,0.00025771945,0.00032322787],"domain_scores_gemma":[0.99762917,0.0010581772,0.0002140946,0.00049121823,0.0004910489,0.00011628178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064087316,0.00022179057,0.00026455888,0.00007821941,0.00026731417,0.00029546465,0.00046771925,0.00013790294,0.00019678666],"category_scores_gemma":[0.00031871142,0.00020484204,0.00013508945,0.00015206645,0.00006409122,0.00044856744,0.00011371018,0.00012794446,0.00006329502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015202389,0.00007988596,0.000047738,0.000012562736,0.00006835951,0.0000010782821,0.0010403974,0.003077087,0.0036750939,0.79510856,0.0015382482,0.19519897],"study_design_scores_gemma":[0.0006118358,0.00011683932,0.0003933356,0.000044922486,0.000011810876,9.4415736e-7,0.0000045272827,0.66469973,0.001955273,0.3269836,0.0050013466,0.00017585172],"about_ca_topic_score_codex":0.000029567378,"about_ca_topic_score_gemma":0.0000124899425,"teacher_disagreement_score":0.66162264,"about_ca_system_score_codex":0.00007789742,"about_ca_system_score_gemma":0.00008973899,"threshold_uncertainty_score":0.8353216},"labels":[],"label_agreement":null},{"id":"W2798711685","doi":"10.1007/s00362-022-01333-9","title":"On the circular correlation coefficients for bivariate von Mises distributions on a torus","year":2022,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"von Mises distribution; Mathematics; Bivariate analysis; Estimator; Univariate; Statistics; von Mises yield criterion; Applied mathematics; Parametric statistics; Multivariate statistics","score_opus":0.01994508815286599,"score_gpt":0.27623437866285805,"score_spread":0.25628929050999205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798711685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029083656,0.000009338667,0.9927633,0.0019994406,0.0005157494,0.00035671255,0.0005343315,0.00004739017,0.0034829048],"genre_scores_gemma":[0.9158422,0.000001026481,0.08213928,0.0015136542,0.000028194472,0.00016328153,0.00007928542,0.000009397312,0.00022369665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987798,0.00024047811,0.00013920563,0.00030663575,0.00030525928,0.00022867284],"domain_scores_gemma":[0.99799234,0.0015478617,0.00004573882,0.000311119,0.000029500334,0.00007346156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042274335,0.00009976446,0.00009960499,0.00003071317,0.0006637847,0.00006424825,0.0003411397,0.000024861121,0.00011118834],"category_scores_gemma":[0.00051228126,0.0000723275,0.00005610678,0.00019716464,0.000050211045,0.000028698618,0.00008054915,0.00017535714,0.000015010049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024039422,0.00007893994,0.0000037251598,0.000003202797,0.000009367065,0.000004064898,0.00009503511,0.00085844,0.00017549103,0.9748932,0.003431715,0.020422745],"study_design_scores_gemma":[0.0007037208,0.00086692604,0.001427772,0.000014477659,0.00003585867,0.000006653733,0.00004865938,0.37514442,0.000087236265,0.586491,0.03487666,0.0002966317],"about_ca_topic_score_codex":0.000007930382,"about_ca_topic_score_gemma":5.1664244e-7,"teacher_disagreement_score":0.91555136,"about_ca_system_score_codex":0.00009590603,"about_ca_system_score_gemma":0.000048944057,"threshold_uncertainty_score":0.51053625},"labels":[],"label_agreement":null},{"id":"W2799134885","doi":"10.4230/lipics.approx-random.2018.5","title":"Greedy Bipartite Matching in Random Type Poisson Arrival Model","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bipartite graph; Poisson distribution; Matching (statistics); Type (biology); Mathematics; Combinatorics; Statistics; Computer science; Geology","score_opus":0.08963032183704714,"score_gpt":0.22040619238418432,"score_spread":0.13077587054713719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799134885","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16610447,0.0000649105,0.82898855,0.00009699804,0.0006556819,0.00023836935,0.0000051503066,0.00015240132,0.003693478],"genre_scores_gemma":[0.87129575,0.000108639026,0.12682459,0.00015017467,0.00010903027,7.8475796e-7,0.000005155101,0.000023033688,0.0014828483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763715,0.00029367948,0.00026378722,0.0012161888,0.0001142166,0.0004749959],"domain_scores_gemma":[0.99807024,0.00008551124,0.00020922594,0.0013076039,0.00013825459,0.00018917212],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007667732,0.00035750403,0.00048823116,0.00037633246,0.00010930176,0.0001375079,0.001863433,0.00037499805,0.000016590755],"category_scores_gemma":[0.000034400975,0.00038942232,0.00019356844,0.00064051483,0.00008916725,0.00042783684,0.0018470915,0.0007205264,0.00007403111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026379956,0.000149504,0.0008736081,0.00011377291,0.00008987191,0.0004767177,0.0018014552,0.47647655,0.00030821405,0.5162491,0.0006089061,0.0025884632],"study_design_scores_gemma":[0.00062281836,0.000023073186,0.000106983185,0.00008728738,0.000020645155,0.0000028304698,0.000005619007,0.6265737,0.00008035341,0.37212345,0.000061472165,0.00029176625],"about_ca_topic_score_codex":0.00024017236,"about_ca_topic_score_gemma":0.000099873505,"teacher_disagreement_score":0.7051913,"about_ca_system_score_codex":0.00016127345,"about_ca_system_score_gemma":0.00030271008,"threshold_uncertainty_score":0.99985576},"labels":[],"label_agreement":null},{"id":"W2799563584","doi":"10.1002/bimj.201700114","title":"Modeling clustered long‐term survivors using marginal mixture cure model","year":2018,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Estimator; Statistics; Censoring (clinical trials); Mathematics; Mixture model; Econometrics; Marginal model; Regression analysis; Bone marrow transplant; Term (time); Sample size determination; Computer science; Applied mathematics; Bone marrow transplantation; Medicine; Transplantation; Surgery","score_opus":0.0705367102434552,"score_gpt":0.3357581750201324,"score_spread":0.2652214647766772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799563584","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044466145,0.0007615385,0.9525886,0.0005444178,0.0011210504,0.00010067268,0.000004226426,0.00008026825,0.0003330759],"genre_scores_gemma":[0.40579736,0.000055591576,0.5928552,0.00033083378,0.00084070815,8.108276e-7,7.0704954e-7,0.00001970426,0.00009903855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997057,0.00026035833,0.0005656105,0.00054350315,0.0008134398,0.0007600677],"domain_scores_gemma":[0.99812084,0.00007128651,0.00019169896,0.0005433881,0.00047831566,0.00059445633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013239187,0.0003103319,0.00038814146,0.0015218861,0.0005188983,0.00068234326,0.0014812424,0.0002810639,0.000030169718],"category_scores_gemma":[0.00011895284,0.00024508432,0.0002567673,0.0034250896,0.00010152216,0.0008260144,0.0004237831,0.0006680915,0.000019917632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030964546,0.0009456813,0.0033220795,0.00011963076,0.0004045547,0.0008268914,0.0022332787,0.024036137,0.02062366,0.023070268,0.0034825448,0.9206256],"study_design_scores_gemma":[0.0004857329,0.00013450766,0.00018542646,0.000049485283,0.000025392525,0.00097330054,0.0000030547208,0.98525465,0.00029185507,0.012168802,0.000094425326,0.00033336948],"about_ca_topic_score_codex":0.000016466734,"about_ca_topic_score_gemma":0.000004421945,"teacher_disagreement_score":0.96121854,"about_ca_system_score_codex":0.00016642504,"about_ca_system_score_gemma":0.00023795589,"threshold_uncertainty_score":0.9994248},"labels":[],"label_agreement":null},{"id":"W2800000274","doi":"10.1080/00949655.2018.1472263","title":"Minimum Hellinger distance estimation for a semiparametric location-shifted mixture model","year":2018,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hellinger distance; Outlier; Mathematics; Estimator; Parametric statistics; Robustness (evolution); Semiparametric model; Applied mathematics; Semiparametric regression; Parametric model; Algorithm; Mathematical optimization; Statistics","score_opus":0.027540740391382393,"score_gpt":0.34382774534162,"score_spread":0.3162870049502376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800000274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028760189,0.00011391674,0.99621594,0.00033104926,0.00019756015,0.00019109473,0.00000908466,0.00002138738,0.000043937172],"genre_scores_gemma":[0.4928052,0.0000032897974,0.5069827,0.00011831118,0.00006580541,0.0000013829592,0.0000053294298,0.0000044728263,0.000013545371],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879277,0.00008831678,0.0005119749,0.00019302557,0.00027554622,0.00013834394],"domain_scores_gemma":[0.9972987,0.0010715973,0.0003658113,0.00009347246,0.0010531954,0.00011723554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005922273,0.00011472198,0.00020993616,0.00020095977,0.00014337891,0.00015696662,0.00012832483,0.00007838717,0.0000022153438],"category_scores_gemma":[0.00057183835,0.000099128694,0.000038780116,0.00040087424,0.00006229379,0.00047219035,0.000018587862,0.00010741591,0.0000015200293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008906583,0.00005167262,0.000015770724,0.000047513153,0.000015316258,0.0000012850574,0.00061697775,0.67167944,0.000044199656,0.1176756,0.00032160923,0.20944157],"study_design_scores_gemma":[0.00043530733,0.00018607453,0.00029399956,0.000026501291,0.000018005096,0.0000059169847,0.000003491719,0.6991178,0.000034962228,0.29973856,0.000060819697,0.000078575016],"about_ca_topic_score_codex":6.6856546e-7,"about_ca_topic_score_gemma":6.2738525e-7,"teacher_disagreement_score":0.4899292,"about_ca_system_score_codex":0.000039237308,"about_ca_system_score_gemma":0.00008566009,"threshold_uncertainty_score":0.4042351},"labels":[],"label_agreement":null},{"id":"W2804065525","doi":"10.1007/s00180-020-00988-y","title":"The two-sample problem via relative belief ratio","year":2020,"lang":"en","type":"preprint","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"A priori and a posteriori; Dirichlet distribution; Mathematics; Bayesian probability; Null (SQL); Sample (material); Combinatorics; Dirichlet process; Applied mathematics; Statistics; Computer science; Physics; Mathematical analysis; Philosophy; Thermodynamics; Epistemology; Data mining","score_opus":0.0325902858752739,"score_gpt":0.3092622086064598,"score_spread":0.2766719227311859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804065525","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018151478,0.0003124496,0.9921583,0.004356515,0.00081037695,0.0005744165,0.0005918941,0.00015876254,0.0010354883],"genre_scores_gemma":[0.004812133,0.000031961157,0.9934218,0.00075627834,0.00026736475,0.00007573815,0.00044399744,0.000028679813,0.00016204547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997259,0.0004139342,0.000600257,0.000747431,0.0006543898,0.00032499558],"domain_scores_gemma":[0.9944885,0.0038299009,0.00045093216,0.0005175442,0.00053400255,0.00017915302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053118344,0.00034411412,0.000343625,0.000053391257,0.0005692814,0.0006122587,0.0013382211,0.0001345186,0.000010886462],"category_scores_gemma":[0.00038905526,0.00027762048,0.000103182356,0.00023597488,0.00015070262,0.0001546839,0.0014313398,0.0008621841,0.00005614478],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004987321,0.00002161077,0.0000067256997,0.000033598295,0.00007219452,0.000012819418,0.00060498883,0.036363147,0.0000026041505,0.85617554,0.0068261316,0.099875644],"study_design_scores_gemma":[0.000120303455,0.00002793951,0.000117055206,0.00001634027,0.0000142816,0.0000039242286,0.0000012559565,0.47515747,0.000003871619,0.52205116,0.0023181976,0.00016817776],"about_ca_topic_score_codex":0.00005734808,"about_ca_topic_score_gemma":0.000016577129,"teacher_disagreement_score":0.4387943,"about_ca_system_score_codex":0.000112835376,"about_ca_system_score_gemma":0.0006205463,"threshold_uncertainty_score":0.9999676},"labels":[],"label_agreement":null},{"id":"W2804835843","doi":"","title":"Fisher Linear Discriminant Construction for Distributions of Diseased Data","year":2007,"lang":"en","type":"article","venue":"CMBES Proceedings","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Queen's University; Mount Allison University","funders":"","keywords":"Linear discriminant analysis; Statistics; Mathematics; Artificial intelligence; Computer science","score_opus":0.053627211795283826,"score_gpt":0.33107286927162966,"score_spread":0.2774456574763458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804835843","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011341914,0.000056758705,0.98660296,0.00046758863,0.00024947693,0.0002340503,0.00010525057,0.00006626014,0.00087574247],"genre_scores_gemma":[0.30898666,0.0000059868657,0.69074214,0.000042060157,0.00011694247,0.000008439627,0.00003584475,0.0000064678297,0.000055453886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990124,0.000003928654,0.0002460425,0.00036025603,0.0001376339,0.00023975759],"domain_scores_gemma":[0.99916255,0.000062481035,0.00011893552,0.00032774344,0.00022535687,0.000102912905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005962845,0.0001017181,0.00015126637,0.000055285072,0.00011326191,0.00004996043,0.0007585544,0.000058514546,0.0000025070121],"category_scores_gemma":[0.00020784853,0.000085244006,0.00005398639,0.00023919345,0.00010504987,0.0006088996,0.00024321776,0.000067276735,0.0000010601133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037606234,0.000100897174,0.0016081586,0.0001596559,0.000020707315,0.0000010096701,0.00027960222,1.3249591e-7,0.009521163,0.8544711,0.005334409,0.12846558],"study_design_scores_gemma":[0.0033793016,0.00068833545,0.039022334,0.00044819037,0.00039383196,0.00013439824,0.0005684419,0.24073185,0.20551246,0.40676755,0.100741915,0.0016113868],"about_ca_topic_score_codex":0.000006520166,"about_ca_topic_score_gemma":0.0000016956085,"teacher_disagreement_score":0.4477035,"about_ca_system_score_codex":0.000018474357,"about_ca_system_score_gemma":0.000042380463,"threshold_uncertainty_score":0.34761494},"labels":[],"label_agreement":null},{"id":"W2804941162","doi":"10.1007/s00500-018-3244-4","title":"Bayesian inference by reversible jump MCMC for clustering based on finite generalized inverted Dirichlet mixtures","year":2018,"lang":"en","type":"article","venue":"Soft Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Umm Al-Qura University","keywords":"Markov chain Monte Carlo; Mixture model; Computer science; Dirichlet process; Cluster analysis; Dirichlet distribution; Machine learning; Model selection; Artificial intelligence; Reversible-jump Markov chain Monte Carlo; Bayesian inference; Context (archaeology); Inference; Bayesian probability; Mathematics","score_opus":0.0260322839539159,"score_gpt":0.2947823977226792,"score_spread":0.26875011376876334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804941162","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006534863,0.00007786412,0.9955002,0.0008513304,0.00080880645,0.0003631191,0.0000118245935,0.00035387784,0.0013795043],"genre_scores_gemma":[0.38199723,0.000001819274,0.61300725,0.0044452343,0.00029154916,0.000009836424,0.000012555232,0.000024448247,0.00021007903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976309,0.00024132685,0.00039318026,0.00078914623,0.00029596378,0.00064946315],"domain_scores_gemma":[0.99764544,0.00101002,0.0002083316,0.00073867134,0.00020713772,0.0001903956],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086764037,0.0003234623,0.0003665363,0.00019414707,0.00051867025,0.00026968855,0.0010274745,0.00015849729,0.00001459887],"category_scores_gemma":[0.00041257482,0.00030508192,0.00015001305,0.00056510576,0.000087750785,0.00022545093,0.0003281317,0.00022535217,0.0000147486135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003072253,0.00044970345,0.0013079852,0.00048300074,0.0001757787,0.00003689203,0.0041230847,0.018795734,0.02405397,0.030865557,0.14336748,0.7760336],"study_design_scores_gemma":[0.00095200446,0.00023708047,0.000033128446,0.00013881254,0.0000114102895,0.0000024941378,0.0000029126684,0.9779578,0.0053845327,0.008413148,0.006481207,0.00038546175],"about_ca_topic_score_codex":0.000043986176,"about_ca_topic_score_gemma":0.000017514527,"teacher_disagreement_score":0.95916206,"about_ca_system_score_codex":0.000060143906,"about_ca_system_score_gemma":0.000112149544,"threshold_uncertainty_score":0.99994016},"labels":[],"label_agreement":null},{"id":"W2806096886","doi":"10.1016/j.csda.2018.05.015","title":"Addressing overfitting and underfitting in Gaussian model-based clustering","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Overfitting; Cluster analysis; Maxima and minima; Mixture model; Expectation–maximization algorithm; Context (archaeology); Maxima; Computer science; Nonparametric statistics; Artificial intelligence; Convergence (economics); Machine learning; Gaussian; Mathematics; Mathematical optimization; Algorithm; Pattern recognition (psychology); Artificial neural network; Econometrics; Maximum likelihood; Statistics","score_opus":0.11429489834700153,"score_gpt":0.3791082464019549,"score_spread":0.2648133480549534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806096886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007151477,0.000068679736,0.9983868,0.00021856929,0.00005461393,0.00006556698,0.0002467532,0.000045109726,0.00019877526],"genre_scores_gemma":[0.38808858,0.0000027391304,0.6113294,0.0002563797,0.0000379042,0.0000015537679,0.0002683908,0.0000069773814,0.0000081202015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980463,0.00016305732,0.00043118992,0.0007338703,0.0003386863,0.0002869104],"domain_scores_gemma":[0.998386,0.00050607306,0.00018856663,0.00066067337,0.00014500141,0.00011367646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009871016,0.00016804604,0.0002976695,0.00042185956,0.0002713411,0.00040179293,0.0006840586,0.000053415915,0.00000978838],"category_scores_gemma":[0.00019373008,0.00017436914,0.00003292449,0.00113256,0.000110148314,0.0004920881,0.0006616972,0.00014665656,0.0000029255884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001099856,0.00006291414,0.005947079,0.000059405673,0.00024443193,0.000031910444,0.00070313364,0.6498353,0.000026029225,0.1398163,0.00041792894,0.2028446],"study_design_scores_gemma":[0.00023127797,0.000013192032,0.007734825,0.000033539545,0.00011499547,0.0000021751832,0.000005061083,0.91125613,0.0000041761327,0.080402695,0.000020820424,0.00018109118],"about_ca_topic_score_codex":0.00014784404,"about_ca_topic_score_gemma":0.0004597765,"teacher_disagreement_score":0.38737342,"about_ca_system_score_codex":0.000049350605,"about_ca_system_score_gemma":0.0001437919,"threshold_uncertainty_score":0.7110567},"labels":[],"label_agreement":null},{"id":"W2806898845","doi":"10.1007/978-3-319-92058-0_34","title":"Bayesian Learning of Finite Asymmetric Gaussian Mixtures","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Gibbs sampling; Computer science; Mixture model; Gaussian; Bayesian probability; Artificial intelligence; Bayesian inference; Gaussian process; Contrast (vision); Importance sampling; Machine learning; Algorithm; Mathematics; Statistics; Monte Carlo method","score_opus":0.016545647833665494,"score_gpt":0.26141024296307325,"score_spread":0.24486459512940775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806898845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000083215255,0.00090528117,0.97739613,0.0003592934,0.0015220135,0.00031046694,0.0000040340883,0.00015066101,0.019343812],"genre_scores_gemma":[0.08996916,0.00008013352,0.9076147,0.0006917026,0.0006211523,0.0000050884414,0.0000036536019,0.00005123809,0.0009631836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950819,0.00014624867,0.00082278124,0.0018470131,0.0012282665,0.0008738042],"domain_scores_gemma":[0.99594605,0.0010185713,0.00064485025,0.0017231754,0.00038697515,0.00028035385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019550011,0.0007038911,0.0009238662,0.0021672926,0.0002840945,0.00038911766,0.0041344524,0.00057802256,0.000068192254],"category_scores_gemma":[0.00039501916,0.0006145038,0.00027236456,0.0017205118,0.0010403194,0.00053810386,0.0014623778,0.0013121304,0.00003676915],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070551423,0.0000282276,0.000039178216,0.00006953245,0.00002024411,0.0000628453,0.0010361891,0.0034242645,0.00014822258,0.051066905,0.000046443998,0.9440509],"study_design_scores_gemma":[0.00027047205,0.00043280097,0.00005592112,0.0005155137,0.000016559577,0.000057496633,1.1764011e-7,0.5007959,0.0046765516,0.49027142,0.0021138676,0.000793367],"about_ca_topic_score_codex":0.000021394224,"about_ca_topic_score_gemma":0.00001732148,"teacher_disagreement_score":0.9432575,"about_ca_system_score_codex":0.00016008748,"about_ca_system_score_gemma":0.00058495667,"threshold_uncertainty_score":0.99963063},"labels":[],"label_agreement":null},{"id":"W2807625977","doi":"10.1016/j.cam.2018.04.032","title":"Fitting the Erlang mixture model to data via a GEM-CMM algorithm","year":2018,"lang":"en","type":"article","venue":"Journal of Computational and Applied Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Graduate School, Chongqing University; Xiamen University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Erlang (programming language); Expectation–maximization algorithm; Erlang distribution; Algorithm; Mathematics; Scale (ratio); Mixture model; Mathematical optimization; Computer science; Applied mathematics; Maximum likelihood; Statistics; Gamma distribution; Theoretical computer science","score_opus":0.03855160777779899,"score_gpt":0.3024386855231926,"score_spread":0.2638870777453936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807625977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010111482,0.000060781374,0.99588037,0.0019505132,0.00009244402,0.0001095505,0.0000059108656,0.000013968341,0.00087533693],"genre_scores_gemma":[0.030984763,0.0000037291306,0.9674493,0.0011582038,0.00034687223,0.0000015780855,0.0000014597489,0.00000816826,0.000045923945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989003,0.000021313894,0.00039100114,0.0001652845,0.00037740215,0.00014469914],"domain_scores_gemma":[0.99880284,0.00029130644,0.00028431354,0.00031354482,0.00020289117,0.000105108455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001023924,0.00011646169,0.00020977335,0.000066854074,0.00015269248,0.00015230292,0.00093428855,0.000040656658,0.0000029676696],"category_scores_gemma":[0.0000329873,0.00007090658,0.000035579822,0.0001786497,0.000050142247,0.00019066088,0.00040032627,0.00017004603,0.000005993233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009041838,0.00011474944,6.4305164e-7,0.00004652374,0.000076369266,0.0000057354036,0.005233978,0.007175306,0.0006921575,0.35293233,0.00900285,0.6247103],"study_design_scores_gemma":[0.00010971655,0.00002553994,0.000008303949,0.000021743212,0.000011362892,0.00012524835,0.000020080832,0.5965544,0.00008916432,0.4026549,0.00032228886,0.00005725812],"about_ca_topic_score_codex":3.169525e-7,"about_ca_topic_score_gemma":2.8401604e-7,"teacher_disagreement_score":0.62465304,"about_ca_system_score_codex":0.000010056103,"about_ca_system_score_gemma":0.00007209949,"threshold_uncertainty_score":0.28914863},"labels":[],"label_agreement":null},{"id":"W2810140685","doi":"10.48550/arxiv.1806.08813","title":"An Annealed Sequential Monte Carlo Method for Bayesian Phylogenetics","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Western Canada Research Grid; Compute Canada","keywords":"Markov chain Monte Carlo; Monte Carlo method; Computer science; Hybrid Monte Carlo; Marginal likelihood; Monte Carlo molecular modeling; Algorithm; Monte Carlo method in statistical physics; Monte Carlo integration; Embarrassingly parallel; Bayesian probability; Mathematics; Statistics; Artificial intelligence","score_opus":0.08271305708433196,"score_gpt":0.25534145495044225,"score_spread":0.17262839786611028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810140685","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010660939,0.00007772086,0.9860118,0.00008831931,0.0012753059,0.0007385006,0.00008848768,0.00027385761,0.00078505],"genre_scores_gemma":[0.41314164,0.000038505357,0.585726,0.00015867056,0.00034399825,0.0000035682988,0.000011757624,0.00003300183,0.0005428165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963577,0.0006545968,0.0003060465,0.001929736,0.0001203411,0.0006315909],"domain_scores_gemma":[0.99638164,0.000141635,0.00033823933,0.0023168041,0.00041991728,0.00040174965],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00095073465,0.0005111278,0.0005956268,0.00028873945,0.00026734723,0.00023879849,0.0030002773,0.00062314264,0.00001698535],"category_scores_gemma":[0.00003326399,0.0005801615,0.00043947645,0.00040710164,0.0001343787,0.00032076315,0.0012266156,0.00046745595,0.000009542922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036668664,0.0006465892,0.00072969566,0.00056847045,0.0008870974,0.0006124893,0.002451946,0.24578702,0.0027353617,0.6760392,0.0033620272,0.065813385],"study_design_scores_gemma":[0.0005093275,0.00020287004,0.00007358201,0.000034505192,0.00013490027,0.000007014431,0.000011187881,0.8147915,0.0011074849,0.18177292,0.00079443684,0.0005602775],"about_ca_topic_score_codex":0.00016661642,"about_ca_topic_score_gemma":0.00008786314,"teacher_disagreement_score":0.5690045,"about_ca_system_score_codex":0.00015435873,"about_ca_system_score_gemma":0.00034118706,"threshold_uncertainty_score":0.99966496},"labels":[],"label_agreement":null},{"id":"W2810411611","doi":"10.1007/978-3-319-94211-7_25","title":"Visual Scene Reconstruction Using a Bayesian Learning Framework","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Dirichlet distribution; Artificial intelligence; Gibbs sampling; Machine learning; Bayesian probability; Parametric statistics; Focus (optics); Density estimation; Prior probability; Hierarchical Dirichlet process; Pattern recognition (psychology); Latent Dirichlet allocation; Mathematics; Topic model; Statistics","score_opus":0.021963991545495304,"score_gpt":0.292800006722466,"score_spread":0.27083601517697065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810411611","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014636728,0.0003542422,0.9933672,0.00020439026,0.0035112947,0.00029523027,0.000001073252,0.00023966926,0.0018805483],"genre_scores_gemma":[0.025317801,0.000033257485,0.97229034,0.0006346415,0.0014792996,0.000003211335,0.0000012777951,0.000051025523,0.00018915819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954588,0.00013638675,0.00062772766,0.002006521,0.00089825236,0.00087232265],"domain_scores_gemma":[0.99738467,0.00043519313,0.00045773236,0.0011319417,0.00032427578,0.00026619845],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015386462,0.0006502568,0.0006757635,0.0010142466,0.0005639966,0.0008096695,0.00227227,0.00073543075,0.000089500754],"category_scores_gemma":[0.00021406318,0.0006211934,0.00019036679,0.0008799265,0.00095291424,0.00081490586,0.0011586939,0.0017363281,0.00003493833],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005403617,0.000012907515,0.00004311174,0.000024281251,0.00001149922,0.00004253286,0.00072161114,0.0027721194,0.00023247016,0.016434478,0.0000032674798,0.97969633],"study_design_scores_gemma":[0.00009074959,0.00013424645,0.000009865573,0.0006392364,0.000008290866,0.00023740919,1.0427567e-7,0.59048235,0.00080989086,0.40688062,0.00022070108,0.00048653394],"about_ca_topic_score_codex":0.000016189524,"about_ca_topic_score_gemma":0.000012637851,"teacher_disagreement_score":0.9792098,"about_ca_system_score_codex":0.00038219488,"about_ca_system_score_gemma":0.00066339335,"threshold_uncertainty_score":0.99962395},"labels":[],"label_agreement":null},{"id":"W2884359305","doi":"10.1093/forestscience/52.2.148","title":"A New Type of Sample Plot that Is Particularly Useful for Sampling Small Clusters of Objects","year":2006,"lang":"en","type":"article","venue":"Forest Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Resolute Forest Products (Canada)","funders":"","keywords":"Sampling (signal processing); Plot (graphics); Sample (material); Statistics; Mathematics; Computer science; Chromatography; Chemistry","score_opus":0.0827122754079726,"score_gpt":0.30836244282344955,"score_spread":0.22565016741547694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884359305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08479728,0.00013390626,0.914171,0.00012477106,0.0002996753,0.00023463703,0.0000058266587,0.000028523324,0.00020438407],"genre_scores_gemma":[0.45526123,0.0000015327985,0.54451215,0.00011193185,0.000025726955,0.000003910745,5.7536386e-7,0.000004514661,0.00007838507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985992,0.000022187156,0.00025340996,0.00041319017,0.00034439523,0.00036763024],"domain_scores_gemma":[0.99871016,0.00021073771,0.00017982822,0.0005547372,0.00022592777,0.00011861447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006710395,0.000118612115,0.000210016,0.00014934609,0.00010769258,0.000093390554,0.0010956594,0.00004633921,0.0000027178576],"category_scores_gemma":[0.00016710412,0.00010032743,0.00008574243,0.00086382194,0.00019342967,0.00043332617,0.00020618811,0.00005277905,0.0000014677237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048954294,0.0001679415,0.011475539,0.0001401961,0.000016553839,0.0000015147596,0.0028639485,0.0043948935,0.017251952,0.92957896,0.0012523807,0.03280715],"study_design_scores_gemma":[0.0006069014,0.0004537686,0.00945627,0.00016073477,0.000029734143,0.000009686163,0.00003264997,0.13284424,0.07264689,0.78179663,0.0016059112,0.00035656584],"about_ca_topic_score_codex":0.0008825874,"about_ca_topic_score_gemma":0.00014245648,"teacher_disagreement_score":0.37046397,"about_ca_system_score_codex":0.000024592482,"about_ca_system_score_gemma":0.00064165937,"threshold_uncertainty_score":0.4091234},"labels":[],"label_agreement":null},{"id":"W2887608518","doi":"10.3390/e20080575","title":"Spherical Minimum Description Length","year":2018,"lang":"en","type":"article","venue":"Entropy","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hypersphere; Minimum description length; Mathematics; Model selection; Selection (genetic algorithm); Applied mathematics; Laplace transform; Algorithm; Mathematical optimization; Artificial intelligence; Computer science; Statistics; Mathematical analysis; Geometry","score_opus":0.02148450439491062,"score_gpt":0.2649447020826102,"score_spread":0.24346019768769955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887608518","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058937557,0.00006715479,0.98606884,0.00094032026,0.0007974652,0.000055421133,2.9194936e-7,0.000116427575,0.006060291],"genre_scores_gemma":[0.25198773,0.0000048867405,0.7459191,0.0005884718,0.00042630947,0.0000031677278,2.9941924e-7,0.000004910222,0.0010650994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992215,0.00008165416,0.00010615118,0.00024239028,0.00013611309,0.00021220275],"domain_scores_gemma":[0.99948204,0.00001682709,0.00003205959,0.0003423247,0.000043452776,0.00008328689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016717173,0.00007845352,0.0000899577,0.00002188329,0.000076510616,0.00008848153,0.00036413234,0.000044761495,0.00008452487],"category_scores_gemma":[0.00002593231,0.0000650314,0.000043083175,0.00015183976,0.000051098632,0.00024070955,0.00009107024,0.00007228715,0.00028394358],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011201175,0.000062192405,0.00015307919,0.0000032431647,0.000010845546,0.000012074097,0.000709754,3.7284286e-7,0.028263362,0.7529835,0.030214531,0.18757583],"study_design_scores_gemma":[0.0012546689,0.000887216,0.004369485,0.00003207712,0.000021401229,0.00007581027,0.000024040077,0.17836283,0.058657303,0.4499177,0.3056607,0.00073675567],"about_ca_topic_score_codex":0.0000065116606,"about_ca_topic_score_gemma":0.0000013071966,"teacher_disagreement_score":0.3030658,"about_ca_system_score_codex":0.00002267265,"about_ca_system_score_gemma":0.00002329244,"threshold_uncertainty_score":0.36496148},"labels":[],"label_agreement":null},{"id":"W2888010039","doi":"10.1007/s11634-018-0333-2","title":"Subspace clustering for the finite mixture of generalized hyperbolic distributions","year":2018,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Mixture model; Mathematics; Subspace topology; Applied mathematics; Hyperbolic function; Gaussian; Finite element method; Extension (predicate logic); Mathematical analysis; Computer science; Statistics; Physics","score_opus":0.05135122907555946,"score_gpt":0.3540267272002225,"score_spread":0.30267549812466304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888010039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005198962,0.0022353968,0.99555343,0.0013175302,0.00006446737,0.00011187743,0.000108275366,0.000010072136,0.000079042504],"genre_scores_gemma":[0.54085183,0.0022119933,0.456569,0.00006117453,0.00005795085,0.000025948722,0.00017809295,0.0000028117724,0.000041179243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991866,0.00007005515,0.00020998773,0.00033460624,0.00008736818,0.000111423265],"domain_scores_gemma":[0.9984034,0.000275139,0.00013948804,0.001076288,0.00008166929,0.000024057525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005444879,0.000070874354,0.0001636304,0.000087904256,0.000126419,0.00005218945,0.0007424978,0.000035093457,0.000002579504],"category_scores_gemma":[0.00012378472,0.000048009893,0.000043440457,0.000901714,0.00010240833,0.000526144,0.0001762643,0.000045727116,4.0346535e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023780956,0.000060194678,0.0027068679,0.000029774828,0.00018257642,2.0228521e-7,0.0003976642,0.0002588177,0.0037941302,0.3142064,0.00029509445,0.6780445],"study_design_scores_gemma":[0.00014448562,0.000013752344,0.009194069,0.000006781815,0.0001552974,4.7653052e-7,0.000022146725,0.9572683,0.00041078022,0.009455794,0.023257118,0.00007099455],"about_ca_topic_score_codex":0.000019115096,"about_ca_topic_score_gemma":0.00081110065,"teacher_disagreement_score":0.9570095,"about_ca_system_score_codex":0.000008757225,"about_ca_system_score_gemma":0.000014274887,"threshold_uncertainty_score":0.19577867},"labels":[],"label_agreement":null},{"id":"W2888488618","doi":"10.1504/ijiei.2018.10015613","title":"A purely Bayesian approach for proportional visual data modelling","year":2018,"lang":"en","type":"article","venue":"International Journal of Intelligent Engineering Informatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Dirichlet distribution; Gibbs sampling; Artificial intelligence; Bayesian probability; Machine learning; Focus (optics); Parametric statistics; Model selection; Density estimation; Face (sociological concept); Mathematics; Statistics","score_opus":0.044910731023640314,"score_gpt":0.3149649434559131,"score_spread":0.2700542124322728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888488618","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019053616,0.000060724517,0.99753857,0.0001693769,0.0014418729,0.00014012586,0.000011318276,0.000036767386,0.00041070484],"genre_scores_gemma":[0.088075705,0.000036417983,0.91078085,0.00017586072,0.00086243445,0.000004094016,0.00002406887,0.0000126910445,0.000027864027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980104,0.000016085674,0.0009987683,0.00012194554,0.00064003706,0.00021277269],"domain_scores_gemma":[0.99788606,0.000098869285,0.0004771238,0.00032252874,0.0010946984,0.00012071449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012966015,0.00015901095,0.00020436247,0.00033040554,0.000052201238,0.00024859962,0.0023627474,0.00007443158,0.000006316656],"category_scores_gemma":[0.00016796075,0.00013364512,0.00011640674,0.00014329769,0.000033212782,0.0013817413,0.00030405485,0.00024941238,0.0000038078338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010896024,0.0003135721,0.000030580944,0.00014273093,0.0007356097,0.00001406399,0.003610525,0.49502245,0.00019299623,0.3212668,0.0037105698,0.17485115],"study_design_scores_gemma":[0.00020279018,0.00014120873,0.0000025830304,0.00006650058,0.000013476018,0.00024741972,0.000031798994,0.9838191,0.0014100716,0.002928255,0.010993252,0.00014351623],"about_ca_topic_score_codex":0.0000012789814,"about_ca_topic_score_gemma":1.1567247e-7,"teacher_disagreement_score":0.48879668,"about_ca_system_score_codex":0.000081194754,"about_ca_system_score_gemma":0.00014989848,"threshold_uncertainty_score":0.544989},"labels":[],"label_agreement":null},{"id":"W2889231032","doi":"10.1109/ccece.2018.8447795","title":"Image Segmentation Using Inverted Dirichlet Mixture Model and Spatial Information","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Image segmentation; Artificial intelligence; Pattern recognition (psychology); Markov random field; Expectation–maximization algorithm; Dirichlet distribution; Computer science; Scale-space segmentation; Segmentation-based object categorization; Mixture model; Pixel; Segmentation; Computer vision; Algorithm; Mathematics; Maximum likelihood; Statistics","score_opus":0.018613769129218794,"score_gpt":0.27738863801875535,"score_spread":0.25877486888953655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889231032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008989355,0.0000072905036,0.9874768,0.00027399987,0.00011305527,0.00011589911,0.0000018163942,0.00007874015,0.0029430387],"genre_scores_gemma":[0.15994811,0.0000031920913,0.83868486,0.0012688648,0.000046723846,0.000002051567,0.0000034398347,0.0000028368438,0.00003991545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994147,0.00003934465,0.00014547403,0.0001389579,0.00013090606,0.00013061878],"domain_scores_gemma":[0.9995767,0.000011985402,0.00005882384,0.00018273712,0.000110123234,0.000059620354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018037936,0.00008710008,0.000078633435,0.000076896154,0.000109475564,0.00018702284,0.00014935163,0.00005558927,0.000010149689],"category_scores_gemma":[0.0000144906235,0.000071563496,0.000016571588,0.00014707982,0.000042267333,0.0017275404,0.00011142208,0.000054061496,0.00001036707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016090613,0.000024677956,0.00010192353,0.00003178192,0.000016953332,0.000001242709,0.005281909,0.000084090105,0.073403955,0.037511803,0.0030839397,0.88044167],"study_design_scores_gemma":[0.00020982865,0.000026424834,0.00013431325,0.000004758194,0.0000046844493,0.00000736705,0.000008130931,0.9763187,0.005371242,0.01773241,0.00008432821,0.00009779255],"about_ca_topic_score_codex":0.00016974306,"about_ca_topic_score_gemma":0.00003256976,"teacher_disagreement_score":0.9762346,"about_ca_system_score_codex":0.00001914086,"about_ca_system_score_gemma":0.000035968984,"threshold_uncertainty_score":0.29182747},"labels":[],"label_agreement":null},{"id":"W2889359843","doi":"10.1109/ccece.2018.8447816","title":"Asymmetric Gaussian Mixtures with Reversible Jump MCMC","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reversible-jump Markov chain Monte Carlo; Markov chain Monte Carlo; Gibbs sampling; Gaussian; Laplace's method; Sampling (signal processing); Computer science; Mixture model; Algorithm; Flexibility (engineering); Markov chain; Bayesian probability; Applied mathematics; Jump; Artificial intelligence; Rejection sampling; Mathematics; Machine learning; Statistics; Hybrid Monte Carlo; Computer vision","score_opus":0.013902203793862516,"score_gpt":0.255492139916265,"score_spread":0.2415899361224025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889359843","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001322067,0.00010743424,0.7584567,0.00106603,0.00020628932,0.000081667196,4.129681e-7,0.0001517675,0.23979749],"genre_scores_gemma":[0.12412457,0.000009871906,0.8663016,0.0016116182,0.00019335473,0.0000041649473,4.220067e-7,0.000009596691,0.007744782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987728,0.00007754617,0.00012979744,0.0004351583,0.00024874863,0.00033593024],"domain_scores_gemma":[0.99893653,0.00005540113,0.000052211184,0.00069314835,0.00010815492,0.00015453833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034323195,0.00014900604,0.00015874716,0.00023334437,0.00015199724,0.00014400584,0.0007577045,0.000072187875,0.00009191098],"category_scores_gemma":[0.000024219293,0.000096361364,0.000047320595,0.0012716376,0.00008382565,0.0003896101,0.00015394934,0.000114164126,0.0001736925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017630806,0.00007133347,0.00029733026,0.000014493163,0.00003762852,0.000032241456,0.00037309414,6.3137855e-7,0.00083067175,0.5971983,0.077521764,0.32360488],"study_design_scores_gemma":[0.0032712563,0.0034739736,0.007594022,0.00017572279,0.00009145993,0.00050271256,0.00004166875,0.04149313,0.27464318,0.33073187,0.33542243,0.0025585652],"about_ca_topic_score_codex":0.00005501148,"about_ca_topic_score_gemma":0.00002022214,"teacher_disagreement_score":0.32104632,"about_ca_system_score_codex":0.000020265057,"about_ca_system_score_gemma":0.000070961134,"threshold_uncertainty_score":0.39295027},"labels":[],"label_agreement":null},{"id":"W288953241","doi":"","title":"Estimating the residual distribution in a semiparametric transformation model.","year":2011,"lang":"en","type":"article","venue":"ORBi (University of Liège)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Semiparametric model; Semiparametric regression; Residual; Econometrics; Transformation (genetics); Mathematics; Distribution (mathematics); Statistics; Nonparametric statistics; Algorithm","score_opus":0.03295225284658791,"score_gpt":0.2254611982933903,"score_spread":0.19250894544680242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W288953241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07815264,0.000017136836,0.91853535,0.00047789802,0.00003749191,0.00009196565,0.000004574122,0.000028077435,0.0026548398],"genre_scores_gemma":[0.602218,0.0000028876866,0.3977245,0.000012786842,0.0000036215781,1.2314932e-7,0.0000017363393,0.0000011704311,0.000035215642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994255,0.00008227753,0.000093337054,0.0001372695,0.00013189079,0.00012975375],"domain_scores_gemma":[0.99958795,0.00003990654,0.00007397064,0.00022675032,0.000040102892,0.000031310272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004862493,0.00005957045,0.00009870311,0.00008958059,0.000106514075,0.000011980187,0.00048236962,0.000053674208,0.0000066622515],"category_scores_gemma":[0.0000061694504,0.000054809974,0.00003965963,0.00053426693,0.00004559332,0.0005654283,0.000069345,0.00011464449,0.000003903325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064187014,0.00020839355,0.0015093866,0.000079018784,0.000027475955,0.00002663364,0.0659909,0.0054327017,0.00041838118,0.7018177,0.0006154116,0.2238098],"study_design_scores_gemma":[0.00023151108,0.000031773852,0.005738886,0.000021066031,0.000008537151,0.000004303285,0.0001264988,0.95747167,0.00024338646,0.036025565,0.000018564035,0.0000782188],"about_ca_topic_score_codex":0.0006017065,"about_ca_topic_score_gemma":0.00004317205,"teacher_disagreement_score":0.952039,"about_ca_system_score_codex":0.000034303386,"about_ca_system_score_gemma":0.000051622595,"threshold_uncertainty_score":0.2235086},"labels":[],"label_agreement":null},{"id":"W2891057340","doi":"10.48550/arxiv.1809.06447","title":"Homogeneity testing under finite location-scale mixtures","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"Yunnan University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Homogeneity (statistics); Univariate; Likelihood-ratio test; Limiting; Ratio test; Applied mathematics; Mathematics; Statistical hypothesis testing; Scale (ratio); Statistics; Statistical physics; Computer science; Multivariate statistics; Physics; Engineering","score_opus":0.10172841370550277,"score_gpt":0.2183081732279925,"score_spread":0.11657975952248974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891057340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026214195,0.00013320034,0.9656649,0.00012770138,0.00077716797,0.00023152448,0.0000110532455,0.0003215253,0.006518681],"genre_scores_gemma":[0.7596957,0.00003245011,0.23852323,0.00030383986,0.00022100954,0.0000011168091,0.000008169368,0.000020299658,0.0011941906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754936,0.00030072453,0.00022897779,0.0013759937,0.0001155718,0.00042939317],"domain_scores_gemma":[0.99693954,0.00033643126,0.00027987952,0.0017323586,0.0004920137,0.00021980426],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051833276,0.00037610417,0.00035294675,0.0002269533,0.0002822187,0.00018867147,0.0021169842,0.00041420682,0.0000215658],"category_scores_gemma":[0.00010215838,0.00041293554,0.00017228124,0.0009687826,0.00018481126,0.0003123688,0.0020709548,0.0005753065,0.00009911296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058932877,0.0005812712,0.010038647,0.0005798382,0.00046809923,0.00047576777,0.0013779651,0.46723062,0.0008140182,0.48125583,0.0075842575,0.029534755],"study_design_scores_gemma":[0.00027023035,0.000054194472,0.002230087,0.00014831829,0.00007428314,0.000008307203,0.000010756701,0.64610946,0.0010880051,0.34900263,0.00034290028,0.0006608277],"about_ca_topic_score_codex":0.00018141718,"about_ca_topic_score_gemma":0.000053179778,"teacher_disagreement_score":0.73348147,"about_ca_system_score_codex":0.00014001038,"about_ca_system_score_gemma":0.0003694521,"threshold_uncertainty_score":0.9998323},"labels":[],"label_agreement":null},{"id":"W2891365885","doi":"10.1007/s11634-019-00377-4","title":"Mixtures of skewed matrix variate bilinear factor analyzers","year":2019,"lang":"en","type":"preprint","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Random variate; Kurtosis; Skewness; Bilinear interpolation; Statistics; Mathematics; Skew; Matrix (chemical analysis); Gaussian; Inverse Gaussian distribution; Applied mathematics; Computer science; Distribution (mathematics); Mathematical analysis; Physics; Random variable","score_opus":0.04467400490465936,"score_gpt":0.3678903485041041,"score_spread":0.3232163435994448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891365885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025167179,0.0063599865,0.9897391,0.0002898215,0.0002260959,0.00021934538,0.0003878228,0.000028713526,0.00023236722],"genre_scores_gemma":[0.47912657,0.009791402,0.50993323,0.000030133615,0.000041676227,0.00001067414,0.0009557945,0.000010139183,0.00010041367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971559,0.00030813375,0.00070943584,0.0013013508,0.0003242035,0.00020094539],"domain_scores_gemma":[0.9953215,0.00021095821,0.0007477511,0.0035361324,0.00011840014,0.00006524362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009005688,0.00025879164,0.00076789176,0.00068699085,0.00003793219,0.00014237278,0.0022033579,0.00023459517,0.000015344123],"category_scores_gemma":[0.00012549905,0.00021870238,0.0001544544,0.0012695685,0.00007489824,0.0008215855,0.001393934,0.00034136735,0.0000028152326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006707089,0.00044362908,0.04105168,0.0010797285,0.0022724096,0.000007548884,0.001300456,0.011171809,0.006304374,0.1263597,0.00027679693,0.8096648],"study_design_scores_gemma":[0.0001798341,0.000015119673,0.028130524,0.00005857535,0.00051172666,5.036781e-7,0.000020768271,0.9442941,0.00031742023,0.024476383,0.0016785734,0.000316484],"about_ca_topic_score_codex":0.00009683098,"about_ca_topic_score_gemma":0.000162292,"teacher_disagreement_score":0.9331223,"about_ca_system_score_codex":0.000033978158,"about_ca_system_score_gemma":0.00010260409,"threshold_uncertainty_score":0.8918424},"labels":[],"label_agreement":null},{"id":"W2891477799","doi":"","title":"Deep Homogeneous Mixture Models: Representation, Separation, and Approximation","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Representation (politics); Connection (principal bundle); Constant (computer programming); Computer science; Mixture model; Homogeneous; Exponential function; Tree (set theory); Graphical model; Algorithm; Mathematics; Exponential growth; Latent variable; Artificial intelligence; Pattern recognition (psychology); Combinatorics; Mathematical analysis","score_opus":0.026015202243382232,"score_gpt":0.2934103046597554,"score_spread":0.2673951024163732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891477799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020133639,0.00045823448,0.99152917,0.00037761475,0.00043039216,0.00033800112,0.0000013808807,0.00025223196,0.004599635],"genre_scores_gemma":[0.85077965,0.000012473938,0.14823441,0.0005239935,0.00021726443,0.000055556866,0.00002152066,0.00000769761,0.0001474162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864215,0.00010551111,0.0005045759,0.00023077484,0.000316118,0.00020085678],"domain_scores_gemma":[0.99863535,0.000026965796,0.00033794806,0.00030769737,0.00060457556,0.00008745722],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00037228063,0.00015478251,0.00016512343,0.00016039284,0.00039394153,0.0011744808,0.0002848517,0.000108526074,0.0000014889995],"category_scores_gemma":[0.00004361331,0.00013293652,0.000026266143,0.00045454508,0.000060767892,0.0074903155,0.0000695952,0.00009726616,0.000017004677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002250902,0.000025121779,0.00007027526,0.0004422502,0.000018330771,0.000001898961,0.02502991,0.010297211,0.00047883118,0.14887196,0.0026263758,0.8121153],"study_design_scores_gemma":[0.00018820184,0.000043296688,0.000042032563,0.000033742905,0.000005755654,0.00014775018,0.00010764856,0.9873626,0.00049392227,0.010133161,0.0012844978,0.000157348],"about_ca_topic_score_codex":0.000020483778,"about_ca_topic_score_gemma":0.0000026814093,"teacher_disagreement_score":0.97706544,"about_ca_system_score_codex":0.000029803174,"about_ca_system_score_gemma":0.000052011954,"threshold_uncertainty_score":0.9998624},"labels":[],"label_agreement":null},{"id":"W2892721734","doi":"10.1016/j.jtbi.2018.09.029","title":"Allelic frequency estimation in presence of uncertain priors","year":2018,"lang":"en","type":"article","venue":"Journal of Theoretical Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Prior probability; Hyperparameter; Bayes' theorem; Estimator; Mathematics; Statistics; Bayes estimator; Bayes factor; Computer science; Bayesian probability; Artificial intelligence","score_opus":0.014404230692381951,"score_gpt":0.31967981363240794,"score_spread":0.305275582940026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892721734","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057665408,0.000121093115,0.93892545,0.0015956274,0.00026162725,0.000045873432,4.9565364e-7,0.00000436192,0.0013800728],"genre_scores_gemma":[0.5745611,0.000014057336,0.42528898,0.0000912638,0.000040098934,3.8453993e-7,7.8586226e-8,0.0000014807504,0.0000025609186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99878085,0.00039370218,0.00043998708,0.00012206759,0.00009945796,0.0001639177],"domain_scores_gemma":[0.99897075,0.00036336607,0.00023207968,0.00020359553,0.00016628962,0.00006391144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013601616,0.00007003877,0.00023296868,0.00013293968,0.000016460699,0.000010024029,0.00063849945,0.000102940474,0.00004067521],"category_scores_gemma":[0.0008032055,0.00004682515,0.00006181842,0.00020083507,0.0005602183,0.000121950936,0.00008719036,0.00016936507,0.0000033404071],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019022496,0.000032451328,0.00034911736,0.00000423518,0.000006720951,0.0000062721792,0.00028551143,0.0000069679463,0.008034859,0.94674253,0.000026625401,0.04448569],"study_design_scores_gemma":[0.00020239929,0.0006279737,0.0008131103,0.000036985617,0.0000038788585,0.00006007597,0.0000044764,0.022709744,0.0040094513,0.97144765,0.00003263353,0.000051643045],"about_ca_topic_score_codex":0.0000067122705,"about_ca_topic_score_gemma":0.0000018950425,"teacher_disagreement_score":0.5168957,"about_ca_system_score_codex":0.000020183923,"about_ca_system_score_gemma":0.00008076836,"threshold_uncertainty_score":0.20641477},"labels":[],"label_agreement":null},{"id":"W2893312973","doi":"10.1002/sim.7984","title":"Judgment post‐stratification in finite mixture modeling: An example in estimating the prevalence of osteoporosis","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Ranking (information retrieval); Statistics; Rank (graph theory); Small area estimation; Econometrics; Mathematics; Computer science; Expectation–maximization algorithm; Measure (data warehouse); Population; Data mining; Maximum likelihood; Artificial intelligence; Medicine","score_opus":0.05566959108421915,"score_gpt":0.3371850861906867,"score_spread":0.28151549510646756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893312973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02086044,0.0001227652,0.9775602,0.0007628713,0.00021974463,0.000260956,0.000012783381,0.00001078702,0.00018943536],"genre_scores_gemma":[0.44578245,0.00001839784,0.5539066,0.00020718224,0.000048518636,0.000012731531,0.0000058065048,0.000004396149,0.000013925053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826336,0.00027892186,0.0005807219,0.00035319861,0.00030924738,0.00021456658],"domain_scores_gemma":[0.9985939,0.00047009523,0.00015286212,0.0005789096,0.00015682331,0.000047373465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021976347,0.00012240087,0.00022125745,0.00016818356,0.00004105119,0.000016820242,0.00058260374,0.000059811726,0.000015122542],"category_scores_gemma":[0.0005462344,0.000086946966,0.0000090269095,0.00047000762,0.0001606861,0.00014836097,0.000067259236,0.00023104915,8.5479047e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000722389,0.00042017526,0.0032552432,0.0009154763,0.000011392211,0.00004248682,0.11804821,0.03356989,0.0072630057,0.42541575,0.00035340223,0.41063273],"study_design_scores_gemma":[0.00032766262,0.0002561954,0.0025543277,0.00024573779,0.000005452635,0.0000018208384,0.00015202613,0.86796135,0.00015284072,0.12825863,0.000005928468,0.00007803397],"about_ca_topic_score_codex":0.0012615687,"about_ca_topic_score_gemma":0.00091503555,"teacher_disagreement_score":0.8343915,"about_ca_system_score_codex":0.000042160533,"about_ca_system_score_gemma":0.00007808986,"threshold_uncertainty_score":0.35455942},"labels":[],"label_agreement":null},{"id":"W2894790280","doi":"10.1111/rssc.12312","title":"Rectangular Latent Markov Models for Time-Specific Clustering, with An Analysis of the Wellbeing of Nations","year":2018,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Merge (version control); Markov chain; Latent class model; Markov model; Markov process; Cluster analysis; Econometrics; Computer science; Statistics; Mathematics; Information retrieval","score_opus":0.01185984865433809,"score_gpt":0.2459645314030187,"score_spread":0.2341046827486806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894790280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008101247,0.000030988194,0.9975721,0.00023367086,0.00017999312,0.00026377372,0.0005447345,0.0000089506575,0.00035564287],"genre_scores_gemma":[0.13583092,0.000014354232,0.8637536,0.00008989853,0.00007534416,0.0000062081117,0.0000053745644,0.000016676764,0.00020757482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979288,0.00017375758,0.0007338992,0.00024853935,0.00063980697,0.0002751903],"domain_scores_gemma":[0.9972001,0.0006570597,0.00082724163,0.0005389242,0.0006577419,0.00011898685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009345811,0.00019274632,0.0005546433,0.00006280626,0.0003668144,0.00008206361,0.0010354427,0.00008629853,0.000041388175],"category_scores_gemma":[0.000093146526,0.00010917866,0.00028021727,0.0006714787,0.0005384375,0.00014671251,0.00021749825,0.00022987663,3.1266296e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036112295,0.00018138609,0.000053277377,0.00008782084,0.0012141364,0.0000017569937,0.0026719656,0.026679212,0.0009290877,0.9504527,0.0040903147,0.013277236],"study_design_scores_gemma":[0.00044879102,0.00047891584,0.0019958944,0.000042729564,0.0006933013,0.0000060723564,0.00009032153,0.88187194,0.00069992273,0.11308784,0.00041636734,0.00016788945],"about_ca_topic_score_codex":0.00001625076,"about_ca_topic_score_gemma":0.0000454506,"teacher_disagreement_score":0.8551927,"about_ca_system_score_codex":0.00008413008,"about_ca_system_score_gemma":0.00014270628,"threshold_uncertainty_score":0.44521764},"labels":[],"label_agreement":null},{"id":"W2896267177","doi":"10.1007/978-3-319-92378-9_8","title":"Simulation from the Tail of the Univariate and Multivariate Normal Distribution","year":2018,"lang":"en","type":"book-chapter","venue":"EAI/Springer Innovations in Communication and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Univariate; Multivariate statistics; Univariate distribution; Multivariate normal distribution; Statistics; Random variate; Inverse-Wishart distribution; Normal distribution; Posterior probability; Mathematics; Bayesian probability; Inference; Bayesian inference; Applied mathematics; Computer science; Artificial intelligence; Random variable","score_opus":0.03539408396978242,"score_gpt":0.2860932072309307,"score_spread":0.25069912326114824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896267177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039612637,0.00044428307,0.98585737,0.0015231627,0.0001734761,0.00028313673,0.000022649683,0.000039543604,0.0076951366],"genre_scores_gemma":[0.862753,0.00008409139,0.13543244,0.00032213985,0.00008617036,0.0000041394333,0.00005506102,0.0000174472,0.0012455676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985459,0.00022346132,0.00059513736,0.0003074839,0.00019083751,0.0001371907],"domain_scores_gemma":[0.99676573,0.0009927909,0.0006045436,0.0013098925,0.000304909,0.000022101822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011176334,0.0001976967,0.00022496584,0.00008370807,0.0004891866,0.00014184171,0.0010167349,0.00018064935,0.000009084575],"category_scores_gemma":[0.00016458868,0.00014625795,0.000043911466,0.0002933873,0.0002497385,0.00019504603,0.0015514621,0.0005429108,0.0000015309424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036313957,0.00001465578,0.00044035466,0.000009488063,0.000027420485,1.5431304e-7,0.0016925116,0.00055883854,0.000050774746,0.91624755,0.00004326245,0.080911346],"study_design_scores_gemma":[0.0005383224,0.000018799177,0.04682881,0.0006776854,0.000034287354,0.0000030706606,0.000041268657,0.6781287,0.00007944466,0.25743088,0.015858755,0.0003599476],"about_ca_topic_score_codex":0.00014612004,"about_ca_topic_score_gemma":0.00004463787,"teacher_disagreement_score":0.8587917,"about_ca_system_score_codex":0.00004865654,"about_ca_system_score_gemma":0.00006408754,"threshold_uncertainty_score":0.5964226},"labels":[],"label_agreement":null},{"id":"W2900067413","doi":"10.1920/wp.cem.2018.6518","title":"Nonparametric maximum likelihood methods for binary response models with random coefficients","year":2019,"lang":"en","type":"report","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Nonparametric statistics; Statistics; Mathematics; Maximum likelihood; Binary number; Random effects model; Econometrics","score_opus":0.04666860828120456,"score_gpt":0.3626757640089872,"score_spread":0.31600715572778265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900067413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018215287,0.002530706,0.95301986,0.00023300677,0.003405072,0.0030495878,0.000045824298,0.00037407843,0.03732363],"genre_scores_gemma":[0.00027196802,0.00035482028,0.97476554,0.00040963004,0.00023328427,0.00035432036,0.000033904576,0.00014496729,0.023431584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926993,0.0016977601,0.0009880997,0.002087282,0.0013611366,0.0011663781],"domain_scores_gemma":[0.98932254,0.004255699,0.0007190757,0.00288264,0.0024259535,0.0003940748],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015813978,0.0009266394,0.0018480152,0.001440044,0.00021365982,0.00041591428,0.002468412,0.0008848384,0.000023068687],"category_scores_gemma":[0.0014854297,0.0006512982,0.00064489996,0.0019611225,0.00008984069,0.0005474547,0.000687384,0.00073754543,0.000030042935],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035383387,0.0004062298,0.0000034030934,0.0005124557,0.00040395567,0.000048273694,0.00022347947,0.0010896683,0.00017605524,0.0067555406,0.032942362,0.9539002],"study_design_scores_gemma":[0.007056603,0.0021629855,0.000019436378,0.0004367043,0.00035407656,0.0002456636,0.000011527393,0.6865139,0.0008820746,0.082183756,0.21810973,0.0020235488],"about_ca_topic_score_codex":0.00007074921,"about_ca_topic_score_gemma":0.0000023439752,"teacher_disagreement_score":0.9518767,"about_ca_system_score_codex":0.00036030248,"about_ca_system_score_gemma":0.0041073156,"threshold_uncertainty_score":0.99959385},"labels":[],"label_agreement":null},{"id":"W2900765633","doi":"10.1002/cjs.11467","title":"Hypothesis testing in finite mixture of regressions: Sparsity and model selection uncertainty","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Model selection; Statistical hypothesis testing; Regression analysis; Mathematics; Statistics; Regression; Set (abstract data type); Data set; Computer science; Selection (genetic algorithm); Econometrics; Artificial intelligence","score_opus":0.04965267094580817,"score_gpt":0.25558743106696663,"score_spread":0.20593476012115847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900765633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010975704,0.000110418776,0.98835605,0.00016527929,0.00009061768,0.000035230212,0.00004125557,0.0000023060281,0.00022315743],"genre_scores_gemma":[0.36219007,0.000010115411,0.6376579,0.00008314394,0.000033577275,1.6944696e-7,1.29604e-7,0.0000031896222,0.000021745385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992453,0.0000849638,0.00027568347,0.00010921378,0.00010546188,0.0001793893],"domain_scores_gemma":[0.99854803,0.00045157847,0.00023226773,0.00010598723,0.00040169005,0.00026047026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005044054,0.00007702541,0.00017632105,0.00024413099,0.00009269093,0.000037335343,0.00021893992,0.000058351652,0.000004428786],"category_scores_gemma":[0.0014963911,0.00006776537,0.000015869746,0.00031490138,0.000102124526,0.0001348151,0.000016564716,0.0001781057,3.014314e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003722736,0.000044124543,0.020701334,0.00010834474,0.00004942645,0.00027215862,0.005508797,0.010254716,0.0014707888,0.10612605,0.009345972,0.8460811],"study_design_scores_gemma":[0.00021511341,0.0001575758,0.006229616,0.00019124978,0.000013500295,0.00009316955,0.000015833797,0.74398,0.0002565923,0.2486215,0.00012086319,0.000105010324],"about_ca_topic_score_codex":0.0014601017,"about_ca_topic_score_gemma":0.015397979,"teacher_disagreement_score":0.84597605,"about_ca_system_score_codex":0.00006438495,"about_ca_system_score_gemma":0.0008765727,"threshold_uncertainty_score":0.8592434},"labels":[],"label_agreement":null},{"id":"W2901065680","doi":"10.1007/s10489-018-1333-9","title":"Model selection and application to high-dimensional count data clustering","year":2018,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Burstiness; Cluster analysis; Model selection; Count data; Dirichlet distribution; Multinomial distribution; Novelty; Selection (genetic algorithm); Data mining; Algorithm; Artificial intelligence; Pattern recognition (psychology); Statistics; Mathematics; Poisson distribution","score_opus":0.04075433305424717,"score_gpt":0.30802255585920624,"score_spread":0.26726822280495904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901065680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001340443,0.000019154993,0.9969177,0.000323879,0.00010097411,0.0002585733,0.0000039035494,0.00010426544,0.0009310799],"genre_scores_gemma":[0.4760773,0.000004850611,0.52313024,0.0006577748,0.00007171996,0.000020956408,0.0000033780386,0.0000055280566,0.0000282469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987125,0.000016388594,0.00018401658,0.00068397884,0.0001924645,0.00021067509],"domain_scores_gemma":[0.99894273,0.000039908635,0.00005012793,0.00077106396,0.00008565298,0.000110507186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046023694,0.00012369052,0.00011501746,0.00006610372,0.00016288599,0.00009051255,0.00082351424,0.00005945551,0.000005316194],"category_scores_gemma":[0.000013040436,0.00011746769,0.000008390824,0.00030033648,0.000045760273,0.00024525842,0.00079784833,0.00009515282,0.00008482507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013167757,0.000017885779,0.0000028012448,0.0000063014504,0.0000053991894,1.981261e-7,0.0002669531,0.004198687,0.022128481,0.3952254,0.00053290004,0.5776018],"study_design_scores_gemma":[0.000026167088,0.00003248772,0.000026739348,0.0000061411697,0.0000035316123,0.00000798991,0.000002385,0.90981144,0.0168499,0.07245517,0.00064300594,0.00013504068],"about_ca_topic_score_codex":0.000051427807,"about_ca_topic_score_gemma":0.000064305685,"teacher_disagreement_score":0.90561277,"about_ca_system_score_codex":0.000030084915,"about_ca_system_score_gemma":0.00004253701,"threshold_uncertainty_score":0.4790193},"labels":[],"label_agreement":null},{"id":"W2901207548","doi":"10.1016/j.jda.2018.11.007","title":"Exploring the median of permutations problem","year":2018,"lang":"en","type":"article","venue":"Journal of Discrete Algorithms","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Division of Electrical, Communications and Cyber Systems; Natural Sciences and Engineering Research Council of Canada","keywords":"Parameterized complexity; Permutation (music); Combinatorics; Mathematics; Integer programming; Solver; Heuristic; Reduction (mathematics); Set (abstract data type); Integer (computer science); Vertex (graph theory); Function (biology); Space (punctuation); Computer science; Discrete mathematics; Algorithm; Mathematical optimization","score_opus":0.07075268947540732,"score_gpt":0.3030294259198073,"score_spread":0.2322767364444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901207548","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004489338,0.0001250111,0.98913234,0.0040991274,0.00063186843,0.000065010834,0.0000020357465,0.000008887758,0.0014463888],"genre_scores_gemma":[0.24937186,0.00007018973,0.74987227,0.000092367576,0.0005249081,0.000003270157,1.4585403e-7,0.000006525118,0.000058452486],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99884546,0.00012276758,0.00041017815,0.000105356696,0.00035199575,0.00016425987],"domain_scores_gemma":[0.9988234,0.00011963034,0.00034256425,0.00027640222,0.00034247228,0.00009552137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009160471,0.000086394204,0.00018141093,0.00010750939,0.00011191462,0.000060619746,0.0007957002,0.000022775677,0.000008334915],"category_scores_gemma":[0.000057965433,0.000048971888,0.00012905942,0.000331398,0.00012053919,0.0007743908,0.00009356067,0.00018179901,0.0000034831196],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012187813,0.000058211266,0.00006227577,0.000020955787,0.00012559448,0.00002792984,0.0147864465,0.000032753036,0.0030744239,0.093447536,0.0010876511,0.887264],"study_design_scores_gemma":[0.0020995867,0.0030242016,0.009151404,0.00060272205,0.00022075788,0.0012399973,0.0014227184,0.12225896,0.06225866,0.783206,0.013729711,0.00078530563],"about_ca_topic_score_codex":0.000010635141,"about_ca_topic_score_gemma":0.000004235313,"teacher_disagreement_score":0.8864787,"about_ca_system_score_codex":0.000015946254,"about_ca_system_score_gemma":0.00010175288,"threshold_uncertainty_score":0.19970156},"labels":[],"label_agreement":null},{"id":"W2902445064","doi":"10.1002/sim.8051","title":"Bayesian adaptive group lasso with semiparametric hidden Markov models","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Mental Health; Canadian Institutes of Health Research; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Covariate; Variable-order Bayesian network; Econometrics; Bayesian probability; Semiparametric regression; Prior probability; Mathematics; Lasso (programming language); Computer science; Nonparametric statistics; Bayesian inference; Artificial intelligence","score_opus":0.02237722273859513,"score_gpt":0.29250909172723244,"score_spread":0.2701318689886373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902445064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010036391,0.0002166664,0.97876847,0.0005405047,0.00037469144,0.00025484647,0.000022988695,0.00007246577,0.01964901],"genre_scores_gemma":[0.18205963,0.000051664912,0.8165627,0.0006715058,0.00025350522,0.000017539633,0.000007641704,0.000019854217,0.0003559585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774563,0.0002274581,0.00038116076,0.0005864752,0.00057984743,0.00047939742],"domain_scores_gemma":[0.99818444,0.0005834487,0.00014613781,0.00066647306,0.00021379396,0.00020571545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010873962,0.00024976337,0.0004315611,0.00041450115,0.000094952426,0.000037800488,0.00072221993,0.00009740866,0.000059788104],"category_scores_gemma":[0.00021676888,0.00018007355,0.00001761417,0.0013387272,0.00041031177,0.00025152718,0.00014450397,0.00033405644,0.00001229318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049511942,0.00004886209,0.00014254595,0.000018275148,0.000024074492,0.00014912372,0.0014519168,0.000009691435,0.000027170945,0.7087268,0.007993979,0.281358],"study_design_scores_gemma":[0.0009991933,0.0011794298,0.0007122107,0.00014721608,0.000021546895,0.000036432757,0.00004977155,0.46077442,0.000029967348,0.53541917,0.00038470497,0.0002459493],"about_ca_topic_score_codex":0.00020110051,"about_ca_topic_score_gemma":0.00025401174,"teacher_disagreement_score":0.4607647,"about_ca_system_score_codex":0.00009264307,"about_ca_system_score_gemma":0.000089454516,"threshold_uncertainty_score":0.7343186},"labels":[],"label_agreement":null},{"id":"W2903455413","doi":"10.1186/s40488-019-0102-6","title":"The unifed distribution","year":2019,"lang":"en","type":"preprint","venue":"Journal of Statistical Distributions and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Distribution (mathematics); Computer science; Mathematics; Statistics; Econometrics; Mathematical analysis","score_opus":0.01321397303178111,"score_gpt":0.2977999922764526,"score_spread":0.2845860192446715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903455413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039655028,0.0011206764,0.9927827,0.003456358,0.0003924536,0.0003098313,0.0015148866,0.0000178855,0.00036551798],"genre_scores_gemma":[0.3898785,0.0039328677,0.603956,0.00016251033,0.00068459654,0.00019209477,0.0007691802,0.000021669674,0.00040259698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853384,0.00013528155,0.00059634366,0.00024628095,0.00026781223,0.00022044004],"domain_scores_gemma":[0.9976517,0.0006498998,0.00048289457,0.0005606974,0.00046851495,0.00018628691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006798165,0.00016531703,0.00028203113,0.00003050547,0.00044255226,0.0004474522,0.0007768677,0.00015484489,0.0000038170897],"category_scores_gemma":[0.00016876981,0.00010941322,0.00011289796,0.00018580644,0.00019592558,0.0001029078,0.0004861077,0.0007842944,0.000007211384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030497306,0.000045681198,0.000022375118,0.000017447528,0.00003038899,0.0000018418859,0.000008322501,0.000011044151,0.0000040262016,0.8994824,0.019216279,0.08115712],"study_design_scores_gemma":[0.0001569648,0.000048971153,0.004346287,0.00004827102,0.000077111195,0.00006667949,0.0000099923045,0.0117426785,0.000011751587,0.8265822,0.1567533,0.00015577345],"about_ca_topic_score_codex":0.0000047636527,"about_ca_topic_score_gemma":8.863872e-7,"teacher_disagreement_score":0.38983884,"about_ca_system_score_codex":0.000089148,"about_ca_system_score_gemma":0.00032095058,"threshold_uncertainty_score":0.44617414},"labels":[],"label_agreement":null},{"id":"W2904816621","doi":"10.1093/bioinformatics/bty1019","title":"ModL: exploring and restoring regularity when testing for positive selection","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type I and type II errors; Selection (genetic algorithm); Context (archaeology); Statistics; Statistical power; Null hypothesis; Statistical hypothesis testing; Mathematics; Mixing (physics); Likelihood-ratio test; Power (physics); Model selection; Type (biology); Variety (cybernetics); Chi-square test; Computer science; Artificial intelligence; Biology","score_opus":0.09692745390537694,"score_gpt":0.2875576846226645,"score_spread":0.19063023071728757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904816621","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004552093,0.000017884113,0.9924436,0.00018663643,0.0002434345,0.00018091852,0.0000016537906,0.000121499004,0.0022522497],"genre_scores_gemma":[0.027182665,0.0000025451156,0.97238797,0.00015132602,0.0001940079,0.000019841904,6.7188057e-7,0.00000606425,0.00005492739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993294,0.000019708945,0.00019321832,0.00013074711,0.00011874498,0.00020821927],"domain_scores_gemma":[0.9993659,0.00011421097,0.00008874373,0.00018601092,0.00017723381,0.00006789698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005327513,0.00009297713,0.00010418265,0.00006783351,0.00026276076,0.00016960391,0.00019211345,0.000047641144,3.5184223e-7],"category_scores_gemma":[0.0001826496,0.00008600365,0.000021829048,0.0001577616,0.00004340055,0.0010700064,0.00018140966,0.00006814916,0.0000021847648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008625115,0.000011190257,0.00025197555,0.00008463855,0.000013426929,3.9547427e-7,0.007406994,0.000004274257,0.00084204844,0.11999956,0.00035034865,0.8710265],"study_design_scores_gemma":[0.00024051062,0.00029127373,0.0013388181,0.00007752763,0.000009400335,0.000030576128,0.000042023323,0.9071298,0.009241336,0.0804938,0.00091221766,0.00019271477],"about_ca_topic_score_codex":0.0000147117835,"about_ca_topic_score_gemma":0.0000030061392,"teacher_disagreement_score":0.90712553,"about_ca_system_score_codex":0.000036632362,"about_ca_system_score_gemma":0.000034035733,"threshold_uncertainty_score":0.35071272},"labels":[],"label_agreement":null},{"id":"W2904833574","doi":"10.1177/0962280218815301","title":"Shape invariant mixture model for clustering non-linear longitudinal growth trajectories","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Markov chain Monte Carlo; Mixture model; Computer science; Invariant (physics); Bayesian probability; Bayesian inference; Linear model; Longitudinal data; Inference; Mathematics; Econometrics; Applied mathematics; Data mining; Artificial intelligence; Machine learning","score_opus":0.16600573259292056,"score_gpt":0.5160146234251991,"score_spread":0.35000889083227854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904833574","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000914116,0.00007499463,0.9937416,0.0029344885,0.0005040841,0.0005757827,0.000031570642,0.00006149254,0.0019845907],"genre_scores_gemma":[0.019625023,0.00004633745,0.978763,0.00046540983,0.00065308565,0.00019737915,0.0000052877285,0.000034845456,0.00020962425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923981,0.0024796664,0.00070268445,0.0011329758,0.0018769868,0.0014095927],"domain_scores_gemma":[0.9855357,0.01198398,0.000059860013,0.00071210053,0.00080979633,0.0008986081],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024472091,0.0002762807,0.00059196155,0.00037466036,0.00035881315,0.00015710822,0.0019572866,0.0004338096,0.0002825099],"category_scores_gemma":[0.031338636,0.00022153999,0.00008913905,0.0011528579,0.0011308646,0.00025302116,0.0009989974,0.0015553777,0.000018023367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012574407,0.00011195347,0.000036834917,0.00014879183,0.000017260792,0.00010240684,0.0008188067,0.0000058216633,0.0004634211,0.50663,0.0015145615,0.4900244],"study_design_scores_gemma":[0.00044678044,0.00027982309,0.0002430728,0.000081925326,0.0000040708596,0.000016296339,0.000010422044,0.63454485,0.0005109409,0.36345488,0.000244641,0.00016229953],"about_ca_topic_score_codex":0.00009056311,"about_ca_topic_score_gemma":0.00011180765,"teacher_disagreement_score":0.634539,"about_ca_system_score_codex":0.00012912246,"about_ca_system_score_gemma":0.0009147487,"threshold_uncertainty_score":0.9768208},"labels":[],"label_agreement":null},{"id":"W2905107612","doi":"10.1101/488924","title":"Identifying and Interpreting Subgroups in Health Care Utilization Data with Count Mixture Regression Models","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"Covariate; Negative binomial distribution; Statistics; Count data; Bayesian probability; Econometrics; Poisson regression; Skewness; Mixture model; Overdispersion; Regression analysis; Dispersion (optics); Health care; Binomial regression; Medicine; Logistic regression; Mathematics; Poisson distribution; Environmental health; Economics; Population","score_opus":0.04202427194684579,"score_gpt":0.2964048170238687,"score_spread":0.25438054507702296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905107612","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032736342,0.007914382,0.9572575,0.00033173934,0.0006717103,0.000702691,0.00009605308,0.000278922,0.000010678677],"genre_scores_gemma":[0.5900568,0.0005325157,0.40892345,0.00026669077,0.00012645422,0.000033208333,0.000001626013,0.000058472266,8.488495e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956324,0.0005092174,0.0006689172,0.0020564208,0.0005198968,0.0006131421],"domain_scores_gemma":[0.9954819,0.00007010924,0.0006808249,0.0030710604,0.00042624632,0.00026982932],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018738643,0.0005809051,0.00067677954,0.0003812036,0.00024467424,0.00072865747,0.0019900321,0.00045842957,0.0000023897508],"category_scores_gemma":[0.00009474012,0.0005114734,0.000043083302,0.00063955033,0.00011444491,0.0010958017,0.0030926615,0.0008947194,0.0000019299075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021088978,0.0031637198,0.09430775,0.08887825,0.002532176,0.003143113,0.0468416,0.004164047,0.22526456,0.4949464,0.017401012,0.01724847],"study_design_scores_gemma":[0.0020514042,0.0003487222,0.014550029,0.02507177,0.00011207707,6.391697e-7,0.00007439354,0.93170106,0.019315777,0.0008425762,0.002504475,0.0034270838],"about_ca_topic_score_codex":0.00015687637,"about_ca_topic_score_gemma":0.00004431034,"teacher_disagreement_score":0.927537,"about_ca_system_score_codex":0.00033795505,"about_ca_system_score_gemma":0.000845104,"threshold_uncertainty_score":0.9997337},"labels":[],"label_agreement":null},{"id":"W2907794603","doi":"10.1007/s13042-018-0900-z","title":"Simultaneous clustering and feature selection via nonparametric Pitman–Yor process mixture models","year":2019,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Dirichlet process; Computer science; Mixture model; Artificial intelligence; Machine learning; Cluster analysis; Model selection; Inference; Nonparametric statistics; Hierarchical Dirichlet process; Feature selection; Process (computing); Bayesian inference; Feature (linguistics); Generative model; Bayesian probability; Generative grammar; Latent Dirichlet allocation; Mathematics; Topic model; Econometrics","score_opus":0.005642067798220262,"score_gpt":0.26231530256124425,"score_spread":0.256673234763024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907794603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09765582,0.0014219309,0.8990861,0.0008251384,0.00039112032,0.000062002924,9.4122566e-7,0.000023493107,0.00053343026],"genre_scores_gemma":[0.85907936,0.00034903272,0.13923399,0.0001606935,0.0001506613,5.583873e-7,0.0000010520229,0.000012001962,0.0010126262],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886507,0.000102511,0.00024858167,0.00021639843,0.00041901006,0.00014845506],"domain_scores_gemma":[0.99891394,0.00022549229,0.0003060082,0.00006935885,0.00038498204,0.00010022317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039598567,0.00014926936,0.00020846206,0.00024542885,0.000057640453,0.00022696672,0.00037272766,0.00010628402,0.0000071921313],"category_scores_gemma":[0.000120245066,0.00012226326,0.00005351662,0.00017777023,0.000021320882,0.0003211007,0.00012395777,0.0006794683,0.0000019983677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020091419,0.00012121798,0.010959914,0.0000861846,0.00025794454,0.0001409392,0.002879635,0.17058103,0.002494183,0.0048512425,0.000086166314,0.8073406],"study_design_scores_gemma":[0.00057087035,0.00026937752,0.00031832105,0.00007586686,0.000017212977,0.0015653186,0.000012782716,0.98578286,0.00019190313,0.009494615,0.0015566238,0.00014427469],"about_ca_topic_score_codex":0.000011195207,"about_ca_topic_score_gemma":0.0000046314644,"teacher_disagreement_score":0.8152018,"about_ca_system_score_codex":0.000030872383,"about_ca_system_score_gemma":0.000032850854,"threshold_uncertainty_score":0.49857506},"labels":[],"label_agreement":null},{"id":"W2907815862","doi":"10.1016/j.insmatheco.2020.06.004","title":"Modeling Frequency and Severity of Claims with the Zero-Inflated Generalized Cluster-Weighted Models","year":2018,"lang":"en","type":"preprint","venue":"Insurance Mathematics and Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"University of Wolverhampton; McMaster University","keywords":"Mixture model; Extension (predicate logic); Computer science; Zero (linguistics); Gaussian; Set (abstract data type); Cluster (spacecraft); Contrast (vision); Covariate; Algorithm; Mathematical optimization; Data mining; Mathematics; Artificial intelligence; Machine learning","score_opus":0.025074865688289982,"score_gpt":0.23538952146449513,"score_spread":0.21031465577620514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907815862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4638578,0.00030422592,0.53489596,0.00020911472,0.00008559967,0.00026328422,0.00002631828,0.000026496058,0.00033121664],"genre_scores_gemma":[0.43555436,0.0008969845,0.5633489,0.00010455327,0.000035315585,0.000022245227,0.0000031359125,0.000021496935,0.000013042599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983762,0.00006575209,0.0006030661,0.00058365485,0.00010249026,0.0002688448],"domain_scores_gemma":[0.99819595,0.000094459094,0.0004416859,0.0010092175,0.00016162844,0.000097091215],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007667522,0.0003677968,0.0007134923,0.000075507516,0.00015157103,0.00026181852,0.00072854955,0.00027940373,0.0000013135428],"category_scores_gemma":[0.0000070091346,0.0002510996,0.000081596496,0.000074219526,0.00018745221,0.00028140968,0.00075825857,0.00034564742,6.481481e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009012709,0.00023743702,0.00032409516,0.0023758395,0.00074220914,0.0000073500664,0.019389106,0.11167879,0.00017179959,0.8312418,0.00012839059,0.033613063],"study_design_scores_gemma":[0.00022639714,0.000020476282,0.000014881751,0.00010771909,0.00001771918,0.000016274935,0.0000066778425,0.5460868,0.000055621367,0.4532632,0.000003211938,0.00018106341],"about_ca_topic_score_codex":0.00008565778,"about_ca_topic_score_gemma":0.00003555873,"teacher_disagreement_score":0.43440798,"about_ca_system_score_codex":0.000029644292,"about_ca_system_score_gemma":0.000105357176,"threshold_uncertainty_score":0.9999941},"labels":[],"label_agreement":null},{"id":"W2908726971","doi":"10.1007/s00362-021-01265-w","title":"Confidence intervals with higher accuracy for short and long-memory linear processes","year":2021,"lang":"en","type":"preprint","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Canadian Blood Services; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Mathematics; Limit (mathematics); Applied mathematics; Sample size determination; Central limit theorem; Population; Statistics; Long memory; Econometrics; Mathematical analysis; Demography","score_opus":0.03621878776434152,"score_gpt":0.33287002122305637,"score_spread":0.29665123345871486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908726971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003372063,0.0009940179,0.9952964,0.00076412235,0.00037813355,0.0005743948,0.00010577878,0.00009270492,0.001457229],"genre_scores_gemma":[0.12213109,0.00014485363,0.87576103,0.0010724703,0.00012755918,0.00016111037,0.00005169007,0.000028878114,0.0005213145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978336,0.00012641569,0.0003275334,0.0010481125,0.00030042251,0.0003639229],"domain_scores_gemma":[0.99720925,0.0015353626,0.00009865334,0.0005942638,0.0003258844,0.00023655647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034538744,0.00034065824,0.0005189836,0.000046203153,0.00009064311,0.0004033171,0.0006271866,0.00019865931,0.00008125798],"category_scores_gemma":[0.00072951557,0.00026404776,0.000055770848,0.00012023595,0.0002320966,0.00017977312,0.00066315354,0.00044993148,0.0000016757392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018383597,0.00021309957,0.00017254752,0.007269346,0.0004213989,0.00061538175,0.0019637668,0.00011079531,0.0004756124,0.50195247,0.0017035973,0.48491818],"study_design_scores_gemma":[0.0047554,0.0033761368,0.02213437,0.010564726,0.0016083246,0.0006129162,0.00046658047,0.10059915,0.0075318525,0.81615424,0.02267758,0.009518721],"about_ca_topic_score_codex":0.000018699902,"about_ca_topic_score_gemma":0.000037255035,"teacher_disagreement_score":0.47539943,"about_ca_system_score_codex":0.000029938727,"about_ca_system_score_gemma":0.0005103698,"threshold_uncertainty_score":0.99998116},"labels":[],"label_agreement":null},{"id":"W2909724110","doi":"10.1109/icmla.2018.00195","title":"Asymmetric Gaussian-Based Statistical Models Using Markov Chain Monte Carlo Techniques for Image Categorization","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reversible-jump Markov chain Monte Carlo; Probabilistic latent semantic analysis; Markov chain Monte Carlo; Mixture model; Artificial intelligence; Computer science; Pattern recognition (psychology); Scale-invariant feature transform; Gaussian process; Gaussian; Machine learning; Markov chain; Feature extraction; Bayesian probability","score_opus":0.029554045271030574,"score_gpt":0.31106585729959063,"score_spread":0.28151181202856007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909724110","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003655714,0.000032251406,0.9942369,0.00035928917,0.00017908268,0.0005347288,0.000021029133,0.00030572014,0.004294455],"genre_scores_gemma":[0.1507045,0.0000026368502,0.84839326,0.00049351546,0.00015174322,0.000041487332,0.000004571056,0.000021862124,0.00018644222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998406,0.0001394273,0.0002952338,0.00052325166,0.00023737477,0.00039873537],"domain_scores_gemma":[0.9987573,0.00021276703,0.00009517665,0.0004943921,0.0003028942,0.00013745658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007750391,0.00019687426,0.00023249158,0.00024309216,0.00018355608,0.00020876646,0.00047045515,0.000121279234,0.000010649962],"category_scores_gemma":[0.00010361622,0.0001660367,0.000068404705,0.0006655493,0.00008860952,0.00052592286,0.00008684152,0.00008956339,0.0000022493725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023273642,0.00006883533,0.000007516057,0.000040365838,0.000012099056,0.000006937186,0.00010195035,0.00008622911,0.002581502,0.67801535,0.002203062,0.31685287],"study_design_scores_gemma":[0.00020586602,0.00014930441,0.000010252406,0.000011305431,0.000011883024,0.000004907734,0.0000019251113,0.8833279,0.018890234,0.09699151,0.00018816262,0.00020675227],"about_ca_topic_score_codex":0.00016941305,"about_ca_topic_score_gemma":0.00001228147,"teacher_disagreement_score":0.88324165,"about_ca_system_score_codex":0.000081710445,"about_ca_system_score_gemma":0.00015456713,"threshold_uncertainty_score":0.67707795},"labels":[],"label_agreement":null},{"id":"W2910422014","doi":"10.1109/icmla.2018.00090","title":"Bounded Laplace Mixture Model with Applications to Image Clustering and Content Based Image Retrieval","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Pattern recognition (psychology); Cluster analysis; Wavelet; Artificial intelligence; Content-based image retrieval; Computer science; Feature extraction; Image retrieval; Wavelet transform; Mathematics; Image (mathematics)","score_opus":0.028901094107865097,"score_gpt":0.2828759864758919,"score_spread":0.2539748923680268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910422014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016193988,0.000014609869,0.9891737,0.0034084672,0.00003462697,0.0004972619,0.0000054518214,0.00016505917,0.0050814003],"genre_scores_gemma":[0.026426919,0.0000014619663,0.96929,0.0026335055,0.000062075254,0.000034331828,0.0000012549999,0.0000144867045,0.0015359729],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988113,0.00004634843,0.00015485338,0.0005152171,0.00019268118,0.0002796086],"domain_scores_gemma":[0.9988326,0.00004695437,0.00004585539,0.0006288229,0.00022483275,0.00022097913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033110523,0.00016622803,0.00016981954,0.00007538479,0.00019196849,0.0003184723,0.0004249747,0.000060178038,0.0000103582615],"category_scores_gemma":[0.000016682892,0.00012343499,0.00002918602,0.00030465887,0.000113401446,0.00035378308,0.00020906895,0.000107270025,0.000018302862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041756124,0.00020872091,0.000032061635,0.00011632065,0.000056709814,0.000022471913,0.0022746953,0.000107519154,0.6651864,0.2899385,0.0035166955,0.03812235],"study_design_scores_gemma":[0.00066822715,0.00020891547,0.0000488901,0.000023504073,0.0000122723495,0.00002311727,0.000024171464,0.9230175,0.06860813,0.005967485,0.0010967058,0.0003010591],"about_ca_topic_score_codex":0.000016842858,"about_ca_topic_score_gemma":0.000049411643,"teacher_disagreement_score":0.92291003,"about_ca_system_score_codex":0.000030446947,"about_ca_system_score_gemma":0.00008267529,"threshold_uncertainty_score":0.5033533},"labels":[],"label_agreement":null},{"id":"W2910497671","doi":"10.1007/s10044-018-00767-y","title":"A nonparametric Bayesian learning model using accelerated variational inference and feature selection","year":2019,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Feature selection; Artificial intelligence; Nonparametric statistics; Bayesian inference; Inference; Computer science; Selection (genetic algorithm); Pattern recognition (psychology); Machine learning; Model selection; Feature (linguistics); Bayesian probability; Mathematics; Econometrics","score_opus":0.02184809992247997,"score_gpt":0.29730838640841345,"score_spread":0.27546028648593346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910497671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018653905,0.00006742631,0.9806695,0.00020651506,0.000006654512,0.00016310342,0.0000033030237,0.000044224274,0.00018534815],"genre_scores_gemma":[0.7159106,0.000027481894,0.28376576,0.000115117604,0.000018124794,0.000016670978,0.000010425276,0.000004224599,0.0001315777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908614,0.000064158194,0.00014415977,0.00042945502,0.00013347474,0.00014259231],"domain_scores_gemma":[0.9994358,0.000079155034,0.000108680855,0.00019953151,0.00009789026,0.000078947465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020910258,0.00011423204,0.00019212389,0.00034905868,0.00020253315,0.0002529499,0.00015389829,0.00007415227,0.000014565537],"category_scores_gemma":[0.000008888158,0.00010554752,0.000052445153,0.0019371111,0.000013913057,0.00023352931,0.00008353684,0.00017266441,0.0000033389797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000330347,0.00010528067,0.22014585,0.000041402633,0.00049965794,4.2616503e-7,0.000535994,0.10921013,0.009320337,0.05534911,0.000014988771,0.6047735],"study_design_scores_gemma":[0.00009573801,0.000009001047,0.015455829,0.000003304006,0.00012554639,0.000002937427,0.0000036611298,0.9768555,0.00010378936,0.0071707238,0.000049697006,0.00012425781],"about_ca_topic_score_codex":0.0000719622,"about_ca_topic_score_gemma":0.000017785082,"teacher_disagreement_score":0.8676454,"about_ca_system_score_codex":0.000019620269,"about_ca_system_score_gemma":0.000033143406,"threshold_uncertainty_score":0.43041033},"labels":[],"label_agreement":null},{"id":"W2912762941","doi":"10.1109/mwscas.2018.8623978","title":"A Smoothed Latent Generalized Dirichlet Allocation Model in the Collapsed Space","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Gibbs sampling; Inference; Computer science; Dirichlet distribution; Latent variable; Algorithm; Bayesian inference; Simple (philosophy); Artificial intelligence; Topic model; Hierarchical Dirichlet process; Nonparametric statistics; GRASP; Bayesian probability; Mathematical optimization; Applied mathematics; Mathematics; Statistics","score_opus":0.030511728883397236,"score_gpt":0.287534463416408,"score_spread":0.2570227345330107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912762941","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012213769,0.000031951688,0.96776485,0.008133679,0.0001002058,0.00023676212,3.9704537e-7,0.000064492364,0.01145391],"genre_scores_gemma":[0.36904776,0.000008396189,0.626406,0.0031322178,0.000047509402,0.000023650247,5.819925e-7,0.0000046406763,0.0013292202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892795,0.0002140928,0.00015827962,0.00027917905,0.0002035639,0.00021694366],"domain_scores_gemma":[0.99921626,0.0000424963,0.000042070395,0.00058665156,0.00007178399,0.000040754312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008387824,0.00010416185,0.00011710143,0.000065355416,0.00007804283,0.0001147007,0.00072966196,0.00005413911,0.000012724948],"category_scores_gemma":[0.000021417583,0.00006257251,0.000039360988,0.0004408432,0.000040780124,0.00016752887,0.00008720432,0.00007087206,0.000023593946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008753931,0.000054387332,0.00004950925,0.0000023396644,0.0000048018674,0.0000022368108,0.0026796667,0.00025299392,0.0031786596,0.9796967,0.005399643,0.008670287],"study_design_scores_gemma":[0.000374133,0.000036757472,0.00034857914,0.0000041519,0.0000027209676,0.0000035078044,0.0000066815865,0.90632683,0.0019857062,0.08978592,0.0010225712,0.00010243511],"about_ca_topic_score_codex":0.00012120983,"about_ca_topic_score_gemma":0.00014549564,"teacher_disagreement_score":0.90607387,"about_ca_system_score_codex":0.000024923367,"about_ca_system_score_gemma":0.00006137648,"threshold_uncertainty_score":0.25516328},"labels":[],"label_agreement":null},{"id":"W2912850978","doi":"10.5555/3320516.3320723","title":"On a generalized splitting method for sampling from a conditional distribution","year":2018,"lang":"en","type":"article","venue":"Winter Simulation Conference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Conditional probability distribution; Mathematics; Event (particle physics); Estimator; Sampling distribution; Rare events; Statistics; Distribution (mathematics); Applied mathematics; Sampling (signal processing); Combinatorics; Computer science; Mathematical analysis; Physics","score_opus":0.08035900643123026,"score_gpt":0.3862331665830063,"score_spread":0.30587416015177604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912850978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042181253,0.000006480735,0.9939884,0.0005583767,0.00039600357,0.00025006896,0.0001381519,0.000107043525,0.00033733816],"genre_scores_gemma":[0.50078577,1.7127869e-7,0.49829894,0.00050638436,0.0002142797,0.000017644119,0.000119236465,0.000004725078,0.000052827698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998698,0.00015095354,0.0002745295,0.00048705685,0.00017759937,0.00021185294],"domain_scores_gemma":[0.9981082,0.0009530418,0.00013612452,0.0003426674,0.00038570835,0.00007423941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043831056,0.00014665486,0.00017673578,0.000048719216,0.00018687441,0.0002087835,0.00034225002,0.00008250921,0.000103543156],"category_scores_gemma":[0.00025273257,0.00013618999,0.000088747336,0.00011622038,0.00003708206,0.00028431142,0.000077789664,0.000087938715,0.000025949286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060621252,0.000028084354,0.000016684406,0.0000048324428,0.00002259244,4.3023553e-7,0.00047835894,0.002467559,0.0017522342,0.9065359,0.00027967853,0.08835301],"study_design_scores_gemma":[0.00039467379,0.0000653133,0.00025523975,0.000030226653,0.0000058428336,5.4933116e-7,0.0000021427993,0.6233847,0.0018584188,0.37203032,0.0018663794,0.00010616333],"about_ca_topic_score_codex":0.000017320337,"about_ca_topic_score_gemma":0.0000049313976,"teacher_disagreement_score":0.6209172,"about_ca_system_score_codex":0.00004447093,"about_ca_system_score_gemma":0.000055274024,"threshold_uncertainty_score":0.55536664},"labels":[],"label_agreement":null},{"id":"W2912973495","doi":"10.1002/9781118445112.stat05723","title":"Systematic Sampling Methods","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Systematic sampling; Sampling (signal processing); Simple random sample; Sampling design; Statistics; Mathematics; Estimator; Slice sampling; Variance (accounting); Stratified sampling; Bias of an estimator; Poisson sampling; Population; Best linear unbiased prediction; Sample (material); Population variance; Importance sampling; Computer science; Minimum-variance unbiased estimator; Monte Carlo method; Selection (genetic algorithm); Artificial intelligence","score_opus":0.06010382286384224,"score_gpt":0.3866030518802719,"score_spread":0.32649922901642964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912973495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.305318e-8,0.0031684425,0.9467288,0.00006569476,0.001154623,0.0007812006,0.0026083372,0.00069976045,0.04479305],"genre_scores_gemma":[0.0000025985105,0.0013700644,0.8619829,0.00038214252,0.00033565462,0.000065982196,0.00063590513,0.00046023086,0.13476455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944119,0.0014470924,0.0011879969,0.0013383203,0.00075693143,0.0008577834],"domain_scores_gemma":[0.9944808,0.0012701359,0.0011955841,0.0023796263,0.00025365493,0.00042018737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015679997,0.00090121134,0.0018517923,0.00058429333,0.00013104212,0.00033361476,0.0023261774,0.00060736237,0.00043274468],"category_scores_gemma":[0.0008147523,0.0007520685,0.00013668124,0.00048020342,0.00014459349,0.00011447163,0.0005371462,0.00088182266,0.00027129802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040179434,0.0001337264,9.895662e-7,0.011504961,0.00022991665,0.00003322092,0.00012498083,0.0000054374896,0.000045783017,0.6739918,0.1809208,0.13300435],"study_design_scores_gemma":[0.0009798708,0.00040699024,0.000011343597,0.027775312,0.00055128516,0.000090017034,0.000029172852,0.08481846,0.000032845957,0.3723893,0.5098188,0.0030966015],"about_ca_topic_score_codex":0.00013383273,"about_ca_topic_score_gemma":0.0001646674,"teacher_disagreement_score":0.328898,"about_ca_system_score_codex":0.00010830135,"about_ca_system_score_gemma":0.00032144264,"threshold_uncertainty_score":0.999493},"labels":[],"label_agreement":null},{"id":"W2913504915","doi":"10.1002/cjs.11484","title":"Modelling hierarchical clustered censored data with the hierarchical Kendall copula","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Goodness of fit; Copula (linguistics); Estimator; Statistics; Mathematics; Cluster analysis; Econometrics; Censoring (clinical trials); Marginal model; Hierarchical clustering; Imputation (statistics); Hierarchical database model; Statistical hypothesis testing; Missing data; Computer science; Regression analysis; Data mining","score_opus":0.0344791499458552,"score_gpt":0.25595470360669975,"score_spread":0.22147555366084454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913504915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016985488,0.00016993366,0.99320847,0.0036285026,0.0003927407,0.00012957824,0.00022437575,0.0000066067805,0.00054121827],"genre_scores_gemma":[0.16317664,0.000017319298,0.83565277,0.0007419108,0.00013558603,4.7082307e-7,0.000014201853,0.000016682045,0.00024441455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983082,0.0002403346,0.0003660747,0.00027628485,0.00036760652,0.0004415135],"domain_scores_gemma":[0.9975174,0.0003774707,0.00021576144,0.0009466926,0.0002274952,0.00071514345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082853565,0.00016030221,0.00028658626,0.00014937956,0.00017003823,0.00027290365,0.0022500039,0.00007194044,0.000035204284],"category_scores_gemma":[0.00007322744,0.000101069854,0.000036866102,0.00021659525,0.00016483135,0.00029981547,0.0001095097,0.0007134705,0.00001091545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075115444,0.000029060056,0.0004661563,0.000048498812,0.000145242,0.0011459125,0.0024099762,0.017298961,0.000026728361,0.8521191,0.036944892,0.08929035],"study_design_scores_gemma":[0.0006045415,0.00023602744,0.00023377594,0.00006674048,0.00003489798,0.00059042615,0.00002884278,0.9201948,0.000006511763,0.047063112,0.030722195,0.00021814964],"about_ca_topic_score_codex":0.0006481357,"about_ca_topic_score_gemma":0.0023421387,"teacher_disagreement_score":0.9028958,"about_ca_system_score_codex":0.00006569581,"about_ca_system_score_gemma":0.0017003092,"threshold_uncertainty_score":0.41811043},"labels":[],"label_agreement":null},{"id":"W2913752236","doi":"10.1016/j.jmva.2019.01.002","title":"Note of Clarification on ‘Hidden truncation hyperbolic distributions, finite mixtures thereof, and their application for clustering’, by Murray, Browne, and McNicholas, J. Multivariate Anal. 161 (2017) 141–156","year":2019,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo; McMaster University","funders":"Canada Research Chairs","keywords":"Mathematics; Truncation (statistics); Multivariate statistics; Cluster analysis; Applied mathematics; Statistics; Pure mathematics","score_opus":0.01356322077687148,"score_gpt":0.28277929625775605,"score_spread":0.26921607548088455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913752236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0398368,0.00054850866,0.9582811,0.0006664094,0.00009841761,0.00038823558,0.00009476539,0.000016570035,0.00006916358],"genre_scores_gemma":[0.8344923,0.00029890353,0.16487888,0.00009591866,0.00006625467,0.000016285723,0.00005098565,0.000013617372,0.00008684769],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786574,0.00035595067,0.0008021977,0.0004661039,0.0002740073,0.00023600881],"domain_scores_gemma":[0.9968469,0.0006927081,0.001239576,0.0005994876,0.00047954507,0.00014178676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017279229,0.00026092934,0.0006644681,0.0004602482,0.0001546895,0.00014215923,0.0004984458,0.00020948473,0.0000047359486],"category_scores_gemma":[0.00023494585,0.00019164337,0.00028964703,0.0007101752,0.00004999321,0.00054606644,0.000090148445,0.00028579362,0.0000018947277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047736606,0.0005693198,0.0018614625,0.0001437383,0.0020198692,0.0000012322673,0.0029646563,0.0017878677,0.6496798,0.015195049,0.00033358546,0.32496604],"study_design_scores_gemma":[0.0027852799,0.0004651365,0.0382491,0.000101325226,0.0010232537,0.000017542825,0.000066441804,0.91523516,0.024139859,0.01367478,0.003754829,0.0004873058],"about_ca_topic_score_codex":0.00019137963,"about_ca_topic_score_gemma":0.000019303927,"teacher_disagreement_score":0.91344726,"about_ca_system_score_codex":0.00006181033,"about_ca_system_score_gemma":0.000059949154,"threshold_uncertainty_score":0.78149897},"labels":[],"label_agreement":null},{"id":"W2915237405","doi":"10.1080/07474938.2022.2140982","title":"Hamiltonian sequential Monte Carlo with application to consumer choice behavior","year":2023,"lang":"en","type":"article","venue":"Econometric Reviews","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canada Foundation for Innovation","keywords":"Markov chain Monte Carlo; Particle filter; Monte Carlo method; Computer science; Hybrid Monte Carlo; Bayesian inference; Random walk; Nonparametric statistics; Scalability; Bayesian probability; Algorithm; Statistical physics; Mathematical optimization; Econometrics; Artificial intelligence; Mathematics; Statistics; Physics; Kalman filter","score_opus":0.05111570066422108,"score_gpt":0.3235668275476152,"score_spread":0.2724511268833941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915237405","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007338152,0.003530384,0.98491174,0.00049821596,0.00026028333,0.0013720425,0.000006260371,0.00015957028,0.0019233524],"genre_scores_gemma":[0.11869458,0.004473154,0.86557627,0.0022674005,0.00036315812,0.003168435,0.000014292579,0.00006285055,0.0053798663],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984071,0.00012284411,0.00041613416,0.00060636713,0.00012590365,0.00032164415],"domain_scores_gemma":[0.9985285,0.000087728295,0.00016888924,0.0009511805,0.000048977563,0.00021476147],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010256296,0.00018256278,0.0004111793,0.000651884,0.00009396982,0.00014476734,0.0007377014,0.000054608605,0.000023631397],"category_scores_gemma":[0.00009147774,0.00014334107,0.000103388906,0.0040075704,0.000020799076,0.00031207345,0.00016287217,0.00011566477,0.0013771019],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011575156,0.00002369962,0.0020003116,0.000030916854,0.000010477917,0.0000051264983,0.000118688375,0.00002869322,0.00005998196,0.002963484,0.0049131103,0.9898444],"study_design_scores_gemma":[0.00023705409,0.000084945736,0.024039038,0.000031667776,0.00003394543,0.000015188059,0.000001958016,0.005468468,0.000093500035,0.00022129268,0.9694221,0.00035085392],"about_ca_topic_score_codex":0.00009317515,"about_ca_topic_score_gemma":0.00004659794,"teacher_disagreement_score":0.9894935,"about_ca_system_score_codex":0.00006792051,"about_ca_system_score_gemma":0.000043500655,"threshold_uncertainty_score":0.99940044},"labels":[],"label_agreement":null},{"id":"W2919572811","doi":"10.48550/arxiv.1903.00655","title":"A Bayesian Nonparametric Estimation to Entropy","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Dirichlet process; Frequentist inference; Mathematics; Minimum-variance unbiased estimator; Bayes estimator; Applied mathematics; Statistics; Dirichlet distribution; Bayesian probability; Econometrics; Computer science; Bayesian inference","score_opus":0.04809146997250294,"score_gpt":0.2111298399296303,"score_spread":0.16303836995712737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919572811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009546232,0.000039842067,0.984739,0.00025759835,0.0009916732,0.00060131215,0.000009114236,0.00024912876,0.0035661065],"genre_scores_gemma":[0.64502895,0.000023971119,0.35305536,0.0002594321,0.000046540816,0.000001238772,0.0000060556995,0.000015352784,0.0015631331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759954,0.00022701593,0.00022119033,0.0013837534,0.00013453029,0.00043395616],"domain_scores_gemma":[0.9973607,0.00014598621,0.0002115929,0.001832854,0.00014505914,0.00030383118],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003966799,0.0003559321,0.00042947175,0.00072672305,0.00009686276,0.00021925011,0.0020918637,0.00034123304,0.000028281731],"category_scores_gemma":[0.00008425641,0.0004010763,0.00023533904,0.0014433574,0.000031694613,0.00035146295,0.0018778124,0.0005423037,0.0004053506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000219099,0.00008200149,0.0003393733,0.0000837778,0.000060069517,0.00013123639,0.00025436404,0.41331363,0.000040388586,0.5632758,0.0009693143,0.021428132],"study_design_scores_gemma":[0.00022987564,0.00005937119,0.00028624004,0.0000624554,0.0000370388,0.0000039479555,0.0000036328431,0.83172053,0.00012972488,0.16664925,0.0004200859,0.00039783615],"about_ca_topic_score_codex":0.000080433725,"about_ca_topic_score_gemma":0.0000057546376,"teacher_disagreement_score":0.63548267,"about_ca_system_score_codex":0.00025659415,"about_ca_system_score_gemma":0.00023281224,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W2921173295","doi":"10.1080/03610926.2019.1584310","title":"Composite likelihood for aggregate data from clustered multistate processes under intermittent observation","year":2019,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Aggregate (composite); Inference; Cluster analysis; Markov chain; Basis (linear algebra); Computer science; Random effects model; Variance (accounting); Statistical inference; Statistics; Econometrics; Mathematics; Artificial intelligence","score_opus":0.08104833944939369,"score_gpt":0.4054631874973751,"score_spread":0.3244148480479814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921173295","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002835361,0.0022500814,0.99321485,0.00036015577,0.00027332993,0.0005814749,0.00030229424,0.000053008553,0.00012945532],"genre_scores_gemma":[0.024916146,0.0006949127,0.9729661,0.00059865793,0.000016769818,0.000062369036,0.0004652141,0.000017776649,0.0002620819],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99619335,0.0025356694,0.0004490956,0.00050551095,0.00009989501,0.00021649893],"domain_scores_gemma":[0.99142444,0.0059753344,0.0002739693,0.002063212,0.0001886376,0.00007437857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004343727,0.0001760898,0.00030230192,0.00008378167,0.00013418445,0.00018813614,0.0016714681,0.00008391694,0.0000095754685],"category_scores_gemma":[0.0006489459,0.00016522201,0.000020225885,0.00020087101,0.00009246355,0.0005995909,0.0009894922,0.0002017748,0.000004684437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010930306,0.000066125656,0.0002646567,0.00013486184,0.00003149179,4.8739065e-7,0.0015984394,0.00002145944,0.0015727753,0.3944212,0.00012426531,0.60165495],"study_design_scores_gemma":[0.0008658944,0.00004063939,0.0041882033,0.00020069406,0.000024942703,0.000002359375,0.0000839909,0.18076503,0.00089010823,0.81094414,0.001786771,0.00020720676],"about_ca_topic_score_codex":0.000050517396,"about_ca_topic_score_gemma":0.000061203194,"teacher_disagreement_score":0.6014477,"about_ca_system_score_codex":0.000030804073,"about_ca_system_score_gemma":0.00008014954,"threshold_uncertainty_score":0.67375576},"labels":[],"label_agreement":null},{"id":"W2921547035","doi":"10.1007/s10489-019-01437-0","title":"Hybrid generative discriminative approaches based on Multinomial Scaled Dirichlet mixture models","year":2019,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Computer science; Generative grammar; Multinomial distribution; Generative model; Machine learning; Artificial intelligence; Support vector machine; Dirichlet distribution; Generative Design; Latent Dirichlet allocation; Pattern recognition (psychology); Topic model; Mathematics","score_opus":0.046803210809598934,"score_gpt":0.25666143142061354,"score_spread":0.2098582206110146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921547035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024195802,0.0000510529,0.94410163,0.0004494939,0.00033200948,0.0008472373,0.000013055054,0.00015899415,0.051626917],"genre_scores_gemma":[0.5775607,0.0000051833563,0.42112607,0.0008300543,0.00007424788,0.00009416788,0.000009212287,0.000019982908,0.00028035132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722564,0.00017807304,0.00038465028,0.0011920241,0.00047971116,0.000539883],"domain_scores_gemma":[0.9980567,0.00037570097,0.00017309937,0.0011253495,0.000086940774,0.00018220278],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005349115,0.00044033895,0.0004413121,0.0001644422,0.0001543426,0.0001792178,0.0014161833,0.0001367806,0.00004616024],"category_scores_gemma":[0.000026789936,0.0003560446,0.00015291826,0.00033890142,0.00012421088,0.0003509017,0.00026332214,0.00046652486,0.00023382623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006741854,0.00018682609,0.0000053855697,0.000023775307,0.000021609407,0.000007771933,0.0011758248,0.027726337,0.0017245767,0.7434536,0.00043458666,0.22517225],"study_design_scores_gemma":[0.0001963226,0.00013803755,0.000013160076,0.00002352387,0.000008925867,0.0000031359057,0.000043489545,0.7610927,0.12663223,0.11126121,0.00018916285,0.00039804497],"about_ca_topic_score_codex":0.000010256564,"about_ca_topic_score_gemma":0.0000015941758,"teacher_disagreement_score":0.73336643,"about_ca_system_score_codex":0.00008863518,"about_ca_system_score_gemma":0.00010105747,"threshold_uncertainty_score":0.99988914},"labels":[],"label_agreement":null},{"id":"W2922529999","doi":"10.1007/s00357-024-09479-x","title":"Flexible Clustering with a Sparse Mixture of Generalized Hyperbolic Distributions","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Cluster analysis; Parametrization (atmospheric modeling); Covariance; Mathematics; Covariance matrix; Component (thermodynamics); Interpretation (philosophy); Matrix (chemical analysis); Clustering high-dimensional data; Mixture model; Algorithm; Computer science; Applied mathematics; Statistics","score_opus":0.037729005645200264,"score_gpt":0.2992783221185225,"score_spread":0.26154931647332225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922529999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074669044,0.000916456,0.9880754,0.002530957,0.00030416687,0.00006056374,0.0000038408143,0.0000308672,0.0006108605],"genre_scores_gemma":[0.5795296,0.00008920309,0.42007533,0.00003134865,0.000118885415,0.0000023147227,0.0000014229512,0.000005839773,0.00014606558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908674,0.00008533622,0.00035389428,0.00013107825,0.00023259352,0.0001103768],"domain_scores_gemma":[0.9991975,0.000054911372,0.0002324294,0.00024330163,0.00020148681,0.000070411734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047223436,0.000083402774,0.00018240535,0.00015157783,0.0000407692,0.000105647705,0.00031858947,0.000054953303,0.0000057176417],"category_scores_gemma":[0.000025433006,0.000056691464,0.00009046362,0.0004500297,0.000033831308,0.00042685764,0.000028358249,0.00017503569,0.0000022450024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005684119,0.00011365635,0.00009102429,0.00012549773,0.00011223254,0.00003480899,0.00084970193,0.00026194614,0.1599978,0.5976136,0.0025565892,0.23818631],"study_design_scores_gemma":[0.0018733443,0.00089810987,0.014301251,0.0014236275,0.0003147976,0.0021950544,0.00008684601,0.67871696,0.10514747,0.11400681,0.08038071,0.00065502024],"about_ca_topic_score_codex":0.0000024990877,"about_ca_topic_score_gemma":0.0000017271096,"teacher_disagreement_score":0.678455,"about_ca_system_score_codex":0.000046347646,"about_ca_system_score_gemma":0.00017173345,"threshold_uncertainty_score":0.23118109},"labels":[],"label_agreement":null},{"id":"W2944505589","doi":"10.1109/isivc.2018.8709190","title":"Learning of Finite Two-Dimensional Beta Mixture Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Mixture model; Expectation–maximization algorithm; Focus (optics); Gaussian; Statistical model; Artificial intelligence; Maximization; Machine learning; Bivariate analysis; Segmentation; Data modeling; Data mining; Mathematics; Mathematical optimization; Maximum likelihood; Statistics","score_opus":0.022750722360675952,"score_gpt":0.27525244776056323,"score_spread":0.2525017253998873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944505589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037752315,0.00006744684,0.9599418,0.00045125326,0.00019304117,0.0000568736,7.23132e-7,0.000092798764,0.0354208],"genre_scores_gemma":[0.4173473,0.0000012908165,0.5803538,0.00038092557,0.00007911847,0.0000013279414,7.0172786e-7,0.000005303782,0.0018302571],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989038,0.00012093717,0.0002000162,0.00031439145,0.00023970152,0.0002211266],"domain_scores_gemma":[0.999117,0.00014017634,0.00007940622,0.00039869786,0.00018228313,0.000082403545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044910825,0.0001168227,0.00017831849,0.00007945022,0.00009582262,0.000034270182,0.0004919905,0.000066213615,0.00007779151],"category_scores_gemma":[0.000023518049,0.000090445894,0.000067658504,0.0002549215,0.000078486744,0.00033828893,0.00025666435,0.0001595263,0.00003137459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008197832,0.000039082246,0.000038570368,0.000007870605,0.000021125317,0.0000042567367,0.0007835684,0.0044229995,0.005439468,0.8983181,0.0014678662,0.08944888],"study_design_scores_gemma":[0.00022928709,0.00014216307,0.000031650052,0.000016546335,0.0000049541845,0.000008373145,0.0000026547311,0.8240309,0.015344326,0.15948065,0.00057640544,0.00013211412],"about_ca_topic_score_codex":0.000024245734,"about_ca_topic_score_gemma":0.0000036571696,"teacher_disagreement_score":0.8196079,"about_ca_system_score_codex":0.00000708812,"about_ca_system_score_gemma":0.000052996686,"threshold_uncertainty_score":0.36882764},"labels":[],"label_agreement":null},{"id":"W2948643372","doi":"10.1002/sim.8213","title":"Analysis of clustered failure time data with cure fraction using copula","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Center for Advancing Translational Sciences; Assam Science Technology and Environment Council","keywords":"Akaike information criterion; Jackknife resampling; Copula (linguistics); Estimator; Statistics; Logistic regression; Computer science; Econometrics; Mathematics","score_opus":0.031513655357949436,"score_gpt":0.3467253180189006,"score_spread":0.3152116626609512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948643372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026526374,0.0000598202,0.99631387,0.000272144,0.00009826401,0.00012747948,0.00008669375,0.000012280995,0.0003767848],"genre_scores_gemma":[0.07387659,0.00001213327,0.92566127,0.00012668814,0.000034775232,6.6509597e-7,0.00016315866,0.0000068427985,0.00011790857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876344,0.0001206149,0.00028583242,0.00034725107,0.0003386194,0.00014424349],"domain_scores_gemma":[0.99841154,0.00023868261,0.00019162952,0.0010091641,0.00010019581,0.000048807102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007128662,0.00010411702,0.00043717862,0.00030938498,0.00002004735,0.000012344858,0.00057324884,0.00005215284,0.00013822489],"category_scores_gemma":[0.00009336372,0.00007536704,0.000011957483,0.0010510342,0.00006150533,0.00018652607,0.00014530368,0.00016340277,0.000004392963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004031484,0.0006039049,0.10582017,0.0010249593,0.004029477,0.00045635633,0.0089379,0.01663907,0.024007222,0.438534,0.040405273,0.35913852],"study_design_scores_gemma":[0.00049526506,0.00010996743,0.002431474,0.00010093814,0.00028536958,0.0000048341526,0.000036177425,0.9910197,0.000019732728,0.0049781143,0.0004210394,0.00009738205],"about_ca_topic_score_codex":0.00021651264,"about_ca_topic_score_gemma":0.00012851438,"teacher_disagreement_score":0.9743806,"about_ca_system_score_codex":0.000035329565,"about_ca_system_score_gemma":0.000056510566,"threshold_uncertainty_score":0.30733788},"labels":[],"label_agreement":null},{"id":"W2948668635","doi":"10.1109/cybermatics_2018.2018.00158","title":"A Finite Multi-Dimensional Generalized Gamma Mixture Model","year":2018,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Expectation–maximization algorithm; Computer science; Cluster analysis; Data modeling; Statistical model; Pattern recognition (psychology); Artificial intelligence; Algorithm; Data set; Set (abstract data type); Synthetic data; Mathematics; Maximum likelihood; Statistics","score_opus":0.03759180638511697,"score_gpt":0.29563269045377094,"score_spread":0.258040884068654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948668635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011045855,0.00007745467,0.991478,0.0011781355,0.0003175058,0.000113819515,0.0000027562057,0.00022098095,0.005506729],"genre_scores_gemma":[0.03470953,0.0000037986704,0.94893426,0.005175456,0.00016647177,0.000010136879,0.0000018476818,0.000011970593,0.010986527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865454,0.00009375231,0.00019759787,0.00048362117,0.0002340888,0.0003363883],"domain_scores_gemma":[0.9989251,0.00005705227,0.00004998989,0.0006405239,0.00016445841,0.00016286515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000329761,0.00017575224,0.00018162405,0.00008070068,0.00014534956,0.000092281676,0.0006390078,0.00011724214,0.00009653901],"category_scores_gemma":[0.000035239478,0.00013108402,0.00009669008,0.00023337801,0.00007025982,0.00027917325,0.00027505757,0.00012492904,0.00014198768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028988248,0.00018478886,0.000021719092,0.000009573107,0.000042294338,0.000026104584,0.0010535311,0.00188727,0.020354886,0.8593628,0.035858046,0.081170045],"study_design_scores_gemma":[0.00050972943,0.00003871555,0.000023592915,0.0000062743698,0.0000040474883,0.000012902414,4.9812235e-7,0.93884575,0.005830768,0.052241832,0.0022931607,0.00019270461],"about_ca_topic_score_codex":0.000016739054,"about_ca_topic_score_gemma":0.000017022498,"teacher_disagreement_score":0.9369585,"about_ca_system_score_codex":0.000015183991,"about_ca_system_score_gemma":0.000089026704,"threshold_uncertainty_score":0.53454506},"labels":[],"label_agreement":null},{"id":"W2949498201","doi":"10.48550/arxiv.1005.3430","title":"Simulation-based Regularized Logistic Regression","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"Engineering and Physical Sciences Research Council","keywords":"Regularization (linguistics); Logistic regression; Estimator; Computer science; Maximum a posteriori estimation; Markov chain Monte Carlo; R package; Flexibility (engineering); Mathematics; Statistics; Data mining; Maximum likelihood; Artificial intelligence; Bayesian probability","score_opus":0.1101581852571016,"score_gpt":0.24354848396191436,"score_spread":0.13339029870481278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949498201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0093084555,0.00002477881,0.98767626,0.00015320738,0.0009971362,0.0002944162,0.000008419587,0.00033136318,0.0012059582],"genre_scores_gemma":[0.75589275,0.0000070316823,0.24274935,0.00014915524,0.00008016471,7.218168e-7,0.000014422793,0.000016404598,0.0010899672],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774677,0.0003222143,0.00021967177,0.0012474869,0.00012377258,0.00034010859],"domain_scores_gemma":[0.99648553,0.0006699936,0.0003306099,0.002074553,0.00022712376,0.00021216708],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047762302,0.00036227968,0.0004019738,0.00026419677,0.00019318041,0.00014868441,0.0018843362,0.00069418276,0.000042054387],"category_scores_gemma":[0.0002592311,0.0003547315,0.0002679556,0.00042167155,0.0001328639,0.00020712616,0.0010904514,0.0010710012,0.000038256185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031365566,0.00006459227,0.00010016161,0.00005389685,0.000023075901,0.00024091285,0.000045265075,0.7466639,0.00018084439,0.24910769,0.000060665105,0.0034276263],"study_design_scores_gemma":[0.00038120957,0.00001793244,0.000079050464,0.00007425403,0.000036898913,6.59467e-7,9.047469e-7,0.7510206,0.00016292352,0.2476758,0.00023845011,0.00031129603],"about_ca_topic_score_codex":0.000040014413,"about_ca_topic_score_gemma":0.000010514261,"teacher_disagreement_score":0.74658436,"about_ca_system_score_codex":0.000100575984,"about_ca_system_score_gemma":0.0003416563,"threshold_uncertainty_score":0.99989045},"labels":[],"label_agreement":null},{"id":"W2950022903","doi":"10.1080/24754269.2019.1630544","title":"Empirical likelihood estimation in multivariate mixture models with repeated measurements","year":2019,"lang":"en","type":"article","venue":"Statistical Theory and Related Fields","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Multivariate statistics; Statistics; Nonparametric statistics; Mixture model; Parametric statistics; Mathematics; Econometrics; Multivariate analysis; Maximum likelihood; Parametric model; Dimension (graph theory); Empirical likelihood; Estimator","score_opus":0.019993018121504467,"score_gpt":0.2922783202139258,"score_spread":0.27228530209242136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950022903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007253185,0.00009842843,0.9835248,0.00036942467,0.00013690628,0.00023915607,0.000004203386,0.000067503504,0.008306415],"genre_scores_gemma":[0.6822562,0.000008526515,0.3172822,0.00022306765,0.0000041666603,0.0000059541285,0.000005608741,0.0000074425257,0.0002067995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982858,0.00056772167,0.0002567264,0.00042564218,0.0001982914,0.0002658185],"domain_scores_gemma":[0.999036,0.00045082456,0.00005520428,0.0002958869,0.000046809026,0.00011528522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011445312,0.00015631289,0.0002242757,0.00007454325,0.000056349934,0.000057397556,0.00018255545,0.00029224486,0.000051118444],"category_scores_gemma":[0.00010613401,0.00010763706,0.000022300339,0.00023855892,0.000051469844,0.00026339764,0.00006933548,0.00049250823,0.000014910565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018301747,0.00007526928,0.00024233318,0.000025439678,0.000045761877,0.000051001116,0.0013535302,0.0009782424,0.00010664414,0.9466667,0.000049514012,0.050222546],"study_design_scores_gemma":[0.0007387011,0.00015481238,0.0009528666,0.00006386345,0.0000127093745,0.00002455417,0.000008685554,0.29445428,0.00008918157,0.7033493,0.000008341578,0.00014270909],"about_ca_topic_score_codex":0.00001052476,"about_ca_topic_score_gemma":0.0000023542136,"teacher_disagreement_score":0.67500305,"about_ca_system_score_codex":0.000017133749,"about_ca_system_score_gemma":0.00004231293,"threshold_uncertainty_score":0.4389312},"labels":[],"label_agreement":null},{"id":"W2950050514","doi":"10.1109/icde.2019.00145","title":"Nonlinear Models Over Normalized Data","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Joins; Key (lock); Computation; Mixture model; Nonlinear system; Data modeling; Construct (python library); Data mining; Machine learning; Gaussian; Artificial intelligence; Algorithm; Database","score_opus":0.04624530610698814,"score_gpt":0.30213667315443044,"score_spread":0.2558913670474423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950050514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013661507,0.0000488013,0.93045133,0.00030998976,0.00030898917,0.00012493768,0.0000068921217,0.00013768265,0.06724523],"genre_scores_gemma":[0.017666947,0.000015020916,0.9751652,0.0015381592,0.00005755053,0.0000015579693,0.000010867824,0.000008137429,0.0055365954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888194,0.000054237993,0.00015174033,0.00047766996,0.00020757953,0.00022683661],"domain_scores_gemma":[0.9975673,0.00004787,0.000036153793,0.002234964,0.00003219527,0.00008153828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000446237,0.00010514164,0.00015255348,0.00004386473,0.000029656243,0.00011287604,0.0020032409,0.00005599638,0.00019959187],"category_scores_gemma":[0.000007533687,0.00007970653,0.00003571103,0.00016988453,0.000010455316,0.0014939171,0.0010741368,0.000097193864,0.00024912116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005829991,0.00005433524,0.00010091341,0.000011094698,0.000016454585,0.0000055289606,0.00012282401,0.000074456984,0.0010299677,0.938228,0.0067601413,0.05359044],"study_design_scores_gemma":[0.00032414877,0.000018078126,0.000033139393,0.000004517284,0.000002516151,0.000005918376,0.0000010221626,0.9462906,0.0004801274,0.03978802,0.012916766,0.00013514094],"about_ca_topic_score_codex":0.00005320761,"about_ca_topic_score_gemma":0.0000042121865,"teacher_disagreement_score":0.94621617,"about_ca_system_score_codex":0.000007504998,"about_ca_system_score_gemma":0.000051399395,"threshold_uncertainty_score":0.37225533},"labels":[],"label_agreement":null},{"id":"W2950093420","doi":"10.48550/arxiv.1510.04514","title":"Mixture Models: Building a Parameter Space","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Flexibility (engineering); Space (punctuation); Identification (biology); Parameter space; Computer science; Popularity; Exponential function; Algorithm; Mathematical optimization; Theoretical computer science; Mathematics; Applied mathematics; Geometry; Mathematical analysis; Statistics","score_opus":0.11622697994866185,"score_gpt":0.2214058635424316,"score_spread":0.10517888359376976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950093420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014508649,0.00036490057,0.9754378,0.00030880558,0.0008806052,0.0003162212,0.0000136944,0.000382752,0.00778658],"genre_scores_gemma":[0.6001166,0.000103580904,0.3974911,0.00019565452,0.00011339442,0.0000012598191,0.000004492176,0.000026897973,0.0019470442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970163,0.00036253475,0.00022355176,0.0016694643,0.00016074826,0.0005674164],"domain_scores_gemma":[0.9967972,0.00014861686,0.00027095253,0.002090381,0.0002823491,0.00041046864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069021917,0.0005031365,0.00055350404,0.0003066383,0.0001260009,0.00025749946,0.0027332527,0.0006311548,0.000009480391],"category_scores_gemma":[0.00006223795,0.0005317735,0.0003345336,0.0006068786,0.00009681622,0.00069378916,0.0031257067,0.0010814165,0.000033290675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018681267,0.00005695917,0.000029326608,0.00005566912,0.00008614683,0.00035679986,0.0004351578,0.12763993,0.00003291632,0.8655163,0.002566899,0.0032051846],"study_design_scores_gemma":[0.00018739837,0.000019697094,0.000003974975,0.000057247868,0.000039307903,0.00000771197,0.0000071368836,0.5042303,0.00006504077,0.49433607,0.0007004944,0.00034558782],"about_ca_topic_score_codex":0.000110923866,"about_ca_topic_score_gemma":0.000011931221,"teacher_disagreement_score":0.58560795,"about_ca_system_score_codex":0.00025649235,"about_ca_system_score_gemma":0.00036562548,"threshold_uncertainty_score":0.99971336},"labels":[],"label_agreement":null},{"id":"W2950118368","doi":"10.48550/arxiv.1206.4658","title":"Dirichlet Process with Mixed Random Measures: A Nonparametric Topic\\n Model for Labeled Data","year":2012,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Dirichlet process; Nonparametric statistics; Random forest; Computer science; Measure (data warehouse); Mixture model; Pattern recognition (psychology); Dirichlet distribution; Artificial intelligence; Process (computing); Hierarchical Dirichlet process; Segmentation; Latent Dirichlet allocation; Mathematics; Data mining; Topic model; Statistics","score_opus":0.20369478577678718,"score_gpt":0.2498801374655578,"score_spread":0.04618535168877061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950118368","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015219353,0.000864608,0.97828364,0.00019669993,0.0009107535,0.0030177257,0.00030120174,0.00021081867,0.0009952071],"genre_scores_gemma":[0.7505368,0.0005673622,0.24518149,0.00017110004,0.00025713257,0.000020027242,0.00010396497,0.00007949858,0.0030826617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922203,0.0007225355,0.00074865174,0.004204708,0.00046087394,0.001642953],"domain_scores_gemma":[0.9897721,0.00090905034,0.0010226462,0.006225552,0.0012053367,0.0008653588],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0030258005,0.0012486591,0.0017221168,0.00075862283,0.0006603872,0.0004609553,0.008745777,0.000900434,0.000021401298],"category_scores_gemma":[0.0004091411,0.0011832517,0.00043998877,0.002813522,0.0003689138,0.0021038097,0.0036990845,0.0012736504,0.000027647884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007124353,0.0030645158,0.0020310245,0.0032149793,0.0029905732,0.00033187628,0.005693053,0.5686647,0.00009942891,0.29900086,0.0015759924,0.10620862],"study_design_scores_gemma":[0.00694417,0.00015815209,0.000049147864,0.00028387416,0.0011425968,0.00001857037,0.000051590934,0.93058145,0.00013754949,0.05841781,0.00074546563,0.001469644],"about_ca_topic_score_codex":0.000083578496,"about_ca_topic_score_gemma":0.00012802261,"teacher_disagreement_score":0.7353174,"about_ca_system_score_codex":0.000282602,"about_ca_system_score_gemma":0.0015587192,"threshold_uncertainty_score":0.99906176},"labels":[],"label_agreement":null},{"id":"W2950411888","doi":"10.1002/sta4.143","title":"A matrix variate skew‐<i>t</i> distribution","year":2017,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs","keywords":"Random variate; Matrix (chemical analysis); Skewness; Work (physics); Data Matrix; Multivariate normal distribution; Distribution (mathematics); Maximization","score_opus":0.016351384420955847,"score_gpt":0.31953158841508517,"score_spread":0.3031802039941293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950411888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060169346,0.00005835954,0.9914686,0.0016353951,0.0005100982,0.00006973376,0.000022394595,0.00007664434,0.0055570584],"genre_scores_gemma":[0.28721717,0.000025648176,0.7106784,0.00016767145,0.00011218765,0.000007667427,0.000007134269,0.000006323324,0.0017778112],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992902,0.00004732056,0.00009698543,0.00023328401,0.00012279552,0.00020936156],"domain_scores_gemma":[0.9988609,0.000022695278,0.0000900451,0.0009121397,0.0000381425,0.00007605252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003309887,0.00007998394,0.000097979064,0.000012856698,0.00035504394,0.00039552586,0.00082190806,0.00004042558,0.000008687061],"category_scores_gemma":[0.000052880314,0.00006733335,0.000046267072,0.000037838512,0.000034461427,0.00044439433,0.00025231182,0.000081665145,0.000062459236],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029928378,0.000015188854,0.000084606974,0.0000056723466,0.0000059047547,0.000017576438,0.0001247315,6.6537257e-7,0.00042066968,0.83468115,0.0041582994,0.16048256],"study_design_scores_gemma":[0.000518608,0.000061898616,0.0072484408,0.00002161065,0.000010817839,0.000021904738,0.0000018149065,0.024587424,0.0023893707,0.8812623,0.08358889,0.00028692963],"about_ca_topic_score_codex":0.000047287536,"about_ca_topic_score_gemma":0.000004635554,"teacher_disagreement_score":0.2866155,"about_ca_system_score_codex":0.00001973888,"about_ca_system_score_gemma":0.000035421363,"threshold_uncertainty_score":0.3814065},"labels":[],"label_agreement":null},{"id":"W2950487938","doi":"10.48550/arxiv.1506.04137","title":"Mixtures of Multivariate Power Exponential Distributions","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Stiefel manifold; Exponential family; Maximization; Multivariate statistics; Skewness; Mathematical optimization; Exponential function; Benchmark (surveying); Applied mathematics; Mathematics; Expectation–maximization algorithm; Mixture model; Computer science; Statistics; Maximum likelihood","score_opus":0.07448628115887698,"score_gpt":0.22403330135017238,"score_spread":0.1495470201912954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950487938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031476583,0.00010941938,0.96381325,0.000080882375,0.00092491123,0.00020616452,0.00008961483,0.00012678122,0.003172387],"genre_scores_gemma":[0.92140645,0.000025890286,0.077780664,0.00002353646,0.000049822265,7.125826e-7,0.000025774858,0.000011622817,0.00067552767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981953,0.00029232222,0.00023935616,0.0008512367,0.00011255767,0.00030925573],"domain_scores_gemma":[0.9977599,0.000075104836,0.0003052897,0.0013054148,0.0003352763,0.00021904879],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004300675,0.00028397117,0.00040645734,0.00017537702,0.00008682315,0.00006198047,0.0016829274,0.00034880583,0.000023633598],"category_scores_gemma":[0.00006607336,0.00029854954,0.0002771874,0.00038880043,0.00012983257,0.00024882134,0.0020576026,0.0004807091,0.00001612894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032374683,0.00017962,0.00008806959,0.000040081115,0.00012217592,0.0001271145,0.0003958071,0.0054066107,0.00070986646,0.9906619,0.0013250596,0.00091129006],"study_design_scores_gemma":[0.0009466067,0.00008857839,0.00064326846,0.000120047844,0.00013444074,0.000007884366,0.000017151673,0.21214439,0.0029220302,0.7807546,0.0015037403,0.00071722455],"about_ca_topic_score_codex":0.00016442145,"about_ca_topic_score_gemma":0.0000078577195,"teacher_disagreement_score":0.8899299,"about_ca_system_score_codex":0.00011022873,"about_ca_system_score_gemma":0.00029509628,"threshold_uncertainty_score":0.99994665},"labels":[],"label_agreement":null},{"id":"W2950542255","doi":"10.1016/j.spl.2019.05.018","title":"Exact distribution of the non-central Wilks’s statistic of the second kind","year":2019,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Mathematics; Statistic; Computation; Series (stratigraphy); Applied mathematics; Distribution (mathematics); Statistics; Calculus (dental); Mathematical analysis; Algorithm","score_opus":0.007922384351172979,"score_gpt":0.22430340147327374,"score_spread":0.21638101712210076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950542255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19138584,0.00000726086,0.80568534,0.00088270183,0.00058305735,0.0005722798,0.00078724686,0.000008870931,0.00008740658],"genre_scores_gemma":[0.55873674,6.6055264e-7,0.44079235,0.00036521765,0.000015309117,0.0000062927656,0.000009966025,0.0000063248563,0.00006715277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980959,0.00037514817,0.00044230395,0.0003545841,0.0004058346,0.00032619105],"domain_scores_gemma":[0.99797285,0.0003539443,0.00033290547,0.0011662109,0.000117397045,0.000056669465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005839231,0.00016074319,0.0002629646,0.00001601756,0.00007774267,0.000036912632,0.001000544,0.00005320621,0.000045722736],"category_scores_gemma":[0.00018500935,0.000098718454,0.00010640193,0.0002685502,0.00031649962,0.00012298874,0.00027533708,0.00023839471,0.000003310354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023549883,0.00015829832,0.023992846,0.0006614706,0.000054470405,0.0000016144877,0.0012602638,0.000071149625,0.018209329,0.9351873,0.008146533,0.012233165],"study_design_scores_gemma":[0.00051061553,0.00008217217,0.40529296,0.00008416003,0.000036937687,0.0000054136344,0.0000023879418,0.0090642,0.008268802,0.57556987,0.00084655837,0.00023590103],"about_ca_topic_score_codex":0.00006307964,"about_ca_topic_score_gemma":0.000052144198,"teacher_disagreement_score":0.38130012,"about_ca_system_score_codex":0.00009713739,"about_ca_system_score_gemma":0.00016611292,"threshold_uncertainty_score":0.40256217},"labels":[],"label_agreement":null},{"id":"W2950697249","doi":"10.1080/03610918.2019.1626881","title":"Simplex regression models with measurement error","year":2019,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Simplex; Observational error; Covariate; Monte Carlo method; Statistics; Errors-in-variables models; Regression analysis; Mathematics; Regression; Data set; Computer science; Algorithm; Applied mathematics","score_opus":0.21734738436365955,"score_gpt":0.4357118961150921,"score_spread":0.21836451175143254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950697249","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020270066,0.0002233875,0.99521923,0.00037037267,0.000054664088,0.00038945855,0.0000073159895,0.00006726178,0.0016413118],"genre_scores_gemma":[0.5221166,0.000023299435,0.47771803,0.000079934514,0.000003128808,0.000010109538,0.000022051936,0.000006116038,0.00002074517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986339,0.00027938545,0.0003227697,0.0002859607,0.0003299395,0.00014801274],"domain_scores_gemma":[0.99823374,0.00040233863,0.00015918845,0.00081834366,0.00032726952,0.00005910242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055433565,0.00013647694,0.00017101962,0.00016717015,0.00014740975,0.00012570388,0.0004396604,0.000055867175,0.000004207304],"category_scores_gemma":[0.00003579132,0.00011895049,0.000014603151,0.00034292976,0.00005236469,0.00046114036,0.000213846,0.00016110334,0.0000074626846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013931078,0.00006815517,0.0003428857,0.000021379541,0.000007744718,7.4730235e-7,0.000990402,0.30279192,0.000021235372,0.46463332,0.000047872865,0.2310604],"study_design_scores_gemma":[0.0005149161,0.00004974805,0.0024103755,0.00006144905,0.0000052639,0.0000018836042,0.000028825705,0.8221925,0.000004508199,0.17428835,0.00031205232,0.00013017065],"about_ca_topic_score_codex":0.000020033776,"about_ca_topic_score_gemma":0.000037917747,"teacher_disagreement_score":0.52008957,"about_ca_system_score_codex":0.000078609206,"about_ca_system_score_gemma":0.00007424307,"threshold_uncertainty_score":0.48506603},"labels":[],"label_agreement":null},{"id":"W2951093609","doi":"10.48550/arxiv.0910.3221","title":"Estimation of a discrete monotone distribution","year":2009,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Monotone polygon; Estimation; Distribution (mathematics); Mathematics; Applied mathematics; Statistics; Econometrics; Computer science; Economics; Mathematical analysis; Geometry","score_opus":0.031050678648530353,"score_gpt":0.30249775941074936,"score_spread":0.271447080762219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951093609","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117735066,0.00023274534,0.88014895,0.00074237405,0.00032468158,0.00025864082,0.000027862032,0.00011108564,0.0004186251],"genre_scores_gemma":[0.70594895,0.00004745815,0.29369962,0.00006664332,0.000060912607,0.000017816832,0.000087696986,0.000007206717,0.000063699204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984286,0.00015443815,0.00040457954,0.00054579496,0.00023687929,0.00022973739],"domain_scores_gemma":[0.9983947,0.000047198908,0.00034236396,0.0010405115,0.00009000262,0.00008522198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048562462,0.00023238387,0.00036934228,0.00006448206,0.000057075267,0.000059789658,0.00081357994,0.00025202316,0.0000039117044],"category_scores_gemma":[0.00008315832,0.00021328137,0.00016558617,0.00019193569,0.00004583436,0.00022155418,0.00058732333,0.00038448995,0.00001551168],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029186096,0.00022423375,0.0050668707,0.00033318,0.0000998447,0.000024590126,0.00093712966,0.0060716826,0.0020734803,0.21467918,0.0010852102,0.7693754],"study_design_scores_gemma":[0.0003448459,0.00012342224,0.106058136,0.00038958972,0.00006550468,0.0000094605575,0.0000026116707,0.52936155,0.020154655,0.34257278,0.00033119254,0.0005862359],"about_ca_topic_score_codex":0.000047456615,"about_ca_topic_score_gemma":0.0000015191682,"teacher_disagreement_score":0.7687892,"about_ca_system_score_codex":0.00006396569,"about_ca_system_score_gemma":0.00010305079,"threshold_uncertainty_score":0.8697362},"labels":[],"label_agreement":null},{"id":"W2951457804","doi":"10.1017/s0021900200003648","title":"A Class of Infinite-Dimensional Diffusion Processes with Connection to Population Genetics","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Sobolev space; Pure mathematics; Connection (principal bundle); Entropy (arrow of time); Diffusion process; Sobolev inequality; Measure (data warehouse); Class (philosophy); Combinatorics; Geometry","score_opus":0.016499827131433577,"score_gpt":0.2607131689329453,"score_spread":0.24421334180151175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951457804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46364412,0.000016275313,0.535779,0.000113365044,0.000056212186,0.00015122264,3.9355595e-7,0.000007713691,0.00023166383],"genre_scores_gemma":[0.5550387,0.0000017099879,0.44483733,0.000077128105,0.00003817543,0.0000012840555,3.142891e-7,0.000003259472,0.0000020930559],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986361,0.000039809307,0.00054859597,0.00019228406,0.00043017627,0.00015303293],"domain_scores_gemma":[0.99839455,0.00022943533,0.00046055572,0.0002376823,0.00055183505,0.00012595503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016564217,0.00010775766,0.00024401711,0.000137793,0.0000530409,0.0000246105,0.00024688832,0.00007312721,0.000003008914],"category_scores_gemma":[0.00011371137,0.000075618635,0.000041843956,0.00052163756,0.000032126412,0.00013988644,0.00007017162,0.00015327072,5.383595e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054672896,0.0023558124,0.038833622,0.0013263526,0.0001587543,0.0000266818,0.005911984,0.02605022,0.10366807,0.21888386,0.00026788245,0.5970495],"study_design_scores_gemma":[0.0027172817,0.0025129637,0.16752017,0.00034812672,0.000088850895,0.00022272585,0.00006680781,0.007587267,0.14032502,0.67691797,0.0010370358,0.00065576227],"about_ca_topic_score_codex":0.000004949719,"about_ca_topic_score_gemma":0.00005237572,"teacher_disagreement_score":0.5963937,"about_ca_system_score_codex":0.00006375013,"about_ca_system_score_gemma":0.00017015757,"threshold_uncertainty_score":0.30836385},"labels":[],"label_agreement":null},{"id":"W2952140288","doi":"10.1017/s0266466617000299","title":"TESTING FOR HOMOGENEITY IN MIXTURE MODELS","year":2017,"lang":"en","type":"article","venue":"Econometric Theory","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Homogeneity (statistics); Estimator; Asymptotic distribution; Parametric statistics; Consistency (knowledge bases); Computation; Nonparametric statistics; Statistical hypothesis testing; Applied mathematics; Inference; Statistics; Mathematical optimization; Algorithm; Computer science","score_opus":0.06124019094083942,"score_gpt":0.29328590258953274,"score_spread":0.2320457116486933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952140288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012087442,0.00068818236,0.960746,0.00022314327,0.0003660006,0.00023003452,0.000007753474,0.000047988196,0.025603484],"genre_scores_gemma":[0.54196745,0.000005797888,0.45746723,0.00012649542,0.0000868078,0.000032908905,4.565709e-7,0.000008226675,0.0003046231],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890554,0.0000832588,0.00021540369,0.00042917428,0.000055172655,0.0003114737],"domain_scores_gemma":[0.99787277,0.00074890093,0.00018073923,0.0010662302,0.000046643898,0.000084689935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022326547,0.00012914036,0.00022923063,0.00040479872,0.00028328277,0.00027514543,0.0015017224,0.00008951735,0.000007704108],"category_scores_gemma":[0.0010105873,0.00012083436,0.00008182691,0.00038108492,0.000045251185,0.00084558286,0.00027806562,0.000120967015,0.000007689473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000389508,0.000021302532,0.0004866899,0.00000897739,0.0000055626224,0.0000036482882,0.00009987908,0.000060169426,0.00002041677,0.547722,0.000050628445,0.45151684],"study_design_scores_gemma":[0.0003384687,0.00003798508,0.008303246,0.0000104551345,0.000003162335,0.000007292675,0.0000032728951,0.0759083,0.00021180467,0.9146709,0.00033861143,0.00016652794],"about_ca_topic_score_codex":0.000015480426,"about_ca_topic_score_gemma":0.0000055352425,"teacher_disagreement_score":0.52988005,"about_ca_system_score_codex":0.000044971344,"about_ca_system_score_gemma":0.000053767588,"threshold_uncertainty_score":0.4927482},"labels":[],"label_agreement":null},{"id":"W2952405725","doi":"10.48550/arxiv.1303.5294","title":"Variable Selection for Clustering and Classification","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"University of Guelph","keywords":"Cluster analysis; Computer science; Variable (mathematics); Feature selection; Data mining; Selection (genetic algorithm); Machine learning; Artificial intelligence; Clustering high-dimensional data; Subspace topology; Focus (optics); Pattern recognition (psychology); Mathematics","score_opus":0.09676217619901079,"score_gpt":0.20976590108998358,"score_spread":0.1130037248909728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952405725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004597949,0.000029457713,0.99259585,0.00008540111,0.00034490216,0.0004063769,0.000003486281,0.00013582382,0.0018007739],"genre_scores_gemma":[0.40193617,0.000038323487,0.5961943,0.000056481174,0.00006256921,0.000004471222,0.0000048894176,0.000009681795,0.0016930666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988367,0.00008284372,0.00011252418,0.0007376761,0.000031556054,0.00019868357],"domain_scores_gemma":[0.99912924,0.00007795663,0.00013953369,0.0004283658,0.00013569716,0.00008923642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002740347,0.00016269863,0.0001794091,0.00012480203,0.00013634597,0.00016151645,0.0004733241,0.00023812862,0.0000060127386],"category_scores_gemma":[0.000019505016,0.00018490323,0.0000590344,0.00020897882,0.000028166882,0.00034424863,0.0005522299,0.00022300292,0.0000066718617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007331008,0.000017346189,0.000119144206,0.000094000425,0.000025284091,9.494501e-7,0.00007322143,0.0063556423,0.00042585342,0.9845545,0.00031812413,0.008008581],"study_design_scores_gemma":[0.00013098276,0.000018280985,0.00018500206,0.00002246991,0.000019702358,0.0000020657933,0.0000032966793,0.6507691,0.000043526376,0.3481036,0.0005667591,0.00013521659],"about_ca_topic_score_codex":0.00007311343,"about_ca_topic_score_gemma":0.000011624359,"teacher_disagreement_score":0.6444135,"about_ca_system_score_codex":0.00008833612,"about_ca_system_score_gemma":0.00008094059,"threshold_uncertainty_score":0.7540135},"labels":[],"label_agreement":null},{"id":"W2952457171","doi":"10.1017/s0001867800004146","title":"Conditionally identically distributed species sampling sequences","year":2010,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Independent and identically distributed random variables; Sequence (biology); Conditional independence; Dirichlet distribution; Random variable; Poisson sampling; Poisson distribution; Sampling (signal processing); Discrete mathematics; Distribution (mathematics); Combinatorics; Statistics; Slice sampling; Importance sampling; Mathematical analysis","score_opus":0.02020482066945352,"score_gpt":0.29533833964606193,"score_spread":0.2751335189766084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952457171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018350635,0.000066920096,0.9634666,0.0004305332,0.00042156232,0.0003602118,0.000011564638,0.00014133427,0.016750677],"genre_scores_gemma":[0.45459422,0.000017541966,0.5451503,0.00010555434,0.000046926587,0.00006006707,0.00001031824,0.0000037522555,0.000011317947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981479,0.0000647002,0.0004516772,0.00066981016,0.00030479685,0.00036113718],"domain_scores_gemma":[0.998643,0.00038515564,0.00011851048,0.000673584,0.000075724456,0.000104041515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011890339,0.00018090401,0.0002549461,0.00005593738,0.00011672862,0.00013345579,0.0009177718,0.00010167285,0.00007557486],"category_scores_gemma":[0.00023584263,0.00015998298,0.00005839847,0.0004224205,0.00033474155,0.0005864975,0.00021182813,0.0004388559,0.000026804115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007610334,0.000067165885,0.0012296992,0.000026264606,0.0000026670248,0.0000023317343,0.000064246495,0.0001983085,0.0075815977,0.93635595,0.000004662648,0.054459527],"study_design_scores_gemma":[0.00018683873,0.000014329812,0.012784355,0.000009113551,0.0000023960395,0.0000061040155,0.0000050090616,0.0009485324,0.0028069422,0.97568536,0.007347893,0.00020311934],"about_ca_topic_score_codex":0.000004392969,"about_ca_topic_score_gemma":0.00015693805,"teacher_disagreement_score":0.43624356,"about_ca_system_score_codex":0.00004965084,"about_ca_system_score_gemma":0.00009711722,"threshold_uncertainty_score":0.6523917},"labels":[],"label_agreement":null},{"id":"W2952597544","doi":"","title":"On Simulations from the Two-Parameter Poisson-Dirichlet Process and the Normalized Inverse-Gaussian Process","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Dirichlet process; Poisson distribution; Inverse; Applied mathematics; Gaussian process; Mathematics; Simple (philosophy); Dirichlet distribution; Gaussian; Process (computing); Poisson process; Inverse Gaussian distribution; Sampling (signal processing); Statistical physics; Mathematical optimization; Mathematical analysis; Computer science; Statistics; Physics; Bayesian probability; Geometry","score_opus":0.0566743211558175,"score_gpt":0.23707525461813744,"score_spread":0.18040093346231995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952597544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20063265,0.00010970175,0.79494977,0.0011152597,0.00036183998,0.00065303413,0.000038004604,0.000115198905,0.002024568],"genre_scores_gemma":[0.9899341,0.000040586576,0.008237327,0.0012717374,0.00015046416,0.000005499776,0.00001618139,0.00002258611,0.00032153432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975427,0.00065177545,0.00023631316,0.00097081333,0.00017399651,0.00042440073],"domain_scores_gemma":[0.99650735,0.0013243143,0.00034127347,0.0014846107,0.00015548062,0.00018695284],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000635411,0.00041200843,0.00042624242,0.00011124435,0.00046546117,0.0002922466,0.0021743304,0.0002506978,0.000032585976],"category_scores_gemma":[0.00014561455,0.00025994304,0.00018108917,0.00054635515,0.00036290727,0.0004947271,0.0009794895,0.00090347737,0.00002181488],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034398108,0.00018444809,0.0023754812,0.00009295607,0.00034619737,0.000048280668,0.010178222,0.111067615,0.000011760821,0.8721061,0.00039470964,0.0028502885],"study_design_scores_gemma":[0.0012735857,0.000012756351,0.00040458623,0.00006661726,0.00014264519,0.000002332597,0.000060087517,0.5231961,0.000049276758,0.47438076,0.00010569901,0.00030553516],"about_ca_topic_score_codex":0.00030338322,"about_ca_topic_score_gemma":0.00011223704,"teacher_disagreement_score":0.78930146,"about_ca_system_score_codex":0.00005976054,"about_ca_system_score_gemma":0.00016035388,"threshold_uncertainty_score":0.9999853},"labels":[],"label_agreement":null},{"id":"W2952741614","doi":"10.48550/arxiv.1107.0521","title":"On a Rapid Simulation of the Dirichlet Process","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Representation (politics); Mathematics; Simple (philosophy); Process (computing); Applied mathematics; Latent Dirichlet allocation; Dirichlet distribution; Poisson process; Dirichlet process; Measure (data warehouse); Random variable; Homogeneous; Poisson distribution; Computer science; Mathematical analysis; Combinatorics; Statistics; Topic model; Artificial intelligence; Data mining","score_opus":0.09319945433032067,"score_gpt":0.21695776701140715,"score_spread":0.12375831268108647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952741614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06009768,0.000023804158,0.9303147,0.000038699403,0.00037503318,0.0002569992,0.0000045826923,0.00006180849,0.008826656],"genre_scores_gemma":[0.99416876,0.000016531543,0.005147212,0.000111832094,0.000026371936,5.5617284e-7,0.0000010302043,0.000009611461,0.00051809056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987354,0.0002191056,0.00014795458,0.00063221337,0.00009117429,0.0001741021],"domain_scores_gemma":[0.99808353,0.00012811733,0.00030487322,0.0012723613,0.0001491919,0.00006193124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026032625,0.0001952244,0.0002333076,0.00012057988,0.000081698956,0.000025487137,0.0018306633,0.00020500197,0.000017547996],"category_scores_gemma":[0.000047728812,0.00015564986,0.00019311931,0.0004422399,0.00007813357,0.00014749466,0.00086690095,0.00038292422,0.00000841237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028972767,0.0001003711,0.0001596056,0.000085936685,0.000040539777,0.00001304174,0.00066357944,0.3932137,0.0000149836005,0.6013891,0.00005986047,0.0042302976],"study_design_scores_gemma":[0.00014317136,0.000031728763,0.00036330914,0.000079775986,0.000026966942,4.0662184e-7,0.0000037740435,0.5036362,0.00048852625,0.49504176,0.000036036265,0.00014834892],"about_ca_topic_score_codex":0.000021351201,"about_ca_topic_score_gemma":0.0000032227483,"teacher_disagreement_score":0.93407106,"about_ca_system_score_codex":0.000044524375,"about_ca_system_score_gemma":0.00013312609,"threshold_uncertainty_score":0.63472176},"labels":[],"label_agreement":null},{"id":"W2952792941","doi":"","title":"Generalized Polya Urn for Time-varying Dirichlet Process Mixtures","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dirichlet process; Markov chain Monte Carlo; Dirichlet distribution; Monte Carlo method; Class (philosophy); Cluster analysis; Inference; Applied mathematics; Computer science; Statistical inference; Mathematics; Hierarchical Dirichlet process; Algorithm; Artificial intelligence; Statistics","score_opus":0.06835278371654155,"score_gpt":0.23297468409776417,"score_spread":0.16462190038122262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952792941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017559301,0.0005381055,0.9769799,0.00019938983,0.0008119075,0.0006800963,0.00003557587,0.0003332398,0.0028624772],"genre_scores_gemma":[0.7540507,0.000093983734,0.24025206,0.00046823532,0.00046846597,0.000010284959,0.00004095585,0.000053492407,0.0045618764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973753,0.000236896,0.00026410806,0.0012942529,0.00012287796,0.0007065775],"domain_scores_gemma":[0.9976305,0.00017047054,0.00034533077,0.0013028905,0.0002343665,0.00031644246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005625036,0.0004882255,0.00057572784,0.0002670352,0.00025620713,0.00018444583,0.0023120136,0.0004869,0.0000364922],"category_scores_gemma":[0.00004949188,0.0005052488,0.00039254528,0.00045735162,0.00008050126,0.0005222293,0.0012371839,0.0005174758,0.000043028613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026157824,0.0005115814,0.0006399265,0.0010014308,0.00065639097,0.00019997687,0.0022160523,0.03027994,0.0027080951,0.93373203,0.0064326557,0.021360317],"study_design_scores_gemma":[0.0011584593,0.00005074031,0.00006624624,0.00013506884,0.00023653593,0.0000130669805,0.0000071290865,0.5859376,0.00313904,0.40615153,0.0019347313,0.0011698487],"about_ca_topic_score_codex":0.00004041323,"about_ca_topic_score_gemma":0.0000026142097,"teacher_disagreement_score":0.73672783,"about_ca_system_score_codex":0.000117106545,"about_ca_system_score_gemma":0.0002380704,"threshold_uncertainty_score":0.9997399},"labels":[],"label_agreement":null},{"id":"W2952893570","doi":"10.48550/arxiv.1704.00352","title":"Simple Measures of Individual Cluster-Membership Certainty for Hard Partitional Clustering","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Silhouette; Cluster analysis; Single-linkage clustering; Fuzzy clustering; Hierarchical clustering; Pattern recognition (psychology); Correlation clustering; Complete-linkage clustering; k-medians clustering; Mathematics; Medoid; Determining the number of clusters in a data set; Data mining; Computer science; Partition (number theory); Artificial intelligence; CURE data clustering algorithm; Combinatorics","score_opus":0.23497583003107322,"score_gpt":0.2552991558231561,"score_spread":0.020323325792082875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952893570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014591159,0.00004939668,0.9823401,0.0001588363,0.0005826949,0.0004766993,0.00015389707,0.00009164065,0.0015555733],"genre_scores_gemma":[0.9018664,0.000026830177,0.09724183,0.00011160992,0.00014418768,0.000004790071,0.00004398374,0.000019204488,0.00054118305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979156,0.00022938036,0.00028282002,0.0009816795,0.0001802305,0.0004102421],"domain_scores_gemma":[0.99730414,0.0002607373,0.00052575435,0.0014349389,0.00029331978,0.00018111244],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011082717,0.00031851177,0.0004929355,0.00019952557,0.00028021648,0.00020522835,0.0027550128,0.0003573875,0.00001712349],"category_scores_gemma":[0.00013958078,0.00035494324,0.00039851762,0.00011615959,0.00015543468,0.00037368212,0.0022145386,0.0003927125,0.0000045903994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029982542,0.00025328205,0.0021128305,0.00090490066,0.0007060452,0.000089925445,0.0014052999,0.15485692,0.00014442767,0.81215376,0.004448868,0.02262395],"study_design_scores_gemma":[0.00090929755,0.00007685705,0.0013167612,0.00014064321,0.00013546953,0.000004570813,0.000021130767,0.44640842,0.00041004148,0.54887253,0.0012156969,0.00048859656],"about_ca_topic_score_codex":0.000079178186,"about_ca_topic_score_gemma":0.000102288046,"teacher_disagreement_score":0.8872752,"about_ca_system_score_codex":0.00009361456,"about_ca_system_score_gemma":0.00028556836,"threshold_uncertainty_score":0.99989027},"labels":[],"label_agreement":null},{"id":"W2952985109","doi":"10.48550/arxiv.math/0701358","title":"Cure-rate estimation under Case-1 interval censoring","year":2007,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Censoring (clinical trials); Estimator; Nonparametric statistics; Mathematics; Statistics; Limiting; Maximum likelihood; Interval estimation; Econometrics; Point estimation; Confidence interval; Applied mathematics","score_opus":0.08881988548307998,"score_gpt":0.3424874732269365,"score_spread":0.25366758774385656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952985109","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1430731,0.0002041518,0.85167694,0.0008991723,0.0021246716,0.00023586946,0.00000406318,0.00028942255,0.0014925868],"genre_scores_gemma":[0.5220901,0.000031511245,0.47646248,0.00058219425,0.00027499022,0.000016094888,0.000007667171,0.000027868,0.0005071253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975613,0.00026193145,0.0005014989,0.00094489584,0.0002370651,0.0004933055],"domain_scores_gemma":[0.9979177,0.00017112911,0.0002868352,0.0012976775,0.00014416962,0.00018246734],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013973257,0.00039438295,0.00041201146,0.00021701405,0.00015380624,0.00023895215,0.0009865384,0.0004060176,0.000018687651],"category_scores_gemma":[0.00007224328,0.00033645643,0.00020776133,0.00024099191,0.00005589378,0.00035387097,0.001437413,0.0010013203,0.00012147683],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049808816,0.00039936596,0.012168086,0.00091110816,0.00049846206,0.007556393,0.006816727,0.020288633,0.0021379131,0.21226059,0.0027753455,0.7341376],"study_design_scores_gemma":[0.000880453,0.00014416387,0.027678106,0.0009501185,0.00016506517,0.0019716746,0.000063920415,0.71449506,0.010866505,0.23713814,0.003289801,0.0023569898],"about_ca_topic_score_codex":0.00014574916,"about_ca_topic_score_gemma":0.000026644237,"teacher_disagreement_score":0.7317806,"about_ca_system_score_codex":0.00014449148,"about_ca_system_score_gemma":0.00011985715,"threshold_uncertainty_score":0.99990875},"labels":[],"label_agreement":null},{"id":"W2953751292","doi":"10.1007/s00357-022-09427-7","title":"Model-Based Clustering and Classification Using Mixtures of Multivariate Skewed Power Exponential Distributions","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Stiefel manifold; Mixture model; Skewness; Mathematics; Expectation–maximization algorithm; Cluster analysis; Exponential family; Multivariate statistics; Multivariate normal distribution; Exponential function; Gaussian; Maximization; Linear discriminant analysis; Kurtosis; Applied mathematics; Statistics; Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematical optimization; Maximum likelihood; Mathematical analysis; Chemistry","score_opus":0.08359715212252727,"score_gpt":0.34054818044832663,"score_spread":0.25695102832579936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953751292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076929815,0.000052237217,0.92160094,0.000937536,0.00027193036,0.00009545691,0.0000066588045,0.000030039157,0.000075409764],"genre_scores_gemma":[0.6846407,0.000015764932,0.31526428,0.000017216911,0.000035825942,0.0000021049912,0.000003949527,0.000006490771,0.000013643128],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985898,0.00017613836,0.00058458507,0.00019190181,0.00029848402,0.00015909015],"domain_scores_gemma":[0.9984236,0.00012224742,0.0007228759,0.0002931515,0.0003454703,0.000092683775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097477733,0.00011203283,0.00021838595,0.000290899,0.000116907075,0.000080734324,0.00031244877,0.000101015605,0.0000016410952],"category_scores_gemma":[0.0001414769,0.000098151366,0.000100709265,0.00045426094,0.00006064581,0.0004602293,0.000055940927,0.00016152785,0.0000010061451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042263924,0.00008205882,0.00011356664,0.000032349675,0.000025885454,0.0000028012605,0.00045483094,0.0044988813,0.9273871,0.047192056,0.00013470472,0.020033501],"study_design_scores_gemma":[0.0004301507,0.000043551787,0.015658328,0.000060053397,0.000026569087,0.000013917965,0.000018602663,0.966782,0.008288469,0.008505892,0.00007861864,0.00009387846],"about_ca_topic_score_codex":0.0000028338873,"about_ca_topic_score_gemma":8.522307e-7,"teacher_disagreement_score":0.9622831,"about_ca_system_score_codex":0.00006088556,"about_ca_system_score_gemma":0.00015616746,"threshold_uncertainty_score":0.40024966},"labels":[],"label_agreement":null},{"id":"W2954489650","doi":"","title":"Bayesian Nonparametric Clustering of Continuous-Time Hidden Markov Models for Health Trajectories","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dirichlet process; Cluster analysis; Markov chain Monte Carlo; Hierarchical Dirichlet process; Gibbs sampling; Inference; Computer science; Markov chain; Bayesian inference; Markov model; Hidden Markov model; Nonparametric statistics; Bayesian probability; Econometrics; Data mining; Mathematics; Artificial intelligence; Machine learning; Topic model; Latent Dirichlet allocation","score_opus":0.05077042648064682,"score_gpt":0.22349984336387474,"score_spread":0.1727294168832279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954489650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032908854,0.0002521799,0.99192464,0.0001675153,0.0007720707,0.0011428456,0.00008865304,0.00017382205,0.0021873866],"genre_scores_gemma":[0.5972911,0.00013296772,0.4001908,0.00012016777,0.0000654631,0.000002958876,0.000014741695,0.0000336476,0.0021481675],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970791,0.00031291493,0.00048640821,0.0013652728,0.00014693744,0.00060941564],"domain_scores_gemma":[0.9967686,0.0003958244,0.0007121316,0.0016214245,0.0002629462,0.00023908935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092373486,0.00045572195,0.0010941055,0.00059365743,0.00012738619,0.00010977858,0.0021142424,0.00040274122,0.000011856454],"category_scores_gemma":[0.000047191836,0.000514028,0.000476491,0.00075052533,0.000091478614,0.0004732004,0.0013981253,0.00046385374,0.000008229371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044626964,0.0004828562,0.00064373825,0.0032554013,0.00072448817,0.00008156605,0.0026305458,0.48763826,0.0001521357,0.40457636,0.0027176703,0.09665073],"study_design_scores_gemma":[0.000613078,0.0001784229,0.00006375415,0.00018014116,0.000048251153,0.0000037129369,0.000017161758,0.88583785,0.0000817479,0.112446785,0.00009289616,0.0004361945],"about_ca_topic_score_codex":0.00022966972,"about_ca_topic_score_gemma":0.00002131143,"teacher_disagreement_score":0.5940002,"about_ca_system_score_codex":0.00025029748,"about_ca_system_score_gemma":0.00058276777,"threshold_uncertainty_score":0.9997311},"labels":[],"label_agreement":null},{"id":"W2955496656","doi":"10.2991/jsta.d.190617.001","title":"A Multivariate Skew-Normal Mean-Variance Mixture Distribution and Its Application to Environmental Data with Outlying Observations","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistics; Mathematics; Skew; Multivariate statistics; Multivariate analysis of variance; Variance (accounting); Multivariate normal distribution; Skew normal distribution; Kurtosis; Normal distribution; Econometrics; Computer science; Economics","score_opus":0.019402637251770067,"score_gpt":0.28406811270893545,"score_spread":0.2646654754571654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955496656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005413889,0.00015204525,0.9928847,0.00060504064,0.000022660395,0.00039978413,0.00045669888,0.000011515514,0.00005365442],"genre_scores_gemma":[0.56252843,0.000037380247,0.4370287,0.00021017283,0.00005572172,0.000026997206,0.000061906576,0.0000057515,0.00004490824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899876,0.00013073052,0.00026647496,0.0002951927,0.00017063842,0.00013822499],"domain_scores_gemma":[0.99875206,0.00047054622,0.00017225114,0.00037653896,0.000053299642,0.00017530272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008407737,0.000108510976,0.00016965317,0.00003298662,0.00015824226,0.00007950678,0.00040141813,0.000062290805,0.000007556929],"category_scores_gemma":[0.0000524405,0.000083698134,0.000013107777,0.00014758023,0.000045338347,0.0004945818,0.00018519886,0.00023808952,0.000007321913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041094423,0.000057299017,0.00012118647,0.00001399604,0.000019934576,0.0000012909624,0.00016625196,0.000027461272,0.0046883104,0.9254575,0.00003243796,0.06937325],"study_design_scores_gemma":[0.0016739771,0.00046144804,0.055724457,0.00012423252,0.00019601629,0.00036260803,0.00016963844,0.110984355,0.0009097959,0.80105287,0.02770657,0.00063405023],"about_ca_topic_score_codex":0.00000231227,"about_ca_topic_score_gemma":9.2179727e-7,"teacher_disagreement_score":0.55711454,"about_ca_system_score_codex":0.000021580865,"about_ca_system_score_gemma":0.000035317335,"threshold_uncertainty_score":0.34131107},"labels":[],"label_agreement":null},{"id":"W2955711579","doi":"10.1002/cjs.11668","title":"Simultaneous variable selection, clustering, and smoothing in function‐on‐scalar regression","year":2021,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute","keywords":"Multicollinearity; Scalar (mathematics); Smoothing; Cluster analysis; Dimensionality reduction; Regression analysis; Regression; Econometrics; Dimension (graph theory); Feature selection; Statistics; Mathematics; Computer science; Covariate; Data mining; Machine learning","score_opus":0.015050524373711136,"score_gpt":0.24460800878005945,"score_spread":0.22955748440634832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955711579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056350406,0.00081033725,0.99621433,0.00022594801,0.0017019187,0.00007813377,0.000037948153,0.000006965296,0.0003609294],"genre_scores_gemma":[0.094629884,0.00009048356,0.90454745,0.00037733951,0.00016044446,0.0000013598808,0.000005113114,0.000017742763,0.00017017275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848217,0.00022256497,0.00048783072,0.0003055601,0.00020789145,0.00029401018],"domain_scores_gemma":[0.99815834,0.00031755358,0.0003599289,0.0002505107,0.00041414445,0.00049951155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006968,0.00020289078,0.00037564474,0.0004158184,0.00013828273,0.0004628413,0.00038148856,0.00023284947,0.00003013251],"category_scores_gemma":[0.00064150576,0.0001929239,0.000038100457,0.00022437861,0.000038653947,0.00013502402,0.00011161655,0.0011305852,5.9113466e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005944853,0.00009098234,0.0017422453,0.0008305846,0.0002699706,0.009473633,0.007663454,0.18385287,0.00019117713,0.20552497,0.014995116,0.5753056],"study_design_scores_gemma":[0.0006301075,0.00034228413,0.0012902848,0.0023590324,0.00007858314,0.0010133615,0.00010466564,0.7751309,0.000044979533,0.21128651,0.0071179233,0.0006013133],"about_ca_topic_score_codex":0.002077413,"about_ca_topic_score_gemma":0.010777437,"teacher_disagreement_score":0.5912781,"about_ca_system_score_codex":0.00026277208,"about_ca_system_score_gemma":0.0023359065,"threshold_uncertainty_score":0.7867208},"labels":[],"label_agreement":null},{"id":"W2962710214","doi":"","title":"Optimal Phylogenetic Reconstruction","year":2005,"lang":"en","type":"article","venue":"ScholarlyCommons (University of Pennsylvania)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Emerging Frontiers; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Harvard University; National Science Foundation","keywords":"Combinatorics; Tree (set theory); Ising model; Mathematics; Binary tree; Markov chain; Conjecture; Gibbs measure; Phylogenetic tree; Measure (data warehouse); Omega; Discrete mathematics; Statistical physics; Physics; Biology; Computer science; Statistics","score_opus":0.013355718990125774,"score_gpt":0.21329310006361438,"score_spread":0.1999373810734886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962710214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16975822,0.00015876048,0.82079786,0.0014093125,0.00015503865,0.00009116559,0.000004624116,0.000090002366,0.0075350073],"genre_scores_gemma":[0.3832158,0.000031968128,0.61606616,0.00004203563,0.000034261502,1.2095644e-7,8.8981295e-7,0.0000048680586,0.00060387026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998879,0.00016418073,0.00013203443,0.0003649175,0.00021070227,0.00024916965],"domain_scores_gemma":[0.99892753,0.00004579747,0.00012947946,0.0006323912,0.000119529774,0.00014527715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041157607,0.0001298724,0.00021197127,0.00021328345,0.00027033704,0.0000753246,0.0011313856,0.00011615426,0.00014094744],"category_scores_gemma":[0.000018722356,0.00016355769,0.0001330015,0.00039663195,0.00011612895,0.001585312,0.0003178222,0.00029311486,0.00009597382],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020933805,0.000102548576,0.0009266821,0.000011508975,0.000042133346,0.000018872572,0.0010638172,0.00014575747,0.013182836,0.054024108,0.00085629296,0.92960453],"study_design_scores_gemma":[0.012966568,0.002050922,0.16137822,0.0004801718,0.0005340752,0.00213292,0.0029724166,0.36929607,0.03249319,0.09194145,0.3183828,0.005371183],"about_ca_topic_score_codex":0.000043389824,"about_ca_topic_score_gemma":0.00008128303,"teacher_disagreement_score":0.9242333,"about_ca_system_score_codex":0.000052529394,"about_ca_system_score_gemma":0.00006922141,"threshold_uncertainty_score":0.66696894},"labels":[],"label_agreement":null},{"id":"W2963111049","doi":"10.1214/18-aihp910","title":"Bayesian nonparametric analysis of Kingman&amp;#8217;s coalescent","year":2019,"lang":"en","type":"article","venue":"Institutional Research Information System University of Turin (University of Turin)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Humanities; Mathematics; Coalescent theory; Population; Philosophy; Demography; Sociology; Biology","score_opus":0.03870052122272637,"score_gpt":0.27029901754326785,"score_spread":0.23159849632054147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963111049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16382076,0.000026630312,0.8192319,0.00015651203,0.000114509916,0.00032762627,0.00008553671,0.000037594276,0.01619892],"genre_scores_gemma":[0.9107432,0.000032235715,0.08865794,0.000007370891,0.0000068580875,6.1722204e-8,0.0000379294,0.000002115635,0.0005122938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997319,0.00031989915,0.00033674572,0.0002805212,0.0014333231,0.0003105006],"domain_scores_gemma":[0.99709195,0.00022575555,0.0004970057,0.00073069386,0.0012662482,0.00018834282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017453444,0.00014160824,0.0005181989,0.0031805178,0.00033617852,0.00003327478,0.0016724844,0.00017075521,0.00011509163],"category_scores_gemma":[0.00006729374,0.00017248749,0.00035902282,0.0034118209,0.00042065134,0.002220674,0.0006995911,0.00028985902,0.00010041078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005397897,0.00031040394,0.01013469,0.0021015033,0.0016222204,0.000041075644,0.009487173,0.03034312,0.0005223962,0.9281651,0.0010039449,0.015728597],"study_design_scores_gemma":[0.007432175,0.0007270723,0.28840882,0.0015054398,0.0007932424,0.000074668606,0.015513525,0.58272713,0.0015349193,0.0013636632,0.09855243,0.0013669219],"about_ca_topic_score_codex":0.0015879755,"about_ca_topic_score_gemma":0.00010960817,"teacher_disagreement_score":0.92680144,"about_ca_system_score_codex":0.00043645236,"about_ca_system_score_gemma":0.0005194361,"threshold_uncertainty_score":0.70338356},"labels":[],"label_agreement":null},{"id":"W2963175784","doi":"10.1214/19-sts706","title":"Comment: Minimalist $g$-Modeling","year":2019,"lang":"en","type":"article","venue":"Statistical Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Computer science; Simple (philosophy); Bayes' theorem; Nonparametric statistics; Maximum likelihood; Machine learning; Artificial intelligence; Mathematical optimization; Econometrics; Algorithm; Mathematics; Bayesian probability; Statistics","score_opus":0.01871884721556452,"score_gpt":0.3057036943803385,"score_spread":0.286984847164774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963175784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012231256,0.000018647996,0.97253346,0.0024770298,0.00039217324,0.00011362577,0.000006473215,0.000070511356,0.023164926],"genre_scores_gemma":[0.41663176,0.0000014987037,0.5818769,0.001394075,0.000014355112,0.0000024551491,5.138018e-7,0.0000026470727,0.000075836106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821365,0.000055212244,0.00017650884,0.00056784204,0.0005262632,0.0004605273],"domain_scores_gemma":[0.99894905,0.00017633909,0.00003100439,0.000523183,0.00008550964,0.00023488577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011574621,0.000101978854,0.00013598318,0.00007139251,0.00017705862,0.00028268268,0.0012765257,0.000027299082,0.000097264536],"category_scores_gemma":[0.00015348093,0.00008253151,0.000023194765,0.0005740289,0.00021725809,0.00052470545,0.00036777346,0.000123007,0.00027368718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013987662,0.000015489151,0.000057545887,0.000004665999,7.815482e-7,0.000004202468,0.00009295712,0.00001703195,0.0008422747,0.9640021,0.0003003159,0.034661256],"study_design_scores_gemma":[0.00012371677,0.0000573238,0.00023392873,0.000009331923,0.0000015569186,0.0000075112985,0.0000059718477,0.78427094,0.0002755247,0.21261671,0.0022550202,0.00014247214],"about_ca_topic_score_codex":0.000029307612,"about_ca_topic_score_gemma":0.0000012312967,"teacher_disagreement_score":0.7842539,"about_ca_system_score_codex":0.000046586963,"about_ca_system_score_gemma":0.00013935684,"threshold_uncertainty_score":0.35177863},"labels":[],"label_agreement":null},{"id":"W2963647411","doi":"","title":"Particle gibbs split-merge sampling for Bayesian inference in mixture models","year":2017,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Western Canada Research Grid; Compute Canada","keywords":"Gibbs sampling; Markov chain Monte Carlo; Particle filter; Computer science; Merge (version control); Monte Carlo method; Algorithm; Computation; Inference; Bayesian inference; Bayesian probability; Importance sampling; Markov chain; Artificial intelligence; Mathematics; Statistics; Machine learning; Information retrieval","score_opus":0.07373631314711705,"score_gpt":0.32076376677045365,"score_spread":0.2470274536233366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963647411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038569015,0.00004497699,0.94434446,0.002181506,0.00008929439,0.0006727859,0.0001231738,0.00006519633,0.013909581],"genre_scores_gemma":[0.55318433,0.0004857693,0.4447471,0.000022214526,0.000027621521,6.4959596e-7,0.000013359529,0.000014410356,0.0015045526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966627,0.00045821568,0.00020791258,0.00093093363,0.00062922016,0.0011110492],"domain_scores_gemma":[0.99634403,0.0008573826,0.00025319582,0.0016536395,0.0004254361,0.00046630052],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0017334461,0.00027092738,0.00050847966,0.0006285435,0.0019628503,0.00018315735,0.0047485996,0.00019508609,0.00003189278],"category_scores_gemma":[0.00029128656,0.00033770216,0.00027752193,0.0005965387,0.000792439,0.002490993,0.0024840524,0.000732859,0.0000031718378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005795392,0.00026218203,0.0048872307,0.00015032996,0.00007912599,0.00017591717,0.0046580043,0.0005909118,0.0011766958,0.8944488,0.0004757762,0.0925155],"study_design_scores_gemma":[0.0030624387,0.0004902969,0.011230559,0.00022034795,0.000030626165,0.0000055017167,0.0017051786,0.5677912,0.00026842733,0.37518755,0.039389804,0.0006180646],"about_ca_topic_score_codex":0.0010496294,"about_ca_topic_score_gemma":0.0023622224,"teacher_disagreement_score":0.5672003,"about_ca_system_score_codex":0.00019188948,"about_ca_system_score_gemma":0.0004859929,"threshold_uncertainty_score":0.9999075},"labels":[],"label_agreement":null},{"id":"W2963714521","doi":"10.1109/tpami.2018.2885760","title":"Flexible High-Dimensional Unsupervised Learning with Missing Data","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; Texas Commission on Environmental Quality; U.S. Environmental Protection Agency","keywords":"Missing data; Imputation (statistics); Computer science; Expectation–maximization algorithm; Mixture model; Curse of dimensionality; Unsupervised learning; Artificial intelligence; Generalization; Data modeling; Gaussian; Pattern recognition (psychology); Data mining; Algorithm; Machine learning; Mathematics; Statistics; Maximum likelihood","score_opus":0.03876824261440971,"score_gpt":0.29690586584326717,"score_spread":0.25813762322885747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963714521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016280597,0.00008408282,0.99719876,0.0006467293,0.00013117667,0.000075258846,0.000020545758,0.0001159644,0.000099406934],"genre_scores_gemma":[0.8384523,0.000047506273,0.16066013,0.0005200378,0.000037810678,0.0000039849615,0.00001046392,0.000011879707,0.0002558909],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981678,0.00016571989,0.0002774864,0.00080886064,0.00031064326,0.00026945845],"domain_scores_gemma":[0.99853593,0.00012712028,0.00008613703,0.0009790866,0.00010989917,0.00016181466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045882008,0.0002281577,0.0003112382,0.0003703485,0.0004349794,0.00020401369,0.00073391024,0.000061386425,0.00018537414],"category_scores_gemma":[0.0000046100618,0.0001713656,0.0000845628,0.0010915509,0.00012701892,0.00040407828,0.000019976007,0.00032050136,0.000024777602],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019305062,0.00007933617,0.00016440022,0.000007249474,0.00032446207,0.000009611147,0.00019006035,0.0043451083,0.0004568181,0.00018672041,0.000009843084,0.9942071],"study_design_scores_gemma":[0.0001451595,0.00030755711,0.0004438561,0.000043592598,0.0004188937,0.000028528726,0.000010463692,0.8893094,0.10788071,0.00093549193,0.00014526636,0.00033108366],"about_ca_topic_score_codex":0.0010454097,"about_ca_topic_score_gemma":0.0005928024,"teacher_disagreement_score":0.993876,"about_ca_system_score_codex":0.00001596742,"about_ca_system_score_gemma":0.000038231803,"threshold_uncertainty_score":0.6988086},"labels":[],"label_agreement":null},{"id":"W2963736043","doi":"10.1016/j.patcog.2019.107031","title":"High-dimensional unsupervised classification via parsimonious contaminated mixtures","year":2019,"lang":"en","type":"preprint","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Mixture model; Gaussian; Expectation–maximization algorithm; Dimensionality reduction; Generalization; Covariance; Context (archaeology); Computer science; Mathematics; Mixture distribution; Maximization; Algorithm; Pattern recognition (psychology); Artificial intelligence; Applied mathematics; Mathematical optimization; Statistics; Probability density function; Maximum likelihood","score_opus":0.0399435296291964,"score_gpt":0.26625261789152366,"score_spread":0.22630908826232726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963736043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07087572,0.00023484278,0.92321455,0.0009973886,0.003087728,0.0008206779,0.000098212826,0.000326533,0.00034431988],"genre_scores_gemma":[0.8460794,0.00007047358,0.1506228,0.0013762346,0.00029924302,0.00015514134,0.0012450144,0.000046030025,0.00010563925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662936,0.0005896955,0.0005830843,0.0012596111,0.00051212346,0.0004261505],"domain_scores_gemma":[0.9976809,0.0001865925,0.00046234007,0.0011061799,0.00041396747,0.00015000351],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060667424,0.0004919361,0.000551159,0.000271079,0.000116017574,0.000275651,0.0008974318,0.0006708845,0.00009035144],"category_scores_gemma":[0.00003613673,0.00047807847,0.00022820606,0.000183282,0.000045342418,0.0002792139,0.0006311519,0.00086106395,0.00044364345],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017026085,0.00014112967,0.00023063846,0.00017754523,0.000083390616,0.000023333005,0.000206875,0.00005947617,0.003976563,0.00017665346,0.0010225519,0.9938848],"study_design_scores_gemma":[0.0024564024,0.00027583522,0.026645392,0.0011980941,0.00024462605,0.0000852204,0.000010353144,0.66308004,0.030696798,0.27271268,0.00026427687,0.0023302967],"about_ca_topic_score_codex":0.000261158,"about_ca_topic_score_gemma":0.000014393552,"teacher_disagreement_score":0.9915545,"about_ca_system_score_codex":0.00013354287,"about_ca_system_score_gemma":0.00013650206,"threshold_uncertainty_score":0.99976707},"labels":[],"label_agreement":null},{"id":"W2963777543","doi":"10.1002/sim.8297","title":"Stein‐type shrinkage estimators in gamma regression model with application to prostate cancer data","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Statistics; Regression analysis; Mathematics; Regression; Linear regression; Proportional hazards model; Computer science; Econometrics; Applied mathematics","score_opus":0.025846596910134332,"score_gpt":0.3604758722269298,"score_spread":0.3346292753167954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963777543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051929005,0.00015385481,0.9921081,0.001231249,0.00017342417,0.0006227888,0.00005020121,0.000028840637,0.00043864976],"genre_scores_gemma":[0.10554638,0.00007410883,0.89331734,0.00046931082,0.000032822554,0.000041284966,0.000054747576,0.000015795187,0.00044822702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984283,0.00006725808,0.0002938221,0.0005886301,0.00035916746,0.00026282057],"domain_scores_gemma":[0.99846166,0.00011773413,0.00009689878,0.0011271529,0.00008607294,0.00011048574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077728624,0.00015401232,0.00028265637,0.00017671919,0.00002287993,0.0000188197,0.00080896623,0.00004846225,0.000011225968],"category_scores_gemma":[0.00010829876,0.000105704996,0.0000035347202,0.00062082644,0.00004451851,0.00018648389,0.0002688357,0.00021968674,0.000010957068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022908593,0.000117487725,0.019889338,0.00031334054,0.0000154753,0.00011463419,0.0064669587,0.044090874,0.0022706417,0.2791747,0.009520338,0.6377971],"study_design_scores_gemma":[0.00072629954,0.00015312263,0.0022654824,0.00043567346,0.0000056441877,0.0000024385856,0.000019511304,0.9691863,0.00004802462,0.02650551,0.00049840665,0.00015358819],"about_ca_topic_score_codex":0.00035410174,"about_ca_topic_score_gemma":0.00047062454,"teacher_disagreement_score":0.92509544,"about_ca_system_score_codex":0.000069442314,"about_ca_system_score_gemma":0.00015167761,"threshold_uncertainty_score":0.43105248},"labels":[],"label_agreement":null},{"id":"W2963804890","doi":"10.1093/sysbio/syz028","title":"An Annealed Sequential Monte Carlo Method for Bayesian Phylogenetics","year":2019,"lang":"en","type":"article","venue":"Systematic Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Western Canada Research Grid; Compute Canada","keywords":"Monte Carlo method; Bayesian probability; Markov chain Monte Carlo; Biology; Statistical physics; Phylogenetics; Bayesian inference; Evolutionary biology; Statistics; Econometrics; Mathematics; Physics; Genetics","score_opus":0.019176377347566196,"score_gpt":0.3297625274541846,"score_spread":0.3105861501066184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963804890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009173788,0.0003412639,0.9871039,0.0001869398,0.0010308484,0.0018300691,0.000012817642,0.00011134528,0.00020903446],"genre_scores_gemma":[0.45885685,0.0000010530326,0.54069656,0.00020033927,0.00006595652,0.00010947727,0.000002007799,0.000010025393,0.000057696725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99700075,0.0013351962,0.0005406339,0.00060894055,0.00010050883,0.00041395923],"domain_scores_gemma":[0.9979622,0.0003285496,0.0002555279,0.0011867842,0.00013540815,0.00013156615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019342307,0.00021904115,0.0007244438,0.00010923214,0.00007124055,0.000083853745,0.0010286438,0.0002491477,0.000008241336],"category_scores_gemma":[0.0000657366,0.00016468365,0.00016649535,0.00014932986,0.00002991267,0.00010732058,0.00013474101,0.000104927996,0.00001762886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034537214,0.00014484276,0.0011181791,0.019336596,0.00031093723,0.000008802937,0.0029556218,0.00073149055,0.11140391,0.85103405,0.00008498744,0.012836061],"study_design_scores_gemma":[0.0005427019,0.0004747286,0.000058292833,0.00028524006,0.000046141373,0.00005107976,0.000036794136,0.92480123,0.0027044476,0.07067661,0.000033238244,0.0002894711],"about_ca_topic_score_codex":0.000028146753,"about_ca_topic_score_gemma":0.00001003087,"teacher_disagreement_score":0.92406976,"about_ca_system_score_codex":0.000029985878,"about_ca_system_score_gemma":0.0000730334,"threshold_uncertainty_score":0.6715604},"labels":[],"label_agreement":null},{"id":"W2963808043","doi":"10.1016/j.spa.2010.03.008","title":"Asymptotic results for the two-parameter Poisson–Dirichlet distribution","year":2010,"lang":"en","type":"article","venue":"Stochastic Processes and their Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Mathematics; Dirichlet distribution; Poisson distribution; Distribution (mathematics); Gamma distribution; Infinity; Applied mathematics; Mathematical analysis; Rate function; Sequence (biology); Large deviations theory; Combinatorics; Statistics","score_opus":0.013250652730919426,"score_gpt":0.2741380628267314,"score_spread":0.260887410095812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963808043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011303034,0.00027081554,0.9947736,0.0034690993,0.00010322298,0.0008176434,0.0001403228,0.0000870402,0.00022522264],"genre_scores_gemma":[0.875396,0.000005974563,0.12294278,0.00021314668,0.00018157801,0.0011348854,0.00003603074,0.00000891038,0.00008070479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913466,0.000012989735,0.00018323275,0.0003705867,0.000078208424,0.00022029619],"domain_scores_gemma":[0.9978141,0.0012637432,0.00009830054,0.00054213556,0.00019904503,0.00008265602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037082782,0.00013830407,0.000120835364,0.000023667704,0.00045320907,0.00017607318,0.0005419042,0.000053359076,8.700824e-7],"category_scores_gemma":[0.00029354906,0.00008238026,0.00004046872,0.00032349452,0.00010575527,0.00013953715,0.00010014752,0.00015969695,0.0000035859075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011777572,0.000046301997,4.6791604e-7,0.000032826785,0.00001806828,3.7719015e-8,0.00031635285,0.000014508955,0.0006825041,0.846776,0.00030879411,0.15179233],"study_design_scores_gemma":[0.00056395825,0.000056971967,0.00004536066,0.000014280567,0.00003444774,0.000026326115,0.00003061735,0.10771089,0.0008054282,0.8796491,0.010837717,0.00022492444],"about_ca_topic_score_codex":0.000007829409,"about_ca_topic_score_gemma":0.000020682313,"teacher_disagreement_score":0.87528294,"about_ca_system_score_codex":0.000006516729,"about_ca_system_score_gemma":0.00008447192,"threshold_uncertainty_score":0.34857637},"labels":[],"label_agreement":null},{"id":"W2963848397","doi":"","title":"{Accurate and conservative estimates of MRF log-likelihood using reverse annealing}","year":2015,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Markov chain Monte Carlo; Mathematics; Markov chain; Markov random field; Statistics; Partition (number theory); Upper and lower bounds; Algorithm; Simulated annealing; Computer science; Artificial intelligence; Combinatorics; Bayesian probability","score_opus":0.25884058999423964,"score_gpt":0.4020975121392004,"score_spread":0.14325692214496077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963848397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046070246,0.00004644236,0.9928189,0.0007576594,0.00036387818,0.00009290557,0.0001332286,0.000019444797,0.0011605438],"genre_scores_gemma":[0.42407215,0.00007645805,0.5755867,0.00020453097,0.000028091941,0.000002172124,0.000007334832,0.0000044361227,0.000018138608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882716,0.000089921254,0.0003677613,0.00029702712,0.00025576702,0.0001623934],"domain_scores_gemma":[0.99851155,0.00034725675,0.00018997185,0.00015354055,0.00065898534,0.00013866476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049507484,0.00014311794,0.00019819986,0.00010438819,0.000060278948,0.00016436457,0.00029090382,0.000057581507,0.000017627912],"category_scores_gemma":[0.00059492025,0.00013126153,0.000017163207,0.000108389155,0.00022565556,0.00024499203,0.00012339427,0.000119100834,0.0000060764287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044039305,0.0000315844,0.00008411931,0.000008166104,0.000018407865,0.000015143884,0.0011081796,0.00009499122,0.0007164133,0.89037186,0.0000934821,0.10741362],"study_design_scores_gemma":[0.000029708779,0.000103343256,0.000036373687,0.00004162163,0.0000060799084,0.000012242241,0.0002213217,0.49933705,0.003136988,0.49695054,0.0000357334,0.00008902761],"about_ca_topic_score_codex":0.00017817602,"about_ca_topic_score_gemma":0.000037087193,"teacher_disagreement_score":0.49924204,"about_ca_system_score_codex":0.000023012915,"about_ca_system_score_gemma":0.00016302674,"threshold_uncertainty_score":0.535269},"labels":[],"label_agreement":null},{"id":"W2963873454","doi":"10.1016/j.spa.2018.03.023","title":"Random locations of periodic stationary processes","year":2018,"lang":"en","type":"article","venue":"Stochastic Processes and their Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Mathematics; Infimum and supremum; Stochastic process; Focus (optics); Stationary sequence; Regular polygon; Convex hull; Path (computing); Combinatorics; Joint probability distribution; Random walk; Statistical physics; Mathematical analysis; Geometry; Statistics","score_opus":0.012322257383661894,"score_gpt":0.2619645169018383,"score_spread":0.24964225951817642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963873454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017224379,0.0014734974,0.99610555,0.0004997064,0.000026987225,0.0004446648,0.000026536494,0.000082657956,0.0011681378],"genre_scores_gemma":[0.8317392,0.00003070141,0.16749752,0.00010523141,0.00008942592,0.00044541332,0.000008991984,0.0000087136,0.00007482357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991762,0.000019445428,0.0002262984,0.00031787084,0.00010420493,0.00015596772],"domain_scores_gemma":[0.99847573,0.00028796625,0.00012958702,0.0003444488,0.0006816869,0.00008060086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015314111,0.00012903786,0.00016982037,0.000088796434,0.0003037492,0.00006130746,0.00040152494,0.000041186267,0.000008422333],"category_scores_gemma":[0.00011463982,0.000099759236,0.000021094706,0.00074934494,0.00027717973,0.00024030155,0.00009267876,0.000057793677,0.0000070081237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030247711,0.00026968835,0.000009863925,0.00084622274,0.000058191647,1.4739413e-7,0.007454831,0.00002798721,0.0009321424,0.7816388,0.00018036424,0.20855148],"study_design_scores_gemma":[0.0009144113,0.00022714262,0.00006472218,0.00013646705,0.000040198684,0.000039794115,0.00040339422,0.01637884,0.0036217193,0.9746357,0.003131755,0.00040583787],"about_ca_topic_score_codex":0.0000073877723,"about_ca_topic_score_gemma":0.000010640774,"teacher_disagreement_score":0.83156693,"about_ca_system_score_codex":0.0000069431358,"about_ca_system_score_gemma":0.0004357099,"threshold_uncertainty_score":0.40680635},"labels":[],"label_agreement":null},{"id":"W2964334712","doi":"10.1002/cjs.11519","title":"A Potts‐mixture spatiotemporal joint model for combined magnetoencephalography and electroencephalography data","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Magnetoencephalography; Computer science; Smoothing; Artificial intelligence; Estimator; Bayesian probability; Electroencephalography; Inverse problem; Potts model; Neuroimaging; Pattern recognition (psychology); Ising model; Computer vision; Mathematics","score_opus":0.044657994018745865,"score_gpt":0.2436175460578083,"score_spread":0.19895955203906243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964334712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017233945,0.00074890273,0.9953326,0.0007785236,0.00038246953,0.000253232,0.0006498518,0.000008307985,0.00012273563],"genre_scores_gemma":[0.24832128,0.00006489923,0.7509711,0.0004961488,0.00004538733,0.0000017266738,0.000029888486,0.000012204823,0.000057412384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985782,0.00006591119,0.00042484238,0.00031240028,0.00019304737,0.00042563534],"domain_scores_gemma":[0.9980315,0.000110423316,0.00030252524,0.00058398873,0.00035130527,0.0006202668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006583843,0.00017569849,0.00034205525,0.00045027203,0.00011755074,0.00020605196,0.001002764,0.00008867606,0.000011235909],"category_scores_gemma":[0.00010244399,0.00015869367,0.00006739049,0.0003018383,0.00010694052,0.00050420495,0.000057505895,0.0002647118,8.8346377e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005093059,0.000046430978,0.00620454,0.00016836051,0.0001659613,0.00017002819,0.0014263778,0.00025392504,0.0004908057,0.79452115,0.069673754,0.12682775],"study_design_scores_gemma":[0.00080850045,0.000602587,0.0027943288,0.000044925175,0.000046059835,0.00013300496,0.000013075239,0.6375416,0.000023689343,0.35562927,0.0021127292,0.00025021003],"about_ca_topic_score_codex":0.00029545225,"about_ca_topic_score_gemma":0.0019880238,"teacher_disagreement_score":0.6372877,"about_ca_system_score_codex":0.000029261257,"about_ca_system_score_gemma":0.0010631813,"threshold_uncertainty_score":0.647134},"labels":[],"label_agreement":null},{"id":"W2964955876","doi":"10.1109/isie.2019.8781217","title":"Finite Two-Dimensional Beta Mixture Models: Model Selection and Applications","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Mixture model; Inference; Model selection; Machine learning; Artificial intelligence; Unsupervised learning; Data modeling; Statistical model; Probabilistic logic; Data mining","score_opus":0.01722665940066035,"score_gpt":0.25834316694587844,"score_spread":0.2411165075452181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964955876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010635579,0.00013560642,0.98338056,0.0005722165,0.000049012484,0.00027584433,0.0000023218283,0.00014360443,0.014377285],"genre_scores_gemma":[0.2031574,0.000007213037,0.7931157,0.00088863826,0.000041435767,0.000033472792,0.00000287738,0.000008335174,0.0027449355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901724,0.000040860235,0.00013989136,0.00044520077,0.00016664593,0.00019013516],"domain_scores_gemma":[0.99935186,0.00007410127,0.000041553336,0.0003559322,0.000082502,0.00009406334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021843286,0.00012597225,0.00013424495,0.00007604777,0.00009781439,0.00008256548,0.0002629983,0.00007645558,0.00001597775],"category_scores_gemma":[0.0000020165512,0.00010457146,0.000037103637,0.00023023202,0.00001434967,0.0005025752,0.00015038063,0.00014439037,0.000034013876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021803655,0.0000226624,0.000017050146,0.0000066789194,0.000007645402,1.634527e-7,0.00006703658,0.14304551,0.0013465936,0.823953,0.0003226465,0.031208826],"study_design_scores_gemma":[0.00015393767,0.00001332617,0.0000070327387,0.0000031908378,0.000003878126,0.000008639412,6.520324e-7,0.7098995,0.00039537178,0.28916746,0.00024477995,0.00010223206],"about_ca_topic_score_codex":0.000012500914,"about_ca_topic_score_gemma":0.00000683234,"teacher_disagreement_score":0.566854,"about_ca_system_score_codex":0.0000146824095,"about_ca_system_score_gemma":0.000057185334,"threshold_uncertainty_score":0.42643005},"labels":[],"label_agreement":null},{"id":"W2965176432","doi":"10.1109/isie.2019.8781499","title":"Color Image Segmentation Using Generalized Inverted Dirichlet Finite Mixture Models By Integrating Spatial Information","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Dirichlet distribution; Image segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Expectation–maximization algorithm; Latent Dirichlet allocation; Markov random field; Segmentation; Maximization; Mathematics; Topic model; Mathematical optimization; Statistics; Maximum likelihood","score_opus":0.014503966204908864,"score_gpt":0.2577725613699182,"score_spread":0.24326859516500934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965176432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026316985,0.000023863857,0.9690807,0.0002686252,0.00033659843,0.00042997717,0.000012542371,0.00015402805,0.003376676],"genre_scores_gemma":[0.11528465,0.0000071133154,0.88213253,0.0021815805,0.000031840715,0.000013266543,0.000074671814,0.000009591937,0.00026472993],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986221,0.00016778242,0.00038527322,0.0002689123,0.00029146337,0.0002644282],"domain_scores_gemma":[0.99912494,0.00007853425,0.00020023083,0.00034531756,0.00016569076,0.000085310916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035671427,0.00019820464,0.00021922946,0.00012546874,0.00010641024,0.00037451598,0.0003899846,0.00012345095,0.00006370962],"category_scores_gemma":[0.000032567197,0.00016144828,0.000069070105,0.00034030675,0.000018445568,0.0035301603,0.00014732877,0.00016159934,0.000042971955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007434903,0.00009768265,0.00015476703,0.000110944995,0.000081435566,0.0000035186893,0.007113768,0.008748146,0.549386,0.11497994,0.01154172,0.30770773],"study_design_scores_gemma":[0.0007035587,0.000042791864,0.000006406494,0.000016689073,0.000008155571,0.000004012765,0.000036123467,0.9703501,0.01944183,0.008846107,0.00032810972,0.00021613154],"about_ca_topic_score_codex":0.00064462074,"about_ca_topic_score_gemma":0.000021257047,"teacher_disagreement_score":0.9616019,"about_ca_system_score_codex":0.00007767373,"about_ca_system_score_gemma":0.000072791845,"threshold_uncertainty_score":0.658367},"labels":[],"label_agreement":null},{"id":"W2965409371","doi":"10.1109/isie.2019.8781307","title":"Model-Based Hierarchical Clustering for Categorical Data","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Bhattacharyya distance; Categorical variable; Computer science; Hierarchical clustering; Brown clustering; Artificial intelligence; Multinomial distribution; Binary data; Data mining; Pattern recognition (psychology); Fuzzy clustering; Consensus clustering; Mixture model; CURE data clustering algorithm; Machine learning; Binary number; Mathematics; Statistics","score_opus":0.07657443905414395,"score_gpt":0.32707370956380694,"score_spread":0.250499270509663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965409371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013260693,0.00001653077,0.9927541,0.0018955236,0.00024347397,0.00025693138,0.000005467768,0.000121566474,0.0045737787],"genre_scores_gemma":[0.16463743,6.867436e-7,0.83311546,0.0012083566,0.00004559303,0.000009933866,0.000010793254,0.000008100877,0.0009636372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988781,0.000038719973,0.00014733618,0.00053140766,0.000142349,0.0002620372],"domain_scores_gemma":[0.9982717,0.00015673082,0.000024627445,0.0014123763,0.000031476615,0.000103073195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004819426,0.00010030778,0.00014986991,0.000046145175,0.00004689946,0.00009595867,0.0016027062,0.00006542608,0.000012395887],"category_scores_gemma":[0.00002463309,0.00007804902,0.000046434136,0.00010594581,0.000014023226,0.00031470053,0.0005660064,0.0001059967,0.00002445104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001824865,0.000052271476,0.000023739825,0.000037803096,0.000007662271,0.0000020043728,0.00005714629,0.004141007,0.00089257915,0.8300584,0.0032920444,0.16141708],"study_design_scores_gemma":[0.00031662412,0.00003843349,0.000008127345,0.0000026997752,0.0000025510167,0.0000028023765,4.365924e-7,0.91949326,0.00019574,0.07763286,0.002190167,0.0001162861],"about_ca_topic_score_codex":0.000005908762,"about_ca_topic_score_gemma":0.0000045381353,"teacher_disagreement_score":0.9153523,"about_ca_system_score_codex":0.000015275895,"about_ca_system_score_gemma":0.000108482265,"threshold_uncertainty_score":0.31827468},"labels":[],"label_agreement":null},{"id":"W2965752214","doi":"10.1109/isie.2019.8781334","title":"Data Clustering using Variational Learning of Finite Scaled Dirichlet Mixture Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Dirichlet distribution; Inference; Model selection; Bayesian inference; Computer science; Dirichlet process; Mixture model; Bayesian information criterion; Artificial intelligence; Bayesian probability; Algorithm; Machine learning; Mathematics; Applied mathematics; Mathematical optimization","score_opus":0.05984945085982361,"score_gpt":0.2983152627598782,"score_spread":0.2384658119000546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965752214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016401889,0.0000687535,0.9913966,0.00014781671,0.0002326287,0.000119456825,0.000009733726,0.00006753645,0.006317257],"genre_scores_gemma":[0.2220079,0.000004735889,0.7771029,0.00015107307,0.000044016313,7.433004e-7,0.000012756796,0.000008569694,0.00066734536],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986475,0.00014206149,0.0002633902,0.00045697033,0.00027914598,0.00021093478],"domain_scores_gemma":[0.9985711,0.00021997042,0.00013372832,0.0009309228,0.00008559013,0.00005867259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074132247,0.00012413121,0.00021880495,0.000092592054,0.000061665385,0.000078913414,0.0011542739,0.000084021354,0.00005716239],"category_scores_gemma":[0.000048140126,0.00010676411,0.000044069235,0.00027996607,0.000015005094,0.0010571952,0.001060683,0.00018411216,0.000009882029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000196312,0.00007867623,0.0006373469,0.00010535477,0.00007455956,0.0000056355384,0.00085933483,0.4724396,0.013981836,0.47064987,0.00024285924,0.04090532],"study_design_scores_gemma":[0.00022621301,0.00001856725,0.00008541555,0.000030825875,0.000007210346,0.000007793362,0.0000046111572,0.9790569,0.00017819603,0.019911656,0.00033808636,0.00013451368],"about_ca_topic_score_codex":0.000028656677,"about_ca_topic_score_gemma":0.0000029354098,"teacher_disagreement_score":0.5066173,"about_ca_system_score_codex":0.000015791675,"about_ca_system_score_gemma":0.00007686334,"threshold_uncertainty_score":0.43537143},"labels":[],"label_agreement":null},{"id":"W2967423800","doi":"10.1007/978-3-030-23876-6_6","title":"L 2 Normalized Data Clustering Through the Dirichlet Process Mixture Model of von Mises Distributions with Localized Feature Selection","year":2019,"lang":"en","type":"book-chapter","venue":"Unsupervised and semi-supervised learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Cluster analysis; Dirichlet process; Pattern recognition (psychology); Dirichlet distribution; Novelty detection; Model selection; Feature selection; Artificial intelligence; Feature (linguistics); Mathematics; Computer science; Inference; Algorithm; Novelty; Boundary value problem","score_opus":0.02904565417221951,"score_gpt":0.2619187567275469,"score_spread":0.23287310255532737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967423800","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034479517,0.0030342992,0.9699713,0.0010942542,0.00013949211,0.0009467818,0.00021601425,0.00025523774,0.023997812],"genre_scores_gemma":[0.073795505,0.0058837896,0.71329755,0.002035622,0.0008767768,0.0001279942,0.0033582146,0.0006202327,0.20000431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99605536,0.0002639318,0.0006562738,0.0015548202,0.00080910046,0.0006605124],"domain_scores_gemma":[0.99673384,0.0003312577,0.00047718638,0.0018082156,0.00046470878,0.00018479602],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006801041,0.00091996696,0.0011665802,0.0001713769,0.0007020992,0.0003655228,0.0022495722,0.00077580375,0.00005163926],"category_scores_gemma":[0.00008836159,0.00062341115,0.00020733381,0.00034865265,0.00025234334,0.0011406022,0.0009493421,0.001992443,0.0000058381856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028450335,0.00066630065,0.001340365,0.011359836,0.0042773033,0.0001447985,0.052923236,0.18475585,0.014132913,0.4632258,0.011983842,0.25234473],"study_design_scores_gemma":[0.0017534998,0.00023835803,0.0000074443274,0.0010194803,0.00037270228,0.00010102434,0.00012875139,0.95116353,0.0002653654,0.0071898955,0.036784977,0.0009749795],"about_ca_topic_score_codex":0.000046171735,"about_ca_topic_score_gemma":0.000041231644,"teacher_disagreement_score":0.76640767,"about_ca_system_score_codex":0.000061687155,"about_ca_system_score_gemma":0.0004996984,"threshold_uncertainty_score":0.99962175},"labels":[],"label_agreement":null},{"id":"W2968392233","doi":"10.1145/3341216.3342217","title":"Hierarchical Bayesian Modelling for Wireless Cellular Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Pooling; Computer science; Cellular network; Bayesian network; Wireless network; Bayesian probability; Data mining; Population; Parametric statistics; Parametric model; Machine learning; Wireless; Artificial intelligence; Computer network; Telecommunications; Mathematics; Statistics","score_opus":0.01577323246974653,"score_gpt":0.24116311390192693,"score_spread":0.22538988143218042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968392233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011179973,0.000087698245,0.99095136,0.00053942844,0.000494953,0.00037852398,6.2657773e-7,0.000157015,0.006272424],"genre_scores_gemma":[0.33895707,0.00000645914,0.6588332,0.00046643332,0.00011426724,0.000014579001,0.0000017735342,0.000012373012,0.0015938309],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866873,0.00006854514,0.0002075497,0.00048925786,0.000152348,0.00041356552],"domain_scores_gemma":[0.99899274,0.00017177686,0.000043120777,0.0006009179,0.00004987232,0.00014158055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004917126,0.00015021159,0.0002209807,0.00005736039,0.00008151996,0.00012688582,0.00070301985,0.00012617659,0.0000252548],"category_scores_gemma":[0.000002974236,0.00012387415,0.00013095306,0.00017154227,0.000018280378,0.00024350094,0.00013301907,0.00017767382,0.000017961374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073343945,0.000022486794,0.000020402542,0.000014047929,0.000009388505,0.000001990853,0.00008724398,0.017367681,0.0004265652,0.9019089,0.00030118908,0.079832785],"study_design_scores_gemma":[0.00024087614,0.00004905064,0.000001738495,0.000010221852,0.0000032725093,0.0000025834809,0.0000016764864,0.88755816,0.0010104894,0.109332725,0.0016177816,0.00017142559],"about_ca_topic_score_codex":0.000007818562,"about_ca_topic_score_gemma":9.146142e-7,"teacher_disagreement_score":0.8701905,"about_ca_system_score_codex":0.000015260493,"about_ca_system_score_gemma":0.00003775939,"threshold_uncertainty_score":0.5051441},"labels":[],"label_agreement":null},{"id":"W2968518909","doi":"10.1007/978-3-030-23876-6_14","title":"Flexible Statistical Learning Model for Unsupervised Image Modeling and Segmentation","year":2019,"lang":"en","type":"book-chapter","venue":"Unsupervised and semi-supervised learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Computer science; Unsupervised learning; Segmentation; Pattern recognition (psychology); Image segmentation; Image (mathematics); Statistical learning; Machine learning","score_opus":0.026760548217581216,"score_gpt":0.26563398885544515,"score_spread":0.23887344063786392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968518909","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006820216,0.0024612625,0.96917194,0.00032319504,0.00022328849,0.0013887185,0.00006733496,0.0005617328,0.025120476],"genre_scores_gemma":[0.014774416,0.0033322223,0.84300584,0.00074878114,0.00034689522,0.00011176107,0.00057653495,0.00040742743,0.1366961],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946566,0.0002657158,0.0010759747,0.0022020107,0.00073051127,0.0010691577],"domain_scores_gemma":[0.99716145,0.00077747856,0.00028645713,0.0007812283,0.00042360998,0.0005697689],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013609735,0.0012157034,0.0014410259,0.0005512877,0.000919324,0.00090451183,0.0007668909,0.0009145655,0.000105391104],"category_scores_gemma":[0.00018476912,0.0012326745,0.00031739176,0.00013299576,0.00017199924,0.0010933012,0.00064570055,0.0019219327,0.000035363955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002681854,0.00007869368,0.00008746553,0.0021356244,0.00040012188,0.000044155666,0.008831362,0.055705614,0.009793694,0.5127176,0.00036594007,0.40957156],"study_design_scores_gemma":[0.002321861,0.00035661273,0.0000031987402,0.0004304719,0.00020297676,0.00003651108,0.00015031967,0.9397703,0.000105881765,0.05253269,0.0027371773,0.0013520198],"about_ca_topic_score_codex":0.000022186441,"about_ca_topic_score_gemma":0.000004032071,"teacher_disagreement_score":0.8840647,"about_ca_system_score_codex":0.0001229234,"about_ca_system_score_gemma":0.0003854028,"threshold_uncertainty_score":0.9990123},"labels":[],"label_agreement":null},{"id":"W2968914429","doi":"10.1007/978-3-030-27202-9_24","title":"Bayesian Learning of Infinite Asymmetric Gaussian Mixture Models for Background Subtraction","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Background subtraction; Computer science; Artificial intelligence; Gaussian; Gaussian process; Bayesian probability; Parametric statistics; Subtraction; Pattern recognition (psychology); Parametric model; Algorithm; Machine learning; Pixel; Mathematics; Statistics","score_opus":0.028660942511489367,"score_gpt":0.2760545609181368,"score_spread":0.24739361840664742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968914429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011710066,0.0007076022,0.9852586,0.00038815365,0.0019324779,0.00085617526,0.000010579709,0.000120152654,0.010714554],"genre_scores_gemma":[0.106527515,0.000094169605,0.8913515,0.0004989038,0.00039439925,0.000012802478,0.000012529188,0.000065663575,0.0010425005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952981,0.000105609,0.00086487544,0.0018542978,0.0010321817,0.0008449321],"domain_scores_gemma":[0.99571735,0.0013057827,0.00080083025,0.001478365,0.0004814588,0.00021622554],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019951581,0.0007125419,0.0010074057,0.001928589,0.00025562965,0.00043994797,0.0027296124,0.00075348123,0.00001051611],"category_scores_gemma":[0.00012523815,0.00065372005,0.00035879086,0.0012791702,0.0003642602,0.0012708722,0.0006822794,0.0013695628,0.000010566388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001742342,0.000030424591,0.000014839808,0.00016647977,0.000022756705,0.000010238766,0.00042576506,0.06304027,0.00017933754,0.2413879,0.000017499477,0.69468707],"study_design_scores_gemma":[0.00031279374,0.00027601747,0.000022711532,0.00029079115,0.000017082639,0.00003457087,2.0139986e-7,0.6481953,0.0007609246,0.34857467,0.001000135,0.00051480596],"about_ca_topic_score_codex":0.00002413273,"about_ca_topic_score_gemma":0.000022346103,"teacher_disagreement_score":0.69417226,"about_ca_system_score_codex":0.0002649912,"about_ca_system_score_gemma":0.00085440284,"threshold_uncertainty_score":0.9995914},"labels":[],"label_agreement":null},{"id":"W2968970577","doi":"10.22215/etd/2018-13213","title":"Clustering Profiles in Generalized Linear Mixed Models Settings Using Bayesian Nonparametric Statistics","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Generalized linear mixed model; Cluster analysis; Dirichlet process; Mathematics; Random effects model; Generalized linear model; Frequentist inference; Mixed model; Statistics; Covariate; Population; Mixture model; Linear model; Nonparametric statistics; Bayesian probability; Bayesian inference","score_opus":0.03263204051873634,"score_gpt":0.31553539463230357,"score_spread":0.2829033541135672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968970577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052884896,0.00020707095,0.9893446,0.000032754593,0.0013477878,0.00060911325,0.00003300873,0.00016580746,0.0029713884],"genre_scores_gemma":[0.003514094,0.000053795287,0.9926015,0.00019623035,0.00023991491,0.000038803977,0.0002268439,0.00008015097,0.0030486302],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965537,0.00029024182,0.0008838538,0.0010695659,0.0005302758,0.00067233486],"domain_scores_gemma":[0.9980979,0.00014502191,0.0004523991,0.000814965,0.00031342913,0.00017631515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008811101,0.0005549511,0.0007604435,0.0009703326,0.00015577403,0.00030231476,0.0011119997,0.0005433596,0.000037255108],"category_scores_gemma":[0.00011687292,0.0005286669,0.00012936925,0.0012727587,0.000033349308,0.0005472147,0.00020086761,0.00048930215,0.000011832083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027118216,0.0005163088,0.00006129464,0.0028175025,0.00029175266,0.00032800838,0.01249579,0.01418063,0.0064945836,0.23278362,0.007991468,0.72176784],"study_design_scores_gemma":[0.00040265714,0.000049002854,0.000028276869,0.00022884553,0.000028461425,0.000010959708,0.000045001954,0.95177263,0.0026815129,0.044044413,0.000100207646,0.0006080311],"about_ca_topic_score_codex":0.0003552935,"about_ca_topic_score_gemma":0.00042329822,"teacher_disagreement_score":0.93759197,"about_ca_system_score_codex":0.00015105047,"about_ca_system_score_gemma":0.00036656167,"threshold_uncertainty_score":0.99971646},"labels":[],"label_agreement":null},{"id":"W2969078223","doi":"10.1007/978-3-030-23876-6_12","title":"Color Image Segmentation Using Semi-bounded Finite Mixture Models by Incorporating Mean Templates","year":2019,"lang":"en","type":"book-chapter","venue":"Unsupervised and semi-supervised learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Pattern recognition (psychology); Dirichlet distribution; Segmentation; Artificial intelligence; Mathematics; Mixture model; Image segmentation; Pixel; Geometric mean; Homogeneity (statistics); Harmonic mean; Computer science; Statistics; Mathematical analysis","score_opus":0.023380741351514453,"score_gpt":0.24539918388375562,"score_spread":0.22201844253224118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969078223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050043603,0.003469954,0.94164777,0.00026055,0.00045041763,0.001149265,0.000088245535,0.0005190965,0.04741036],"genre_scores_gemma":[0.041132234,0.0016947169,0.8296355,0.0021158135,0.0007114277,0.000056547495,0.0011414916,0.00065150234,0.12286077],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944937,0.00043689492,0.0011804109,0.0020272608,0.0009320698,0.00092961447],"domain_scores_gemma":[0.9966627,0.0006940123,0.00071991916,0.0010504314,0.0004115363,0.00046140538],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0011566051,0.0013556076,0.001460157,0.0005181019,0.0009534093,0.0011904746,0.0011504174,0.0012062002,0.00014337007],"category_scores_gemma":[0.00007230652,0.0013362877,0.0003933986,0.000273939,0.00020849043,0.0019411087,0.00073533447,0.0020624737,0.000051919706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036301327,0.00028000036,0.00037436318,0.0031936506,0.0015683348,0.0004562869,0.02970764,0.023585059,0.37449163,0.3683346,0.0035711185,0.1940743],"study_design_scores_gemma":[0.0017707763,0.00027236322,0.0000015388358,0.00092642754,0.0001998297,0.00007912257,0.00021269755,0.9364798,0.0014463173,0.051822547,0.004982996,0.0018055914],"about_ca_topic_score_codex":0.00008199685,"about_ca_topic_score_gemma":0.000011218515,"teacher_disagreement_score":0.9128947,"about_ca_system_score_codex":0.00023013826,"about_ca_system_score_gemma":0.0004127512,"threshold_uncertainty_score":0.9999195},"labels":[],"label_agreement":null},{"id":"W2969211293","doi":"10.1002/sta4.243","title":"A bootstrap‐augmented alternating expectation‐conditional maximization algorithm for mixtures of factor analyzers","year":2019,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Latent variable; Expectation–maximization algorithm; Cluster analysis; Curse of dimensionality; Benchmark (surveying); Computer science; Nonparametric statistics; Maximization; Latent variable model; Mixture model; Algorithm; Factor (programming language); Artificial intelligence; Machine learning; Mathematics; Statistics; Mathematical optimization; Maximum likelihood","score_opus":0.02134522745326021,"score_gpt":0.30081382187536704,"score_spread":0.2794685944221068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969211293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011126638,0.00005304356,0.98776484,0.00011116258,0.00025740132,0.0002812206,0.00010319949,0.000040099294,0.00026242482],"genre_scores_gemma":[0.17408459,0.0000044784747,0.82547,0.00008930867,0.000040494782,0.000018816228,0.000059440958,0.000007833219,0.00022507335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991144,0.00004745549,0.00021524697,0.0002527399,0.00021035361,0.00015978234],"domain_scores_gemma":[0.9993453,0.00011907199,0.00015752742,0.00019722899,0.00013510024,0.000045761335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001223412,0.000097146236,0.00014531527,0.00011212962,0.00004513759,0.000043186672,0.00025026445,0.000037915906,0.000060626946],"category_scores_gemma":[0.000021266713,0.000089334724,0.00008145399,0.00015469243,0.000017180539,0.0002980526,0.000034159904,0.00004751249,0.0000034739003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026758285,0.00014214384,0.0010373881,0.00012098641,0.00020817711,0.0000043752284,0.0032474485,0.0012900162,0.03639529,0.10581129,0.0011888741,0.8505272],"study_design_scores_gemma":[0.0010820638,0.00015643246,0.0018298567,0.0000312753,0.000012387457,0.0000046339283,0.000062413375,0.8920657,0.04164328,0.062582724,0.00030781043,0.00022141101],"about_ca_topic_score_codex":0.000010259542,"about_ca_topic_score_gemma":0.0000011543237,"teacher_disagreement_score":0.8907757,"about_ca_system_score_codex":0.00002453792,"about_ca_system_score_gemma":0.00004564824,"threshold_uncertainty_score":0.36429644},"labels":[],"label_agreement":null},{"id":"W2969422181","doi":"10.1002/cjs.11520","title":"A random‐effects model for clustered circular data","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Statistics; von Mises distribution; Mathematics; Cluster (spacecraft); Measure (data warehouse); Regression analysis; Random effects model; Regression; Distribution (mathematics); Maximum likelihood; von Mises yield criterion; Computer science; Engineering; Data mining; Mathematical analysis; Finite element method","score_opus":0.059241308369944665,"score_gpt":0.2720931044941898,"score_spread":0.2128517961242451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969422181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016954784,0.00037603878,0.9976137,0.00031133014,0.0007740424,0.000247777,0.0003341401,0.000004068183,0.00016933188],"genre_scores_gemma":[0.06832047,0.000010863103,0.9307399,0.0005845952,0.00007899115,0.0000014468876,0.000011966207,0.000012559882,0.00023923558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990015,0.00006965344,0.0002968331,0.00018927502,0.00014963347,0.0002931041],"domain_scores_gemma":[0.9981092,0.0003196417,0.00019297171,0.0006381938,0.00024300993,0.00049695827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007865363,0.000104954524,0.00027475884,0.00014782663,0.00006999369,0.00014071337,0.0012925233,0.000056655324,0.000007074363],"category_scores_gemma":[0.000331308,0.000094248004,0.000049422266,0.00009617886,0.000026439027,0.0003283864,0.000048245052,0.00014783401,0.0000053014105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007359194,0.000035134442,0.00024367175,0.00052124925,0.00024699795,0.00054383604,0.0024172196,0.0059680846,0.0004890591,0.55420643,0.12722056,0.30803418],"study_design_scores_gemma":[0.0014247618,0.00008060863,0.00003988509,0.000043649103,0.00003052656,0.00008206759,0.0000033400254,0.89210457,0.000021497734,0.1025963,0.0034574897,0.00011533317],"about_ca_topic_score_codex":0.00013120227,"about_ca_topic_score_gemma":0.00081570965,"teacher_disagreement_score":0.8861365,"about_ca_system_score_codex":0.000060309045,"about_ca_system_score_gemma":0.0016538345,"threshold_uncertainty_score":0.3843322},"labels":[],"label_agreement":null},{"id":"W2970480640","doi":"10.1139/cjfr-2019-0170","title":"An application niche for finite mixture models in forest resource surveys","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"","keywords":"Statistics; Mathematics; Estimator; Variance (accounting); Population; Sampling (signal processing); Sample (material); Sample size determination; Mixture model; Econometrics; Computer science; Demography","score_opus":0.05690737247889674,"score_gpt":0.34284193584592276,"score_spread":0.28593456336702605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970480640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08699442,0.00034899882,0.9094354,0.0012508017,0.00011764336,0.0005396495,0.000012423099,0.000006349754,0.0012943103],"genre_scores_gemma":[0.91992366,0.000010955152,0.07938636,0.00012970479,0.00015915636,0.000025166037,0.000008255501,0.00002252057,0.00033424108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697024,0.00096740935,0.00043110963,0.00036048176,0.0004799648,0.0007908162],"domain_scores_gemma":[0.9968388,0.00068800367,0.00013989786,0.00078105915,0.0006980233,0.0008542181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011132031,0.00013996805,0.0002810786,0.0010177013,0.00016122224,0.00027992312,0.0019206945,0.00019104726,0.000007978685],"category_scores_gemma":[0.00028609287,0.00012391765,0.00010524236,0.0009032141,0.00008824716,0.0007770966,0.000045910212,0.0007742444,0.000010051883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009094381,0.00012200424,0.20033802,0.00013964047,0.000041649208,0.00015828776,0.0031370828,0.059115477,0.00054390857,0.511304,0.005713981,0.21929498],"study_design_scores_gemma":[0.0011143875,0.0007682247,0.07101598,0.00012265652,0.0000043141704,0.00006748443,0.000062870335,0.4804315,0.00014221542,0.42850152,0.017477443,0.00029141488],"about_ca_topic_score_codex":0.0047208252,"about_ca_topic_score_gemma":0.16658288,"teacher_disagreement_score":0.8329292,"about_ca_system_score_codex":0.0002358654,"about_ca_system_score_gemma":0.0019174201,"threshold_uncertainty_score":0.8486248},"labels":[],"label_agreement":null},{"id":"W2970638446","doi":"10.11575/prism/36741","title":"Joint modeling of clustered binary data with crossed random effects via the Gaussian copula mixed model","year":2019,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Copula (linguistics); Binary number; Gaussian; Joint (building); Binary data; Mathematics; Statistics; Computer science; Econometrics; Engineering; Physics","score_opus":0.06274235725773347,"score_gpt":0.33308470070444984,"score_spread":0.27034234344671637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970638446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017050603,0.00032110224,0.97497964,0.00011804606,0.0005280332,0.0020529092,0.00005100787,0.0000053268586,0.0048933295],"genre_scores_gemma":[0.32719555,0.000017927048,0.66800153,0.00005647767,0.000038622155,0.000048404534,0.00073488336,0.00005085726,0.0038557379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970387,0.00037773943,0.000593128,0.0011333758,0.00049105415,0.00036595165],"domain_scores_gemma":[0.99563897,0.00017273804,0.0005570864,0.0033652778,0.00016222722,0.000103720784],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015854992,0.00043752222,0.0009017101,0.00012092174,0.00020096278,0.0005697838,0.005271287,0.00029261556,0.000017478063],"category_scores_gemma":[0.000048894504,0.0002710934,0.000113097114,0.00028110077,0.000045868812,0.00080615404,0.001045668,0.00044679962,0.000023837694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038898934,0.00054583064,0.0000075931493,0.0013148983,0.0007780001,0.00011097042,0.017266918,0.13328056,0.02186168,0.0018946084,0.0011931602,0.8178559],"study_design_scores_gemma":[0.0024841924,0.00012262694,0.000013231075,0.00064491056,0.0001383202,0.000010663874,0.000070291055,0.9909698,0.003449429,0.0016654228,0.000046025092,0.0003851153],"about_ca_topic_score_codex":0.00015012248,"about_ca_topic_score_gemma":0.00018358724,"teacher_disagreement_score":0.8576892,"about_ca_system_score_codex":0.00002864645,"about_ca_system_score_gemma":0.00058421656,"threshold_uncertainty_score":0.99997413},"labels":[],"label_agreement":null},{"id":"W2974097300","doi":"10.1109/iri.2019.00050","title":"Data Clustering Using Online Variational Learning of Finite Scaled Dirichlet Mixture Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Scalability; Inference; Latent Dirichlet allocation; Data mining; Mixture model; Dirichlet distribution; Topic model; Machine learning; Data modeling; Anomaly detection; Artificial intelligence; Bayesian inference; Bayesian probability; Mathematics","score_opus":0.06868351113407842,"score_gpt":0.311060159901088,"score_spread":0.24237664876700957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974097300","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003805247,0.000077458746,0.99332994,0.00021609482,0.0002267829,0.00012281767,0.000030467756,0.000071336304,0.0021198245],"genre_scores_gemma":[0.15847863,0.0000074411414,0.8405132,0.00021409077,0.00006612178,5.475443e-7,0.000045133038,0.000010300159,0.0006645242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985732,0.00014273428,0.00029962455,0.0004775131,0.00028955334,0.00021737772],"domain_scores_gemma":[0.9985153,0.00022572593,0.00014869665,0.00094665954,0.00010035254,0.00006324473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006291541,0.00013567234,0.00024274304,0.00010082692,0.00005813941,0.00006730482,0.0011815195,0.0000894058,0.00005182367],"category_scores_gemma":[0.000056527326,0.000115945884,0.000046787114,0.0003016538,0.000015955446,0.0009705455,0.0011198102,0.00021570412,0.000006053807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027404385,0.00020118429,0.0007116036,0.00012985068,0.0000951661,0.000007645945,0.00081208226,0.6508648,0.015849084,0.2694812,0.00021736998,0.06160263],"study_design_scores_gemma":[0.00027128286,0.000023373497,0.0001389797,0.000038704682,0.00000868018,0.00000857281,0.000006310493,0.9854678,0.000105776024,0.013451551,0.00033498564,0.00014396533],"about_ca_topic_score_codex":0.00003476476,"about_ca_topic_score_gemma":0.0000076117512,"teacher_disagreement_score":0.33460304,"about_ca_system_score_codex":0.000016986634,"about_ca_system_score_gemma":0.00008591789,"threshold_uncertainty_score":0.4728136},"labels":[],"label_agreement":null},{"id":"W2975042594","doi":"10.1109/tnnls.2019.2938830","title":"Modeling and Clustering Positive Vectors via Nonparametric Mixture Models of Liouville Distributions","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Huaqiao University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Cluster analysis; Mixture model; Bayesian inference; Inference; Computer science; Nonparametric statistics; Mixture distribution; Bayes' theorem; Algorithm; Mathematics; Bayesian probability; Artificial intelligence; Applied mathematics; Probability density function; Statistics","score_opus":0.010398795867819088,"score_gpt":0.22535031836682987,"score_spread":0.21495152249901078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975042594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07286982,0.00088185683,0.92505556,0.000049094237,0.0006963161,0.00028695574,0.0000054866123,0.000078673875,0.000076259406],"genre_scores_gemma":[0.99163175,0.00012291285,0.008020355,0.000023750179,0.00004419192,0.000013925058,0.0000018536978,0.00001713178,0.00012412568],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984966,0.0003067537,0.00030808133,0.0004319201,0.00017132773,0.00028531122],"domain_scores_gemma":[0.9992047,0.00024696463,0.00010226903,0.00024422017,0.00007942237,0.000122439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034838956,0.00020697928,0.00034864436,0.00018331104,0.00029855059,0.00014084126,0.00017055158,0.00015330188,0.000001538736],"category_scores_gemma":[0.0000033571273,0.00018219653,0.000087400935,0.0004983232,0.000033738655,0.0003660906,0.000008675608,0.00063077314,7.225267e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015981916,0.000021192836,0.000014583548,0.000039032708,0.000028332004,0.0000019023241,0.0002666982,0.9753401,0.00023986233,0.0006594519,0.0000017213782,0.023371132],"study_design_scores_gemma":[0.00026110365,0.0002122567,0.000021766933,0.00012786043,0.000023301482,0.00006381875,0.000035724093,0.9988873,0.00006099479,0.00011021344,0.000006674948,0.00018901406],"about_ca_topic_score_codex":0.00020686933,"about_ca_topic_score_gemma":0.0000065407294,"teacher_disagreement_score":0.9187619,"about_ca_system_score_codex":0.000024897236,"about_ca_system_score_gemma":0.000011064179,"threshold_uncertainty_score":0.7429759},"labels":[],"label_agreement":null},{"id":"W2980316693","doi":"10.3390/econometrics7040043","title":"Likelihood Inference for Generalized Integer Autoregressive Time Series Models","year":2019,"lang":"en","type":"article","venue":"Econometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoregressive model; Mathematics; Negative binomial distribution; Series (stratigraphy); STAR model; Binomial (polynomial); Applied mathematics; Inference; Quasi-likelihood; Integer (computer science); Count data; Statistics; Time series; Likelihood function; Overdispersion; Estimation theory; Computer science; Autoregressive integrated moving average; Artificial intelligence; Poisson distribution","score_opus":0.027097747589056292,"score_gpt":0.2614788993959245,"score_spread":0.23438115180686822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980316693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033964824,0.0004246868,0.9856675,0.00051237625,0.0006796996,0.0003950313,0.000021939059,0.00012947145,0.008772762],"genre_scores_gemma":[0.06268908,0.0000659783,0.9301327,0.00056545995,0.00011006171,0.00006699716,0.000010411158,0.000022909971,0.006336444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863076,0.000051544648,0.0002940508,0.00051933626,0.00011630283,0.0003879791],"domain_scores_gemma":[0.9985658,0.00030734474,0.00016970778,0.0006645496,0.00015457271,0.00013804957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050368713,0.00019396006,0.00035078003,0.00047211384,0.000068467525,0.00024254629,0.0008651242,0.00012305155,0.00010469035],"category_scores_gemma":[0.00014270547,0.0001729858,0.00013699669,0.00065701274,0.000025169835,0.0012976587,0.00024626963,0.000120818244,0.00023701096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016702705,0.000055188884,0.00020007258,0.00004844114,0.00004807436,0.0000024697347,0.0006150251,0.0007864271,0.00016127393,0.88863075,0.0027667116,0.10666889],"study_design_scores_gemma":[0.00055103214,0.00016485678,0.00010117257,0.000013966142,0.000009297245,0.0000057297752,0.0000044731455,0.5700576,0.0009263076,0.42088327,0.0069520227,0.00033031908],"about_ca_topic_score_codex":0.0000056129925,"about_ca_topic_score_gemma":9.577539e-7,"teacher_disagreement_score":0.56927115,"about_ca_system_score_codex":0.0000665522,"about_ca_system_score_gemma":0.00012888566,"threshold_uncertainty_score":0.70541567},"labels":[],"label_agreement":null},{"id":"W2989118260","doi":"10.1109/globalsip45357.2019.8969324","title":"An Accurate Evaluation of MSD Log-likelihood and its Application in Human Action Recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Likelihood function; Inference; Fisher information; Cluster analysis; Dirichlet distribution; Scoring algorithm; Function (biology); Artificial intelligence; Multinomial distribution; Model selection; Statistical inference; Algorithm; Pattern recognition (psychology); Machine learning; Estimation theory; Mathematics; Statistics","score_opus":0.07974195215454467,"score_gpt":0.3725193695027588,"score_spread":0.29277741734821416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989118260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47784868,0.000018647714,0.520644,0.000043196193,0.00003594287,0.0002680706,3.4460336e-7,0.000018165523,0.0011229434],"genre_scores_gemma":[0.95693856,0.000010389589,0.0429272,0.00004842153,0.000017304199,0.000029973275,0.000009006985,0.0000036808792,0.00001542887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990366,0.00022131999,0.00017674474,0.00027247466,0.00019780346,0.00009506981],"domain_scores_gemma":[0.99943227,0.000021779137,0.00010051515,0.00023745932,0.00017457783,0.000033399545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014535355,0.000064648884,0.00009494167,0.00010993681,0.00002401722,0.0000280216,0.00013598251,0.00006521907,0.000017003857],"category_scores_gemma":[0.00001232739,0.00006013373,0.000013435978,0.00019354066,0.0000055215337,0.0007747854,0.000025770787,0.00006094216,0.000010345552],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039026872,0.00005514673,0.00035724108,0.000016859833,0.0000023003936,4.6842295e-8,0.00022794296,0.000027112143,0.20223169,0.020760832,0.000003897602,0.776313],"study_design_scores_gemma":[0.00067692436,0.00012310484,0.020926747,0.000018716464,0.000010954782,0.00000259392,0.000027065242,0.686743,0.090216,0.20111893,0.000011627921,0.00012433188],"about_ca_topic_score_codex":0.00004383886,"about_ca_topic_score_gemma":0.00006406997,"teacher_disagreement_score":0.7761887,"about_ca_system_score_codex":0.000028367242,"about_ca_system_score_gemma":0.000029291656,"threshold_uncertainty_score":0.24521823},"labels":[],"label_agreement":null},{"id":"W2989153917","doi":"10.1007/s00180-019-00931-w","title":"A support vector machine based semiparametric mixture cure model","year":2019,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Covariate; Support vector machine; Mixture model; Computer science; Nonparametric statistics; Semiparametric model; Incidence (geometry); Accelerated failure time model; Machine learning; Artificial intelligence; Data mining; Statistics; Mathematics","score_opus":0.013355577703301326,"score_gpt":0.26861180554985825,"score_spread":0.25525622784655694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989153917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018339096,0.00009134496,0.99660933,0.00056834635,0.0003547627,0.00024651052,0.00041271804,0.00012504023,0.0014085826],"genre_scores_gemma":[0.16013482,0.0000029075359,0.8373969,0.0014954116,0.000035753794,0.000008592194,0.0002056562,0.00001825416,0.00070166175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982722,0.00009507643,0.00030635708,0.00048392895,0.00053895655,0.00030351346],"domain_scores_gemma":[0.9984692,0.0005784452,0.00013746865,0.00039133066,0.00025953425,0.00016406819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029419098,0.00021740637,0.00025947197,0.00018592284,0.00009250774,0.00013947781,0.00060061424,0.00009721491,0.00013285686],"category_scores_gemma":[0.000076103956,0.0002045996,0.00006901013,0.00056575617,0.00003291218,0.00018397022,0.000118483775,0.0002496,0.00018624084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009024201,0.000084946245,0.00026798685,0.00004736931,0.000018268196,0.000019426272,0.00010319928,0.2519377,0.000032304044,0.7093675,0.017193837,0.020918436],"study_design_scores_gemma":[0.00037447648,0.00006955785,0.00072681037,0.000007789199,0.000008355623,0.000010830006,4.5034133e-7,0.7608276,0.000020553387,0.23676275,0.0009947332,0.00019609134],"about_ca_topic_score_codex":0.0000066297484,"about_ca_topic_score_gemma":0.0000016746726,"teacher_disagreement_score":0.5088899,"about_ca_system_score_codex":0.00006087027,"about_ca_system_score_gemma":0.00036919222,"threshold_uncertainty_score":0.83433294},"labels":[],"label_agreement":null},{"id":"W2990179544","doi":"10.1007/s00500-019-04567-2","title":"A new hybrid discriminative/generative model using the full-covariance multivariate generalized Gaussian mixture models","year":2019,"lang":"en","type":"article","venue":"Soft Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Fisher kernel; Artificial intelligence; Pattern recognition (psychology); Computer science; Covariance; Machine learning; Kernel (algebra); Model selection; Mixture model; Gaussian process; Markov chain Monte Carlo; Generative model; Support vector machine; Marginal likelihood; Gaussian; Mathematics; Kernel Fisher discriminant analysis; Bayesian probability; Facial recognition system; Generative grammar; Statistics","score_opus":0.041435020689575344,"score_gpt":0.3000837096003409,"score_spread":0.2586486889107656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990179544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010873437,0.0003698708,0.98472744,0.0013234814,0.0008084863,0.0006025392,0.0000071730587,0.00022980169,0.0010577827],"genre_scores_gemma":[0.34475526,0.0000035620114,0.65361696,0.0008123705,0.00024729397,0.0000036591957,0.0000029321711,0.00003229837,0.00052563543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996668,0.0005158044,0.00050698104,0.0010568426,0.00047654542,0.0007758259],"domain_scores_gemma":[0.99787736,0.0002429245,0.00035239145,0.0011404991,0.00017077649,0.00021604024],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009287154,0.00048001762,0.0005293672,0.000113980575,0.0005507807,0.00047003885,0.0016021078,0.00012194035,0.000010692513],"category_scores_gemma":[0.000047541598,0.00034077812,0.00022935552,0.0004963874,0.00006003328,0.00085279025,0.0008175476,0.00054734846,0.000014479718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018896513,0.0000290418,0.000005455817,0.000018761171,0.000059912567,0.000013631321,0.005535369,0.6204941,0.016362548,0.3155803,0.00035097604,0.041530985],"study_design_scores_gemma":[0.0006417445,0.000029461786,0.0000074523036,0.00007938277,0.000022248338,0.000054293705,0.00002465018,0.80184364,0.002869993,0.19398206,0.000054076496,0.0003909722],"about_ca_topic_score_codex":0.00017594424,"about_ca_topic_score_gemma":0.0000063132534,"teacher_disagreement_score":0.33388183,"about_ca_system_score_codex":0.00011191017,"about_ca_system_score_gemma":0.00039131008,"threshold_uncertainty_score":0.9999044},"labels":[],"label_agreement":null},{"id":"W2990678768","doi":"10.1007/978-981-15-2700-5_11","title":"Parsimonious Mixtures of Matrix Variate Bilinear Factor Analyzers","year":2020,"lang":"en","type":"book-chapter","venue":"Behaviormetrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random variate; Bilinear interpolation; Cluster analysis; Computer science; Dimensionality reduction; Dimension (graph theory); Artificial intelligence; Data Matrix; Matrix (chemical analysis); Pattern recognition (psychology); Factor (programming language); Multivariate statistics; Data mining; Machine learning; Mathematics; Statistics; Chromatography; Chemistry; Random variable","score_opus":0.04303499046687131,"score_gpt":0.2973956567679975,"score_spread":0.2543606663011262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990678768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008359955,0.0021125814,0.9714852,0.00013349351,0.00081018335,0.00040305752,0.00025565948,0.00019728298,0.02451897],"genre_scores_gemma":[0.009638729,0.0009514799,0.92006844,0.00022357698,0.00031483348,0.000008708307,0.000057726997,0.00015502787,0.068581454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99695146,0.00006435549,0.00081721344,0.0009150814,0.00086562446,0.00038626333],"domain_scores_gemma":[0.99723685,0.00023323526,0.00069260004,0.001223113,0.0002867887,0.0003274076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032069505,0.00057980826,0.0009880513,0.0010604019,0.0000754531,0.00012807251,0.0017059487,0.00070553256,0.00012107333],"category_scores_gemma":[0.00012251333,0.0005298442,0.0005618814,0.0007851599,0.00009321035,0.00018996549,0.00051199395,0.0007396198,0.00006245502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023979805,0.00014723111,0.0001783544,0.0002205721,0.0002132566,0.0003679688,0.00050803425,0.000012236124,0.0010418604,0.634041,0.0037969332,0.35944855],"study_design_scores_gemma":[0.0054374468,0.0043476024,0.0031249165,0.0010397037,0.0046666507,0.00029157355,0.000025418003,0.020586267,0.026838614,0.47268602,0.4486706,0.012285191],"about_ca_topic_score_codex":0.00003220883,"about_ca_topic_score_gemma":0.0000020730708,"teacher_disagreement_score":0.44487366,"about_ca_system_score_codex":0.00009440955,"about_ca_system_score_gemma":0.00028314107,"threshold_uncertainty_score":0.9997153},"labels":[],"label_agreement":null},{"id":"W2990773367","doi":"10.1111/coin.12246","title":"Proportional data modeling via selection and estimation of a finite mixture of scaled Dirichlet distributions","year":2019,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Generalized Dirichlet distribution; Computer science; Mathematics; Latent Dirichlet allocation; Flexibility (engineering); Model selection; Selection (genetic algorithm); Minimum description length; Algorithm; Artificial intelligence; Applied mathematics; Statistics; Topic model; Dirichlet's principle","score_opus":0.03672841445888648,"score_gpt":0.3151502190633023,"score_spread":0.27842180460441585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990773367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0098487595,0.00018375754,0.9893324,0.00021922533,0.0000890159,0.00019155552,0.000049835897,0.000027320135,0.000058179525],"genre_scores_gemma":[0.5471075,0.000009029537,0.4527507,0.00001650058,0.000008963302,0.0000024595374,0.00009365296,0.000002534116,0.000008627179],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987808,0.00006872344,0.00040247184,0.00034994236,0.00028854172,0.00010950994],"domain_scores_gemma":[0.9988534,0.00025800042,0.00019458191,0.00030008802,0.0003479845,0.000045960423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042097727,0.00010074522,0.00017255121,0.000099316625,0.000055906265,0.000028024157,0.00042799252,0.000057620357,0.000014861369],"category_scores_gemma":[0.00008409637,0.0000950988,0.000032434415,0.0003621311,0.00004988713,0.00048650653,0.00022647007,0.00010558364,0.0000049571304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008524539,0.00005733181,0.00017092454,0.00005480109,0.000015863208,2.6553533e-7,0.00010651822,0.76162684,0.0002960717,0.1753927,0.000020547957,0.062249627],"study_design_scores_gemma":[0.000047258305,0.000038361246,0.00029655456,0.00004034278,0.0000073938304,0.00001331673,0.000002009196,0.7955412,0.0008574105,0.20307416,0.000008038979,0.0000739268],"about_ca_topic_score_codex":0.0000145023905,"about_ca_topic_score_gemma":0.0000012820212,"teacher_disagreement_score":0.53725874,"about_ca_system_score_codex":0.000017375865,"about_ca_system_score_gemma":0.00011508934,"threshold_uncertainty_score":0.38780168},"labels":[],"label_agreement":null},{"id":"W2993455707","doi":"10.1016/j.knosys.2019.105335","title":"A novel approach for modeling positive vectors with inverted Dirichlet-based hidden Markov models","year":2019,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet distribution; Latent Dirichlet allocation; Markov model; Hierarchical Dirichlet process; Markov chain; Mathematics; Computer science; Hidden Markov model; Artificial intelligence; Statistics; Topic model; Mathematical analysis","score_opus":0.030298391765096105,"score_gpt":0.2504546480282327,"score_spread":0.2201562562631366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993455707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023763662,0.00065375667,0.9858807,0.00009412837,0.0006622896,0.0025604614,0.00005254053,0.00035960527,0.007360153],"genre_scores_gemma":[0.5429987,4.3347185e-7,0.4559286,0.00013665858,0.00010961835,0.0003557846,0.00004115147,0.000058488957,0.0003705618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99654853,0.00035422522,0.00057733187,0.0012626228,0.00047981986,0.0007774672],"domain_scores_gemma":[0.99706155,0.00041388304,0.00024725552,0.0012822491,0.0006937626,0.0003012791],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012412996,0.0005557469,0.000800962,0.00040037523,0.00021350752,0.00033579816,0.0011847506,0.00027877325,0.0000022208897],"category_scores_gemma":[0.000030014258,0.00044105173,0.0002576546,0.00087400485,0.000054737036,0.0005082102,0.000102780294,0.00029212813,0.000019914414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010023636,0.0023250624,0.00031141928,0.0034210084,0.0005691674,0.000015596252,0.0034160048,0.79346305,0.017385775,0.14980397,0.0014186315,0.02686796],"study_design_scores_gemma":[0.0031289095,0.00033433252,0.0000068141,0.00037026306,0.00005136651,0.000011427698,0.000043089836,0.99362975,0.0011786186,0.0005025069,0.000077070596,0.0006658762],"about_ca_topic_score_codex":0.00017066636,"about_ca_topic_score_gemma":0.00001477285,"teacher_disagreement_score":0.54062235,"about_ca_system_score_codex":0.00024826918,"about_ca_system_score_gemma":0.00074863824,"threshold_uncertainty_score":0.99980414},"labels":[],"label_agreement":null},{"id":"W2996041149","doi":"10.1007/s00180-022-01289-2","title":"Parameter-wise co-clustering for high-dimensional data","year":2022,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Cluster analysis; Interpretability; Dimensionality reduction; Clustering high-dimensional data; Curse of dimensionality; Computer science; Mathematics; Data mining; Model selection; Statistics; Artificial intelligence","score_opus":0.06835811246927098,"score_gpt":0.3403554281679049,"score_spread":0.27199731569863395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996041149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016886847,0.00005636794,0.9945682,0.00047654368,0.00062224775,0.0002463512,0.0037241234,0.00007075187,0.000066505316],"genre_scores_gemma":[0.034434833,8.2417404e-7,0.9623066,0.0009770256,0.00007646647,0.000050643455,0.0020268182,0.000014826182,0.00011193577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984109,0.00013790304,0.00027394367,0.00049471174,0.00045291337,0.00022965825],"domain_scores_gemma":[0.99776715,0.0014053955,0.00012074708,0.0005055824,0.00011301943,0.000088118875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054833735,0.0001279875,0.00016635924,0.000073624695,0.0004904968,0.00010753985,0.0011050144,0.000021437518,0.000064691914],"category_scores_gemma":[0.00012805086,0.00013951931,0.000025314836,0.000152029,0.000037716472,0.00018532491,0.001015716,0.00013888732,0.0000082475635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018458099,0.00008376047,0.000012270763,0.000020127787,0.00002959101,0.000021411272,0.00009945432,0.07409273,0.000016681084,0.75389045,0.05287811,0.11883698],"study_design_scores_gemma":[0.00027935932,0.000066065404,0.00019123097,0.0000017891738,0.000006053877,0.000022787568,0.0000015063531,0.5946054,0.0000038360467,0.40183303,0.0028798354,0.00010912805],"about_ca_topic_score_codex":0.000012882889,"about_ca_topic_score_gemma":0.000002129513,"teacher_disagreement_score":0.52051264,"about_ca_system_score_codex":0.000060919254,"about_ca_system_score_gemma":0.0001777093,"threshold_uncertainty_score":0.56894326},"labels":[],"label_agreement":null},{"id":"W2996949682","doi":"10.1609/aaai.v34i04.6148","title":"Fragmentation Coagulation Based Mixed Membership Stochastic Blockmodel","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Inference; Gibbs sampling; Data mining; Fragmentation (computing); Bayesian inference; Community structure; Parametric statistics; Bayesian probability; Theoretical computer science; Artificial intelligence; Mathematics; Statistics","score_opus":0.13246840546758681,"score_gpt":0.3062725757817495,"score_spread":0.17380417031416268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996949682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021720776,0.000009693939,0.96562815,0.00984924,0.00022881788,0.00036461846,0.0000030006042,0.000095920564,0.002099813],"genre_scores_gemma":[0.9089815,0.0000020823115,0.089932084,0.0009608495,0.000064308835,0.00002008208,7.116264e-7,0.000010763256,0.00002759387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825436,0.000038278235,0.00045553097,0.00049230334,0.0005032391,0.0002562729],"domain_scores_gemma":[0.99874336,0.00011129945,0.0003402007,0.00021835447,0.00045073635,0.00013604837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043586091,0.00020436611,0.00023317516,0.00007726208,0.00015119865,0.00019286091,0.0013043097,0.00009140958,0.00005228297],"category_scores_gemma":[0.00036446485,0.00016104504,0.00011334058,0.0006249572,0.00012219862,0.00036567872,0.00016823971,0.00024331237,0.000037017013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063969586,0.000062713276,0.000016760523,0.000037326266,0.00000879068,1.9873725e-7,0.0012241033,0.0027900266,0.032738,0.8988946,0.00012577565,0.06403774],"study_design_scores_gemma":[0.000028830664,0.000097638476,0.000029279887,0.000059838698,0.00001068073,5.4367445e-7,0.0000694871,0.62101215,0.21565779,0.16290484,0.000005943407,0.00012295153],"about_ca_topic_score_codex":0.00001137122,"about_ca_topic_score_gemma":0.0000022547797,"teacher_disagreement_score":0.88726074,"about_ca_system_score_codex":0.00003188051,"about_ca_system_score_gemma":0.00010401427,"threshold_uncertainty_score":0.6567226},"labels":[],"label_agreement":null},{"id":"W2999012716","doi":"","title":"Échantillonnage de Gibbs avec augmentation de données et imputation multiple","year":2006,"lang":"fr","type":"article","venue":"Corpus Université Laval (Université Laval)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.013595324639748899,"score_gpt":0.21826410614413222,"score_spread":0.20466878150438333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999012716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.115542114,0.0028257207,0.85791856,0.008022349,0.0010708917,0.0004354206,0.00008788586,0.00032074787,0.013776315],"genre_scores_gemma":[0.56753427,0.0039868904,0.35180938,0.00096494006,0.00046194403,0.0000034203854,0.00015029468,0.000091097085,0.07499777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960781,0.00091311045,0.00035706017,0.0009937958,0.0005422408,0.0011157264],"domain_scores_gemma":[0.9977571,0.00037550426,0.0004326848,0.00064257317,0.00035416157,0.00043800834],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008982877,0.00057052204,0.00049604435,0.00056044577,0.0008056563,0.0003319375,0.0011378991,0.00049007917,0.00004425462],"category_scores_gemma":[0.000046671983,0.0007371856,0.000403083,0.0011983028,0.00021633325,0.0020115892,0.0005921489,0.0005650288,0.00004356779],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028184807,0.00044681484,0.007275373,0.00021207434,0.00018138543,0.002396367,0.044272106,0.0038492302,0.0827448,0.6554224,0.0038978083,0.1990198],"study_design_scores_gemma":[0.010977362,0.0010476253,0.06360068,0.0008457571,0.0012153321,0.0013468878,0.0032250797,0.54477835,0.12067053,0.09427162,0.15490495,0.0031158272],"about_ca_topic_score_codex":0.031916097,"about_ca_topic_score_gemma":0.014341039,"teacher_disagreement_score":0.5611507,"about_ca_system_score_codex":0.0017306665,"about_ca_system_score_gemma":0.00091390277,"threshold_uncertainty_score":0.9995079},"labels":[],"label_agreement":null},{"id":"W3001762958","doi":"10.48550/arxiv.2001.09367","title":"Particle-Gibbs Sampling For Bayesian Feature Allocation Models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gibbs sampling; Markov chain Monte Carlo; Feature (linguistics); Computer science; Bayesian inference; Inference; Particle filter; Bayesian probability; Markov chain; Algorithm; Artificial intelligence; Data mining; Machine learning; Mathematical optimization; Mathematics","score_opus":0.16377050649369362,"score_gpt":0.23767608843934115,"score_spread":0.07390558194564753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001762958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010119805,0.00014009161,0.9942791,0.002276691,0.0004643131,0.0006202712,0.000026074573,0.00032500626,0.00085651234],"genre_scores_gemma":[0.60231674,0.00006656011,0.39637256,0.0003747884,0.00013120627,0.0000041761614,0.000022044716,0.000022358296,0.00068954093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977549,0.0001523991,0.00019627626,0.0013835648,0.000093973664,0.00041894222],"domain_scores_gemma":[0.99805504,0.00014876199,0.00021946189,0.001102202,0.00019299073,0.000281556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034958037,0.0003466882,0.00039346822,0.00009869532,0.0001923704,0.0001967019,0.0016298157,0.0003996194,0.0000040286836],"category_scores_gemma":[0.00004324977,0.00039452527,0.00030458937,0.00043450372,0.00004803817,0.00050393626,0.0010423687,0.00054932246,0.0000094358875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029479983,0.00003302419,0.000015871226,0.00009683148,0.00005729324,0.0000222041,0.00034833653,0.113769375,0.00011016603,0.87907916,0.00029297243,0.006145292],"study_design_scores_gemma":[0.0002086448,0.000024846757,0.000009589525,0.00003435402,0.00004353301,0.0000012800195,0.0000097143475,0.5341381,0.00022274828,0.46473268,0.00033851576,0.00023600478],"about_ca_topic_score_codex":0.000023611554,"about_ca_topic_score_gemma":0.000010389919,"teacher_disagreement_score":0.60130477,"about_ca_system_score_codex":0.00014019049,"about_ca_system_score_gemma":0.00025732294,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W3004297963","doi":"10.1109/globalsip45357.2019.8969368","title":"Component Splitting-based Approach for Multivariate Beta Mixture Models Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multivariate statistics; Component (thermodynamics); Computer science; Inference; Focus (optics); Artificial intelligence; Mixture model; Categorization; Data modeling; Machine learning; Pattern recognition (psychology); Data mining; Object (grammar)","score_opus":0.02663243910837752,"score_gpt":0.26440843189218366,"score_spread":0.23777599278380615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004297963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007019568,0.00006596506,0.98388577,0.00042546596,0.00021211116,0.0007263584,0.0000023366113,0.00028966443,0.013690401],"genre_scores_gemma":[0.2993914,7.1601266e-7,0.6983628,0.00048596927,0.000045218807,0.000035666668,0.000012726478,0.000017355309,0.0016481039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817824,0.0001756875,0.00026791816,0.0006988752,0.00024067836,0.0004386111],"domain_scores_gemma":[0.99877995,0.00023589458,0.00011859029,0.0006297827,0.00010786852,0.00012788553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009211714,0.00022797137,0.00032144604,0.00009212673,0.00013894959,0.00016087347,0.00077364943,0.00013968328,0.000013784211],"category_scores_gemma":[0.00001699293,0.00018127105,0.00018288563,0.00018827293,0.00001867339,0.00034582213,0.00016802168,0.0002657988,0.000016328213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027939477,0.00015102235,0.000095503616,0.00010967407,0.000033964563,0.0000011632653,0.00045009083,0.09509248,0.004314578,0.8677453,0.00030984235,0.03166845],"study_design_scores_gemma":[0.000886712,0.0000847421,0.00003880988,0.000015188823,0.00000855024,0.0000023999762,0.000009379743,0.97946715,0.0023302415,0.015387482,0.0015017263,0.00026759072],"about_ca_topic_score_codex":0.00002987281,"about_ca_topic_score_gemma":4.4436712e-7,"teacher_disagreement_score":0.8843747,"about_ca_system_score_codex":0.000029751365,"about_ca_system_score_gemma":0.000061712024,"threshold_uncertainty_score":0.7392019},"labels":[],"label_agreement":null},{"id":"W3004403696","doi":"10.48550/arxiv.2001.10657","title":"The Indian Chefs Process","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Nonparametric statistics; Prior probability; Directed acyclic graph; Bayesian network; Computer science; Joint probability distribution; Artificial intelligence; Bayesian probability; Mathematics; Machine learning; Algorithm; Econometrics; Statistics","score_opus":0.07867511522997653,"score_gpt":0.20886698145039861,"score_spread":0.1301918662204221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004403696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0080935825,0.000102203965,0.9834094,0.0014969459,0.00056249544,0.0002670288,0.000005231386,0.00023345104,0.005829626],"genre_scores_gemma":[0.9837992,0.00017041096,0.0142702125,0.00038247948,0.00013701206,0.0000015635515,0.0000032664836,0.000016881704,0.0012189674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99817777,0.00020296901,0.00015525772,0.0010078407,0.00009821416,0.00035796428],"domain_scores_gemma":[0.99810106,0.000119251024,0.00020303378,0.001232248,0.00011552547,0.00022887354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034575333,0.0002721706,0.00025461687,0.00007792961,0.000318767,0.00026684368,0.0034244196,0.0002530512,0.0000063596294],"category_scores_gemma":[0.0000547063,0.00022880889,0.00018550917,0.0005720903,0.00011454064,0.0002262488,0.00182369,0.00084586715,0.0000639562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001816479,0.000033662407,0.00018767713,0.00010127825,0.00009219865,0.0004715116,0.0016512703,0.0032525645,0.000014180293,0.97823626,0.00079670845,0.015144508],"study_design_scores_gemma":[0.0002079905,0.00003110584,0.00021400671,0.00004779942,0.00003249164,0.000006112963,0.00006261629,0.1847699,0.00018272064,0.8115523,0.0024885836,0.0004043996],"about_ca_topic_score_codex":0.000028585511,"about_ca_topic_score_gemma":0.00001932525,"teacher_disagreement_score":0.9757056,"about_ca_system_score_codex":0.00007316292,"about_ca_system_score_gemma":0.00033754032,"threshold_uncertainty_score":0.9330556},"labels":[],"label_agreement":null},{"id":"W3004816779","doi":"10.1002/cjs.11645","title":"A test for independence via Bayesian nonparametric estimation of mutual information","year":2021,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mutual information; Frequentist inference; Independence (probability theory); Dirichlet process; Nonparametric statistics; Conditional independence; Mathematics; Bayesian probability; Econometrics; Estimation; Statistics; Computer science; Artificial intelligence; Data mining; Bayesian inference; Engineering","score_opus":0.01646882914035225,"score_gpt":0.25947171742922515,"score_spread":0.2430028882888729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004816779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026911747,0.00023448288,0.99725735,0.00016800022,0.0011077656,0.00024694944,0.00060722744,0.000005124075,0.0001039832],"genre_scores_gemma":[0.2488048,0.000020293948,0.75094426,0.00010302057,0.000056780424,0.000004592649,0.00004626099,0.000008372695,0.000011649975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981024,0.00008267203,0.0009730615,0.00016762839,0.00039590086,0.00027830456],"domain_scores_gemma":[0.9955505,0.0006157517,0.0013149214,0.00038999572,0.0016454689,0.00048337097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009481515,0.00019773544,0.00046951536,0.0008737004,0.00008370011,0.000357607,0.0008855957,0.000277204,0.000014187033],"category_scores_gemma":[0.002531514,0.00020569337,0.000121530495,0.00042054194,0.000066974906,0.0006381585,0.0000871496,0.0005975084,0.000001206449],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008442137,0.00003271124,0.00022326139,0.000701404,0.000089848196,0.00011393703,0.0030396825,0.01111132,0.000019238783,0.04503248,0.0034549518,0.9361727],"study_design_scores_gemma":[0.00040201287,0.00028069605,0.00097422756,0.00038645937,0.00009247568,0.00023060384,0.000042095166,0.8675181,0.00034074023,0.12904677,0.00037786114,0.00030796137],"about_ca_topic_score_codex":0.0011543033,"about_ca_topic_score_gemma":0.0017598865,"teacher_disagreement_score":0.93586475,"about_ca_system_score_codex":0.00022790652,"about_ca_system_score_gemma":0.0059745274,"threshold_uncertainty_score":0.9996607},"labels":[],"label_agreement":null},{"id":"W3006840371","doi":"10.1109/ssci44817.2019.9003076","title":"Efficient Computation of Log-likelihood Function in Clustering Overdispersed Count Data Using Multinomial Beta-Liouville Distribution","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Cluster analysis; Count data; Dirichlet distribution; Mathematics; Computer science; Algorithm; Statistics; Poisson distribution","score_opus":0.03387391639320726,"score_gpt":0.29009316489992787,"score_spread":0.2562192485067206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006840371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2597266,0.000025715051,0.7391717,0.000037086495,0.00050851656,0.00022595293,0.000018361847,0.000032080654,0.0002539899],"genre_scores_gemma":[0.7839786,9.2183313e-7,0.2158855,0.000037290447,0.000028687278,0.0000011084838,0.000056525132,0.000005495732,0.0000058786986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857134,0.000116412804,0.00035891452,0.0004712185,0.0002501562,0.00023193938],"domain_scores_gemma":[0.9990816,0.000058080972,0.00015243069,0.000588133,0.00007337982,0.000046334357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008040307,0.00012613507,0.00022531535,0.00009244302,0.00004443104,0.000053782136,0.00041737495,0.00007874945,0.0000105527715],"category_scores_gemma":[0.000016190286,0.00011505911,0.000041773717,0.00032411196,0.000019617612,0.00027984908,0.00047278134,0.00010480347,0.000009073627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028385906,0.0007849254,0.0069333278,0.0003190281,0.00008589681,0.000009573347,0.001510728,0.600081,0.06313749,0.046912998,0.00028131518,0.2796598],"study_design_scores_gemma":[0.00088735693,0.00005065491,0.0063206395,0.000042326392,0.000009863283,0.0000039861457,0.000033748463,0.9914841,0.00062666583,0.00036393324,0.000043743457,0.00013299119],"about_ca_topic_score_codex":0.00030289026,"about_ca_topic_score_gemma":0.00005333595,"teacher_disagreement_score":0.524252,"about_ca_system_score_codex":0.00012385627,"about_ca_system_score_gemma":0.000071098846,"threshold_uncertainty_score":0.46919745},"labels":[],"label_agreement":null},{"id":"W3007567173","doi":"10.1109/ssci44817.2019.9002803","title":"Learning of Multivariate Beta Mixture Models via Entropy-based component splitting","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Inference; Multivariate statistics; Principle of maximum entropy; Bayesian inference; Entropy (arrow of time); Artificial intelligence; Mixture model; Machine learning; Data modeling; Flexibility (engineering); Pattern recognition (psychology); Bayesian probability; Data mining; Algorithm; Mathematics; Statistics","score_opus":0.01458401807251919,"score_gpt":0.25032897062363535,"score_spread":0.23574495255111616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007567173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016168302,0.000059534064,0.9782125,0.00034785774,0.00023092687,0.00024237226,7.819114e-7,0.0001458977,0.004591863],"genre_scores_gemma":[0.51138526,0.0000011189347,0.48802954,0.00015887346,0.000017887583,0.0000024705253,0.0000019767597,0.00000872723,0.0003941601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982573,0.00026072064,0.0003551982,0.00047275497,0.00031454203,0.00033953],"domain_scores_gemma":[0.9987924,0.00020140395,0.00020055306,0.00058931235,0.00011125067,0.00010504122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068996736,0.00019216246,0.0003469353,0.000103162834,0.00006835915,0.000058797774,0.0006592139,0.00010555495,0.000046433797],"category_scores_gemma":[0.000013416495,0.00015541633,0.00014933696,0.0002256008,0.000024323255,0.00032042153,0.00021788597,0.00028066704,0.000027834734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017648328,0.00010743146,0.00045401504,0.00007711516,0.000035733512,0.0000051192146,0.00079004647,0.02587914,0.11503074,0.8105953,0.000031556705,0.046976168],"study_design_scores_gemma":[0.00057075074,0.00008822211,0.000185793,0.000042996966,0.000007776902,0.0000027929939,0.0000064633773,0.9570187,0.025322104,0.016245566,0.00032027898,0.00018860353],"about_ca_topic_score_codex":0.00008848609,"about_ca_topic_score_gemma":8.131184e-7,"teacher_disagreement_score":0.9311395,"about_ca_system_score_codex":0.000024724224,"about_ca_system_score_gemma":0.000051407296,"threshold_uncertainty_score":0.6337694},"labels":[],"label_agreement":null},{"id":"W3008182123","doi":"10.1109/ssci44817.2019.9002852","title":"Variational Inference of Finite Generalized Gaussian Mixture Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Expectation–maximization algorithm; Mixture model; Computer science; Gaussian; Inference; Estimator; Artificial intelligence; Posterior probability; Algorithm; Prior probability; Image segmentation; Generative model; Pattern recognition (psychology); Mathematical optimization; Image (mathematics); Mathematics; Maximum likelihood; Generative grammar; Bayesian probability; Statistics","score_opus":0.022571593057783987,"score_gpt":0.2702057833013048,"score_spread":0.2476341902435208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008182123","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001016511,0.00005036214,0.9567297,0.00061138655,0.00022977138,0.00012659586,0.0000039812194,0.000058395904,0.041173313],"genre_scores_gemma":[0.33213454,0.000008498872,0.6651655,0.0004924337,0.000023539922,0.000003959044,0.0000026247205,0.000004338313,0.0021645394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989169,0.0000983565,0.00023718599,0.00030541598,0.00025754631,0.00018459768],"domain_scores_gemma":[0.9990079,0.00016176871,0.0000974945,0.0005529306,0.00010748566,0.000072462404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030096457,0.0001194182,0.00020731926,0.000084961255,0.000026916481,0.000048450762,0.00061776274,0.000092933915,0.00022369288],"category_scores_gemma":[0.00002289326,0.00009220325,0.00007632029,0.00026011548,0.00001651103,0.00048742007,0.00015434768,0.00010150654,0.000037517468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034626266,0.000023515877,0.00009900225,0.000009925634,0.000010854001,6.9783977e-7,0.0002254797,0.0026284119,0.001479324,0.9877314,0.00020745095,0.0075804903],"study_design_scores_gemma":[0.00024477293,0.000025505735,0.00024700016,0.000008828531,0.0000024770684,0.0000016391115,9.878268e-7,0.6075559,0.0011112397,0.39039218,0.00030882194,0.000100654164],"about_ca_topic_score_codex":0.000032255353,"about_ca_topic_score_gemma":0.0000028498657,"teacher_disagreement_score":0.6049275,"about_ca_system_score_codex":0.000010475523,"about_ca_system_score_gemma":0.00010991828,"threshold_uncertainty_score":0.3759939},"labels":[],"label_agreement":null},{"id":"W3008477519","doi":"10.1080/01621459.2021.1987250","title":"Model-Assisted Estimation Through Random Forests in Finite Population Sampling","year":2021,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Variance (accounting); Statistics; Random forest; Estimation; Point estimation; Computer science; Random effects model; Population; Sampling (signal processing); Simple random sample; Small area estimation; Calibration; Sampling design; Sample (material); Econometrics; Random variable; Confidence interval; Mathematics; Machine learning; Engineering","score_opus":0.0405564620954532,"score_gpt":0.3468353973952853,"score_spread":0.3062789352998321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008477519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031724077,0.00006207192,0.9655226,0.0017882726,0.0006349235,0.00017667685,0.000025660722,0.000015795653,0.000049928014],"genre_scores_gemma":[0.46863583,0.000028789887,0.53103113,0.00020316854,0.000060709117,0.000004255898,0.000012902417,0.000008505063,0.00001469242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659777,0.0010108593,0.001006652,0.00028942758,0.0008373059,0.00025801203],"domain_scores_gemma":[0.9942785,0.0016339293,0.0032741923,0.00036837166,0.00037943636,0.00006557548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017730356,0.00020482719,0.0007554308,0.00012387891,0.00009041172,0.0003134173,0.00064111396,0.00014666714,0.0000022726924],"category_scores_gemma":[0.003574891,0.0001566992,0.000244966,0.00047526814,0.000033034306,0.0003906409,0.00037510289,0.00096631795,6.037349e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012232657,0.00020956242,0.016345678,0.00008037684,0.00018246366,0.000023265191,0.0015364612,0.7238056,0.00010155814,0.01900444,0.00045069167,0.23813757],"study_design_scores_gemma":[0.00037312883,0.00002481078,0.15208063,0.00015975587,0.000053958873,0.000006668457,0.000007348732,0.6276478,0.000010282367,0.21951577,0.0000039589454,0.00011585352],"about_ca_topic_score_codex":0.00025650096,"about_ca_topic_score_gemma":0.00014176042,"teacher_disagreement_score":0.43691173,"about_ca_system_score_codex":0.0009807729,"about_ca_system_score_gemma":0.0003249598,"threshold_uncertainty_score":0.6390008},"labels":[],"label_agreement":null},{"id":"W3008588871","doi":"10.1109/ssci44817.2019.9002954","title":"Variational Inference of Finite Asymmetric Gaussian Mixture Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Inference; Gaussian; Computer science; Artificial intelligence; Bayes' theorem; Gaussian process; Machine learning; Homogeneous; Algorithm; Pattern recognition (psychology); Mathematics; Bayesian probability","score_opus":0.019416951341944332,"score_gpt":0.26350408338862086,"score_spread":0.24408713204667654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008588871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023445916,0.000065578526,0.89418036,0.00041000397,0.0002248782,0.00011648513,0.000003350947,0.00005297644,0.104711935],"genre_scores_gemma":[0.45934924,0.0000070595415,0.53896797,0.00029023862,0.000017746435,0.0000025620168,0.0000014838953,0.000003687598,0.0013600083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988398,0.00008360764,0.0002422219,0.00032290583,0.00031288026,0.00019857925],"domain_scores_gemma":[0.9987794,0.00034582,0.00010731757,0.000563079,0.0001255446,0.00007880116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037938732,0.00012100097,0.00020244205,0.0002224034,0.000027170592,0.000052442927,0.00069911545,0.000100189674,0.00010682992],"category_scores_gemma":[0.000056974917,0.00009462951,0.00007513771,0.0008066281,0.000015503372,0.0005742365,0.0001759808,0.00013104017,0.00005958742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001970573,0.00003148224,0.00022359962,0.000012061979,0.0000098240625,7.23209e-7,0.00014238953,0.0012385899,0.0001935659,0.9650142,0.0001652497,0.032966297],"study_design_scores_gemma":[0.00018574783,0.000045255314,0.0010396953,0.000011009344,0.0000029755038,0.000002134817,0.0000016370392,0.62223876,0.000703409,0.3753839,0.00026814753,0.0001172934],"about_ca_topic_score_codex":0.000024654646,"about_ca_topic_score_gemma":0.0000016542083,"teacher_disagreement_score":0.6210002,"about_ca_system_score_codex":0.000013701407,"about_ca_system_score_gemma":0.000116510935,"threshold_uncertainty_score":0.38588795},"labels":[],"label_agreement":null},{"id":"W3009489148","doi":"10.2139/ssrn.3547890","title":"A Counterexample to the Central Limit Theorem for Pairwise Independent Random Variables Having a Common Absolutely Continuous Arbitrary Margin","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kensington Health","funders":"","keywords":"Central limit theorem; Mathematics; Independent and identically distributed random variables; Pairwise independence; Random variable; Asymptotic distribution; Sequence (biology); Gaussian; Limit (mathematics); Independence (probability theory); Distribution (mathematics); Combinatorics; Infinity; Pairwise comparison; Discrete mathematics; Statistics; Mathematical analysis; Sum of normally distributed random variables; Estimator","score_opus":0.016921970349909672,"score_gpt":0.24249990851545378,"score_spread":0.2255779381655441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009489148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064982534,0.0017503307,0.97503,0.015204083,0.0003513472,0.0007134873,0.00001063887,0.00008266107,0.0003591994],"genre_scores_gemma":[0.8960442,0.00042268046,0.09567645,0.0066618673,0.00085390644,0.000057525474,0.0000034398984,0.00004430299,0.00023563571],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957812,0.0004123144,0.000456459,0.00044812006,0.000387431,0.002514502],"domain_scores_gemma":[0.99858785,0.00039484477,0.00021235662,0.0003888239,0.00010215913,0.00031398522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037824414,0.0002703171,0.00041879193,0.00006570144,0.0004358574,0.00047120152,0.0016657704,0.00009771918,0.000010949027],"category_scores_gemma":[0.00015484254,0.00018580178,0.0002698169,0.00027330682,0.0000337793,0.0003396352,0.0002199963,0.0014861055,0.000008345422],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055323826,0.000076232354,0.00014615699,0.000015277195,0.0002078657,0.000018619106,0.003151951,0.00012504787,0.00065561046,0.8675242,0.0019151195,0.12561065],"study_design_scores_gemma":[0.0047735437,0.0012213631,0.0003413202,0.00007923567,0.00010678295,0.00078479486,0.00064129074,0.05452003,0.00042178395,0.91327417,0.023252195,0.0005834865],"about_ca_topic_score_codex":0.00008525819,"about_ca_topic_score_gemma":0.0003621571,"teacher_disagreement_score":0.8895459,"about_ca_system_score_codex":0.00031907545,"about_ca_system_score_gemma":0.0013028026,"threshold_uncertainty_score":0.7576777},"labels":[],"label_agreement":null},{"id":"W3012523934","doi":"10.1049/iet-ipr.2019.1029","title":"Background subtraction using infinite asymmetric Gaussian mixture models with simultaneous feature selection","year":2020,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Background subtraction; Subtraction; Pattern recognition (psychology); Gaussian; Feature selection; Mixture model; Computer science; Selection (genetic algorithm); Artificial intelligence; Feature (linguistics); Gaussian process; Mathematics; Algorithm; Physics; Arithmetic","score_opus":0.03128967769602271,"score_gpt":0.283177917989747,"score_spread":0.2518882402937243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012523934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037843364,0.0005952427,0.9916598,0.0016137245,0.000099321056,0.00022636568,0.0000026417165,0.00038867,0.0016299031],"genre_scores_gemma":[0.4503459,0.000008994457,0.54870945,0.0006532128,0.00019206358,0.000003932595,0.0000028168183,0.00002862418,0.00005497576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978915,0.00013637035,0.000255236,0.0007788553,0.00045349798,0.00048455573],"domain_scores_gemma":[0.998795,0.00009790484,0.0002689772,0.0002513394,0.00033343106,0.0002533798],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00025713383,0.0003459577,0.00031704863,0.00021106123,0.0004177065,0.001051778,0.00046037932,0.00021367795,0.0000041575663],"category_scores_gemma":[0.00006711687,0.00028840898,0.00007311204,0.0025538686,0.00005384099,0.0031494384,0.00009363026,0.0006848764,0.000007019154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029264097,0.00021378121,0.00018958768,0.0008189895,0.000099067656,0.00033844632,0.005345499,0.046870824,0.07372264,0.003633963,0.0006075846,0.867867],"study_design_scores_gemma":[0.0003846217,0.00013289833,0.000033449734,0.00009794292,0.000043272157,0.0003224454,0.00005211276,0.9894092,0.005466289,0.003269449,0.0003769258,0.00041139108],"about_ca_topic_score_codex":0.000019017745,"about_ca_topic_score_gemma":0.0000050803687,"teacher_disagreement_score":0.9425384,"about_ca_system_score_codex":0.00009989721,"about_ca_system_score_gemma":0.00026154122,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W3013592304","doi":"10.1371/journal.pcbi.1008799","title":"DCMD: Distance-based classification using mixture distributions on microbiome data","year":2021,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Crohn's and Colitis Canada; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Microbiome; Computer science; Statistics; Computational biology; Biology; Mathematics; Bioinformatics","score_opus":0.12338692168427283,"score_gpt":0.3445565658723923,"score_spread":0.22116964418811946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013592304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030053896,0.0001753937,0.9911531,0.0043113627,0.00029247435,0.000104708844,0.00065634854,0.000090674934,0.000210524],"genre_scores_gemma":[0.3543355,0.0000027614142,0.6417944,0.00084742776,0.000082187806,0.0000054358766,0.0029079064,0.0000065242525,0.000017880355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983514,0.00031875962,0.0002562589,0.00070975383,0.00013004846,0.00023376732],"domain_scores_gemma":[0.9983608,0.00039378443,0.00011948668,0.00080723997,0.00024189781,0.00007677553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019147388,0.00014985535,0.00018886063,0.00008154491,0.0002074695,0.00008644212,0.0007702756,0.00012256639,0.000019640054],"category_scores_gemma":[0.000116249525,0.00013974786,0.000051965126,0.00047268168,0.00009154148,0.00016107259,0.00023309594,0.00016714941,0.00002526324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012182209,0.00036239022,0.00033772175,0.000019551582,0.00005555194,0.000017012597,0.000032588847,0.001647665,0.052278884,0.93213403,0.0012124416,0.011889957],"study_design_scores_gemma":[0.00032544255,0.00003736194,0.0014848824,0.000031422154,0.000016854978,0.000023483963,0.000002203961,0.8834233,0.0033893988,0.10588612,0.0051673986,0.00021210224],"about_ca_topic_score_codex":0.000002543152,"about_ca_topic_score_gemma":0.0000026720309,"teacher_disagreement_score":0.8817757,"about_ca_system_score_codex":0.00008118235,"about_ca_system_score_gemma":0.00035505215,"threshold_uncertainty_score":0.56987524},"labels":[],"label_agreement":null},{"id":"W3014069359","doi":"10.1016/j.jmaa.2021.124982","title":"A counterexample to the existence of a general central limit theorem for pairwise independent identically distributed random variables","year":2021,"lang":"en","type":"article","venue":"Journal of Mathematical Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Fonds de recherche du Québec – Nature et technologies; Australian Research Council; University of New South Wales","keywords":"Mathematics; Pairwise independence; Independent and identically distributed random variables; Central limit theorem; Random variable; Sequence (biology); Independence (probability theory); Asymptotic distribution; Counterexample; Pairwise comparison; Limit (mathematics); Gaussian; Distribution (mathematics); Discrete mathematics; Combinatorics; Sum of normally distributed random variables; Statistics; Mathematical analysis; Estimator","score_opus":0.01910649304901969,"score_gpt":0.2802859622462338,"score_spread":0.26117946919721413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014069359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032599731,0.00019358254,0.99344003,0.0027629628,0.000014406639,0.00021080842,0.000033697965,0.0000046638124,0.000079892176],"genre_scores_gemma":[0.25608248,0.00006134131,0.74341655,0.00021423183,0.00008657588,0.000052249514,0.0000041992216,0.0000042595184,0.00007808806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866027,0.00011198433,0.0006049396,0.00017439346,0.00028483022,0.00016356277],"domain_scores_gemma":[0.9980984,0.0006600752,0.0002729248,0.0003632137,0.0004490321,0.00015637286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011580392,0.00009169514,0.00042754304,0.000072720104,0.00010324001,0.00014368257,0.00046764425,0.00003847146,0.000020560328],"category_scores_gemma":[0.00020842475,0.000053518033,0.00032167384,0.0006865744,0.000046983212,0.000087845634,0.00011414344,0.00008964707,6.996822e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019787538,0.00023593848,0.000049602237,0.00004061369,0.0004537259,0.0000022450215,0.00032173347,0.00021742536,0.0014677048,0.98621446,0.00017005444,0.010806728],"study_design_scores_gemma":[0.00072751276,0.0000728853,0.00113347,0.000050474373,0.001308674,0.000079445184,0.00010847148,0.13222115,0.0019543294,0.85993814,0.0022682925,0.0001371854],"about_ca_topic_score_codex":0.0000029118373,"about_ca_topic_score_gemma":0.000007973287,"teacher_disagreement_score":0.25282252,"about_ca_system_score_codex":0.000015864682,"about_ca_system_score_gemma":0.00007624762,"threshold_uncertainty_score":0.2182402},"labels":[],"label_agreement":null},{"id":"W3016225341","doi":"10.1002/ima.22421","title":"Online variational learning of finite inverted <scp>Beta‐Liouville</scp> mixture model for biomedical analysis","year":2020,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Segmentation; Artificial intelligence; Cluster analysis; Pattern recognition (psychology); Medical imaging; Image segmentation; Mixture model; Noise (video); Image (mathematics)","score_opus":0.015171097039586846,"score_gpt":0.27515628819890076,"score_spread":0.2599851911593139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016225341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031205092,0.0008716359,0.98444104,0.011059504,0.00032556252,0.00006772913,0.00003862728,0.000038915387,0.00003647163],"genre_scores_gemma":[0.6989481,0.00004018489,0.30056626,0.00023972974,0.00015104999,0.0000024008846,0.000011225301,0.000006866617,0.000034204033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985227,0.00006288758,0.0006568687,0.00022091095,0.00039357864,0.00014303668],"domain_scores_gemma":[0.9978172,0.00029984332,0.00070761517,0.000109523084,0.0009685144,0.00009727973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049737864,0.00012187313,0.00042033952,0.00094047294,0.000044218476,0.00007247461,0.00077473035,0.000117668984,9.716439e-7],"category_scores_gemma":[0.0006821355,0.00010104432,0.00015046408,0.00071323727,0.000091922055,0.00022964372,0.00016206632,0.00031367654,2.6795203e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035823534,0.00036066837,0.011009396,0.00012209672,0.0043701134,0.00013734307,0.002079308,0.034604188,0.013349624,0.860533,0.0028665354,0.07053192],"study_design_scores_gemma":[0.00060579646,0.00007993021,0.00011208038,0.00004974836,0.000104364284,0.0001206873,0.00006220828,0.98531383,0.0001596805,0.011412376,0.0019331264,0.000046141162],"about_ca_topic_score_codex":0.0000087510225,"about_ca_topic_score_gemma":8.4495736e-7,"teacher_disagreement_score":0.9507097,"about_ca_system_score_codex":0.000025213149,"about_ca_system_score_gemma":0.00012513936,"threshold_uncertainty_score":0.4120468},"labels":[],"label_agreement":null},{"id":"W3024523094","doi":"10.1007/978-3-030-44246-0_3","title":"Stratified Sampling and Cluster Sampling","year":2020,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster sampling; Stratified sampling; Sampling (signal processing); Stratification (seeds); Cluster analysis; Sampling design; Selection (genetic algorithm); Cluster (spacecraft); Statistics; Computer science; Data mining; Mathematics; Artificial intelligence; Biology; Population; Sociology","score_opus":0.055701035689639605,"score_gpt":0.302941380611329,"score_spread":0.24724034492168942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024523094","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.1927998e-7,0.0011248043,0.8879405,0.0004050619,0.00041714782,0.00026975494,0.0002747688,0.000084819825,0.10948269],"genre_scores_gemma":[0.000034912762,0.0012225342,0.9461137,0.0013283638,0.00018371068,0.000008430517,0.00004668739,0.00006095088,0.051000714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979701,0.000049403217,0.00060743344,0.0007508425,0.00030022117,0.0003219998],"domain_scores_gemma":[0.9984473,0.0004655361,0.0002495033,0.00056690676,0.00009636053,0.0001743981],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029983878,0.00044702672,0.0005963684,0.00012288705,0.000116580384,0.0003193155,0.00053542835,0.0003283815,0.00004956756],"category_scores_gemma":[0.00009535778,0.00047263238,0.000051221457,0.00004480598,0.0001813058,0.00044354936,0.00049583457,0.00070283824,0.000013119616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014349703,0.000003562609,0.000002218658,0.00013054992,0.000021700322,0.0000612004,0.0005260333,0.0000138021705,0.000013537841,0.9414834,0.0007699822,0.05695969],"study_design_scores_gemma":[0.00020415348,0.00009089987,0.000014119093,0.00017975419,0.000023831999,0.00003515137,0.0000064501664,0.0039849044,0.000014604109,0.77255154,0.22239244,0.00050217356],"about_ca_topic_score_codex":0.00000897706,"about_ca_topic_score_gemma":0.00007365608,"teacher_disagreement_score":0.22162245,"about_ca_system_score_codex":0.00006132105,"about_ca_system_score_gemma":0.0001640612,"threshold_uncertainty_score":0.99977255},"labels":[],"label_agreement":null},{"id":"W3033347958","doi":"10.3934/cpaa.2020187","title":"A numerical method to compute Fisher information for a special case of heterogeneous negative binomial regression","year":2020,"lang":"en","type":"article","venue":"Communications on Pure &amp Applied Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Negative binomial distribution; Fisher information; Statistics; Regression; Regression analysis; Binomial (polynomial); Mathematics; Applied mathematics; Computer science; Binomial distribution; Count data; Econometrics; Poisson distribution","score_opus":0.04704634275284272,"score_gpt":0.33960537369092814,"score_spread":0.29255903093808544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033347958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003354433,0.000018828443,0.99144936,0.0056625647,0.000035004745,0.00055604737,0.00004996894,0.00007026729,0.0018225425],"genre_scores_gemma":[0.22925416,0.0000055709083,0.7688203,0.0016356857,0.00009387387,0.00011933336,0.000054508346,0.000007748494,0.000008838847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839985,0.00030324268,0.0005575918,0.00034126287,0.00019963755,0.00019843795],"domain_scores_gemma":[0.9968123,0.0005860825,0.00033545398,0.0018284465,0.00021880957,0.00021895095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047316085,0.00020119442,0.0005275954,0.00035596464,0.00027930847,0.00012352418,0.0016146108,0.00010899123,0.000016384172],"category_scores_gemma":[0.00010997279,0.00017624121,0.00032691102,0.0022499955,0.000046445894,0.00019406888,0.0005149483,0.00021234839,0.000021416621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022659653,0.00024849304,0.000012333006,0.000039421535,0.00088661816,0.0000050613426,0.012963712,0.024556328,0.0005052119,0.16683957,0.005754924,0.7879617],"study_design_scores_gemma":[0.00091601204,0.00022268633,0.000034163968,0.00001909576,0.00056251365,0.000026308886,0.00010944186,0.9382549,0.0026836349,0.013064739,0.043630365,0.00047613616],"about_ca_topic_score_codex":0.00003046402,"about_ca_topic_score_gemma":0.00003239704,"teacher_disagreement_score":0.91369855,"about_ca_system_score_codex":0.00005053751,"about_ca_system_score_gemma":0.000056160785,"threshold_uncertainty_score":0.7186908},"labels":[],"label_agreement":null},{"id":"W3033447626","doi":"","title":"Exploiter l'approche hiérarchique bayésienne pour la modélisation statistique de structures spatiales. Application en écologie des populations","year":2008,"lang":"fr","type":"preprint","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Geography; Philosophy","score_opus":0.09574073366549075,"score_gpt":0.33770154231935756,"score_spread":0.24196080865386682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033447626","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013748463,0.00030429242,0.97539836,0.003273992,0.00040619556,0.0013411032,0.00007751821,0.00035612838,0.00509392],"genre_scores_gemma":[0.28380954,0.0006677766,0.7127442,0.00038467217,0.00036937586,0.0004667865,0.00015591738,0.000051758463,0.0013499684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993871,0.0025648195,0.0008966882,0.0014680421,0.00040049545,0.0007989573],"domain_scores_gemma":[0.99642795,0.0010001301,0.00051176874,0.0012998865,0.0003888329,0.00037145242],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015773703,0.00071131164,0.0006344668,0.0002900677,0.00045241273,0.00038320353,0.001385218,0.0010777017,0.00006985803],"category_scores_gemma":[0.0005131861,0.00068650587,0.00025113404,0.000373683,0.00049268943,0.0006441985,0.00094159046,0.0012332577,0.000030475636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000140578595,0.00011812982,0.0009524255,0.000129464,0.000037642792,0.000018226747,0.0062423167,0.022256074,0.0018303,0.6636434,0.00049771986,0.30426022],"study_design_scores_gemma":[0.00020156802,0.0000320363,0.045975193,0.000059022954,0.000034674424,0.000112713555,0.000030343948,0.37746495,0.0015530937,0.573082,0.0010086515,0.00044578392],"about_ca_topic_score_codex":0.002777696,"about_ca_topic_score_gemma":0.001044281,"teacher_disagreement_score":0.35520887,"about_ca_system_score_codex":0.00069541694,"about_ca_system_score_gemma":0.001345031,"threshold_uncertainty_score":0.9995586},"labels":[],"label_agreement":null},{"id":"W3033672304","doi":"10.1007/s42952-020-00072-7","title":"Kullback–Leibler divergence for Bayesian nonparametric model checking","year":2020,"lang":"en","type":"article","venue":"Journal of the Korean Statistical Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Dirichlet process; Kullback–Leibler divergence; Dirichlet distribution; Divergence (linguistics); Mathematics; Nonparametric statistics; Applied mathematics; Bayesian probability; Hierarchical Dirichlet process; Mathematical optimization; Statistics; Mathematical analysis","score_opus":0.040792197824806656,"score_gpt":0.29404656082987485,"score_spread":0.2532543630050682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033672304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033120703,0.000102804916,0.9926813,0.006124352,0.00030545637,0.00015752735,0.000035312547,0.000019223047,0.00024277385],"genre_scores_gemma":[0.13869625,0.000032787513,0.85803604,0.0029459575,0.0002158681,0.0000022776248,4.3140508e-7,0.00001239988,0.000057985177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832666,0.00010741944,0.00048906036,0.00024985362,0.0004998434,0.00032715738],"domain_scores_gemma":[0.99831647,0.0005098357,0.0003520985,0.00026966707,0.00024061046,0.00031130365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084967935,0.0001621788,0.0003341718,0.000021510765,0.00021594607,0.00013235687,0.0013431481,0.000089261426,0.000013248929],"category_scores_gemma":[0.00064370653,0.00010180877,0.00048573784,0.00052605744,0.00009521164,0.00026976687,0.00029624795,0.00042016184,0.0000022160907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083007624,0.00018591507,0.00054535107,0.00017636931,0.00027590533,0.000016619046,0.0049478975,0.0058731087,0.0020022143,0.67264694,0.14537305,0.16787365],"study_design_scores_gemma":[0.00038902927,0.00010982064,0.0003457663,0.000020846031,0.0000520117,0.00001641502,0.000018457582,0.84929436,0.00049593276,0.14830351,0.0008191541,0.00013467956],"about_ca_topic_score_codex":0.000002358535,"about_ca_topic_score_gemma":2.906927e-7,"teacher_disagreement_score":0.8434213,"about_ca_system_score_codex":0.00006432422,"about_ca_system_score_gemma":0.0001742806,"threshold_uncertainty_score":0.4151641},"labels":[],"label_agreement":null},{"id":"W3034218606","doi":"10.6000/1929-6029.2020.09.05","title":"Inference Procedures on the Ratio of Modified Generalized Poisson Distribution Means: Applications to RNA_SEQ Data","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Negative binomial distribution; Count data; Poisson distribution; Statistics; Mathematics; Estimator; Statistical inference; Binomial distribution; Sample size determination; Inference; Overdispersion; Confidence interval; Binomial proportion confidence interval; Poisson regression; Variance (accounting); Beta-binomial distribution; Quasi-likelihood; Population; Computer science; Artificial intelligence","score_opus":0.22167514907988428,"score_gpt":0.4941758465509761,"score_spread":0.2725006974710918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034218606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000648873,0.000054697706,0.9485189,0.05008161,0.00010956537,0.00019545239,0.00021249233,0.0000039263714,0.00017450996],"genre_scores_gemma":[0.7125299,0.00038493815,0.28511462,0.0015616887,0.00032140262,0.000021289175,0.00004357348,0.0000061069964,0.000016493617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956262,0.0004748659,0.0005898016,0.00022285078,0.0029076627,0.00017860095],"domain_scores_gemma":[0.9952887,0.0025467412,0.00018121628,0.00033891795,0.0013817956,0.00026261996],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004156306,0.000074864605,0.00017045972,0.00014108223,0.000051945124,0.00010561706,0.004008317,0.00005733576,0.000050106482],"category_scores_gemma":[0.020567384,0.000050006867,0.00002424103,0.0004729312,0.00012788655,0.00015776533,0.00060866866,0.0006752298,0.0000062785375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088334804,0.00010091224,0.000029864197,0.000014512938,0.000027397793,0.000044338485,0.00044491029,0.00024021887,0.0004373912,0.8739377,0.011328889,0.113305524],"study_design_scores_gemma":[0.0009545455,0.00042650363,0.00090083684,0.00034808333,0.0000067670603,0.000026806845,0.00006967864,0.6397792,0.0017604887,0.34480065,0.0107879415,0.00013846488],"about_ca_topic_score_codex":0.000036942492,"about_ca_topic_score_gemma":0.000024261302,"teacher_disagreement_score":0.71188104,"about_ca_system_score_codex":0.00007847963,"about_ca_system_score_gemma":0.000846771,"threshold_uncertainty_score":0.9876828},"labels":[],"label_agreement":null},{"id":"W3037124698","doi":"","title":"MCMC-Based Learning of Finite Bivariate Beta Mixture Models.","year":2020,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Bivariate analysis; BETA (programming language); Markov chain Monte Carlo; Beta distribution; Computer science; Mathematics; Statistics; Artificial intelligence; Monte Carlo method","score_opus":0.10279513536465062,"score_gpt":0.35046767438934184,"score_spread":0.24767253902469122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037124698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009802873,0.00040367988,0.96050096,0.03639432,0.00012119873,0.0002858982,0.0000070438746,0.00012639398,0.0011802005],"genre_scores_gemma":[0.5820063,0.00019061437,0.41241112,0.004353969,0.0005144185,0.00004078044,0.000006401128,0.000037650843,0.00043872878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996335,0.00102016,0.0002984525,0.00054096483,0.0011303724,0.00067502935],"domain_scores_gemma":[0.9973849,0.0009905634,0.00009374719,0.0008181337,0.00046354288,0.00024913118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041246056,0.00019122867,0.0003034888,0.000046700257,0.0005190628,0.00019243245,0.0021877943,0.0001563246,0.00002639788],"category_scores_gemma":[0.0002584152,0.00013086948,0.00034620726,0.0015417841,0.0002761005,0.00038566478,0.00080949214,0.0017172464,0.000026062564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016010064,0.0001651532,0.00016570915,0.00052669254,0.00035931254,0.000030282969,0.052030534,0.088170744,0.025464548,0.689955,0.0765332,0.06643874],"study_design_scores_gemma":[0.0003826811,0.00017017627,0.00003677427,0.000029962095,0.000009156703,9.366754e-7,0.000065639804,0.9422402,0.0054782997,0.04214627,0.009286891,0.00015305851],"about_ca_topic_score_codex":0.0000638055,"about_ca_topic_score_gemma":7.689359e-7,"teacher_disagreement_score":0.8540694,"about_ca_system_score_codex":0.000041169667,"about_ca_system_score_gemma":0.0003693648,"threshold_uncertainty_score":0.74606764},"labels":[],"label_agreement":null},{"id":"W3037668816","doi":"","title":"Asynchronous Gibbs Sampling.","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Gibbs sampling; Markov chain Monte Carlo; Asynchronous communication; Computer science; Markov chain; Algorithm; Bayesian probability; Sampling (signal processing); Set (abstract data type); Theoretical computer science; Artificial intelligence; Machine learning","score_opus":0.2058612348148112,"score_gpt":0.3747995126403912,"score_spread":0.16893827782558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037668816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010698532,0.00002166932,0.98039263,0.009260232,0.00044871104,0.000088453366,0.00007223639,0.00007083626,0.009538243],"genre_scores_gemma":[0.4093853,0.000112634945,0.58817303,0.0021176639,0.00015091944,0.0000054771112,0.000009479066,0.0000063422626,0.00003913379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987229,0.00006596562,0.0003114767,0.0004138093,0.00029430076,0.00019153961],"domain_scores_gemma":[0.9991125,0.00022573222,0.000088295834,0.0001707348,0.00021956986,0.00018320854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018978187,0.0001528423,0.00015528704,0.000060496375,0.00009612187,0.00036613405,0.00061876874,0.000057767422,0.00021180774],"category_scores_gemma":[0.0003137346,0.00014383778,0.000029777935,0.00011759749,0.000094860196,0.0001806057,0.00013724455,0.00019158146,0.00016791362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016183352,0.000018496696,0.0000044605954,0.0000028994089,0.000007831053,0.000011104125,0.00040760805,0.000023722312,0.00035547797,0.60322523,0.00013815373,0.39578885],"study_design_scores_gemma":[0.000019093633,0.00016233786,0.000031695294,0.000013166753,0.00000326271,0.0000068116587,0.000055260254,0.4031604,0.0015515054,0.5937707,0.0010780765,0.00014769056],"about_ca_topic_score_codex":0.000014683814,"about_ca_topic_score_gemma":0.000009301994,"teacher_disagreement_score":0.40927833,"about_ca_system_score_codex":0.00001878724,"about_ca_system_score_gemma":0.0000892508,"threshold_uncertainty_score":0.5865534},"labels":[],"label_agreement":null},{"id":"W3041541684","doi":"10.29252/jirss.19.1.1","title":"Accurate Inference for the Mean of the Poisson-Exponential Distribution","year":2020,"lang":"en","type":"article","venue":"Journal of the Iranian Statistical Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Thompson Rivers University","funders":"","keywords":"Mathematics; Poisson distribution; Statistics; Exponential distribution; Inference; Exponential family; Poisson regression; Exponential function; Applied mathematics; Artificial intelligence; Computer science; Mathematical analysis; Demography","score_opus":0.03465199919821783,"score_gpt":0.30296110692370304,"score_spread":0.2683091077254852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041541684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010995963,0.00006727665,0.9736501,0.024376601,0.00047132527,0.000177342,0.00013563181,0.0000055223104,0.000016584667],"genre_scores_gemma":[0.798783,0.000020179235,0.19965534,0.0013080509,0.00020993486,0.0000017482146,5.9459313e-7,0.000005273888,0.000015850728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865174,0.00021590957,0.00040630065,0.00012355125,0.00041966292,0.00018285212],"domain_scores_gemma":[0.99806374,0.0009251546,0.0004336813,0.0002751527,0.00020667595,0.0000955841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008383295,0.000102853875,0.00020334103,0.0000027772076,0.00027100169,0.00009060127,0.0014431655,0.00004704623,0.000009236782],"category_scores_gemma":[0.0006601343,0.00004337727,0.0004110002,0.00022228382,0.000173823,0.00013706474,0.0002501444,0.00036081,6.3030615e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016731968,0.000155942,0.00030673816,0.00014157777,0.0003879459,0.0000036154652,0.009960095,0.0004923589,0.007330541,0.8337461,0.06367593,0.08363184],"study_design_scores_gemma":[0.0024415615,0.00047595616,0.041224133,0.00016672543,0.00047709997,0.000062317835,0.0003518241,0.65477854,0.0074219857,0.27389398,0.01830495,0.00040090908],"about_ca_topic_score_codex":0.00000865631,"about_ca_topic_score_gemma":0.0000020909079,"teacher_disagreement_score":0.7976834,"about_ca_system_score_codex":0.000035199297,"about_ca_system_score_gemma":0.00014421946,"threshold_uncertainty_score":0.26817846},"labels":[],"label_agreement":null},{"id":"W3044696131","doi":"10.1007/s10796-020-10027-2","title":"Online Variational Learning of Dirichlet Process Mixtures of Scaled Dirichlet Distributions","year":2020,"lang":"en","type":"article","venue":"Information Systems Frontiers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Latent Dirichlet allocation; Dirichlet process; Dirichlet distribution; Artificial intelligence; Process (computing); Categorization; Machine learning; Class (philosophy); Data mining; Topic model; Hierarchical Dirichlet process; Pattern recognition (psychology); Mathematics","score_opus":0.01273554771810375,"score_gpt":0.2493567327782382,"score_spread":0.23662118506013444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044696131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001778912,0.0002087481,0.9955311,0.00066287495,0.00037835786,0.0002482921,0.00014075263,0.00008175611,0.000969219],"genre_scores_gemma":[0.81463355,0.000009444221,0.18494974,0.00013369232,0.000068104986,0.000016279648,0.00015780397,0.0000046161385,0.000026774238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838877,0.0001330154,0.0007465051,0.00013370541,0.00043878448,0.00015924763],"domain_scores_gemma":[0.9985349,0.000054429653,0.00065047824,0.00018989672,0.00046085918,0.00010942997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003799818,0.00012550045,0.0003224886,0.00012762846,0.00008052972,0.000069397465,0.00046578937,0.000090955145,0.0000030016542],"category_scores_gemma":[0.00026638494,0.00011144468,0.00008224329,0.00063064526,0.000044948825,0.0013505268,0.00006903093,0.00015263059,0.000004130171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016964658,0.0004143648,0.012389362,0.0032525575,0.00059173314,0.000003838542,0.04645591,0.066967286,0.00195689,0.73158973,0.051899884,0.08430882],"study_design_scores_gemma":[0.0008204787,0.00012766432,0.0023973398,0.000099636,0.000030130761,0.000008181477,0.0006258216,0.9751225,0.0013581301,0.001858574,0.017278839,0.00027268074],"about_ca_topic_score_codex":0.000018332885,"about_ca_topic_score_gemma":1.4866298e-7,"teacher_disagreement_score":0.90815526,"about_ca_system_score_codex":0.000028776005,"about_ca_system_score_gemma":0.00012736605,"threshold_uncertainty_score":0.45445824},"labels":[],"label_agreement":null},{"id":"W3045087557","doi":"10.1080/00949655.2020.1795174","title":"A comparison of preliminary test, Stein-type and penalty estimators in gamma regression model","year":2020,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Mathematics; Subspace topology; Statistics; Monte Carlo method; Regression; Extremum estimator; M-estimator","score_opus":0.0651926303864389,"score_gpt":0.3965991824984395,"score_spread":0.3314065521120006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045087557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09589408,0.0001462248,0.9034348,0.0003876345,0.00003056854,0.000073109724,0.0000023483308,0.0000066231655,0.000024567713],"genre_scores_gemma":[0.5609409,0.0000050528038,0.43898654,0.000052018822,0.000010852555,1.0927519e-7,0.0000010520631,0.0000024577364,9.774868e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988981,0.00011635335,0.000534824,0.00013690071,0.0002332467,0.00008060586],"domain_scores_gemma":[0.99839073,0.00088039937,0.0003203697,0.000044467273,0.00023238892,0.00013163422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003040254,0.00008593418,0.00028520168,0.00009573255,0.00003522314,0.000041117648,0.00007903327,0.00004911575,0.0000015474678],"category_scores_gemma":[0.00053198845,0.00006897042,0.000016378623,0.00020822315,0.000038635128,0.0002782942,0.00004900466,0.0001602221,2.0906802e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019700249,0.0000904013,0.0054380945,0.00009447766,0.0000056643153,0.000013853687,0.0020715573,0.837775,0.00031845894,0.01087818,0.000107190855,0.14301014],"study_design_scores_gemma":[0.00056368706,0.0006930366,0.015078642,0.00007337346,0.00001119049,0.0000062928343,0.000021521788,0.95769167,0.00006328417,0.025728593,0.0000037413536,0.00006496185],"about_ca_topic_score_codex":0.0000012509058,"about_ca_topic_score_gemma":2.61344e-7,"teacher_disagreement_score":0.46504685,"about_ca_system_score_codex":0.000012266575,"about_ca_system_score_gemma":0.000057937203,"threshold_uncertainty_score":0.28125322},"labels":[],"label_agreement":null},{"id":"W3045573207","doi":"10.1002/cjs.11562","title":"On‐line partitioning of the sample space in the regional adaptive algorithm","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Ergodicity; Recursion (computer science); Hyperplane; Algorithm; Partition (number theory); Computer science; Line (geometry); Mahalanobis distance; Space partitioning; Mathematics; Artificial intelligence; Statistics; Combinatorics; Geometry","score_opus":0.06338899942913834,"score_gpt":0.26021488762345313,"score_spread":0.1968258881943148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045573207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016304113,0.000090187554,0.98856044,0.010763275,0.00012904008,0.000046950205,0.00012420394,9.1258e-7,0.000121936246],"genre_scores_gemma":[0.17012022,0.000007288915,0.82678765,0.0029858998,0.000086669694,5.3158465e-7,7.238169e-7,0.0000035564958,0.0000074544228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992128,0.00016798193,0.00021534013,0.00007273687,0.00019444944,0.00013670028],"domain_scores_gemma":[0.9989103,0.0004742459,0.00017915235,0.00013007816,0.00013121979,0.0001749861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036633894,0.00005919928,0.00011485141,0.00004709721,0.00007695298,0.000038158265,0.0005492476,0.00002265068,0.000011144533],"category_scores_gemma":[0.00038280129,0.000036167792,0.000037488193,0.00025931234,0.00007683118,0.00006406205,0.00001301714,0.0002535475,7.43835e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041199087,0.0000075122007,0.00009703134,0.0000034061354,0.000010745368,0.00009314284,0.0037546754,0.0011892882,0.0000047641065,0.9425357,0.01603216,0.03626747],"study_design_scores_gemma":[0.00052213407,0.00062307063,0.0043303366,0.00013931091,0.000022902059,0.00012274373,0.00033854388,0.22160648,0.000117303636,0.7631929,0.008824083,0.00016021104],"about_ca_topic_score_codex":0.00093172817,"about_ca_topic_score_gemma":0.002877669,"teacher_disagreement_score":0.2204172,"about_ca_system_score_codex":0.000035575533,"about_ca_system_score_gemma":0.00071957515,"threshold_uncertainty_score":0.16058068},"labels":[],"label_agreement":null},{"id":"W3045859451","doi":"10.1002/sim.8662","title":"A bivariate autoregressive Poisson model and its application to asthma‐related emergency room visits","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Autoregressive model; Statistics; Poisson regression; Poisson distribution; Overdispersion; Estimator; Bayesian probability; Series (stratigraphy); Econometrics; Time series; Computer science; Mathematics; Count data; Medicine","score_opus":0.019389079551677096,"score_gpt":0.3185714517097249,"score_spread":0.29918237215804777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045859451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006849227,0.0004558893,0.9880719,0.009632043,0.00016747805,0.000335996,0.00003166839,0.000060762653,0.0005593321],"genre_scores_gemma":[0.3218775,0.000107283326,0.6765626,0.0011665572,0.00008523262,0.000026362488,0.000013367428,0.000014272592,0.0001467801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855506,0.00008800785,0.00037658788,0.00047819613,0.00027290656,0.0002292522],"domain_scores_gemma":[0.9991878,0.0000754785,0.00011192435,0.00022431707,0.000114018905,0.00028644162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037855632,0.00015867063,0.00027309087,0.00010200402,0.000053791555,0.000012682012,0.0003530858,0.000071913724,0.00001985545],"category_scores_gemma":[0.0004167179,0.00013377276,0.00001106935,0.00046785074,0.000010877597,0.0001017467,0.00015739142,0.0002071905,0.000016193002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014580841,0.000018239076,0.000038420025,0.000048075686,0.000010810324,0.000030588053,0.0068605663,0.0013166611,0.0040047723,0.8760555,0.0026285117,0.10897328],"study_design_scores_gemma":[0.00034364845,0.00014356173,0.0009584309,0.00003819198,0.0000073896567,0.000003087785,0.000008486368,0.7806776,0.0000589485,0.21742798,0.00021461825,0.00011804834],"about_ca_topic_score_codex":0.000023062878,"about_ca_topic_score_gemma":0.000013238434,"teacher_disagreement_score":0.77936095,"about_ca_system_score_codex":0.000024506911,"about_ca_system_score_gemma":0.00003910825,"threshold_uncertainty_score":0.54550946},"labels":[],"label_agreement":null},{"id":"W3048329011","doi":"10.1111/gean.12252","title":"Classification and Regression via Integer Optimization for Neighborhood Change","year":2020,"lang":"en","type":"article","venue":"Geographical Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome Canada; University of Toronto","funders":"","keywords":"Leverage (statistics); Computer science; Cluster analysis; Regression; Artificial intelligence; Machine learning; Term (time); Cluster (spacecraft); Data mining; Econometrics; Mathematics; Statistics","score_opus":0.0464197581316487,"score_gpt":0.2821685643216782,"score_spread":0.2357488061900295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048329011","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004342302,0.00021395732,0.9843096,0.01468989,0.00003118454,0.00016563416,0.0000035215328,0.000080874444,0.00007111988],"genre_scores_gemma":[0.55482143,0.00015007782,0.4435618,0.0013145168,0.000075591306,0.000047135087,0.00002097586,0.000004565919,0.000003889641],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989455,0.00008638967,0.00018773941,0.0004748708,0.00014656481,0.00015898688],"domain_scores_gemma":[0.9993112,0.00006609017,0.00009240121,0.00025700152,0.00010003115,0.00017324358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022781381,0.00011485596,0.0002275442,0.00023388746,0.00011160335,0.00009535434,0.00025232518,0.00010132185,0.000015277217],"category_scores_gemma":[0.000047923997,0.00008656489,0.00019995429,0.002103027,0.00003611831,0.00026707436,0.000090324465,0.000091644455,9.592803e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053963136,0.00012587303,0.027691219,0.00008473906,0.0006880364,0.0000031138336,0.001289223,0.00071928324,0.0005402188,0.21230564,0.00020453283,0.7562942],"study_design_scores_gemma":[0.00014949721,0.000055635013,0.010226072,0.000004371513,0.00026575633,5.482458e-7,0.000004452645,0.97915375,0.000019596846,0.009798216,0.00020811093,0.00011401497],"about_ca_topic_score_codex":0.000009825715,"about_ca_topic_score_gemma":0.0000039758647,"teacher_disagreement_score":0.97843444,"about_ca_system_score_codex":0.0000042840084,"about_ca_system_score_gemma":0.000005261952,"threshold_uncertainty_score":0.3530014},"labels":[],"label_agreement":null},{"id":"W3048555279","doi":"10.1002/9781118445112.stat07846","title":"Dimension Reduction in Clustering","year":2016,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Dimensionality reduction; Cluster analysis; Dimension (graph theory); Curse of dimensionality; Computer science; Variable (mathematics); Transformation (genetics); Reduction (mathematics); Clustering high-dimensional data; Data mining; Mathematics; Artificial intelligence; Combinatorics","score_opus":0.033440053368792674,"score_gpt":0.32605129101463054,"score_spread":0.29261123764583785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048555279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002930935,0.0005927784,0.9537359,0.000175119,0.001040523,0.00032526063,0.0017721736,0.00027067322,0.04208465],"genre_scores_gemma":[0.00005298159,0.0027689335,0.8159521,0.00007702135,0.00026095184,0.000018543593,0.00032259212,0.00021060322,0.18033628],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99726343,0.00023969606,0.0005451084,0.00093621557,0.0004491612,0.0005664023],"domain_scores_gemma":[0.9982378,0.00010399447,0.00039884905,0.0009792922,0.000096176824,0.00018389069],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029395043,0.00047962894,0.00058777945,0.00055878394,0.000052751486,0.0000894101,0.000803531,0.0003773956,0.00046631668],"category_scores_gemma":[0.00006436983,0.00038682338,0.00004250145,0.0002758456,0.00009690163,0.00015751319,0.00037315884,0.00049264636,0.00015706463],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016984177,0.0001502156,0.0000064295546,0.00013743863,0.000029100562,0.000096884505,0.00012896245,0.0000043913124,0.0003474991,0.15439367,0.23127571,0.61341274],"study_design_scores_gemma":[0.0021639722,0.00039364057,0.0001299062,0.0047900146,0.000061367464,0.000107944594,0.000025380223,0.03131218,0.00011168514,0.25062948,0.7078803,0.0023941179],"about_ca_topic_score_codex":0.00026228436,"about_ca_topic_score_gemma":0.0007961806,"teacher_disagreement_score":0.6110186,"about_ca_system_score_codex":0.00015223275,"about_ca_system_score_gemma":0.00021203875,"threshold_uncertainty_score":0.9998584},"labels":[],"label_agreement":null},{"id":"W3049670640","doi":"10.1002/cjs.11560","title":"A Bayesian mixture of experts approach to covariate misclassification","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Covariate; Categorical variable; Bayesian probability; Computer science; Identifiability; Context (archaeology); Econometrics; Statistics; Inference; Regression; Bayes' theorem; Mathematics; Machine learning; Artificial intelligence","score_opus":0.05091477935871081,"score_gpt":0.25000883977436306,"score_spread":0.19909406041565225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049670640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000072659685,0.00014847388,0.99483526,0.0030678606,0.00021112247,0.00009023668,0.00007915043,0.000004790679,0.0014904308],"genre_scores_gemma":[0.21623434,0.0000052640917,0.7823778,0.0012472526,0.00009286394,0.0000010003475,0.0000021707401,0.000008278266,0.000031069885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989315,0.00009919356,0.000402163,0.00016069761,0.00019426175,0.00021213047],"domain_scores_gemma":[0.99808407,0.00005914652,0.00024970155,0.00020797415,0.000320968,0.0010781125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002701749,0.000106701526,0.0002484388,0.00015061858,0.00005724538,0.00007792647,0.0006444162,0.00006163166,0.000013059453],"category_scores_gemma":[0.0002737336,0.00009642088,0.000047735135,0.00035330062,0.000038156842,0.00012869386,0.000017917175,0.00014717667,0.0000020474947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022868533,0.000042107516,0.00020297883,0.00010852488,0.00007687001,0.00019585183,0.019122463,0.0005000111,0.0024478328,0.70923644,0.12345656,0.1445875],"study_design_scores_gemma":[0.0033110979,0.0025157102,0.0075976388,0.00044626347,0.0002661333,0.0009972469,0.0011629699,0.53586924,0.0067823916,0.22657315,0.21236996,0.0021081741],"about_ca_topic_score_codex":0.00018409328,"about_ca_topic_score_gemma":0.00018749153,"teacher_disagreement_score":0.5353692,"about_ca_system_score_codex":0.000050773517,"about_ca_system_score_gemma":0.0009708432,"threshold_uncertainty_score":0.39319295},"labels":[],"label_agreement":null},{"id":"W3080792994","doi":"10.1002/sta4.310","title":"A family of parsimonious mixtures of multivariate Poisson‐lognormal distributions for clustering multivariate count data","year":2020,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Count data; Multivariate statistics; Poisson distribution; Mathematics; Statistics; Multivariate normal distribution; Log-normal distribution; Cluster analysis; Latent variable; Multivariate t-distribution","score_opus":0.08185702299938706,"score_gpt":0.3330524113410217,"score_spread":0.25119538834163463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080792994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022568617,0.00022908377,0.9940991,0.0009031591,0.00021957811,0.00036570738,0.0017737476,0.000054849865,0.00009792392],"genre_scores_gemma":[0.42376813,0.000012869443,0.57591736,0.00015694243,0.000039399245,0.0000098408655,0.00007830458,0.000008570314,0.0000085595475],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984966,0.00011074708,0.00041806165,0.00046808567,0.00020192427,0.00030461507],"domain_scores_gemma":[0.99846274,0.00026105976,0.0002348808,0.00075530726,0.00015660196,0.00012942233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045902774,0.00016327716,0.00034849613,0.000036994756,0.000083042694,0.000038694332,0.0012359816,0.000072923394,0.0000022323625],"category_scores_gemma":[0.00026003103,0.00014268409,0.00008516044,0.00023039596,0.00006466196,0.00034912917,0.0007931461,0.0001162732,8.2056357e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081414025,0.0007457993,0.00042783434,0.0013203261,0.0006438546,0.000049547292,0.0135142775,0.0036439425,0.38678002,0.30882967,0.009507087,0.2737235],"study_design_scores_gemma":[0.001355755,0.00022907677,0.0011240974,0.00005607108,0.00004742402,0.0000029726214,0.000033882014,0.9734407,0.0113751,0.0079188775,0.004169255,0.00024677522],"about_ca_topic_score_codex":0.00027346853,"about_ca_topic_score_gemma":0.000015523588,"teacher_disagreement_score":0.9697968,"about_ca_system_score_codex":0.000016310622,"about_ca_system_score_gemma":0.000106631254,"threshold_uncertainty_score":0.5818488},"labels":[],"label_agreement":null},{"id":"W3081416849","doi":"10.14288/1.0392911","title":"Optimal algorithms for experts and mixtures of Gaussians","year":2020,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Algorithm; Computer science; Mixture model; Artificial intelligence","score_opus":0.017792797318672057,"score_gpt":0.20888526450560693,"score_spread":0.19109246718693487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081416849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13768624,0.00030679037,0.86090004,0.0005521844,0.000050994313,0.00016187053,0.000052740856,0.000035878635,0.0002532375],"genre_scores_gemma":[0.53579426,0.000050443952,0.46394345,0.00011227363,0.000020365558,3.43947e-7,0.0000016098799,0.000004669943,0.00007258656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99924845,0.000038162663,0.000092970724,0.00034020405,0.00012448298,0.00015571508],"domain_scores_gemma":[0.999463,0.00004458468,0.000086336295,0.00017588878,0.00009288388,0.00013728424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000114627896,0.000036066052,0.00023598154,0.000019407622,0.00009751029,0.000059624635,0.0004262916,0.00007312123,0.0000074147442],"category_scores_gemma":[0.00002100845,0.00011284588,0.00009039216,0.00015345459,0.0001347495,0.00027991977,0.00017621195,0.000049914306,3.6412231e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007779593,0.00003958212,0.00018485602,0.000092861235,0.00002595819,0.000030439296,0.0013790905,0.0000054894285,0.0014661939,0.0001419306,0.0040409393,0.9925849],"study_design_scores_gemma":[0.00832191,0.0021995034,0.7120196,0.00051164784,0.00018345065,0.00032810518,0.0025597513,0.24849156,0.0005541537,0.017075682,0.0061660726,0.0015885351],"about_ca_topic_score_codex":0.0034709298,"about_ca_topic_score_gemma":0.0014605931,"teacher_disagreement_score":0.99099636,"about_ca_system_score_codex":0.0000074656214,"about_ca_system_score_gemma":0.000042185537,"threshold_uncertainty_score":0.5247031},"labels":[],"label_agreement":null},{"id":"W3086637446","doi":"10.1109/iri49571.2020.00025","title":"Fully Bayesian Learning of Multivariate Beta Mixture Models","year":2020,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain Monte Carlo; Gibbs sampling; Computer science; Artificial intelligence; Conjugate prior; Mixture model; Cluster analysis; Multivariate statistics; Machine learning; Monte Carlo method; Bayesian probability; Bayesian inference; Pattern recognition (psychology); Prior probability; Mathematics; Statistics","score_opus":0.027827281489345802,"score_gpt":0.2619372086326765,"score_spread":0.2341099271433307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086637446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018613836,0.00011053688,0.9728792,0.0043137316,0.00008228987,0.00011858037,0.000001015006,0.00020370334,0.022104813],"genre_scores_gemma":[0.42060503,0.0000061506835,0.5781763,0.00081738323,0.000045809968,0.0000023653956,8.2135153e-7,0.000009124216,0.00033699584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985789,0.00018655513,0.0002850231,0.00044459672,0.00024057423,0.00026437247],"domain_scores_gemma":[0.9991658,0.00007686195,0.0001142675,0.00034528854,0.00008941661,0.00020838687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002933646,0.00016636572,0.00028959147,0.000048733742,0.00006925487,0.00006139855,0.0007875448,0.00010447357,0.0000365355],"category_scores_gemma":[0.000041811232,0.00013559936,0.00011934148,0.0003686646,0.000028294033,0.00046126082,0.00028637634,0.00028052786,0.00001017309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008256104,0.000022549972,0.000025794674,0.000027700513,0.00002252038,0.0000089117075,0.0021113972,0.0017069746,0.006428909,0.92746836,0.00038026628,0.061788343],"study_design_scores_gemma":[0.0002770421,0.000101973616,0.000036969195,0.000012132126,0.000008084663,0.0000038396256,0.000012049249,0.9477585,0.007518745,0.042588856,0.0015049053,0.00017689736],"about_ca_topic_score_codex":0.000026856622,"about_ca_topic_score_gemma":0.0000012736475,"teacher_disagreement_score":0.94605154,"about_ca_system_score_codex":0.000007747487,"about_ca_system_score_gemma":0.00005597756,"threshold_uncertainty_score":0.55295813},"labels":[],"label_agreement":null},{"id":"W3086823818","doi":"10.1109/iri49571.2020.00024","title":"Background Subtraction with a Hierarchical Pitman-Yor Process Mixture Model of Generalized Gaussian Distributions","year":2020,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Background subtraction; Gaussian process; Gaussian; Subtraction; Mixture model; Computer science; Artificial intelligence; Process (computing); Algorithm; Pattern recognition (psychology); Mathematics; Extension (predicate logic); Applied mathematics; Arithmetic","score_opus":0.04031610511621322,"score_gpt":0.29147190217665125,"score_spread":0.25115579706043806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086823818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013395973,0.00003060373,0.9752834,0.008540835,0.000036363326,0.00020952604,0.00001976224,0.00014059037,0.0023429408],"genre_scores_gemma":[0.46739236,0.000005067399,0.5318847,0.0005210951,0.000044123502,0.000015406238,0.00000918756,0.0000077033355,0.00012036772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862665,0.00009071281,0.00025704497,0.0004603808,0.00030194683,0.0002632634],"domain_scores_gemma":[0.9991353,0.000036739686,0.0001057505,0.00034653416,0.00012700894,0.00024864855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015078344,0.00017809423,0.00026552464,0.000043204673,0.00010558861,0.00008540775,0.0005117542,0.00010306535,0.000024274268],"category_scores_gemma":[0.000018025892,0.00012425394,0.00007982584,0.00050417107,0.0000750053,0.00047070158,0.00007541199,0.0002595112,0.00000428619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009655665,0.00014978547,0.000048289727,0.0000828961,0.00004013962,0.000008668655,0.0009711663,0.0011125251,0.010701714,0.97742903,0.0008254342,0.008533772],"study_design_scores_gemma":[0.0006832923,0.0001925824,0.00014456276,0.000019206316,0.000027042426,0.000022495306,0.000017275932,0.9136061,0.012163233,0.07260268,0.00025970268,0.0002618266],"about_ca_topic_score_codex":0.000013412266,"about_ca_topic_score_gemma":0.000010505841,"teacher_disagreement_score":0.9124936,"about_ca_system_score_codex":0.000020121397,"about_ca_system_score_gemma":0.00018673627,"threshold_uncertainty_score":0.5066929},"labels":[],"label_agreement":null},{"id":"W3093801655","doi":"10.1002/ima.22506","title":"Nonparametric variational learning of multivariate beta mixture models in medical applications","year":2020,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Cluster analysis; Multivariate statistics; Flexibility (engineering); Machine learning; Mixture model; Artificial intelligence; Field (mathematics); Nonparametric statistics; Data mining; Mathematics; Statistics","score_opus":0.011899639176277912,"score_gpt":0.28360155269776793,"score_spread":0.27170191352149003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093801655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013729119,0.0015105711,0.98305637,0.013495501,0.00022979898,0.000078590616,0.0000018944685,0.000024343055,0.00023003461],"genre_scores_gemma":[0.8616557,0.000080113816,0.1380034,0.00013019469,0.000111359695,0.0000058185915,6.969253e-7,0.00000507481,0.0000076112465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986027,0.00008372483,0.0005754424,0.00017515762,0.00045428012,0.00010867936],"domain_scores_gemma":[0.99872136,0.00015457152,0.00046189607,0.00009218577,0.00049290113,0.00007708488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063440413,0.0000861621,0.0002567874,0.00063509203,0.00002366704,0.0000499349,0.0008437046,0.00010327305,0.0000026180676],"category_scores_gemma":[0.00023948895,0.00007388057,0.000043443546,0.0005741073,0.00005745046,0.00030137424,0.00018709357,0.00043134208,5.8947666e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007689117,0.00004745456,0.0028538555,0.000017445735,0.000060644175,0.00006786185,0.00024372563,0.0011167024,0.0008222145,0.8968001,0.00003329246,0.09792904],"study_design_scores_gemma":[0.00077138754,0.00004556029,0.00033149755,0.00012188913,0.000007713786,0.0006507836,0.000039662755,0.9518421,0.00020126915,0.043629304,0.0022668988,0.000091891074],"about_ca_topic_score_codex":0.000026275753,"about_ca_topic_score_gemma":5.394049e-7,"teacher_disagreement_score":0.95072544,"about_ca_system_score_codex":0.00002768674,"about_ca_system_score_gemma":0.00012549719,"threshold_uncertainty_score":0.3012762},"labels":[],"label_agreement":null},{"id":"W3093996040","doi":"10.1214/21-aihp1239","title":"On mean estimation for heteroscedastic random variables","year":2023,"lang":"fr","type":"article","venue":"Annales de l Institut Henri Poincaré Probabilités et Statistiques","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mathematics; Heteroscedasticity; Combinatorics; Statistics","score_opus":0.06484620437189509,"score_gpt":0.3617960807709058,"score_spread":0.2969498763990107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093996040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038507788,0.0017573683,0.97533303,0.01095853,0.0018342156,0.00231362,0.00076166925,0.000724922,0.0024658416],"genre_scores_gemma":[0.056821264,0.0007812773,0.9345657,0.002914215,0.00025768552,0.0007774823,0.0002643709,0.00008976419,0.0035282418],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944197,0.0014557944,0.0009978293,0.0013213119,0.00052224624,0.0012831343],"domain_scores_gemma":[0.99346566,0.0042588026,0.00034652045,0.0010020545,0.0005138297,0.00041314107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004676656,0.00068950484,0.0008313777,0.0003641675,0.00051312067,0.00075809594,0.0008605602,0.00042197554,0.00003882522],"category_scores_gemma":[0.0032508583,0.00069293217,0.00033333962,0.0007761729,0.0005093314,0.0013606702,0.00027875276,0.00055717194,0.00012768728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021763828,0.00020464431,0.000023262868,0.0011557932,0.00009628484,0.000062700296,0.0053086444,0.012141991,0.00011748283,0.7956982,0.012290355,0.17268299],"study_design_scores_gemma":[0.0011756088,0.0006106186,0.00017866479,0.0006484713,0.000066120985,0.00004700698,0.000018049815,0.40125105,0.00038920043,0.58543485,0.009723639,0.0004567219],"about_ca_topic_score_codex":0.00041566516,"about_ca_topic_score_gemma":0.00042246497,"teacher_disagreement_score":0.38910908,"about_ca_system_score_codex":0.00031380585,"about_ca_system_score_gemma":0.0010747816,"threshold_uncertainty_score":0.9995522},"labels":[],"label_agreement":null},{"id":"W3094595856","doi":"10.1101/2020.10.24.353599","title":"Microbial diversity estimation and hill number calculation using the hierarchical Pitman-Yor process","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; HEC Montréal; York University","funders":"Medical Research Council","keywords":"Population; Abundance (ecology); Statistics; Context (archaeology); Diversity (politics); Relative species abundance; Biology; Mathematics; Ecology","score_opus":0.02614307284607648,"score_gpt":0.2628381144831295,"score_spread":0.23669504163705302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094595856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24326521,0.00007241634,0.7544954,0.0010370974,0.00046086367,0.00044697896,0.000024779758,0.0001930018,0.0000042465176],"genre_scores_gemma":[0.68967634,0.000012423804,0.30972627,0.00033930334,0.00020596087,0.000013882639,1.3693968e-7,0.000024926685,7.54714e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975312,0.00039026418,0.0003517967,0.001001668,0.00037456918,0.0003505206],"domain_scores_gemma":[0.9982739,0.000090278714,0.00031865574,0.0008209599,0.00026651804,0.0002296706],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008550512,0.0003797465,0.00037666538,0.00008365771,0.0005751603,0.00047508616,0.00095939887,0.0003698413,0.00000426562],"category_scores_gemma":[0.00016680328,0.00032988217,0.00010532421,0.00042268488,0.00014142269,0.00038044743,0.0022427603,0.00082677766,0.000008249258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002147101,0.0006396357,0.02546623,0.0038611996,0.0008973884,0.000366214,0.0030022087,0.006507237,0.7743781,0.18194899,0.0014121718,0.0013058912],"study_design_scores_gemma":[0.00050935673,0.000025650772,0.030860296,0.00028054483,0.00016749007,2.682654e-7,0.0000012661119,0.9380908,0.027706254,0.001217768,0.00020501118,0.0009353188],"about_ca_topic_score_codex":0.00005239682,"about_ca_topic_score_gemma":8.7457755e-7,"teacher_disagreement_score":0.9315835,"about_ca_system_score_codex":0.00013018213,"about_ca_system_score_gemma":0.0003384607,"threshold_uncertainty_score":0.9999153},"labels":[],"label_agreement":null},{"id":"W3095100001","doi":"10.1371/journal.pone.0141942","title":"Correction: A Fast Incremental Gaussian Mixture Model","year":2015,"lang":"en","type":"erratum","venue":"PLoS ONE","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"MNIST database; Statement (logic); Computer science; Code (set theory); Source code; Set (abstract data type); Gaussian; Data set; Software; Gaussian network model; Data mining; Artificial intelligence; Information retrieval; Programming language; Deep learning; Chemistry","score_opus":0.0505591227469245,"score_gpt":0.2586483496512064,"score_spread":0.20808922690428192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095100001","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000028567651,0.00092975114,0.69522744,0.00081443187,0.007940087,0.0002821439,0.000031004678,0.00026856732,0.2945037],"genre_scores_gemma":[0.0000989179,0.00015501099,0.48827034,0.0007575278,0.002162661,0.000057615816,0.00012097084,0.000057249406,0.5083197],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967179,0.0001890814,0.0003989676,0.00096764497,0.001178097,0.00054835755],"domain_scores_gemma":[0.9977324,0.000031239135,0.00026869346,0.0013112087,0.00028052845,0.00037593936],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005225328,0.0005151664,0.0007607395,0.0002338995,0.00016737124,0.00029711644,0.0015917673,0.00079730083,0.000045249402],"category_scores_gemma":[0.00007968665,0.00048171432,0.00016446448,0.0004187012,0.000060651004,0.00041532074,0.0006153069,0.0017113999,0.00013084087],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007721073,0.00053585134,0.0000015337548,0.000099118,0.00017181257,0.000024122062,0.0004694841,0.0000063602733,0.00023122321,0.0025004218,0.9874213,0.00853105],"study_design_scores_gemma":[0.00040762968,0.00019003119,0.0000046696427,0.00094758614,0.0002091646,0.000033321325,0.000010440237,0.9452608,0.0009083439,0.020364525,0.03075077,0.00091269566],"about_ca_topic_score_codex":0.000030601015,"about_ca_topic_score_gemma":0.0000327039,"teacher_disagreement_score":0.9566705,"about_ca_system_score_codex":0.00024600068,"about_ca_system_score_gemma":0.00072226836,"threshold_uncertainty_score":0.9997634},"labels":[],"label_agreement":null},{"id":"W3096529391","doi":"10.1002/cjs.11582","title":"Flexible Bayesian quantile curve fitting with shape restrictions under the Dirichlet process mixture of the generalized asymmetric Laplace distribution","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quantile; Mathematics; Quantile regression; Laplace distribution; Overfitting; Applied mathematics; Dirichlet distribution; Shape parameter; Dirichlet process; Laplace transform; Mathematical optimization; Bayesian probability; Statistics; Mathematical analysis; Computer science; Artificial intelligence","score_opus":0.024579930845012424,"score_gpt":0.25656660666224834,"score_spread":0.23198667581723592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096529391","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019472993,0.00041090793,0.9891749,0.0076017245,0.0002294498,0.00013676634,0.00030695365,0.000008049261,0.00018393439],"genre_scores_gemma":[0.7855159,0.000030311761,0.21329245,0.0009478856,0.000138628,0.0000022989677,0.0000073470173,0.000013985543,0.000051188876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859065,0.0002385892,0.0003944407,0.00016311949,0.00033383895,0.0002793415],"domain_scores_gemma":[0.9980923,0.0002668178,0.0005013187,0.00025740653,0.000501658,0.00038051038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003529446,0.00013924926,0.00022802678,0.000091708775,0.00035205326,0.00014763646,0.0008807153,0.00006350153,0.000011194898],"category_scores_gemma":[0.00040696742,0.000079249665,0.00006571693,0.0016401303,0.00012200174,0.0001802409,0.00003083833,0.0004268518,7.165699e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059617465,0.000054704753,0.008945841,0.00016314999,0.00023798326,0.0001558324,0.0040510255,0.009317231,0.00010838396,0.8524129,0.07416264,0.050330687],"study_design_scores_gemma":[0.0038614501,0.001766583,0.0748144,0.00071437017,0.0007628573,0.0011718385,0.0017036567,0.71726376,0.004484857,0.15281497,0.039157655,0.0014836161],"about_ca_topic_score_codex":0.00059319026,"about_ca_topic_score_gemma":0.0017804231,"teacher_disagreement_score":0.7835686,"about_ca_system_score_codex":0.00008064421,"about_ca_system_score_gemma":0.0016228099,"threshold_uncertainty_score":0.32317078},"labels":[],"label_agreement":null},{"id":"W3097039570","doi":"10.1093/bioinformatics/btad167","title":"Finite mixtures of matrix variate Poisson-log normal distributions for three-way count data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Carleton University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; University of Toronto; Carleton University","keywords":"Random variate; Cluster analysis; Computer science; Poisson distribution; Markov chain Monte Carlo; Covariance matrix; Algorithm; Gaussian; Mixture model; Data mining; Mathematics; Statistics; Artificial intelligence; Bayesian probability; Random variable","score_opus":0.04948721312213769,"score_gpt":0.31552877440143295,"score_spread":0.26604156127929524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097039570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014709031,0.000068140966,0.99563164,0.00069762074,0.0005038688,0.00034111316,0.001840446,0.00017304497,0.0005970552],"genre_scores_gemma":[0.011340581,0.000040471034,0.9875301,0.000119142125,0.000086730324,0.000021529582,0.00067421136,0.000010287404,0.00017691815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985558,0.000027009266,0.0005417987,0.00019760821,0.00028801415,0.00038976272],"domain_scores_gemma":[0.99775374,0.0004021668,0.0002466783,0.001351577,0.00014551953,0.00010030099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012023593,0.00015992037,0.00025024798,0.00013101175,0.00017558003,0.00013066472,0.0016692366,0.000110362744,0.000006130798],"category_scores_gemma":[0.00027703552,0.00013194093,0.000085147665,0.00061922387,0.00005735334,0.0008286086,0.00077849336,0.000107583095,0.000047287922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027167656,0.0000964307,0.0001220885,0.00059467985,0.00012226595,0.000005596167,0.0016281803,0.000491403,0.00027725473,0.7545588,0.067737885,0.17433827],"study_design_scores_gemma":[0.000334089,0.000062625935,0.00044770233,0.000029713152,0.000025656112,0.0000061526985,0.000011057845,0.95289415,0.00047101063,0.03214168,0.013398309,0.00017782359],"about_ca_topic_score_codex":0.0000191476,"about_ca_topic_score_gemma":0.000013465385,"teacher_disagreement_score":0.9524028,"about_ca_system_score_codex":0.000019744106,"about_ca_system_score_gemma":0.00013092355,"threshold_uncertainty_score":0.5380395},"labels":[],"label_agreement":null},{"id":"W3098230082","doi":"10.1002/wics.1536","title":"A convergence diagnostic for Bayesian clustering","year":2020,"lang":"en","type":"review","venue":"Wiley Interdisciplinary Reviews Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada); McGill University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain Monte Carlo; Cluster analysis; Computer science; Gibbs sampling; Posterior probability; Bayesian probability; Data mining; Markov chain; Machine learning; Artificial intelligence","score_opus":0.06919171479297738,"score_gpt":0.39066541610541294,"score_spread":0.3214737013124356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098230082","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.30216e-10,0.49324036,0.50341946,0.0001234303,0.0007455313,0.0016846746,0.0006330413,0.00007720043,0.00007631805],"genre_scores_gemma":[1.5230998e-7,0.5069298,0.49149868,0.00015201209,0.00026016627,0.00059464324,0.00045010066,0.000050949406,0.00006351413],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948328,0.00071011396,0.0021118773,0.0013572893,0.0004097782,0.0005781387],"domain_scores_gemma":[0.99254614,0.004894238,0.0011926895,0.0007421148,0.00021831183,0.00040650347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000796949,0.0009417115,0.0032042158,0.00021151258,0.00038249764,0.00031489076,0.0020744368,0.0002555966,0.000049882863],"category_scores_gemma":[0.0007588724,0.00079973554,0.00090609957,0.0006402902,0.00011060996,0.00029761798,0.0020103455,0.00056278,0.0002599303],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003099065,0.000043357184,1.5217799e-7,0.01546144,0.00009560206,0.000068373934,0.000198483,0.00007357789,1.2683009e-8,0.046091773,0.031888463,0.90607566],"study_design_scores_gemma":[0.00013641102,0.00017688851,3.450247e-7,0.012582275,0.00031872102,0.00016079874,0.0000019525119,0.17694563,1.8646327e-8,0.081714906,0.72731274,0.00064929255],"about_ca_topic_score_codex":0.0000013143214,"about_ca_topic_score_gemma":0.0000039987385,"teacher_disagreement_score":0.9054264,"about_ca_system_score_codex":0.00023031162,"about_ca_system_score_gemma":0.0005094734,"threshold_uncertainty_score":0.9994454},"labels":[],"label_agreement":null},{"id":"W3098381019","doi":"","title":"Clustering and Classification via Cluster-Weighted Factor Analyzers","year":2014,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Expectation–maximization algorithm; Mixture model; Mathematics; Covariance matrix; Multivariate random variable; Pattern recognition (psychology); k-medians clustering; Covariance; Artificial intelligence; Computer science; Algorithm; Statistics; Correlation clustering; Random variable; CURE data clustering algorithm; Maximum likelihood","score_opus":0.021584819916020605,"score_gpt":0.2631628635724246,"score_spread":0.24157804365640398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098381019","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038578396,0.000019391398,0.9867878,0.0010349205,0.00014766291,0.00008293321,3.0029366e-7,0.0001365093,0.007932659],"genre_scores_gemma":[0.46979848,0.0000050065346,0.5294513,0.00042817031,0.000031561478,0.0000028829716,5.5723456e-7,0.000004152966,0.00027789376],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991228,0.00011982364,0.00015127558,0.00032402,0.00011309202,0.00016901165],"domain_scores_gemma":[0.99934506,0.000081351645,0.000052486004,0.000379798,0.000034817065,0.000106463274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027917727,0.00010295345,0.00012332872,0.00007937768,0.000078485275,0.00012891753,0.00027763977,0.000061938066,0.000015880656],"category_scores_gemma":[0.000014510661,0.00008109246,0.0000303288,0.00015692542,0.000024573921,0.00030548603,0.00013396141,0.00007383681,0.000015276544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002627218,0.000012463284,0.0002709813,0.000011676635,0.000008801422,3.9934875e-7,0.00027136414,0.0000029273795,0.00800012,0.05787306,0.00022816182,0.9333174],"study_design_scores_gemma":[0.00018042482,0.000030014617,0.0057942513,0.0000050012222,0.0000033531235,0.000007597808,0.000002465741,0.9781902,0.0010062522,0.012999707,0.001651475,0.00012926916],"about_ca_topic_score_codex":0.000011718333,"about_ca_topic_score_gemma":0.000013212234,"teacher_disagreement_score":0.97818726,"about_ca_system_score_codex":0.000014723128,"about_ca_system_score_gemma":0.00000859097,"threshold_uncertainty_score":0.33068544},"labels":[],"label_agreement":null},{"id":"W3098654049","doi":"","title":"Minimax estimation for mixtures of Wishart distributions","year":2016,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Wishart distribution; Mathematics; Estimator; Applied mathematics; Nonparametric statistics; Density estimation; Minimax; Eigenvalues and eigenvectors; Statistical inference; Euclidean space; Statistics; Mathematical optimization; Multivariate statistics; Combinatorics","score_opus":0.018556762740624514,"score_gpt":0.2886745519256017,"score_spread":0.2701177891849772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098654049","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003030988,0.000028312174,0.9952669,0.0026272056,0.00010544284,0.00012319235,0.0000307619,0.000049506623,0.0014655933],"genre_scores_gemma":[0.16845815,0.0000022891436,0.8307872,0.00006106801,0.000017630697,0.000018138351,0.0000022115748,0.0000021503863,0.00065117906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99951315,0.000021327167,0.00013317475,0.00014901829,0.00007093967,0.000112385045],"domain_scores_gemma":[0.9993964,0.00018393794,0.000048239835,0.00025210992,0.00008070279,0.000038605573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018856669,0.00005340057,0.000086691434,0.000028749539,0.00003662661,0.00001689182,0.000249645,0.000033780354,0.000016057425],"category_scores_gemma":[0.00010929189,0.00003082548,0.000055742545,0.00008438149,0.000027480852,0.00022353795,0.00004205428,0.000012899159,0.0000047462227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000176755,0.000014717741,0.000009664072,0.0000053482877,0.0000035194528,8.474126e-8,0.000019641848,2.7952913e-7,0.010073282,0.71763664,0.005204442,0.2670306],"study_design_scores_gemma":[0.000384104,0.00008458205,0.00047974815,0.000029387027,0.0000074428335,0.0000038763847,6.9043125e-7,0.022066858,0.19737671,0.77503306,0.0044198413,0.00011369127],"about_ca_topic_score_codex":0.0000028690272,"about_ca_topic_score_gemma":0.0000011739407,"teacher_disagreement_score":0.2669169,"about_ca_system_score_codex":0.000009656361,"about_ca_system_score_gemma":0.000028107246,"threshold_uncertainty_score":0.12570265},"labels":[],"label_agreement":null},{"id":"W3099704538","doi":"","title":"Fractionally-Supervised Classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McGill University","funders":"","keywords":"Artificial intelligence; Cluster analysis; Pattern recognition (psychology); Classifier (UML); A priori and a posteriori; Supervised learning; Machine learning; Mixture model; Mathematics; Gaussian; Unsupervised learning; Computer science; Artificial neural network","score_opus":0.03474285585562811,"score_gpt":0.27682092163968297,"score_spread":0.24207806578405486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099704538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029569108,0.000011705341,0.94133914,0.0106473435,0.00015851327,0.000037340622,2.990127e-7,0.00012996186,0.047380015],"genre_scores_gemma":[0.20258902,0.000012169776,0.79144335,0.000754506,0.000054004446,0.000007382358,1.8003803e-7,0.000002778185,0.005136584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994724,0.00004164538,0.00008453613,0.00019111842,0.00011169924,0.00009863082],"domain_scores_gemma":[0.9994764,0.00008216721,0.000021811724,0.00032334027,0.000046169043,0.000050152445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001776913,0.00004758409,0.000046994584,0.000033460543,0.00003868163,0.000033391338,0.00029457145,0.000033897566,0.00014571361],"category_scores_gemma":[0.00002237027,0.000026014852,0.00002903689,0.000092879396,0.000012198801,0.000403775,0.000039958333,0.000024874564,0.00022334332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.6246504e-7,0.000007089345,0.000051156803,3.4147914e-7,0.0000013880858,2.820891e-7,0.0000096609965,1.6380435e-8,0.017935809,0.57843447,0.0015583555,0.40200093],"study_design_scores_gemma":[0.00071733346,0.000055883673,0.030995632,0.000020888483,0.000004299724,0.000021649921,0.000004965183,0.03313345,0.022400144,0.8076815,0.10460131,0.00036297194],"about_ca_topic_score_codex":0.0000021645235,"about_ca_topic_score_gemma":9.0506103e-7,"teacher_disagreement_score":0.40163797,"about_ca_system_score_codex":0.000016570146,"about_ca_system_score_gemma":0.000027640132,"threshold_uncertainty_score":0.2870701},"labels":[],"label_agreement":null},{"id":"W3102966675","doi":"10.5430/air.v10n1p57","title":"Estimation of the number of clusters on d-dimensional sphere","year":2021,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimation; Mathematics; Spherical model; SPHERES; Computer science; Statistical physics; Algorithm; Physics; Engineering","score_opus":0.1450089567830776,"score_gpt":0.4388428390960517,"score_spread":0.29383388231297414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102966675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06987434,0.000036816014,0.9238615,0.0017462533,0.00021967219,0.00011244836,0.0000017470121,0.000008700047,0.004138502],"genre_scores_gemma":[0.86204374,0.000006282245,0.13758498,0.000063003776,0.000024977813,0.000004358501,5.044231e-7,0.000004503068,0.0002676695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99787104,0.0005530912,0.00030486868,0.00026029552,0.00077808026,0.00023260654],"domain_scores_gemma":[0.9981857,0.00060989335,0.000065959925,0.0006309397,0.00045491566,0.00005260203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014917953,0.00006672255,0.0001272136,0.000047045458,0.00011681486,0.000038408834,0.00063093106,0.000060700193,0.00012538307],"category_scores_gemma":[0.0005262045,0.000047646132,0.00008420538,0.0009654912,0.00021314652,0.00011101681,0.00034809695,0.00026402844,0.00006609001],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011110643,0.00009221092,0.000027824459,0.000015024875,0.000005998211,0.0000036293227,0.00031670617,0.0025963408,0.0054317815,0.5605113,0.00014231082,0.43084577],"study_design_scores_gemma":[0.0000085895645,0.000025108095,0.00006408856,0.000055174714,0.0000011863006,0.000005182931,0.00005084204,0.1966922,0.48865741,0.31436962,0.00003357726,0.000037015587],"about_ca_topic_score_codex":0.00006367061,"about_ca_topic_score_gemma":0.000020934476,"teacher_disagreement_score":0.7921694,"about_ca_system_score_codex":0.000027746728,"about_ca_system_score_gemma":0.00028503896,"threshold_uncertainty_score":0.19429529},"labels":[],"label_agreement":null},{"id":"W3103120851","doi":"","title":"LARGE DEVIATIONS ASSOCIATED WITH POISSON–DIRICHLET DISTRIBUTION AND EWENS SAMPLING FORMULA","year":2012,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Poisson distribution; Dirichlet distribution; Poisson sampling; Infinity; Applied mathematics; Statistics; Mathematical analysis; Importance sampling; Monte Carlo method","score_opus":0.026571343313325696,"score_gpt":0.28207060532945016,"score_spread":0.2554992620161245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103120851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019309644,0.00016654532,0.9783625,0.00049893884,0.00006925039,0.00009846407,0.00001978764,0.00012391967,0.0013509733],"genre_scores_gemma":[0.803279,0.000010481352,0.1961706,0.00025954397,0.000034317145,0.0000063918014,0.000031828797,0.0000048640045,0.00020298858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99916524,0.00006232143,0.00011287249,0.00016684251,0.00013194454,0.00036078386],"domain_scores_gemma":[0.9994304,0.00011424595,0.000059879945,0.00019455497,0.00006982486,0.00013107229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005905173,0.00009677232,0.00011317089,0.000028291353,0.00021173054,0.00008953916,0.00013281689,0.00006097246,0.000008127445],"category_scores_gemma":[0.000092286704,0.000070388414,0.000022804532,0.00025670123,0.00001395957,0.00061478326,0.00008946686,0.000085426196,0.0000045246147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014552264,0.000078560435,0.0076217027,0.0000033492227,0.000020310212,5.363992e-7,0.00053941493,0.000001377868,0.000112110996,0.985225,0.0007589066,0.005637235],"study_design_scores_gemma":[0.0035138947,0.0003634736,0.6290043,0.00017689144,0.00018384066,0.000093973715,0.0001668699,0.14883201,0.0034857988,0.15090077,0.061352916,0.0019252953],"about_ca_topic_score_codex":0.000006521857,"about_ca_topic_score_gemma":0.00001964879,"teacher_disagreement_score":0.8343243,"about_ca_system_score_codex":0.00003802301,"about_ca_system_score_gemma":0.000019548155,"threshold_uncertainty_score":0.28703564},"labels":[],"label_agreement":null},{"id":"W3103402818","doi":"10.1109/ai4i49448.2020.00024","title":"Variational learning of a shifted scaled Dirichlet model with component splitting approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Agence Nationale de la Recherche","keywords":"Component (thermodynamics); Inference; Focus (optics); Computer science; Dirichlet distribution; Data modeling; Artificial intelligence; Machine learning; Mixture model; Algorithm; Data mining; Mathematics","score_opus":0.025401223672572124,"score_gpt":0.23133594186895498,"score_spread":0.20593471819638287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103402818","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003822889,0.0000165643,0.98488545,0.0012345671,0.000010391722,0.00011846421,7.992515e-7,0.00012116649,0.009789698],"genre_scores_gemma":[0.37046778,5.15643e-7,0.6290852,0.00034228782,0.00001895391,0.0000044856465,0.0000024224776,0.0000052856963,0.00007306008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886996,0.00011125016,0.0002150043,0.00034120746,0.0002939063,0.0001686605],"domain_scores_gemma":[0.9994505,0.00007405062,0.000109789085,0.00017620811,0.000077245415,0.00011219159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033858477,0.0001120063,0.00020689766,0.00003793669,0.0000677286,0.00004708335,0.00038070916,0.00004115971,0.000006838875],"category_scores_gemma":[0.000031504682,0.00008298093,0.000045454773,0.000336721,0.000025128993,0.00018991536,0.00016201264,0.0001723652,0.0000020483003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025531383,0.00007375218,0.0002644166,0.00003899146,0.000031207124,0.000002108487,0.002110638,0.048035942,0.002033385,0.93840414,0.0000570209,0.008922844],"study_design_scores_gemma":[0.00034780704,0.000058138823,0.00037737432,0.000008435505,0.0000071596432,0.0000037656382,0.000014262153,0.9919379,0.00045958694,0.0066448315,0.000026492822,0.00011429329],"about_ca_topic_score_codex":0.00000775833,"about_ca_topic_score_gemma":1.5001113e-7,"teacher_disagreement_score":0.9439019,"about_ca_system_score_codex":0.000009919224,"about_ca_system_score_gemma":0.00006658892,"threshold_uncertainty_score":0.33838642},"labels":[],"label_agreement":null},{"id":"W3105189197","doi":"10.1007/s00184-021-00856-9","title":"Consistency of the MLE under a two-parameter Gamma mixture model with a structural shape parameter","year":2022,"lang":"en","type":"article","venue":"Metrika","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Consistency (knowledge bases); Randomness; Shape parameter; Estimator; Estimation theory; Likelihood function; Mixing (physics); Gamma distribution; Mixture model; Applied mathematics; Generalized gamma distribution; Statistics","score_opus":0.024297362825762413,"score_gpt":0.2626929480173383,"score_spread":0.23839558519157586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105189197","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15097634,0.00034140193,0.8461948,0.0009012173,0.00028628192,0.00030887985,0.000019352286,0.000048614074,0.0009231059],"genre_scores_gemma":[0.60645205,0.0000010716908,0.3918605,0.0010930366,0.000017253677,0.000033045577,9.785923e-7,0.000013192843,0.0005288992],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977762,0.00039566934,0.00030494574,0.0005114773,0.0006444835,0.0003672294],"domain_scores_gemma":[0.99820936,0.0003676943,0.00020531754,0.0010317791,0.00009712832,0.00008871284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050371443,0.00022779606,0.0003430167,0.000172017,0.00029079456,0.00008205481,0.0013700202,0.000054324817,0.00008945972],"category_scores_gemma":[0.00009128621,0.00013755467,0.00020251349,0.001284253,0.00013725171,0.00019719717,0.0006883991,0.0004444759,0.0000016095267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037870026,0.00038021867,0.00263718,0.00012198737,0.00060582435,0.00007004819,0.0060694846,0.045580246,0.0102172755,0.7076533,0.004684408,0.22160134],"study_design_scores_gemma":[0.0010669036,0.00022256882,0.0009313565,0.0000145673675,0.000062694744,0.00014642511,0.000043444183,0.84253186,0.0033244134,0.15085962,0.0004481827,0.00034797247],"about_ca_topic_score_codex":0.000035104713,"about_ca_topic_score_gemma":0.000011319598,"teacher_disagreement_score":0.7969516,"about_ca_system_score_codex":0.00006366025,"about_ca_system_score_gemma":0.00019094019,"threshold_uncertainty_score":0.5609316},"labels":[],"label_agreement":null},{"id":"W3105302963","doi":"","title":"ASYMPTOTIC BEHAVIOR OF THE POISSON–DIRICHLET DISTRIBUTION FOR LARGE MUTATION RATE 1","year":2006,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Carleton University","funders":"","keywords":"Poisson distribution; Dirichlet distribution; Mathematics; Mutation rate; Statistics; Applied mathematics; Statistical physics; Econometrics; Mathematical analysis; Biology; Physics; Genetics","score_opus":0.00997749866204411,"score_gpt":0.26023888449504134,"score_spread":0.25026138583299723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105302963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018309325,0.000023066747,0.97988594,0.0006626804,0.00020466157,0.0003191133,0.000035512414,0.00003879156,0.00052089576],"genre_scores_gemma":[0.8242939,4.6057795e-7,0.17475037,0.000110229965,0.000034451426,0.000036066456,0.000021135795,0.0000037938044,0.0007495829],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99931425,0.00008290488,0.00017165804,0.00016556523,0.00010376373,0.00016186105],"domain_scores_gemma":[0.99943686,0.00007638349,0.00009012419,0.00027983324,0.000097381926,0.000019435716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046118788,0.00006972688,0.000090509915,0.000016826507,0.00009000873,0.000036244455,0.00029438364,0.00004378871,0.0000054092047],"category_scores_gemma":[0.00003154784,0.000044924793,0.00008356876,0.00019788487,0.000013789608,0.000148061,0.00005732785,0.000038996903,0.0000019068957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025039815,0.000095035284,0.00037025532,0.000009214437,0.0000028150137,6.204034e-7,0.000034981527,0.000014134218,0.0044350824,0.9824453,0.0023738686,0.0102161905],"study_design_scores_gemma":[0.0018827837,0.00018179374,0.18655975,0.000033925025,0.000103079146,0.000023909432,0.000013733327,0.18099503,0.23883533,0.38339096,0.0075400546,0.0004396394],"about_ca_topic_score_codex":0.00003046551,"about_ca_topic_score_gemma":0.00001847623,"teacher_disagreement_score":0.80598456,"about_ca_system_score_codex":0.000020547712,"about_ca_system_score_gemma":0.000028330755,"threshold_uncertainty_score":0.18319799},"labels":[],"label_agreement":null},{"id":"W3108528945","doi":"10.1016/j.jspi.2021.01.006","title":"Asymptotic results with estimating equations for time-evolving clustered data","year":2021,"lang":"en","type":"preprint","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Victoria University of Wellington","keywords":"Mathematics; Asymptotic distribution; Estimator; Estimating equations; Applied mathematics; Martingale (probability theory); Generalized estimating equation; Covariate; Exponential family; Multivariate statistics; Consistency (knowledge bases); Asymptotically optimal algorithm; Generalized linear model; Statistics; Mathematical optimization; Discrete mathematics","score_opus":0.08999486621297653,"score_gpt":0.37307141379160236,"score_spread":0.2830765475786258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108528945","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019869403,0.0004915748,0.99790055,0.00046299218,0.0003225473,0.00013168872,0.00025137316,0.000019879966,0.00022070477],"genre_scores_gemma":[0.1202694,0.00001047956,0.879331,0.00007613214,0.00017906779,0.0000028735747,0.00009629217,0.000010355789,0.00002442489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980054,0.00016724734,0.0007439838,0.00048843527,0.00034453996,0.00025039408],"domain_scores_gemma":[0.9935923,0.0042863484,0.0007693632,0.00062521215,0.00053005764,0.00019668354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015701469,0.00021685383,0.00053756114,0.0001149477,0.0001565652,0.000830372,0.0009405304,0.00013554792,0.0000041440903],"category_scores_gemma":[0.0055236607,0.0001660806,0.00003598068,0.000096882985,0.000072053015,0.0005570035,0.00097022636,0.00071445387,4.9017774e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055014045,0.0003868909,0.0004024287,0.002181777,0.00091928866,0.0010883932,0.009221883,0.061285317,0.0003212742,0.095495455,0.017010033,0.81113714],"study_design_scores_gemma":[0.00050344423,0.0002599161,0.0004721558,0.0020271088,0.0000933167,0.00010681035,0.000019780206,0.959868,0.0000075064413,0.03639329,0.000036509788,0.00021213775],"about_ca_topic_score_codex":0.000009051548,"about_ca_topic_score_gemma":0.000001244579,"teacher_disagreement_score":0.8985827,"about_ca_system_score_codex":0.000029467596,"about_ca_system_score_gemma":0.0006172581,"threshold_uncertainty_score":0.80072963},"labels":[],"label_agreement":null},{"id":"W3108864434","doi":"10.1016/j.tcs.2020.11.022","title":"Automedian sets of permutations: direct sum and shuffle","year":2020,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Combinatorics; Mathematics; Set (abstract data type); Separable space; Permutation (music); Function (biology); Discrete mathematics; Computer science","score_opus":0.015218746994989584,"score_gpt":0.27381356770253873,"score_spread":0.25859482070754913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108864434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01175486,0.00007162812,0.9799008,0.0045233886,0.00016789,0.000106691325,0.0000024948802,0.000114035756,0.0033582507],"genre_scores_gemma":[0.5732601,0.000004676443,0.42594156,0.0007563156,0.000031395586,0.0000016081575,1.7231667e-7,0.0000028651746,0.000001305761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998418,0.00011796491,0.0002137637,0.0005447344,0.00040235135,0.0003031929],"domain_scores_gemma":[0.99885535,0.00023998845,0.00005390085,0.00036451427,0.000114778835,0.00037144174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008481828,0.00012138779,0.0002147489,0.00009040855,0.0001570887,0.00016427352,0.0011570252,0.00003742451,0.000012048441],"category_scores_gemma":[0.00014622558,0.00009716359,0.000040297895,0.0009050323,0.0018362614,0.00044034058,0.0006699509,0.00012229958,0.000008597983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023504742,0.000013979944,0.000036986992,0.000011666851,0.000001921698,0.0000052107926,0.0016609749,0.00001082611,0.001016743,0.9160365,0.00003378832,0.08116908],"study_design_scores_gemma":[0.00015382358,0.00019423902,0.00097236264,0.000017412616,0.000004553381,0.000015478265,0.0000045434954,0.77742404,0.0054231854,0.21555646,0.00008430645,0.00014958343],"about_ca_topic_score_codex":0.0000017249323,"about_ca_topic_score_gemma":1.5382305e-7,"teacher_disagreement_score":0.77741325,"about_ca_system_score_codex":0.000011021364,"about_ca_system_score_gemma":0.0001099795,"threshold_uncertainty_score":0.6765781},"labels":[],"label_agreement":null},{"id":"W3111363863","doi":"10.1109/smc42975.2020.9283007","title":"Variational Inference of Infinite Generalized Gaussian Mixture Models with Feature Selection","year":2020,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Cluster analysis; Inference; Gaussian; Model selection; Feature selection; Selection (genetic algorithm); Computer science; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Gaussian process; Generalized normal distribution; Flexibility (engineering); Algorithm; Mathematics; Mathematical optimization; Normal distribution; Statistics","score_opus":0.026114397770897118,"score_gpt":0.25834608272426,"score_spread":0.2322316849533629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111363863","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004051599,0.000041003786,0.98621285,0.0061079836,0.000044501558,0.000131781,0.0000040171944,0.00011883608,0.006933879],"genre_scores_gemma":[0.23914926,0.000007700875,0.75873685,0.0017778745,0.00006560804,0.000006813217,0.0000043510877,0.0000067800365,0.0002447414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989063,0.00010680443,0.00016987798,0.00035216194,0.00028998038,0.00017487974],"domain_scores_gemma":[0.99931043,0.000054589087,0.00011288307,0.00021179943,0.000174859,0.00013546289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013533724,0.0001523692,0.00021248075,0.000059861333,0.000059008395,0.00007031237,0.00039812995,0.00011373747,0.00003718744],"category_scores_gemma":[0.00002349455,0.000107227635,0.000049724204,0.0006712386,0.000023498658,0.0005431532,0.00008104091,0.00019837727,0.0000029757346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030377765,0.000022204931,0.00015327704,0.000018173081,0.000028813703,0.000002075567,0.0008185967,0.004576795,0.002754428,0.9839133,0.0011056946,0.0065762773],"study_design_scores_gemma":[0.0005228217,0.00017052537,0.00048618644,0.000014762565,0.000012538885,0.000011524724,0.0000033951999,0.9134287,0.003669978,0.080763645,0.00071869296,0.00019717668],"about_ca_topic_score_codex":0.00002374409,"about_ca_topic_score_gemma":0.00001096876,"teacher_disagreement_score":0.908852,"about_ca_system_score_codex":0.000011941861,"about_ca_system_score_gemma":0.00016564218,"threshold_uncertainty_score":0.4372616},"labels":[],"label_agreement":null},{"id":"W3113374883","doi":"","title":"Interpretable Bayesian Functional Linear Regression","year":2015,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Bayesian probability; Linear regression; Bayesian multivariate linear regression; Artificial intelligence; Bayesian linear regression; Regression; Machine learning; Computer science; Regression analysis; Mathematics; Statistics; Pattern recognition (psychology); Bayesian inference","score_opus":0.033122536281248886,"score_gpt":0.2652861271825114,"score_spread":0.23216359090126248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113374883","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010093738,0.0039479374,0.84656674,0.026412483,0.0019577916,0.00047792727,0.000051458654,0.00031890164,0.119257376],"genre_scores_gemma":[0.06660939,0.0006559843,0.80320406,0.00040155026,0.00019289585,0.000080779064,0.00030200343,0.000083418396,0.12846993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.981057,0.013954729,0.0010933941,0.0019656136,0.0010578536,0.00087142835],"domain_scores_gemma":[0.986366,0.0017358128,0.0009547056,0.004467411,0.0056716185,0.0008044748],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.016186966,0.0008091765,0.00085555983,0.00030084376,0.0006766854,0.0010427407,0.0031903763,0.0008401307,0.0006733563],"category_scores_gemma":[0.0024261936,0.0007977997,0.0005064499,0.000848092,0.00050261436,0.0007612037,0.0044109314,0.0017263138,0.00030033727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029140761,0.0006339725,0.00024037763,0.0001378649,0.00010383895,0.00002194374,0.009278036,0.00020943575,0.0013788834,0.74533,0.01322615,0.22941041],"study_design_scores_gemma":[0.0009139777,0.0000016457046,0.0008771444,0.005428135,0.0000981235,0.00011549209,0.000050454248,0.6618315,0.012557042,0.15152179,0.16550413,0.0011005702],"about_ca_topic_score_codex":0.0011179532,"about_ca_topic_score_gemma":0.00051409623,"teacher_disagreement_score":0.66162205,"about_ca_system_score_codex":0.0003667484,"about_ca_system_score_gemma":0.0014651433,"threshold_uncertainty_score":0.9999943},"labels":[],"label_agreement":null},{"id":"W3116487341","doi":"10.3390/stats4010002","title":"General Formulas for the Central and Non-Central Moments of the Multinomial Distribution","year":2021,"lang":"en","type":"article","venue":"Stats","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Multinomial distribution; Mathematics; Factorial; Distribution (mathematics); Order (exchange); L-moment; Central moment; Argument (complex analysis); Method of moments (probability theory); Applied mathematics; Mathematical analysis; Statistics; Random variable; Order statistic; Moment-generating function","score_opus":0.015374971255060989,"score_gpt":0.2656864378694993,"score_spread":0.2503114666144383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116487341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06906357,0.00009226524,0.92920953,0.0006780344,0.0006157103,0.00020424451,0.00007629145,0.0000063218636,0.00005402369],"genre_scores_gemma":[0.8598706,0.000019438487,0.13967885,0.000117822645,0.00009896809,0.000010767881,0.000008100013,0.0000037007292,0.00019177262],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929535,0.000047785186,0.00012151247,0.00016420093,0.000111570946,0.00025955882],"domain_scores_gemma":[0.9995185,0.000071971765,0.00005378072,0.000256009,0.000051866642,0.00004787986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013551924,0.00006905106,0.00008643801,0.0000048689035,0.00013554905,0.000049324895,0.00025134615,0.000029327108,0.0000017823921],"category_scores_gemma":[0.000029718463,0.00003921673,0.000068956586,0.0000854217,0.000034159653,0.00009760562,0.00015695723,0.000055171873,1.284796e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074002775,0.00015937966,0.005189296,0.000089733694,0.00012361631,0.0000072260204,0.0037539094,0.00030561967,0.020338422,0.32325658,0.006859661,0.63984257],"study_design_scores_gemma":[0.002833282,0.00010627019,0.28623718,0.000041781797,0.00006139535,0.000023560702,0.000045564153,0.52325124,0.1274214,0.051227715,0.008441122,0.00030948495],"about_ca_topic_score_codex":0.00002233059,"about_ca_topic_score_gemma":0.00001367454,"teacher_disagreement_score":0.790807,"about_ca_system_score_codex":0.000023642275,"about_ca_system_score_gemma":0.000076782926,"threshold_uncertainty_score":0.15992118},"labels":[],"label_agreement":null},{"id":"W3116578073","doi":"10.1111/coin.12429","title":"Mixture‐based clustering for count data using approximated Fisher Scoring and Minorization–Maximization approaches","year":2020,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Mixture model; Count data; Dirichlet distribution; Multinomial distribution; Computer science; Hyperparameter; Burstiness; Overdispersion; Mathematics; Algorithm; Artificial intelligence; Statistics; Poisson distribution","score_opus":0.34864057237599905,"score_gpt":0.34046367904344504,"score_spread":0.008176893332554003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116578073","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029691655,0.00018953296,0.9978302,0.0009429141,0.00015428639,0.00038620803,0.000026302167,0.000111038185,0.000062587744],"genre_scores_gemma":[0.17547898,0.0000035867756,0.8235506,0.00070939155,0.000098501674,0.0000117576365,0.0001281959,0.000014220389,0.000004818562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985443,0.000066881265,0.00030898434,0.00066513923,0.0002217641,0.00019293306],"domain_scores_gemma":[0.9990053,0.00025945462,0.00013304992,0.00031771962,0.00016831202,0.0001161203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032462552,0.0001670044,0.00017439394,0.00006741295,0.000185663,0.000285861,0.00073433085,0.00006544715,0.000003883537],"category_scores_gemma":[0.00015918833,0.00017021762,0.000028776414,0.0003813434,0.000051938387,0.00066114025,0.0003493717,0.0000901656,0.000001507452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001961369,0.000030270696,0.00013269224,0.00017051569,0.00001933505,0.0000018156657,0.0005169917,0.8833002,0.00013918967,0.045518253,0.00009822508,0.0700529],"study_design_scores_gemma":[0.00012041926,0.000030495856,0.000053067055,0.000034834982,0.000012853973,0.000007083495,0.000014731369,0.98432624,0.00053335575,0.0145145925,0.00015796382,0.00019436853],"about_ca_topic_score_codex":0.0000052089,"about_ca_topic_score_gemma":0.0000012196815,"teacher_disagreement_score":0.17518206,"about_ca_system_score_codex":0.000027776121,"about_ca_system_score_gemma":0.00011077694,"threshold_uncertainty_score":0.6941273},"labels":[],"label_agreement":null},{"id":"W3118804762","doi":"10.1007/s00357-023-09452-0","title":"Logistic Normal Multinomial Factor Analyzers for Clustering Microbiome Data","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Simons Foundation","keywords":"Cluster analysis; Microbiome; Multinomial logistic regression; Mixture model; Computer science; Multinomial distribution; Expectation–maximization algorithm; Human microbiome; Gaussian; Data mining; Pattern recognition (psychology); Artificial intelligence; Statistics; Mathematics; Machine learning; Bioinformatics; Biology; Maximum likelihood","score_opus":0.2580616931963199,"score_gpt":0.39386718861884285,"score_spread":0.13580549542252296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118804762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00561377,0.000027843069,0.99210674,0.0012461385,0.0007879135,0.00010087004,0.000027336882,0.000032538563,0.000056834095],"genre_scores_gemma":[0.52222747,0.000023714209,0.47728947,0.00004845569,0.00027928097,0.0000019885795,0.000017797925,0.0000072664507,0.00010453774],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899715,0.000068564834,0.00041498285,0.00019645772,0.00014919447,0.00017363939],"domain_scores_gemma":[0.99865735,0.00019404569,0.0004234542,0.00048785834,0.00016105738,0.00007626737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096145004,0.00008160436,0.00017356557,0.00023228202,0.000076054646,0.00012203741,0.001113236,0.000060272367,0.0000033964698],"category_scores_gemma":[0.00020628587,0.00006791438,0.00007589762,0.00031742142,0.000024207073,0.0006486744,0.00015401775,0.00011196848,0.000008865377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009481213,0.00008196249,0.000380216,0.00009299022,0.000095589436,0.000017229591,0.00084021327,0.00039971733,0.30589873,0.0064581432,0.008620711,0.6770197],"study_design_scores_gemma":[0.00067770324,0.00009322194,0.014824545,0.000029819068,0.000027012793,0.000036361336,0.000040345352,0.97271085,0.0018348799,0.0016250222,0.007954042,0.00014620334],"about_ca_topic_score_codex":0.0000019905635,"about_ca_topic_score_gemma":0.0000039230654,"teacher_disagreement_score":0.97231114,"about_ca_system_score_codex":0.00004604909,"about_ca_system_score_gemma":0.00009782496,"threshold_uncertainty_score":0.2769468},"labels":[],"label_agreement":null},{"id":"W3119882815","doi":"10.3390/jimaging7010007","title":"Bayesian Learning of Shifted-Scaled Dirichlet Mixture Models and Its Application to Early COVID-19 Detection in Chest X-ray Images","year":2021,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Taif University","keywords":"Overfitting; Markov chain Monte Carlo; Computer science; Bayesian probability; Artificial intelligence; Frequentist inference; Robustness (evolution); Dirichlet process; Machine learning; Dirichlet distribution; Bayesian inference; Pattern recognition (psychology); Mathematics; Artificial neural network","score_opus":0.012540808213531618,"score_gpt":0.2801808884637346,"score_spread":0.267640080250203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119882815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035224628,0.0011888904,0.959712,0.0035357515,0.00008189394,0.00010077877,7.8692494e-7,0.000017583312,0.00013764384],"genre_scores_gemma":[0.73459035,0.000052900526,0.26492515,0.00034491383,0.00005484531,0.0000030362185,2.2064734e-7,0.000008527541,0.000020047048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856085,0.00026499102,0.00045343625,0.0002614425,0.00026416354,0.00019511166],"domain_scores_gemma":[0.9988664,0.00014145634,0.00033218868,0.00017918553,0.00025853593,0.0002222806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011450683,0.0001259886,0.00028870514,0.00030279352,0.00007693844,0.0001133071,0.0002793546,0.000052001473,0.0000021800765],"category_scores_gemma":[0.000286571,0.0001176568,0.00007130253,0.0006151279,0.000018454282,0.0008170838,0.00011863539,0.00038894138,5.222191e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006415633,0.0001168378,0.0042860904,0.00018140119,0.000036126,0.000239562,0.0067312564,0.0124858385,0.4844729,0.0055353884,0.00006452606,0.4857859],"study_design_scores_gemma":[0.0013196743,0.00013435887,0.013217464,0.00024011753,0.00004092123,0.00058478507,0.00023474476,0.85259944,0.08681865,0.04376749,0.00065621827,0.00038610888],"about_ca_topic_score_codex":0.000021204736,"about_ca_topic_score_gemma":0.000008416074,"teacher_disagreement_score":0.84011364,"about_ca_system_score_codex":0.000067037414,"about_ca_system_score_gemma":0.0001392405,"threshold_uncertainty_score":0.47979048},"labels":[],"label_agreement":null},{"id":"W3119925796","doi":"10.1007/s11634-020-00432-5","title":"Functional data clustering by projection into latent generalized hyperbolic subspaces","year":2021,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Linear subspace; Projection (relational algebra); Dimension (graph theory); Basis (linear algebra); Mathematics; Clustering high-dimensional data; Computer science; Applied mathematics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Combinatorics; Pure mathematics","score_opus":0.07372087970399593,"score_gpt":0.3428838780099273,"score_spread":0.2691629983059314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119925796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017174196,0.007425544,0.9891021,0.0013603751,0.00012912502,0.000062143496,0.000048038743,0.00003000739,0.00012524493],"genre_scores_gemma":[0.19581445,0.019027706,0.7782718,0.00023761914,0.00010158708,0.000027709712,0.0061804666,0.0000097407155,0.00032891778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982135,0.00022224642,0.00027599436,0.0009447007,0.00020478053,0.00013876798],"domain_scores_gemma":[0.99779534,0.00006476693,0.00012910021,0.0018990426,0.00006364409,0.000048124697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007501735,0.00011054587,0.00021127345,0.00015051755,0.00011538986,0.00019374107,0.0007997204,0.000052446107,0.00001101275],"category_scores_gemma":[0.00006616033,0.000099630895,0.000026546244,0.0012718029,0.00003501187,0.002364284,0.00074710674,0.00009473329,0.000002247399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011523251,0.00011325901,0.008111451,0.000030644886,0.00016160336,0.0000034925356,0.00015128491,0.00018301349,0.013931154,0.010934081,0.0015915764,0.96477693],"study_design_scores_gemma":[0.00018687546,0.000005489797,0.008393896,0.000008574115,0.00012203511,0.0000049631035,0.000035665762,0.96521074,0.0004191233,0.0030370427,0.022431318,0.00014428704],"about_ca_topic_score_codex":0.00008318118,"about_ca_topic_score_gemma":0.0019128231,"teacher_disagreement_score":0.9650277,"about_ca_system_score_codex":0.000028482447,"about_ca_system_score_gemma":0.000043138294,"threshold_uncertainty_score":0.406283},"labels":[],"label_agreement":null},{"id":"W3120202655","doi":"10.1007/978-981-15-9663-6_4","title":"Distribution of Number of Levels in an $$[\\varvec{s}]$$-Specified Random Permutation","year":2020,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Permutation (music); Random permutation; Mathematics; Combinatorics; Distribution (mathematics); Markov chain; Eulerian path; Discrete mathematics; Statistics; Applied mathematics; Mathematical analysis; Physics; Lagrangian; Symmetric group","score_opus":0.04807973252303337,"score_gpt":0.3150184780485199,"score_spread":0.2669387455254865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120202655","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023823706,0.000099262936,0.98303443,0.000044352782,0.00024897553,0.00031867714,0.0008499944,0.0000252208,0.015140864],"genre_scores_gemma":[0.16271383,0.0001290467,0.83426946,0.00005272214,0.0000947448,0.000011351661,0.0002477585,0.000049874816,0.0024312004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976683,0.00012706537,0.001008439,0.0005400431,0.0004338477,0.00022226216],"domain_scores_gemma":[0.9982732,0.00031199807,0.000550155,0.00054974883,0.00022095749,0.00009397125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005917857,0.00029955042,0.0007943651,0.00012427327,0.000020743933,0.000036254503,0.00056023407,0.0002787663,0.00005487258],"category_scores_gemma":[0.0001641243,0.00032943,0.000082855884,0.00014827505,0.00013009305,0.00019797828,0.00017151001,0.00043598586,0.000007844558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000754767,0.000037912687,0.00013857918,0.0001725861,0.000014007814,0.000055347457,0.0005941384,0.000045783738,0.00009074468,0.95340097,0.00009198397,0.045282483],"study_design_scores_gemma":[0.0020843584,0.0001411644,0.012813167,0.0005088006,0.00003707344,0.00000998736,0.000006774629,0.019056313,0.0006655291,0.9618758,0.002204111,0.0005969052],"about_ca_topic_score_codex":0.00005492294,"about_ca_topic_score_gemma":0.000077840996,"teacher_disagreement_score":0.16247559,"about_ca_system_score_codex":0.00011892904,"about_ca_system_score_gemma":0.00017858448,"threshold_uncertainty_score":0.9999158},"labels":[],"label_agreement":null},{"id":"W3121531903","doi":"10.1007/978-3-030-45240-7_8","title":"Online Variational Learning Using Finite Generalized Inverted Dirichlet Mixture Model with Feature Selection on Medical Data Sets","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Feature selection; Artificial intelligence; Pattern recognition (psychology); Feature extraction; Data mining; Model selection; Mixture model; Segmentation; Machine learning","score_opus":0.07059102098049724,"score_gpt":0.3025531981051855,"score_spread":0.23196217712468825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121531903","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025771085,0.00010841529,0.9706949,0.005878888,0.00017548214,0.00025170032,0.0001292819,0.00031319045,0.022445546],"genre_scores_gemma":[0.00009969836,0.00007512331,0.9247714,0.007208107,0.00051403174,0.0000029372063,0.0017401098,0.00008040907,0.06550818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963156,0.00017391148,0.00037304562,0.0014453761,0.0013652798,0.00032678602],"domain_scores_gemma":[0.99800366,0.0002035004,0.00032480864,0.00089732994,0.00022008902,0.00035059545],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046724375,0.0005935098,0.0006270955,0.00021702526,0.00023586354,0.00018789344,0.0015795936,0.0009369894,0.0001596517],"category_scores_gemma":[0.00016192306,0.0004489401,0.00010144928,0.0002220784,0.000051793308,0.0003981397,0.0007483707,0.0021545887,0.000012474147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012163498,0.0000923184,0.000004031543,0.00006397488,0.00038365403,0.00013088003,0.00018620201,0.03817471,0.00009055967,0.9067876,0.022324119,0.031640355],"study_design_scores_gemma":[0.0006114947,0.00011427166,0.0000025878117,0.0001896936,0.00008740047,0.00007992612,4.5457617e-7,0.9451154,0.000007377527,0.03561869,0.017640749,0.0005319449],"about_ca_topic_score_codex":0.000021226417,"about_ca_topic_score_gemma":0.00006836998,"teacher_disagreement_score":0.9069407,"about_ca_system_score_codex":0.000097007556,"about_ca_system_score_gemma":0.0010252605,"threshold_uncertainty_score":0.9997962},"labels":[],"label_agreement":null},{"id":"W3121859486","doi":"10.2139/ssrn.691887","title":"Bayesian clustering of many GARCH models","year":2003,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Autoregressive conditional heteroskedasticity; Series (stratigraphy); Cluster analysis; Bayesian probability; Mathematics; Bayesian inference; Inference; Cluster (spacecraft); Component (thermodynamics); A priori and a posteriori; Econometrics; Statistics; Computer science; Artificial intelligence; Volatility (finance)","score_opus":0.014550749281039131,"score_gpt":0.256552905204646,"score_spread":0.24200215592360688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121859486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073850853,0.0020005764,0.98648506,0.00024665846,0.00021195342,0.000077086916,2.8204624e-7,0.000029958535,0.010209919],"genre_scores_gemma":[0.66777396,0.0008641236,0.33036909,0.00007878368,0.000055558532,0.000002247094,1.1395827e-7,0.0000147771825,0.00084133877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99701554,0.00027335942,0.00035215274,0.00026038196,0.00030689882,0.0017916433],"domain_scores_gemma":[0.9991861,0.000044965807,0.0001638599,0.00039722925,0.00009079591,0.00011703251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002967685,0.00015676273,0.00023688468,0.00016026356,0.00013845052,0.00007079643,0.0007790272,0.000078308745,0.000009718815],"category_scores_gemma":[0.00002989184,0.0001367144,0.00014363613,0.0002837159,0.000031411735,0.00048483742,0.00007990935,0.0011419385,0.000003494891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047565454,0.000027124026,0.000018244355,0.0000055179016,0.0000345613,0.000003831004,0.00018860366,0.00055063935,0.00042114835,0.92480224,0.000016095848,0.07392726],"study_design_scores_gemma":[0.00031676728,0.0001361559,0.0000070977794,0.000016932112,0.000008084366,0.0007889914,0.00005016347,0.12513626,0.00066061347,0.87249345,0.0002472999,0.00013821847],"about_ca_topic_score_codex":0.0000130533035,"about_ca_topic_score_gemma":0.000046484354,"teacher_disagreement_score":0.66703546,"about_ca_system_score_codex":0.00024186523,"about_ca_system_score_gemma":0.0012714838,"threshold_uncertainty_score":0.55750513},"labels":[],"label_agreement":null},{"id":"W3122734306","doi":"","title":"Bayesian clustering of many GARCH models","year":2003,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Center for Interuniversity Research and Analysis on Organizations; HEC Montréal","funders":"","keywords":"Autoregressive conditional heteroskedasticity; Series (stratigraphy); Cluster analysis; Bayesian probability; Component (thermodynamics); Bayesian inference; Cluster (spacecraft); Mathematics; Inference; A priori and a posteriori; Econometrics; Statistics; Computer science; Artificial intelligence; Volatility (finance)","score_opus":0.0505580784234177,"score_gpt":0.3310044258445991,"score_spread":0.2804463474211814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122734306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018742861,0.00024680025,0.8201633,0.00023526604,0.00049641845,0.0005943009,0.000013692859,0.00004457674,0.17633133],"genre_scores_gemma":[0.23993644,0.005460627,0.7517114,0.00013022158,0.00013086895,0.00017689202,0.000008061869,0.000082693325,0.0023627381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99533087,0.0008393558,0.0009395825,0.0014264885,0.00042424316,0.001039468],"domain_scores_gemma":[0.99633634,0.00042006202,0.00026723373,0.002526529,0.0001741341,0.000275716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0042799045,0.00039289767,0.00082824804,0.0007831779,0.00011358289,0.00022067995,0.002697879,0.00058168435,0.000025198175],"category_scores_gemma":[0.0001390714,0.00042807194,0.00027391026,0.00026005396,0.00023541835,0.00028372262,0.0034413014,0.0019972,0.0000029803393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034362645,0.00017222669,0.00013426373,0.00048433006,0.00008793312,0.00005980285,0.0010909063,0.06899152,0.00020987175,0.07674037,0.00006302188,0.8519314],"study_design_scores_gemma":[0.00030312486,0.00005521616,0.000092761715,0.00022897018,0.0000036140993,0.000017474584,0.000030694806,0.82077694,0.00029537757,0.17683318,0.000982408,0.0003802086],"about_ca_topic_score_codex":0.00007376233,"about_ca_topic_score_gemma":0.000071734365,"teacher_disagreement_score":0.8515512,"about_ca_system_score_codex":0.0004987396,"about_ca_system_score_gemma":0.0007868218,"threshold_uncertainty_score":0.99981713},"labels":[],"label_agreement":null},{"id":"W3122760863","doi":"","title":"Bayesian semiparametric multivariate GARCH modeling","year":2012,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Autoregressive conditional heteroskedasticity; Markov chain Monte Carlo; Econometrics; Bayesian probability; Dirichlet process; Dirichlet distribution; Multivariate normal distribution; Semiparametric model; Mathematics; Parametric statistics; Conjugate prior; Computer science; Posterior probability; Statistics; Nonparametric statistics","score_opus":0.06581751059239543,"score_gpt":0.35540531232083344,"score_spread":0.289587801728438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122760863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007860708,0.000686751,0.92851657,0.00037250944,0.0011007687,0.00090013887,0.000015770629,0.00014551595,0.060401257],"genre_scores_gemma":[0.5366944,0.0027182489,0.4589847,0.00009747288,0.00039122422,0.00021269187,0.0000135298105,0.00007562642,0.0008120995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936874,0.0011395765,0.00096194877,0.001826693,0.00053546525,0.0018489094],"domain_scores_gemma":[0.99525267,0.00088071305,0.00022574358,0.0028633776,0.00020627654,0.00057119556],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0069930865,0.0005416947,0.0008662566,0.0015817307,0.00023963719,0.0005392383,0.0033388184,0.0008866959,0.000031999312],"category_scores_gemma":[0.00059054955,0.0005670756,0.00031464893,0.00061691506,0.00014801635,0.00041840228,0.005017474,0.0037384941,0.00002471436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024244668,0.00020015956,0.00033469836,0.00015437805,0.00007693324,0.000034118006,0.0009783036,0.041881878,0.00013018874,0.014089248,0.000022192326,0.94207364],"study_design_scores_gemma":[0.0003509802,0.000028796723,0.00016122546,0.00015272702,0.000006625322,0.000015832684,0.00002612884,0.9474206,0.00012497665,0.050014716,0.001115299,0.0005821248],"about_ca_topic_score_codex":0.00023299908,"about_ca_topic_score_gemma":0.00004216885,"teacher_disagreement_score":0.94149154,"about_ca_system_score_codex":0.00095756137,"about_ca_system_score_gemma":0.000835226,"threshold_uncertainty_score":0.9996781},"labels":[],"label_agreement":null},{"id":"W3122868537","doi":"10.2139/ssrn.3649934","title":"Bayesian Nonparametric Forecast Pooling","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pooling; Bayesian probability; Nonparametric statistics; Econometrics; Computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.015392017927252605,"score_gpt":0.24734198232578591,"score_spread":0.2319499643985333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122868537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011975218,0.002169504,0.988001,0.0061440663,0.00021861689,0.000087116015,4.2977723e-7,0.00009707544,0.0020846569],"genre_scores_gemma":[0.7706465,0.00072862615,0.22653948,0.0014838488,0.0003941381,0.0000022381769,3.93562e-7,0.000019537645,0.0001852083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966811,0.00015038764,0.00030554392,0.00035651136,0.00032297702,0.0021835137],"domain_scores_gemma":[0.9991511,0.00006681688,0.00015321885,0.00025604304,0.00007595383,0.0002968702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014707175,0.00018482037,0.00023545981,0.0001607268,0.00022367133,0.00023600082,0.001135072,0.00008360278,0.000011654542],"category_scores_gemma":[0.00013356541,0.0001586123,0.00017220643,0.0009785357,0.0000213027,0.0005169554,0.00013425536,0.0019271491,0.00004039683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009498702,0.000017500393,0.00006527267,0.000003600992,0.00004482405,0.000014791863,0.00026028254,0.00004861417,0.00021687677,0.5702427,0.00014591086,0.4289301],"study_design_scores_gemma":[0.00056002085,0.00046403988,0.000051979358,0.000011217155,0.000019852889,0.0009588367,0.00007551663,0.123702936,0.0003119308,0.8709826,0.0025525608,0.00030851417],"about_ca_topic_score_codex":0.00000821485,"about_ca_topic_score_gemma":0.000013635841,"teacher_disagreement_score":0.769449,"about_ca_system_score_codex":0.00026221757,"about_ca_system_score_gemma":0.001261589,"threshold_uncertainty_score":0.8372611},"labels":[],"label_agreement":null},{"id":"W3123121008","doi":"10.1007/978-3-030-45240-7_9","title":"Entropy-Based Variational Inference for Semi-Bounded Data Clustering in Medical Applications","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Mixture model; Machine learning; Inference; Artificial intelligence; Entropy (arrow of time); Data science","score_opus":0.06799185254980937,"score_gpt":0.3319142062182402,"score_spread":0.2639223536684308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123121008","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.059963e-8,0.00005941094,0.9272911,0.0051310207,0.00013598875,0.0006478966,0.00011987539,0.00010865833,0.06650603],"genre_scores_gemma":[0.0001667655,0.000021487287,0.9856675,0.0031356185,0.00031450883,0.00014131605,0.00052952394,0.000025393358,0.00999788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978437,0.00003327188,0.00046439213,0.00092554133,0.0005174415,0.00021564063],"domain_scores_gemma":[0.99768925,0.0006400777,0.0001565844,0.0012233873,0.00008709586,0.00020358658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060085993,0.0002511237,0.00034817928,0.0001264048,0.00007218583,0.00014453426,0.0025816981,0.00034410664,0.00022114557],"category_scores_gemma":[0.00013275965,0.00023706873,0.00007374854,0.00007647076,0.000046712856,0.00020792075,0.00094146497,0.00037585184,0.000030356021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045987795,0.000014140128,0.0000010203139,0.000047475143,0.000014284325,0.000004646328,0.000015214054,0.00002065306,0.000005877996,0.95366263,0.00077951374,0.045429967],"study_design_scores_gemma":[0.00026490315,0.000014300864,0.0000020858633,0.00004767946,0.000008354194,0.0000023412183,1.4182355e-7,0.54376566,0.000003602258,0.3433979,0.11232064,0.00017241106],"about_ca_topic_score_codex":0.0000111560075,"about_ca_topic_score_gemma":0.00008937991,"teacher_disagreement_score":0.6102647,"about_ca_system_score_codex":0.00006417323,"about_ca_system_score_gemma":0.0009803611,"threshold_uncertainty_score":0.9667382},"labels":[],"label_agreement":null},{"id":"W3123187555","doi":"10.5539/ijsp.v10n2p28","title":"Application of Gibbs Sampling in Modelling the Utilization Rate of Raw Materials for Drug Coating","year":2021,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Gibbs sampling; Computer science; Sampling (signal processing); Cluster analysis; Bayesian probability; Feature selection; Data mining; Covariate; Statistics; Machine learning; Mathematical optimization; Artificial intelligence; Mathematics; Filter (signal processing)","score_opus":0.05990076293663546,"score_gpt":0.3397228682958272,"score_spread":0.2798221053591917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123187555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033591542,0.00018686002,0.9654729,0.00038871964,0.00017402273,0.00011058513,0.00006116698,0.0000012613398,0.000012973478],"genre_scores_gemma":[0.49860257,0.00009819249,0.5012529,0.000016834585,0.000021214442,0.0000020640928,0.000003313273,0.0000016523078,0.0000012904654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895126,0.00014325726,0.0005698907,0.000104818246,0.0001756721,0.00005513214],"domain_scores_gemma":[0.9974184,0.0006407899,0.0005011382,0.00010262272,0.001319709,0.000017333008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024086398,0.000049439466,0.00015622773,0.000040679573,0.000021513815,0.000038650887,0.00022468517,0.000021125092,0.0000016059124],"category_scores_gemma":[0.0003876546,0.00003757022,0.000026387472,0.000064788226,0.000035692025,0.000118773845,0.000054288925,0.0000515299,2.0144066e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054155767,0.00006669353,0.00021943121,0.00011413959,0.000022456446,0.0000010629363,0.0010566908,0.015022087,0.018347507,0.87214255,0.000010554559,0.09294268],"study_design_scores_gemma":[0.00023176255,0.000018213002,0.00061564735,0.00005846456,0.000006798106,0.000007908963,0.00001694948,0.2681071,0.03247077,0.69837713,0.000056713947,0.000032588414],"about_ca_topic_score_codex":0.000031677322,"about_ca_topic_score_gemma":0.000013686316,"teacher_disagreement_score":0.46501103,"about_ca_system_score_codex":0.000023853298,"about_ca_system_score_gemma":0.00010834014,"threshold_uncertainty_score":0.1532069},"labels":[],"label_agreement":null},{"id":"W3123194690","doi":"10.1017/asb.2015.15","title":"FITTING MIXTURES OF ERLANGS TO CENSORED AND TRUNCATED DATA USING THE EM ALGORITHM","year":2015,"lang":"en","type":"article","venue":"Astin Bulletin","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Algorithm; Class (philosophy); Computer science; Expectation–maximization algorithm; Mathematics; Applied mathematics; Maximum likelihood; Statistics; Artificial intelligence","score_opus":0.07359289273314527,"score_gpt":0.310641159870224,"score_spread":0.23704826713707872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123194690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009783929,0.00043196493,0.9858632,0.003303529,0.00016397038,0.0001504154,0.000016164471,0.000043472624,0.00024332516],"genre_scores_gemma":[0.026477348,0.000002626951,0.9725821,0.00066601083,0.00010534405,0.0000023476484,0.000004064996,0.000010514665,0.00014963678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874866,0.00020227737,0.00021995489,0.00038100232,0.00022326954,0.00022486033],"domain_scores_gemma":[0.9986189,0.0001930003,0.00010116963,0.0008442804,0.00010969233,0.00013293914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013033786,0.00012253076,0.00018305474,0.00004902032,0.00008007621,0.000098380144,0.0010559106,0.00005060056,0.00000807242],"category_scores_gemma":[0.00039865845,0.00008457429,0.000020092113,0.00023644311,0.00004343572,0.00006674433,0.0008562254,0.00011861455,0.0000074770865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002014194,0.000043033546,0.0002000754,0.000025051831,0.000037698373,0.00002358181,0.005499812,0.00009393124,0.003557954,0.0043709385,0.06217579,0.923952],"study_design_scores_gemma":[0.0019795415,0.00034723486,0.0025305953,0.00031021383,0.000097893135,0.00032509028,0.0008739962,0.82396924,0.012480926,0.012051644,0.14399958,0.0010340082],"about_ca_topic_score_codex":0.0001693538,"about_ca_topic_score_gemma":0.0000032503635,"teacher_disagreement_score":0.92291796,"about_ca_system_score_codex":0.000009727251,"about_ca_system_score_gemma":0.000049105594,"threshold_uncertainty_score":0.34488395},"labels":[],"label_agreement":null},{"id":"W3123649785","doi":"10.2139/ssrn.3413016","title":"A Multivariate Evolutionary Generalised Linear Model Framework with Adaptive Estimation for Claims Reserving","year":2019,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"University of New South Wales","keywords":"Computer science; Multivariate statistics; Dependency (UML); Set (abstract data type); Dimension (graph theory); Process (computing); Econometrics; Estimation; Mathematical optimization; Data mining; Machine learning; Artificial intelligence; Mathematics","score_opus":0.029767033783225164,"score_gpt":0.30404537748344324,"score_spread":0.2742783437002181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123649785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010522923,0.0017206393,0.99412334,0.0014293143,0.00051857455,0.0009146514,0.000018885823,0.00010820732,0.00011411652],"genre_scores_gemma":[0.11029045,0.0004535612,0.88779694,0.00018873859,0.00049336936,0.000091107846,0.000018848925,0.000059938728,0.0006070159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956009,0.00031181885,0.00051459926,0.0008581181,0.0005423266,0.0021722822],"domain_scores_gemma":[0.99751604,0.00022639758,0.0006526138,0.00094313995,0.00051341945,0.00014836832],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026566435,0.00046518794,0.00054054544,0.0002547477,0.00035784012,0.00022448452,0.0016799533,0.00056270766,0.0000018094829],"category_scores_gemma":[0.00011019611,0.00038040057,0.00029422756,0.00022295144,0.00003969585,0.0005389962,0.0006204182,0.005251337,0.0000051853017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001693849,0.000041182135,0.0000048977677,0.000031021627,0.0001940533,0.0000018278575,0.0003491235,0.44661924,0.0000449395,0.53934985,0.00006344868,0.013131045],"study_design_scores_gemma":[0.00042459826,0.00019464378,0.000007930905,0.00019315575,0.000038986826,0.00006311212,0.000013310585,0.505437,0.00001917176,0.49334845,0.000011794926,0.00024784764],"about_ca_topic_score_codex":0.0000547424,"about_ca_topic_score_gemma":0.00003661969,"teacher_disagreement_score":0.10923816,"about_ca_system_score_codex":0.001390214,"about_ca_system_score_gemma":0.007771569,"threshold_uncertainty_score":0.9998648},"labels":[],"label_agreement":null},{"id":"W3124740106","doi":"","title":"Flexible clustering of high-dimensional data via mixtures of joint generalized hyperbolic distributions: Mixtures of joint generalized hyperbolic distributions","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"","keywords":"Joint (building); Hyperbolic function; Cluster analysis; Mathematics; Mixture model; Joint probability distribution; Mathematical analysis; Applied mathematics; Statistics; Structural engineering; Engineering","score_opus":0.09854218865339533,"score_gpt":0.2351299211151132,"score_spread":0.13658773246171785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124740106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26671842,0.00028175386,0.73165745,0.00013864668,0.0003064734,0.00021361929,0.00048475756,0.00007251294,0.00012638363],"genre_scores_gemma":[0.83071876,0.0001090134,0.1686333,0.00006753704,0.00011244607,0.0000013781504,0.00018954185,0.000017166903,0.00015084085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720883,0.00040247448,0.000695834,0.00094735704,0.00024695825,0.00049854774],"domain_scores_gemma":[0.9963372,0.00010888281,0.0005756328,0.002198819,0.0005496849,0.0002297967],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006326467,0.00035353898,0.00081511284,0.00030354416,0.0002554778,0.000032555792,0.0017076391,0.00020807743,0.000075784934],"category_scores_gemma":[0.00013140206,0.0003416856,0.00027339763,0.0012037477,0.0006065482,0.0005584366,0.0016291189,0.00021643945,0.000008493689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020326464,0.0006173191,0.00025422755,0.00015623009,0.00036870973,0.00004128649,0.0002185893,0.0045783687,0.32971734,0.65755266,0.002283047,0.0040089744],"study_design_scores_gemma":[0.0030171925,0.00034682255,0.0036423998,0.00020718544,0.00031255538,0.000057189114,0.00001356415,0.43850133,0.43335587,0.11910086,0.000701157,0.0007438945],"about_ca_topic_score_codex":0.001152379,"about_ca_topic_score_gemma":0.000067802626,"teacher_disagreement_score":0.56400037,"about_ca_system_score_codex":0.000086630804,"about_ca_system_score_gemma":0.00021834146,"threshold_uncertainty_score":0.9999035},"labels":[],"label_agreement":null},{"id":"W3125744459","doi":"10.48550/arxiv.1703.08882","title":"Finite Mixtures of Skewed Matrix Variate Distributions","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random variate; Cluster analysis; Expectation–maximization algorithm; Mathematics; Data Matrix; Statistics; Matrix (chemical analysis); Multivariate statistics; Multivariate normal distribution; Applied mathematics; Computer science; Random variable; Maximum likelihood; Materials science","score_opus":0.0684987053061779,"score_gpt":0.23357934297080887,"score_spread":0.165080637664631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125744459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003450807,0.0001515171,0.99036497,0.00017357749,0.0007877588,0.00022446217,0.0001707067,0.00013320443,0.0045429706],"genre_scores_gemma":[0.89575845,0.00020063302,0.101326495,0.000023739069,0.00007515757,9.031249e-7,0.000030862255,0.000013290782,0.0025704831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810624,0.00025458474,0.0002516861,0.0009395648,0.000099017874,0.00034891415],"domain_scores_gemma":[0.99641126,0.00018971735,0.00054363755,0.0024460976,0.00023476125,0.00017454814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045506543,0.00031871875,0.0004919762,0.00019931475,0.00027006227,0.0001521136,0.003052442,0.0004009474,0.000024659987],"category_scores_gemma":[0.00013230131,0.00034049794,0.00036176728,0.00025428235,0.00017389639,0.000301793,0.0024203607,0.0005767384,0.00002940296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017343942,0.00008843544,0.00017701718,0.00009425755,0.00011938028,0.00015227194,0.00012967255,0.0084006665,0.00013727663,0.9884256,0.000525799,0.001732237],"study_design_scores_gemma":[0.00038529275,0.0000353001,0.00075530977,0.00012653702,0.0001225043,0.000003880023,0.0000022790207,0.27081725,0.0008136456,0.72548586,0.0010260904,0.00042603575],"about_ca_topic_score_codex":0.00020255742,"about_ca_topic_score_gemma":0.000013276749,"teacher_disagreement_score":0.89230764,"about_ca_system_score_codex":0.000078607074,"about_ca_system_score_gemma":0.0002843547,"threshold_uncertainty_score":0.9999047},"labels":[],"label_agreement":null},{"id":"W3125921778","doi":"10.5539/ijsp.v10n2p18","title":"Estimation of Receiver Operating Characteristic Surface Using Mixtures of Finite Polya Trees (MFPT)","year":2021,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nonparametric statistics; Prior probability; Parametric statistics; Mathematics; Receiver operating characteristic; Parametric model; Inference; Bayesian probability; Computer science; Statistics; Artificial intelligence; Algorithm","score_opus":0.026339085508558013,"score_gpt":0.30895245745958594,"score_spread":0.2826133719510279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125921778","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24303658,0.00017147644,0.75621396,0.00015773215,0.00026470318,0.000032569067,0.0000887748,0.0000017763593,0.00003242764],"genre_scores_gemma":[0.49012876,0.000038859544,0.5097818,0.000019257677,0.000020993106,1.088013e-7,0.0000025806617,0.0000019295067,0.0000057521775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871725,0.00016398862,0.00059101294,0.00012993127,0.00032387167,0.00007393869],"domain_scores_gemma":[0.9977376,0.00046079408,0.0005418816,0.00012353045,0.00108818,0.000048018155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006877177,0.00008043116,0.00023371863,0.000049867118,0.000029891133,0.000067109264,0.0002492981,0.00003752676,0.00001695576],"category_scores_gemma":[0.0008046771,0.00006908752,0.000047002064,0.0000856894,0.00006908461,0.00023866883,0.00009142385,0.00011162722,9.29882e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013833569,0.00051190174,0.008939298,0.00033638428,0.00037460285,0.00014236479,0.003438707,0.02856367,0.10086195,0.24373114,0.00009571248,0.6128659],"study_design_scores_gemma":[0.000542128,0.00015740148,0.021442765,0.00029099733,0.000042698346,0.00017933467,0.000016624284,0.7029956,0.03202223,0.2421285,0.000037126425,0.0001445878],"about_ca_topic_score_codex":0.000028993316,"about_ca_topic_score_gemma":0.0000047552235,"teacher_disagreement_score":0.6744319,"about_ca_system_score_codex":0.000030466612,"about_ca_system_score_gemma":0.00019850678,"threshold_uncertainty_score":0.2817307},"labels":[],"label_agreement":null},{"id":"W3126142129","doi":"","title":"Further results on the limiting distribution of GMM sample moment conditions","year":2010,"lang":"en","type":"preprint","venue":"Econstor (Econstor)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Asymptotic distribution; Moment (physics); Mathematics; Distribution (mathematics); V-statistic; Sample (material); Limiting; Generalized method of moments; Degeneracy (biology); Applied mathematics; Asymptotic analysis; Inference; Statistical inference; Sampling distribution; Statistical physics; Statistics; Mathematical analysis; Physics; Computer science; Panel data; Classical mechanics","score_opus":0.02785633383890521,"score_gpt":0.27321108950783374,"score_spread":0.24535475566892853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126142129","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20156242,0.00014495368,0.77945024,0.0049294787,0.003298517,0.000691426,0.0021828802,0.00015909037,0.0075809783],"genre_scores_gemma":[0.9046899,0.000054567885,0.09333078,0.000536589,0.0005169306,0.00018850346,0.000322847,0.000037682174,0.00032216404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99654305,0.0004719127,0.0009954137,0.0010596911,0.00040302685,0.0005268885],"domain_scores_gemma":[0.9943865,0.0018308397,0.0010213528,0.0023185879,0.00024549474,0.00019724626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019695195,0.0004978162,0.00064722047,0.00017356822,0.0003479227,0.00020565712,0.0016773271,0.0005508777,0.00014774797],"category_scores_gemma":[0.0006689296,0.00039778647,0.00042745844,0.00020488676,0.0004523987,0.00018129605,0.0009296575,0.0015952329,0.00006981964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043113007,0.0003671926,0.0056517376,0.00010330609,0.00025351185,0.000014899554,0.0018520658,0.00022917907,0.00082034996,0.96001494,0.01631029,0.014339437],"study_design_scores_gemma":[0.0036918395,0.0007560119,0.07219872,0.0022357379,0.00038308956,0.00019363573,0.00032670057,0.046340104,0.024417281,0.76896304,0.07625307,0.004240763],"about_ca_topic_score_codex":0.00012267656,"about_ca_topic_score_gemma":0.00006889371,"teacher_disagreement_score":0.7031275,"about_ca_system_score_codex":0.00022455995,"about_ca_system_score_gemma":0.00054406846,"threshold_uncertainty_score":0.9998474},"labels":[],"label_agreement":null},{"id":"W3127132637","doi":"10.1016/b978-0-12-822314-7.00012-2","title":"Variational learning of finite shifted scaled Dirichlet mixture models","year":2021,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Cluster analysis; Inference; Bayesian inference; Computer science; Artificial intelligence; Bayesian probability; Machine learning; Applied mathematics; Mathematics; Algorithm","score_opus":0.018615331616866446,"score_gpt":0.240790068934546,"score_spread":0.22217473731767956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127132637","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010541556,0.0010425429,0.50613713,0.00008872942,0.00023280054,0.0001649703,0.000015549998,0.00006574442,0.49225146],"genre_scores_gemma":[0.00026149844,0.00007665638,0.35381603,0.00032188644,0.00020691515,0.000015921853,0.00003945559,0.000054092627,0.6452075],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970218,0.00021497076,0.000742941,0.0009128056,0.0007305387,0.000376957],"domain_scores_gemma":[0.99741185,0.00038988754,0.00058388617,0.0010130827,0.00042116822,0.00018014957],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006952099,0.0005417102,0.0009223452,0.0002569473,0.0001445721,0.00012961503,0.001023489,0.00063898176,0.0001368583],"category_scores_gemma":[0.000067661465,0.00051870354,0.0004683513,0.00006933256,0.0000976354,0.00018326374,0.0005646905,0.001069613,0.000020684369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004414382,0.000008340731,6.1899885e-7,0.000054693162,0.00009004865,0.000032043066,0.00029363297,0.000119702774,0.000032392913,0.4846959,0.00003949377,0.5146287],"study_design_scores_gemma":[0.00039132373,0.00006533584,0.000008166739,0.0006148775,0.00011010484,0.00002794994,0.0000014123814,0.056448482,0.00009962227,0.6619503,0.27958912,0.000693354],"about_ca_topic_score_codex":5.323052e-7,"about_ca_topic_score_gemma":0.0000024653946,"teacher_disagreement_score":0.5139353,"about_ca_system_score_codex":0.000058516784,"about_ca_system_score_gemma":0.00039877358,"threshold_uncertainty_score":0.9997265},"labels":[],"label_agreement":null},{"id":"W3127555970","doi":"10.1007/s00500-021-05598-4","title":"Bayesian inference for infinite asymmetric Gaussian mixture with feature selection","year":2021,"lang":"en","type":"article","venue":"Soft Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Inference; Feature selection; Bayesian probability; Gaussian process; Feature (linguistics); Computer science; Bayesian inference; Artificial intelligence; Gaussian; Selection (genetic algorithm); Pattern recognition (psychology); Mathematics; Machine learning; Algorithm; Physics","score_opus":0.013754023442699152,"score_gpt":0.27517391960899346,"score_spread":0.2614198961662943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127555970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049126707,0.00032789644,0.9942903,0.0015747865,0.0003625496,0.00023381971,0.0000028825339,0.0002957423,0.0024207584],"genre_scores_gemma":[0.33724424,0.0000038067933,0.6614245,0.0007105065,0.0002284563,0.0000070428814,0.000007764264,0.000018398121,0.0003552565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807274,0.0001633051,0.00023219537,0.00072551385,0.00027497392,0.000531286],"domain_scores_gemma":[0.9983008,0.0005368599,0.00016882547,0.00045546523,0.00037677557,0.0001613004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047085364,0.00026614362,0.00031230692,0.00020780388,0.00039319496,0.00039341362,0.0004916069,0.00018510807,0.000003857836],"category_scores_gemma":[0.00027762365,0.00022638707,0.00011071529,0.002086959,0.000029277255,0.00031804582,0.00019459677,0.00042591753,0.0000037735085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001821149,0.000084491316,0.0026797955,0.00013113518,0.00007692314,0.000057019144,0.0009535949,0.0009486903,0.0007686316,0.13537958,0.0017080547,0.8571939],"study_design_scores_gemma":[0.0013534361,0.00036879588,0.003961188,0.00031164134,0.000053818225,0.0004733155,0.000041294716,0.92462516,0.008200956,0.04448221,0.015168341,0.00095982914],"about_ca_topic_score_codex":0.0000072278413,"about_ca_topic_score_gemma":0.000023643732,"teacher_disagreement_score":0.9236765,"about_ca_system_score_codex":0.000052791376,"about_ca_system_score_gemma":0.00031180496,"threshold_uncertainty_score":0.9231797},"labels":[],"label_agreement":null},{"id":"W3128004291","doi":"10.1016/b978-0-12-804288-5.00014-3","title":"Statistical inference and a mixture model","year":2021,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Identifiability; Computer science; Inference; Statistical inference; Component (thermodynamics); Binary number; Mixture model; Statistical model; Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.021774537788943088,"score_gpt":0.27446295475440735,"score_spread":0.2526884169654643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128004291","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.0657503e-7,0.0010308917,0.50735503,0.00008902172,0.000101138015,0.00011639234,0.000024466872,0.00004715907,0.49123552],"genre_scores_gemma":[0.00007114547,0.00012814338,0.4478681,0.00062798796,0.00007064026,0.000010141105,0.000006925527,0.000027059228,0.55118984],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99802136,0.00005978109,0.00035437164,0.0008827518,0.00035316416,0.00032858484],"domain_scores_gemma":[0.998372,0.00018062328,0.00013609171,0.00091421476,0.00013459266,0.0002624767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027385892,0.00044608692,0.0006003213,0.000096982,0.00010407876,0.0002427821,0.0005893848,0.00043414405,0.000043360636],"category_scores_gemma":[0.00004029752,0.00040119555,0.000113574875,0.000015254141,0.00014158816,0.00009122475,0.0006363634,0.0007135374,0.000018957007],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.618896e-7,0.0000021343362,1.407308e-7,0.000032223048,0.000017023693,0.000057637924,0.00010382975,6.2242117e-7,0.000010151271,0.48010057,0.00009331229,0.5195814],"study_design_scores_gemma":[0.00013652524,0.00003243592,0.0000020334114,0.00024095664,0.000046526315,0.00005772304,4.5274996e-7,0.0177619,0.000019077486,0.7120157,0.26920527,0.00048140733],"about_ca_topic_score_codex":2.191686e-7,"about_ca_topic_score_gemma":0.000006296656,"teacher_disagreement_score":0.5191,"about_ca_system_score_codex":0.00003329672,"about_ca_system_score_gemma":0.00034134765,"threshold_uncertainty_score":0.999844},"labels":[],"label_agreement":null},{"id":"W3128717465","doi":"10.1007/978-3-030-64583-0_1","title":"Revisiting Clustering as Matrix Factorisation on the Stiefel Manifold","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Stiefel manifold; Cluster analysis; Estimator; Computer science; Context (archaeology); Rank (graph theory); Manifold (fluid mechanics); Applied mathematics; Factorization; Matrix decomposition; Matrix (chemical analysis); Algorithm; Mathematics; Artificial intelligence; Combinatorics; Eigenvalues and eigenvectors; Physics; Pure mathematics; Statistics","score_opus":0.03231176423547592,"score_gpt":0.28039685951657034,"score_spread":0.2480850952810944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128717465","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016032891,0.00024393963,0.9809572,0.007299592,0.001403119,0.0004481156,0.0000030970014,0.00017460983,0.009454294],"genre_scores_gemma":[0.12399265,0.00004709687,0.86599004,0.007716339,0.0016924746,0.000010765127,0.000002905993,0.000055198307,0.0004925051],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963215,0.000106435364,0.00050772895,0.00148463,0.0010475955,0.00053214026],"domain_scores_gemma":[0.9972098,0.00081621873,0.00034884032,0.0013219024,0.00013136472,0.00017189051],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013577841,0.00053774455,0.0004725311,0.0003401743,0.0003871456,0.00088211586,0.003299596,0.00027837692,0.000025939828],"category_scores_gemma":[0.00022457112,0.0003885549,0.00016347434,0.00048343767,0.00017770556,0.00041458034,0.0013481621,0.001210585,0.0000993426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005115145,0.000004990145,0.000003633039,0.000037249425,0.000008278856,0.00006387907,0.0008489971,0.0033727163,0.0001589378,0.3809169,0.000025483538,0.6145538],"study_design_scores_gemma":[0.00012814642,0.00014050084,0.00002459014,0.00055449846,0.000008630441,0.000053480715,2.863057e-7,0.57951576,0.00081236963,0.4164507,0.0017569877,0.0005540395],"about_ca_topic_score_codex":0.000014471962,"about_ca_topic_score_gemma":0.000005854718,"teacher_disagreement_score":0.6139998,"about_ca_system_score_codex":0.00024887818,"about_ca_system_score_gemma":0.00028921803,"threshold_uncertainty_score":0.99985665},"labels":[],"label_agreement":null},{"id":"W3129654956","doi":"10.52933/jdssv.v2i6.47","title":"Robust Model-Based Clustering","year":2022,"lang":"en","type":"article","venue":"Journal of Data Science Statistics and Visualisation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Defense; Universidad de Buenos Aires","keywords":"Cluster analysis; Estimator; Computer science; Mixture model; Robust statistics; Algorithm; Set (abstract data type); Monte Carlo method; Data mining; Class (philosophy); Multivariate statistics; Artificial intelligence; Machine learning; Mathematics; Statistics","score_opus":0.13285055889970954,"score_gpt":0.37598612300373296,"score_spread":0.24313556410402343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129654956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007960652,0.000042233474,0.99834377,0.00031338717,0.000271965,0.00004215673,0.00012870286,0.00000608245,0.000055612618],"genre_scores_gemma":[0.20797385,0.0000136399685,0.79173535,0.00022841517,0.000029574334,6.6448354e-7,0.000008667085,0.0000027808433,0.000007068791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860895,0.00009132096,0.00028491745,0.0002287075,0.00064032385,0.00014576138],"domain_scores_gemma":[0.99895906,0.00009453363,0.00030287984,0.00036883805,0.00017085322,0.00010380736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038162305,0.000062994324,0.0001099906,0.00021017069,0.00044877428,0.00026584652,0.0013305584,0.000010048462,0.0000066999905],"category_scores_gemma":[0.00015207085,0.000055640667,0.000011080128,0.000389204,0.00010428352,0.0017762389,0.0007163778,0.00014597343,1.5296597e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024926048,0.00011929463,0.000082199076,0.0000291364,0.000008829107,0.000030043057,0.0012749841,0.11961692,0.004091626,0.47007015,0.0027702674,0.40188164],"study_design_scores_gemma":[0.00019199851,0.00013623254,0.00011595195,0.000005754742,0.0000072379453,0.000044976456,0.000029711662,0.9799493,0.00006546614,0.019063352,0.00032018122,0.00006985855],"about_ca_topic_score_codex":0.000005169816,"about_ca_topic_score_gemma":0.0000019642741,"teacher_disagreement_score":0.86033237,"about_ca_system_score_codex":0.000054771746,"about_ca_system_score_gemma":0.00047936782,"threshold_uncertainty_score":0.34516543},"labels":[],"label_agreement":null},{"id":"W3129859778","doi":"10.1080/08982112.2020.1814959","title":"Using simulation to handle implicit likelihoods in a Bayesian analysis","year":2021,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Markov chain Monte Carlo; Bayesian probability; Computer science; Variable-order Bayesian network; Key (lock); Bayesian inference; Markov chain; Marginal likelihood; Econometrics; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.054413614561321016,"score_gpt":0.37417425237494345,"score_spread":0.3197606378136224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129859778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04640659,0.00008383939,0.95303345,0.00013303604,0.000099784775,0.00006542772,0.0000016602071,0.000079311474,0.00009691163],"genre_scores_gemma":[0.5141442,7.999104e-7,0.48571798,0.00009346064,0.000024310422,0.000002676153,0.0000011291897,0.0000049800756,0.00001051392],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879724,0.00011042374,0.00030732516,0.0003627023,0.00016582664,0.00025647104],"domain_scores_gemma":[0.99918664,0.00012992446,0.000034195644,0.00047785303,0.000057873593,0.000113512964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005489636,0.00011699291,0.00027268892,0.00029130626,0.000033072527,0.00011299118,0.00021488362,0.000062244966,0.000006726585],"category_scores_gemma":[0.00014820424,0.00013180208,0.00010808717,0.0022083158,0.0000025045472,0.00021001381,0.00012712566,0.000107743224,0.0000020928335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011573361,0.00002000507,0.0006375535,0.00001973311,0.000043657026,0.0000125547795,0.000699294,0.95162517,0.0151544,0.017646974,0.0000012900495,0.014138209],"study_design_scores_gemma":[0.00009568875,0.0000056332874,0.0063265236,0.000017761975,0.000019576251,0.0000016833244,0.000007218636,0.98917615,0.0025454422,0.0015195432,0.00011307519,0.00017171886],"about_ca_topic_score_codex":0.00010213532,"about_ca_topic_score_gemma":0.00005229172,"teacher_disagreement_score":0.4677376,"about_ca_system_score_codex":0.000079248966,"about_ca_system_score_gemma":0.000039868155,"threshold_uncertainty_score":0.53747326},"labels":[],"label_agreement":null},{"id":"W3130326228","doi":"10.1109/icdmw51313.2020.00045","title":"Temporally-Reweighted Dirichlet Process Mixture Anomaly Detector","year":2020,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Anomaly detection; Dirichlet process; Computer science; Streaming data; Naive Bayes classifier; Detector; Parametric statistics; Artificial intelligence; Process (computing); Data mining; Bayesian probability; Anomaly (physics); Algorithm; Pattern recognition (psychology); Mathematics; Support vector machine; Statistics","score_opus":0.0189801902305601,"score_gpt":0.2568452401752701,"score_spread":0.23786504994471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130326228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046501625,0.00017591812,0.9711435,0.008741299,0.00013521215,0.00019785992,0.000002309897,0.0005246689,0.014429083],"genre_scores_gemma":[0.47016758,0.000002936904,0.5233914,0.00584646,0.00014436133,0.00001210513,0.0000014151434,0.000012775057,0.00042095897],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849546,0.000092577364,0.00023300713,0.0005891365,0.00027261346,0.00031722613],"domain_scores_gemma":[0.99903625,0.000045382913,0.000076961696,0.00042572946,0.000108906585,0.00030675836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001675602,0.00020619875,0.00024147789,0.000048254802,0.00008780469,0.00016336403,0.0011010662,0.00011091391,0.00009108254],"category_scores_gemma":[0.000058843318,0.00015304395,0.00008715039,0.00071621523,0.000027054008,0.00045735334,0.00017666622,0.00019964979,0.00008278208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012436065,0.0003977587,0.0038955775,0.0005024526,0.00022013753,0.0006621997,0.012581468,0.00003362212,0.070345454,0.39249638,0.07002667,0.44871393],"study_design_scores_gemma":[0.0032957548,0.001370895,0.0039086053,0.00009769987,0.000078937606,0.00020294801,0.00008745831,0.49305427,0.23683403,0.1501289,0.10748756,0.0034529401],"about_ca_topic_score_codex":0.000009766954,"about_ca_topic_score_gemma":0.000003202086,"teacher_disagreement_score":0.49302065,"about_ca_system_score_codex":0.000011167465,"about_ca_system_score_gemma":0.00009420414,"threshold_uncertainty_score":0.62409514},"labels":[],"label_agreement":null},{"id":"W3130349901","doi":"10.1002/sta4.372","title":"Mode merging for the finite mixture of <i>t</i>‐distributions","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Component (thermodynamics); Expectation–maximization algorithm; Gaussian; Cluster (spacecraft); Mode (computer interface); Computer science; Population; Algorithm; Mathematics; Statistical physics; Artificial intelligence; Statistics; Maximum likelihood; Physics; Thermodynamics","score_opus":0.02012592673133263,"score_gpt":0.3013657857676358,"score_spread":0.28123985903630316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130349901","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000882869,0.0008922443,0.99431264,0.0035541032,0.00025375446,0.00008873676,0.00010785794,0.000022693936,0.0006796495],"genre_scores_gemma":[0.08129038,0.00006912494,0.91754633,0.0004263725,0.0000533151,0.00002121744,0.000013379226,0.0000052606115,0.000574593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994171,0.000051371266,0.000117472504,0.00016523636,0.000095085685,0.00015369907],"domain_scores_gemma":[0.99893504,0.00044604763,0.000043877095,0.00040958202,0.00013301827,0.000032405205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019774523,0.00006163146,0.00009784188,0.000013748357,0.00012407871,0.000038590948,0.000314213,0.000029783421,0.000007073312],"category_scores_gemma":[0.00010658455,0.00004239798,0.00008758706,0.00021793276,0.00002754397,0.00009039666,0.00009824104,0.00007162973,0.0000011575156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034848956,0.000026812855,0.00000850529,0.000023087126,0.000029032266,0.000004179497,0.00071024563,0.00032684687,0.005461265,0.8712971,0.0063914335,0.115718],"study_design_scores_gemma":[0.0003995155,0.000036538568,0.00007652137,0.00003196683,0.00003763871,0.000013052736,0.000054710315,0.32714427,0.080735676,0.47688213,0.114405476,0.00018250501],"about_ca_topic_score_codex":0.000007170155,"about_ca_topic_score_gemma":0.000010838035,"teacher_disagreement_score":0.394415,"about_ca_system_score_codex":0.000008397519,"about_ca_system_score_gemma":0.00008842053,"threshold_uncertainty_score":0.17289394},"labels":[],"label_agreement":null},{"id":"W3134525918","doi":"","title":"Appraisal of models for the study of disease progression in psoriatic arthritis.","year":2000,"lang":"en","type":"dissertation","venue":"UCL Discovery (University College London)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Covariate; Goodness of fit; Statistics; Logistic regression; Negative binomial distribution; Mathematics; Econometrics; Regression analysis; Test statistic; Statistic; Binomial regression; Statistical hypothesis testing; Poisson distribution","score_opus":0.012528766711734623,"score_gpt":0.26605533574780926,"score_spread":0.2535265690360746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134525918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36542436,0.0013129218,0.6279154,0.00011178791,0.00073973654,0.0030294273,0.00051266875,0.000034487344,0.0009192332],"genre_scores_gemma":[0.9805757,0.0003616761,0.015264592,0.000011776966,0.000036003465,0.000026839638,0.00007929988,0.000023677112,0.0036204306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805325,0.00025859117,0.00036906142,0.00057143526,0.00047848906,0.00026916675],"domain_scores_gemma":[0.9981745,0.00043601764,0.00040811446,0.00076894276,0.00012423756,0.00008822016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034557958,0.0002770889,0.0006004709,0.00037636154,0.00017620985,0.00003692986,0.0012752728,0.0001572472,0.0000072292755],"category_scores_gemma":[0.00003447115,0.00024420425,0.000254571,0.0007627207,0.000054329783,0.0011537339,0.00013458241,0.00023023374,6.373135e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011379009,0.0058932877,0.000269689,0.0013835088,0.00048718328,0.00025531137,0.023053149,0.005957132,0.00007977562,0.5769716,0.0018136763,0.37245667],"study_design_scores_gemma":[0.027434697,0.003861088,0.034020513,0.004243782,0.0013483607,0.000007154713,0.026264854,0.7876971,0.00034929835,0.11047479,0.0015987213,0.0026996904],"about_ca_topic_score_codex":0.00014791047,"about_ca_topic_score_gemma":0.0009106078,"teacher_disagreement_score":0.78173995,"about_ca_system_score_codex":0.000056490164,"about_ca_system_score_gemma":0.00046487406,"threshold_uncertainty_score":0.995836},"labels":[],"label_agreement":null},{"id":"W3134530083","doi":"","title":"Impact of cluster sampling on scale psychometrics: simulation study and application to mental health survey","year":2018,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Cluster (spacecraft); Sampling (signal processing); Psychometrics; Mental health; Cluster sampling; Psychology; Applied psychology; Clinical psychology; Computer science; Medicine; Geography; Environmental health; Psychiatry; Cartography; Population","score_opus":0.03703284039205517,"score_gpt":0.33834531872965395,"score_spread":0.3013124783375988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134530083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46501952,0.000018638686,0.534191,0.000050546514,0.00009898648,0.0005036241,0.00002981345,0.000013655658,0.000074211646],"genre_scores_gemma":[0.90831983,0.000022265747,0.09139125,0.000021839553,0.000025168194,4.875105e-7,0.00011849347,0.000012521434,0.00008816894],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986484,0.0002370553,0.00015301745,0.00047038024,0.00032842997,0.00016271061],"domain_scores_gemma":[0.9986826,0.00012873599,0.0003955732,0.0004484705,0.00022635199,0.000118272066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086327567,0.00017183847,0.0003664461,0.00061170006,0.00017979492,0.000029192277,0.0004390293,0.00011507713,0.0000010678683],"category_scores_gemma":[0.000023755685,0.0001958859,0.00008230523,0.00074994436,0.00002228229,0.00017924802,0.00009479189,0.00011894881,0.0000052495507],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020826783,0.0024245838,0.25521275,0.00038806567,0.00044681347,0.000001392042,0.033401124,0.0034209534,0.0005167606,0.0004425588,0.0045748185,0.69708747],"study_design_scores_gemma":[0.00050065946,0.0012695829,0.97754085,0.00006735086,0.000014099105,2.62785e-7,0.0010587184,0.01918047,0.000011556105,0.00014128315,0.000051453826,0.00016369439],"about_ca_topic_score_codex":0.0046253586,"about_ca_topic_score_gemma":0.1284489,"teacher_disagreement_score":0.7223281,"about_ca_system_score_codex":0.0001559074,"about_ca_system_score_gemma":0.00007372696,"threshold_uncertainty_score":0.8874546},"labels":[],"label_agreement":null},{"id":"W3134670936","doi":"10.1049/ipr2.12154","title":"Online variational inference on finite multivariate Beta mixture models for medical applications","year":2021,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Multivariate statistics; BETA (programming language); Computer science; Applied mathematics; Artificial intelligence; Algorithm; Mathematics; Machine learning","score_opus":0.033690444704147074,"score_gpt":0.34232530243949927,"score_spread":0.3086348577353522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134670936","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016654027,0.00030908812,0.9928454,0.005091981,0.00010438774,0.00022835776,0.000059707516,0.00013342511,0.00121099],"genre_scores_gemma":[0.029072113,0.000019109444,0.96770275,0.0023913207,0.00028655425,0.0001453513,0.00008918512,0.000018135075,0.00027549433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982328,0.000093093855,0.00032053728,0.0006064792,0.00044768595,0.00029939567],"domain_scores_gemma":[0.99817085,0.00057232456,0.00013434111,0.00042275852,0.00053172646,0.00016797156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046662005,0.00018300349,0.00021732712,0.000069735725,0.00026968424,0.0003276589,0.0006411641,0.00015864344,0.000016118216],"category_scores_gemma":[0.0003744181,0.00016523084,0.00008331399,0.00042443362,0.000046011508,0.00069486315,0.00018721278,0.00029782855,0.0000058023284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010934608,0.00050923193,0.000005555835,0.00014989411,0.000023746434,0.000017567978,0.0006193852,0.00089036254,0.0017320315,0.38416108,0.00029870632,0.6115815],"study_design_scores_gemma":[0.00036869146,0.000016334838,0.000040348074,0.000091532325,0.00001095943,0.000010893062,0.000004888632,0.7813918,0.001263903,0.21510567,0.0015262678,0.000168693],"about_ca_topic_score_codex":0.0000032713347,"about_ca_topic_score_gemma":0.0000042103707,"teacher_disagreement_score":0.7805015,"about_ca_system_score_codex":0.00002794678,"about_ca_system_score_gemma":0.00076325826,"threshold_uncertainty_score":0.6737918},"labels":[],"label_agreement":null},{"id":"W3135684272","doi":"10.1016/j.jmva.2022.105043","title":"Density ratio model with data-adaptive basis function","year":2022,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Basis (linear algebra); Function (biology); Basis function; Mathematics; Probability density function; Mathematical optimization; Population; Computer science; Algorithm; Econometrics; Statistics","score_opus":0.04516578256387216,"score_gpt":0.28672749268929154,"score_spread":0.24156171012541938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135684272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003868097,0.00006869921,0.9951068,0.000600675,0.00010999216,0.000054564043,0.000012422615,0.000016232925,0.00016251802],"genre_scores_gemma":[0.49756098,0.0000053120607,0.5020141,0.00022170923,0.000040458264,0.0000016080965,0.000004717455,0.0000050044996,0.00014609784],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786454,0.0004906814,0.00043129778,0.0003492125,0.0006860714,0.00017820668],"domain_scores_gemma":[0.99794465,0.000109039516,0.0006667357,0.00082967087,0.0003339285,0.000115956165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020929044,0.00014016952,0.0004510145,0.0004904881,0.00031261964,0.00009990288,0.0011478382,0.00003270577,0.0000390833],"category_scores_gemma":[0.000040998686,0.000103139784,0.00023066564,0.0015478359,0.000019321882,0.00095517625,0.00051070494,0.0003853683,0.0000010659123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006128176,0.00043759952,0.00085920905,0.0000052812743,0.0073424354,0.00016471272,0.0017890397,0.8888059,0.0023838836,0.039549228,0.0012380683,0.05681182],"study_design_scores_gemma":[0.00046522796,0.00021220806,0.0015054727,0.000002519579,0.0017596865,0.000039356484,0.000051076506,0.9903572,0.00012893167,0.0051561357,0.00018793737,0.00013423055],"about_ca_topic_score_codex":0.00009377333,"about_ca_topic_score_gemma":0.00003849472,"teacher_disagreement_score":0.49369287,"about_ca_system_score_codex":0.00009831985,"about_ca_system_score_gemma":0.00020917569,"threshold_uncertainty_score":0.42059183},"labels":[],"label_agreement":null},{"id":"W3138271423","doi":"10.1080/03610918.2021.1894334","title":"Assessing the variability of posterior probabilities in Gaussian model-based clustering","year":2021,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Cluster analysis; Percentile; Statistics; Posterior probability; Confidence interval; Computer science; Data set; Gaussian; Mathematics; Data mining; Pattern recognition (psychology); Artificial intelligence; Bayesian probability","score_opus":0.13808537766272716,"score_gpt":0.4451762601127643,"score_spread":0.30709088245003713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138271423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013549462,0.000099289166,0.9850254,0.0006806094,0.000038085902,0.00020015298,0.000009310382,0.00001856183,0.00037914174],"genre_scores_gemma":[0.5160826,0.0000052647574,0.48381928,0.000060035978,0.0000016767468,0.000009182327,0.000016227403,0.0000028438387,0.0000029420346],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982859,0.0008084114,0.00047317182,0.00020327594,0.0001251803,0.0001040601],"domain_scores_gemma":[0.9970386,0.0018503178,0.00014690596,0.00072409783,0.00021615977,0.000023904488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001027055,0.000086531225,0.00015523189,0.00009962577,0.00012432277,0.00016724347,0.00034041866,0.0000478858,0.0000012939024],"category_scores_gemma":[0.00031848534,0.00008055339,0.000018098264,0.000408419,0.00011672557,0.00030913862,0.000256997,0.00015308373,1.72077e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023953091,0.000079311285,0.0015631972,0.000048343703,0.0000020774896,5.482447e-7,0.0017393109,0.76936376,0.00005219661,0.110871956,9.687168e-7,0.11627591],"study_design_scores_gemma":[0.00022472815,0.00000792106,0.01653629,0.0000501292,0.0000035092382,0.0000010978208,0.00007093097,0.8069995,0.000017298838,0.17601827,0.000005272019,0.00006503021],"about_ca_topic_score_codex":0.000021159838,"about_ca_topic_score_gemma":0.00012731936,"teacher_disagreement_score":0.5025331,"about_ca_system_score_codex":0.000058259975,"about_ca_system_score_gemma":0.0001817785,"threshold_uncertainty_score":0.32848722},"labels":[],"label_agreement":null},{"id":"W3139051417","doi":"10.1111/exsy.12688","title":"Multivariate‐bounded Gaussian mixture model with minimum message length criterion for model selection","year":2021,"lang":"en","type":"article","venue":"Expert Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; MNIST database; Cluster analysis; Model selection; Mixture model; Selection (genetic algorithm); Artificial intelligence; Representation (politics); Pattern recognition (psychology); Feature selection; Bounded function; Data mining; Gaussian; Machine learning; Artificial neural network; Mathematics","score_opus":0.03003543556985333,"score_gpt":0.29848945313278,"score_spread":0.2684540175629267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139051417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074622885,0.00096901687,0.994485,0.000949379,0.00059911225,0.0005921389,0.00001385376,0.00025216283,0.0013930588],"genre_scores_gemma":[0.2851742,0.000018185641,0.7094002,0.00037520533,0.00022211176,0.00028807027,0.000014263133,0.000041852294,0.004465964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976712,0.00022914103,0.00037563563,0.0008700868,0.00035776774,0.0004961541],"domain_scores_gemma":[0.99859446,0.00007628317,0.0001485998,0.0006912954,0.00030955285,0.0001797926],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043772339,0.0003293863,0.00044430234,0.000100708094,0.00032276928,0.00045870757,0.0004567994,0.00023905195,0.0000034422278],"category_scores_gemma":[0.00003302675,0.0002588662,0.00013338108,0.0003342336,0.000027691389,0.000586042,0.000093505994,0.00018384364,0.000003625325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023802715,0.00056241534,0.000017261938,0.0004630692,0.00029038536,0.000073895295,0.02183857,0.037901856,0.25828013,0.6450145,0.02066228,0.01465756],"study_design_scores_gemma":[0.00084980734,0.00008571825,0.0000024740232,0.00012867968,0.000012658545,0.000102513004,0.00008411452,0.98268354,0.0073991213,0.006233048,0.002036779,0.00038154502],"about_ca_topic_score_codex":0.000083825464,"about_ca_topic_score_gemma":0.000029952678,"teacher_disagreement_score":0.94478166,"about_ca_system_score_codex":0.00011436425,"about_ca_system_score_gemma":0.00031001781,"threshold_uncertainty_score":0.99998635},"labels":[],"label_agreement":null},{"id":"W3139958101","doi":"10.1007/978-3-030-73280-6_12","title":"Mixture-Based Unsupervised Learning for Positively Correlated Count Data","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Mixture model; Multinomial distribution; Artificial intelligence; Feature selection; Data mining; Dimensionality reduction; Curse of dimensionality; Pattern recognition (psychology); Machine learning; Statistics; Mathematics","score_opus":0.03559352313604585,"score_gpt":0.281113702822973,"score_spread":0.24552017968692713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139958101","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009856108,0.0015186985,0.9928624,0.0012997453,0.0020631088,0.00074093475,0.000044499273,0.00022583017,0.0012349219],"genre_scores_gemma":[0.009378909,0.000043654574,0.9859611,0.0031453671,0.00043053343,0.00001725849,0.00019640337,0.000070274626,0.000756499],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942445,0.00015111861,0.00067146664,0.0029849163,0.0010293762,0.0009186353],"domain_scores_gemma":[0.9942886,0.0015141647,0.00037545824,0.002877958,0.00067950436,0.0002642688],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021869019,0.00075317564,0.00087691477,0.0006287039,0.00048691698,0.0009570159,0.0061344714,0.0006245798,0.000023693123],"category_scores_gemma":[0.00036648492,0.00070364616,0.00020809562,0.0007789525,0.00047700846,0.0007214131,0.0021063075,0.0014435296,0.00001147618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029307868,0.000061261075,0.000022397882,0.00011689991,0.000043990516,0.0002077248,0.00041154417,0.023377992,0.0006372489,0.037977554,0.00013372106,0.93698037],"study_design_scores_gemma":[0.00069452374,0.00020722546,0.000030197727,0.00062792294,0.00003237865,0.000057978483,1.0381678e-7,0.94008315,0.0013501638,0.050110884,0.0059498567,0.00085564016],"about_ca_topic_score_codex":0.000021397986,"about_ca_topic_score_gemma":0.00004009632,"teacher_disagreement_score":0.93612474,"about_ca_system_score_codex":0.000305194,"about_ca_system_score_gemma":0.0019774125,"threshold_uncertainty_score":0.99954146},"labels":[],"label_agreement":null},{"id":"W3140112271","doi":"10.1002/ima.22577","title":"Nonparametric learning approach based on infinite flexible mixture model and its application to medical data analysis","year":2021,"lang":"en","type":"article","venue":"International Journal of Imaging Systems and Technology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Computer science; Generative model; Mixture model; Flexibility (engineering); Nonparametric statistics; Artificial intelligence; Identification (biology); Machine learning; Dirichlet distribution; Generative grammar; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.018180965220078962,"score_gpt":0.30898761009715525,"score_spread":0.2908066448770763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140112271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002183807,0.0014449105,0.9864697,0.009342178,0.0001631786,0.000056653204,0.0000052585456,0.000037194874,0.00029711303],"genre_scores_gemma":[0.7378352,0.00006444383,0.26155433,0.0004228818,0.00006311366,0.0000040834243,0.0000067380097,0.0000051766174,0.00004400108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985596,0.00008034954,0.00036691225,0.00035614806,0.0005124806,0.0001245397],"domain_scores_gemma":[0.998491,0.00010886158,0.0002420996,0.00033951062,0.00069109857,0.00012744825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010422058,0.0001017636,0.0002668986,0.0013617048,0.000053132935,0.0001682246,0.0010041043,0.00010061257,0.0000013970078],"category_scores_gemma":[0.00081542577,0.0000858206,0.000036713365,0.0012187806,0.000026425167,0.00023411476,0.00041651103,0.00037276384,7.344636e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003284218,0.00025889976,0.00632474,0.000063595886,0.0008030964,0.00031341033,0.00020171817,0.14876637,0.0028819893,0.32465014,0.0005828513,0.5151203],"study_design_scores_gemma":[0.00026017227,0.000022684164,0.00008151762,0.000054649707,0.000040209026,0.00047334345,0.000017434808,0.9957428,0.00014737798,0.0016236458,0.0014540363,0.000082135506],"about_ca_topic_score_codex":0.000006732602,"about_ca_topic_score_gemma":0.0000010126408,"teacher_disagreement_score":0.8469764,"about_ca_system_score_codex":0.000029096853,"about_ca_system_score_gemma":0.00016136958,"threshold_uncertainty_score":0.34996623},"labels":[],"label_agreement":null},{"id":"W3140468623","doi":"","title":"1 - Introduction aux Statistiques de deuxième espèce : applications des Logs-moments et des Logs-cumulants à l'analyse des lois d'images radar","year":2002,"lang":"fr","type":"article","venue":"Traitement du signal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cumulant; Estimator; Mathematics; Moment (physics); Probability density function; Function (biology); Statistics; Mellin transform; Fourier transform; Applied mathematics; Calculus (dental); Mathematical analysis; Physics","score_opus":0.07239121881595284,"score_gpt":0.3308136743767197,"score_spread":0.2584224555607669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3140468623","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013973176,0.0074123535,0.9714433,0.0046191155,0.00022746938,0.00069770386,0.00016805048,0.000201196,0.0012576221],"genre_scores_gemma":[0.15386905,0.0025184061,0.8365171,0.0006381036,0.00080839876,0.00020692521,0.00004653313,0.000055346398,0.005340142],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99532765,0.001083756,0.0008156658,0.0010770524,0.00056703284,0.0011288667],"domain_scores_gemma":[0.9978115,0.0002749397,0.00031963526,0.00064740557,0.00047372188,0.0004727729],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017378271,0.0005757676,0.0005349815,0.0002880658,0.0008581927,0.0006663591,0.0008754224,0.0002006464,0.0023018862],"category_scores_gemma":[0.0001014568,0.0005943093,0.0002139383,0.00083558384,0.0010927921,0.001611582,0.00022534265,0.00041038307,0.00014786771],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039727118,0.0013530477,0.0012550731,0.0003961415,0.00036593297,0.00006832762,0.0133938845,0.0008071463,0.0133817755,0.07367594,0.015619666,0.8796433],"study_design_scores_gemma":[0.0033040147,0.0014089622,0.024434337,0.00065295247,0.0010487866,0.0007325586,0.00064052426,0.13434242,0.046833128,0.6985002,0.0855847,0.0025174152],"about_ca_topic_score_codex":0.0007635438,"about_ca_topic_score_gemma":0.00027427296,"teacher_disagreement_score":0.8771259,"about_ca_system_score_codex":0.00080146384,"about_ca_system_score_gemma":0.00019405347,"threshold_uncertainty_score":0.99965084},"labels":[],"label_agreement":null},{"id":"W3152404744","doi":"10.1002/cjs.11671","title":"Bayesian clustering for continuous‐time hidden Markov models","year":2021,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov chain Monte Carlo; Gibbs sampling; Cluster analysis; Computer science; Dirichlet process; Merge (version control); Algorithm; Hierarchical Dirichlet process; Bayesian inference; Bayesian probability; Mathematics; Artificial intelligence; Latent Dirichlet allocation","score_opus":0.024756581759730653,"score_gpt":0.2522323345800609,"score_spread":0.22747575282033022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152404744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000689474,0.00093878247,0.99381673,0.0007841784,0.0022465156,0.00029820667,0.000806328,0.000012039074,0.0010282876],"genre_scores_gemma":[0.013108229,0.00005383587,0.98503613,0.00048562215,0.0004384314,0.000008577808,0.000041904863,0.00005000184,0.00077724474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972711,0.00025266423,0.0010688433,0.00046020147,0.00033900962,0.000608149],"domain_scores_gemma":[0.99565506,0.00034436176,0.0009085948,0.00076139095,0.0012101511,0.0011204148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013471011,0.00036252345,0.0009547031,0.00039658576,0.00016610474,0.001012529,0.001707739,0.0003283423,0.000071654926],"category_scores_gemma":[0.0003532393,0.00037062835,0.00029564265,0.00012693726,0.00007388172,0.00030116353,0.00025461172,0.0008140796,0.0000020417885],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025152449,0.000037318536,0.000049083596,0.00063024776,0.0005177879,0.0031163585,0.0040543205,0.004976227,0.000078013734,0.08366911,0.082733646,0.8201127],"study_design_scores_gemma":[0.00041582668,0.00011127415,0.000047932113,0.0004678173,0.000107842374,0.00036721153,0.000036879814,0.718884,0.000037464335,0.27670762,0.0023159718,0.00050019997],"about_ca_topic_score_codex":0.0009933725,"about_ca_topic_score_gemma":0.0047960565,"teacher_disagreement_score":0.8196125,"about_ca_system_score_codex":0.0003044859,"about_ca_system_score_gemma":0.005468907,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W3152638140","doi":"10.1214/20-bjps483","title":"A Bayesian nonparametric estimation to entropy","year":2021,"lang":"en","type":"article","venue":"Brazilian Journal of Probability and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Estimator; Dirichlet process; Statistics; Frequentist inference; Minimum-variance unbiased estimator; Bayes estimator; Nonparametric statistics; Consistent estimator; Dirichlet distribution; Minimax estimator; Applied mathematics; Econometrics; Bayesian probability; Bayesian inference","score_opus":0.01572332641170777,"score_gpt":0.28072505489386795,"score_spread":0.2650017284821602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152638140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002115444,0.0002228419,0.9956247,0.0015229124,0.000263055,0.00010587407,0.000017952958,0.000010881633,0.00011634679],"genre_scores_gemma":[0.056055404,0.000028643348,0.9434656,0.00033756046,0.000042862317,0.0000014127747,0.0000011075265,0.000004887586,0.000062548825],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985394,0.00026187013,0.00048643813,0.00023402249,0.0002851205,0.00019313433],"domain_scores_gemma":[0.99842423,0.0003141961,0.00018635376,0.00029778105,0.0004815111,0.00029595345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009261295,0.00011486561,0.000273104,0.00012661214,0.00008751017,0.00019870572,0.00028133785,0.000053586176,0.000021648315],"category_scores_gemma":[0.0015518838,0.00010116888,0.000053639622,0.0005357879,0.000047272108,0.00028624805,0.00009558061,0.00019156413,0.0000036485967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015535988,0.00009681765,0.0003065509,0.0000619272,0.00001726182,0.00010918779,0.0005017286,0.00020887837,0.0001934832,0.4592097,0.00097484153,0.5383041],"study_design_scores_gemma":[0.00039125042,0.00032700706,0.0038106812,0.00005227695,0.000025588066,0.0004374258,0.0000126121995,0.09256708,0.00086910074,0.9001106,0.001232734,0.00016363298],"about_ca_topic_score_codex":0.0000019068856,"about_ca_topic_score_gemma":0.000006532325,"teacher_disagreement_score":0.5381404,"about_ca_system_score_codex":0.000045240016,"about_ca_system_score_gemma":0.00026803333,"threshold_uncertainty_score":0.4125547},"labels":[],"label_agreement":null},{"id":"W3153250534","doi":"","title":"Bayesian Computations via MCMC, with applications to Big Data and Spatial Data","year":2018,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Markov chain Monte Carlo; Approximate Bayesian computation; Big data; Bayesian probability; Computation; Computer science; Spatial analysis; Data science; Data mining; Statistics; Artificial intelligence; Mathematics; Algorithm","score_opus":0.037130292459169434,"score_gpt":0.294794767296401,"score_spread":0.25766447483723154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153250534","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016924748,0.0002694029,0.9862517,0.000596304,0.00020310775,0.0005075239,0.00026016773,0.00007195979,0.011670575],"genre_scores_gemma":[0.047745075,0.00010533407,0.9473295,0.000047765967,0.00016129008,0.0000012916796,0.0020042458,0.000019910549,0.0025855938],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983198,0.000075780634,0.0001162835,0.0009956027,0.0002826727,0.00020984652],"domain_scores_gemma":[0.9964573,0.00005530095,0.00023389954,0.0028518536,0.00019226958,0.00020937009],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002497946,0.00022050246,0.0003335838,0.00008343731,0.0003039987,0.00006637478,0.003418181,0.00015828485,0.00019384045],"category_scores_gemma":[0.000009558071,0.00024970103,0.000025968273,0.00016447203,0.000082511346,0.000787858,0.0011550026,0.00012802935,0.000011439977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042986012,0.00005280556,0.0000172753,0.00007857949,0.0000816063,0.000005179339,0.005495924,0.0000023238056,0.00006770403,0.0016752081,0.0022322286,0.9902482],"study_design_scores_gemma":[0.0031734286,0.0013736067,0.084077165,0.00083666923,0.0014308888,0.0000645456,0.011206983,0.74404,0.0001308986,0.004896815,0.14531673,0.0034522694],"about_ca_topic_score_codex":0.064305,"about_ca_topic_score_gemma":0.35950816,"teacher_disagreement_score":0.9867959,"about_ca_system_score_codex":0.0000649932,"about_ca_system_score_gemma":0.00026066252,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W3156276029","doi":"","title":"Efficiency of the minimum quadratic distance estimator for the bivariate Poisson distribution","year":2009,"lang":"fr","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Poisson distribution; Bivariate analysis; Estimator; Combinatorics; Statistics; Calculus (dental)","score_opus":0.02456532956628817,"score_gpt":0.29086576004834225,"score_spread":0.2663004304820541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156276029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039689714,0.0036125842,0.93247956,0.060034517,0.0019034074,0.0007548315,0.00006987651,0.000030950403,0.0007173962],"genre_scores_gemma":[0.68899196,0.000054230815,0.30330494,0.00080905634,0.00017058745,0.000021285428,0.0000034234217,0.000009480433,0.0066350102],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981571,0.00024193963,0.00045412694,0.0003904739,0.00030509708,0.0004512511],"domain_scores_gemma":[0.99781936,0.00068342756,0.0002653521,0.00096664083,0.00018499198,0.00008025126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011361566,0.00021874445,0.00026356732,0.000015776439,0.0004471634,0.00016796628,0.0012407892,0.00011646328,0.000015838723],"category_scores_gemma":[0.00035200623,0.00011462099,0.00025303726,0.0006058835,0.00023275036,0.0002519342,0.00010275599,0.0001668936,0.0000051857496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013535767,0.00013915429,0.000010215629,0.000040419407,0.0000103474285,5.7539387e-7,0.00041416145,0.00012048741,0.0004508495,0.86231464,0.0029940875,0.13349155],"study_design_scores_gemma":[0.0003850338,0.0002483889,0.0029960412,0.00016183892,0.00008821612,0.000013549957,0.000022420138,0.76725936,0.0042211246,0.21008411,0.014308314,0.00021161659],"about_ca_topic_score_codex":0.00007375921,"about_ca_topic_score_gemma":0.00001880256,"teacher_disagreement_score":0.76713884,"about_ca_system_score_codex":0.000055062264,"about_ca_system_score_gemma":0.0001851743,"threshold_uncertainty_score":0.46741083},"labels":[],"label_agreement":null},{"id":"W3158446859","doi":"10.1007/s00357-021-09389-2","title":"Matrix Normal Cluster-Weighted Models","year":2021,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Università di Catania","keywords":"Covariate; Univariate; Mathematics; Cluster analysis; Independence (probability theory); Statistics; Data set; Multivariate statistics; Grouped data; Econometrics; Conditional independence","score_opus":0.04685364537515465,"score_gpt":0.31580409727873926,"score_spread":0.26895045190358463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158446859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004691984,0.0013970897,0.98556316,0.0037897425,0.002010912,0.00014790465,0.000002810623,0.000036660596,0.002359716],"genre_scores_gemma":[0.2621274,0.00044277287,0.73645866,0.0001800226,0.00046473314,0.000005925898,0.000007945125,0.000016377686,0.0002961387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972402,0.00045659143,0.0010377107,0.0003864216,0.00064982846,0.0002292464],"domain_scores_gemma":[0.99617994,0.00011106473,0.0016576974,0.0009110211,0.00096249813,0.00017779866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014749824,0.00024557576,0.0005277235,0.00031423056,0.00007267418,0.0005301679,0.0015014006,0.0004068637,0.000012066054],"category_scores_gemma":[0.000052459018,0.00021218935,0.00038518448,0.00026573573,0.0000312403,0.000994449,0.00054037716,0.0010958195,0.0000040737923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112490685,0.000704012,0.000088131696,0.0005239274,0.00048090462,0.00020259712,0.004707369,0.009718851,0.011251869,0.41532326,0.010158347,0.54672825],"study_design_scores_gemma":[0.0004006408,0.0000518038,0.00058140955,0.00027245237,0.000072957475,0.0002518804,0.000031013617,0.8347261,0.0012982426,0.16096331,0.0010586022,0.00029161113],"about_ca_topic_score_codex":0.0000044999438,"about_ca_topic_score_gemma":0.0000016330735,"teacher_disagreement_score":0.8250072,"about_ca_system_score_codex":0.00015674913,"about_ca_system_score_gemma":0.0007388181,"threshold_uncertainty_score":0.8652831},"labels":[],"label_agreement":null},{"id":"W3158909498","doi":"10.1007/s11009-021-09866-6","title":"Asymptotics of Running Maxima for φ-Subgaussian Random Double Arrays","year":2021,"lang":"en","type":"article","venue":"Methodology And Computing In Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Mathematics; Maxima; Combinatorics; Discrete mathematics","score_opus":0.09129259072330917,"score_gpt":0.3260548852488721,"score_spread":0.23476229452556294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158909498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03080501,0.0002234107,0.96515757,0.00035862753,0.00026141873,0.00049829896,0.0000012402579,0.000059484755,0.0026349162],"genre_scores_gemma":[0.2562159,0.0000052758382,0.74356014,0.00014026526,0.000035068733,0.000022768452,0.0000020129949,0.0000071393256,0.000011415601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99748397,0.0007070709,0.0005780209,0.00073645794,0.00010976945,0.00038472787],"domain_scores_gemma":[0.99674404,0.0023254664,0.00019480535,0.00056424853,0.00009736215,0.00007409197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074394126,0.00018944396,0.00067720877,0.000076229735,0.00013245697,0.00003815613,0.0003772859,0.00021026633,0.0000032484004],"category_scores_gemma":[0.00027615222,0.00017971796,0.00009709094,0.00037151863,0.00016423783,0.00005221467,0.000348419,0.000280364,3.5721715e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022493606,0.00011180053,0.001878912,0.00024184925,0.000026502628,0.0000035854248,0.0014318707,0.0007572294,0.0038913123,0.82502407,0.0000075395074,0.16640037],"study_design_scores_gemma":[0.0034794912,0.00006030954,0.0031372537,0.000037093097,0.000019808245,0.000030499164,0.000037376638,0.05298847,0.03083122,0.9089572,0.00018112602,0.00024019153],"about_ca_topic_score_codex":0.000009553591,"about_ca_topic_score_gemma":0.00001008734,"teacher_disagreement_score":0.22541088,"about_ca_system_score_codex":0.000025968371,"about_ca_system_score_gemma":0.00012312844,"threshold_uncertainty_score":0.73286855},"labels":[],"label_agreement":null},{"id":"W3159100424","doi":"10.1016/j.knosys.2021.107051","title":"Online mixture-based clustering for high dimensional count data using Neerchal–Morel distribution","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; Mixture model; Expectation–maximization algorithm; Artificial intelligence; Clustering high-dimensional data; Selection (genetic algorithm); Maximization; Machine learning; Unsupervised learning; Model selection; Data mining; Pattern recognition (psychology); Maximum likelihood; Mathematical optimization; Statistics","score_opus":0.07983090663054626,"score_gpt":0.3283377075129023,"score_spread":0.24850680088235605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159100424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032414303,0.0023760528,0.98798877,0.0005235567,0.0035372963,0.0005817174,0.0015176702,0.00019469344,0.00003881169],"genre_scores_gemma":[0.41052145,0.0000016513435,0.5851624,0.00019859915,0.0007495567,0.000048059148,0.0031426237,0.000042856485,0.00013278409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669546,0.00049150304,0.0006820843,0.0011284519,0.0004241239,0.00057839986],"domain_scores_gemma":[0.99610054,0.0005484331,0.00024024643,0.002042607,0.0008329757,0.00023522008],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015486154,0.00037023326,0.00055765174,0.00011083273,0.00038420258,0.00034963625,0.0011976534,0.00024213393,0.00000546417],"category_scores_gemma":[0.00025520986,0.00034535828,0.00014769733,0.0006032995,0.000061796476,0.00038109254,0.00046341668,0.00025082682,0.000009444021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007238695,0.009537626,0.00047278413,0.010532408,0.0009496507,0.00066250307,0.0014308137,0.1820843,0.20371173,0.31157494,0.048757724,0.22956164],"study_design_scores_gemma":[0.0014393925,0.00005653597,0.00005464356,0.0004889488,0.00005626287,0.000030676223,0.000009804525,0.9844849,0.0039786007,0.00057922653,0.008407223,0.0004137663],"about_ca_topic_score_codex":0.0000864572,"about_ca_topic_score_gemma":0.00013633784,"teacher_disagreement_score":0.8024006,"about_ca_system_score_codex":0.00031582222,"about_ca_system_score_gemma":0.0013840186,"threshold_uncertainty_score":0.99989986},"labels":[],"label_agreement":null},{"id":"W3160487084","doi":"10.32473/flairs.v34i1.128379","title":"Entropy-based Variational Learning of Finite Inverted Beta-Liouville Mixture Model","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Agence Nationale de la Recherche; Equipex","keywords":"Cluster analysis; Inference; Artificial intelligence; Entropy (arrow of time); Mixture model; Unsupervised learning; Computer science; Categorization; Pattern recognition (psychology); BETA (programming language); Kullback–Leibler divergence; Machine learning; Algorithm; Mathematics; Physics","score_opus":0.11354511964787596,"score_gpt":0.3514613912485156,"score_spread":0.23791627160063966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160487084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072086183,0.00005978679,0.9799408,0.008205066,0.00042407203,0.00020922249,0.000021689602,0.000041716696,0.003889047],"genre_scores_gemma":[0.75647,0.00009456096,0.24242142,0.00018243837,0.00014047917,0.000028889315,0.0000070261567,0.0000128727015,0.0006423179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961953,0.00009940042,0.00067935267,0.0006078454,0.0019684678,0.00044959775],"domain_scores_gemma":[0.99227726,0.00066385925,0.0003476537,0.0002957641,0.006290858,0.00012458072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023690066,0.00020504264,0.00030669756,0.00014220978,0.0003190063,0.00031664694,0.0026373551,0.00017661514,0.00012297138],"category_scores_gemma":[0.0018216524,0.00017083746,0.0003946414,0.0012550843,0.0003925098,0.0005306484,0.001005578,0.00092564174,0.000008976924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000259817,0.00011492049,0.00020888227,0.000059859452,0.000080759884,6.408471e-7,0.0015729078,0.0058600185,0.12534969,0.8593895,0.0007101502,0.006626724],"study_design_scores_gemma":[0.000035578796,0.00002478917,0.000022827831,0.00008333425,0.0000060406123,0.0000013517183,0.00020432351,0.5163112,0.27326256,0.20979807,0.00016419623,0.000085670334],"about_ca_topic_score_codex":0.000042675736,"about_ca_topic_score_gemma":0.000005380864,"teacher_disagreement_score":0.7492614,"about_ca_system_score_codex":0.00014128734,"about_ca_system_score_gemma":0.0011213229,"threshold_uncertainty_score":0.696655},"labels":[],"label_agreement":null},{"id":"W3160954170","doi":"10.1109/icassp39728.2021.9414099","title":"Phase Transitions for One-Vs-One and One-Vs-All Linear Separability in Multiclass Gaussian Mixtures","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gaussian; Binary number; Focus (optics); Mathematics; Separable space; Function (biology); Binary data; Mixture model; Applied mathematics; Algorithm; Statistics; Mathematical analysis; Physics; Arithmetic","score_opus":0.05802227800532476,"score_gpt":0.35115236566005154,"score_spread":0.29313008765472676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160954170","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028559081,0.00019544647,0.9558619,0.013672211,0.00011468802,0.00047377186,0.00003894841,0.00010270221,0.000981195],"genre_scores_gemma":[0.3168169,0.000027873093,0.6814407,0.0013127256,0.000061682804,0.00004872777,0.000013050112,0.000010883297,0.00026745614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979636,0.00026159297,0.00039380573,0.0007554907,0.00020235799,0.0004231668],"domain_scores_gemma":[0.99867487,0.00027691913,0.000051700554,0.0006392755,0.00012916107,0.00022804974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006996182,0.00020357253,0.0004076187,0.000096487005,0.000120424535,0.0001390385,0.00031555543,0.00015948695,0.00004044989],"category_scores_gemma":[0.00010218028,0.00019757559,0.00012583047,0.0003376455,0.000082937404,0.00037254358,0.00009818299,0.00022736922,0.000004004143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036892598,0.008108836,0.00011855176,0.00041496297,0.00017494486,0.00008163572,0.007496781,0.0000710169,0.21926226,0.49519143,0.00062008016,0.26809058],"study_design_scores_gemma":[0.0112196095,0.0008891183,0.0023435806,0.00017306847,0.00011845437,0.000045059092,0.00006670729,0.57163584,0.19784907,0.21176994,0.0028937205,0.0009958274],"about_ca_topic_score_codex":0.00005275739,"about_ca_topic_score_gemma":0.0003438537,"teacher_disagreement_score":0.57156485,"about_ca_system_score_codex":0.000037686674,"about_ca_system_score_gemma":0.00014072808,"threshold_uncertainty_score":0.8056899},"labels":[],"label_agreement":null},{"id":"W3161568123","doi":"10.46298/jnsao-2022-7492","title":"Minimal angle spread in the probability simplex with respect to the uniform distribution","year":2022,"lang":"en","type":"article","venue":"Journal of Nonsmooth Analysis and Optimization","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simplex; Dimension (graph theory); Infinity; Distribution (mathematics); Mathematics; Zero (linguistics); Probability distribution; Uniform distribution (continuous); Mathematical analysis; Mathematical optimization; Geometry; Combinatorics; Statistics","score_opus":0.015518095950547602,"score_gpt":0.2584291334580708,"score_spread":0.2429110375075232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161568123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017842012,0.000073466756,0.97567034,0.0061529125,0.000023807557,0.00013910093,0.00000783068,0.0000033898007,0.00008713314],"genre_scores_gemma":[0.65520704,0.000015509882,0.3443485,0.0003641531,0.00003211098,0.000008725915,0.0000074200675,0.000002445019,0.000014107238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865854,0.00043352076,0.00029002316,0.0001442676,0.00035322324,0.00012043668],"domain_scores_gemma":[0.9992179,0.00012116724,0.00023370705,0.00026198148,0.00011891153,0.000046322406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024775637,0.00007384398,0.00017370279,0.0001655612,0.00025467633,0.00014081784,0.00044110476,0.000016328931,0.0000134561715],"category_scores_gemma":[0.000063298314,0.000036200217,0.000085644024,0.0021729611,0.000022141505,0.00021535865,0.000085280684,0.00017469264,7.75938e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010128472,0.00011156335,0.0021238558,0.0000029751325,0.00008806464,0.000018279989,0.0012923059,0.9677378,0.0000048650786,0.007807918,0.00037837593,0.02033273],"study_design_scores_gemma":[0.00042336565,0.0006770227,0.022256238,0.0000072278763,0.0002868757,0.00011736035,0.00026720262,0.96943337,0.000026349377,0.0035900935,0.0027862717,0.0001286242],"about_ca_topic_score_codex":0.00003428845,"about_ca_topic_score_gemma":0.00014031265,"teacher_disagreement_score":0.63736504,"about_ca_system_score_codex":0.00006288308,"about_ca_system_score_gemma":0.00007008842,"threshold_uncertainty_score":0.19587903},"labels":[],"label_agreement":null},{"id":"W3161812580","doi":"10.5539/ijsp.v10n4p1","title":"A Diagnostic Test Based on a 9-Component Mixture Gaussian Copula Model","year":2021,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Copula (linguistics); Receiver operating characteristic; Markov chain; Gaussian; Mathematics; Mixture model; Diagnostic test; Statistics; Computer science; Artificial intelligence; Pattern recognition (psychology); Applied mathematics; Econometrics; Medicine; Pediatrics","score_opus":0.016767041920503857,"score_gpt":0.2831873057560954,"score_spread":0.26642026383559153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161812580","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002566249,0.00011029343,0.991428,0.004908366,0.00041491125,0.00006522714,0.00015284303,0.000007731755,0.00034637176],"genre_scores_gemma":[0.38207656,0.000043603166,0.6171586,0.0006269738,0.00006251475,0.0000019092627,0.000004714906,0.000003880243,0.000021232789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864566,0.00011894482,0.00039677243,0.00022180642,0.0004930386,0.00012376196],"domain_scores_gemma":[0.9970892,0.001583858,0.00022063019,0.00020957719,0.00075635104,0.00014036614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005679303,0.0001183088,0.00019366421,0.00006813281,0.000047824768,0.00018034563,0.00040362266,0.000048925856,0.000017005328],"category_scores_gemma":[0.0020224068,0.0000953877,0.0000641539,0.00007661226,0.000049758386,0.00012746992,0.000088408415,0.00023369105,0.0000010993729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009419064,0.0012812403,0.00376631,0.00008337554,0.000094716794,0.0011734585,0.00047099873,0.007793431,0.0007059857,0.732011,0.0031393047,0.24938597],"study_design_scores_gemma":[0.0004801414,0.00013344771,0.0048351986,0.00009774227,0.000012736902,0.00013938613,0.0000016418992,0.5098708,0.00031918648,0.48350254,0.00050383277,0.00010329908],"about_ca_topic_score_codex":0.000005375769,"about_ca_topic_score_gemma":0.000008208623,"teacher_disagreement_score":0.5020774,"about_ca_system_score_codex":0.00006735081,"about_ca_system_score_gemma":0.0002893471,"threshold_uncertainty_score":0.38897976},"labels":[],"label_agreement":null},{"id":"W3163694547","doi":"10.32473/flairs.v34i1.128506","title":"Covid-19 News Clustering using MCMC-Based Learing of finite EMSD Mixture Models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain Monte Carlo; Cluster analysis; Computer science; Mixture model; Multinomial distribution; Artificial intelligence; Bayesian probability; Machine learning; Generative model; Flexibility (engineering); Task (project management); Dirichlet distribution; Statistical model; Data mining; Generative grammar; Mathematics; Statistics; Engineering","score_opus":0.28698765060979586,"score_gpt":0.4139066479645853,"score_spread":0.12691899735478945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163694547","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013032485,0.0001077558,0.97673887,0.006628909,0.00061202643,0.00027354775,0.000016650292,0.000045922217,0.0025438585],"genre_scores_gemma":[0.737291,0.00013261831,0.26168132,0.00045199948,0.00018622926,0.000018948162,0.0000020046166,0.000016877322,0.00021900567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99616027,0.0000967507,0.0007611437,0.00072613824,0.0017022868,0.00055339595],"domain_scores_gemma":[0.9945044,0.0007019187,0.00036048787,0.00043568312,0.003716592,0.00028089687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026337178,0.00023542024,0.00035332446,0.00016551091,0.0003923948,0.00046605646,0.0031977212,0.0001859592,0.000076601245],"category_scores_gemma":[0.0026301546,0.00020334471,0.00040744574,0.0013139448,0.0004629721,0.0008331793,0.0017589801,0.0007945975,0.0000032241974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000599197,0.00014600602,0.00023035872,0.00034446927,0.0001116279,0.000004080975,0.0052611385,0.02864238,0.24830979,0.69686574,0.00049421657,0.019530289],"study_design_scores_gemma":[0.000039703154,0.000023266208,0.0000039491692,0.00016455652,0.0000063419716,0.000005958861,0.0008005698,0.57790697,0.22414786,0.19661303,0.0001689203,0.0001188603],"about_ca_topic_score_codex":0.00042627967,"about_ca_topic_score_gemma":0.000053120137,"teacher_disagreement_score":0.72425854,"about_ca_system_score_codex":0.00033624715,"about_ca_system_score_gemma":0.0018634936,"threshold_uncertainty_score":0.8292157},"labels":[],"label_agreement":null},{"id":"W3164752615","doi":"10.1002/pds.5297","title":"Classification and visualization of longitudinal patterns of medication dose: An application to interferon‐beta‐1a and amitriptyline in patients with multiple sclerosis","year":2021,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal; Institut National de la Recherche Scientifique","funders":"Fonds de Recherche du Québec - Santé; Armand-Frappier Foundation","keywords":"Medicine; Amitriptyline; Representation (politics); Cohort; BETA (programming language); Multiple sclerosis; Dosing; Statistics; Internal medicine; Mathematics; Computer science; Immunology","score_opus":0.039093621106984056,"score_gpt":0.3296400437597162,"score_spread":0.2905464226527321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164752615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43976817,0.00013907871,0.5593451,0.0005588965,0.000023691799,0.00014331714,0.000008379763,0.0000074139475,0.000005957959],"genre_scores_gemma":[0.9538606,0.00042574882,0.04535561,0.00025522895,0.000016415892,0.000021095297,0.000057294677,0.000005283924,0.00000274346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982763,0.00065808283,0.00043626607,0.00042043845,0.00008732003,0.000121598896],"domain_scores_gemma":[0.99892706,0.0003976111,0.00023070708,0.00020622094,0.00014101082,0.00009736873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013534997,0.000107940876,0.0002891052,0.00010565084,0.000045193832,0.0000064022556,0.0001114878,0.00006420933,0.0000023159816],"category_scores_gemma":[0.00011663185,0.00009253641,0.000013019018,0.00020617722,0.00007038344,0.00025035843,0.000098506214,0.00008616548,1.24786e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018845609,0.00011665039,0.8711176,0.00006145078,0.000014374438,1.5422404e-7,0.00054211123,0.000033686767,0.004105315,0.010322609,0.00001074241,0.11348688],"study_design_scores_gemma":[0.0011850573,0.000107469525,0.9365891,0.000053083655,0.000019510724,0.0000012741625,0.000024821307,0.058580663,0.002751212,0.0005727873,0.000025821357,0.00008918957],"about_ca_topic_score_codex":0.000080774706,"about_ca_topic_score_gemma":0.0000923371,"teacher_disagreement_score":0.51409245,"about_ca_system_score_codex":0.000015250941,"about_ca_system_score_gemma":0.000022377964,"threshold_uncertainty_score":0.37735254},"labels":[],"label_agreement":null},{"id":"W316894210","doi":"","title":"Tests d'ajustement fondés sur la méthode Monte Carlo randomisée pour des distributions exponentielles","year":2009,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Humanities; Mathematics; Maximum likelihood; Philosophy; Statistics","score_opus":0.03389553044964576,"score_gpt":0.2594736170363044,"score_spread":0.22557808658665862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W316894210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015967134,0.01365906,0.90315354,0.038518026,0.00045393413,0.00057945075,0.000091643284,0.00024825684,0.027328946],"genre_scores_gemma":[0.34014866,0.0019831075,0.6055537,0.0002390452,0.000060254264,0.000048616334,0.000045409113,0.000034678862,0.051886532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9827981,0.013688945,0.0008962935,0.0010854092,0.0005926903,0.00093857053],"domain_scores_gemma":[0.99038196,0.0037330124,0.00048975326,0.0023991435,0.0024574893,0.00053865486],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010623997,0.0005536878,0.0006308982,0.00018742138,0.00093033427,0.0011510627,0.0019067829,0.0003403572,0.00012783956],"category_scores_gemma":[0.0024430638,0.00058153947,0.0004603552,0.00096421916,0.0005267869,0.00093396904,0.00061642297,0.0006010905,0.00006409413],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002639723,0.0012194263,0.00022421214,0.000074914344,0.00006817672,0.00003626237,0.0063972366,0.000051891027,0.0035111392,0.55181026,0.0070291115,0.42955095],"study_design_scores_gemma":[0.013260414,0.000012718406,0.01737993,0.007856722,0.0005225903,0.0005754642,0.00034125076,0.34975314,0.13032399,0.27154887,0.20542157,0.0030033286],"about_ca_topic_score_codex":0.0011605499,"about_ca_topic_score_gemma":0.00088262564,"teacher_disagreement_score":0.42654762,"about_ca_system_score_codex":0.00023222865,"about_ca_system_score_gemma":0.0005303175,"threshold_uncertainty_score":0.99988586},"labels":[],"label_agreement":null},{"id":"W3169822441","doi":"10.1002/sta4.410","title":"A multivariate normal approximation for the Dirichlet density and some applications","year":2021,"lang":"en","type":"preprint","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Mathematics; Estimator; Multivariate statistics; Dirichlet distribution; Applied mathematics; Gaussian; Statistics; Covariance matrix; Equivalence (formal languages); Asymptotic expansion; Mathematical analysis; Pure mathematics; Physics","score_opus":0.026886505875816296,"score_gpt":0.2975746641302438,"score_spread":0.2706881582544275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169822441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006547328,0.00078409154,0.99516505,0.0019599982,0.00026422957,0.0009988907,0.000025511703,0.000059758313,0.00008771155],"genre_scores_gemma":[0.02451607,0.00014515455,0.97399074,0.00036570325,0.00015975224,0.0006746533,0.00003427731,0.000009839334,0.00010380191],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989921,0.0000903767,0.00016277168,0.00046341188,0.00012062008,0.00017072115],"domain_scores_gemma":[0.99873906,0.00027079546,0.000119629185,0.0006991246,0.00011879717,0.00005257802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004967088,0.00014216908,0.00017611355,0.000033904253,0.00021194167,0.00032904503,0.0004559803,0.00011007321,0.00000114257],"category_scores_gemma":[0.000034929202,0.0001038832,0.000075867414,0.00008066096,0.00003883839,0.0001749344,0.0009159825,0.00023564188,0.0000010274496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068398176,0.00004788264,0.000015694053,0.00022710825,0.00007058695,0.0000016929017,0.0023534808,0.00012914954,0.00062537333,0.378838,0.0003114052,0.61737275],"study_design_scores_gemma":[0.0002586306,0.000013014491,0.0006662227,0.000029399245,0.000050884064,0.000008051057,0.000029979776,0.5720763,0.0012219917,0.4222904,0.0031053692,0.0002497285],"about_ca_topic_score_codex":0.000042548494,"about_ca_topic_score_gemma":0.000011518953,"teacher_disagreement_score":0.61712307,"about_ca_system_score_codex":0.000022104015,"about_ca_system_score_gemma":0.000095438394,"threshold_uncertainty_score":0.42362338},"labels":[],"label_agreement":null},{"id":"W3173120468","doi":"10.3150/23-bej1674","title":"An asymptotic Peskun ordering and its application to lifted samplers","year":2024,"lang":"en","type":"article","venue":"Bernoulli","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Environmental science; Statistical physics; Physics","score_opus":0.01552410014170505,"score_gpt":0.2949554795104116,"score_spread":0.27943137936870655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173120468","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023886638,0.0006280413,0.9729669,0.0013257286,0.00019313529,0.00020117497,0.0000026033792,0.00027502797,0.0005207463],"genre_scores_gemma":[0.6118118,0.000023042923,0.38745666,0.00039087023,0.00010348562,0.00003452215,0.0000022707327,0.000013461207,0.00016386992],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910206,0.000042090007,0.000113089336,0.00043403692,0.00012226317,0.00018648557],"domain_scores_gemma":[0.99942935,0.0000494167,0.000014096163,0.0003155448,0.000030152381,0.00016145656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519175,0.00010218171,0.00009706535,0.00009131929,0.00006749606,0.0002275328,0.00030548105,0.00004908295,0.0000058279493],"category_scores_gemma":[0.000016017433,0.00009440794,0.00002186057,0.00035625033,0.000008064467,0.00029963866,0.00009300146,0.00008562397,0.000056567867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019840525,0.000017478405,0.000043007447,0.000044671462,0.000011036651,0.000007379557,0.0012360844,0.00009271753,0.018016864,0.2948572,0.00019670938,0.6854749],"study_design_scores_gemma":[0.00014071136,0.00014522781,0.0024428107,0.00007993478,0.000017153312,0.000048383914,0.000013857223,0.9123247,0.0056222663,0.037661996,0.041088697,0.000414255],"about_ca_topic_score_codex":0.000028854929,"about_ca_topic_score_gemma":0.000011333751,"teacher_disagreement_score":0.912232,"about_ca_system_score_codex":0.000019910123,"about_ca_system_score_gemma":0.000031698557,"threshold_uncertainty_score":0.38498437},"labels":[],"label_agreement":null},{"id":"W3173482532","doi":"10.1002/sta4.398","title":"A (non‐central) chi‐squared mixture of non‐central chi‐squareds is (non‐central) chi‐squared and related results, corollaries and applications","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Chi-square test; Mathematics; Mean squared error; Representation (politics); Distribution (mathematics); Square (algebra); Degrees of freedom (physics and chemistry); Statistics; Mathematical analysis","score_opus":0.006693404061062815,"score_gpt":0.24138984590351215,"score_spread":0.23469644184244934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173482532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033797458,0.0049177324,0.95162797,0.003320957,0.00077251374,0.0015131091,0.0007225165,0.00021876881,0.0031089538],"genre_scores_gemma":[0.73004335,0.002992292,0.26329127,0.00094845187,0.00030525675,0.00013012858,0.00034501523,0.0001060974,0.0018381329],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947386,0.0002908699,0.001191674,0.0016572663,0.00065257,0.0014690453],"domain_scores_gemma":[0.9965064,0.00018145064,0.000515135,0.00168401,0.0003429438,0.0007700927],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004767604,0.0007086528,0.0010126542,0.00022173348,0.00052250404,0.00044608605,0.00087421376,0.0004917458,0.000048119837],"category_scores_gemma":[0.000117388176,0.00067271467,0.00027211598,0.0013077249,0.0004274225,0.00066596305,0.00052970496,0.0007096202,0.000008644717],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015405057,0.0024870671,0.008626435,0.002429168,0.0022056655,0.0009224605,0.15339515,0.00038399373,0.05380498,0.1470891,0.046810023,0.58030546],"study_design_scores_gemma":[0.038958043,0.0026693766,0.1637967,0.002525977,0.0017983813,0.0024275705,0.004160851,0.2702017,0.13958955,0.17775318,0.18709517,0.009023511],"about_ca_topic_score_codex":0.00016106149,"about_ca_topic_score_gemma":0.00009413741,"teacher_disagreement_score":0.6962459,"about_ca_system_score_codex":0.00011959589,"about_ca_system_score_gemma":0.00067630404,"threshold_uncertainty_score":0.9995724},"labels":[],"label_agreement":null},{"id":"W3174807046","doi":"10.1007/s11222-021-10032-8","title":"Bayesian inference for continuous-time hidden Markov models with an unknown number of states","year":2021,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Reversible-jump Markov chain Monte Carlo; Markov chain Monte Carlo; Computer science; Bayesian inference; Cluster analysis; State space; Hidden Markov model; Bayesian probability; Algorithm; Context (archaeology); Mathematics; Machine learning; Artificial intelligence; Statistics","score_opus":0.012387033746359098,"score_gpt":0.2849827437581099,"score_spread":0.2725957100117508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174807046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004018265,0.00006955701,0.9945565,0.0000707155,0.000059943817,0.00013021399,0.00008790264,0.00003969733,0.00096722913],"genre_scores_gemma":[0.18752801,0.000013888677,0.8121266,0.00009741531,0.000029664445,0.000002913542,0.00002659358,0.000012726402,0.00016219335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987672,0.00010779813,0.0002792792,0.0004055451,0.00016080645,0.00027938973],"domain_scores_gemma":[0.9985415,0.00049144,0.00015050345,0.0003123645,0.0003825603,0.00012164172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032964037,0.00015880143,0.0003218968,0.000029175166,0.00012930181,0.00015621992,0.000244064,0.00004663856,0.000007730439],"category_scores_gemma":[0.000040927902,0.00013894167,0.000024995888,0.00013937696,0.0000648097,0.00018602543,0.00016123247,0.000090156864,5.7320455e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012132676,0.00004307876,0.00017333218,0.00006593239,0.000026878663,0.000020029918,0.00072261045,0.00017345422,0.00009262954,0.5958934,0.00009664455,0.40267986],"study_design_scores_gemma":[0.00029104637,0.000111765454,0.000080669,0.000051478124,0.000013695571,0.000027243086,0.000024391784,0.69050777,0.00028301662,0.30840093,0.000058547354,0.00014944274],"about_ca_topic_score_codex":0.00002870334,"about_ca_topic_score_gemma":0.000012457318,"teacher_disagreement_score":0.6903343,"about_ca_system_score_codex":0.000008712705,"about_ca_system_score_gemma":0.00013839937,"threshold_uncertainty_score":0.5665877},"labels":[],"label_agreement":null},{"id":"W3176470375","doi":"10.3390/app11135798","title":"Nonparametric Bayesian Learning of Infinite Multivariate Generalized Normal Mixture Models and Its Applications","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Taif University","keywords":"Mixture model; Nonparametric statistics; Pattern recognition (psychology); Artificial intelligence; Multivariate statistics; Computer science; Bayesian probability; Support vector machine; Classifier (UML); Machine learning; Mathematics; Statistics","score_opus":0.02906831461288434,"score_gpt":0.2858745349169517,"score_spread":0.25680622030406736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176470375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006141003,0.0010253179,0.9781816,0.0002790841,0.000058067377,0.0002114883,0.000002514286,0.000066530265,0.014034374],"genre_scores_gemma":[0.5297024,0.00008112291,0.46990353,0.00014556557,0.000024064631,0.000036196438,0.0000013445174,0.000004328737,0.000101428675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824625,0.0001276964,0.00030476565,0.00062833837,0.0003652963,0.00032763564],"domain_scores_gemma":[0.99896604,0.0002962117,0.00017298531,0.0003053184,0.00012730845,0.00013214702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084596884,0.00016244919,0.0002697656,0.0002173175,0.00037923103,0.0001766054,0.00066432526,0.00009708969,0.000010629431],"category_scores_gemma":[0.00005538919,0.00014129594,0.000053744956,0.00217265,0.00014796083,0.00043035657,0.00034280724,0.0002033994,0.0000042759675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023687132,0.000034230332,0.000034626733,0.000019473557,0.000010226807,0.0000020907853,0.00059021957,0.0035738866,0.027387071,0.9128633,0.00001189789,0.055470593],"study_design_scores_gemma":[0.00043623507,0.000041692245,0.00016881317,0.000014659827,0.000016114414,0.000023545299,0.000054826673,0.80530596,0.03825136,0.15441978,0.0009641927,0.00030280824],"about_ca_topic_score_codex":0.000012844885,"about_ca_topic_score_gemma":0.000002827363,"teacher_disagreement_score":0.80173206,"about_ca_system_score_codex":0.0000093632825,"about_ca_system_score_gemma":0.00016492701,"threshold_uncertainty_score":0.57618815},"labels":[],"label_agreement":null},{"id":"W3184053854","doi":"10.1007/978-3-030-79457-6_25","title":"Birth-Death MCMC Approach for Multivariate Beta Mixture Models in Medical Applications","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Multivariate statistics; Mixture model; Bayesian probability; Artificial intelligence; Multivariate normal distribution; Data mining; Machine learning; Flexibility (engineering); Bayesian inference; Statistics; Mathematics","score_opus":0.03484743283623854,"score_gpt":0.2923724810792327,"score_spread":0.25752504824299416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184053854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018937117,0.0014596372,0.990493,0.0011189877,0.0006157571,0.0013851649,0.000025911462,0.0001420792,0.0047575743],"genre_scores_gemma":[0.0054527894,0.00010498847,0.9912888,0.0017699002,0.0005865128,0.0002327882,0.000033460063,0.00005753375,0.0004732701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940172,0.000116175375,0.00083536323,0.0027126211,0.0013530577,0.00096558954],"domain_scores_gemma":[0.99615544,0.00080798205,0.00029312688,0.0020025652,0.00034924044,0.00039166945],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022676352,0.0007201223,0.0009734719,0.00086124375,0.0002625002,0.0004745655,0.004647828,0.0009603592,0.000015879314],"category_scores_gemma":[0.00010062756,0.0006409521,0.00027782063,0.0009798903,0.00042099832,0.0005913608,0.0015793083,0.0014651519,0.000003990726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048521906,0.00007935762,0.0000048070597,0.00009059342,0.000012717327,0.00003832925,0.00040338043,0.012511836,0.000034633747,0.486404,0.000011348136,0.5004041],"study_design_scores_gemma":[0.00036761537,0.00003156543,0.000008512428,0.00017761302,0.0000069425373,0.000054446413,1.08449825e-7,0.6354785,0.00016488989,0.36217347,0.0010590064,0.00047733012],"about_ca_topic_score_codex":0.000034602377,"about_ca_topic_score_gemma":0.00005462612,"teacher_disagreement_score":0.62296665,"about_ca_system_score_codex":0.00026900074,"about_ca_system_score_gemma":0.0013957417,"threshold_uncertainty_score":0.99960417},"labels":[],"label_agreement":null},{"id":"W3185747415","doi":"10.1080/01621459.2021.1996377","title":"Accelerating Bayesian Structure Learning in Sparse Gaussian Graphical Models","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Graphical model; Hyperparameter; Bottleneck; Algorithm; Computer science; Gaussian; Bayesian probability; Wishart distribution; Scalability; Graph; Laplace's method; Mathematics; Mathematical optimization; Artificial intelligence; Machine learning; Theoretical computer science","score_opus":0.014799831060358051,"score_gpt":0.27521854319626987,"score_spread":0.26041871213591183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185747415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029418651,0.0000360513,0.9649935,0.004958922,0.00023508811,0.000040707626,0.0000061682786,0.000011712705,0.000299252],"genre_scores_gemma":[0.59792346,0.000015749074,0.40144262,0.00047591387,0.00008325237,4.864991e-7,6.732962e-7,0.0000060977145,0.00005175734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972741,0.0011097491,0.0005286683,0.00019623594,0.0006036682,0.00028754945],"domain_scores_gemma":[0.9978233,0.00065113785,0.0009911228,0.0001888679,0.00023361934,0.00011194236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092541205,0.00012122345,0.00038683624,0.0000901149,0.00012248612,0.0001824132,0.000442098,0.000061160405,0.000011740345],"category_scores_gemma":[0.0013324923,0.00008659665,0.00011796034,0.0008409793,0.00004470219,0.00035618062,0.00013121055,0.00088295393,5.8270723e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004746036,0.00021506772,0.050312307,0.000020966623,0.00017395061,0.00033523387,0.0021773642,0.009960018,0.006806941,0.5906273,0.0017889544,0.33753443],"study_design_scores_gemma":[0.0005670617,0.00015296706,0.13325104,0.00007503299,0.000044035256,0.00014334865,0.00011321136,0.29233342,0.00063808315,0.5722239,0.00021013898,0.0002477623],"about_ca_topic_score_codex":0.000025605712,"about_ca_topic_score_gemma":0.000043073884,"teacher_disagreement_score":0.5685048,"about_ca_system_score_codex":0.00025673513,"about_ca_system_score_gemma":0.00023862654,"threshold_uncertainty_score":0.38360447},"labels":[],"label_agreement":null},{"id":"W3191255899","doi":"10.1017/9781108377423.003","title":"Estimation of an Observed Markov Chain","year":2018,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Markov chain; Content (measure theory); Computer science; Estimation; Mathematics; Machine learning; Engineering; Systems engineering","score_opus":0.03499149550579661,"score_gpt":0.22473246475224543,"score_spread":0.18974096924644882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191255899","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007847495,0.000023272727,0.5110493,0.0000062307677,0.00013919036,0.00015924063,0.00003440606,0.00007620271,0.48843372],"genre_scores_gemma":[0.00046531568,0.0000117360105,0.22465558,0.00004220182,0.000074131516,3.2935603e-7,0.000020202719,0.000021764854,0.77470875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862057,0.000106088344,0.00021462924,0.0005730099,0.00026964553,0.00021607656],"domain_scores_gemma":[0.9981454,0.0000543124,0.00032624186,0.0011212329,0.00018430244,0.00016848343],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003000672,0.00029232074,0.00039822172,0.00017907542,0.000106323,0.000049393373,0.0012990171,0.0003469142,0.000004089088],"category_scores_gemma":[0.000009673198,0.00033335987,0.000166563,0.000013452618,0.00018760437,0.00027947928,0.00051324803,0.00024147301,0.0000048452584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024294945,0.000009186823,5.7296884e-8,0.00005957775,0.00004097755,0.00007159956,0.000103858554,0.0000034831085,0.000050934133,0.93000686,0.0031864098,0.06644276],"study_design_scores_gemma":[0.0021876844,0.00086261553,0.000052342268,0.0009081299,0.00044256853,0.00010384158,0.000017561879,0.29376844,0.008936794,0.007310538,0.683052,0.0023574894],"about_ca_topic_score_codex":0.000051210973,"about_ca_topic_score_gemma":0.0000014942667,"teacher_disagreement_score":0.92269635,"about_ca_system_score_codex":0.00007780217,"about_ca_system_score_gemma":0.00011769266,"threshold_uncertainty_score":0.99991184},"labels":[],"label_agreement":null},{"id":"W3194220760","doi":"10.14288/1.0401455","title":"Some research problems under finite mixture models","year":2021,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.04091581173163052,"score_gpt":0.24182953896503487,"score_spread":0.20091372723340434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194220760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046764735,0.001419998,0.94668365,0.0009876793,0.00018651316,0.0001756966,0.000034112036,0.00009639,0.003651209],"genre_scores_gemma":[0.80528724,0.00063886866,0.18778895,0.0002471704,0.00007328225,9.646269e-7,0.000009711215,0.000016304959,0.0059374985],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99778855,0.00037801004,0.00013222662,0.0006984509,0.00054608216,0.0004566925],"domain_scores_gemma":[0.99819535,0.00016515116,0.00007030374,0.0007537482,0.00062260317,0.00019283427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007836036,0.000052399646,0.00027118495,0.00007533443,0.0003858153,0.00033837615,0.0010261127,0.00018421952,0.000036550096],"category_scores_gemma":[0.000036188696,0.000178973,0.00014371063,0.0008760456,0.00022398372,0.0011681843,0.0007158528,0.00039982545,0.0000210563],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037245622,0.00030964418,0.00010137166,0.00016209051,0.00007532976,0.0008911486,0.0010550895,0.0007163502,0.0015097976,0.013292571,0.012728084,0.9691548],"study_design_scores_gemma":[0.0011423326,0.000091368944,0.070634276,0.0003383771,0.000021322467,0.00019709356,0.00043214095,0.05428498,0.000022327755,0.8708003,0.0015711556,0.00046430342],"about_ca_topic_score_codex":0.011345055,"about_ca_topic_score_gemma":0.034757547,"teacher_disagreement_score":0.9686905,"about_ca_system_score_codex":0.00006655925,"about_ca_system_score_gemma":0.0003287073,"threshold_uncertainty_score":0.9952385},"labels":[],"label_agreement":null},{"id":"W3195273118","doi":"10.11159/icsta21.135","title":"Robustness of Gaussian Mixture Reduction for Split-and-Conquer Learning of Finite Gaussian Mixtures","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Statistics, Theory and Applications (ICSTA ...)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Robustness (evolution); Gaussian; Divide and conquer algorithms; Gaussian process; Computer science; Reduction (mathematics); Mathematics; Algorithm; Applied mathematics; Computational chemistry; Chemistry; Geometry","score_opus":0.02340139224559361,"score_gpt":0.2912400077920799,"score_spread":0.2678386155464863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195273118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029618319,0.00009181506,0.99270046,0.0011187083,0.00011555248,0.00025432903,0.00016798188,0.000012755221,0.0025765523],"genre_scores_gemma":[0.6451403,0.00015106515,0.3536263,0.00004372763,0.0000697134,0.00006307943,0.000014956396,0.000009174461,0.00088169286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998986,0.00003742822,0.0003467341,0.00031360064,0.0002063807,0.000109821965],"domain_scores_gemma":[0.99805576,0.00034151413,0.00044100775,0.0001553503,0.0009602996,0.00004605412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062596845,0.00012703359,0.00021436064,0.00008525347,0.00011436514,0.00007327164,0.0004815778,0.00007325118,0.000016519403],"category_scores_gemma":[0.00034317383,0.000101854865,0.000049702994,0.00015458599,0.00023434468,0.00014159878,0.0001682073,0.00016868881,1.4837983e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050831128,0.000052302075,0.000040764502,0.00013330077,0.000040814764,6.7065926e-8,0.00033978466,0.000053956122,0.021649959,0.9477296,0.00012406807,0.029784568],"study_design_scores_gemma":[0.00029916322,0.0000682267,0.00022496765,0.00017668412,0.000042632433,0.000015589127,0.00039946372,0.03506495,0.06201946,0.90060425,0.00094126933,0.0001433762],"about_ca_topic_score_codex":0.0000036319918,"about_ca_topic_score_gemma":6.5310616e-7,"teacher_disagreement_score":0.6421785,"about_ca_system_score_codex":0.000012457734,"about_ca_system_score_gemma":0.00007617604,"threshold_uncertainty_score":0.41535208},"labels":[],"label_agreement":null},{"id":"W3198205467","doi":"10.82308/13578","title":"Bayesian model selection for deep exponential families","year":2016,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Model selection; Bayesian probability; Selection (genetic algorithm); Econometrics; Computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.01923236448092903,"score_gpt":0.24484016885323448,"score_spread":0.22560780437230546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198205467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02588504,0.00006198043,0.96396005,0.00019227187,0.0006801249,0.0005653383,0.00012099146,0.00054306997,0.00799114],"genre_scores_gemma":[0.57093805,0.00005392187,0.42732444,0.0003849628,0.00005774835,0.00014030738,0.0000031726079,0.000053243664,0.0010441723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99653447,0.00030507203,0.00057389995,0.001192141,0.0004937925,0.00090062903],"domain_scores_gemma":[0.9979464,0.00030227605,0.00022201503,0.00085252797,0.0003107374,0.00036605317],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011843476,0.0004663177,0.00043800968,0.00030415755,0.0010033875,0.00012700808,0.0011743547,0.00033323362,0.0000281412],"category_scores_gemma":[0.0003282328,0.00036852475,0.00033673167,0.00048684925,0.00007452609,0.0020782584,0.00033763086,0.00031332328,0.000061774146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003142815,0.00005475167,0.0000048154957,0.000016369997,0.000028368484,0.0000022295474,0.000004177871,0.00006964433,0.09827944,0.43532202,0.000008528987,0.4661782],"study_design_scores_gemma":[0.0014842357,0.00021292602,0.00003187594,0.00006957903,0.0000442762,0.000044901237,0.0000055509536,0.12456374,0.18594925,0.6731965,0.013601564,0.00079564005],"about_ca_topic_score_codex":0.000032202766,"about_ca_topic_score_gemma":0.000118308046,"teacher_disagreement_score":0.545053,"about_ca_system_score_codex":0.00031913794,"about_ca_system_score_gemma":0.000049847284,"threshold_uncertainty_score":0.9998767},"labels":[],"label_agreement":null},{"id":"W3198387749","doi":"10.1007/s10044-021-01023-6","title":"Batch and online variational learning of hierarchical Dirichlet process mixtures of multivariate Beta distributions in medical applications","year":2021,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Interpretability; Latent Dirichlet allocation; Computer science; Cluster analysis; Machine learning; Artificial intelligence; Multivariate statistics; Health care; Process (computing); Task (project management); Hierarchical clustering; Data mining; Topic model","score_opus":0.011169136132250323,"score_gpt":0.31091202498829634,"score_spread":0.299742888856046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198387749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008518641,0.0003017513,0.9890569,0.0017744033,0.0000038374046,0.00014451651,0.00010464431,0.000013853351,0.00008143803],"genre_scores_gemma":[0.9210544,0.00016046088,0.07825914,0.00006885496,0.000031526113,0.00014972004,0.00025213227,0.0000041428525,0.00001962609],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986493,0.00014388887,0.0004265633,0.00039213515,0.00025946248,0.00012864944],"domain_scores_gemma":[0.9989432,0.00030173405,0.00016277295,0.00029339787,0.00018524371,0.00011364623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000346045,0.00009851401,0.000317498,0.00016895267,0.00009980915,0.000029855919,0.00024957038,0.00008279944,0.000023185894],"category_scores_gemma":[0.000052343916,0.00009170989,0.000078736215,0.0015022522,0.00009746453,0.00007117795,0.00015677573,0.0002059488,3.009715e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027895335,0.0009519847,0.08469644,0.00012627934,0.00039230048,0.0000026191958,0.0005842773,0.0002801572,0.002347483,0.48868817,0.000005833188,0.42192167],"study_design_scores_gemma":[0.00069520756,0.000026561054,0.37313786,0.000050891715,0.00047423408,0.00001608083,0.00006242499,0.55780476,0.0029257222,0.063324094,0.0011614873,0.0003206388],"about_ca_topic_score_codex":0.00009511895,"about_ca_topic_score_gemma":0.00012835016,"teacher_disagreement_score":0.9125357,"about_ca_system_score_codex":0.000008004838,"about_ca_system_score_gemma":0.000091128255,"threshold_uncertainty_score":0.37398204},"labels":[],"label_agreement":null},{"id":"W3199132933","doi":"10.1007/s00521-021-06483-9","title":"A Bayesian sampling framework for asymmetric generalized Gaussian mixture models learning","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain Monte Carlo; Gibbs sampling; Computer science; Gaussian; Bayesian probability; Mixture model; Variable-order Bayesian network; Benchmark (surveying); Artificial intelligence; Bayesian inference; Machine learning; Importance sampling; Cluster analysis; Sampling (signal processing); Monte Carlo method; Algorithm; Mathematics; Statistics","score_opus":0.039191499840373664,"score_gpt":0.32614527791209974,"score_spread":0.28695377807172606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199132933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006803438,0.001199446,0.9949062,0.0018503958,0.0001102812,0.00032264588,0.000003878594,0.00025761704,0.0006692052],"genre_scores_gemma":[0.30806413,0.00003434616,0.69087607,0.00060337613,0.00025248402,0.000054039516,0.000010990444,0.000015446127,0.00008911467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841446,0.00013208644,0.0002738943,0.00067235954,0.00014306807,0.00036413711],"domain_scores_gemma":[0.9985522,0.00057951227,0.00012433152,0.00044135534,0.00013820795,0.00016441874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030174214,0.00018872615,0.00025516888,0.000103793755,0.0007218514,0.00034111008,0.00036076683,0.00013508477,0.0000013971967],"category_scores_gemma":[0.00008708314,0.00018331142,0.000113792186,0.00085966836,0.000028688904,0.00015231654,0.00021453622,0.0003845842,0.0000012193958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014201413,0.000021005022,0.000024769859,0.00002393525,0.000009680964,0.0000011609035,0.00017183722,0.004075644,0.00030397304,0.6284759,0.0000398778,0.36685082],"study_design_scores_gemma":[0.00016662198,0.000018360877,0.000051184474,0.000022889926,0.00001249392,0.000034687502,0.000013785069,0.6611805,0.0003234666,0.33462074,0.003385504,0.00016977967],"about_ca_topic_score_codex":0.0000054495217,"about_ca_topic_score_gemma":0.0000010529615,"teacher_disagreement_score":0.65710485,"about_ca_system_score_codex":0.000017129765,"about_ca_system_score_gemma":0.00005020891,"threshold_uncertainty_score":0.7475223},"labels":[],"label_agreement":null},{"id":"W3200683212","doi":"10.3390/e23091206","title":"Generalized Poisson Hurdle Model for Count Data and Its Application in Ear Disease","year":2021,"lang":"en","type":"article","venue":"Entropy","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre de Recherches Mathématiques","keywords":"Count data; Poisson distribution; Generalized linear model; Estimator; Quasi-likelihood; Zero-inflated model; Poisson regression; Statistics; Mathematics; Variance (accounting); Applied mathematics; Generalized estimating equation; Zero (linguistics); Overdispersion; Medicine; Population","score_opus":0.042139067267646324,"score_gpt":0.31483766543651376,"score_spread":0.27269859816886743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200683212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008917539,0.0013708988,0.9868468,0.0024885286,0.00005403538,0.00022392267,0.000052004943,0.000024932027,0.000021333055],"genre_scores_gemma":[0.20325571,0.00014795786,0.79530543,0.0006399178,0.000068505506,0.00006201532,0.00007657884,0.000008878576,0.00043501332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991733,0.000049684386,0.00011495775,0.00041441494,0.000098733646,0.00014891966],"domain_scores_gemma":[0.9991937,0.000025007868,0.000032396612,0.000616384,0.000040177852,0.000092308546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023297656,0.00007086491,0.00010384507,0.000023996596,0.00004233702,0.000059825932,0.00036320416,0.000028293416,0.0000018666115],"category_scores_gemma":[0.000046683337,0.00006763971,0.00001780365,0.000096827716,0.000006638218,0.00024063747,0.00023870793,0.000044005825,0.000002423515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023662526,0.00007279039,0.000110578425,0.000033033182,0.000006250297,0.000007785352,0.0002517351,0.0005010269,0.011978936,0.96077836,0.0011993404,0.025036506],"study_design_scores_gemma":[0.00043320248,0.0000043684195,0.00016155126,0.0000059346794,0.0000058216115,0.0000011307984,0.0000010888043,0.9251958,0.00093962107,0.0707035,0.0024707732,0.00007717409],"about_ca_topic_score_codex":0.000005863982,"about_ca_topic_score_gemma":0.000008559975,"teacher_disagreement_score":0.92469484,"about_ca_system_score_codex":0.000017319255,"about_ca_system_score_gemma":0.00007832221,"threshold_uncertainty_score":0.27582672},"labels":[],"label_agreement":null},{"id":"W3200858256","doi":"10.1002/sta4.421","title":"Parsimonious mixture‐of‐experts based on mean mixture of multivariate normal distributions","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Cluster analysis; Multivariate normal distribution; Expectation–maximization algorithm; Mixture model; Data set; Artificial intelligence; Mathematics; Computer science; Robust regression; Statistics; Machine learning; Regression; Maximum likelihood","score_opus":0.014208667951048538,"score_gpt":0.27375741864971326,"score_spread":0.25954875069866473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200858256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034887039,0.00020761427,0.9929244,0.00091419066,0.00038693284,0.00010831184,0.00013928447,0.000044651806,0.0017858937],"genre_scores_gemma":[0.57149625,0.000009254244,0.4280452,0.00023052518,0.000031772335,0.0000061880864,0.00003237304,0.000008312149,0.00014009594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984671,0.0002562368,0.0002984646,0.00037976785,0.00030632011,0.0002920969],"domain_scores_gemma":[0.99854535,0.0002186057,0.00013937021,0.00075277855,0.00022441195,0.00011950647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027088518,0.00017028498,0.00029078373,0.00006433048,0.000084994965,0.00003346507,0.00042921,0.00010635693,0.000029109655],"category_scores_gemma":[0.000108252345,0.00014485556,0.00015880947,0.00042799357,0.0000647597,0.00013072898,0.00012774533,0.00015378724,0.0000025078514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014806415,0.0016726742,0.0005778524,0.00025026375,0.00017736753,0.00038523742,0.0055416273,0.0012273472,0.12567224,0.62650615,0.009451065,0.22839011],"study_design_scores_gemma":[0.0023478428,0.0004801124,0.0022752432,0.00028437705,0.00006665363,0.000030145246,0.00006876405,0.17334114,0.7591497,0.04464023,0.016541239,0.00077460305],"about_ca_topic_score_codex":0.00003885646,"about_ca_topic_score_gemma":0.000028237737,"teacher_disagreement_score":0.63347745,"about_ca_system_score_codex":0.000029252675,"about_ca_system_score_gemma":0.00018830998,"threshold_uncertainty_score":0.5907038},"labels":[],"label_agreement":null},{"id":"W3202723447","doi":"10.1002/cjs.11655","title":"Bayesian spline smoothing with ambiguous penalties","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science Foundation","keywords":"Smoothing; Penalty method; Spline (mechanical); Smoothing spline; Mathematical optimization; Nonparametric statistics; Computer science; Bayesian probability; Ambiguity; Function (biology); Constraint (computer-aided design); Prior probability; Mathematics; Econometrics; Artificial intelligence; Spline interpolation; Engineering","score_opus":0.014177393783026614,"score_gpt":0.22237741372038106,"score_spread":0.20820001993735443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202723447","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046680454,0.00067354966,0.9959939,0.0012398103,0.00041218873,0.00002688682,0.000038441816,0.0000061489463,0.0011422441],"genre_scores_gemma":[0.10070242,0.000027734233,0.89796543,0.00073491636,0.000120764955,3.4571568e-7,0.0000021113003,0.000012258844,0.0004339888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893373,0.000091242226,0.00030549796,0.0001461995,0.00021641787,0.00030689314],"domain_scores_gemma":[0.99825865,0.00007528122,0.00019222038,0.00025795627,0.0005565208,0.0006593624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034205528,0.00011796101,0.00023253949,0.00015464786,0.00014859978,0.00027217844,0.00041369282,0.00004503666,0.000058818896],"category_scores_gemma":[0.00015493456,0.000099159246,0.000038450937,0.00025486405,0.000068540365,0.00023833549,0.000019765244,0.00028763353,0.0000028902662],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000106859525,0.000026811158,0.00078368495,0.00006644322,0.00011836475,0.019198485,0.0029784085,0.0003566564,0.0001580849,0.5735956,0.015128212,0.38757858],"study_design_scores_gemma":[0.0037028792,0.0017100561,0.014443327,0.0011781215,0.00033461372,0.02562575,0.0008547297,0.07535971,0.004917978,0.76753896,0.10220325,0.0021306155],"about_ca_topic_score_codex":0.0010319604,"about_ca_topic_score_gemma":0.012767403,"teacher_disagreement_score":0.38544798,"about_ca_system_score_codex":0.000082683044,"about_ca_system_score_gemma":0.003028655,"threshold_uncertainty_score":0.71245104},"labels":[],"label_agreement":null},{"id":"W3202737858","doi":"10.1007/s10182-021-00419-3","title":"A Bayesian nonparametric multi-sample test in any dimension","year":2021,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Dirichlet process; Nonparametric statistics; Prior probability; Dirichlet distribution; Statistics; Multivariate statistics; Dimension (graph theory); Bayesian probability; Multivariate normal distribution; Population; Sample (material); Combinatorics; Mathematical analysis","score_opus":0.013346212943969758,"score_gpt":0.3215683268169546,"score_spread":0.3082221138729848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202737858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045406245,0.0014102202,0.99735916,0.00021955317,0.00007602454,0.000078939884,0.000066775785,0.00003153622,0.000303746],"genre_scores_gemma":[0.31097287,0.0002198816,0.6885567,0.00014817933,0.000009695222,0.000011972861,0.000020981015,0.00000601352,0.000053736283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997565,0.00031756025,0.00051711575,0.0008013917,0.00032768745,0.00047127687],"domain_scores_gemma":[0.99593264,0.0031121369,0.0000885736,0.00059714983,0.000101085,0.000168404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005122911,0.00019331863,0.00055061985,0.0006778779,0.000057024183,0.00010142653,0.0003992088,0.000072003495,0.000095133204],"category_scores_gemma":[0.002394889,0.00017788202,0.00010691685,0.0074224635,0.000072141,0.00046693825,0.00023288821,0.00025777635,0.000010191589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012135082,0.0009161831,0.18455113,0.00004248413,0.00009095355,0.0009170222,0.0003249884,0.0052814516,0.00019431608,0.17685917,0.000035381065,0.6307748],"study_design_scores_gemma":[0.0004668455,0.000049297327,0.0488612,0.00002258176,0.00008055317,0.000005413887,0.000027049515,0.8638,0.00013174475,0.085633636,0.0006365153,0.00028518468],"about_ca_topic_score_codex":0.00020914657,"about_ca_topic_score_gemma":0.002936013,"teacher_disagreement_score":0.85851854,"about_ca_system_score_codex":0.000082024075,"about_ca_system_score_gemma":0.0000738424,"threshold_uncertainty_score":0.7253818},"labels":[],"label_agreement":null},{"id":"W3204009844","doi":"10.21203/rs.3.rs-7246683/v1","title":"Sample Size Determination for Skewed and Heavy-tailed Distributions","year":2025,"lang":"en","type":"article","venue":"Research Square","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Kurtosis; Skewness; Heavy-tailed distribution; Sample size determination; Mathematics; Sample (material); Monte Carlo method; Distribution (mathematics); Statistics; Applied mathematics; Statistical physics; Pareto principle; Central limit theorem; Domain (mathematical analysis); Degrees of freedom (physics and chemistry); Limit (mathematics); Probability distribution; Mathematical analysis","score_opus":0.04488157809082638,"score_gpt":0.4200325795139338,"score_spread":0.3751510014231074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204009844","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014325393,0.00018023497,0.9929149,0.0040759,0.000078417645,0.00055343175,0.00005772385,0.000055670735,0.00065117213],"genre_scores_gemma":[0.40474686,0.00003630834,0.5941728,0.000067669804,0.000037880225,0.00020628367,0.000009594177,0.0000045094334,0.00071811094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987105,0.0002612387,0.00012972137,0.0003236391,0.00022389901,0.00035098617],"domain_scores_gemma":[0.9956767,0.0034876112,0.000018344777,0.0003656687,0.00035983758,0.00009185642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014615324,0.000072859846,0.00011499687,0.00013124257,0.00042858286,0.00021877748,0.000335937,0.00006791732,0.000007075055],"category_scores_gemma":[0.0029085146,0.000064868065,0.000047191465,0.00057359465,0.000069904985,0.0001909747,0.00022968746,0.0001546847,0.0000020730492],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022036998,0.000045930126,0.00030339387,0.000118150296,0.0000065469303,0.0000015328465,0.00013661536,3.9025085e-7,0.00050490827,0.6600788,0.00203056,0.3367511],"study_design_scores_gemma":[0.00068309566,0.00019138672,0.007227207,0.00011176199,0.000005287838,0.0000022369145,0.000028463952,0.08692415,0.0055752415,0.87874526,0.02036647,0.00013946964],"about_ca_topic_score_codex":0.00003252168,"about_ca_topic_score_gemma":0.000019358213,"teacher_disagreement_score":0.40331432,"about_ca_system_score_codex":0.00006925217,"about_ca_system_score_gemma":0.00015266672,"threshold_uncertainty_score":0.34819737},"labels":[],"label_agreement":null},{"id":"W3204314768","doi":"10.1214/21-ba1290","title":"Functional Central Limit Theorems for Stick-Breaking Priors","year":2021,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Mathematics; Central limit theorem; Dirichlet process; Applied mathematics; Dirichlet distribution; Limit (mathematics); Prior probability; Mathematical analysis; Bayesian probability; Statistics","score_opus":0.01910684797705753,"score_gpt":0.2575463279633895,"score_spread":0.23843947998633197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204314768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045903938,0.00024493434,0.9947339,0.001517321,0.00031157504,0.000112628644,0.00001204165,0.00010856483,0.0024999527],"genre_scores_gemma":[0.3392942,0.000014061269,0.6584479,0.00061909115,0.00019768575,0.000019749523,0.000033866505,0.00001335852,0.0013600932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979783,0.00017456234,0.0003282935,0.0006933384,0.00031952755,0.00050597097],"domain_scores_gemma":[0.9984689,0.00024849374,0.00012158675,0.00074895914,0.00020487941,0.00020717632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047548194,0.00020023776,0.00039345544,0.00025945596,0.00021809057,0.00028118954,0.00046074783,0.000102798454,0.00018380716],"category_scores_gemma":[0.00013240667,0.00018401015,0.0006606864,0.0017576288,0.00004018842,0.00026244737,0.00013260113,0.00012647739,0.000009745888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014746388,0.00011487104,0.0013629732,0.000020609037,0.0012177823,0.000042088002,0.00052464794,0.0007799933,0.0008847753,0.8505992,0.0013667576,0.1430715],"study_design_scores_gemma":[0.0008390943,0.000061147184,0.020385591,0.00002627449,0.002055862,0.000045883175,0.00010034481,0.7849555,0.00535456,0.17738833,0.007999878,0.00078753295],"about_ca_topic_score_codex":0.000015199074,"about_ca_topic_score_gemma":0.000057466776,"teacher_disagreement_score":0.7841755,"about_ca_system_score_codex":0.000060602528,"about_ca_system_score_gemma":0.00018662236,"threshold_uncertainty_score":0.7503716},"labels":[],"label_agreement":null},{"id":"W3204460067","doi":"10.1080/01621459.2021.1987250","title":"Model-assisted estimation through random forests in finite population sampling","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Variance (accounting); Statistics; Point estimation; Computer science; Estimation; Population; Small area estimation; Variety (cybernetics); Sampling (signal processing); Calibration; Sample (material); Econometrics; Variable (mathematics); Random effects model; Sample size determination; Mathematics; Engineering","score_opus":0.16655612615127796,"score_gpt":0.23908750850592436,"score_spread":0.0725313823546464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204460067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073457114,0.000012919595,0.9254414,0.0002733794,0.00005161328,0.00014428503,0.0000014962005,0.000113653026,0.00050416845],"genre_scores_gemma":[0.72248685,0.0000074970294,0.27721396,0.00023268987,0.000013192242,3.5368816e-7,0.000005614278,0.000005490071,0.000034360957],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990423,0.000105216204,0.00015582705,0.0004473232,0.00005888156,0.00019049662],"domain_scores_gemma":[0.9994122,0.00011674935,0.00008788868,0.00026450187,0.00003609278,0.00008260883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016811528,0.00012067495,0.0001747806,0.00007629039,0.000084241976,0.000050154344,0.00038439737,0.000080266946,0.0000036249744],"category_scores_gemma":[0.00007507119,0.00013275357,0.000068223424,0.0007430874,0.000017108105,0.0009331038,0.000119208555,0.00013459494,0.000010764087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040246843,0.000016525166,0.0017965779,0.000010633736,0.000004777392,0.000020250121,0.0004121925,0.776856,0.000043538934,0.21504714,0.000011801576,0.005740334],"study_design_scores_gemma":[0.0008816359,0.000018230847,0.003544361,0.000015797295,0.000008027842,8.500389e-7,0.000004477265,0.8181155,0.000029042892,0.177248,0.000011994073,0.00012212085],"about_ca_topic_score_codex":0.00006868617,"about_ca_topic_score_gemma":0.000063412,"teacher_disagreement_score":0.64902973,"about_ca_system_score_codex":0.00005753921,"about_ca_system_score_gemma":0.000032166132,"threshold_uncertainty_score":0.54135334},"labels":[],"label_agreement":null},{"id":"W3205092057","doi":"10.1002/cjs.11651","title":"Testing homogeneity in contaminated mixture models","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Homogeneity (statistics); Limiting; Computer science; Null hypothesis; Mathematics; Biological system; Statistics; Engineering","score_opus":0.036054772577676704,"score_gpt":0.2493521132847954,"score_spread":0.2132973407071187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205092057","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004161878,0.0006763433,0.99298465,0.00036771936,0.00038368648,0.000033009695,0.00006945846,0.0000036193358,0.0013196378],"genre_scores_gemma":[0.28950188,0.000007808576,0.7100457,0.0003170108,0.00004030685,3.2764788e-7,0.0000018671458,0.000006304783,0.00007880054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873394,0.00019772013,0.0004488807,0.00015581978,0.00016611587,0.00029750745],"domain_scores_gemma":[0.998081,0.00024824686,0.00019738643,0.00023894584,0.0007596461,0.00047472309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006537105,0.00010513449,0.00026073307,0.00018769431,0.000071376744,0.00013982327,0.00043581804,0.0000729377,0.000017891341],"category_scores_gemma":[0.0007216405,0.000101776044,0.000037251473,0.0005147765,0.000037140682,0.00024609055,0.000024396466,0.00032216447,0.000001719507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031305742,0.00003347941,0.0043214615,0.000036950274,0.000037238467,0.016073821,0.0017181808,0.0014003542,0.0009553997,0.59179306,0.008071958,0.375555],"study_design_scores_gemma":[0.00095819135,0.00014750811,0.024544533,0.00023624772,0.000030336523,0.0024096435,0.00007822788,0.21536118,0.0014467919,0.75134933,0.002988004,0.0004499894],"about_ca_topic_score_codex":0.0010893412,"about_ca_topic_score_gemma":0.017007435,"teacher_disagreement_score":0.375105,"about_ca_system_score_codex":0.00012502878,"about_ca_system_score_gemma":0.002804718,"threshold_uncertainty_score":0.9490548},"labels":[],"label_agreement":null},{"id":"W3208335533","doi":"10.1007/s10994-023-06340-x","title":"A moment-matching metric for latent variable generative models","year":2023,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Canadian Statistical Sciences Institute; University of Toronto","keywords":"Latent variable; Metric (unit); Regularization (linguistics); Gaussian; Matrix norm; Computer science; Latent variable model; Mathematics; Applied mathematics; Moment (physics); Generative grammar; Norm (philosophy); Artificial intelligence; Algorithm; Mathematical optimization","score_opus":0.060794617866384765,"score_gpt":0.30770584740672646,"score_spread":0.2469112295403417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208335533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017269565,0.0010995961,0.99363476,0.0012001175,0.001081965,0.00075081724,0.00003677974,0.0007447531,0.0012785244],"genre_scores_gemma":[0.0098286,0.0001374835,0.9815159,0.00026610633,0.00032026507,0.00036310925,0.00010232763,0.00009382892,0.0073723653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680036,0.0004505894,0.0005001751,0.0012159575,0.00040900163,0.00062392856],"domain_scores_gemma":[0.9981181,0.00042318652,0.00037499226,0.00076859054,0.00015597808,0.00015913315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022047143,0.00047254557,0.0006625759,0.0005502958,0.0004678814,0.00056539406,0.0012832775,0.00031098354,0.000008124952],"category_scores_gemma":[0.00014432504,0.00043553798,0.0002857544,0.00062288396,0.000018798042,0.0002777175,0.0024030826,0.0013089908,0.000013650957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071953095,0.00003118577,0.000021711136,0.00016832029,0.00013466577,0.0000101854885,0.0013542571,0.7356918,0.00020646305,0.23222834,0.00030806495,0.029837847],"study_design_scores_gemma":[0.00020035073,0.000042212836,0.000006921255,0.00007301832,0.000028298591,0.000003038877,0.0000032858065,0.61692166,0.00007986311,0.3809542,0.0013933969,0.00029371493],"about_ca_topic_score_codex":0.00056968146,"about_ca_topic_score_gemma":0.000010334564,"teacher_disagreement_score":0.14872587,"about_ca_system_score_codex":0.0001501376,"about_ca_system_score_gemma":0.00016710523,"threshold_uncertainty_score":0.9998096},"labels":[],"label_agreement":null},{"id":"W3208459932","doi":"10.1109/isie45552.2021.9576233","title":"Online Variational Learning of Shifted Scaled Dirichlet Mixture","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Agence Nationale de la Recherche","keywords":"Cluster analysis; Computer science; Artificial intelligence; Unsupervised learning; Machine learning; Mixture model; Set (abstract data type); Dirichlet distribution; Data set; Data modeling; Latent Dirichlet allocation; Online learning; Data mining; Scale (ratio); Pattern recognition (psychology); Topic model; Mathematics","score_opus":0.013881141981996291,"score_gpt":0.26569240219908213,"score_spread":0.25181126021708583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208459932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030163487,0.00015489281,0.9885864,0.002045132,0.0001376046,0.000033820885,0.0000030262233,0.000071884795,0.005950842],"genre_scores_gemma":[0.055218324,0.000010217285,0.9409648,0.00054770574,0.00006707277,0.0000014247105,0.000016468042,0.0000049740925,0.0031689927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990141,0.00017969488,0.00019305467,0.00025940695,0.00021411102,0.0001396659],"domain_scores_gemma":[0.9992597,0.00014808262,0.000067684094,0.0002738902,0.00019132608,0.00005930819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025472126,0.00008297331,0.00016069572,0.00004560841,0.00004803509,0.000038458144,0.00028312017,0.00006996904,0.00016053487],"category_scores_gemma":[0.0001410722,0.00006979264,0.00006841197,0.00044248725,0.00001561522,0.00014935057,0.00016389592,0.0001640454,0.000005348785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026166283,0.00016332087,0.00036131896,0.000012685327,0.000025366782,0.00001874291,0.00025626295,0.000067531335,0.0056464565,0.9432748,0.0005361351,0.04963478],"study_design_scores_gemma":[0.0011581952,0.00010754192,0.03152432,0.00006081814,0.000029687832,0.000080809135,0.0000314099,0.62989026,0.02574225,0.29726186,0.013619194,0.0004936452],"about_ca_topic_score_codex":0.000006554141,"about_ca_topic_score_gemma":0.000005450437,"teacher_disagreement_score":0.6460129,"about_ca_system_score_codex":0.000009240362,"about_ca_system_score_gemma":0.00011518366,"threshold_uncertainty_score":0.28460613},"labels":[],"label_agreement":null},{"id":"W3208584122","doi":"10.1002/sam.11555","title":"A family of mixture models for biclustering","year":2021,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Biclustering; Cluster analysis; Diagonal; Covariance matrix; Latent variable; Covariance; Block matrix; Mathematics; Algorithm; Computer science; Matrix (chemical analysis); Pattern recognition (psychology); Data mining; Artificial intelligence; Statistics; Correlation clustering; CURE data clustering algorithm; Eigenvalues and eigenvectors","score_opus":0.11421512759505388,"score_gpt":0.3767657191606953,"score_spread":0.2625505915656414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208584122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011967275,0.0005243613,0.99533975,0.0009812521,0.00012909019,0.000048967773,0.0016695552,0.0000074358195,0.00010288678],"genre_scores_gemma":[0.06981896,0.00020860002,0.9294482,0.00027579482,0.000066744884,0.0000010202932,0.0001599512,0.000004032351,0.00001673279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759156,0.00015090198,0.00045808224,0.00082760473,0.00061022956,0.00036165467],"domain_scores_gemma":[0.99569994,0.00076252234,0.00022642608,0.0027822377,0.0003103498,0.00021852463],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0066537624,0.00012699275,0.0003590082,0.00019294865,0.00061883504,0.0009568013,0.0054740496,0.00003314498,0.0000085194715],"category_scores_gemma":[0.0012498514,0.000078168116,0.00004956126,0.0017806108,0.00042305022,0.0026241257,0.004622164,0.00018732384,2.9357813e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028275701,0.00010564874,0.00037469144,0.000041978394,0.0005754113,0.00006649732,0.0010139056,0.00037438277,0.0045834626,0.23281266,0.007316781,0.7527063],"study_design_scores_gemma":[0.00014474426,0.00003061146,0.0011921007,0.000021111717,0.00036802038,0.00010363193,0.00015704944,0.95978165,0.000077994475,0.037464816,0.0005448508,0.000113442606],"about_ca_topic_score_codex":0.000029823485,"about_ca_topic_score_gemma":0.000029767773,"teacher_disagreement_score":0.95940727,"about_ca_system_score_codex":0.000011212892,"about_ca_system_score_gemma":0.00043652116,"threshold_uncertainty_score":0.99990684},"labels":[],"label_agreement":null},{"id":"W3210195101","doi":"10.1109/isie45552.2021.9576224","title":"Inverted Dirichlet State Space Model for Time Series Forecasting","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Inference; Dirichlet distribution; Series (stratigraphy); Latent Dirichlet allocation; Applied mathematics; Time series; State space; State-space representation; Latent variable; Computer science; Mathematics; Mathematical optimization; Algorithm; Topic model; Artificial intelligence; Statistics; Mathematical analysis","score_opus":0.03869101775410788,"score_gpt":0.2617709655562732,"score_spread":0.22307994780216533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210195101","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039267514,0.000059307527,0.99050766,0.0027408758,0.00009401166,0.00012659082,0.000007284768,0.00016238185,0.0059092245],"genre_scores_gemma":[0.003926248,0.0000061442743,0.94915915,0.0009649726,0.000026634694,0.000017304636,0.0000043651316,0.0000122026595,0.045882992],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901134,0.000050750736,0.00015766543,0.00036274956,0.000121222576,0.00029630048],"domain_scores_gemma":[0.9992052,0.00010070256,0.000046405014,0.0003830124,0.0001715589,0.0000931402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002867064,0.00012343282,0.00017386455,0.00003603084,0.000107599495,0.00015425414,0.0002981327,0.000043148157,0.000015608748],"category_scores_gemma":[0.00008878236,0.00010644981,0.000073684176,0.00024527765,0.000018611861,0.0005004796,0.00021695941,0.00006645889,0.000011750698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024874542,0.00008113088,0.000026624279,0.00008304751,0.000065442895,0.000050998515,0.0026725656,0.0031971068,0.01627851,0.6771786,0.03397251,0.26636857],"study_design_scores_gemma":[0.0001493525,0.00001822342,0.0000027691199,0.000007672585,0.0000036377505,0.000017960727,0.000002851046,0.78779435,0.01129383,0.19966574,0.00091900956,0.00012460945],"about_ca_topic_score_codex":0.000004374962,"about_ca_topic_score_gemma":0.000016557218,"teacher_disagreement_score":0.7845972,"about_ca_system_score_codex":0.00001639479,"about_ca_system_score_gemma":0.00013509892,"threshold_uncertainty_score":0.43408972},"labels":[],"label_agreement":null},{"id":"W3210309470","doi":"10.1080/03610918.2021.1995753","title":"Generalized Birnbaum–Saunders mixture cure frailty model: inferential method and an application to bone marrow transplant data","year":2021,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Inference; Unobservable; Similarity (geometry); Likelihood function; Flexibility (engineering); Monte Carlo method; Computer science; Mixture model; Maximum likelihood; Marginal likelihood; Statistics; Mathematics; Artificial intelligence; Econometrics; Image (mathematics)","score_opus":0.17312460348140563,"score_gpt":0.4662218811548981,"score_spread":0.2930972776734925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210309470","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012807983,0.00036985835,0.9959749,0.0015588515,0.000055861343,0.00036072166,0.00023527669,0.00008011257,0.0000836037],"genre_scores_gemma":[0.42196423,0.00015847152,0.57638794,0.00032161755,0.000012944118,0.000018734507,0.0011132472,0.000010258187,0.000012558323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784243,0.0006727355,0.00047870947,0.0006138709,0.00021488506,0.0001773933],"domain_scores_gemma":[0.99728006,0.0005251661,0.00013998625,0.0016425864,0.00026015812,0.00015201925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006623417,0.00018310927,0.0002517324,0.00017974654,0.0002779443,0.00027462767,0.0006894184,0.00012161881,0.0000026909854],"category_scores_gemma":[0.00007966645,0.00020533055,0.00001675322,0.00048639614,0.000058608715,0.00057641655,0.00055078155,0.0002308717,0.0000013559411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013723492,0.00010659535,0.00010700694,0.000025731893,0.00001270187,0.000001722303,0.0019845804,0.34093443,0.0005869606,0.30364922,0.00010417298,0.35247317],"study_design_scores_gemma":[0.00048061527,0.000019980023,0.0008454076,0.000018505478,0.000024141162,0.0000072173984,0.000022588818,0.8157202,0.00002705226,0.18213813,0.0005075436,0.00018864767],"about_ca_topic_score_codex":0.00004841503,"about_ca_topic_score_gemma":0.00037716381,"teacher_disagreement_score":0.47478577,"about_ca_system_score_codex":0.0000361168,"about_ca_system_score_gemma":0.00011854365,"threshold_uncertainty_score":0.83731365},"labels":[],"label_agreement":null},{"id":"W3211668472","doi":"10.1002/sta4.437","title":"A partial EM algorithm for model‐based clustering with highly diverse missing data patterns","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Missing data; Expectation–maximization algorithm; Computer science; Algorithm; Cluster analysis; Mixture model; Convergence (economics); Computation; Divergence (linguistics); Gaussian; Data mining; Mathematics; Artificial intelligence; Machine learning; Statistics; Maximum likelihood","score_opus":0.06896115937110447,"score_gpt":0.3166993067351346,"score_spread":0.2477381473640301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211668472","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037891482,0.000044943998,0.9982363,0.00064631674,0.00020346836,0.00013701714,0.00021493214,0.000078578814,0.000059538303],"genre_scores_gemma":[0.014261979,0.0000032943833,0.9847461,0.00067316054,0.00008831243,0.000011732213,0.00006762121,0.00001540091,0.00013241163],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987115,0.0000658123,0.0001416736,0.0005743242,0.00019355686,0.00031311932],"domain_scores_gemma":[0.99868655,0.000070289556,0.00005554605,0.0009878897,0.00008216985,0.00011754358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025378878,0.00013517561,0.00016553864,0.000032648404,0.00014421188,0.00025117124,0.00062982313,0.00003996392,0.0000053212366],"category_scores_gemma":[0.00001391347,0.00011448725,0.00003861464,0.00012005182,0.000016440223,0.0004535918,0.00046830883,0.000085129504,0.0000014414323],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012373424,0.000040092204,0.000015669706,0.000037117727,0.000020110085,0.0001018128,0.00052014727,0.0013690238,0.00030464437,0.001037861,0.0004179061,0.99612325],"study_design_scores_gemma":[0.0006640702,0.0000452069,0.000008773122,0.000049617247,0.000019434447,0.000011396538,0.000028931634,0.99354076,0.0024573072,0.0019825443,0.0010148044,0.00017712632],"about_ca_topic_score_codex":0.0000151336,"about_ca_topic_score_gemma":0.00006011747,"teacher_disagreement_score":0.9959461,"about_ca_system_score_codex":0.000022794784,"about_ca_system_score_gemma":0.00020510748,"threshold_uncertainty_score":0.46686548},"labels":[],"label_agreement":null},{"id":"W3211963602","doi":"10.1109/iecon48115.2021.9589943","title":"Stochastic Expectation Propagation Learning of Infinite Multivariate Beta Mixture Models for Human Tissue Analysis","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multivariate statistics; Computer science; Stochastic process; Multivariate analysis; Artificial intelligence; BETA (programming language); Machine learning; Mathematics; Statistics","score_opus":0.030444696263369705,"score_gpt":0.31407271235409306,"score_spread":0.28362801609072336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211963602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026980476,0.00006216903,0.99607116,0.00017087618,0.000056564346,0.00023241878,0.000002855965,0.00007381665,0.0006320646],"genre_scores_gemma":[0.5355764,7.7050515e-7,0.46379027,0.00002424396,0.000020901085,0.000022235823,0.000027360174,0.0000055659534,0.00053225347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872535,0.00018125909,0.00032199122,0.0003988368,0.00019884521,0.0001736904],"domain_scores_gemma":[0.99880385,0.00016273552,0.00019026393,0.00033767472,0.0004507879,0.00005470378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003648145,0.00012508426,0.00028888742,0.0002125877,0.00013575323,0.00007736652,0.00022713054,0.00008532416,0.000016610882],"category_scores_gemma":[0.000083767925,0.000112967406,0.00013361569,0.0008809863,0.000016717966,0.0004051435,0.00008245892,0.00010490327,9.897251e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000656701,0.00006678788,0.000022613287,0.00004434498,0.00022220562,0.0000020834982,0.0036546648,0.116846345,0.06605215,0.7756057,0.000015145107,0.037461407],"study_design_scores_gemma":[0.0002824224,0.00006298251,0.00019286024,0.000013308327,0.00014229158,0.0000013419478,0.000042579726,0.90723985,0.036815636,0.0550556,0.000015906377,0.00013522571],"about_ca_topic_score_codex":0.000041718627,"about_ca_topic_score_gemma":0.000027256012,"teacher_disagreement_score":0.7903935,"about_ca_system_score_codex":0.000018227522,"about_ca_system_score_gemma":0.000055494354,"threshold_uncertainty_score":0.46066773},"labels":[],"label_agreement":null},{"id":"W3213258851","doi":"10.1080/10618600.2021.1999825","title":"Mixtures of Matrix-Variate Contaminated Normal Distributions","year":2021,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random variate; Cluster analysis; Computer science; Expectation–maximization algorithm; Data mining; Matrix (chemical analysis); Data Matrix; Algorithm; Artificial intelligence; Statistics; Mathematics; Maximum likelihood; Random variable","score_opus":0.00868830389333632,"score_gpt":0.275012658105719,"score_spread":0.2663243542123827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213258851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007304056,0.0005105906,0.9908609,0.0009130321,0.00017238091,0.000024314926,0.00015970923,0.0000051835123,0.000049876267],"genre_scores_gemma":[0.38332552,0.0000522267,0.6164835,0.000077612356,0.000029897968,2.4140294e-7,0.000013357482,0.0000021012415,0.000015575955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988381,0.00014859647,0.00047757354,0.000106638974,0.00031420484,0.00011484508],"domain_scores_gemma":[0.9980315,0.0005899434,0.00028888302,0.00007297185,0.00089045486,0.00012627196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031070894,0.00008497441,0.00024413371,0.0000822509,0.00007722945,0.00005839425,0.00016374867,0.000053709588,0.000012114505],"category_scores_gemma":[0.0001656473,0.000069110385,0.000073978685,0.00031237167,0.000092577284,0.00013503556,0.00006611187,0.00019058303,3.347132e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015349711,0.000096430136,0.000309057,0.000023446566,0.000060154154,0.00011746569,0.000069594375,0.0003444777,0.000279963,0.97887695,0.0006885961,0.019118508],"study_design_scores_gemma":[0.00056330924,0.00014939475,0.039161447,0.00003076989,0.000038066013,0.0004760034,0.000004290132,0.038089283,0.00042270377,0.9205288,0.00044333976,0.00009256488],"about_ca_topic_score_codex":0.0000031402876,"about_ca_topic_score_gemma":0.0000013138583,"teacher_disagreement_score":0.37602144,"about_ca_system_score_codex":0.000007826875,"about_ca_system_score_gemma":0.00015810199,"threshold_uncertainty_score":0.28182396},"labels":[],"label_agreement":null},{"id":"W3214669781","doi":"10.1109/tpami.2021.3128271","title":"Unsupervised Grouped Axial Data Modeling via Hierarchical Bayesian Nonparametric Models With Watson Distributions","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Dirichlet process; Hierarchical Dirichlet process; Cluster analysis; Nonparametric statistics; Bayesian inference; Inference; Bayesian probability; Pattern recognition (psychology); Hierarchical database model; Bayes' theorem","score_opus":0.04088356343208351,"score_gpt":0.2862290134686316,"score_spread":0.2453454500365481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214669781","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006890523,0.00024804645,0.9973727,0.0009948323,0.00012522376,0.00014935981,0.0002354311,0.00011309164,0.00007226078],"genre_scores_gemma":[0.80677193,0.0004988949,0.19221465,0.0003103042,0.000027008928,0.000018549828,0.00009598909,0.000017170605,0.000045523688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969006,0.00030831504,0.0005366077,0.0013183719,0.00048858556,0.00044750824],"domain_scores_gemma":[0.99739534,0.00020586529,0.00008394449,0.0018115918,0.00018075445,0.00032252987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004694473,0.0003677246,0.0005585425,0.00055276597,0.00041942231,0.00032697295,0.0010668878,0.00013183604,0.00007267712],"category_scores_gemma":[0.00000819507,0.00029971788,0.00024360747,0.0027389706,0.00008414199,0.00071973045,0.000042200783,0.000608212,0.0000060663388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023723876,0.00034170633,0.000031242547,0.000017362789,0.00056288356,0.000054305652,0.00020390842,0.14240253,0.0001524786,0.0018069808,0.0000020746352,0.8544008],"study_design_scores_gemma":[0.0001744049,0.0000910925,0.00002168057,0.000024478575,0.0006350146,0.000059508053,0.000011197053,0.98264855,0.0077621555,0.008189892,0.000010536251,0.00037151598],"about_ca_topic_score_codex":0.0008356116,"about_ca_topic_score_gemma":0.001243394,"teacher_disagreement_score":0.8540293,"about_ca_system_score_codex":0.000045180594,"about_ca_system_score_gemma":0.00009088816,"threshold_uncertainty_score":0.9999455},"labels":[],"label_agreement":null},{"id":"W3215522589","doi":"10.1080/00949655.2022.2084093","title":"Model-based clustering via skewed matrix-variate cluster-weighted models","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Università di Catania","keywords":"Random variate; Mathematics; Cluster analysis; Matrix (chemical analysis); Statistics; Random variable","score_opus":0.028899351188574025,"score_gpt":0.32057928302422345,"score_spread":0.29167993183564944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215522589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021065301,0.000053053525,0.99690837,0.00042941052,0.00023626417,0.00013770854,0.000011580417,0.000032039785,0.000085032356],"genre_scores_gemma":[0.50951827,0.0000011692701,0.49020374,0.00023327404,0.000021996115,0.0000014752662,0.000005144032,0.0000061671853,0.000008777091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981149,0.00041211967,0.00059864984,0.00020723749,0.00049985136,0.00016724497],"domain_scores_gemma":[0.9985175,0.0006126401,0.00037397174,0.00010942011,0.00024198853,0.00014445762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095161377,0.00013091319,0.0002563088,0.00023031465,0.00027578566,0.00013686548,0.00020379765,0.000042718442,0.000013342702],"category_scores_gemma":[0.000038530554,0.00012303257,0.0000595928,0.0002321631,0.000024960713,0.00046497476,0.00012725455,0.0002747564,6.1327154e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084302264,0.000051069725,0.0000046187392,0.000016593809,0.000011054163,0.000012556871,0.00031644406,0.9013872,0.000060505565,0.03601076,0.00004002382,0.06200483],"study_design_scores_gemma":[0.00084645057,0.00016165906,0.00007268682,0.0000073207575,0.00001621222,0.000026877487,0.0000047015246,0.7067786,0.0000040554837,0.29196426,0.000019780218,0.00009742807],"about_ca_topic_score_codex":0.0000035142139,"about_ca_topic_score_gemma":5.8186356e-7,"teacher_disagreement_score":0.5074117,"about_ca_system_score_codex":0.000084810585,"about_ca_system_score_gemma":0.000102948325,"threshold_uncertainty_score":0.50171226},"labels":[],"label_agreement":null},{"id":"W3216183861","doi":"10.1109/iri51335.2021.00015","title":"A Hierarchical Nonparametric Bayesian Model Based on Scaled Dirichlet Distribution","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Dirichlet distribution; Cluster analysis; Hierarchical Dirichlet process; Artificial intelligence; Machine learning; Inference; Dirichlet process; Mixture model; Data mining; Flexibility (engineering); Hierarchical clustering; Bayesian inference; Unsupervised learning; Bayesian probability; Domain (mathematical analysis); Topic model; Latent Dirichlet allocation; Mathematics; Statistics","score_opus":0.0147331209690797,"score_gpt":0.26828402253510686,"score_spread":0.25355090156602716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216183861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003683184,0.00003392181,0.9777692,0.004394153,0.00014196914,0.000114851435,0.0000150450915,0.0001988709,0.016963681],"genre_scores_gemma":[0.3934397,0.0000034520365,0.6037156,0.002091313,0.00003271937,0.000012705515,0.000023040819,0.0000075238286,0.0006739592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979945,0.0002552476,0.0002499638,0.00066889526,0.00043572663,0.00039566692],"domain_scores_gemma":[0.9984008,0.000283037,0.000046963756,0.00089926063,0.00012245454,0.0002474922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045201596,0.0001925164,0.00024474444,0.00012818069,0.00013518539,0.00019572314,0.00052873715,0.00013131765,0.00004498652],"category_scores_gemma":[0.00022087163,0.00016073068,0.00015785194,0.0014221574,0.000038744027,0.0001888609,0.00015856858,0.00028874128,0.000030525316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018349696,0.00037394284,0.00006334781,0.000013780841,0.0000101023015,0.00008032792,0.000034070657,0.00471743,0.0005060455,0.7642666,0.0037312498,0.22618477],"study_design_scores_gemma":[0.00039348722,0.000054617583,0.00027549762,0.000013525277,0.0000063621587,0.000010412017,6.3078875e-7,0.9219635,0.0033119172,0.073233515,0.0005355934,0.0002009473],"about_ca_topic_score_codex":0.0000039482475,"about_ca_topic_score_gemma":0.0000027282201,"teacher_disagreement_score":0.91724604,"about_ca_system_score_codex":0.00007183172,"about_ca_system_score_gemma":0.00024735564,"threshold_uncertainty_score":0.6554407},"labels":[],"label_agreement":null},{"id":"W3216701780","doi":"10.1109/iri51335.2021.00018","title":"A Nonparametric Bayesian Framework for Multivariate Beta Mixture Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Computer science; Cluster analysis; Markov chain Monte Carlo; Artificial intelligence; Multivariate statistics; Model selection; Machine learning; Posterior probability; Bayesian probability; Unsupervised learning; Pattern recognition (psychology); Data mining","score_opus":0.032896244484891576,"score_gpt":0.305678424601518,"score_spread":0.2727821801166264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216701780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032851152,0.0005658841,0.9874757,0.003284502,0.00060987484,0.00032171066,0.000009812048,0.00023859728,0.00746109],"genre_scores_gemma":[0.039456062,0.00002471281,0.95583016,0.002510054,0.00016303256,0.00006130419,0.000005391977,0.000025257626,0.0019240478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99788445,0.00015934446,0.0003184875,0.00083353545,0.00027130445,0.0005328531],"domain_scores_gemma":[0.9975564,0.0007198286,0.00009161201,0.0011363091,0.0002664292,0.00022945006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048632929,0.00025256578,0.00036711417,0.00015574177,0.00016929826,0.0003145111,0.0008702182,0.00029274024,0.00004693736],"category_scores_gemma":[0.00023242958,0.00021494439,0.00025451503,0.0012524062,0.000024541238,0.000533117,0.00029374834,0.00029675392,0.000013565287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004720284,0.000074462056,0.000004561751,0.000019618306,0.000031689273,0.000017381073,0.00025144508,0.000104569575,0.00023144095,0.9068285,0.0009686629,0.09146292],"study_design_scores_gemma":[0.00023851976,0.000027569778,0.000018253091,0.000019597805,0.000011921778,0.0000167556,0.000005391005,0.4058669,0.004155341,0.58786756,0.0015673755,0.00020483267],"about_ca_topic_score_codex":0.000015484182,"about_ca_topic_score_gemma":0.000005791764,"teacher_disagreement_score":0.4057623,"about_ca_system_score_codex":0.00003301372,"about_ca_system_score_gemma":0.00017575282,"threshold_uncertainty_score":0.8765178},"labels":[],"label_agreement":null},{"id":"W3217421674","doi":"10.1109/iri51335.2021.00012","title":"Statistical Modeling Using Bounded Asymmetric Gaussian Mixtures: Application to Human Action and Gender Recognition","year":2021,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Bounded function; Mixture model; Computer science; Gaussian; Artificial intelligence; Categorization; Pattern recognition (psychology); Expectation–maximization algorithm; Gaussian process; Machine learning; Range (aeronautics); Task (project management); Model selection; Maximization; Feature (linguistics); Algorithm; Mathematics; Mathematical optimization; Statistics; Maximum likelihood","score_opus":0.11788967515129556,"score_gpt":0.36785110774417223,"score_spread":0.24996143259287668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217421674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013778411,0.000064035805,0.98340696,0.00020082369,0.000097904536,0.00015461087,0.0000023919097,0.0000858387,0.0022090373],"genre_scores_gemma":[0.3809529,0.0000071844397,0.6185451,0.00038721936,0.000054496442,0.000008793292,0.0000091321235,0.000006833334,0.0000283487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874926,0.0001351458,0.00020641218,0.0005079857,0.00019209954,0.00020908254],"domain_scores_gemma":[0.99933106,0.000053105457,0.000038722883,0.00029006542,0.0001284002,0.000158663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032497686,0.000117104115,0.00013498602,0.00016952213,0.00022567896,0.0002636846,0.00012093749,0.00008572982,0.000011161673],"category_scores_gemma":[0.000051050723,0.000113809634,0.00002601224,0.00055930455,0.0000118274975,0.00030751436,0.000105257765,0.0001184919,0.0000075056646],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046243313,0.00005732624,0.000020405747,0.0000374972,0.000016403434,0.000008392336,0.00031071014,0.00020496982,0.044315644,0.2719127,0.00008101093,0.6830303],"study_design_scores_gemma":[0.00014554628,0.000018760938,0.000136306,0.000007649372,0.000015212641,0.000044992335,0.0000203872,0.66010064,0.006080426,0.33320633,0.000059565842,0.0001641727],"about_ca_topic_score_codex":0.0000682364,"about_ca_topic_score_gemma":0.00001990469,"teacher_disagreement_score":0.68286616,"about_ca_system_score_codex":0.000059661128,"about_ca_system_score_gemma":0.00005808914,"threshold_uncertainty_score":0.4641022},"labels":[],"label_agreement":null},{"id":"W3217739957","doi":"10.1177/1471082x211059233","title":"Bayesian analysis of two-part nonlinear latent variable model: Semiparametric method","year":2021,"lang":"en","type":"article","venue":"Statistical Modelling","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Covariate; Mathematics; Collinearity; Econometrics; Statistics; Semiparametric regression; Latent variable; Bayesian probability; Semiparametric model; Population; Parametric statistics","score_opus":0.03581909957611684,"score_gpt":0.3270863331790412,"score_spread":0.29126723360292434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217739957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005537468,0.00021208302,0.9968618,0.00010293488,0.0001416238,0.00009628862,0.00015982387,0.00007876286,0.0022913173],"genre_scores_gemma":[0.017379662,0.00005150145,0.98192686,0.00022481765,0.000042868644,0.000009190861,0.000052316056,0.000021388347,0.00029141444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970157,0.00039089174,0.0007114499,0.0008411138,0.00053056265,0.0005102377],"domain_scores_gemma":[0.99724734,0.0010321593,0.0001600743,0.0008988025,0.00038279337,0.00027883882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011994769,0.00024439205,0.0007785851,0.00043103076,0.000104134364,0.00012062866,0.00052203395,0.00012273387,0.00008974204],"category_scores_gemma":[0.00018236352,0.00023434356,0.00021470363,0.0036132196,0.00004736976,0.00021264204,0.00023720929,0.0003063276,0.0000047645804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003440375,0.0000672859,0.000009391432,0.000018757913,0.00019958464,0.000017791794,0.00006689982,0.55500686,0.00015633866,0.43650472,0.00003125149,0.007917698],"study_design_scores_gemma":[0.00016497585,0.0000184061,0.0000015167963,0.000014059251,0.0004899316,0.0000046942882,0.0000017833007,0.72843236,0.00073077803,0.26989627,0.000056793182,0.00018841393],"about_ca_topic_score_codex":0.00008409232,"about_ca_topic_score_gemma":0.0000056249723,"teacher_disagreement_score":0.17342553,"about_ca_system_score_codex":0.000046928155,"about_ca_system_score_gemma":0.00025885119,"threshold_uncertainty_score":0.95562536},"labels":[],"label_agreement":null},{"id":"W32579068","doi":"10.1007/978-3-642-21593-3_21","title":"Infinite Generalized Gaussian Mixture Modeling and Applications","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Overfitting; Mixture model; Computer science; Bayesian probability; Gaussian; Artificial intelligence; Gaussian process; Pattern recognition (psychology); Face (sociological concept); Machine learning; Algorithm; Artificial neural network","score_opus":0.02856930667628637,"score_gpt":0.26323900702226843,"score_spread":0.23466970034598206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W32579068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008104585,0.0014593524,0.9875798,0.00052260485,0.0005022032,0.0005261204,0.0000055772375,0.00016511853,0.009231125],"genre_scores_gemma":[0.015457297,0.0002964181,0.9815444,0.0017247469,0.0004990905,0.000036104768,0.0000045067804,0.000040887146,0.00039659298],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965677,0.000053828713,0.00051684614,0.0017032537,0.0005396325,0.0006187108],"domain_scores_gemma":[0.9975818,0.00015730351,0.000222004,0.0015609545,0.00019125182,0.00028668513],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008454744,0.0005760656,0.0005790783,0.00072272244,0.0003234899,0.00046920404,0.0023905328,0.00047062,0.000015259728],"category_scores_gemma":[0.000023980709,0.0005043154,0.000119679404,0.00048488379,0.00045454217,0.0005164253,0.0012040676,0.00086659985,0.000012702162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026995772,0.000011992277,0.0000035683217,0.000028216065,0.000008831835,0.000015921372,0.00052990194,0.0022630005,0.00008475254,0.3008108,0.00000769228,0.6962326],"study_design_scores_gemma":[0.00014014186,0.00003439911,0.000003698579,0.00010148347,0.000008671113,0.000055894307,2.4285166e-8,0.43793476,0.00011571403,0.5590086,0.002176221,0.00042037782],"about_ca_topic_score_codex":0.000027877528,"about_ca_topic_score_gemma":0.00003437193,"teacher_disagreement_score":0.6958122,"about_ca_system_score_codex":0.000091615424,"about_ca_system_score_gemma":0.00033558402,"threshold_uncertainty_score":0.99974084},"labels":[],"label_agreement":null},{"id":"W39496697","doi":"10.1093/oso/9780198526155.003.0005","title":"Bayesian Treed Generalized Linear Models","year":2003,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalized linear model; Mathematics; Bayesian probability; Partition (number theory); Poisson distribution; Applied mathematics; Constant (computer programming); Bayesian linear regression; Algorithm; Computer science; Bayesian inference; Statistics; Combinatorics","score_opus":0.036550079768433795,"score_gpt":0.260243652376702,"score_spread":0.2236935726082682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W39496697","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1957267e-8,0.00039153156,0.51229227,0.00046442964,0.00031419133,0.0001743017,0.0000044660583,0.00018744785,0.48617133],"genre_scores_gemma":[0.0000058059804,0.00016162329,0.51874083,0.002277617,0.00013475883,0.0000066964953,0.000006437159,0.000049191323,0.47861707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973306,0.00008720823,0.0005510161,0.0010728164,0.00047658663,0.00048175306],"domain_scores_gemma":[0.997602,0.00005742347,0.0002149138,0.0016728225,0.00014146122,0.00031142248],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043980492,0.0006412658,0.0007595668,0.00025355545,0.0001182635,0.00015208521,0.0013164292,0.00066986994,0.00045645158],"category_scores_gemma":[0.0000075065254,0.00054327335,0.00042944655,0.00007392072,0.00006362569,0.00036697494,0.00025765775,0.0005003427,0.0001278843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030008337,0.000010483476,3.364085e-8,0.000011598225,0.000047809343,0.00003555336,0.000047888057,0.00004941829,0.00001407763,0.943771,0.013237527,0.042771634],"study_design_scores_gemma":[0.00028847792,0.00003622955,3.6685286e-8,0.00003037963,0.000025083003,0.000029568682,1.8162875e-7,0.14165139,0.00008297378,0.68959624,0.16772868,0.00053078576],"about_ca_topic_score_codex":0.000016566617,"about_ca_topic_score_gemma":0.000011803365,"teacher_disagreement_score":0.25417477,"about_ca_system_score_codex":0.00006386322,"about_ca_system_score_gemma":0.00014278745,"threshold_uncertainty_score":0.99970186},"labels":[],"label_agreement":null},{"id":"W40600744","doi":"10.5591/978-1-57735-516-8/ijcai11-215","title":"Continuous Correlated Beta Processes","year":2012,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Bernoulli's principle; Dirichlet distribution; Computer science; Gaussian process; Bernoulli process; Kernel (algebra); Algorithm; Gaussian; Applied mathematics; Mathematics; Discrete mathematics; Mathematical analysis","score_opus":0.017153366244681677,"score_gpt":0.2579623914407879,"score_spread":0.24080902519610625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W40600744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001084006,0.00062445144,0.931534,0.00039166055,0.00037476575,0.00006973212,2.6308854e-7,0.00021763596,0.065703504],"genre_scores_gemma":[0.4412951,0.000010601206,0.5543024,0.0005787903,0.00006973945,0.000004996518,4.786652e-7,0.0000047356675,0.0037331574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993245,0.00004031204,0.00010741301,0.0001460503,0.000104505474,0.00027720584],"domain_scores_gemma":[0.9994431,0.00006301394,0.000034042998,0.00027454583,0.00006656673,0.00011870185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026860202,0.00008077572,0.000107116,0.000032453972,0.000048858652,0.00005860811,0.00036644336,0.000051528714,0.00004719478],"category_scores_gemma":[0.00003393352,0.000058893507,0.00002435451,0.00026902734,0.000015986581,0.00053782476,0.00009728926,0.00007435379,0.00011952117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019138706,0.00010664667,0.0025631425,0.000021362363,0.000015239659,0.0000032150167,0.0010191451,6.087067e-7,0.000399668,0.7748194,0.009008014,0.21204168],"study_design_scores_gemma":[0.003373707,0.0005971589,0.022479095,0.00019268673,0.00013485046,0.0007993625,0.00015536456,0.038279835,0.17462754,0.2165685,0.53905827,0.0037336075],"about_ca_topic_score_codex":0.000008444487,"about_ca_topic_score_gemma":0.0000011525979,"teacher_disagreement_score":0.55825084,"about_ca_system_score_codex":0.000006471862,"about_ca_system_score_gemma":0.000035061003,"threshold_uncertainty_score":0.24016075},"labels":[],"label_agreement":null},{"id":"W4200040246","doi":"10.18187/pjsor.v17i4.2512","title":"On Smoothed MWSD Estimation of Mixing Proportion","year":2021,"lang":"en","type":"article","venue":"Pakistan Journal of Statistics and Operation Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Estimator; Mixing (physics); Statistics; Mean squared error; Applied mathematics; Independent and identically distributed random variables; Monte Carlo method; Convergence (economics); Parametric statistics; Minimum mean square error; Mean square; Square (algebra); Random variable; Geometry","score_opus":0.05046941693685391,"score_gpt":0.41172406450254123,"score_spread":0.3612546475656873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200040246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0091706,0.0002459614,0.98954654,0.00048009722,0.00008846127,0.00006760409,0.00000927991,0.000002440508,0.00038899947],"genre_scores_gemma":[0.42123452,0.00013008181,0.57849014,0.000026025107,0.0000212046,8.8064604e-7,0.0000024090289,0.0000033334015,0.00009143307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983945,0.00035341855,0.0004136952,0.00012552575,0.0005913285,0.00012156372],"domain_scores_gemma":[0.9980677,0.00032792985,0.00015462688,0.00014419308,0.0012231575,0.000082414685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023801036,0.000055643573,0.00014356003,0.00015174161,0.00012348061,0.00017887996,0.00013637534,0.000032770262,0.000024982819],"category_scores_gemma":[0.00047153624,0.00004489072,0.000020469217,0.00021760038,0.00005548191,0.0002020178,0.000041676398,0.00021806521,0.0000010904282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020728516,0.00005419311,0.000019857594,0.000040436964,0.000010084651,0.000052182357,0.00052913034,0.00057305174,0.004630239,0.77965313,0.00039303652,0.21402395],"study_design_scores_gemma":[0.0008464609,0.0009255162,0.002181332,0.00022577881,0.000011783952,0.00012508842,0.00016046925,0.4827698,0.031773914,0.48055172,0.00028606772,0.00014208836],"about_ca_topic_score_codex":0.000005197337,"about_ca_topic_score_gemma":0.0000036187625,"teacher_disagreement_score":0.48219672,"about_ca_system_score_codex":0.000031788604,"about_ca_system_score_gemma":0.0002845426,"threshold_uncertainty_score":0.18305904},"labels":[],"label_agreement":null},{"id":"W4200534113","doi":"10.1002/eap.2524","title":"Automatic selection of the number of clusters using Bayesian clustering and sparsity‐inducing priors","year":2021,"lang":"en","type":"article","venue":"Ecological Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Biodiversity Monitoring Institute; University of Alberta","funders":"Fundação de Apoio ao Desenvolvimento do Ensino, Ciência e Tecnologia do Estado de Mato Grosso do Sul; National Science Foundation of Sri Lanka; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cluster analysis; Prior probability; Computer science; Bayesian probability; Context (archaeology); Model selection; Mixture model; Data mining; Machine learning; Ecology; Artificial intelligence; Geography; Biology","score_opus":0.022344287689072782,"score_gpt":0.28651016366169424,"score_spread":0.2641658759726215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200534113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2402676,0.000012007657,0.7588211,0.00027793852,0.000031269938,0.0001572108,7.709905e-7,0.00002166418,0.00041039576],"genre_scores_gemma":[0.5530913,0.0000024917435,0.4468027,0.000060198996,0.000009507142,0.000011845014,1.8864839e-7,0.000001948321,0.000019836854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922806,0.00011984245,0.0002197701,0.00022259552,0.00009391546,0.00011581315],"domain_scores_gemma":[0.9993888,0.00011595924,0.00011962049,0.0002685432,0.00006787067,0.000039212795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022157493,0.00006705732,0.00014907424,0.000020758023,0.00014621741,0.000022923297,0.00023763935,0.00006813196,0.000030172094],"category_scores_gemma":[0.000036873193,0.00004987358,0.000050678154,0.0004528733,0.000062117906,0.0000812837,0.00030386893,0.000096989,8.100976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063069865,0.00096332165,0.052373677,0.00052666286,0.00014860445,0.000004852116,0.0026547115,0.0038851798,0.13591678,0.39554924,0.00008742207,0.40788326],"study_design_scores_gemma":[0.0001697359,0.00001673181,0.07397173,0.00003920868,0.000032717166,0.000100604404,0.00003642307,0.8856265,0.010810921,0.028970825,0.00009453444,0.0001300884],"about_ca_topic_score_codex":0.000009954928,"about_ca_topic_score_gemma":0.000019668627,"teacher_disagreement_score":0.8817413,"about_ca_system_score_codex":0.000029003353,"about_ca_system_score_gemma":0.000058711386,"threshold_uncertainty_score":0.20337856},"labels":[],"label_agreement":null},{"id":"W4200590193","doi":"10.1002/cjs.11680","title":"Cluster analysis with regression of non‐Gaussian functional data on covariates","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Covariate; Functional principal component analysis; Consistency (knowledge bases); Functional data analysis; Computer science; Normality; Econometrics; Regression; Regression analysis; Flexibility (engineering); Data mining; Mathematics; Statistics; Artificial intelligence; Machine learning","score_opus":0.03476858928479686,"score_gpt":0.27406470728271637,"score_spread":0.2392961179979195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200590193","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038425607,0.000110176734,0.9974001,0.001004028,0.00025940774,0.000023652217,0.00034010562,0.0000015998005,0.00047669013],"genre_scores_gemma":[0.13465281,0.000012429249,0.8646152,0.00041596152,0.000068472116,1.9646336e-7,0.000046724046,0.000006156168,0.00018203743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989345,0.000111012785,0.00031600113,0.00019177227,0.00027428797,0.00017241704],"domain_scores_gemma":[0.99808425,0.00019188234,0.0002993607,0.00058715185,0.00046063418,0.00037670395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044229097,0.00010131346,0.0002848589,0.00030927142,0.00008232453,0.00008920616,0.0005418467,0.00004604452,0.000088107445],"category_scores_gemma":[0.00016033002,0.0000702227,0.00004464258,0.0006267472,0.000055814206,0.00020070681,0.00004442004,0.00018865032,0.0000015697019],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016042305,0.00017095868,0.0116257025,0.00012376065,0.0028459863,0.005137034,0.0018723359,0.007735499,0.00041263504,0.572293,0.16758017,0.23004249],"study_design_scores_gemma":[0.004443584,0.0017841975,0.19962808,0.0011877142,0.0031028176,0.0018066624,0.00027103868,0.65043765,0.0028850145,0.107599355,0.025499685,0.0013542034],"about_ca_topic_score_codex":0.00039095784,"about_ca_topic_score_gemma":0.007613949,"teacher_disagreement_score":0.64270216,"about_ca_system_score_codex":0.000046189245,"about_ca_system_score_gemma":0.0019347648,"threshold_uncertainty_score":0.42487624},"labels":[],"label_agreement":null},{"id":"W4205212204","doi":"10.1007/978-3-030-86133-9_4","title":"Bayesian Inference for Inverse Gaussian Data with Emphasis on the Coefficient of Variation","year":2021,"lang":"en","type":"book-chapter","venue":"Springer proceedings in mathematics & statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Prior probability; Gibbs sampling; Conjugate prior; Inverse Gaussian distribution; Bayesian inference; Mathematics; Applied mathematics; Gaussian; Bayesian probability; Posterior probability; Inference; Inverse problem; Generalized inverse Gaussian distribution; Computer science; Algorithm; Statistics; Gaussian process; Distribution (mathematics); Artificial intelligence; Mathematical analysis; Physics; Gaussian random field","score_opus":0.05108537156228236,"score_gpt":0.2970232349796469,"score_spread":0.24593786341736454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205212204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008364519,0.000040062783,0.9669166,0.00024694423,0.0001299514,0.0008544874,0.00031203873,0.000035823145,0.0314557],"genre_scores_gemma":[0.0010415396,0.00010461844,0.9918314,0.00012774905,0.00005940496,0.000044300075,0.000036781737,0.00006491395,0.0066892467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997536,0.000014565764,0.0007295776,0.00075662194,0.0006440067,0.00031922993],"domain_scores_gemma":[0.996517,0.00092803664,0.0008374618,0.0011287276,0.000505104,0.00008368266],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013152028,0.00042071973,0.0006172354,0.00021164361,0.000104734594,0.00022624015,0.0017177803,0.00021360078,0.000025146155],"category_scores_gemma":[0.0007172632,0.0003033683,0.000054218683,0.00014713393,0.00013193347,0.00016659194,0.00057420746,0.00042174174,0.0000036906865],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008578784,0.000087548935,0.000002805187,0.00074453244,0.00005897661,0.000008646386,0.0021456724,0.00001784269,0.000026761769,0.9871841,0.0005370033,0.009177511],"study_design_scores_gemma":[0.0003044848,0.00018105062,0.000011460548,0.0015229973,0.000116437004,0.000008320849,0.000051279578,0.2776094,0.00017196049,0.7160279,0.003560902,0.00043380205],"about_ca_topic_score_codex":0.000005447748,"about_ca_topic_score_gemma":0.00002682197,"teacher_disagreement_score":0.27759156,"about_ca_system_score_codex":0.000088450644,"about_ca_system_score_gemma":0.00029289591,"threshold_uncertainty_score":0.9999418},"labels":[],"label_agreement":null},{"id":"W4205844968","doi":"10.31234/osf.io/scg59","title":"The Emperor Has No Blanket!","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Charles Phelps Taft Research Center; Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; University of Cincinnati","keywords":"Emperor; Blanket; Construct (python library); Work (physics); Computer science; History; Engineering; Archaeology; Mechanical engineering","score_opus":0.04100523760294035,"score_gpt":0.28997303300862237,"score_spread":0.24896779540568204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205844968","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046685243,0.0004667084,0.88192636,0.007046542,0.0032329508,0.00024036717,0.0000053916037,0.00022518233,0.10680981],"genre_scores_gemma":[0.002483743,0.00017759753,0.9499096,0.0018830083,0.0003224225,0.00016132186,0.0000067098363,0.000020737818,0.045034844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99805635,0.00033450368,0.00025268047,0.0006542816,0.00037760782,0.00032457852],"domain_scores_gemma":[0.9974773,0.0002408252,0.000115061644,0.0020000252,0.000077576966,0.00008922246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011753159,0.00022317906,0.00022030852,0.00004544081,0.000611646,0.0009042092,0.0034780866,0.00013046367,0.00036644796],"category_scores_gemma":[0.000058285787,0.00013676238,0.00019542572,0.00012498786,0.00007030327,0.00007391102,0.0059864656,0.00083062437,0.00015780322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005427374,0.00003715204,0.000013243359,0.00002689567,0.00006029939,0.000024668718,0.00066867005,0.000045847264,0.00004712195,0.65997267,0.12569228,0.21340571],"study_design_scores_gemma":[0.000093074384,0.00003576362,0.000094347175,0.0000107146725,0.000008882704,0.000009208361,0.000008698605,0.038893048,0.00008373537,0.24220352,0.71823,0.0003290211],"about_ca_topic_score_codex":0.000079687634,"about_ca_topic_score_gemma":0.000013726858,"teacher_disagreement_score":0.5925377,"about_ca_system_score_codex":0.000056085875,"about_ca_system_score_gemma":0.00031765748,"threshold_uncertainty_score":0.871931},"labels":[],"label_agreement":null},{"id":"W4206202687","doi":"10.21203/rs.3.rs-1240350/v1","title":"Estimating F-statistics Using Non-independent Samples","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"China Scholarship Council; Chinese Academy of Sciences; University of British Columbia; National Natural Science Foundation of China","keywords":"Statistics; Mathematics; Econometrics","score_opus":0.161896460152583,"score_gpt":0.45802534281129975,"score_spread":0.29612888265871673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206202687","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013130851,0.00037843816,0.9941046,0.00023964472,0.0011585128,0.00081868144,0.00023106503,0.00010375241,0.0016522085],"genre_scores_gemma":[0.027303837,0.000040214654,0.97164476,0.000050955066,0.0003866975,0.00014349134,0.00006392796,0.000049462345,0.00031665957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99352807,0.0014511874,0.00047086825,0.0012364512,0.0023230251,0.000990408],"domain_scores_gemma":[0.99616736,0.0009172125,0.00019185695,0.0018954646,0.00053115113,0.00029696297],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005431512,0.00032527963,0.00046629345,0.0005698151,0.0008651263,0.0008742481,0.0028488464,0.00024835585,0.00022573282],"category_scores_gemma":[0.00064447394,0.0003292828,0.00015639066,0.0006251088,0.000106197025,0.00017672194,0.010691618,0.0031487802,0.000020596413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033643253,0.00045916584,0.0011255129,0.004536568,0.00022755956,0.0014462583,0.0071597034,0.072798416,0.002096072,0.49516582,0.009410867,0.4055404],"study_design_scores_gemma":[0.00012562853,0.00007002691,0.00036256874,0.0002761399,0.000007652533,0.00001883947,0.000050593346,0.78340995,0.00015169059,0.21439993,0.0008086398,0.00031833004],"about_ca_topic_score_codex":0.0007772313,"about_ca_topic_score_gemma":0.000020649051,"teacher_disagreement_score":0.7106115,"about_ca_system_score_codex":0.00057133025,"about_ca_system_score_gemma":0.0013806574,"threshold_uncertainty_score":0.9999159},"labels":[],"label_agreement":null},{"id":"W4206298479","doi":"10.1007/s00357-021-09396-3","title":"Chimeral Clustering","year":2021,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Computer science","score_opus":0.04135846136028306,"score_gpt":0.301972910995361,"score_spread":0.26061444963507796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206298479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024410356,0.0002395996,0.98919696,0.004024351,0.00049174216,0.000013825315,1.0971204e-7,0.00000918519,0.003583177],"genre_scores_gemma":[0.34044743,0.000049545317,0.6588308,0.00023449586,0.00016521208,3.6471528e-7,2.1088475e-7,0.0000027683443,0.0002691564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933267,0.00009423674,0.0002493001,0.00008466952,0.00016350596,0.000075643096],"domain_scores_gemma":[0.9992709,0.000034399905,0.00022068493,0.00019768701,0.00022139376,0.000054936736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039614365,0.000042970765,0.00009911951,0.000052203097,0.000035197707,0.00008393276,0.00024873548,0.000032511347,0.000008407175],"category_scores_gemma":[0.000057298304,0.000035933925,0.00006714352,0.00016691943,0.000008173702,0.00037602888,0.00003601404,0.00011867158,0.0000043260497],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064314618,0.00006545495,0.00014448537,0.000010637782,0.000022631919,0.000047231028,0.00042114675,0.000032475968,0.11334942,0.17821094,0.0015678242,0.7061213],"study_design_scores_gemma":[0.0019521782,0.00030050954,0.10472994,0.00023665841,0.000069035355,0.0038206584,0.00013340978,0.47516146,0.106166594,0.22613358,0.08069808,0.0005978754],"about_ca_topic_score_codex":2.6259377e-7,"about_ca_topic_score_gemma":6.1449583e-7,"teacher_disagreement_score":0.70552343,"about_ca_system_score_codex":0.000024751984,"about_ca_system_score_gemma":0.00011085511,"threshold_uncertainty_score":0.14653428},"labels":[],"label_agreement":null},{"id":"W4206299884","doi":"10.1007/s00521-021-06839-1","title":"Expectation propagation learning of finite multivariate Beta mixture models and applications","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Inference; Cluster analysis; Multivariate statistics; Artificial intelligence; Machine learning; Flexibility (engineering); Mixture model; Unsupervised learning; Digitization; Computational Science and Engineering; Data mining; Expectation–maximization algorithm; Pattern recognition (psychology); Mathematics; Maximum likelihood; Statistics","score_opus":0.023073375227140317,"score_gpt":0.2844996461042609,"score_spread":0.26142627087712056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206299884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007281086,0.00030344882,0.9909637,0.00037540097,0.000022521594,0.0005397439,0.000006136769,0.00012154275,0.000386437],"genre_scores_gemma":[0.87099034,0.0000135394475,0.12852344,0.00008054842,0.000057020243,0.00025550785,0.000018827126,0.000008765207,0.000051998013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888486,0.00017147405,0.00024505152,0.0003970077,0.0001585108,0.00014310918],"domain_scores_gemma":[0.99918646,0.00022820116,0.00020180976,0.00024805142,0.00007511643,0.00006035252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028662116,0.00011163473,0.00014505874,0.00009506662,0.0007660528,0.00006228553,0.0002447339,0.00003352001,0.0000013722364],"category_scores_gemma":[0.000008491739,0.00011387744,0.00003182241,0.0004126636,0.00004449636,0.00016523754,0.00030587259,0.0002606813,4.154196e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037195864,0.00006119569,0.00015757256,0.000040484898,0.000010235275,3.061044e-7,0.001764347,0.039030734,0.0038213679,0.5150684,0.000015958729,0.4400257],"study_design_scores_gemma":[0.00018600468,0.00004711579,0.00054254604,0.000005396212,0.000011482801,0.0000142801955,0.00008498443,0.9724675,0.0003502957,0.024950882,0.0012160041,0.0001235547],"about_ca_topic_score_codex":0.000018227849,"about_ca_topic_score_gemma":4.94293e-7,"teacher_disagreement_score":0.9334367,"about_ca_system_score_codex":0.000013795759,"about_ca_system_score_gemma":0.000021536298,"threshold_uncertainty_score":0.58919364},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05268794575636098,"score_gpt":0.3223231908272784,"score_spread":0.2696352450709174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206548271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082493976,0.0013161907,0.9116451,0.0019714024,0.0005302711,0.0001905025,0.0000025706818,0.000035352845,0.001814631],"genre_scores_gemma":[0.28997013,0.00031280407,0.70869607,0.000620281,0.000017178434,0.00011169263,0.0000015100463,0.000006012678,0.0002643417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99552435,0.0032622635,0.00031190232,0.00046159193,0.00007838886,0.0003615018],"domain_scores_gemma":[0.99898356,0.00060858263,0.00008691998,0.00023488635,0.000020173604,0.00006587332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048848526,0.00013598568,0.00031372707,0.00041987872,0.0002070519,0.000021204076,0.00029497794,0.00015822178,0.000022536466],"category_scores_gemma":[0.00009187197,0.0001464682,0.000025920208,0.00024038991,0.00013297118,0.00032956904,0.00066413835,0.00041346808,4.3915657e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038743136,0.00010509231,0.021765755,0.000021113307,0.000011152918,0.00006699188,0.0015476207,0.00024127761,0.00016102915,0.61493057,0.00018388423,0.36092678],"study_design_scores_gemma":[0.0004792501,0.00017356966,0.13979997,0.000003683097,0.0000056817407,0.000119722186,0.00016921914,0.22864918,0.000010508255,0.629954,0.00047548747,0.00015972815],"about_ca_topic_score_codex":0.00007459159,"about_ca_topic_score_gemma":0.0002724401,"teacher_disagreement_score":0.36076704,"about_ca_system_score_codex":0.00017295837,"about_ca_system_score_gemma":0.00011066928,"threshold_uncertainty_score":0.59727997},"labels":[],"label_agreement":null},{"id":"W4207071787","doi":"10.1090/mbk/139/05","title":"Dirichlet’s theorem","year":2021,"lang":"en","type":"book-chapter","venue":"American Mathematical Society eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Mathematics; Dirichlet distribution; Mathematical economics; Economics; Mathematical analysis","score_opus":0.019144771962021294,"score_gpt":0.25907127801471724,"score_spread":0.23992650605269594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207071787","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.2692414e-7,0.00012294736,0.50927985,0.00034846208,0.00007188642,0.00013823669,0.000004448886,0.00016424355,0.489869],"genre_scores_gemma":[0.00008927252,0.00005242946,0.5567021,0.002441241,0.00015582678,0.000018487148,0.000003428285,0.0000653466,0.4404719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972388,0.00007639875,0.0005547421,0.00092936447,0.0006600921,0.0005405962],"domain_scores_gemma":[0.9970456,0.00051473314,0.00040154936,0.001568603,0.000156013,0.00031350396],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052351714,0.00059509324,0.0010923408,0.0000368154,0.00016524279,0.0002338732,0.0012611472,0.0003084996,0.00026377538],"category_scores_gemma":[0.00004651546,0.00049711234,0.001131246,0.00005843302,0.0008089787,0.00006539131,0.0007654212,0.00078304025,0.00021787116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.994985e-7,0.000015834923,5.5695367e-8,0.00006022192,0.0001370217,0.000026328658,0.00077865017,6.1873614e-8,0.000029255243,0.8548144,0.0043617547,0.13977571],"study_design_scores_gemma":[0.0000974573,0.00006227446,3.992457e-7,0.00017810584,0.00007109392,0.00005101737,0.00002831885,0.0015690768,0.000093150324,0.8931663,0.10409081,0.00059197954],"about_ca_topic_score_codex":0.0000036559406,"about_ca_topic_score_gemma":6.2284613e-7,"teacher_disagreement_score":0.13918373,"about_ca_system_score_codex":0.00010167206,"about_ca_system_score_gemma":0.00019906685,"threshold_uncertainty_score":0.99974805},"labels":[],"label_agreement":null},{"id":"W4210287153","doi":"10.2139/ssrn.4021201","title":"A Computationally Efficient Mixture Innovation Model for Time-Varying Parameter Regressions","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Econometrics; Mathematics; Statistics; Computer science; Applied mathematics","score_opus":0.018199222466985566,"score_gpt":0.28738803863813045,"score_spread":0.2691888161711449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210287153","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005447417,0.00076558616,0.98929465,0.0039251423,0.00016307455,0.00014314246,0.000003518787,0.00004985275,0.0002075988],"genre_scores_gemma":[0.2059146,0.000058937298,0.7912058,0.0008579639,0.00015105688,0.000015265558,0.000014894646,0.000019016428,0.0017624163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976234,0.0001318894,0.00036850118,0.00035170795,0.0003086876,0.0012158066],"domain_scores_gemma":[0.99866897,0.00020458354,0.00020734279,0.0002673797,0.000584876,0.00006683956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016474307,0.00015904508,0.00019586137,0.000169567,0.00035809382,0.00018957947,0.0004278009,0.0001006317,0.000003768977],"category_scores_gemma":[0.00022297705,0.00013586287,0.00013369556,0.00065756164,0.000018885405,0.00022308841,0.00009453733,0.0009211516,0.000006110342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013473886,0.000079026126,0.00000431573,0.0000056841595,0.000065165324,0.000004770624,0.0003423933,0.021611456,0.005704249,0.9175861,0.00039339656,0.054189987],"study_design_scores_gemma":[0.00029985126,0.0000322517,0.000008023325,0.000019947924,0.000009034124,0.00024559762,0.000008396335,0.5367866,0.0003118949,0.46208724,0.00009480877,0.000096356576],"about_ca_topic_score_codex":4.6503985e-7,"about_ca_topic_score_gemma":0.0000025314782,"teacher_disagreement_score":0.51517516,"about_ca_system_score_codex":0.00033759317,"about_ca_system_score_gemma":0.0036034775,"threshold_uncertainty_score":0.63924146},"labels":[],"label_agreement":null},{"id":"W4210521435","doi":"10.1007/978-3-030-95408-6_14","title":"Sparse Generalized Dirichlet Prior Based Bayesian Multinomial Estimation","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Multinomial distribution; Multinomial probit; Computer science; Bayesian probability; Context (archaeology); Probabilistic logic; Categorical distribution; Prior probability; Artificial intelligence; Property (philosophy); Machine learning; Econometrics; Mathematics; Bayesian hierarchical modeling; Bayesian inference; Multinomial logistic regression; Geography","score_opus":0.02178237617829529,"score_gpt":0.2685821701325137,"score_spread":0.2467997939542184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210521435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025503274,0.00025461006,0.9923607,0.0012480732,0.0025140094,0.00070864795,0.000013639537,0.00027222923,0.0026026003],"genre_scores_gemma":[0.013299212,0.000016297634,0.9828586,0.0029772632,0.0004058146,0.00003726264,0.000019559797,0.000056358756,0.00032964765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947408,0.00019050951,0.00074072595,0.002141354,0.0013404705,0.0008461324],"domain_scores_gemma":[0.99660504,0.00049814436,0.00046725714,0.001976364,0.00016802404,0.00028518404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018206489,0.00073179684,0.0007671854,0.0010646409,0.0005708883,0.00062029815,0.0038337018,0.00035739207,0.00019541719],"category_scores_gemma":[0.00014598884,0.00069762766,0.00025837636,0.0007937858,0.00044071747,0.0007119018,0.0014685331,0.0011361368,0.000022373695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014722097,0.000041248863,0.0000082586785,0.000031121876,0.000008808116,0.00011958266,0.00034385987,0.08685603,0.00012061379,0.055137426,0.000053945925,0.8572644],"study_design_scores_gemma":[0.00061129883,0.00012908642,0.000030640556,0.00009508521,0.000013216663,0.00004197366,2.3660977e-8,0.8800528,0.0007392856,0.114140876,0.0034235613,0.0007221435],"about_ca_topic_score_codex":0.000050748586,"about_ca_topic_score_gemma":0.000035969828,"teacher_disagreement_score":0.8565422,"about_ca_system_score_codex":0.0005265579,"about_ca_system_score_gemma":0.0010601042,"threshold_uncertainty_score":0.9995475},"labels":[],"label_agreement":null},{"id":"W4211201089","doi":"10.1002/9780470391341.refs","title":"References","year":2008,"lang":"en","type":"other","venue":"Wiley series in probability and statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.02313419758117689,"score_gpt":0.2551284659753957,"score_spread":0.2319942683942188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211201089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000021267672,0.0018019117,0.8635464,0.00010626819,0.00030108303,0.00022195434,0.00016914042,0.000104272265,0.13374685],"genre_scores_gemma":[0.000018494991,0.006561361,0.9081045,0.0000746567,0.00005004372,0.000022325901,0.000014656434,0.000043910542,0.085110046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99865174,0.00018506238,0.00025422277,0.0005114544,0.00016670815,0.00023083271],"domain_scores_gemma":[0.9991427,0.00010237741,0.00011073344,0.0005404337,0.000029039082,0.000074733885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002530402,0.00022401141,0.0003638469,0.00009759756,0.000051747687,0.00006407552,0.00041225186,0.00023694115,0.00008946892],"category_scores_gemma":[0.00013291596,0.00019749369,0.000019807725,0.00015277449,0.0003257752,0.000112042755,0.00019482263,0.00024911363,0.000006089032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004366597,0.000031744,0.00014621402,0.00017592689,0.000007801964,0.000028525978,0.00036754852,2.9783536e-7,2.9596575e-7,0.7349502,0.1261913,0.13809577],"study_design_scores_gemma":[0.00011075906,0.00008363827,0.00015883535,0.00018986872,0.0000043387495,0.000027681024,0.0000038638814,0.0004987325,0.0000025113852,0.691921,0.30672324,0.00027556048],"about_ca_topic_score_codex":0.00015402821,"about_ca_topic_score_gemma":0.0009636172,"teacher_disagreement_score":0.18053193,"about_ca_system_score_codex":0.00002182318,"about_ca_system_score_gemma":0.0001156129,"threshold_uncertainty_score":0.8053559},"labels":[],"label_agreement":null},{"id":"W4220699641","doi":"10.5539/ijsp.v11n3p9","title":"Bayesian Bivariate Cure Rate Models Using Copula Functions","year":2022,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Copula (linguistics); Bivariate analysis; Weibull distribution; Statistics; Bayesian probability; Mathematics; Survival function; Joint probability distribution; Marginal distribution; Econometrics; Applied mathematics; Survival analysis","score_opus":0.03592773821732773,"score_gpt":0.2992986381178914,"score_spread":0.26337089990056367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220699641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022915602,0.0001221385,0.99465823,0.0010765665,0.0012839733,0.000077757046,0.00020124124,0.000009128477,0.00027939968],"genre_scores_gemma":[0.27929744,0.000023377663,0.7203014,0.00020985873,0.00008799747,0.0000026174516,0.000004035225,0.0000052837727,0.00006797087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854034,0.0003076649,0.0004269107,0.00018677616,0.00041583652,0.00012249821],"domain_scores_gemma":[0.99876857,0.00016378236,0.00033023127,0.00015594119,0.00048328604,0.000098209806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014314243,0.000096310185,0.00016432672,0.000117703166,0.00019115531,0.00014959965,0.0005252733,0.000023807637,0.00005496099],"category_scores_gemma":[0.00007507115,0.00008699474,0.000055938097,0.0001225753,0.00004483173,0.00035809824,0.00029028562,0.00028354416,2.4590793e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009775515,0.00021107761,0.0005281962,0.000017849667,0.00014861248,0.00011735135,0.00067727984,0.030062933,0.00046257125,0.8553791,0.0013791187,0.110918164],"study_design_scores_gemma":[0.00023127861,0.00007517431,0.00020778105,0.0000065878467,0.000012290798,0.00020267739,0.000008601261,0.40086624,0.00001362352,0.5971194,0.0011884132,0.00006794935],"about_ca_topic_score_codex":0.000031310054,"about_ca_topic_score_gemma":0.0000039481324,"teacher_disagreement_score":0.3708033,"about_ca_system_score_codex":0.00011814144,"about_ca_system_score_gemma":0.00019690377,"threshold_uncertainty_score":0.35475427},"labels":[],"label_agreement":null},{"id":"W4220757114","doi":"10.1002/sim.9367","title":"A mixture distribution approach for assessing genetic impact from twin study","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Restricted maximum likelihood; Estimator; Bivariate analysis; Consistency (knowledge bases); Inference; Dizygotic twins; Twin study; Econometrics; Correlation; Monozygotic twin; Genetic correlation; Mathematics; Maximum likelihood; Computer science; Heritability; Biology; Genetics; Genetic variation; Artificial intelligence; Medicine","score_opus":0.030329456089655076,"score_gpt":0.36346358413950375,"score_spread":0.33313412804984865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220757114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005371678,0.00027918955,0.9924501,0.00017033736,0.00037508877,0.00063827407,0.0005763793,0.000032840944,0.00010609926],"genre_scores_gemma":[0.3926799,0.0000016220184,0.606663,0.0001096602,0.000114967756,0.00010396786,0.00029675642,0.000008576048,0.000021550437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981066,0.00041566,0.0003346236,0.0004467289,0.0004206757,0.00027573053],"domain_scores_gemma":[0.9988337,0.00047230412,0.00012181412,0.00042538287,0.00006135173,0.00008543855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011756247,0.00015629269,0.00031921017,0.00008627432,0.00019830027,0.000050803246,0.00052924646,0.00003276969,0.000040206596],"category_scores_gemma":[0.00027719222,0.00012647096,0.000029148925,0.0004164773,0.00004439497,0.00007646305,0.00018859375,0.00031269406,2.87506e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012157487,0.0017450479,0.012475393,0.0000937853,0.00017258854,0.00032688593,0.015039884,0.0034852438,0.0006736428,0.11030881,0.04834224,0.8072149],"study_design_scores_gemma":[0.0025181011,0.0009926836,0.042208843,0.000019203451,0.00006469938,0.000017543929,0.0007752505,0.69253457,0.00001510431,0.260007,0.00056786026,0.0002791818],"about_ca_topic_score_codex":0.00030364783,"about_ca_topic_score_gemma":0.000010274074,"teacher_disagreement_score":0.8069357,"about_ca_system_score_codex":0.00018126534,"about_ca_system_score_gemma":0.00010326944,"threshold_uncertainty_score":0.5157336},"labels":[],"label_agreement":null},{"id":"W4220851616","doi":"10.1016/j.eswa.2022.116780","title":"Feature extraction of auto insurance size of loss data using functional principal component analysis","year":2022,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Principal component analysis; Interpretability; Computer science; Dimensionality reduction; Data mining; Feature (linguistics); Dimension (graph theory); Benchmark (surveying); Pattern recognition (psychology); Artificial intelligence; Mathematics","score_opus":0.045594108710802536,"score_gpt":0.31459272490444745,"score_spread":0.2689986161936449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220851616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005424184,0.00079670496,0.9926179,0.00025620716,0.00012736025,0.0004617892,0.00015021247,0.000043123873,0.00012251287],"genre_scores_gemma":[0.7119275,0.0000057867433,0.2875492,0.00002277966,0.000055664448,0.00026861753,0.000049882387,0.000006910074,0.00011368694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984543,0.00017734828,0.00029888898,0.00045986375,0.00047819933,0.00013143104],"domain_scores_gemma":[0.9977579,0.00014437013,0.00041718924,0.0014797824,0.00014310797,0.000057668283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047627644,0.000114186194,0.00029990645,0.00014079103,0.00024388691,0.000026337144,0.00083958585,0.000038212635,0.000010263527],"category_scores_gemma":[0.000007955803,0.00009960383,0.000063679,0.001353225,0.000049368464,0.00024166716,0.0003131263,0.00014094778,5.312356e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002892903,0.0026474723,0.024290679,0.0004928556,0.0033141884,0.000020161475,0.005027553,0.25984043,0.24726921,0.43432912,0.004875884,0.017603155],"study_design_scores_gemma":[0.0006123889,0.00008068639,0.021846276,0.000035565343,0.00016282368,0.00019827136,0.00024946057,0.9263758,0.001103717,0.00030535203,0.04865095,0.00037868193],"about_ca_topic_score_codex":0.00024139408,"about_ca_topic_score_gemma":0.000008229177,"teacher_disagreement_score":0.70650333,"about_ca_system_score_codex":0.00007337546,"about_ca_system_score_gemma":0.00012558572,"threshold_uncertainty_score":0.40617263},"labels":[],"label_agreement":null},{"id":"W4220926165","doi":"10.1109/ieecon53204.2022.9741682","title":"An Accelerated Nonparametric Bayesian Approach for Anomaly Detection with Feature Selection","year":2022,"lang":"en","type":"article","venue":"2022 International Electrical Engineering Congress (iEECON)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet process; Cluster analysis; Weighting; Feature selection; Computer science; Anomaly detection; Feature (linguistics); Pattern recognition (psychology); Dirichlet distribution; Artificial intelligence; Hierarchical Dirichlet process; Data mining; Nonparametric statistics; Latent Dirichlet allocation; Bounded function; Selection (genetic algorithm); Bayesian probability; Mathematics; Topic model; Statistics","score_opus":0.008827537961830778,"score_gpt":0.24194219871329972,"score_spread":0.23311466075146894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220926165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048559112,0.00009991227,0.9929155,0.00017015972,0.0008456949,0.0004510589,0.000016626364,0.00035103635,0.00029408012],"genre_scores_gemma":[0.6650855,0.000004595403,0.3334604,0.00016709018,0.00019065794,0.00045937023,0.00005921933,0.000036997084,0.00053621293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980197,0.00010141102,0.00024898612,0.00070728734,0.0005054016,0.0004172077],"domain_scores_gemma":[0.9990556,0.00014668122,0.000132523,0.0002850536,0.00022947365,0.00015063323],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004443639,0.00025683493,0.00025103334,0.0006905986,0.0002834558,0.00029068883,0.0009916626,0.00010177646,0.000045941666],"category_scores_gemma":[0.000083499974,0.00025363028,0.000103098384,0.0018132064,0.000012729844,0.0006059212,0.00009923501,0.0006418399,9.655736e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006689143,0.0010256399,0.0006689687,0.00007050761,0.0006905223,0.00005210788,0.00024363055,0.3894323,0.07550977,0.10279566,0.0017314828,0.42711046],"study_design_scores_gemma":[0.0006968299,0.000649121,0.00047214428,0.000002739381,0.000017277527,0.00020776427,0.0000028335392,0.98454577,0.0083058225,0.00032190888,0.004444495,0.0003332929],"about_ca_topic_score_codex":0.000016841323,"about_ca_topic_score_gemma":0.000002831413,"teacher_disagreement_score":0.66022956,"about_ca_system_score_codex":0.0003934606,"about_ca_system_score_gemma":0.00010222493,"threshold_uncertainty_score":0.9999916},"labels":[],"label_agreement":null},{"id":"W4220966911","doi":"10.1145/3502727","title":"Stochastic Variational Optimization of a Hierarchical Dirichlet Process Latent Beta-Liouville Topic Model","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Dirichlet process; Hierarchical Dirichlet process; Topic model; Computer science; Measure (data warehouse); Dirichlet distribution; Inference; Prior probability; Parametric statistics; Bayesian inference; Posterior probability; Mathematics; Bayesian probability; Applied mathematics; Artificial intelligence; Data mining; Statistics","score_opus":0.04890874881870901,"score_gpt":0.30447905946343445,"score_spread":0.25557031064472546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220966911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075371406,0.0001397633,0.9948135,0.00078322034,0.0004282722,0.0002509056,0.0025815496,0.00005919693,0.00018985667],"genre_scores_gemma":[0.53854185,0.00001192953,0.46027473,0.000107633634,0.000042535274,0.000092085575,0.00062498014,0.000016660737,0.00028761773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804693,0.0002525247,0.00036015178,0.00071352517,0.00041156955,0.00021531002],"domain_scores_gemma":[0.99740034,0.00035983065,0.00011571077,0.001965271,0.00007810251,0.00008071945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038951464,0.00017920171,0.00025811064,0.00018272456,0.00038985474,0.00008887001,0.0026198367,0.000057516616,0.00012545632],"category_scores_gemma":[0.00004735011,0.00017741033,0.00008688738,0.0005522099,0.000047502363,0.0011138809,0.00028503532,0.0004107635,0.0000045648762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046766214,0.0007779908,0.000006229852,0.000016962673,0.00008472484,0.0000015493542,0.00111712,0.96532774,0.0000610475,0.013236632,0.00019185955,0.01913139],"study_design_scores_gemma":[0.00045083414,0.00007737064,0.000060110156,0.000016161202,0.000059494574,0.0000035676558,0.000019037616,0.95721227,0.00011747921,0.041748453,0.00005026381,0.00018495855],"about_ca_topic_score_codex":0.000027745271,"about_ca_topic_score_gemma":0.000013356408,"teacher_disagreement_score":0.5377881,"about_ca_system_score_codex":0.0000690711,"about_ca_system_score_gemma":0.00035591918,"threshold_uncertainty_score":0.72345835},"labels":[],"label_agreement":null},{"id":"W4221109862","doi":"10.1214/21-aoas1518","title":"Accounting for drop-out using inverse probability censoring weights in longitudinal clustered data with informative cluster size","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Censoring (clinical trials); Statistics; Inverse probability; Inference; Generalized estimating equation; Mathematics; Random effects model; Estimating equations; Marginal structural model; Econometrics; Causal inference; Computer science; Medicine; Estimator; Artificial intelligence; Meta-analysis","score_opus":0.16111533411320592,"score_gpt":0.35644827601533313,"score_spread":0.19533294190212722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221109862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021621328,0.000010136175,0.9764931,0.00023467239,0.00008046503,0.00079468964,0.0003932223,0.000020995894,0.0003513717],"genre_scores_gemma":[0.22009861,0.0000031890152,0.7793494,0.00043471163,0.000028925764,0.00004111768,0.000021913433,0.0000112596035,0.000010903577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833834,0.0001228082,0.00045372656,0.00036346464,0.00036687806,0.00035477878],"domain_scores_gemma":[0.99753344,0.0009100044,0.00038646854,0.00097640173,0.00014689502,0.0000468142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002188983,0.00017072368,0.0002996118,0.00006954012,0.00030899388,0.00008107564,0.0013538988,0.00003043965,0.0000052805754],"category_scores_gemma":[0.00011341988,0.00012392133,0.000025663912,0.0002947747,0.0001112007,0.0003766797,0.0013324751,0.00025860983,7.572377e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017622787,0.0003700943,0.00045119948,0.0007444011,0.0002184071,0.000014653446,0.044143707,0.024287157,0.0005661051,0.8649769,0.0024775658,0.059987567],"study_design_scores_gemma":[0.0007216842,0.0000972458,0.00048311386,0.000025569912,0.000022657832,0.0000061939186,0.00025878742,0.77558166,0.00033723796,0.2216986,0.0005537302,0.00021350574],"about_ca_topic_score_codex":0.00003195826,"about_ca_topic_score_gemma":0.00007212636,"teacher_disagreement_score":0.7512945,"about_ca_system_score_codex":0.000040062474,"about_ca_system_score_gemma":0.00015371596,"threshold_uncertainty_score":0.5053365},"labels":[],"label_agreement":null},{"id":"W4224083579","doi":"10.1080/01969722.2022.2062850","title":"Unsupervised Learning Using Expectation Propagation Inference of Inverted Beta-Liouville Mixture Models for Pattern Recognition Applications","year":2022,"lang":"en","type":"article","venue":"Cybernetics & Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Inference; Artificial intelligence; Pattern recognition (psychology); Categorization; Generative model; Machine learning; Mixture model; Unsupervised learning; Scheme (mathematics); Generative grammar; Mathematics","score_opus":0.05525624368380263,"score_gpt":0.28159580137212853,"score_spread":0.2263395576883259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224083579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013684099,0.00036543893,0.9839416,0.000052877465,0.00023467708,0.0013484885,0.00003121124,0.0000918704,0.0002497071],"genre_scores_gemma":[0.8736995,0.000010747007,0.12518898,0.000033419925,0.000068274676,0.00080995087,0.00010622239,0.000021447617,0.00006144994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816847,0.00039928715,0.00047348856,0.00040402898,0.0003453459,0.0002093931],"domain_scores_gemma":[0.9986686,0.00015971684,0.00038890776,0.00035878728,0.0003619321,0.000062061925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005663682,0.00015368764,0.00025239965,0.00017082486,0.00030579462,0.00008713366,0.00041404032,0.00007743072,0.0000051673405],"category_scores_gemma":[0.000027729338,0.00016245076,0.000080153324,0.00048762676,0.000025070345,0.00027320426,0.00013611623,0.00019008524,0.0000014872111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038811675,0.00037357974,0.00065149064,0.00091683713,0.0001428534,0.0000027840122,0.018763933,0.29960755,0.050515782,0.07787327,0.00024666698,0.5508664],"study_design_scores_gemma":[0.00037126,0.00010911948,0.000031427015,0.000048501857,0.000030984407,0.000008768524,0.00027618726,0.986045,0.0017417707,0.0108300885,0.00031261615,0.00019426938],"about_ca_topic_score_codex":0.00013702681,"about_ca_topic_score_gemma":0.0000049462656,"teacher_disagreement_score":0.8600154,"about_ca_system_score_codex":0.000098710545,"about_ca_system_score_gemma":0.00010389686,"threshold_uncertainty_score":0.66245496},"labels":[],"label_agreement":null},{"id":"W4224211732","doi":"10.48550/arxiv.2204.10649","title":"Choice of mixture Poisson models based on Extreme value theory","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Gumbel distribution; Overdispersion; Extreme value theory; Poisson distribution; Count data; Generalized extreme value distribution; Mathematics; Focus (optics); Econometrics; Computer science; Applied mathematics; Statistics; Mathematical optimization; Statistical physics; Physics","score_opus":0.11197579900052118,"score_gpt":0.21779948132509536,"score_spread":0.10582368232457418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224211732","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006259882,0.0001298784,0.97280604,0.00017275212,0.00065784215,0.00036532132,0.000047503854,0.00018812498,0.01937265],"genre_scores_gemma":[0.9214308,0.00005278417,0.07524622,0.0005702319,0.00007152607,0.0000027136718,0.000018741433,0.00003639645,0.0025705523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964632,0.0011603492,0.0002753469,0.0014522464,0.00024538336,0.00040346608],"domain_scores_gemma":[0.99630535,0.00058698776,0.00040851595,0.0023742097,0.00013545372,0.00018948983],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010887859,0.00044312698,0.00054796186,0.00044320757,0.00017596132,0.000057487865,0.003028505,0.0003694948,0.00012948977],"category_scores_gemma":[0.000064407315,0.00048061353,0.00045056597,0.0007137592,0.00009947418,0.00028263647,0.0018493241,0.0011129723,0.000006525429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046738744,0.00011743611,0.00003602038,0.0000599095,0.000036960675,0.0000728427,0.00013217305,0.43536878,0.000034935645,0.56246895,0.00014520336,0.0014800162],"study_design_scores_gemma":[0.00030419463,0.00006863659,0.00006692154,0.00006342923,0.00004801464,7.1420476e-7,0.000007843781,0.57730216,0.00014477411,0.4214026,0.00030327807,0.00028743793],"about_ca_topic_score_codex":0.00012395636,"about_ca_topic_score_gemma":0.0000059132863,"teacher_disagreement_score":0.91517097,"about_ca_system_score_codex":0.0002219904,"about_ca_system_score_gemma":0.000337334,"threshold_uncertainty_score":0.99976456},"labels":[],"label_agreement":null},{"id":"W4225609744","doi":"10.4236/ojs.2022.122016","title":"Quasi-Negative Binomial: Properties, Parametric Estimation, Regression Model and Application to RNA-SEQ Data","year":2022,"lang":"en","type":"article","venue":"Open Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Overdispersion; Count data; Negative binomial distribution; Quasi-likelihood; Akaike information criterion; Beta-binomial distribution; Mathematics; Statistics; Binomial distribution; Multinomial distribution; Poisson distribution; Negative multinomial distribution; Goodness of fit","score_opus":0.07842162581472943,"score_gpt":0.3468887030059208,"score_spread":0.26846707719119134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225609744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043643342,0.00014107753,0.9974813,0.0011826245,0.0001255531,0.00035196537,0.00014834238,0.000006508234,0.00012622823],"genre_scores_gemma":[0.099251196,0.000041580268,0.90019816,0.00031211335,0.000022287848,0.000015660757,0.00000966576,0.000009572726,0.00013974668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985319,0.00022469366,0.00043101178,0.0002790024,0.0003956078,0.00013783202],"domain_scores_gemma":[0.9984091,0.00017019833,0.0004667255,0.0005749492,0.00022280597,0.00015621608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016138217,0.00010794906,0.00024045173,0.0001730305,0.00029601555,0.00031437282,0.0020784163,0.000022190121,0.0000062512854],"category_scores_gemma":[0.0004415415,0.000084051564,0.000012289171,0.00047792765,0.000029376377,0.0007700556,0.0018389755,0.00023993313,0.0000016781112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092903894,0.0001865795,0.000016043718,0.000021260623,0.000025629404,0.000019730687,0.0014236978,0.032928247,0.00047009246,0.085057005,0.02364101,0.8561178],"study_design_scores_gemma":[0.00032341294,0.00028758694,0.00004925589,0.000025383293,0.000017094935,0.00007059149,0.000035048535,0.9025765,0.00013760042,0.0953628,0.0010039794,0.00011075504],"about_ca_topic_score_codex":0.00005207328,"about_ca_topic_score_gemma":0.0000041451244,"teacher_disagreement_score":0.8696482,"about_ca_system_score_codex":0.000079187,"about_ca_system_score_gemma":0.00033313723,"threshold_uncertainty_score":0.38622493},"labels":[],"label_agreement":null},{"id":"W4226108323","doi":"10.1002/rsa.21110","title":"The height of record‐biased trees","year":2022,"lang":"en","type":"preprint","venue":"Random Structures and Algorithms","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Combinatorics; Permutation (music); Sigma; Tree (set theory); Mathematics; Binary tree; Order (exchange); Random permutation; Binary number; Binary search tree; Random binary tree; Rank (graph theory); Binary logarithm; Discrete mathematics; Physics; Symmetric group; Arithmetic","score_opus":0.01583621775068175,"score_gpt":0.2714602099799519,"score_spread":0.2556239922292702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226108323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022931274,0.008226492,0.98483074,0.0008084192,0.0021320514,0.00046547965,0.00005797066,0.00006366962,0.0011220797],"genre_scores_gemma":[0.059397954,0.0055383593,0.9330029,0.00028387186,0.00059642224,0.00013358863,0.00002651665,0.000044048033,0.00097633444],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977466,0.0004689692,0.00046463992,0.00062803633,0.0003899461,0.00030181505],"domain_scores_gemma":[0.9978384,0.0006233397,0.00036907697,0.001001697,0.00006605794,0.00010145996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008814842,0.0003188517,0.00061396806,0.0000827437,0.00042625415,0.00026092157,0.0013665264,0.00016653367,0.00004184584],"category_scores_gemma":[0.00006314014,0.00019395696,0.0002670352,0.00014799323,0.00014109231,0.000069444155,0.0015680549,0.00067866413,1.9161965e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086976615,0.000013066569,0.000025931222,0.00006027249,0.00012233293,0.00001370035,0.0005589384,0.00010227858,0.00007083295,0.057809256,0.00090197875,0.9402344],"study_design_scores_gemma":[0.0032047906,0.00012779048,0.0013203023,0.00005742123,0.00007255973,0.000037148176,0.000045495435,0.06810765,0.000734155,0.88547033,0.040266495,0.0005558662],"about_ca_topic_score_codex":0.00014457724,"about_ca_topic_score_gemma":0.00001913302,"teacher_disagreement_score":0.93967855,"about_ca_system_score_codex":0.000020092248,"about_ca_system_score_gemma":0.00011449335,"threshold_uncertainty_score":0.79093355},"labels":[],"label_agreement":null},{"id":"W4229334056","doi":"10.1142/s1793351x22500039","title":"A Non-parametric Bayesian Learning Model Using Accelerated Variational Inference on Multivariate Beta Mixture Models for Medical Applications","year":2022,"lang":"en","type":"article","venue":"International Journal of Semantic Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet process; Computer science; Cluster analysis; Inference; Mixture model; Dirichlet distribution; Bayesian inference; Multivariate statistics; Artificial intelligence; Machine learning; Parametric model; Parametric statistics; Hierarchical Dirichlet process; Bayesian probability; Data mining; Latent Dirichlet allocation; Topic model; Mathematics; Statistics","score_opus":0.04458933156397867,"score_gpt":0.35163627531161434,"score_spread":0.3070469437476357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229334056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063568363,0.000048701066,0.9912189,0.0012008568,0.00070916483,0.00027326762,0.000008703971,0.000038383383,0.00014516222],"genre_scores_gemma":[0.5713255,0.000004143987,0.42803985,0.00033986167,0.0002501987,0.0000065256313,0.000005818799,0.000012750873,0.000015389473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967519,0.00018558648,0.00086523435,0.0003846713,0.0015178545,0.0002947612],"domain_scores_gemma":[0.9968921,0.00094596075,0.00088633207,0.00020544969,0.00089926965,0.00017089439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020808412,0.00020566293,0.00034072564,0.0006964348,0.00047812483,0.00025066154,0.0019512693,0.00008793157,0.000021685602],"category_scores_gemma":[0.00027121033,0.0001998725,0.00021382394,0.00061625784,0.000026469303,0.00042828466,0.0006080188,0.00086029666,8.583436e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037053873,0.00018120391,0.00005314652,0.000010444367,0.00013129401,0.000027614293,0.00058304047,0.8673208,0.0003776871,0.094863795,0.000034939865,0.03637903],"study_design_scores_gemma":[0.0009303557,0.00010519196,0.000059064434,0.00008111864,0.000023227576,0.0002584182,0.000018746305,0.9210311,0.00009774372,0.07713926,0.00007500286,0.00018074478],"about_ca_topic_score_codex":0.00001841445,"about_ca_topic_score_gemma":4.767673e-7,"teacher_disagreement_score":0.56496865,"about_ca_system_score_codex":0.00024705942,"about_ca_system_score_gemma":0.00067579816,"threshold_uncertainty_score":0.81505644},"labels":[],"label_agreement":null},{"id":"W4230242023","doi":"10.1002/0470011815.b2a15012","title":"Bivariate Distributions","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Bivariate analysis; Bivariate data; Mathematics; Statistics; Econometrics; Statistical physics; Physics","score_opus":0.007454005870036902,"score_gpt":0.2584990321451809,"score_spread":0.25104502627514397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230242023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.048365e-8,0.00048041638,0.5394525,0.00010578597,0.00050642854,0.000093091614,0.00075852213,0.0001017696,0.45850143],"genre_scores_gemma":[0.000007236248,0.0017128946,0.67046463,0.00004290928,0.0003075666,0.0000054559628,0.00006869578,0.000083679835,0.32730693],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998724,0.00008020022,0.00032482392,0.00036591382,0.00023987598,0.00026521858],"domain_scores_gemma":[0.99865043,0.00011915365,0.0003231824,0.0007404419,0.000050253275,0.000116540694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014548829,0.0002500235,0.00036730838,0.00018371447,0.00003310724,0.000029016046,0.0007494991,0.0002464703,0.0006053384],"category_scores_gemma":[0.00011272307,0.00023283924,0.00007616626,0.00027345866,0.00008376623,0.000047522022,0.00018297006,0.00019042383,0.000100800906],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9018008e-7,0.000029646724,0.000002856433,0.000028858858,0.000019284793,0.000007798411,0.000035475783,1.4354927e-7,0.0000024376416,0.38951468,0.47239065,0.13796778],"study_design_scores_gemma":[0.00012982698,0.000031085438,0.00006204884,0.000074851065,0.000033430104,0.0000047899052,7.2711464e-7,0.0005342909,0.00002088523,0.019695977,0.9791423,0.00026980456],"about_ca_topic_score_codex":0.00007776941,"about_ca_topic_score_gemma":0.000030425374,"teacher_disagreement_score":0.50675166,"about_ca_system_score_codex":0.00002209581,"about_ca_system_score_gemma":0.0001493943,"threshold_uncertainty_score":0.94949085},"labels":[],"label_agreement":null},{"id":"W4230320142","doi":"10.1007/s10463-009-0239-z","title":"Semiparametric marginal and association regression methods for clustered binary data","year":2009,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"National Heart, Lung, and Blood Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Inference; Semiparametric regression; Nuisance parameter; Marginal model; Mathematics; Econometrics; Binary data; Statistics; Association (psychology); Binary number; Semiparametric model; Regression; Statistical inference; Regression analysis; Computer science; Artificial intelligence; Estimator; Psychology","score_opus":0.13702687448004242,"score_gpt":0.4420097317015558,"score_spread":0.30498285722151336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230320142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079700886,0.00024557445,0.99492216,0.003109272,0.00019590865,0.00026798795,0.00009823657,0.000014234131,0.00034962548],"genre_scores_gemma":[0.01395196,0.00008470734,0.98558563,0.00025157514,0.000020966963,0.0000027213055,0.0000073224974,0.000004670449,0.000090462614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874616,0.000142585,0.00044393257,0.00023384599,0.0002572622,0.00017620352],"domain_scores_gemma":[0.99720746,0.00128288,0.00044778094,0.00081436185,0.00018397272,0.00006356992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002232596,0.00011896316,0.00035691762,0.00007831089,0.00007696337,0.000036987083,0.0009684593,0.00008984838,0.0000013303517],"category_scores_gemma":[0.003337573,0.000076424694,0.00005175614,0.0003018576,0.000082891536,0.0003198158,0.00036676147,0.000101336744,3.035759e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014938611,0.00015668079,0.000008019878,0.00022678838,0.000031247597,7.9720917e-7,0.00015346914,0.000010277444,0.0009881224,0.6902609,0.004625568,0.30352318],"study_design_scores_gemma":[0.00021074968,0.00014821933,0.0005134419,0.00018509157,0.000041744068,0.000006711592,0.0000040615514,0.21614265,0.0028231982,0.7786434,0.0011829959,0.000097711614],"about_ca_topic_score_codex":0.0000037876991,"about_ca_topic_score_gemma":4.5352226e-7,"teacher_disagreement_score":0.3034255,"about_ca_system_score_codex":0.000010856771,"about_ca_system_score_gemma":0.000058087157,"threshold_uncertainty_score":0.39956278},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02534143546384614,"score_gpt":0.34045663582690844,"score_spread":0.3151152003630623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230827384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9242954e-7,0.0004256231,0.75732994,0.00007757486,0.0010220554,0.00016300779,0.00004796655,0.00009082923,0.24084279],"genre_scores_gemma":[0.0000012458971,0.00036946032,0.66317195,0.000121603065,0.00013427524,0.000015979114,0.00002920827,0.00003400136,0.33612227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99790573,0.00026494687,0.00051193906,0.00062460836,0.00030463404,0.00038813325],"domain_scores_gemma":[0.9983399,0.00034873208,0.00023964142,0.0008377617,0.00013425002,0.00009973845],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008335222,0.00036250116,0.0005099621,0.00025562017,0.000072200055,0.0001777983,0.0008633616,0.00032803553,0.00007272032],"category_scores_gemma":[0.00017268825,0.00038157467,0.00006530704,0.00020493542,0.00011457434,0.0003190493,0.0003646239,0.00058548053,0.000038053284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035171963,0.00000891561,0.0000036528593,0.00006243302,0.0000119783335,0.00012434428,0.00040661512,0.000007268652,0.000007183735,0.6547874,0.008715013,0.33586165],"study_design_scores_gemma":[0.000106468215,0.000047734804,0.000053655254,0.00007539214,0.000015049796,0.000035828372,0.000003191435,0.003063776,0.00004625618,0.68753785,0.3086509,0.00036388927],"about_ca_topic_score_codex":0.000010694285,"about_ca_topic_score_gemma":0.000040790175,"teacher_disagreement_score":0.33549777,"about_ca_system_score_codex":0.00023739038,"about_ca_system_score_gemma":0.0004282658,"threshold_uncertainty_score":0.9998636},"labels":[],"label_agreement":null},{"id":"W4232641003","doi":"10.1017/s0021900200021513","title":"On probability generating functions for waiting time distributions of compound patterns in a sequence of multistate trials","year":2002,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Markov chain; Mathematics; Probability distribution; Sequence (biology); Probability-generating function; Generating function; Probability mass function; Discrete phase-type distribution; Algorithm; Markov process; Applied mathematics; Markov property; Statistics; Markov model; Discrete mathematics","score_opus":0.11092957150548823,"score_gpt":0.31637288672889785,"score_spread":0.20544331522340964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232641003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36118433,0.000019286344,0.637676,0.00018124744,0.00006948365,0.00061348564,0.000117785574,0.000008611145,0.00012978147],"genre_scores_gemma":[0.6198422,0.00000276654,0.38006204,0.000015867177,0.00003685243,0.000027712082,0.0000029241348,0.000004360321,0.0000052933274],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968481,0.00044202432,0.0018399477,0.00031921986,0.00030339597,0.00024731323],"domain_scores_gemma":[0.99595165,0.0016855883,0.0014251744,0.00044824355,0.00039819136,0.000091159614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068100025,0.00016582964,0.0008140297,0.00010820853,0.000093368755,0.000038268925,0.0004373485,0.00008842493,0.000021581342],"category_scores_gemma":[0.001106437,0.00013282454,0.00027487037,0.0003194393,0.0001097257,0.00019790838,0.00007306092,0.00027946767,7.7703794e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008567054,0.004608942,0.0018212927,0.0013585809,0.0002484429,0.000011820308,0.0045850202,0.026861073,0.19576666,0.3666794,0.00045729484,0.3967448],"study_design_scores_gemma":[0.0025169936,0.0006633005,0.00077783875,0.00025432513,0.000064185704,0.000026468488,0.000025012805,0.41996503,0.020257745,0.5550751,0.00008354082,0.00029043073],"about_ca_topic_score_codex":0.000011832967,"about_ca_topic_score_gemma":0.000010979552,"teacher_disagreement_score":0.39645433,"about_ca_system_score_codex":0.00017027867,"about_ca_system_score_gemma":0.00010342201,"threshold_uncertainty_score":0.5416427},"labels":[],"label_agreement":null},{"id":"W4233480015","doi":"10.1515/iupac.81.0092","title":"Bayesian Probability","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Glossary; Ecotoxicology; Bayesian probability; Relation (database); Computer science; Ecology; Biology; Data mining; Artificial intelligence; Linguistics; Philosophy","score_opus":0.01867095943699669,"score_gpt":0.3883203934184031,"score_spread":0.3696494339814064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233480015","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.332588e-7,0.00021858474,0.49340698,0.0010540767,0.0006622028,0.00023976727,0.50422657,0.00010966389,0.00008181548],"genre_scores_gemma":[0.0000021394665,0.00024450835,0.13570258,0.00064955396,0.000771778,0.000028131772,0.86223984,0.00002865033,0.00033282532],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573046,0.00040260205,0.0006367798,0.001260559,0.0012673754,0.0007022339],"domain_scores_gemma":[0.99558717,0.00017024744,0.00032720633,0.0030374217,0.0005246655,0.00035331212],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018459761,0.00060241745,0.00082574924,0.00021834757,0.00015712541,0.00022611853,0.0024642567,0.0005581802,0.0005808325],"category_scores_gemma":[0.0005207652,0.0004221897,0.00029597298,0.0003689885,0.00016493871,0.00033621126,0.00076906756,0.00065286725,0.0000028910974],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017274951,0.00014900112,9.405096e-7,0.00010642542,0.00003864785,0.00005005761,0.000012166464,2.2755445e-7,0.0000030028232,0.0019667062,0.91491884,0.082736686],"study_design_scores_gemma":[0.00041279735,0.0001451102,0.000005029154,0.00021040224,0.000032030923,0.000026901947,4.5007485e-7,0.00014164121,0.00002140537,0.07631458,0.9221637,0.00052590884],"about_ca_topic_score_codex":0.000051683302,"about_ca_topic_score_gemma":0.0002123961,"teacher_disagreement_score":0.35801324,"about_ca_system_score_codex":0.00040486048,"about_ca_system_score_gemma":0.0013542641,"threshold_uncertainty_score":0.999823},"labels":[],"label_agreement":null},{"id":"W4235606038","doi":"10.1007/978-1-4939-7131-2_101018","title":"Scale-Free Distributions","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Scale (ratio); Environmental science; Computer science; Geography; Cartography","score_opus":0.020307012560548333,"score_gpt":0.25160664097885177,"score_spread":0.23129962841830343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235606038","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.441275e-8,0.000057888963,0.51193863,0.00068361504,0.00028221254,0.00006479957,0.000030263907,0.00013380888,0.48680872],"genre_scores_gemma":[0.000003320401,0.000020631624,0.48003563,0.00023731371,0.0002185759,0.0000026151693,0.000009160486,0.000011150326,0.5194616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875355,0.000016658349,0.00022302083,0.0005290565,0.00024030554,0.00023739038],"domain_scores_gemma":[0.99771243,0.0000464464,0.00009046201,0.0018710509,0.00013113003,0.00014847014],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022053985,0.00025394987,0.00026495283,0.00007684543,0.00011538129,0.00012834922,0.0017518075,0.00029838996,0.0011989097],"category_scores_gemma":[0.000015843472,0.00017793286,0.00017948062,0.000035821155,0.00011778723,0.00014915512,0.00079817016,0.00024229387,0.00074665534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.838147e-7,0.0000037401637,1.1236965e-7,0.0000035026042,0.0000104301525,0.000004327181,0.00001782609,3.6436476e-9,0.000002782421,0.81053394,0.121764265,0.067658715],"study_design_scores_gemma":[0.000052708456,0.000022302238,0.000001757751,0.000022385757,0.0000090840185,0.000013338174,7.123199e-8,0.00015668025,0.000075927914,0.6006662,0.3988066,0.00017288781],"about_ca_topic_score_codex":0.0000043137607,"about_ca_topic_score_gemma":0.000018884311,"teacher_disagreement_score":0.27704233,"about_ca_system_score_codex":0.000041506628,"about_ca_system_score_gemma":0.00008470823,"threshold_uncertainty_score":0.99971414},"labels":[],"label_agreement":null},{"id":"W4236319758","doi":"10.1017/s0021900200006690","title":"On the number of runs for Bernoulli arrays","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Mathematics; Multinomial distribution; Row; Bernoulli's principle; Independent and identically distributed random variables; Combinatorics; Bernoulli trial; Row and column spaces; Sampling (signal processing); Statistics; Random variable; Computer science","score_opus":0.019655331318162064,"score_gpt":0.279054144279261,"score_spread":0.25939881296109896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236319758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14879115,0.0000031805093,0.84167093,0.0015460374,0.00032461536,0.00028090645,0.0000022539348,0.000007600502,0.0073733306],"genre_scores_gemma":[0.453985,9.0890757e-7,0.54571587,0.00018568616,0.00008791821,0.00000861472,6.594263e-8,0.0000039182387,0.000012015868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989391,0.00004942263,0.00042650333,0.00016478957,0.00026132306,0.00015887493],"domain_scores_gemma":[0.99808365,0.0006478586,0.00041062338,0.0005611574,0.00022116424,0.00007555198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028740312,0.000102184866,0.00024548318,0.000024775554,0.000073177114,0.000037760416,0.00083464757,0.00008249688,0.00003259563],"category_scores_gemma":[0.00017265274,0.000057496458,0.00017781879,0.00012683982,0.00009697429,0.00009211913,0.000060135586,0.00042174224,0.0000029649862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006568627,0.00013463691,0.000070865055,0.00002107891,0.00001675905,3.0055023e-7,0.00033656883,0.000018221263,0.0066272523,0.9663392,0.0005860733,0.025783379],"study_design_scores_gemma":[0.00026078924,0.00007036009,0.00031088048,0.000008080967,0.000010092106,0.000014013972,0.0000045926777,0.0008292469,0.017736545,0.9790881,0.0016019703,0.000065316075],"about_ca_topic_score_codex":0.0000011899385,"about_ca_topic_score_gemma":0.0000022862614,"teacher_disagreement_score":0.30519387,"about_ca_system_score_codex":0.000016288375,"about_ca_system_score_gemma":0.0001153745,"threshold_uncertainty_score":0.23446375},"labels":[],"label_agreement":null},{"id":"W4236852595","doi":"10.1007/978-1-4939-7131-2_100914","title":"Probability Distributions","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics","score_opus":0.04808679159076895,"score_gpt":0.26685295991925606,"score_spread":0.2187661683284871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236852595","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.216127e-7,0.00003769393,0.51539,0.000293963,0.00017903805,0.000107161955,0.0000129912105,0.0001234223,0.48385566],"genre_scores_gemma":[0.000012886755,0.000007637437,0.5274405,0.00012284682,0.00012221323,0.000004228689,0.0000076293463,0.0000071051118,0.47227496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99884945,0.000021132904,0.00021513057,0.0005427996,0.00017999313,0.000191514],"domain_scores_gemma":[0.9984702,0.000044411852,0.000081694074,0.0011417131,0.00014913433,0.00011287198],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031101282,0.000212689,0.00022844164,0.000040970688,0.00009133326,0.00009270001,0.00078602845,0.0002534533,0.0011468421],"category_scores_gemma":[0.000018940957,0.00016854118,0.00015156054,0.00002830275,0.000118436605,0.0001272602,0.00035119048,0.00021124343,0.0005274423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.8026133e-7,0.0000061513815,1.7800336e-7,0.0000068689624,0.00000944302,0.0000021527019,0.000017697379,7.7835765e-9,0.0000017573916,0.9431876,0.021074882,0.035692897],"study_design_scores_gemma":[0.000025119973,0.000023499748,0.0000024866436,0.000014100483,0.0000060431717,0.0000062143563,2.612204e-8,0.00018753446,0.000037171634,0.6825645,0.31698754,0.00014578167],"about_ca_topic_score_codex":0.0000028041482,"about_ca_topic_score_gemma":0.000007867086,"teacher_disagreement_score":0.29591265,"about_ca_system_score_codex":0.000056721157,"about_ca_system_score_gemma":0.000111779846,"threshold_uncertainty_score":0.99976623},"labels":[],"label_agreement":null},{"id":"W4236940986","doi":"10.1017/s0021900200005532","title":"A Central Limit Theorem Associated with the Transformed Two-Parameter Poisson–Dirichlet Distribution","year":2009,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Dirichlet distribution; Poisson distribution; Central limit theorem; Limit (mathematics); Distribution (mathematics); Concentration parameter; Simplex; Applied mathematics; Mathematical analysis; Pure mathematics; Statistical physics; Combinatorics; Statistics","score_opus":0.012979437113765806,"score_gpt":0.23696040582359254,"score_spread":0.22398096870982673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236940986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14333451,0.0000332311,0.84840184,0.0062026954,0.00007349967,0.00035978507,0.000005764335,0.00003432767,0.0015543664],"genre_scores_gemma":[0.90361506,0.000005253205,0.09562178,0.0006618926,0.000074529984,0.00000518637,0.0000026515513,0.0000053048348,0.000008327358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981095,0.00023915022,0.00046636333,0.00026142166,0.00049287704,0.00043065977],"domain_scores_gemma":[0.99843425,0.0003466547,0.00041522685,0.00042162635,0.00021831301,0.00016391944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002511761,0.00019889776,0.00035725944,0.00003201158,0.00015202224,0.00015674582,0.00079165667,0.00009390943,0.000006104417],"category_scores_gemma":[0.00011429639,0.000104298466,0.00018159418,0.00043652792,0.00011639932,0.00029651195,0.000026348256,0.00052578363,8.10327e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084018527,0.0008806288,0.00022165207,0.000016148051,0.00017168758,0.000021291446,0.0034436341,0.00061651325,0.0014195951,0.6440166,0.0013012363,0.3470508],"study_design_scores_gemma":[0.0019896852,0.0007852409,0.021075064,0.000045862966,0.00010518192,0.0000738528,0.000027991557,0.006016485,0.0049288603,0.9635739,0.0010639648,0.0003139463],"about_ca_topic_score_codex":0.0000013470985,"about_ca_topic_score_gemma":0.000007741871,"teacher_disagreement_score":0.76028055,"about_ca_system_score_codex":0.00019189261,"about_ca_system_score_gemma":0.00017306415,"threshold_uncertainty_score":0.42531678},"labels":[],"label_agreement":null},{"id":"W4237557945","doi":"10.1002/0471667196.ess5083","title":"<scp>B</scp>ox–<scp>C</scp>ox Transformations: Selecting for Symmetry","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistical Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Citation; Encyclopedia; Library science; Computer science","score_opus":0.015282669156785045,"score_gpt":0.29379413166004925,"score_spread":0.2785114625032642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237557945","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007896385,0.0010563397,0.5435533,0.00007435504,0.0005619479,0.00045207574,0.00020572412,0.00014832192,0.45394003],"genre_scores_gemma":[0.00016414796,0.0011993608,0.8946327,0.00023487366,0.0007037308,0.00009931415,0.000024119541,0.000101565114,0.10284021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956708,0.00023468341,0.0008574387,0.0010879441,0.0010737034,0.0010754127],"domain_scores_gemma":[0.99250007,0.0059721875,0.00054086273,0.00048251107,0.00013982132,0.00036454937],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018288948,0.0005350145,0.000800251,0.00057142734,0.00038709,0.00027853044,0.0020326364,0.0004121826,0.00009569751],"category_scores_gemma":[0.0030683721,0.00044351595,0.00019219305,0.0013370888,0.0006297406,0.0005456658,0.00016296838,0.00043742085,0.00005304305],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.85281e-7,0.00009037831,0.00002673394,0.00020779556,0.000035201483,0.0000035060227,0.0010566098,0.000008574125,0.00001046157,0.44458112,0.39478588,0.15919325],"study_design_scores_gemma":[0.00035742114,0.0003125059,0.00011062233,0.00022998177,0.00007198483,0.000017719118,0.00018997816,0.011422485,0.00011513292,0.087540366,0.8994421,0.0001897476],"about_ca_topic_score_codex":0.00010960931,"about_ca_topic_score_gemma":0.00009595318,"teacher_disagreement_score":0.50465614,"about_ca_system_score_codex":0.000054295142,"about_ca_system_score_gemma":0.00051556394,"threshold_uncertainty_score":0.99980164},"labels":[],"label_agreement":null},{"id":"W4237669612","doi":"10.5539/cis.v1n4p0","title":"Computer and Information Science, Vol. 1, No. 4, November 2008, all in one file","year":2008,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.024833682263597695,"score_gpt":0.25564079143446206,"score_spread":0.23080710917086436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237669612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011787028,0.000023356906,0.9776765,0.00023632741,0.0009577332,0.00025883206,0.000011254245,0.00008663939,0.00896229],"genre_scores_gemma":[0.08555684,0.00017907133,0.907144,0.0068770004,0.00017077422,0.000016808604,0.000015915466,0.0000036426004,0.000035959758],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977361,0.000032528216,0.00055952073,0.00034696196,0.0008097195,0.00051518617],"domain_scores_gemma":[0.99797946,0.00008277413,0.00019210753,0.00044404506,0.0010158049,0.00028577656],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001526359,0.0001924638,0.00022356375,0.0010729912,0.00055519247,0.00096883764,0.0009862705,0.00006909125,0.000029341725],"category_scores_gemma":[0.00012969847,0.0001712165,0.000027565484,0.0020457706,0.0009641296,0.050270155,0.000900878,0.00019565028,0.00012625105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015524722,0.00009269609,0.0010937832,0.00009327253,0.000007785896,0.0000044116728,0.015109669,0.00054160116,0.00018487283,0.13083456,0.033315953,0.81870586],"study_design_scores_gemma":[0.000583478,0.00012171055,0.07835292,0.000043486998,0.0000014635833,0.00008557197,0.0000074962986,0.8642213,0.00020762306,0.0006980666,0.05537919,0.0002976995],"about_ca_topic_score_codex":0.000028802831,"about_ca_topic_score_gemma":0.0000012190546,"teacher_disagreement_score":0.8636797,"about_ca_system_score_codex":0.0000688744,"about_ca_system_score_gemma":0.000349851,"threshold_uncertainty_score":0.96301323},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.026056546071332128,"score_gpt":0.3550975326748263,"score_spread":0.3290409866034942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237780050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075478584,0.0005908089,0.9968912,0.001351629,0.00013055153,0.00011966213,0.000049318598,0.0000137733905,0.000098276156],"genre_scores_gemma":[0.017723335,0.00011490999,0.9812755,0.0006920618,0.00013100162,0.0000044980934,0.0000068138506,0.000009536401,0.0000423416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861145,0.00017554774,0.00050958944,0.00020398265,0.00029553342,0.00020387913],"domain_scores_gemma":[0.9975937,0.0014225312,0.00022253502,0.000085766005,0.00047874294,0.00019670697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545322,0.00014907985,0.00031741703,0.0001293733,0.00015778778,0.00012993516,0.00031630762,0.00008485125,0.000012552368],"category_scores_gemma":[0.00010241538,0.00011488226,0.000096546326,0.00027524686,0.00007231227,0.0002832073,0.00002537238,0.00024619457,2.5069468e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004749068,0.000050016657,0.000008689816,0.000038013568,0.000036414007,0.000005503342,0.00019992213,0.010335753,0.000009194619,0.38175908,0.0004257402,0.60708416],"study_design_scores_gemma":[0.00029778449,0.000112482005,0.00028479283,0.000018467159,0.000016064141,0.00009059925,0.0000020837076,0.42082125,0.000005446339,0.5772555,0.0010092694,0.00008626935],"about_ca_topic_score_codex":9.2706875e-7,"about_ca_topic_score_gemma":3.06515e-7,"teacher_disagreement_score":0.6069979,"about_ca_system_score_codex":0.000010358478,"about_ca_system_score_gemma":0.00009096467,"threshold_uncertainty_score":0.46847627},"labels":[],"label_agreement":null},{"id":"W4238363556","doi":"10.22215/etd/2012-09586","title":"Uniform and Mallows random permutations : inversions, levels &amp; sampling","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Mathematics; Combinatorics; Computer science; Humanities; Philosophy","score_opus":0.05953981127414389,"score_gpt":0.3265836779658595,"score_spread":0.26704386669171565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238363556","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053217215,0.00075108715,0.9641262,0.00019999403,0.00076368474,0.0002896786,0.000009344567,0.00012737355,0.028410882],"genre_scores_gemma":[0.028343674,0.00012507057,0.93438023,0.00027467153,0.0001180121,0.000032398853,0.00020111178,0.00002558361,0.03649924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863076,0.000089358255,0.00029883208,0.00042548127,0.0002360898,0.00031950074],"domain_scores_gemma":[0.9988638,0.00021826115,0.000142436,0.00045483382,0.000117648226,0.00020297673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005246223,0.00026837268,0.00032532515,0.00021588335,0.00027528673,0.00018879089,0.0004473036,0.00028009975,0.00015772629],"category_scores_gemma":[0.00006455529,0.00022733043,0.000108766115,0.000217458,0.000020291527,0.00053874997,0.00008970241,0.0002982902,0.00005175673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004262318,0.00007574913,0.0001526006,0.00025117706,0.000119600816,0.0000035741418,0.01027182,0.000010118864,0.0020970614,0.6456334,0.0025438466,0.33879843],"study_design_scores_gemma":[0.009670896,0.00016343663,0.050589405,0.0012344918,0.00090506696,0.0002458614,0.0022446234,0.028472103,0.00295974,0.690007,0.20716463,0.0063427524],"about_ca_topic_score_codex":0.000065017455,"about_ca_topic_score_gemma":0.0003098623,"teacher_disagreement_score":0.33245566,"about_ca_system_score_codex":0.000024462113,"about_ca_system_score_gemma":0.00013957614,"threshold_uncertainty_score":0.92702657},"labels":[],"label_agreement":null},{"id":"W4239715372","doi":"10.1002/9781118445112.stat00939.pub2","title":"Asymptotic Expansions","year":2017,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Statistical inference; Asymptotic expansion; Inference; Applied mathematics; Asymptotic analysis; Calculus (dental); Statistical physics; Computer science; Statistics; Physics; Mathematical analysis; Artificial intelligence; Medicine","score_opus":0.04802184269948695,"score_gpt":0.33776664886276186,"score_spread":0.2897448061632749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239715372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.5642373e-7,0.0013831385,0.8000669,0.00014895941,0.00101871,0.0003222604,0.007857145,0.00044128875,0.18876135],"genre_scores_gemma":[0.00001549077,0.0031443713,0.62203556,0.0002028716,0.00027511935,0.000020319712,0.0008481217,0.0002550695,0.37320307],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99653685,0.00022790134,0.0004895818,0.0012254136,0.00071554055,0.0008047337],"domain_scores_gemma":[0.99529076,0.00021773345,0.0007928711,0.003046286,0.00020269904,0.00044965255],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028069154,0.00074309466,0.00092050416,0.0004131049,0.0002716845,0.00036817387,0.002919298,0.000551408,0.00068399264],"category_scores_gemma":[0.0002961473,0.0006555071,0.000099163226,0.00018457978,0.0002568493,0.0001852503,0.0006792276,0.00085259683,0.0003036064],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024849414,0.000109634144,0.0000033615534,0.00007345576,0.00005437465,0.00010488861,0.000041182422,7.0134104e-7,0.0000127999,0.23213615,0.5412473,0.22621368],"study_design_scores_gemma":[0.00044738076,0.00015203036,0.00004713713,0.00097119616,0.000075050244,0.000024186931,0.0000041300023,0.00486144,0.000008000049,0.092829734,0.8996347,0.00094497105],"about_ca_topic_score_codex":0.00036640847,"about_ca_topic_score_gemma":0.00096740626,"teacher_disagreement_score":0.35838747,"about_ca_system_score_codex":0.00007929755,"about_ca_system_score_gemma":0.0006246234,"threshold_uncertainty_score":0.9995896},"labels":[],"label_agreement":null},{"id":"W4241899158","doi":"10.1017/s0021900200019604","title":"On ordered series and later waiting time distributions in a sequence of Markov dependent multistate trials","year":2003,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Council","keywords":"Markov chain; Mathematics; Series (stratigraphy); Sequence (biology); Markov process; Probability distribution; Variable-order Markov model; Applied mathematics; Simple (philosophy); Discrete phase-type distribution; Markov model; Statistics","score_opus":0.03631565173903959,"score_gpt":0.29071477998055023,"score_spread":0.2543991282415106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241899158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4337394,0.00004028085,0.56467676,0.0002876156,0.00005991642,0.00030783066,0.000017351838,0.000008088491,0.0008627547],"genre_scores_gemma":[0.6487449,0.00000944028,0.35120118,0.000018569543,0.0000076179986,0.000004914535,4.2989763e-7,0.0000027775275,0.00001021215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980654,0.00047918857,0.00085303985,0.00021275092,0.00021209155,0.00017750864],"domain_scores_gemma":[0.99854875,0.0004869984,0.00052563066,0.00023924396,0.00011945816,0.00007991851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006029503,0.00011865326,0.0004909344,0.00006973216,0.000047746653,0.000049776358,0.00021893236,0.00006410979,0.000013428638],"category_scores_gemma":[0.000670807,0.00008773901,0.00007287681,0.00018247511,0.000078829515,0.00020320056,0.000052570475,0.00022398244,7.599072e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009900742,0.0005971322,0.00059096224,0.00021164911,0.00008717476,0.00005074084,0.0018739409,0.00059566926,0.07246488,0.7890808,0.00007763709,0.13337931],"study_design_scores_gemma":[0.0013130383,0.00022195207,0.0007433589,0.00007502281,0.000018529334,0.00008506533,0.000015232627,0.0030470644,0.036678072,0.9575346,0.0001071495,0.00016091917],"about_ca_topic_score_codex":0.0000035982728,"about_ca_topic_score_gemma":0.000005764766,"teacher_disagreement_score":0.21500549,"about_ca_system_score_codex":0.0000706666,"about_ca_system_score_gemma":0.00012346207,"threshold_uncertainty_score":0.3577893},"labels":[],"label_agreement":null},{"id":"W4244575239","doi":"10.22215/etd/2016-11343","title":"Estimation of the Amount of Sparsity in Normal Mixture Models","year":2016,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Estimator; Context (archaeology); Rate of convergence; Selection (genetic algorithm); Convergence (economics); Applied mathematics; Computer science; Model selection; Mathematical optimization; Mathematics; Algorithm; Estimation; Statistics; Machine learning; Engineering","score_opus":0.012860329112318148,"score_gpt":0.2595963964401946,"score_spread":0.24673606732787645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244575239","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019154197,0.00008944856,0.9582052,0.00010670717,0.00039004983,0.00020652261,0.00000671916,0.000013298728,0.021827836],"genre_scores_gemma":[0.7085327,0.000017949036,0.28785944,0.000037414913,0.000016782114,0.000006702722,0.000009722644,0.000007878087,0.003511423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885064,0.00011086232,0.0003605172,0.00024375711,0.00029678704,0.00013740304],"domain_scores_gemma":[0.99889874,0.000058160873,0.00033775,0.0005719587,0.000107979395,0.000025400592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036805397,0.0001468068,0.00028862775,0.000116931296,0.000027770346,0.000012812697,0.0008671615,0.00023105703,0.00001063031],"category_scores_gemma":[0.000025718042,0.00008424557,0.000119587494,0.0002509726,0.000024052686,0.00030640606,0.00008310851,0.0001619046,0.0000011072253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003362463,0.00009414224,0.000082570776,0.00029919998,0.000022796417,0.0000011510348,0.00270901,0.0015413689,0.0030346138,0.6828466,0.00031104748,0.30902386],"study_design_scores_gemma":[0.0004234195,0.000044455555,0.006638159,0.0006499153,0.0000274194,0.000002713967,0.000022453976,0.38975304,0.104256235,0.49784446,0.000026165975,0.0003115733],"about_ca_topic_score_codex":0.00015380046,"about_ca_topic_score_gemma":0.00023909865,"teacher_disagreement_score":0.6893785,"about_ca_system_score_codex":0.000026663329,"about_ca_system_score_gemma":0.00015027233,"threshold_uncertainty_score":0.34354347},"labels":[],"label_agreement":null},{"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.10550402890426634,"score_gpt":0.3245205179113725,"score_spread":0.21901648900710613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246027503","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031883765,0.000126458,0.98288256,0.00004711693,0.000102624734,0.00017892926,0.0000060861166,0.0004222983,0.013045546],"genre_scores_gemma":[0.5034998,0.0000103537695,0.49600658,0.0001421145,0.000049251736,0.00001394597,0.000006629544,0.000022635282,0.00024869668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968482,0.00033586487,0.0005176683,0.0010948171,0.00049350254,0.00070991233],"domain_scores_gemma":[0.9974446,0.000029355353,0.00032849706,0.0015587826,0.00020781478,0.00043089097],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068275764,0.00039969024,0.0007067616,0.00078177993,0.00028931163,0.00030387045,0.0015604477,0.00018614985,0.00009437188],"category_scores_gemma":[0.000017417795,0.00031239857,0.00043734812,0.002241179,0.0001065164,0.0016969783,0.00018790536,0.00022581955,0.000011405975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016484642,0.0024313773,0.016716039,0.00032716076,0.0061121243,0.002273351,0.06684305,0.03861808,0.0021660717,0.5049411,0.00020291831,0.35920385],"study_design_scores_gemma":[0.00019452536,0.000053836684,0.0009666468,0.00002163948,0.00063460506,0.000017056216,0.00006304671,0.8494728,0.002509735,0.14559004,0.000010622668,0.00046545127],"about_ca_topic_score_codex":0.00020041125,"about_ca_topic_score_gemma":0.00015519295,"teacher_disagreement_score":0.81085473,"about_ca_system_score_codex":0.000051051415,"about_ca_system_score_gemma":0.00013513249,"threshold_uncertainty_score":0.9999328},"labels":[],"label_agreement":null},{"id":"W4246063725","doi":"10.1007/978-1-4614-6170-8_100502","title":"Scale-Free Distributions","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Scale (ratio); Environmental science; Geography; Cartography","score_opus":0.01589913796774766,"score_gpt":0.23782433903414235,"score_spread":0.22192520106639468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246063725","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4560259e-8,0.00005381757,0.51190096,0.0010546392,0.00022386764,0.000060136226,0.000016916034,0.0001346208,0.48655504],"genre_scores_gemma":[0.000011494056,0.000019427038,0.46885866,0.0003396286,0.00014364871,0.00000300192,0.000009956613,0.000011785954,0.5306024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987735,0.000022821469,0.00023103907,0.00050471816,0.00023899232,0.00022893187],"domain_scores_gemma":[0.99772465,0.00007317803,0.00009604916,0.0018669614,0.00008549562,0.0001536687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002640488,0.00025743773,0.00030737947,0.000075354175,0.00010028758,0.00011973557,0.0016881936,0.0002923275,0.0002517242],"category_scores_gemma":[0.000018517087,0.00018102156,0.00019693487,0.000028531447,0.00006464186,0.000081518076,0.00065144507,0.00029587618,0.0003487921],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.44356e-7,0.0000021384706,1.3649625e-7,0.0000046405066,0.00000770717,0.000002607035,0.0000056680806,2.7628657e-8,0.0000022535348,0.76550174,0.04283788,0.19163498],"study_design_scores_gemma":[0.00005741439,0.000014375355,0.0000021137598,0.000020585841,0.000008809005,0.000011087459,2.4142338e-8,0.00038759917,0.000036465193,0.5635867,0.43570232,0.0001724875],"about_ca_topic_score_codex":0.0000052248256,"about_ca_topic_score_gemma":0.000014079755,"teacher_disagreement_score":0.39286444,"about_ca_system_score_codex":0.000035178207,"about_ca_system_score_gemma":0.000060057177,"threshold_uncertainty_score":0.7381845},"labels":[],"label_agreement":null},{"id":"W4246839045","doi":"10.1007/978-94-007-0753-5_101409","title":"Finite Mixture Model","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Materials science","score_opus":0.024105333869870155,"score_gpt":0.24476030449450098,"score_spread":0.22065497062463083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246839045","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.39248e-9,0.00013380956,0.50737256,0.00039805702,0.00017112598,0.000070753376,0.0000031840968,0.00014377672,0.49170676],"genre_scores_gemma":[0.000024769222,0.000043056647,0.4795603,0.0019931258,0.00012661543,0.0000025641018,0.0000035185483,0.000024784313,0.51822126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99840057,0.000022898099,0.00027972355,0.0007027151,0.00031441086,0.00027965705],"domain_scores_gemma":[0.99815947,0.00011206256,0.00013937932,0.0013270508,0.000095303985,0.0001667549],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030702644,0.00039931186,0.00043527852,0.0001374041,0.00007016271,0.00013193896,0.0012783464,0.00055771746,0.00015712305],"category_scores_gemma":[0.000013729196,0.0003203137,0.00024420113,0.000025827034,0.000040633447,0.000109922155,0.00037669952,0.00048939604,0.00035491746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.656074e-7,0.0000020786104,1.8203025e-8,0.000012395585,0.000013912949,0.0000064704,0.000033544537,0.00010531218,0.0000046887494,0.86389023,0.022026679,0.11390389],"study_design_scores_gemma":[0.00005123383,0.0000144538935,3.772094e-8,0.000027153834,0.0000087461,0.000005387558,2.4568124e-8,0.30276754,0.000015535607,0.5022797,0.1945851,0.00024508912],"about_ca_topic_score_codex":0.0000016326534,"about_ca_topic_score_gemma":0.0000032862592,"teacher_disagreement_score":0.36161056,"about_ca_system_score_codex":0.00002409633,"about_ca_system_score_gemma":0.00009872457,"threshold_uncertainty_score":0.9999249},"labels":[],"label_agreement":null},{"id":"W4247169681","doi":"10.1017/s0001867800005309","title":"The sampling formula and Laplace transform associated with the two-parameter Poisson-Dirichlet distribution","year":2011,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Dirichlet distribution; Laplace distribution; Laplace transform; Poisson distribution; Applied mathematics; Mathematical analysis; Statistics","score_opus":0.023740790130915686,"score_gpt":0.26585208943576366,"score_spread":0.24211129930484798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247169681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022742394,0.00048625527,0.97139275,0.0005614469,0.00005595924,0.0007432893,0.000007395854,0.0000654594,0.0039450503],"genre_scores_gemma":[0.80550694,0.0000731667,0.19411947,0.00011058966,0.000010366832,0.00015765407,0.0000037436682,0.00000636437,0.000011708975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863803,0.0001389082,0.0002361707,0.0004269789,0.0001923265,0.00036760847],"domain_scores_gemma":[0.99842453,0.00084655726,0.000111439316,0.0005207766,0.00004385303,0.00005284235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019119643,0.00017220173,0.00018469842,0.000012938591,0.00031932697,0.000086012085,0.00055265264,0.00005999637,0.0000013065127],"category_scores_gemma":[0.000087688866,0.00008702109,0.000034066405,0.0003471908,0.00026800632,0.00034525277,0.000092672846,0.00028045633,7.2078006e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010070255,0.00007084458,0.0008037413,0.000015312738,0.000013130302,6.881131e-7,0.0013951494,0.000048522157,0.00003425845,0.56938267,0.000009178384,0.4281258],"study_design_scores_gemma":[0.00058527594,0.00007562092,0.0047699767,0.000019209536,0.0000122293895,0.0000042011065,0.000032997254,0.0046459967,0.0010525228,0.9850302,0.0035604418,0.00021133962],"about_ca_topic_score_codex":0.00001607142,"about_ca_topic_score_gemma":0.00049097365,"teacher_disagreement_score":0.78276455,"about_ca_system_score_codex":0.00007848327,"about_ca_system_score_gemma":0.000031778025,"threshold_uncertainty_score":0.35486174},"labels":[],"label_agreement":null},{"id":"W4248602074","doi":"10.1007/978-94-007-0753-5_3109","title":"Univariate Normal Distribution","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Univariate; Univariate distribution; Distribution (mathematics); Statistics; Mathematics; Mathematical analysis; Exponential distribution; Multivariate statistics","score_opus":0.013301881789659012,"score_gpt":0.22381573691409426,"score_spread":0.21051385512443524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248602074","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.3622883e-8,0.000029007966,0.52129835,0.00023061693,0.00024878597,0.000045758014,0.0000069640982,0.00010065699,0.47803986],"genre_scores_gemma":[0.00014607885,0.00002423034,0.32039946,0.0003486369,0.00019018035,0.000001433522,0.000041506843,0.000013779071,0.6788347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893796,0.000028725695,0.00021056892,0.000411808,0.00020280202,0.0002081299],"domain_scores_gemma":[0.99892735,0.000045773377,0.00011689784,0.000728817,0.000071560724,0.000109566485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033023502,0.00023339677,0.00025405062,0.00004701014,0.0000687068,0.000102353,0.0007052875,0.00028899725,0.00018089668],"category_scores_gemma":[0.0000071420345,0.00019580961,0.00013086677,0.00002354462,0.000030399593,0.00011379641,0.00027176167,0.00025895808,0.000286103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.8549505e-7,0.0000015242376,9.450974e-8,0.0000056320278,0.000009240838,0.0000050073277,0.000006530854,4.686714e-7,0.000003351791,0.8468924,0.0052140774,0.14786084],"study_design_scores_gemma":[0.000074064956,0.000023429273,0.0000044877997,0.000021926518,0.000010180856,0.00001248089,3.8644234e-8,0.0044852155,0.000037231115,0.46374595,0.5313585,0.00022648645],"about_ca_topic_score_codex":0.000008039952,"about_ca_topic_score_gemma":0.000002229258,"teacher_disagreement_score":0.52614444,"about_ca_system_score_codex":0.000040548846,"about_ca_system_score_gemma":0.000058921065,"threshold_uncertainty_score":0.79848844},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.012404052224277515,"score_gpt":0.26020939399824977,"score_spread":0.24780534177397226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249826780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009550209,0.0002930677,0.99517506,0.0004734105,0.0008459304,0.000041625408,0.000012638566,0.000015943306,0.0021872846],"genre_scores_gemma":[0.12721258,0.00028335222,0.8718057,0.00023090313,0.00021646183,3.3394306e-7,7.1336376e-7,0.000010215678,0.00023968967],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986476,0.0000992013,0.00045328296,0.00013409888,0.00036374078,0.00030209892],"domain_scores_gemma":[0.9986493,0.00012994834,0.00034940874,0.000270714,0.00032588578,0.00027476254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005892119,0.00013028417,0.00025510177,0.00015042973,0.000083831175,0.0001359803,0.00069167203,0.00005497773,0.000035709225],"category_scores_gemma":[0.00010829945,0.000107516455,0.00007375231,0.0002988055,0.00004692014,0.0003098185,0.000066229004,0.0002602838,0.000015408428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000227286,0.00009575835,0.0032886239,0.000015513317,0.00005177858,0.0010561937,0.00062766543,0.00001582025,0.00015951543,0.34803838,0.0131619,0.6334661],"study_design_scores_gemma":[0.001296148,0.0009712352,0.008228043,0.0001843355,0.00007049285,0.0037125715,0.000046223977,0.00940287,0.00041830642,0.9618265,0.013428183,0.00041509248],"about_ca_topic_score_codex":0.0000023605132,"about_ca_topic_score_gemma":0.0000016870387,"teacher_disagreement_score":0.63305104,"about_ca_system_score_codex":0.000051900402,"about_ca_system_score_gemma":0.0001256628,"threshold_uncertainty_score":0.43843937},"labels":[],"label_agreement":null},{"id":"W4250271509","doi":"10.1198/jasa.2009.0103","title":"Order Selection in Finite Mixture Models With a Nonsmooth Penalty","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Akaike information criterion; Bayesian information criterion; Mathematics; Information Criteria; Mixing (physics); Mixture model; Scad; Model selection; Maximization; Bayesian probability; Expectation–maximization algorithm; Penalty method; Applied mathematics; Selection (genetic algorithm); Mathematical optimization; Absolute deviation; Statistics; Computer science; Maximum likelihood; Artificial intelligence","score_opus":0.007316331187808707,"score_gpt":0.25892188898643553,"score_spread":0.2516055577986268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250271509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063628894,0.000017162905,0.9876482,0.0054538203,0.000061823914,0.00007088217,0.000003921729,0.00000984555,0.00037149087],"genre_scores_gemma":[0.45933685,0.000011698373,0.5394054,0.001112397,0.00005146861,7.533857e-7,2.191824e-7,0.0000035798953,0.00007761125],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842256,0.0004026199,0.00032163702,0.00013452345,0.00050394767,0.00021470235],"domain_scores_gemma":[0.99822867,0.0004442845,0.00085177046,0.00010766529,0.0002983102,0.00006927654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008240052,0.00010126534,0.0002797084,0.00009348903,0.000065465705,0.00008182316,0.00034153348,0.000036549296,0.0000030446122],"category_scores_gemma":[0.0004486999,0.000060069207,0.000051954125,0.0009405711,0.000027141654,0.00034332395,0.000023259541,0.00040921473,0.0000010822143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005029418,0.00078270334,0.015254035,0.0000140214925,0.00018325602,0.00007529279,0.002134491,0.024377855,0.0014936646,0.34476697,0.012967977,0.5974468],"study_design_scores_gemma":[0.000929564,0.0011235795,0.1927182,0.00007177554,0.000057884503,0.00008397724,0.00002150471,0.37114176,0.00012953555,0.4331303,0.0003425321,0.00024938877],"about_ca_topic_score_codex":0.000033686087,"about_ca_topic_score_gemma":0.000031049458,"teacher_disagreement_score":0.5971974,"about_ca_system_score_codex":0.00029979652,"about_ca_system_score_gemma":0.00017511258,"threshold_uncertainty_score":0.24495511},"labels":[],"label_agreement":null},{"id":"W4252321446","doi":"10.1017/s0021900200015436","title":"NWU property of a class of random sums","year":2000,"lang":"en","type":"article","venue":"Journal of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Class (philosophy); Binomial (polynomial); Combinatorics; Property (philosophy); Identity (music); Renewal theory; Poisson distribution; Negative binomial distribution; Geometric distribution; Poisson process; Discrete mathematics; Statistics; Probability distribution","score_opus":0.016864405626746095,"score_gpt":0.2406202301730825,"score_spread":0.2237558245463364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252321446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17541866,0.00011395699,0.80284834,0.0004203661,0.00010251371,0.0003933908,0.0000021130325,0.00001325528,0.02068742],"genre_scores_gemma":[0.57384086,0.000021366533,0.4259712,0.000054815107,0.000039061884,0.0000034292273,8.717223e-8,0.000004387214,0.00006479767],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981465,0.00015906752,0.00090684835,0.00020480169,0.00040391687,0.00017888908],"domain_scores_gemma":[0.9984422,0.00014101059,0.00053142506,0.0005212893,0.00025915424,0.00010493006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026590393,0.00012737997,0.00057925197,0.0000632728,0.000029893376,0.000019715533,0.00075279793,0.00008949533,0.000073362906],"category_scores_gemma":[0.00004982676,0.000072685914,0.00021667684,0.00028398618,0.00013954507,0.00019469667,0.00006437126,0.00024553598,0.0000020214136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015768209,0.0007495042,0.0002575899,0.00026261597,0.000090384376,0.000005409555,0.001725457,0.0005081634,0.014357064,0.05540089,0.0004589362,0.92460716],"study_design_scores_gemma":[0.005875901,0.00075913063,0.0019855509,0.00014195543,0.000077851466,0.00008703298,0.000018465584,0.008593907,0.08883996,0.88404125,0.009231863,0.000347149],"about_ca_topic_score_codex":0.000007991759,"about_ca_topic_score_gemma":0.0000020253772,"teacher_disagreement_score":0.92426,"about_ca_system_score_codex":0.000034752957,"about_ca_system_score_gemma":0.00021315468,"threshold_uncertainty_score":0.29640454},"labels":[],"label_agreement":null},{"id":"W4252376696","doi":"10.1515/iupac.79.1556","title":"Log-Normal Distribution","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Glossary; Chemical nomenclature; Computer science; Hazard; Toxicology; Chemistry; Biology; Philosophy; Linguistics","score_opus":0.013454040844343509,"score_gpt":0.38230348262027075,"score_spread":0.36884944177592727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252376696","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.5416587e-7,0.00025118745,0.49656516,0.00060912885,0.00076175114,0.00009759721,0.50161743,0.00007179677,0.000025400816],"genre_scores_gemma":[0.0000033190909,0.00044677878,0.021254241,0.00037775855,0.00091034203,0.000011685984,0.97666746,0.00001716914,0.00031125025],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969601,0.0002221424,0.0004623182,0.0007618765,0.0010060857,0.000587465],"domain_scores_gemma":[0.997382,0.00010409361,0.00027633875,0.0015896293,0.00040431856,0.00024366226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010699099,0.00044495056,0.00055967114,0.00012077548,0.00015202725,0.00018816385,0.0016206715,0.00046665387,0.0003319251],"category_scores_gemma":[0.00028007428,0.00032279093,0.00021291937,0.00028027588,0.00010703698,0.00034231707,0.0006002603,0.00052124594,0.0000041671874],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017971704,0.00007637114,8.890643e-7,0.000039894763,0.000030177906,0.00005790489,0.0000046412097,2.123689e-7,0.0000034239854,0.0023834412,0.9217488,0.07563628],"study_design_scores_gemma":[0.00045238688,0.00012039299,0.00001338324,0.00016559083,0.000034961504,0.000040883504,5.615405e-7,0.00011420561,0.000032480555,0.007125227,0.99145824,0.00044166524],"about_ca_topic_score_codex":0.000052419466,"about_ca_topic_score_gemma":0.00007070137,"teacher_disagreement_score":0.47531092,"about_ca_system_score_codex":0.00033749972,"about_ca_system_score_gemma":0.0007479292,"threshold_uncertainty_score":0.9999224},"labels":[],"label_agreement":null},{"id":"W4253133166","doi":"10.1515/iupac.79.1657","title":"Multistage Cluster Sampling","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Glossary; Chemical nomenclature; Computer science; Hazard; Toxicology; Chemistry; Biology; Philosophy; Linguistics","score_opus":0.02603571518015014,"score_gpt":0.4231488185778554,"score_spread":0.3971131033977053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253133166","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.4303734e-7,0.00030487415,0.49701363,0.0005772033,0.00089438766,0.00016206043,0.5009252,0.00008703896,0.000035084777],"genre_scores_gemma":[9.282433e-7,0.00034965802,0.2218538,0.0011416359,0.00091251347,0.000013827251,0.7750914,0.000033692308,0.0006025458],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99633616,0.00024982696,0.0005947771,0.001044153,0.0010932009,0.00068190804],"domain_scores_gemma":[0.9965617,0.00027556284,0.00033113436,0.0021524958,0.0003950388,0.00028403793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013783465,0.00057177554,0.0007406988,0.00027190018,0.00017399556,0.0002935994,0.0020558613,0.0005086017,0.000363354],"category_scores_gemma":[0.00038767813,0.0004141813,0.00025785045,0.00025275137,0.00010125686,0.00032248258,0.00089166645,0.0006501262,0.000004653671],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020246502,0.00007093919,3.4759674e-7,0.00007682667,0.000041241885,0.000050581446,0.000019034658,8.867723e-7,0.000009613958,0.00070240046,0.9183881,0.08061978],"study_design_scores_gemma":[0.0007562893,0.00008944793,0.0000037828859,0.00032973677,0.00003423767,0.000031928637,0.0000011639127,0.00033125843,0.000018982983,0.005098991,0.99272436,0.00057984964],"about_ca_topic_score_codex":0.00005587514,"about_ca_topic_score_gemma":0.00016253108,"teacher_disagreement_score":0.27515984,"about_ca_system_score_codex":0.00029400995,"about_ca_system_score_gemma":0.0006246484,"threshold_uncertainty_score":0.999831},"labels":[],"label_agreement":null},{"id":"W4254482864","doi":"10.1016/s0169-7161(09)00230-2","title":"Empirical Likelihood Methods","year":2009,"lang":"en","type":"book-chapter","venue":"Handbook of statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.044453926400318935,"score_gpt":0.35189998708337017,"score_spread":0.30744606068305125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254482864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0613622e-8,0.002785161,0.74082476,0.0000870364,0.00026417625,0.00014668675,0.000119419936,0.000061389466,0.25571138],"genre_scores_gemma":[6.58237e-7,0.0010547788,0.872342,0.00053061405,0.00012840045,0.000002679132,0.000019313959,0.00003571633,0.12588584],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978804,0.00011846028,0.0006472164,0.00057775836,0.00043478847,0.00034139515],"domain_scores_gemma":[0.99762607,0.00052794255,0.0004267784,0.0009401187,0.00026570685,0.00021337967],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000654455,0.00041402003,0.00079513836,0.00018755869,0.00006550954,0.00006429044,0.00088702753,0.00041351037,0.00012473887],"category_scores_gemma":[0.00007602485,0.00038323452,0.00017184833,0.000045406137,0.00013146426,0.00008639355,0.00022912784,0.0004783026,0.000047034628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031512584,0.000012133575,2.5209647e-7,0.000031736326,0.000027458596,0.000029069764,0.00009899926,2.5335464e-7,0.000041020572,0.46280375,0.014262162,0.52269],"study_design_scores_gemma":[0.00018395012,0.00021117849,0.0000059328895,0.00029956087,0.000070342925,0.000022420354,3.278492e-7,0.0016582285,0.00072663475,0.8285706,0.16789193,0.00035886932],"about_ca_topic_score_codex":0.0000024034075,"about_ca_topic_score_gemma":0.000002239581,"teacher_disagreement_score":0.5223311,"about_ca_system_score_codex":0.000047156747,"about_ca_system_score_gemma":0.00028070924,"threshold_uncertainty_score":0.99986196},"labels":[],"label_agreement":null},{"id":"W4255225174","doi":"10.1109/icpr.2004.1334107","title":"A powerful finite mixture model based on the generalized Dirichlet distribution: unsupervised learning and applications","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Mixture model; Dirichlet distribution; Expectation–maximization algorithm; Generalization; Generalized Dirichlet distribution; Applied mathematics; Computer science; Mathematics; Artificial intelligence; Pattern recognition (psychology); Gaussian; Maximization; Algorithm; Maximum likelihood; Mathematical optimization; Dirichlet series; Statistics; Mathematical analysis","score_opus":0.03131567034985834,"score_gpt":0.27042080368891047,"score_spread":0.23910513333905214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255225174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007844412,0.000053414067,0.96872056,0.013801281,0.00015853958,0.00056546874,0.00018534141,0.00008695577,0.008584003],"genre_scores_gemma":[0.97558534,0.00007048572,0.020087475,0.0033324235,0.0001513692,0.00019341495,0.00007491143,0.000023918794,0.00048063524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808836,0.000048843307,0.0004002499,0.0005560963,0.00062648073,0.00027998484],"domain_scores_gemma":[0.99828285,0.00011771971,0.00035101178,0.00024453975,0.0008997703,0.000104086175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050379906,0.00029593564,0.00022708908,0.00012296706,0.00030843372,0.00028823732,0.001144705,0.00013134176,0.00008737666],"category_scores_gemma":[0.00018804075,0.0001994311,0.00014150358,0.0003627777,0.00014696851,0.00028853476,0.00015110054,0.00047766283,0.000028869279],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027076472,0.0011328643,0.0031631533,0.00018579944,0.00026539934,0.0000042495108,0.0013906481,0.008263987,0.0045192125,0.81898427,0.0064611053,0.15535852],"study_design_scores_gemma":[0.0024806862,0.0002625077,0.0009926644,0.0008092863,0.000067075496,0.000026164853,0.0000885765,0.59256005,0.015041919,0.38472512,0.0022290524,0.000716933],"about_ca_topic_score_codex":0.000019410085,"about_ca_topic_score_gemma":0.0000032801568,"teacher_disagreement_score":0.96774095,"about_ca_system_score_codex":0.00011134114,"about_ca_system_score_gemma":0.00013795047,"threshold_uncertainty_score":0.81325644},"labels":[],"label_agreement":null},{"id":"W4255299861","doi":"10.22215/etd/2014-10561","title":"Optimal Component Selection in High Dimensions","year":2014,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Component (thermodynamics); Selection (genetic algorithm); Dimension (graph theory); High dimensional; Construct (python library); Computer science; Point (geometry); Model selection; Feature selection; Clustering high-dimensional data; Mathematical optimization; Data mining; Mathematics; Artificial intelligence; Cluster analysis","score_opus":0.01053952983960467,"score_gpt":0.26974168260301656,"score_spread":0.2592021527634119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255299861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03560173,0.000054998094,0.9537482,0.00012230322,0.0008036146,0.00017038069,4.790686e-7,0.00012355208,0.009374688],"genre_scores_gemma":[0.1638807,0.000021996828,0.82748884,0.00017399227,0.00008138958,0.000029623317,0.000067265675,0.00001764613,0.008238548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986645,0.00014636014,0.00026910636,0.00047641166,0.00020714047,0.00023646608],"domain_scores_gemma":[0.9994454,0.00006277957,0.00010289902,0.00024852788,0.0000680535,0.000072390096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031937697,0.00020089769,0.00028947706,0.00024436484,0.000068066096,0.000078833655,0.00040628298,0.0002421927,0.000032460695],"category_scores_gemma":[0.000014569054,0.00017689893,0.000070386304,0.0002962873,0.0000062239405,0.00013603123,0.000043481425,0.00032216773,0.000040065643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025015797,0.00015581258,0.000044433767,0.00006337581,0.000026035737,0.000010947563,0.0006482604,0.0006630439,0.0053913817,0.9015529,0.003900771,0.087518014],"study_design_scores_gemma":[0.0021247151,0.0005377699,0.041058745,0.0005985377,0.00008215459,0.000047234244,0.0000698991,0.7751941,0.03030143,0.1374501,0.0098476065,0.0026877145],"about_ca_topic_score_codex":0.0003197082,"about_ca_topic_score_gemma":0.00045705153,"teacher_disagreement_score":0.77453107,"about_ca_system_score_codex":0.000051374765,"about_ca_system_score_gemma":0.00007440581,"threshold_uncertainty_score":0.7213729},"labels":[],"label_agreement":null},{"id":"W4255473311","doi":"10.22215/etd/2008-06349","title":"Estimation in mixture models","year":2008,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Humanities; Computer science; Art","score_opus":0.018979137302064224,"score_gpt":0.2859259378335966,"score_spread":0.26694680053153236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255473311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047246955,0.00041986577,0.88374525,0.00010047651,0.0004781406,0.00018449295,8.4326854e-7,0.00011638321,0.11448206],"genre_scores_gemma":[0.022338416,0.0002101821,0.9543555,0.00021074504,0.000033446406,0.00003665655,0.000116112664,0.000020341202,0.022678602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866587,0.00007314753,0.00029296236,0.00048003157,0.00026233436,0.00022562637],"domain_scores_gemma":[0.999243,0.000039113904,0.000108252185,0.0004913841,0.00005727299,0.000060981223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017593736,0.00022949188,0.00028256205,0.00026980086,0.000049868187,0.00007238482,0.0006413851,0.00038331462,0.000012180773],"category_scores_gemma":[0.000016881895,0.00020424846,0.00008478683,0.0003630431,0.0000069902535,0.0005520967,0.00003119987,0.00034018978,0.000022251434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007700106,0.000050332048,0.000001488437,0.000057572466,0.000009010381,0.000040434406,0.0027863046,0.0012534169,0.00007318181,0.46568796,0.0037397868,0.5262928],"study_design_scores_gemma":[0.00012676005,0.0000131544375,0.000083645136,0.00006356656,0.0000032533908,0.000010868301,0.000008680161,0.70745474,0.0007212969,0.29108903,0.00018087756,0.00024413623],"about_ca_topic_score_codex":0.00006466959,"about_ca_topic_score_gemma":0.00017552887,"teacher_disagreement_score":0.7062013,"about_ca_system_score_codex":0.00004423061,"about_ca_system_score_gemma":0.00015738652,"threshold_uncertainty_score":0.832901},"labels":[],"label_agreement":null},{"id":"W4256484418","doi":"10.1137/s0040585x97979615","title":"On Consistency of Bayes Procedures","year":2003,"lang":"en","type":"article","venue":"Theory of Probability and Its Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Prior probability; Bayes' theorem; Consistency (knowledge bases); Invariant (physics); Sigma; Statistical model; Applied mathematics; Class (philosophy); Bayes error rate; Strong consistency; Statistics; Pure mathematics; Combinatorics; Discrete mathematics; Bayes classifier; Bayesian probability; Computer science; Artificial intelligence; Physics; Mathematical physics","score_opus":0.023490406857678076,"score_gpt":0.2652478351814662,"score_spread":0.24175742832378813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256484418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011590695,0.0005095091,0.973001,0.00016790969,0.000011175231,0.00045507238,0.000005871441,0.000023641727,0.014235117],"genre_scores_gemma":[0.7699227,0.000026153652,0.22984926,0.000054177075,0.0000031424267,0.000069399684,3.2208132e-7,0.0000023230953,0.000072524614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99923307,0.00017281208,0.00020485205,0.00022526392,0.00007972066,0.00008428977],"domain_scores_gemma":[0.99899435,0.00036867874,0.00009340684,0.00039643957,0.00010488954,0.000042235275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008687255,0.000069506976,0.00014315729,0.00003396706,0.00006709747,0.000007313541,0.00021527245,0.00003997359,0.000014677648],"category_scores_gemma":[0.0002868476,0.000056259352,0.000035359586,0.0001609289,0.00014959628,0.00007456128,0.000031564534,0.000052836214,0.0000017411703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047957624,0.00013340046,0.00001139837,0.00011735522,0.0000055712053,1.8016065e-8,0.00024188333,0.000002534618,0.0015528699,0.98055553,0.000011209587,0.017363416],"study_design_scores_gemma":[0.00008220106,0.00005917421,0.00019026805,0.0000162317,0.00000644925,0.000002155191,0.000010225565,0.000103264225,0.017449053,0.9817942,0.00023186271,0.000054955246],"about_ca_topic_score_codex":6.8005903e-7,"about_ca_topic_score_gemma":9.273762e-7,"teacher_disagreement_score":0.758332,"about_ca_system_score_codex":0.0000046795367,"about_ca_system_score_gemma":0.00007798536,"threshold_uncertainty_score":0.22941898},"labels":[],"label_agreement":null},{"id":"W4280515996","doi":"10.1016/j.eswa.2022.117516","title":"Multivariate bounded support asymmetric generalized Gaussian mixture model with model selection using minimum message length","year":2022,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Bounded function; Selection (genetic algorithm); Computer science; Gaussian; Model selection; Mixture model; Minimum description length; Multivariate normal distribution; Mathematical optimization; Mathematics; Artificial intelligence; Statistics; Algorithm; Machine learning","score_opus":0.027425922024945582,"score_gpt":0.28789038445424375,"score_spread":0.26046446242929816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280515996","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065106445,0.0003538521,0.9942934,0.00042269123,0.000095406096,0.0017061415,0.000035854253,0.00035949628,0.0020821153],"genre_scores_gemma":[0.34041348,0.000007236959,0.6547323,0.0002944737,0.00009376997,0.00293517,0.000027750133,0.000055047687,0.0014407837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691355,0.00030097328,0.00047207033,0.0010300135,0.0007243617,0.0005590537],"domain_scores_gemma":[0.9980613,0.00005133562,0.00036633655,0.0010823681,0.000191251,0.00024742508],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005845143,0.0003913454,0.00045920262,0.0004035832,0.001278352,0.00028140345,0.0009170464,0.00011624879,0.000011113013],"category_scores_gemma":[0.0000051147445,0.00031170505,0.000086758846,0.0019495942,0.000053310767,0.00045296026,0.00021308968,0.00037818446,0.0000046407263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010636229,0.00048087732,0.000040446394,0.00005918689,0.00019641894,0.00001289962,0.0039942423,0.5690683,0.018271465,0.40122715,0.0028517812,0.0036908537],"study_design_scores_gemma":[0.00095546414,0.000111788904,0.000003986191,0.00001474166,0.000033813936,0.00024163483,0.00008823995,0.9914192,0.0005244967,0.002286268,0.0038432602,0.00047711778],"about_ca_topic_score_codex":0.00034666824,"about_ca_topic_score_gemma":0.000016669295,"teacher_disagreement_score":0.42235085,"about_ca_system_score_codex":0.00035947506,"about_ca_system_score_gemma":0.0006225423,"threshold_uncertainty_score":0.9999335},"labels":[],"label_agreement":null},{"id":"W4281387922","doi":"10.1007/s10463-022-00835-5","title":"Semiparametric modelling of two-component mixtures with stochastic dominance","year":2022,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Mathematics; Estimator; Semiparametric regression; Statistics; Applied mathematics; Asymptotic distribution; Monte Carlo method; Econometrics","score_opus":0.06664828147712305,"score_gpt":0.31125365926413384,"score_spread":0.2446053777870108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281387922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01796181,0.00019511832,0.9806617,0.0002373618,0.00016806778,0.00025692608,0.00008829563,0.000012373814,0.00041836538],"genre_scores_gemma":[0.47981855,0.000005080268,0.5200944,0.00004323922,0.0000056253316,0.000009060177,7.672148e-7,0.00000598143,0.000017272176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981889,0.00010200893,0.0005924167,0.0002190304,0.0006871198,0.0002105321],"domain_scores_gemma":[0.9979492,0.0005561328,0.00054968026,0.00069947884,0.00018416539,0.000061345054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007150962,0.00015626599,0.0004887367,0.00012234178,0.00011369357,0.000013338491,0.0011273194,0.000026665119,0.000008759255],"category_scores_gemma":[0.00017944661,0.00010445099,0.00009804089,0.0006399078,0.00031357957,0.00012220241,0.00044187187,0.00019626631,4.3163521e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024115341,0.00028088992,0.0000016297909,0.00021444607,0.000042821048,0.0000041096473,0.00049410766,0.21257544,0.00051680394,0.78243136,0.00014321806,0.0032710868],"study_design_scores_gemma":[0.0002530006,0.0001633796,0.000008326003,0.00013753118,0.00003307568,0.000025822741,0.000011075066,0.48769027,0.007115446,0.5044232,0.000026512407,0.00011236266],"about_ca_topic_score_codex":0.000049759525,"about_ca_topic_score_gemma":0.0000012430011,"teacher_disagreement_score":0.46185675,"about_ca_system_score_codex":0.000012228892,"about_ca_system_score_gemma":0.000120006975,"threshold_uncertainty_score":0.42593879},"labels":[],"label_agreement":null},{"id":"W4281985242","doi":"10.1016/j.jclinepi.2022.05.008","title":"Part I: A friendly introduction to latent class analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Women's College Hospital; University of Toronto","funders":"","keywords":"Latent class model; Class (philosophy); Probabilistic logic; Set (abstract data type); Computer science; Population; Data science; Data mining; Risk analysis (engineering); Machine learning; Artificial intelligence; Medicine; Environmental health","score_opus":0.18078557491138483,"score_gpt":0.47009702053056723,"score_spread":0.28931144561918243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281985242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010168134,0.00015428236,0.8813449,0.10422521,0.003892441,0.00005611425,0.0000019138856,0.000014364111,0.00014259979],"genre_scores_gemma":[0.108506314,0.00010844736,0.87132746,0.01591535,0.0037390983,0.000009184339,0.0000015538767,0.000007722649,0.00038487674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9860655,0.00953291,0.003335896,0.00044774957,0.00027830538,0.00033961606],"domain_scores_gemma":[0.99009985,0.006671562,0.0020021354,0.0006107591,0.00020717962,0.00040851993],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047802735,0.00011756557,0.0017925197,0.00034702115,0.00012301195,0.00001365312,0.0010035847,0.00011108947,0.00016854872],"category_scores_gemma":[0.01522729,0.00008954722,0.0010512273,0.0010203276,0.00005581651,0.00014402319,0.00043565052,0.0010934898,0.000011491263],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002930726,0.0004450406,0.036106475,0.0000057007705,0.0012401452,0.00009626029,0.00018529748,0.031670947,0.00003443724,0.3293736,0.24266784,0.3578812],"study_design_scores_gemma":[0.0006575536,0.002981948,0.048642818,0.000004724603,0.00036122213,0.00025575198,0.0000149958805,0.05156547,0.000009443474,0.14292477,0.7523509,0.00023039451],"about_ca_topic_score_codex":0.000008368337,"about_ca_topic_score_gemma":0.000003593747,"teacher_disagreement_score":0.5096831,"about_ca_system_score_codex":0.000056110297,"about_ca_system_score_gemma":0.0001482636,"threshold_uncertainty_score":0.99306786},"labels":[],"label_agreement":null},{"id":"W4285129940","doi":"10.1007/978-3-030-99142-5_10","title":"Multivariate Beta-Based Hierarchical Dirichlet Process Hidden Markov Models in Medical Applications","year":2022,"lang":"en","type":"book-chapter","venue":"Unsupervised and semi-supervised learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hidden Markov model; Hierarchical Dirichlet process; Dirichlet process; Computer science; Dirichlet distribution; Multivariate statistics; Parametric model; Inference; Nonparametric statistics; Artificial intelligence; Parametric statistics; Machine learning; Pattern recognition (psychology); Data mining; Mathematics; Latent Dirichlet allocation; Econometrics; Topic model; Statistics","score_opus":0.019992021211866096,"score_gpt":0.2663316830322359,"score_spread":0.24633966182036982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285129940","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023592688,0.0025274013,0.8628119,0.002506951,0.00016519362,0.0012688166,0.000043074142,0.00048391378,0.12995678],"genre_scores_gemma":[0.149094,0.0055920845,0.7100778,0.013106432,0.002100733,0.003970977,0.0019990983,0.0013971602,0.11266169],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934085,0.0006507889,0.0011626339,0.0021204483,0.001695472,0.0009621311],"domain_scores_gemma":[0.9966876,0.000918158,0.00027935716,0.001166061,0.00017849151,0.0007703695],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019390772,0.0009949275,0.0013269293,0.0008655613,0.0006734896,0.00029238407,0.0022433416,0.0010039532,0.0013391126],"category_scores_gemma":[0.00010430157,0.0009785835,0.00036154754,0.00046343394,0.00023762227,0.0005998996,0.0009710931,0.004178437,0.000022552367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008094393,0.00019076603,0.000121930854,0.0004707076,0.00011697015,0.00030453777,0.0026211669,0.0012417779,0.000055633227,0.4457478,0.00011315652,0.54893464],"study_design_scores_gemma":[0.0023699973,0.00018097162,0.000042687756,0.00044368443,0.00008228617,0.000060713835,0.00004663223,0.85020244,0.000014795334,0.09493122,0.050190154,0.0014344316],"about_ca_topic_score_codex":0.0000684831,"about_ca_topic_score_gemma":0.000016874303,"teacher_disagreement_score":0.84896064,"about_ca_system_score_codex":0.00016772014,"about_ca_system_score_gemma":0.0008655541,"threshold_uncertainty_score":0.9995738},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.2969045554887873,"score_gpt":0.4814858611530845,"score_spread":0.1845813056642972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285391282","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063332487,0.00059720676,0.9871492,0.0026497687,0.001873902,0.0004250135,0.000008317417,0.00028454477,0.0006788381],"genre_scores_gemma":[0.0689428,0.000041481715,0.9290143,0.0009164156,0.00034297904,0.00042851528,0.0000087825,0.000038418933,0.0002662965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9560808,0.03689243,0.00067014026,0.0012915835,0.0035296872,0.0015353413],"domain_scores_gemma":[0.97142154,0.026022242,0.00010166266,0.0013134386,0.0002326207,0.0009085155],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06369945,0.00028009573,0.000701327,0.00065796764,0.0009644847,0.00010108361,0.0034734674,0.00028497892,0.0009789652],"category_scores_gemma":[0.019445995,0.00019071814,0.0002399442,0.0013706571,0.00046963146,0.00018552352,0.0016127077,0.0025888612,0.00001924991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047970522,0.0006103415,0.00035912337,0.00032818966,0.00006985704,0.0009321039,0.0019797457,0.009021951,0.0032729553,0.4216443,0.0017761455,0.5595256],"study_design_scores_gemma":[0.00084034126,0.0004450204,0.00006278621,0.000023111274,0.0000071517907,0.00007309267,0.00009546171,0.84223056,0.00046383214,0.15191922,0.0035735,0.00026593084],"about_ca_topic_score_codex":0.00050671183,"about_ca_topic_score_gemma":0.000342809,"teacher_disagreement_score":0.8332086,"about_ca_system_score_codex":0.00025086175,"about_ca_system_score_gemma":0.0026931062,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W4285601419","doi":"10.24963/ijcai.2022/738","title":"Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent (Extended Abstract)","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of British Columbia","funders":"","keywords":"Bregman divergence; Divergence (linguistics); Kullback–Leibler divergence; Applied mathematics; Mathematics; Exponential family; Gradient descent; Gaussian; Convergence (economics); Invariant (physics); Exponential function; Probabilistic logic; Parametrization (atmospheric modeling); Expectation–maximization algorithm; Mathematical optimization; Computer science; Mathematical analysis; Artificial neural network; Artificial intelligence; Physics; Statistics; Maximum likelihood","score_opus":0.060292365951161574,"score_gpt":0.28296751202799825,"score_spread":0.22267514607683667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285601419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16028774,0.000029042436,0.8333516,0.0022161948,0.0022961926,0.0009441171,0.00007860959,0.000045136196,0.00075138715],"genre_scores_gemma":[0.9579263,0.000082811755,0.041425873,0.0001890548,0.00004492021,0.00021126495,0.0000041975004,0.000016886794,0.00009871841],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99638003,0.00004099526,0.0012304104,0.0008024734,0.001094494,0.00045161045],"domain_scores_gemma":[0.99739313,0.00020202884,0.0009914219,0.00039342427,0.0009160064,0.0001039839],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013719088,0.00033529513,0.00054123445,0.0005204214,0.0002981517,0.000122412,0.0033077195,0.000095076844,0.00023187541],"category_scores_gemma":[0.00032552143,0.00029857183,0.00035897712,0.0010750786,0.00026858013,0.00047214673,0.0010320562,0.0004816988,0.00000871383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004654154,0.0008653856,0.0012671191,0.00017210627,0.00016809597,0.0000039228507,0.0048668818,0.0012391458,0.0818725,0.8920283,0.00008321132,0.016967941],"study_design_scores_gemma":[0.00022822579,0.0004465786,0.011966397,0.00032344964,0.00006343002,0.0000145609965,0.00096995605,0.33396596,0.34655952,0.3048327,0.00008970201,0.0005395171],"about_ca_topic_score_codex":0.00030049897,"about_ca_topic_score_gemma":0.00012837395,"teacher_disagreement_score":0.79763854,"about_ca_system_score_codex":0.00018892947,"about_ca_system_score_gemma":0.00018120847,"threshold_uncertainty_score":0.99994665},"labels":[],"label_agreement":null},{"id":"W4287328882","doi":"10.48550/arxiv.2102.06851","title":"Robust Model-Based Clustering","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Defense; Universidad de Buenos Aires","keywords":"Estimator; Cluster analysis; Computer science; Multivariate statistics; Set (abstract data type); Robust statistics; Data mining; Monte Carlo method; Class (philosophy); Algorithm; Mathematics; Artificial intelligence; Statistics; Machine learning","score_opus":0.12604933352546693,"score_gpt":0.20066070225209423,"score_spread":0.0746113687266273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287328882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008396638,0.00009367532,0.9861414,0.00014312602,0.00060765096,0.00017974392,0.000006093152,0.00028593856,0.004145762],"genre_scores_gemma":[0.5798534,0.00003547497,0.4189464,0.00025227264,0.00004189308,7.226158e-7,0.000008151127,0.000017011893,0.00084468507],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976527,0.00022028497,0.0001957615,0.0014209796,0.00010064776,0.00040958906],"domain_scores_gemma":[0.9975524,0.000068631794,0.00017586353,0.0018078724,0.00017527674,0.00021993247],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034261183,0.00035781163,0.0004058491,0.00021180326,0.00014552027,0.0002729979,0.001953398,0.00038289675,0.000019893767],"category_scores_gemma":[0.000021536443,0.00042728096,0.00032373224,0.00046344593,0.00006282783,0.00034169052,0.002488244,0.0006983986,0.000012134434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000665072,0.000046875957,0.00003551173,0.00007719619,0.000030408964,0.00033823567,0.000110090186,0.9341446,0.00003913934,0.0627786,0.00008365545,0.0023090085],"study_design_scores_gemma":[0.00028549862,0.000013658951,0.0000249767,0.000119716075,0.000040953902,0.0000036993617,0.000009447982,0.9628224,0.00019855102,0.035991598,0.0000427255,0.00044676938],"about_ca_topic_score_codex":0.000051189523,"about_ca_topic_score_gemma":0.000047760142,"teacher_disagreement_score":0.57145673,"about_ca_system_score_codex":0.00017832039,"about_ca_system_score_gemma":0.0005056218,"threshold_uncertainty_score":0.9998179},"labels":[],"label_agreement":null},{"id":"W4287775987","doi":"10.48550/arxiv.2005.11641","title":"Estimating the Number of Components in Finite Mixture Models via the Group-Sort-Fuse Procedure","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fuse (electrical); Univariate; Mixture model; sort; Mathematics; Convergence (economics); Applied mathematics; Mixing (physics); Finite set; Component (thermodynamics); Range (aeronautics); Measure (data warehouse); Function (biology); Upper and lower bounds; Multivariate statistics; Mathematical optimization; Algorithm; Computer science; Statistics; Data mining","score_opus":0.09352276067981784,"score_gpt":0.22210195969244953,"score_spread":0.1285791990126317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287775987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05371052,0.00006239491,0.9432286,0.00081036927,0.00034232318,0.0005345688,0.000014003817,0.000087963854,0.0012092487],"genre_scores_gemma":[0.8990642,0.000029516497,0.10028578,0.0004013581,0.00007227002,0.0000033961678,0.000010190481,0.0000216968,0.00011161982],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976307,0.0004863885,0.000354367,0.0009892975,0.00017951989,0.00035972396],"domain_scores_gemma":[0.997555,0.00034951363,0.00044325678,0.0014246327,0.0001159374,0.0001116701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006120209,0.00037882934,0.0004697405,0.00009372727,0.00017660424,0.00010054902,0.0033481636,0.00030267972,0.000008821662],"category_scores_gemma":[0.0000611659,0.00026927906,0.00025209493,0.00084084435,0.00016878331,0.00034994222,0.002475082,0.0012690587,0.000012135126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004505611,0.0001447075,0.0016193955,0.0002670553,0.00011161059,0.00016974234,0.003209503,0.5739516,0.00011809431,0.4180498,0.00017354828,0.0021398584],"study_design_scores_gemma":[0.00020257218,0.000008684768,0.00043210693,0.00010127941,0.00003286316,0.000006148908,0.0000149441075,0.62691844,0.000019767314,0.372061,0.00002047404,0.00018168573],"about_ca_topic_score_codex":0.00024141073,"about_ca_topic_score_gemma":0.000041358457,"teacher_disagreement_score":0.84535366,"about_ca_system_score_codex":0.00007314101,"about_ca_system_score_gemma":0.00013013827,"threshold_uncertainty_score":0.9999759},"labels":[],"label_agreement":null},{"id":"W4287883007","doi":"10.1109/isie51582.2022.9831530","title":"A Hierarchical Pitman-Yor mixture of Scaled Dirichlet Distributions","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 31st International Symposium on Industrial Electronics (ISIE)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Robustness (evolution); Computer science; Dirichlet distribution; Inference; Cluster analysis; Latent Dirichlet allocation; Dirichlet process; Artificial intelligence; Flexibility (engineering); Hierarchical clustering; Hierarchical Dirichlet process; Gaussian; Machine learning; Data mining; Topic model; Mathematics; Statistics","score_opus":0.019243793984783892,"score_gpt":0.2698742535938535,"score_spread":0.2506304596090696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287883007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03278422,0.00023986367,0.9302598,0.020628946,0.006347348,0.0007683842,0.00078198884,0.0002043472,0.00798505],"genre_scores_gemma":[0.98304373,0.00014335854,0.0098362565,0.0013083443,0.001574078,0.0003938564,0.00037539992,0.00006043855,0.0032645387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956889,0.0006239975,0.0007383966,0.00083501864,0.0014417538,0.00067189854],"domain_scores_gemma":[0.9980487,0.000416733,0.00039315756,0.0007562426,0.00018001528,0.00020513401],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001228442,0.00034149212,0.00044194912,0.0002850635,0.00046737937,0.0001456833,0.002546446,0.000229171,0.00037913985],"category_scores_gemma":[0.00014294968,0.0003459415,0.00035236264,0.0010398414,0.00008000107,0.00025191688,0.00061392324,0.0019628957,0.000016725851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040660563,0.0009230957,0.00013328146,0.000006488249,0.00027601453,0.00003957932,0.0002932227,0.0013470337,0.02716276,0.9143461,0.03557772,0.019488111],"study_design_scores_gemma":[0.008934397,0.0044386294,0.00019936205,0.00009983504,0.00017795643,0.00040801495,0.00005015548,0.09621053,0.08210206,0.12383622,0.6815548,0.00198805],"about_ca_topic_score_codex":0.000043069973,"about_ca_topic_score_gemma":0.000009107401,"teacher_disagreement_score":0.9502595,"about_ca_system_score_codex":0.0008947408,"about_ca_system_score_gemma":0.000548638,"threshold_uncertainty_score":0.99989927},"labels":[],"label_agreement":null},{"id":"W4288855572","doi":"10.1007/s11222-021-10076-w","title":"Polya tree-based nearest neighborhood regression","year":2022,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Covariate; Kernel density estimation; Estimator; Kernel regression; Statistics; Nonparametric regression; Variable kernel density estimation; Kernel (algebra); Polynomial regression; Parametric statistics; Regression analysis; Kernel method; Computer science; Artificial intelligence; Support vector machine","score_opus":0.012577982772324614,"score_gpt":0.26303328768615136,"score_spread":0.2504553049138267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288855572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097309053,0.00023554292,0.99655807,0.00039943933,0.0003527281,0.00007335439,0.000029147639,0.00007305715,0.0013055794],"genre_scores_gemma":[0.4531398,0.0000020139496,0.5463084,0.0004413183,0.00003797813,0.000002304923,0.000006420712,0.0000067459864,0.00005502629],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988449,0.00018015946,0.00017515209,0.00032452474,0.0002346565,0.00024056873],"domain_scores_gemma":[0.9992813,0.00022496916,0.00010011334,0.00026557583,0.00003333252,0.00009471684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000376067,0.000117887976,0.00014468213,0.00006511728,0.0006173107,0.00013942675,0.0003406362,0.000020262321,0.00001676318],"category_scores_gemma":[0.000027345892,0.000107951666,0.000024911713,0.00020819918,0.000027024535,0.00004664647,0.00046400324,0.00020532665,0.0000013084752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035642922,0.000026263599,0.00024007005,0.000009588348,0.0000038321373,0.000042664942,0.00023274767,0.00016428514,0.00008440178,0.38722607,0.00091824634,0.6110483],"study_design_scores_gemma":[0.00032027782,0.00013162744,0.0011770399,0.00001412046,0.000005179329,0.000018512417,0.000019189918,0.9323004,0.000063636195,0.06414959,0.0016380068,0.00016244488],"about_ca_topic_score_codex":0.000022278427,"about_ca_topic_score_gemma":0.0000021022986,"teacher_disagreement_score":0.9321361,"about_ca_system_score_codex":0.000022718788,"about_ca_system_score_gemma":0.00007850015,"threshold_uncertainty_score":0.47479174},"labels":[],"label_agreement":null},{"id":"W4289256720","doi":"10.1002/9781118445112.stat01250","title":"Discrete Multivariate Distributions","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Notation; Multivariate analysis; Mathematics; Computer science; Statistics; Econometrics; Arithmetic","score_opus":0.030852237473395164,"score_gpt":0.3263563983540235,"score_spread":0.29550416088062836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289256720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0944542e-7,0.0004914941,0.910561,0.00023097926,0.00077076355,0.00037154197,0.035348244,0.000572551,0.051653206],"genre_scores_gemma":[0.000067334324,0.0008773714,0.8287907,0.00019920552,0.0003541524,0.000034063516,0.005272849,0.00029057104,0.16411376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963378,0.0003867532,0.00065735995,0.0011926001,0.0006094413,0.0008160682],"domain_scores_gemma":[0.9966752,0.0002918957,0.0006232717,0.001779371,0.00019877766,0.00043148373],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033050746,0.00074037316,0.00087951834,0.000302843,0.00016621516,0.0002451579,0.0017385519,0.00049180427,0.00071399764],"category_scores_gemma":[0.00026576885,0.0006366563,0.00010298253,0.00039242257,0.00021214409,0.00012438893,0.0005433952,0.00082158606,0.00034460676],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003961254,0.000098205644,0.0000031932482,0.00007486391,0.000062613406,0.000028903254,0.000033268938,0.0000017168637,0.000019873929,0.55490416,0.35941166,0.08535756],"study_design_scores_gemma":[0.00055804336,0.0001486133,0.00008484573,0.00048216057,0.00008335158,0.000012527333,0.0000031703967,0.023415307,0.000010468862,0.1420846,0.8321236,0.000993368],"about_ca_topic_score_codex":0.00045259518,"about_ca_topic_score_gemma":0.0005495291,"teacher_disagreement_score":0.4727119,"about_ca_system_score_codex":0.000095918855,"about_ca_system_score_gemma":0.00031342258,"threshold_uncertainty_score":0.99960846},"labels":[],"label_agreement":null},{"id":"W4290713184","doi":"10.1109/access.2022.3197603","title":"Hierarchical Dirichlet Process Based Gamma Mixture Modeling for Terahertz Band Wireless Communication Channels","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Qatar National Research Fund; Institut de Valorisation des Données","keywords":"Computer science; Expectation–maximization algorithm; Channel (broadcasting); Terahertz radiation; Hierarchical Dirichlet process; Divergence (linguistics); Algorithm; Wireless; Metric (unit); Nakagami distribution; Artificial intelligence; Mathematics; Latent Dirichlet allocation; Fading; Maximum likelihood; Telecommunications; Physics; Topic model; Statistics; Engineering","score_opus":0.043090986673853436,"score_gpt":0.331523722093017,"score_spread":0.2884327354191636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290713184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033948984,0.00022860088,0.9606881,0.0033562342,0.00060367474,0.0006465418,0.00002433611,0.00017164496,0.00033186667],"genre_scores_gemma":[0.89782995,0.000008991558,0.0989749,0.0020820037,0.00015028153,0.00079219486,0.000028078279,0.00003124776,0.00010235928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978213,0.0003773184,0.00034067762,0.0006047094,0.0004262073,0.000429809],"domain_scores_gemma":[0.99828154,0.0002706098,0.00014637453,0.0009938922,0.00017381688,0.00013378277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009500817,0.0002279572,0.00029734502,0.00016842583,0.0007522825,0.0004665422,0.0033641937,0.0000911604,0.000018553306],"category_scores_gemma":[0.000029463314,0.00021601608,0.0001247729,0.0005851706,0.00003935084,0.0007821759,0.0003365923,0.0004614109,0.0000010251073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005913647,0.0014268075,0.0003600371,0.00075849955,0.00016622647,0.000049500377,0.0091350535,0.28634694,0.007370037,0.062984236,0.01060572,0.6202056],"study_design_scores_gemma":[0.00065133104,0.00006677934,0.0000076197025,0.000027384496,0.000011998642,0.000009468044,0.000010970138,0.9263414,0.005320601,0.065452546,0.0018107675,0.00028910357],"about_ca_topic_score_codex":0.00002607977,"about_ca_topic_score_gemma":0.000006536365,"teacher_disagreement_score":0.863881,"about_ca_system_score_codex":0.00006370828,"about_ca_system_score_gemma":0.0001654434,"threshold_uncertainty_score":0.88088804},"labels":[],"label_agreement":null},{"id":"W4292513139","doi":"10.21203/rs.3.rs-1903006/v1","title":"A multidimensional ODE-based model of Alzheimer's disease progression","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; IXICO; H. Lundbeck A/S; Servier; National Institutes of Health; Innoviris; Eisai; Pfizer; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Biomarker; Disease; Computer science; Dementia; Logistic regression; Artificial intelligence; Machine learning; Medicine; Biology; Pathology","score_opus":0.12638190065586458,"score_gpt":0.4386344727914195,"score_spread":0.3122525721355549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292513139","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002230321,0.003959674,0.989416,0.0016281593,0.00023323852,0.0014933397,0.00020267676,0.00013943027,0.00069718476],"genre_scores_gemma":[0.33824098,0.00006412038,0.6606158,0.00007276663,0.0000656553,0.0006600321,0.0000984399,0.000040167717,0.00014205156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928532,0.0017364876,0.00047555714,0.0012415514,0.0029730464,0.0007201416],"domain_scores_gemma":[0.9958875,0.0003788713,0.00021396666,0.002227848,0.00074058067,0.0005512417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003771782,0.00032302766,0.0004720252,0.00065108854,0.00036116625,0.000111430745,0.0019126539,0.00021922705,0.00010784195],"category_scores_gemma":[0.00026468298,0.00028267343,0.0003752935,0.00057394855,0.00020553534,0.00014627886,0.0063144844,0.0019252091,0.000008685278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007408736,0.0033315045,0.0009084232,0.0033708261,0.00028009654,0.0004873927,0.0016637696,0.35932308,0.003317818,0.36851153,0.008243804,0.24982087],"study_design_scores_gemma":[0.00034896747,0.000118461074,0.00033148495,0.00055070035,0.000019503237,5.0609714e-7,0.0000062678064,0.93206614,0.0012109185,0.064679675,0.00039015673,0.00027724085],"about_ca_topic_score_codex":0.000050539988,"about_ca_topic_score_gemma":0.0000022056165,"teacher_disagreement_score":0.57274306,"about_ca_system_score_codex":0.00014469207,"about_ca_system_score_gemma":0.0031089925,"threshold_uncertainty_score":0.99996257},"labels":[],"label_agreement":null},{"id":"W4292794370","doi":"10.1007/s12652-022-04359-x","title":"Occupancy estimation in smart buildings using predictive modeling in imbalanced domains","year":2022,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Occupancy; Computer science; Inference; Complement (music); Dirichlet distribution; Machine learning; Artificial intelligence; Computational intelligence; Focus (optics); Data mining; Bayesian inference; Bayesian probability; Gibbs sampling; GRASP; Sampling (signal processing); Mathematics","score_opus":0.046742717469601174,"score_gpt":0.31191363970286035,"score_spread":0.26517092223325917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292794370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42330155,0.00024404365,0.5760858,0.00003538662,0.00021263755,0.00008407554,3.2147676e-7,0.000009076308,0.000027130018],"genre_scores_gemma":[0.64300525,0.000024223222,0.3568526,0.00008039158,0.00002890065,0.0000011506598,2.2047185e-7,0.0000056600315,0.0000015856442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979811,0.00022971052,0.0008356006,0.00028542217,0.00037262094,0.00029559017],"domain_scores_gemma":[0.9990984,0.00012755109,0.00044110796,0.00015627645,0.00010818618,0.00006845028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021422172,0.0001466568,0.00035145076,0.0005557485,0.00025571606,0.00012052173,0.0005282757,0.000037433707,0.0000044620806],"category_scores_gemma":[0.00006447266,0.00014669019,0.00007509366,0.0005605965,0.000025745201,0.0004980946,0.00039598215,0.00057910243,2.0345671e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009116314,0.0001681882,0.0016925678,0.000027147778,0.000020020902,0.0001708738,0.011819283,0.8565535,0.0015052622,0.027827533,0.000004281971,0.100120164],"study_design_scores_gemma":[0.00036120406,0.00020088612,0.000251765,0.00018226143,0.000007025029,0.00026851112,0.00037180271,0.9510753,0.00033684607,0.046800803,0.0000073234,0.00013625578],"about_ca_topic_score_codex":0.00006471801,"about_ca_topic_score_gemma":0.0000057134757,"teacher_disagreement_score":0.21970373,"about_ca_system_score_codex":0.0002474825,"about_ca_system_score_gemma":0.00010266642,"threshold_uncertainty_score":0.59818524},"labels":[],"label_agreement":null},{"id":"W4292998295","doi":"","title":"Some recent statistical methods applied in genetics/genomics","year":2017,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistical genetics; Genomics; Computational biology; Biology; Evolutionary biology; Genetics; Genome; Gene","score_opus":0.032624525979073477,"score_gpt":0.3085221064176629,"score_spread":0.2758975804385895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292998295","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060723064,0.002715774,0.9553019,0.007077179,0.000612316,0.0005545751,0.000035328514,0.000166888,0.032928858],"genre_scores_gemma":[0.010996996,0.003335078,0.98394656,0.00026313937,0.000064003936,0.000108047,0.00011384449,0.000049181937,0.0011231677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99008435,0.006745981,0.00074585614,0.0014352154,0.000405423,0.00058317697],"domain_scores_gemma":[0.99140286,0.0016927276,0.00066176325,0.0050893896,0.00090059964,0.00025263664],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.013321042,0.00045156476,0.0006625049,0.0002836646,0.0003255835,0.0011067796,0.0044833613,0.00047559175,0.000036857433],"category_scores_gemma":[0.0013682736,0.00048739978,0.000145691,0.00022657505,0.00026919492,0.0001921955,0.0046662763,0.0011360383,0.00003217586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034886136,0.00014639732,0.000027230779,0.000048993174,0.000018383971,0.000005755611,0.0015624764,0.000025512241,0.0009139166,0.5313218,0.00026844052,0.46565762],"study_design_scores_gemma":[0.0006025887,4.0159156e-7,0.0015679157,0.0004711109,0.000031022355,0.0000093071985,0.000010139408,0.12748726,0.029934466,0.8044516,0.03464573,0.0007884736],"about_ca_topic_score_codex":0.00030607716,"about_ca_topic_score_gemma":0.00032570708,"teacher_disagreement_score":0.46486914,"about_ca_system_score_codex":0.00023241738,"about_ca_system_score_gemma":0.0006926561,"threshold_uncertainty_score":0.99993014},"labels":[],"label_agreement":null},{"id":"W4293451216","doi":"10.1007/978-3-031-08530-7_36","title":"A Generalized Inverted Dirichlet Predictive Model for Activity Recognition Using Small Training Data","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Computer science; Inference; Flexibility (engineering); Artificial intelligence; Machine learning; Bounded function; Bayesian inference; Bayesian probability; Algorithm; Pattern recognition (psychology); Data mining; Training set; Mathematics; Statistics","score_opus":0.20407600592725775,"score_gpt":0.3237577202768275,"score_spread":0.11968171434956973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293451216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014726285,0.00016798974,0.9961101,0.0003669687,0.0012624214,0.001047538,0.00028771025,0.00018725327,0.00042279015],"genre_scores_gemma":[0.007017218,0.00003515379,0.9909174,0.0013769284,0.00036909597,0.00004535093,0.00009492399,0.00005782279,0.000086103966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99516696,0.00015139511,0.0005063649,0.0026014706,0.0007800923,0.00079374824],"domain_scores_gemma":[0.9962033,0.00063726964,0.0004609035,0.0022390415,0.00025383878,0.00020562393],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002428623,0.00060999015,0.00075737457,0.0007509772,0.0005713981,0.00042021475,0.0047433493,0.00034205877,0.000013476653],"category_scores_gemma":[0.0002123988,0.0006072783,0.00016689753,0.0006240876,0.0003471072,0.0013062101,0.003373288,0.00097527815,0.0000011503519],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003821429,0.000033222703,9.462285e-7,0.000039137227,0.000029432682,0.000018130644,0.0015327573,0.07134252,0.00046696572,0.004887852,0.000019314582,0.9215915],"study_design_scores_gemma":[0.00040214136,0.00009786981,0.0000016017847,0.00011305086,0.000030180578,0.0000368578,1.0648e-7,0.7135531,0.00018141516,0.2849109,0.00017213935,0.0005006897],"about_ca_topic_score_codex":0.00005237563,"about_ca_topic_score_gemma":0.00009235439,"teacher_disagreement_score":0.92109084,"about_ca_system_score_codex":0.00044055603,"about_ca_system_score_gemma":0.001434181,"threshold_uncertainty_score":0.99963784},"labels":[],"label_agreement":null},{"id":"W4295690809","doi":"10.48550/arxiv.2209.04757","title":"Normal approximations for the multivariate inverse Gaussian distribution and asymmetric kernel smoothing on $d$-dimensional half-spaces","year":2022,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Centre de Recherches Mathématiques","keywords":"Inverse Gaussian distribution; Mathematics; Multivariate normal distribution; Normal-inverse Gaussian distribution; Extension (predicate logic); Inverse-Wishart distribution; Gaussian; Generalized inverse Gaussian distribution; Inverse; Limit (mathematics); Distribution (mathematics); Metric (unit); Multivariate statistics; Inverse distribution; Applied mathematics; Normal distribution; Statistics; Mathematical analysis; Heavy-tailed distribution; Gaussian function; Gaussian random field; Physics; Computer science; Geometry","score_opus":0.04920358586537667,"score_gpt":0.296532288744306,"score_spread":0.24732870287892933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295690809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03088008,0.00024892006,0.96097803,0.0053201434,0.0011760416,0.00080923823,0.00013628996,0.000119750584,0.00033148727],"genre_scores_gemma":[0.69050455,0.00005038135,0.30699217,0.0009278021,0.00026357936,0.00046918966,0.00020992043,0.000033369095,0.0005490291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978228,0.0002899438,0.0003337904,0.0008189395,0.00036410318,0.000370403],"domain_scores_gemma":[0.9977833,0.0008349772,0.00031563558,0.00084688095,0.00009494973,0.0001242798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013375272,0.0003210723,0.0003002756,0.00017450961,0.00086119573,0.00027177093,0.0008751129,0.00019798135,0.000013817186],"category_scores_gemma":[0.00031439314,0.00024089839,0.0001787191,0.00041896105,0.00008385003,0.0002605696,0.0016219218,0.0008633064,0.0000066226685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017079437,0.0006707367,0.013004922,0.0005314718,0.00060797017,0.000040946386,0.00544631,0.018160261,0.000475317,0.7935004,0.0067390953,0.16065174],"study_design_scores_gemma":[0.00093920407,0.00014678984,0.06771067,0.00010684293,0.00011770083,0.00001672081,0.00007773567,0.88721013,0.0004228345,0.030971304,0.011577939,0.0007021107],"about_ca_topic_score_codex":0.00029198139,"about_ca_topic_score_gemma":0.000016818625,"teacher_disagreement_score":0.8690499,"about_ca_system_score_codex":0.0001288986,"about_ca_system_score_gemma":0.00015462504,"threshold_uncertainty_score":0.9823551},"labels":[],"label_agreement":null},{"id":"W4296500923","doi":"10.1007/978-3-031-16210-7_55","title":"Stochastic Expectation Propagation Learning for Unsupervised Feature Selection","year":2022,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Frequentist inference; Dirichlet distribution; Feature selection; Computer science; Cluster analysis; Artificial intelligence; Machine learning; Feature (linguistics); Unsupervised learning; Bayesian probability; Pattern recognition (psychology); Model selection; Selection (genetic algorithm); Dirichlet process; Algorithm; Data mining; Bayesian inference; Mathematics","score_opus":0.033928913838547604,"score_gpt":0.2976711487856283,"score_spread":0.26374223494708066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296500923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011098835,0.00017127121,0.974047,0.0009899675,0.0002461816,0.00077644136,0.0000046994314,0.000117828706,0.02363548],"genre_scores_gemma":[0.019577656,0.00048807368,0.976461,0.00050197827,0.0000667109,0.0002804172,0.00017699618,0.000017139955,0.0024300609],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849075,0.00007617678,0.00045833236,0.00034321085,0.0004138034,0.00021770364],"domain_scores_gemma":[0.99799734,0.00027009487,0.00036209915,0.00085167657,0.00044522653,0.00007354231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013559018,0.00020792703,0.00021965502,0.0009605892,0.0010783866,0.00049801293,0.0016691126,0.00012257343,0.000009189538],"category_scores_gemma":[0.00008721814,0.00021898077,0.000056289315,0.0005282693,0.00022255836,0.005964358,0.0009440109,0.00059484417,0.0000051205197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039987876,0.00000790755,0.000003080011,0.000023397351,0.0000035413086,4.491413e-8,0.0020222839,0.0022690373,0.000012030656,0.6847216,0.00010485778,0.31082824],"study_design_scores_gemma":[0.00031152405,0.0001180119,0.00013433909,0.00006365442,0.0000072037524,0.000017517528,0.000017679318,0.92551994,0.0000105247755,0.019943926,0.053595353,0.00026034296],"about_ca_topic_score_codex":0.000004662403,"about_ca_topic_score_gemma":0.0000038465287,"teacher_disagreement_score":0.9232509,"about_ca_system_score_codex":0.00024656902,"about_ca_system_score_gemma":0.0003276665,"threshold_uncertainty_score":0.89297765},"labels":[],"label_agreement":null},{"id":"W4297965119","doi":"10.1109/tnnls.2022.3208202","title":"Grouped Spherical Data Modeling Through Hierarchical Nonparametric Bayesian Models and Its Application to fMRI Data Analysis","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Nonparametric statistics; Bayesian probability; Computer science; Bayesian hierarchical modeling; Hierarchical database model; Multilevel model; Artificial intelligence; Pattern recognition (psychology); Data mining; Bayesian inference; Machine learning; Statistics; Mathematics","score_opus":0.05664004246985695,"score_gpt":0.29950133311309673,"score_spread":0.2428612906432398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297965119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021313704,0.0011574691,0.99508893,0.00056151993,0.00034497379,0.00048292195,0.000036925943,0.00016474607,0.000031126263],"genre_scores_gemma":[0.93691057,0.00014752871,0.062346336,0.00024672886,0.00010370312,0.00009137307,0.00005165309,0.000024741988,0.00007738582],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962985,0.0009994073,0.00044430938,0.0014161848,0.0004373544,0.00040424793],"domain_scores_gemma":[0.9977618,0.00034678823,0.00011389,0.0015020048,0.00004061213,0.00023492571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013207066,0.00025487976,0.0004652774,0.0002471682,0.00107972,0.0003267329,0.0014316591,0.00009837991,0.0000044262147],"category_scores_gemma":[0.000010065142,0.00024384222,0.000065417276,0.002104959,0.000023855075,0.0008690274,0.00015772523,0.0011583345,8.070732e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026811143,0.00005911591,0.000005058677,0.000012621793,0.00009841502,0.000004895184,0.00021090984,0.93671453,0.000017184799,0.0013091903,0.000020184601,0.061521064],"study_design_scores_gemma":[0.00020124472,0.00016623852,0.0000046279656,0.000009207457,0.00016315372,0.0000482003,0.00004549577,0.99858874,9.448806e-7,0.00020757956,0.00029459398,0.00026995895],"about_ca_topic_score_codex":0.00030075156,"about_ca_topic_score_gemma":0.000017883202,"teacher_disagreement_score":0.93477917,"about_ca_system_score_codex":0.00003670565,"about_ca_system_score_gemma":0.000022777635,"threshold_uncertainty_score":0.99435973},"labels":[],"label_agreement":null},{"id":"W4297966707","doi":"10.15672/hujms.1094273","title":"Generating function for generalized Fisher information measure and its application to finite mixture models","year":2022,"lang":"en","type":"article","venue":"DergiPark (Istanbul University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Measure (data warehouse); Fisher information; Function (biology); Mathematics; Applied mathematics; Computer science; Calculus (dental); Statistical physics; Statistics; Data mining; Physics; Medicine","score_opus":0.015435353010323108,"score_gpt":0.2035319738895451,"score_spread":0.188096620879222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297966707","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033811606,0.0000864248,0.9927895,0.0008493814,0.00017391128,0.00059200154,0.000034805948,0.00011252458,0.001980255],"genre_scores_gemma":[0.3510311,0.000021965101,0.64291674,0.0031633568,0.000110266024,0.000086405555,0.0001109408,0.00002125817,0.00253796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989505,0.00014109025,0.00015497017,0.00032129398,0.00022427602,0.00020791037],"domain_scores_gemma":[0.99926263,0.00006434814,0.00011081461,0.0002722327,0.00017760554,0.00011236508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036629935,0.00013525433,0.00014084503,0.00026159786,0.0006269712,0.00010578215,0.00037381786,0.0000620765,0.00000859152],"category_scores_gemma":[0.000024916764,0.00015837802,0.000057387246,0.0006293419,0.0000078373305,0.0011837621,0.00025369134,0.00013159156,0.000002185878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020049285,0.000034244535,0.000006218259,0.00004853146,0.000042992815,0.0000040651485,0.0026940096,0.1313775,0.0036082934,0.7910277,0.0051010144,0.06585491],"study_design_scores_gemma":[0.00064311805,0.00009127601,0.000010707214,0.0000038315834,0.000028051614,0.000004879132,0.00011672285,0.8020097,0.00018391255,0.009274225,0.18741931,0.0002142971],"about_ca_topic_score_codex":0.000012727821,"about_ca_topic_score_gemma":0.000011281541,"teacher_disagreement_score":0.7817535,"about_ca_system_score_codex":0.00012679529,"about_ca_system_score_gemma":0.000067175926,"threshold_uncertainty_score":0.64584684},"labels":[],"label_agreement":null},{"id":"W4297995547","doi":"10.1515/mcma-2022-2123","title":"Estimation of entropy and extropy based on right censored data: A Bayesian non-parametric approach","year":2022,"lang":"en","type":"article","venue":"Monte Carlo Methods and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Parametric statistics; Bayesian probability; Mathematics; Entropy (arrow of time); Principle of maximum entropy; Econometrics; Statistics; Applied mathematics; Computer science; Physics","score_opus":0.02316970924384907,"score_gpt":0.32584309438981424,"score_spread":0.30267338514596515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297995547","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039901023,0.00045921933,0.99714315,0.0003894752,0.000045461948,0.00067283335,0.00008538568,0.00004912069,0.0007563681],"genre_scores_gemma":[0.13619538,0.000027835333,0.8630457,0.00018402761,0.00002688722,0.00041809838,0.000028092842,0.000012501221,0.00006147739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795806,0.0005440152,0.000310224,0.000733337,0.00025018302,0.00020415419],"domain_scores_gemma":[0.99787974,0.0004311727,0.00018644855,0.0013281627,0.000045490375,0.00012898451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015065401,0.0001731017,0.00030655166,0.0002625287,0.00037055727,0.000083716564,0.0007274987,0.00005205688,0.000004742327],"category_scores_gemma":[0.00005855167,0.00015687643,0.00004977797,0.00091831456,0.00008134376,0.00018069777,0.00044532388,0.00022161784,1.6228964e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001672275,0.00023509361,0.00004436282,0.00005350778,0.000021384823,0.0000013841044,0.000193317,0.005719633,0.0012690099,0.19024712,0.00027443958,0.80192405],"study_design_scores_gemma":[0.00036815362,0.00009032336,0.00027286916,0.000004826786,0.000033522407,0.000010677417,0.000024731775,0.98247176,0.00067345536,0.011463892,0.0044252467,0.00016052941],"about_ca_topic_score_codex":0.000043654272,"about_ca_topic_score_gemma":4.5631174e-7,"teacher_disagreement_score":0.97675216,"about_ca_system_score_codex":0.000031658867,"about_ca_system_score_gemma":0.00005124559,"threshold_uncertainty_score":0.6397235},"labels":[],"label_agreement":null},{"id":"W4298066383","doi":"10.1002/0471667196.ess5099","title":"Discrete Multivariate Distributions","year":2004,"lang":"en","type":"other","venue":"Encyclopedia of Statistical Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Notation; Multivariate analysis; Mathematics; Computer science; Statistics; Econometrics; Arithmetic","score_opus":0.014154329457790627,"score_gpt":0.3078528405316583,"score_spread":0.2936985110738677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298066383","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8499344e-7,0.00019713811,0.5556971,0.00016938348,0.00035333837,0.00011660949,0.00032327988,0.000080676735,0.44306234],"genre_scores_gemma":[0.00026861904,0.00031309386,0.93569505,0.000035147463,0.0001421072,0.000014929955,0.000019582008,0.000040917486,0.06347052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99795574,0.00012215298,0.00032745957,0.0006419424,0.0005337321,0.00041897496],"domain_scores_gemma":[0.998857,0.00028550238,0.0002288917,0.00040391507,0.000029890432,0.00019478059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042031435,0.0002495858,0.00039520513,0.00015299597,0.000120800185,0.000076869495,0.0012877738,0.0001653564,0.0005978791],"category_scores_gemma":[0.00027095838,0.00018427911,0.000072230694,0.0005281006,0.000789766,0.00013833186,0.00027028617,0.00019266935,0.00006104813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.969313e-7,0.00003563377,0.000011613306,0.000028575563,0.00000998023,0.000010843373,0.00005158166,0.000001602131,0.0000040697996,0.91898984,0.05016335,0.030692333],"study_design_scores_gemma":[0.00028663594,0.00018769712,0.0006565777,0.00026782585,0.000036338624,0.0000077966915,0.0000057667685,0.0015091172,0.000027911397,0.6246168,0.3718291,0.000568433],"about_ca_topic_score_codex":0.0007082482,"about_ca_topic_score_gemma":0.000058457583,"teacher_disagreement_score":0.37999803,"about_ca_system_score_codex":0.000030380488,"about_ca_system_score_gemma":0.00035620554,"threshold_uncertainty_score":0.7514684},"labels":[],"label_agreement":null},{"id":"W4298267155","doi":"10.48550/arxiv.1609.02249","title":"Clustering Sequence Data with Mixture Markov Chains with Covariates Using Multiple Simplex Constrained Optimization Routine (MSiCOR)","year":2016,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Expectation–maximization algorithm; Cluster analysis; Computer science; Covariate; Context (archaeology); Maximization; Markov chain; Simplex; Mathematical optimization; Data mining; Artificial intelligence; Machine learning; Mathematics; Statistics; Maximum likelihood","score_opus":0.09582392206924462,"score_gpt":0.30981971178132717,"score_spread":0.21399578971208255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298267155","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015507157,0.00011261952,0.9814149,0.0009723118,0.00040287906,0.00078537455,0.00025778392,0.00033426975,0.00021267582],"genre_scores_gemma":[0.3733741,0.00002948464,0.6257884,0.00028233675,0.00020494385,0.000019114792,0.00017443433,0.000052465242,0.00007471007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996155,0.0003220799,0.00052368874,0.0018722456,0.0004323078,0.00069466874],"domain_scores_gemma":[0.9953264,0.00026278917,0.000637028,0.0032374777,0.00030328342,0.0002330037],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008493093,0.0006876115,0.000701871,0.0001683214,0.00027659576,0.00035152253,0.0026252088,0.0003828248,0.00002371233],"category_scores_gemma":[0.00014730205,0.0004727192,0.00007006459,0.0003745384,0.000247795,0.00084604416,0.0032865899,0.00065519806,0.0000028332227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012921194,0.0007128086,0.26116475,0.0022472697,0.0024051208,0.0016461799,0.005268772,0.54523146,0.020339001,0.013722674,0.00047632065,0.14549349],"study_design_scores_gemma":[0.0011278574,0.00008303433,0.0011334945,0.0008670834,0.00009057149,0.00016404927,0.0000122815145,0.99487096,0.0004263673,0.00032471376,0.00009355017,0.00080603344],"about_ca_topic_score_codex":0.00017160963,"about_ca_topic_score_gemma":0.00008332468,"teacher_disagreement_score":0.44963947,"about_ca_system_score_codex":0.00014088757,"about_ca_system_score_gemma":0.0006676673,"threshold_uncertainty_score":0.9997724},"labels":[],"label_agreement":null},{"id":"W4298350535","doi":"","title":"Distribution functions of the sequence phi(n)/n, n in (k,k+N]","year":2010,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Sequence (biology); Distribution (mathematics); Combinatorics; Mathematics; Mathematical analysis; Biology; Genetics","score_opus":0.02040299232631669,"score_gpt":0.2501871431570078,"score_spread":0.2297841508306911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298350535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022273833,0.0002461976,0.9560065,0.011021782,0.00059408194,0.00034839456,0.00008361466,0.000093212344,0.009332383],"genre_scores_gemma":[0.750272,0.00010964251,0.24721314,0.0000722355,0.000017721568,0.00005565107,0.0001073158,0.000015329591,0.0021369986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99387354,0.00427614,0.00051305897,0.0006761308,0.0003786332,0.0002825193],"domain_scores_gemma":[0.9941997,0.00070951233,0.00051490136,0.0033078422,0.0011723695,0.00009566373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054947743,0.0002384933,0.00030340423,0.00010729247,0.00021271313,0.00021571234,0.0028668188,0.00035155445,0.000019862859],"category_scores_gemma":[0.0011538905,0.00020100758,0.00021774638,0.00069188455,0.00026802794,0.00018253642,0.00238656,0.0011994002,0.000007054048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030737083,0.00035481853,0.0013899528,0.0001002857,0.00002268658,0.0000020614013,0.0035513698,0.000077945166,0.008981767,0.8477467,0.00067483453,0.13709454],"study_design_scores_gemma":[0.0011206402,9.823837e-7,0.04110362,0.004370802,0.000080482656,0.000047578847,0.000049833303,0.27893892,0.20405039,0.44489413,0.023986002,0.0013565996],"about_ca_topic_score_codex":0.00096571643,"about_ca_topic_score_gemma":0.0019364725,"teacher_disagreement_score":0.72799814,"about_ca_system_score_codex":0.000096853306,"about_ca_system_score_gemma":0.00043614372,"threshold_uncertainty_score":0.81968516},"labels":[],"label_agreement":null},{"id":"W4299390741","doi":"10.1002/0471667196.ess5099.pub2","title":"Discrete Multivariate Distributions","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistical Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Multivariate analysis; Notation; Mathematics; Computer science; Statistics; Econometrics; Arithmetic","score_opus":0.013644398209613516,"score_gpt":0.3113016143539072,"score_spread":0.2976572161442937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299390741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4708685e-7,0.00024010713,0.5309938,0.00020796561,0.00028330978,0.00009687358,0.0003112879,0.00007653297,0.46778995],"genre_scores_gemma":[0.00013130787,0.00040177515,0.8568554,0.000040900555,0.0002515384,0.000012817291,0.000016530435,0.000036727033,0.142253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997927,0.000146876,0.00034116683,0.0006324625,0.0005283219,0.0004241767],"domain_scores_gemma":[0.9987661,0.00036561713,0.00023337375,0.00041040327,0.000029358038,0.00019513798],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047108874,0.0002480073,0.00039395803,0.00015419001,0.0001160871,0.00007551987,0.0013160509,0.00016340885,0.0014923456],"category_scores_gemma":[0.00025828197,0.00018330151,0.000070913135,0.00047606527,0.0006936665,0.00015393984,0.0002770974,0.00019212217,0.000078051264],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.507982e-7,0.00003157498,0.000010965305,0.000015825583,0.00000891233,0.000005227703,0.0000409902,7.6563185e-7,0.0000033926915,0.7567505,0.1185686,0.12456264],"study_design_scores_gemma":[0.0001681069,0.00011284124,0.0006022011,0.00012148215,0.000028507868,0.000005355142,0.0000041129565,0.0044893194,0.000015214223,0.093624406,0.90037996,0.00044851663],"about_ca_topic_score_codex":0.00033338272,"about_ca_topic_score_gemma":0.00006090453,"teacher_disagreement_score":0.78181136,"about_ca_system_score_codex":0.000019694877,"about_ca_system_score_gemma":0.00019547054,"threshold_uncertainty_score":0.9994204},"labels":[],"label_agreement":null},{"id":"W4299532496","doi":"10.1007/0-8176-4477-6_2","title":"Lagrangian Probability Distributions","year":2006,"lang":"en","type":"book-chapter","venue":"Birkhäuser-Verlag eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Lagrangian; Statistical physics; Mathematics; Computer science; Applied mathematics; Physics","score_opus":0.024050758041553152,"score_gpt":0.23684312511448638,"score_spread":0.21279236707293323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299532496","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000041306535,0.00015552127,0.50276595,0.00016974773,0.0003702813,0.000442146,0.00012231096,0.0004027448,0.49556714],"genre_scores_gemma":[0.0010160115,0.0000119571005,0.22657245,0.00028535345,0.0004305501,0.000057418136,0.000084205,0.00009385152,0.7714482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99654406,0.000101620935,0.0007256982,0.0013275243,0.0006099015,0.00069118163],"domain_scores_gemma":[0.9966072,0.0001367405,0.0003653216,0.00232811,0.0002562531,0.0003063694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057771243,0.00076050183,0.0007549108,0.00021307777,0.00033811937,0.0003109057,0.0017595786,0.0008137744,0.00006907162],"category_scores_gemma":[0.000027605904,0.00071057264,0.00059467065,0.000059270114,0.00025426582,0.00018679611,0.0005700521,0.0007789595,0.00022210607],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048427605,0.000027454136,0.0000031114453,0.000055744928,0.0000424224,0.00004457066,0.00005130158,8.5644797e-7,0.000050290077,0.9185809,0.019123917,0.06201463],"study_design_scores_gemma":[0.00021799127,0.00005650561,0.00004204905,0.000095814714,0.00005241779,0.000026076053,2.5580664e-7,0.00017374294,0.00020152073,0.539039,0.45947614,0.00061843346],"about_ca_topic_score_codex":0.00007000916,"about_ca_topic_score_gemma":0.00011687703,"teacher_disagreement_score":0.44035223,"about_ca_system_score_codex":0.00023169714,"about_ca_system_score_gemma":0.00036727623,"threshold_uncertainty_score":0.99953455},"labels":[],"label_agreement":null},{"id":"W4299614488","doi":"10.48550/arxiv.1310.2888","title":"Transdimensional Approximate Bayesian Computation for Inference on\\n Invasive Species Models with Latent Variables of Unknown Dimension","year":2013,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Approximate Bayesian computation; Latent variable; Inference; Bayesian inference; Bayesian probability; Sampling (signal processing); Computation; Dimension (graph theory); Computer science; Statistics; Mathematics; Ecology; Artificial intelligence; Algorithm; Biology","score_opus":0.09589094610777238,"score_gpt":0.20937495561623742,"score_spread":0.11348400950846504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299614488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058059946,0.000053545682,0.9378314,0.00014494533,0.0004890104,0.002188099,0.000106409374,0.00009741895,0.0010292273],"genre_scores_gemma":[0.69303095,0.0002977151,0.30575496,0.0001004289,0.000047240497,0.000009251451,0.000059748345,0.000044442088,0.00065525435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949276,0.00055360334,0.0008191517,0.0024681448,0.00039446575,0.0008370496],"domain_scores_gemma":[0.99427825,0.0013298878,0.0011305048,0.0013303587,0.001497419,0.00043354864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007716036,0.0010115803,0.0013342905,0.0005779237,0.00043903067,0.00019627428,0.0015101143,0.00064173725,0.000045244786],"category_scores_gemma":[0.000050044404,0.00094622123,0.00047130053,0.00089970574,0.0005546504,0.0010430407,0.0008020838,0.0007537816,0.000008529329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031269435,0.0002938043,0.000038137467,0.0003428091,0.00018720047,0.000028533104,0.00078547926,0.51026464,0.0004137544,0.48612916,0.000035035413,0.0011687666],"study_design_scores_gemma":[0.0013549431,0.00064390263,0.00008944902,0.0008847066,0.00021978715,0.000005771549,0.000041323816,0.63098687,0.0017587839,0.36333808,0.000011573673,0.00066484406],"about_ca_topic_score_codex":0.00014387611,"about_ca_topic_score_gemma":0.00003159974,"teacher_disagreement_score":0.634971,"about_ca_system_score_codex":0.00025259895,"about_ca_system_score_gemma":0.0009268101,"threshold_uncertainty_score":0.9992988},"labels":[],"label_agreement":null},{"id":"W4300821755","doi":"10.1007/978-3-030-99142-5_6","title":"Bayesian Inference of Hidden Markov Models Using Dirichlet Mixtures","year":2012,"lang":"en","type":"book-chapter","venue":"Unsupervised and semi-supervised learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Markov chain Monte Carlo; Hierarchical Dirichlet process; Hidden Markov model; Computer science; Dirichlet process; Variable-order Bayesian network; Reversible-jump Markov chain Monte Carlo; Artificial intelligence; Bayesian inference; Machine learning; Inference; Dirichlet distribution; Model selection; Benchmark (surveying); Bayesian probability; Gibbs sampling; Latent Dirichlet allocation; Topic model; Mathematics","score_opus":0.03312889631722289,"score_gpt":0.2585312073238452,"score_spread":0.22540231100662234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300821755","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006941023,0.014762264,0.8926979,0.00012679187,0.0003221201,0.00048567698,0.000027349975,0.0002634963,0.09062031],"genre_scores_gemma":[0.2400931,0.006526901,0.70506316,0.0007123747,0.00089343695,0.000027497385,0.00010714571,0.00038508492,0.04619128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99521375,0.00037798448,0.0011300286,0.0013771312,0.0008853261,0.0010157687],"domain_scores_gemma":[0.99660176,0.0005674187,0.0005432161,0.0013214784,0.0003545855,0.0006115604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011067899,0.0011445058,0.001590114,0.0006704863,0.00042839473,0.00028214077,0.0014883993,0.0011028241,0.00031178474],"category_scores_gemma":[0.00009851687,0.0010826471,0.00046433462,0.00023950635,0.00026287304,0.0011489058,0.0009989316,0.0017342794,0.000011036025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006092608,0.000089494315,0.00032632306,0.0008632275,0.00037434226,0.00006755057,0.006482844,0.00061220396,0.00625066,0.2974263,0.00018899849,0.6872571],"study_design_scores_gemma":[0.0015096376,0.000291014,0.000042451793,0.0017925604,0.00043790086,0.00013308745,0.0000751243,0.8180363,0.0007375558,0.16452591,0.00976184,0.002656615],"about_ca_topic_score_codex":0.00008417397,"about_ca_topic_score_gemma":0.000004537567,"teacher_disagreement_score":0.8174241,"about_ca_system_score_codex":0.00009043054,"about_ca_system_score_gemma":0.00029236445,"threshold_uncertainty_score":0.9991624},"labels":[],"label_agreement":null},{"id":"W4300881738","doi":"10.1007/978-3-030-99142-5_11","title":"Shifted-Scaled Dirichlet-Based Hierarchical Dirichlet Process Hidden Markov Models with Variational Inference Learning","year":2012,"lang":"en","type":"book-chapter","venue":"Unsupervised and semi-supervised learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hierarchical Dirichlet process; Dirichlet distribution; Inference; Dirichlet process; Mathematics; Applied mathematics; Generalized Dirichlet distribution; Artificial intelligence; Computer science; Dirichlet's principle; Mathematical analysis","score_opus":0.0176861583926015,"score_gpt":0.2400167336939107,"score_spread":0.22233057530130917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300881738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011264832,0.0028334688,0.90129733,0.00079333334,0.00018296928,0.0007909779,0.00002391004,0.0007943213,0.0921572],"genre_scores_gemma":[0.27748266,0.0012853718,0.6494136,0.0020794503,0.001368082,0.0002794197,0.00072961184,0.00064455526,0.0667173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928121,0.000703713,0.0011024425,0.0022104078,0.0016928161,0.0014785139],"domain_scores_gemma":[0.99538493,0.0013827313,0.00054096256,0.0010896603,0.000601824,0.0009998936],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0015490055,0.0015766352,0.001613422,0.0007739654,0.001058256,0.0007634289,0.0016570566,0.0012318352,0.0004826077],"category_scores_gemma":[0.00020259125,0.0013651911,0.00036577563,0.000458393,0.0003489511,0.001447596,0.00059717306,0.004291433,0.000051604475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046618888,0.0002825683,0.0023173024,0.0011115101,0.00058222783,0.0002259707,0.007854148,0.008293731,0.0003009768,0.4790567,0.00014665077,0.49936202],"study_design_scores_gemma":[0.003199458,0.00067039346,0.00038669902,0.0013739326,0.00035088,0.00009734598,0.00006361723,0.91057456,0.000044966957,0.0674939,0.012794475,0.0029498013],"about_ca_topic_score_codex":0.00002777261,"about_ca_topic_score_gemma":0.000008011403,"teacher_disagreement_score":0.9022808,"about_ca_system_score_codex":0.00015055618,"about_ca_system_score_gemma":0.0008023057,"threshold_uncertainty_score":0.99969816},"labels":[],"label_agreement":null},{"id":"W4301065033","doi":"10.17615/5rwj-gb21","title":"A Bivariate Pseudolikelihood for Incomplete Longitudinal Binary Data with Nonignorable Nonmonotone Missingness","year":2020,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Missing data; Bivariate analysis; Binary number; Longitudinal data; Multivariate statistics; Statistics; Computer science; Mathematics; Econometrics; Data mining; Arithmetic","score_opus":0.09612720943571457,"score_gpt":0.2792066298596823,"score_spread":0.18307942042396774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301065033","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004491063,0.00040711212,0.98419046,0.012997102,0.00017350649,0.00040356017,0.000074469805,0.0003149093,0.0009897891],"genre_scores_gemma":[0.028531738,0.0000032045218,0.9689293,0.00199496,0.00027810293,0.000032461947,0.00006250124,0.00003455864,0.00013318459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979956,0.00009731473,0.00027803465,0.00093110395,0.0002472226,0.00045068545],"domain_scores_gemma":[0.99806315,0.00022281097,0.00013440831,0.0012396533,0.0000729763,0.0002670237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028700268,0.00027642198,0.00039116034,0.00007372121,0.0003340342,0.0008458197,0.0022929783,0.000083289015,0.000016652126],"category_scores_gemma":[0.00007897214,0.00021496709,0.00005338256,0.00059848855,0.00012241346,0.0029513992,0.0011921804,0.00017187124,0.0000132440755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002730544,0.00010085751,0.00042937265,0.00018037892,0.00009750931,0.00008095678,0.0015885066,0.000061395294,0.0008904819,0.96506256,0.011437719,0.019797219],"study_design_scores_gemma":[0.0022217736,0.000994685,0.0006316067,0.00012523092,0.00008639499,0.000057420293,0.00005017774,0.5120445,0.0042568943,0.44876808,0.029835204,0.00092801097],"about_ca_topic_score_codex":0.000028326407,"about_ca_topic_score_gemma":0.0000029672403,"teacher_disagreement_score":0.5162945,"about_ca_system_score_codex":0.000009250326,"about_ca_system_score_gemma":0.0003870132,"threshold_uncertainty_score":0.87661034},"labels":[],"label_agreement":null},{"id":"W4302316314","doi":"10.48550/arxiv.1408.2128","title":"High-dimensional unsupervised classification via parsimonious\\n contaminated mixtures","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canada Research Chairs","keywords":"Mixture model; Gaussian; Expectation–maximization algorithm; Dimensionality reduction; Generalization; Covariance; Computer science; Context (archaeology); Mathematics; Mixture distribution; Algorithm; Pattern recognition (psychology); Artificial intelligence; Statistics; Probability density function; Maximum likelihood","score_opus":0.05581815113066747,"score_gpt":0.19732755118525783,"score_spread":0.14150940005459034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302316314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095927045,0.00008098806,0.9012175,0.0003318437,0.0010431784,0.00034796845,0.000013891387,0.0003567435,0.00068083376],"genre_scores_gemma":[0.9250023,0.000050236016,0.07335556,0.0004257171,0.00012539119,0.0000024710127,0.000072164825,0.000028894161,0.0009373123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99677557,0.00063101324,0.00032763,0.0016214853,0.0001751289,0.00046920357],"domain_scores_gemma":[0.99703586,0.00020265207,0.00036566108,0.001791468,0.00032745276,0.00027691998],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005739887,0.00048992166,0.0005683768,0.00030330417,0.00022538996,0.00014389472,0.0020269635,0.00063735864,0.00003531472],"category_scores_gemma":[0.000037430716,0.0005187056,0.00027475136,0.00048040788,0.0001473092,0.00028873654,0.0012537865,0.00079247734,0.00009454737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008513148,0.00026379462,0.00037418614,0.00013182973,0.0002434552,0.00029260124,0.00023295308,0.035823755,0.0030198928,0.9316798,0.0023953982,0.025457198],"study_design_scores_gemma":[0.00065022975,0.000056418274,0.0017682547,0.00007294432,0.00008177291,0.000006563832,0.0000036016454,0.7757185,0.0009793829,0.21979932,0.00029617493,0.0005668209],"about_ca_topic_score_codex":0.00021834648,"about_ca_topic_score_gemma":0.000021058882,"teacher_disagreement_score":0.8290752,"about_ca_system_score_codex":0.0001900715,"about_ca_system_score_gemma":0.00020272567,"threshold_uncertainty_score":0.9997265},"labels":[],"label_agreement":null},{"id":"W4303650241","doi":"10.1007/s00180-022-01286-5","title":"Pretest and shrinkage estimators for log-normal means","year":2022,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Estimator; Pooling; Mathematics; Homogeneity (statistics); Shrinkage; Statistics; Population; Applied mathematics; Shrinkage estimator; Asymptotic analysis; Econometrics; Computer science; Artificial intelligence; Efficient estimator; Medicine","score_opus":0.017163725475393066,"score_gpt":0.2767689234488893,"score_spread":0.25960519797349624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303650241","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002961682,0.00008889105,0.9981213,0.00024727304,0.00026410233,0.00020366357,0.00044685838,0.000059779006,0.0002719168],"genre_scores_gemma":[0.062445264,0.0000015526492,0.9368053,0.0004448318,0.000032737957,0.00005549079,0.0000806123,0.0000097563325,0.00012446489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990511,0.00007806369,0.00017925599,0.00026875478,0.00024242293,0.0001804006],"domain_scores_gemma":[0.99892175,0.0007080499,0.00007408944,0.00012735293,0.00008468264,0.000084075764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030609482,0.0001003494,0.00011926859,0.00005779081,0.000406466,0.00008759823,0.00029090134,0.000018076307,0.000021309703],"category_scores_gemma":[0.00007065921,0.000109003704,0.00002379003,0.00012569733,0.000045169443,0.000109873625,0.00025800322,0.000105514526,0.0000018012134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048362463,0.000026413483,0.00011617785,0.000018436382,0.00001055203,0.000008710363,0.00028740457,0.023257604,0.0000056583444,0.9108442,0.0049912785,0.060428705],"study_design_scores_gemma":[0.00019836678,0.0000848377,0.0012225861,0.0000013822444,0.000005171347,0.000028195498,0.0000040101663,0.59289265,0.000003910262,0.40258604,0.0028827982,0.00009008493],"about_ca_topic_score_codex":0.000003903168,"about_ca_topic_score_gemma":9.62998e-7,"teacher_disagreement_score":0.56963503,"about_ca_system_score_codex":0.000034203225,"about_ca_system_score_gemma":0.00009777107,"threshold_uncertainty_score":0.4445042},"labels":[],"label_agreement":null},{"id":"W4306820107","doi":"10.48550/arxiv.2210.08385","title":"A Joint Modeling Approach for Clustering Mixed-Type Multivariate Longitudinal Data: Application to the CHILD Cohort Study","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multivariate statistics; Categorical variable; Cluster analysis; Longitudinal study; Cohort; Markov chain Monte Carlo; Statistics; Multivariate analysis; Computer science; Cluster (spacecraft); Mixed model; Data mining; Monte Carlo method; Mathematics","score_opus":0.1838334589808447,"score_gpt":0.2604311135505951,"score_spread":0.07659765456975043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306820107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012046746,0.000041308682,0.9826077,0.00015313817,0.0006799087,0.0037301315,0.000047708792,0.00016691774,0.0005264051],"genre_scores_gemma":[0.78438985,0.000015275436,0.21505456,0.00009016323,0.000146633,0.000051703122,0.00010243073,0.000026377416,0.0001230232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99638915,0.00036597022,0.00030965643,0.0023652795,0.00018086925,0.00038905442],"domain_scores_gemma":[0.99542737,0.00007621319,0.00023307909,0.0039469395,0.00017115295,0.00014525029],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002275754,0.0003580575,0.00044934393,0.00020745532,0.0006622978,0.00021121954,0.004541142,0.00017337574,0.0000033344566],"category_scores_gemma":[0.00005992162,0.00033220608,0.00014702344,0.00068306626,0.000023999537,0.00031633698,0.011118781,0.0009282393,0.0000047366193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004971558,0.00023469448,0.0009838875,0.000047000452,0.00017970074,0.000010780209,0.00039675873,0.97357327,0.0000052179616,0.022742897,0.000074683485,0.0017013863],"study_design_scores_gemma":[0.00034585886,0.000077076744,0.0012311948,0.000015582806,0.00017267914,0.000004467322,0.00013493629,0.9925899,0.0000028544953,0.0048305565,0.00021351303,0.00038138393],"about_ca_topic_score_codex":0.0004888672,"about_ca_topic_score_gemma":0.00009111539,"teacher_disagreement_score":0.7723431,"about_ca_system_score_codex":0.00021112656,"about_ca_system_score_gemma":0.00012249117,"threshold_uncertainty_score":0.999913},"labels":[],"label_agreement":null},{"id":"W4307734616","doi":"10.1111/rssb.12546","title":"Dimension-Free Mixing for High-Dimensional Bayesian Variable Selection","year":2022,"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":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Science and Engineering Research Board; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain Monte Carlo; Mixing (physics); Markov chain; Algorithm; Computer science; Bayesian probability; Mathematics; Rate of convergence; Applied mathematics; Mathematical optimization; Dimension (graph theory); Offset (computer science); Convergence (economics); Statistical physics; Artificial intelligence; Machine learning; Combinatorics","score_opus":0.028506472820216653,"score_gpt":0.28787135126117397,"score_spread":0.2593648784409573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307734616","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001414061,0.00011265052,0.991863,0.004477847,0.0025791246,0.00032934215,0.00037011236,0.000043919597,0.00008256179],"genre_scores_gemma":[0.0044663874,0.0000033225112,0.99254936,0.0020677396,0.0003198327,0.000042753614,0.000009070185,0.000033710225,0.00050783495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939325,0.0029736548,0.0009912248,0.00051033765,0.0009135326,0.0006787408],"domain_scores_gemma":[0.99035096,0.007834334,0.0006029918,0.0005008347,0.00040112564,0.00030972506],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0062217913,0.00031246035,0.00077160995,0.000055489894,0.0013621819,0.00011845393,0.0015324068,0.0001660983,0.00042743416],"category_scores_gemma":[0.005731945,0.00022615126,0.0003375318,0.000494553,0.00034206247,0.00022158869,0.0011592002,0.0011822501,0.0000013025419],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029608922,0.00013398184,0.00002329142,0.000044559096,0.0001771785,0.000022811257,0.00019399806,0.0030948014,0.00062718225,0.91446286,0.067543656,0.013379602],"study_design_scores_gemma":[0.0009822171,0.0010080074,0.000525427,0.000016125101,0.00016859318,0.0004011592,0.00004298638,0.14547287,0.000347707,0.84567785,0.00508792,0.00026915796],"about_ca_topic_score_codex":0.000059149832,"about_ca_topic_score_gemma":0.000003285846,"teacher_disagreement_score":0.14237808,"about_ca_system_score_codex":0.0002967721,"about_ca_system_score_gemma":0.00043312545,"threshold_uncertainty_score":0.9999379},"labels":[],"label_agreement":null},{"id":"W4308298782","doi":"10.1111/coin.12558","title":"Hierarchical Dirichlet and Pitman–Yor process mixtures of shifted‐scaled Dirichlet distributions for proportional data modeling","year":2022,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Hierarchical Dirichlet process; Dirichlet distribution; Dirichlet process; Computer science; Latent Dirichlet allocation; Inference; Cluster analysis; Model selection; Mixture model; Artificial intelligence; Mathematics; Algorithm; Topic model; Pattern recognition (psychology); Data mining","score_opus":0.07561757794380095,"score_gpt":0.35869497653702404,"score_spread":0.2830773985932231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308298782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045217695,0.00068825996,0.9913218,0.0020554818,0.00016635924,0.00045537876,0.00066771696,0.00006465957,0.000058574788],"genre_scores_gemma":[0.5405857,0.000011412925,0.45861906,0.0001769038,0.000047409758,0.00010303085,0.0004265217,0.000008238622,0.000021724505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778396,0.00014825285,0.0005291186,0.00071453914,0.0005576376,0.0002664634],"domain_scores_gemma":[0.9983373,0.0005588319,0.00017928214,0.00047719633,0.0003274404,0.00011993905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008630792,0.00017489164,0.00024933202,0.00012941637,0.00046879688,0.00007942084,0.0013845686,0.000046323647,0.000023872006],"category_scores_gemma":[0.00017897431,0.00016828746,0.000066572065,0.0004381212,0.00014570702,0.00036430926,0.0009730397,0.0002635041,9.3655444e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005231674,0.00026408106,0.0000872575,0.00009076478,0.00004317249,0.0000048363004,0.0005091627,0.15869053,0.000048343692,0.801046,0.0006052377,0.038558256],"study_design_scores_gemma":[0.0000725267,0.000061354585,0.00006851125,0.000009758436,0.000009685739,0.000026218504,0.000011606966,0.5814288,0.00010127779,0.41787502,0.00021927904,0.00011596373],"about_ca_topic_score_codex":0.0000068327663,"about_ca_topic_score_gemma":9.947273e-7,"teacher_disagreement_score":0.5360639,"about_ca_system_score_codex":0.000036943995,"about_ca_system_score_gemma":0.0002999123,"threshold_uncertainty_score":0.68625635},"labels":[],"label_agreement":null},{"id":"W4309346662","doi":"10.1007/s11634-022-00526-2","title":"A dual subspace parsimonious mixture of matrix normal distributions","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Identifiability; Subspace topology; Dual (grammatical number); Set (abstract data type); Covariance matrix; Cluster analysis; Algorithm; Principal component analysis; Computer science; Matrix (chemical analysis); Covariance; Mathematics; Column (typography); Pattern recognition (psychology); Mathematical optimization; Data mining; Applied mathematics; Artificial intelligence; Statistics","score_opus":0.023172619704976628,"score_gpt":0.3273198306380522,"score_spread":0.30414721093307556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309346662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00386551,0.0029818006,0.99157286,0.0009016966,0.0000532479,0.00006938912,0.00035264666,0.000016110356,0.00018673616],"genre_scores_gemma":[0.8385336,0.0009306381,0.1597092,0.000023921632,0.000013127471,0.000022858936,0.00069598196,0.0000027058484,0.00006798015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874014,0.00019230042,0.0002675198,0.00044426403,0.00021867304,0.00013708773],"domain_scores_gemma":[0.9985855,0.00008779094,0.00019234867,0.0010591741,0.00003564835,0.00003949555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064630574,0.000082122075,0.00020509206,0.00019672603,0.0001543742,0.000037361056,0.0007462246,0.000026729193,0.000015374366],"category_scores_gemma":[0.0000388962,0.0000779227,0.000046683304,0.0018362268,0.00005077658,0.0007702144,0.0005376408,0.00013710125,4.793905e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029935763,0.0003683829,0.034857206,0.000037144477,0.00021696386,0.000011462626,0.0006199892,0.0012826481,0.002421475,0.637034,0.00083387253,0.32228693],"study_design_scores_gemma":[0.0004537415,0.000067250476,0.06779222,0.000008147104,0.00042634143,0.000015230001,0.00033661257,0.84996057,0.00037031175,0.027484644,0.052725233,0.00035969733],"about_ca_topic_score_codex":0.000028340924,"about_ca_topic_score_gemma":0.00020255511,"teacher_disagreement_score":0.84867793,"about_ca_system_score_codex":0.000028340008,"about_ca_system_score_gemma":0.00003222933,"threshold_uncertainty_score":0.31775954},"labels":[],"label_agreement":null},{"id":"W4311034063","doi":"10.1145/3550469.3555388","title":"Marginal Multiple Importance Sampling","year":2022,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Sampling (signal processing); Marginal distribution; Probability density function; Importance sampling; Computer science; Mathematics; Conditional probability distribution; Algorithm; Mathematical optimization; Applied mathematics; Statistics; Random variable; Monte Carlo method","score_opus":0.036672471781799526,"score_gpt":0.27599568954676706,"score_spread":0.23932321776496754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311034063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022741794,0.000105329455,0.9851933,0.00082163286,0.0002679236,0.00006534804,0.0000015408825,0.00013776335,0.011132958],"genre_scores_gemma":[0.21294948,0.0000016399417,0.7847264,0.0010788676,0.000029867773,0.000021282287,9.136377e-7,0.000004162893,0.0011874192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919283,0.00006243366,0.00011160821,0.00026229591,0.00018236555,0.0001884588],"domain_scores_gemma":[0.99946123,0.000064270615,0.000035371457,0.000370773,0.000014297626,0.00005405897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004135944,0.00006490292,0.00007917145,0.000039637107,0.00023028128,0.000046024503,0.0006025688,0.000011414687,0.00025469603],"category_scores_gemma":[0.000014427808,0.000059895436,0.0000429189,0.00021831921,0.00000845566,0.00014542733,0.00041339349,0.00013512478,0.000008766713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004782154,0.000045022218,0.0034363961,0.000003675675,0.0000065762138,0.000024470964,0.0002701505,0.00016464881,0.0015044094,0.8523113,0.0035009908,0.13872756],"study_design_scores_gemma":[0.00084095675,0.00016236112,0.006416855,0.0000037376824,0.0000056034996,0.00021151688,0.00006932782,0.43360558,0.0015615148,0.31183589,0.24465269,0.0006339474],"about_ca_topic_score_codex":0.000014654057,"about_ca_topic_score_gemma":0.0000042842894,"teacher_disagreement_score":0.5404754,"about_ca_system_score_codex":0.000030078643,"about_ca_system_score_gemma":0.000035346715,"threshold_uncertainty_score":0.2788743},"labels":[],"label_agreement":null},{"id":"W4312072439","doi":"10.1214/22-aos2229","title":"Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations","year":2022,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Estimator; Minimax; Applied mathematics; Context (archaeology); Matrix (chemical analysis); Combinatorics; Multinomial distribution; Matrix norm; Statistics; Eigenvalues and eigenvectors; Mathematical optimization","score_opus":0.06472341957351041,"score_gpt":0.3489276257576649,"score_spread":0.2842042061841545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312072439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059113987,0.00024824945,0.9902484,0.0027200114,0.000028067698,0.00035245926,0.00036586032,0.00000886659,0.00011673209],"genre_scores_gemma":[0.7178592,0.00004206205,0.28183734,0.00008593012,0.0000053168064,0.00010063077,0.000016409982,0.0000025877234,0.000050524905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991515,0.000103683946,0.00027784752,0.00015126773,0.00018337072,0.00013227794],"domain_scores_gemma":[0.9992439,0.000191225,0.00010914862,0.00031385597,0.00009367025,0.000048198253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037624448,0.000066482455,0.00013198359,0.000059732844,0.00013138239,0.000017995357,0.00031264577,0.000014287111,0.000005632356],"category_scores_gemma":[0.00004810769,0.000058965048,0.000019657924,0.00036384206,0.000025225083,0.00011153685,0.0001946242,0.00008017996,5.312359e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002783563,0.000045089335,0.000011701484,0.00001981763,0.0000056473386,4.999398e-7,0.0007410827,0.02280748,0.00007549208,0.9376302,0.00015015554,0.038510077],"study_design_scores_gemma":[0.0000863304,0.00004921125,0.0008732511,0.000010521379,0.000007326214,0.0000012629954,0.000035639427,0.38813832,0.0005314849,0.60981673,0.0003880428,0.00006190248],"about_ca_topic_score_codex":0.000048534563,"about_ca_topic_score_gemma":0.000029898692,"teacher_disagreement_score":0.7119478,"about_ca_system_score_codex":0.000021719068,"about_ca_system_score_gemma":0.000049195492,"threshold_uncertainty_score":0.24045248},"labels":[],"label_agreement":null},{"id":"W4312384497","doi":"10.1007/978-3-031-06784-6_13","title":"Bayesian Computation Methods","year":2022,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Prior probability; Conjugate prior; Bayesian probability; Computer science; Markov chain; Posterior probability; Mathematics; Computation; Markov chain Monte Carlo; Algorithm; Artificial intelligence; Machine learning","score_opus":0.09987620520094698,"score_gpt":0.371740452115156,"score_spread":0.271864246914209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312384497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.319291e-7,0.00086207327,0.712255,0.0019294411,0.00094866264,0.00020804873,0.000052739677,0.000060633716,0.28368297],"genre_scores_gemma":[0.00011572399,0.00034776347,0.9872476,0.0007845632,0.00014055661,0.000017525734,0.000064424705,0.00001857168,0.011263304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99659914,0.0005298783,0.00044309048,0.0012311486,0.0008132054,0.00038356212],"domain_scores_gemma":[0.99678266,0.0005015222,0.00028916326,0.0023399792,0.00003118872,0.000055472152],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008529336,0.0003233423,0.00036657078,0.00030167607,0.0006094042,0.000599784,0.010994155,0.0001178077,0.00016129095],"category_scores_gemma":[0.000102487924,0.0002329077,0.00007344908,0.00039492146,0.00058560073,0.0018607691,0.004284241,0.0006480821,0.000012624976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019781667,0.0000073866413,0.000001937054,0.000012341113,0.000007728782,0.000022246064,0.0005716377,0.000037288522,0.0000047865274,0.8192963,0.0014127223,0.17862366],"study_design_scores_gemma":[0.00005202406,0.00008375073,0.000016105883,0.000033366956,0.000012721225,0.00006838511,0.00004113932,0.015646784,0.000011412004,0.55858,0.4251316,0.00032270324],"about_ca_topic_score_codex":0.00005038725,"about_ca_topic_score_gemma":0.000053858723,"teacher_disagreement_score":0.42371887,"about_ca_system_score_codex":0.00004913205,"about_ca_system_score_gemma":0.0002439328,"threshold_uncertainty_score":0.9943568},"labels":[],"label_agreement":null},{"id":"W4313564007","doi":"10.1109/icit48603.2022.10002790","title":"Multivariate Beta Dirichlet Process-based Hidden Markov Models Applied to Medical Applications","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Industrial Technology (ICIT)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Dirichlet process; Computer science; Hierarchical Dirichlet process; Multivariate statistics; Artificial intelligence; Dirichlet distribution; Cluster analysis; Nonparametric statistics; Inference; Pattern recognition (psychology); Machine learning; Beta distribution; Data mining; Latent Dirichlet allocation; Mathematics; Topic model; Statistics","score_opus":0.08514358041628443,"score_gpt":0.3447798478374638,"score_spread":0.25963626742117935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313564007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018831205,0.000010265041,0.9452496,0.03277244,0.0011555493,0.0010345249,0.00011583034,0.00052599295,0.017252674],"genre_scores_gemma":[0.9394693,0.0000058327078,0.05237147,0.003421528,0.00037102646,0.0036692529,0.000058163936,0.00003493756,0.0005985001],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961799,0.00017915947,0.00061215437,0.0010995232,0.0014421381,0.0004871753],"domain_scores_gemma":[0.99811524,0.00018624401,0.00028196143,0.000887948,0.00024846435,0.0002801643],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009935152,0.0003322331,0.0004039328,0.0010067004,0.00040387397,0.00012650999,0.0045965062,0.00046171792,0.0010788678],"category_scores_gemma":[0.00016943637,0.0003402683,0.00010078587,0.001517738,0.00014160364,0.00016988025,0.00083538657,0.0016785255,0.00006103762],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009994322,0.00024311648,0.000025635642,0.000002874521,0.000056707155,0.000022422711,0.000083315215,0.0006045942,0.0010676808,0.8128603,0.0025358403,0.18239757],"study_design_scores_gemma":[0.003078375,0.00048494714,0.000012404175,0.0000559413,0.000029634597,0.000042207295,0.00016638798,0.47794732,0.008254072,0.49299794,0.01604316,0.0008876152],"about_ca_topic_score_codex":0.000030312147,"about_ca_topic_score_gemma":0.000007871672,"teacher_disagreement_score":0.9375862,"about_ca_system_score_codex":0.00029187722,"about_ca_system_score_gemma":0.0009856283,"threshold_uncertainty_score":0.99990493},"labels":[],"label_agreement":null},{"id":"W4313564081","doi":"10.1109/icit48603.2022.10002736","title":"Fully Bayesian Libby-Novick Beta Mixture Model with Feature Selection","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Industrial Technology (ICIT)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"BETA (programming language); Feature selection; Bayesian probability; Artificial intelligence; Computer science; Feature (linguistics); Pattern recognition (psychology); Model selection; Selection (genetic algorithm); Philosophy","score_opus":0.054423901566103175,"score_gpt":0.29096666434218216,"score_spread":0.236542762776079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313564081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065955753,0.000025960406,0.9400232,0.03965907,0.0018128952,0.0004797448,0.000080441365,0.0006109861,0.01071213],"genre_scores_gemma":[0.8957037,0.000020314472,0.09374267,0.0015420902,0.000492249,0.0003999526,0.00004938075,0.00005030244,0.007999363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968739,0.00021676699,0.0003862431,0.001058404,0.0009479246,0.0005167314],"domain_scores_gemma":[0.9984841,0.00006490351,0.00034377244,0.0006907066,0.00029664327,0.0001199076],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005233867,0.00040482567,0.00039891936,0.0009539622,0.0005171521,0.00020667518,0.0027473401,0.0005917371,0.0003767078],"category_scores_gemma":[0.000056578418,0.0003738431,0.00011769239,0.0014780912,0.00014596852,0.00037226788,0.0005208683,0.0028364875,0.000016556889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002602839,0.00020299647,0.00031370312,0.0000031051297,0.00015387988,0.000072365474,0.00015554395,0.0026416867,0.005436953,0.9097734,0.022084987,0.058901105],"study_design_scores_gemma":[0.003056343,0.0018478985,0.00002732246,0.00007851889,0.000055082495,0.000493031,0.00017894778,0.74141246,0.014396086,0.21467862,0.022709945,0.0010657364],"about_ca_topic_score_codex":0.000023785557,"about_ca_topic_score_gemma":0.00003280499,"teacher_disagreement_score":0.8891081,"about_ca_system_score_codex":0.0003898463,"about_ca_system_score_gemma":0.00065007363,"threshold_uncertainty_score":0.9998714},"labels":[],"label_agreement":null},{"id":"W4313564281","doi":"10.1109/icit48603.2022.10002752","title":"Bayesian Model and Feature Selection in Asymmetric Generalized Gaussian Mixtures","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Industrial Technology (ICIT)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Feature selection; Computer science; Gaussian process; Bayesian probability; Gaussian; Artificial intelligence; Selection (genetic algorithm); Model selection; Pattern recognition (psychology); Feature (linguistics); Machine learning; Algorithm; Chemistry","score_opus":0.06199279767613432,"score_gpt":0.3106579513614001,"score_spread":0.24866515368526582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313564281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032042798,0.00011205348,0.9309235,0.025457924,0.0017962031,0.00052325596,0.00005043275,0.00034319432,0.008750624],"genre_scores_gemma":[0.95485455,0.00006214404,0.042299233,0.0007519894,0.00017855057,0.0002288759,0.00001358953,0.000020178586,0.0015908639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976048,0.00026828423,0.00037319533,0.00081153866,0.000552537,0.00038968492],"domain_scores_gemma":[0.9992133,0.00006863732,0.00021579476,0.00032181584,0.000095512805,0.00008495514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064277055,0.00027746925,0.00033781107,0.0019918962,0.00027078026,0.00014323834,0.0014219582,0.0004533259,0.000116112846],"category_scores_gemma":[0.00013632982,0.0002824234,0.00007183529,0.0018782945,0.000092019356,0.0002427633,0.00044978445,0.0018334853,0.0000035305795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113201735,0.00013229219,0.0006696174,0.0000022248996,0.000048506645,0.000045577155,0.00012130026,0.0015290935,0.007869242,0.87832725,0.0053724847,0.105769195],"study_design_scores_gemma":[0.0019202334,0.0003386628,0.000085614156,0.00002414348,0.00001055355,0.000118433716,0.000054088552,0.7137913,0.0044930335,0.27677158,0.001993371,0.000398995],"about_ca_topic_score_codex":0.00006489953,"about_ca_topic_score_gemma":0.000043889362,"teacher_disagreement_score":0.92281175,"about_ca_system_score_codex":0.00031877504,"about_ca_system_score_gemma":0.00026301324,"threshold_uncertainty_score":0.9999628},"labels":[],"label_agreement":null},{"id":"W4313595020","doi":"10.1007/s11634-022-00532-4","title":"Flexible mixture regression with the generalized hyperbolic distribution","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Covariate; Component (thermodynamics); Flexibility (engineering); Generalized additive model; Mathematics; Computer science; Generalized linear model; Regression; Regression analysis; Variable (mathematics); Mixture distribution; Set (abstract data type); Mathematical optimization; Applied mathematics; Algorithm; Statistics; Artificial intelligence; Random variable","score_opus":0.039099777819178984,"score_gpt":0.3375096525388514,"score_spread":0.2984098747196724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313595020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003229025,0.001537202,0.9905525,0.0043131486,0.00003512985,0.000087133354,0.00003919507,0.00006710374,0.00013959418],"genre_scores_gemma":[0.8519482,0.011987506,0.13192941,0.0002808451,0.00008830884,0.000070736976,0.0030723053,0.000010885566,0.00061182416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988252,0.00015971129,0.00015988687,0.00050498446,0.0001943542,0.0001558942],"domain_scores_gemma":[0.9984569,0.00008851672,0.00011555368,0.0012662115,0.00003628891,0.000036513222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006800695,0.00010044579,0.00016918576,0.00012474587,0.00015908049,0.000117386204,0.0007781711,0.000044264674,0.0000024072258],"category_scores_gemma":[0.000032411706,0.000054269087,0.000027691189,0.002893465,0.0000592595,0.0009098543,0.00020852132,0.00009941906,0.0000029594457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023421122,0.000039978982,0.005318692,0.000017065431,0.0000966321,0.0000045188276,0.00023778854,0.00039530863,0.0016319915,0.18125899,0.003394098,0.80758154],"study_design_scores_gemma":[0.00026125915,0.000017095625,0.050201546,0.000021182495,0.00016112096,0.0000029548937,0.00006673606,0.8712477,0.0003737993,0.01176464,0.065702826,0.00017911626],"about_ca_topic_score_codex":0.000013699005,"about_ca_topic_score_gemma":0.00017426432,"teacher_disagreement_score":0.8708524,"about_ca_system_score_codex":0.000014738471,"about_ca_system_score_gemma":0.00001755279,"threshold_uncertainty_score":0.22130291},"labels":[],"label_agreement":null},{"id":"W4313890093","doi":"10.3390/math11020334","title":"Generalised Additive Modelling of Auto Insurance Data with Territory Design: A Rate Regulation Perspective","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Consistency (knowledge bases); Cluster analysis; Actuarial science; Set (abstract data type); Construct (python library); Econometrics; Work (physics); Computer science; Economics; Engineering; Machine learning; Artificial intelligence","score_opus":0.11896591998561576,"score_gpt":0.30129311033893896,"score_spread":0.1823271903533232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313890093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018434812,0.000032651806,0.9968236,0.00019781134,0.00006462265,0.0002494178,0.000040188814,0.00014872651,0.0005995008],"genre_scores_gemma":[0.08222665,0.000016768972,0.91737354,0.000030641855,0.000045509194,0.000015463265,0.000012198495,0.000015769947,0.00026345535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888384,0.00014680556,0.00022266274,0.00034383667,0.00022892542,0.00017389793],"domain_scores_gemma":[0.998397,0.00025391355,0.00017605418,0.0009743245,0.00015513544,0.00004358114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000858557,0.00012774514,0.00022182547,0.00010366011,0.00006729094,0.000049972205,0.0007126704,0.000048663856,0.0000033332417],"category_scores_gemma":[0.00005014088,0.00010104414,0.000026669988,0.00043500497,0.000050465213,0.00042287167,0.00019495108,0.0000822156,0.000008197804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060499875,0.00031242534,0.000015820155,0.00034332628,0.00023390616,0.000057345915,0.046647903,0.1470242,0.00903373,0.7683565,0.0061720023,0.021742314],"study_design_scores_gemma":[0.00016997076,0.000035696325,0.00006007827,0.00008720741,0.00000968765,0.000004561445,0.00008840803,0.8403471,0.002583985,0.15646547,0.000036832767,0.00011096075],"about_ca_topic_score_codex":0.0000146411385,"about_ca_topic_score_gemma":0.0000022636184,"teacher_disagreement_score":0.69332296,"about_ca_system_score_codex":0.000032754226,"about_ca_system_score_gemma":0.000086467444,"threshold_uncertainty_score":0.41204605},"labels":[],"label_agreement":null},{"id":"W4317040236","doi":"10.54932/uxsg1990","title":"Score-type tests for normal mixtures","year":2023,"lang":"en","type":"report","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Ministerio de Ciencia e Innovación","keywords":"Mathematics; Null (SQL); Heteroscedasticity; Null hypothesis; Score test; Asymptotic distribution; Likelihood-ratio test; Applied mathematics; Statistics; Statistical hypothesis testing; Null distribution; Function (biology); Asymptotic analysis; Likelihood function; Econometrics; Maximum likelihood; Test statistic; Computer science; Estimator","score_opus":0.16857666945773378,"score_gpt":0.39860909707744463,"score_spread":0.23003242761971085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317040236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000062782487,0.0007128993,0.88830966,0.0003817105,0.006487112,0.00047435422,0.000018833673,0.00057254324,0.10303658],"genre_scores_gemma":[0.00016116614,0.0005045529,0.83172774,0.00043347722,0.0013883726,0.00007619326,0.000051112358,0.000070932336,0.16558647],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974269,0.00005792721,0.00042684318,0.0008301532,0.0007089977,0.0005491235],"domain_scores_gemma":[0.9974334,0.00037725104,0.00020978966,0.0010784335,0.0007369522,0.00016414573],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014558118,0.00036699392,0.0005391553,0.00023867244,0.00012382641,0.0002390875,0.0013953428,0.0004768511,0.00002750526],"category_scores_gemma":[0.00054599746,0.00028465132,0.0002886892,0.00051434425,0.000034301745,0.00019095093,0.00045214893,0.00033121672,0.00008944995],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048147103,0.000024147013,0.000026465039,0.00023976203,0.00006509434,0.000040982995,0.000042823154,0.0000024222088,0.00010825017,0.035017442,0.73476183,0.22966598],"study_design_scores_gemma":[0.0003163488,0.00031343912,0.00055724895,0.00024616008,0.00007765781,0.00016950503,0.0000012932824,0.0045449897,0.0012708746,0.10250476,0.88891345,0.001084279],"about_ca_topic_score_codex":0.00014458838,"about_ca_topic_score_gemma":0.000071184324,"teacher_disagreement_score":0.2285817,"about_ca_system_score_codex":0.000082320075,"about_ca_system_score_gemma":0.0014817236,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W4317733154","doi":"10.1214/23-ecp511","title":"Hierarchical Dirichlet process and relative entropy","year":2023,"lang":"en","type":"article","venue":"Electronic Communications in Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Generalized Dirichlet distribution; Dirichlet process; Concentration parameter; Mathematics; Hierarchical Dirichlet process; Dirichlet distribution; Dirichlet's energy; Latent Dirichlet allocation; Dirichlet L-function; Principle of maximum entropy; Rate function; Applied mathematics; Dirichlet's principle; Statistics; Combinatorics; Mathematical analysis; Bayesian probability; Large deviations theory; Computer science; Topic model; Artificial intelligence","score_opus":0.028490539891177166,"score_gpt":0.3309609857241762,"score_spread":0.30247044583299904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317733154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05748277,0.0011995189,0.918174,0.018413968,0.00003675587,0.000647535,0.0000021955398,0.00035256712,0.0036906716],"genre_scores_gemma":[0.8288049,0.00048203842,0.17031235,0.00008898867,0.0000071268805,0.00019234013,0.000006141361,0.000006562801,0.00009953515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980914,0.00066466886,0.00027391437,0.00040688537,0.00014219907,0.00042091974],"domain_scores_gemma":[0.99724764,0.0005901909,0.00005781513,0.0019812477,0.00006109491,0.00006204041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017738383,0.000115890245,0.00017013708,0.0001279417,0.00019505076,0.000054124597,0.0015244621,0.000073517345,0.0000034896354],"category_scores_gemma":[0.00033498672,0.00010806987,0.00003602682,0.0013300034,0.00023015984,0.000355633,0.0008306401,0.0006616127,0.000010694037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003897513,0.0000833674,0.0014460454,0.00001124949,0.0000072220532,4.631546e-7,0.0012987745,0.0000070621063,0.000043363387,0.94406146,0.000032677883,0.053004388],"study_design_scores_gemma":[0.00018657127,0.000046194687,0.007014798,0.000011575607,0.0000029431528,0.000004877612,0.000007800216,0.058517836,0.000053529788,0.9321275,0.0019152459,0.000111144516],"about_ca_topic_score_codex":0.0000143715,"about_ca_topic_score_gemma":0.00011282617,"teacher_disagreement_score":0.77132213,"about_ca_system_score_codex":0.00015160437,"about_ca_system_score_gemma":0.00024071196,"threshold_uncertainty_score":0.44069615},"labels":[],"label_agreement":null},{"id":"W4319453058","doi":"10.48550/arxiv.2302.02522","title":"Prior Density Learning in Variational Bayesian Phylogenetic Parameters Inference","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Markov chain Monte Carlo; Initialization; Inference; Computer science; Bayesian inference; Markov chain; Artificial neural network; Artificial intelligence; Posterior probability; Algorithm; Bayesian probability; Mathematical optimization; Machine learning; Mathematics","score_opus":0.0884369715829856,"score_gpt":0.224003306797595,"score_spread":0.13556633521460942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319453058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110370465,0.000018052939,0.88815284,0.00014846498,0.00044320722,0.0002448975,0.0000036041858,0.00025714433,0.0003613454],"genre_scores_gemma":[0.8359686,0.000080069185,0.16295166,0.00007787022,0.000033338736,0.0000018734856,0.000009353118,0.000018655743,0.00085859286],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99728024,0.00054095633,0.0002638495,0.0013345543,0.0001355349,0.00044487498],"domain_scores_gemma":[0.99816334,0.00042544503,0.00024528446,0.0008833435,0.00011439666,0.00016817631],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007029597,0.00032613377,0.000398692,0.0004509878,0.00014530565,0.00014580165,0.0014864018,0.0003728796,0.000009529363],"category_scores_gemma":[0.00019896796,0.0003945205,0.000170528,0.0008593393,0.000077232275,0.00021290274,0.001855108,0.001047382,0.000057674122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002326427,0.00008746844,0.04098528,0.00008744332,0.000079082616,0.0006173683,0.00072546623,0.6151078,0.00007463104,0.33196864,0.00003745683,0.0102061],"study_design_scores_gemma":[0.00024127882,0.000026455984,0.034231953,0.00007495337,0.000020860047,0.0000022661748,0.000008859888,0.68149704,0.000044659566,0.2834912,0.000019325498,0.0003411279],"about_ca_topic_score_codex":0.0003297259,"about_ca_topic_score_gemma":0.00018535809,"teacher_disagreement_score":0.7255981,"about_ca_system_score_codex":0.00021200071,"about_ca_system_score_gemma":0.00039726245,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W4319945856","doi":"10.1007/s10463-023-00865-7","title":"Mixture of shifted binomial distributions for rating data","year":2023,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Categorical variable; Estimator; Expectation–maximization algorithm; Statistics; Binomial distribution; Binomial (polynomial); Ordinal data; Mixture model; Maximum likelihood; Econometrics; Applied mathematics","score_opus":0.16659196732130865,"score_gpt":0.39384389044840235,"score_spread":0.2272519231270937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319945856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00362916,0.000023799066,0.99160314,0.0016141245,0.00026491712,0.0002723584,0.0023602517,0.000025416057,0.00020685267],"genre_scores_gemma":[0.102420874,0.000012446574,0.8973867,0.000040647534,0.000028467268,0.0000069902994,0.00006511667,0.0000065182917,0.00003223012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875355,0.000045779077,0.00056363805,0.00019219462,0.00026020495,0.00018466514],"domain_scores_gemma":[0.99755263,0.0008014272,0.00033338642,0.0010412661,0.0002197841,0.000051486833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008887916,0.00010576767,0.0003409331,0.000050977495,0.00008006884,0.000018431665,0.0015069449,0.00006218014,0.0000025488653],"category_scores_gemma":[0.0023939116,0.00007249762,0.0000844263,0.00044260186,0.00025577878,0.0001979775,0.0006344771,0.000082355975,0.0000012964633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055604914,0.00008931501,0.000004050279,0.00040807115,0.000038542363,9.2098566e-7,0.00019118874,0.000023790302,0.0011134082,0.98173547,0.0056099603,0.010779703],"study_design_scores_gemma":[0.00016962634,0.000052761796,0.00014734638,0.00018046032,0.000033670607,0.0000025796496,0.000010297324,0.12890013,0.012766473,0.85694027,0.0007098164,0.00008659586],"about_ca_topic_score_codex":0.000012775651,"about_ca_topic_score_gemma":0.000005489302,"teacher_disagreement_score":0.12887634,"about_ca_system_score_codex":0.0000034884797,"about_ca_system_score_gemma":0.000120572724,"threshold_uncertainty_score":0.2956367},"labels":[],"label_agreement":null},{"id":"W4321500972","doi":"10.5539/ijsp.v12n2p1","title":"Wavelet Estimation of a Density From Observations of Almost Periodically Correlated Process Under Positive Quadrant Dependence","year":2023,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Mathematics; Wavelet; Quadrant (abdomen); Mean squared error; Rate of convergence; Upper and lower bounds; Statistics; Convergence (economics); Applied mathematics; Econometrics; Mathematical optimization; Mathematical analysis; Computer science; Artificial intelligence","score_opus":0.027625558301037006,"score_gpt":0.30454046294436593,"score_spread":0.2769149046433289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321500972","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35838383,0.000019842048,0.6407251,0.0004547424,0.000150447,0.000059195765,0.00019187371,0.0000048784996,0.00001013053],"genre_scores_gemma":[0.5926216,0.000020742367,0.40729544,0.000031964108,0.000010547866,7.62687e-7,0.000013928861,0.0000020166565,0.0000029674043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986079,0.00010908785,0.0005675941,0.00014782108,0.00048749885,0.00008013124],"domain_scores_gemma":[0.99720776,0.00055840256,0.000522376,0.00011535587,0.0015344535,0.000061625935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068802707,0.00007967873,0.00020932329,0.00008399994,0.000040262545,0.0000452676,0.00036269502,0.000051559182,0.000008052395],"category_scores_gemma":[0.0005738935,0.00006744081,0.000041552652,0.00018110967,0.000116970514,0.0002533376,0.00008613843,0.00014224397,5.0269483e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043386128,0.0006241019,0.0195498,0.00017573076,0.00055080326,0.00012731827,0.010333146,0.0085364105,0.007853783,0.6833598,0.0002491697,0.26820606],"study_design_scores_gemma":[0.0002608065,0.00008764681,0.19719249,0.000088800276,0.000018042321,0.000024880526,0.00001928194,0.22586413,0.0010933537,0.57529515,0.0000015661481,0.00005384339],"about_ca_topic_score_codex":0.000097169286,"about_ca_topic_score_gemma":0.000023176108,"teacher_disagreement_score":0.26815224,"about_ca_system_score_codex":0.000033527886,"about_ca_system_score_gemma":0.00023813723,"threshold_uncertainty_score":0.27501562},"labels":[],"label_agreement":null},{"id":"W4321505814","doi":"10.1214/22-sts877","title":"A Conversation with Mary E. Thompson","year":2023,"lang":"en","type":"article","venue":"Statistical Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"University of Waterloo; Royal Society; Royal Society of Canada","keywords":"Honour; Medal; Annals; Gold medal; Library science; Conversation; Statistician; Management; Sociology; Mathematics; History; Political science; Law; Classics; Statistics; Art history; Computer science","score_opus":0.01362446477603719,"score_gpt":0.2841100491595704,"score_spread":0.2704855843835332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321505814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001007015,0.0000037260215,0.9892286,0.001796205,0.00017803986,0.00008629791,0.0000053861236,0.0001974249,0.007497277],"genre_scores_gemma":[0.33900872,0.000002791102,0.6605273,0.0002382701,0.00001824452,0.000006466101,0.0000014071094,0.0000027177387,0.00019411261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859434,0.00004570595,0.0000916941,0.0004193852,0.0004991428,0.00034973392],"domain_scores_gemma":[0.999245,0.0002032652,0.000026476397,0.00028942456,0.00006874852,0.00016711318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009234807,0.00007249333,0.00008231632,0.00010420248,0.00017467806,0.00017211803,0.00059982843,0.000019066383,0.000031276177],"category_scores_gemma":[0.00014541077,0.00005085352,0.000009508516,0.0016446818,0.00039577976,0.0004484123,0.00016254798,0.0000769248,0.00015597274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029092953,0.000006223252,0.00009323568,0.0000040062364,8.9619397e-7,0.000030796036,0.00027134529,0.00000533226,0.0007844372,0.85621184,0.00069515075,0.14189385],"study_design_scores_gemma":[0.00033549758,0.00024003374,0.056672033,0.000022838229,0.0000055553332,0.000033917746,0.000041541356,0.49347132,0.0015520166,0.44576576,0.001553737,0.000305754],"about_ca_topic_score_codex":0.000012879957,"about_ca_topic_score_gemma":0.0000025928514,"teacher_disagreement_score":0.493466,"about_ca_system_score_codex":0.000031310046,"about_ca_system_score_gemma":0.00018081503,"threshold_uncertainty_score":0.20737463},"labels":[],"label_agreement":null},{"id":"W4353031156","doi":"10.1017/9781107588493.004","title":"Probability Distributions","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Beta-binomial distribution; Multinomial distribution; Mathematics; Inverse-chi-squared distribution; Univariate distribution; Compound probability distribution; Statistics; Negative binomial distribution; Negative multinomial distribution; Compound Poisson distribution; Gamma distribution; Heavy-tailed distribution; Distribution fitting; Probability distribution; Poisson distribution; Poisson regression","score_opus":0.05011718061385696,"score_gpt":0.22449293406582196,"score_spread":0.174375753451965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353031156","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.727678e-7,0.000017132328,0.48801032,0.000043789172,0.00022788509,0.00021877266,0.00019466146,0.00034767424,0.5109388],"genre_scores_gemma":[0.00003867975,0.000036349345,0.03661607,0.00003634514,0.000082437786,0.0000013138879,0.00003978604,0.000027497237,0.96312153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832314,0.00007583821,0.0001910078,0.0007982458,0.00027240906,0.00033936265],"domain_scores_gemma":[0.99803317,0.000111423426,0.00016143532,0.001288611,0.00018365741,0.0002216838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025604785,0.0003365112,0.00037321053,0.0001294306,0.00025651237,0.00009610913,0.0014085312,0.00037747173,0.000001314952],"category_scores_gemma":[0.00001990219,0.0003793016,0.00028784538,0.000022608196,0.00019530134,0.00015084448,0.0011238704,0.0005171332,0.000042388616],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005455224,0.000006457017,1.9534353e-7,0.000040219755,0.00004795974,0.00014749075,0.000018135746,4.3220493e-7,0.0000073719816,0.9649758,0.026115324,0.008635194],"study_design_scores_gemma":[0.00023899617,0.000035822017,0.0000144084315,0.00009632662,0.00008227913,0.000014827463,9.705014e-7,0.0006251235,0.00013286587,0.012492945,0.9857402,0.0005252709],"about_ca_topic_score_codex":0.000041963496,"about_ca_topic_score_gemma":0.0000017454577,"teacher_disagreement_score":0.9596248,"about_ca_system_score_codex":0.00019834455,"about_ca_system_score_gemma":0.00018498446,"threshold_uncertainty_score":0.9998659},"labels":[],"label_agreement":null},{"id":"W4360979829","doi":"10.1007/s11042-023-14666-w","title":"Expectation propagation learning of finite and infinite Gamma mixture models and its applications","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Flexibility (engineering); Inference; Artificial intelligence; Machine learning; Bayesian inference; Bayesian probability; Expectation propagation; Finite set; Mixture model; Statistical inference; Mathematics; Gaussian process","score_opus":0.036509788408073396,"score_gpt":0.2844256494885097,"score_spread":0.24791586108043628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360979829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057357806,0.0005950871,0.99171144,0.0005190253,0.000013409739,0.00083869224,0.00002530434,0.00014684154,0.00041444958],"genre_scores_gemma":[0.72513306,0.0016594203,0.27083144,0.00007060247,0.00010083409,0.0017789904,0.00010241058,0.000018986699,0.00030424327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901253,0.00005807551,0.00024733384,0.00038758578,0.00013337379,0.00016108397],"domain_scores_gemma":[0.99894536,0.00047609775,0.000134513,0.00021937084,0.000117347685,0.0001073417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002580216,0.00012845942,0.00016391488,0.00014284655,0.00023354488,0.000104223516,0.00014646475,0.00009130025,0.0000015607502],"category_scores_gemma":[0.000058887912,0.00012137641,0.000022711089,0.00054652296,0.000063626576,0.00045806402,0.0001291347,0.00013936787,0.000006279078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030888689,0.000028802608,0.00015403803,0.00009640802,0.0000127706435,3.880433e-7,0.002357416,0.0005480518,0.009425069,0.18069282,0.000033381966,0.8066478],"study_design_scores_gemma":[0.0003168577,0.000031134598,0.0027454619,0.000024025114,0.000017626682,0.0000052104156,0.000090226014,0.957748,0.0017939424,0.033285916,0.0037588102,0.00018277239],"about_ca_topic_score_codex":0.0000045417173,"about_ca_topic_score_gemma":0.000001597538,"teacher_disagreement_score":0.9572,"about_ca_system_score_codex":0.000006131815,"about_ca_system_score_gemma":0.000025396923,"threshold_uncertainty_score":0.49495864},"labels":[],"label_agreement":null},{"id":"W4361192899","doi":"10.48550/arxiv.2303.14211","title":"Tackling the infinite likelihood problem when fitting mixtures of shifted asymmetric Laplace distributions","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Laplace transform; Expectation–maximization algorithm; Maximization; Skewness; Laplace distribution; Scheme (mathematics); Applied mathematics; Estimation theory; Laplace's method; Mathematical optimization; Cluster analysis; Mixture model; Mathematics; Bayesian probability; Maximum likelihood; Computer science; Algorithm; Statistics; Mathematical analysis","score_opus":0.060133658896701164,"score_gpt":0.2159721085521187,"score_spread":0.15583844965541754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361192899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013568376,0.0002193401,0.9824106,0.0006359161,0.0004733426,0.0004637246,0.00008669594,0.00032745302,0.0018145255],"genre_scores_gemma":[0.84033775,0.00019721428,0.15825374,0.00008491245,0.000104882034,0.0000039956603,0.00003924719,0.000030603613,0.00094762974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99736655,0.00048642798,0.00040765433,0.0010365222,0.00017667038,0.0005261479],"domain_scores_gemma":[0.9966611,0.0008005473,0.0005624436,0.0015240762,0.00029439002,0.00015739693],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012586255,0.00036703647,0.00046267835,0.00045778556,0.00032708465,0.00017795451,0.0026984315,0.0003696907,0.00000645556],"category_scores_gemma":[0.00021646028,0.00032237376,0.0003537564,0.00210752,0.00013607038,0.0002646524,0.0029878882,0.0010352987,0.000029715873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026009004,0.00014755585,0.0017645196,0.00031851404,0.0003476801,0.00014670794,0.0014617253,0.020105027,0.00006619458,0.9592892,0.0020898224,0.014237064],"study_design_scores_gemma":[0.00035214316,0.000047235346,0.00092318485,0.00028378272,0.0001494061,0.0000042078364,0.000046250185,0.28918198,0.00046804015,0.7076024,0.000477232,0.00046416125],"about_ca_topic_score_codex":0.0002981145,"about_ca_topic_score_gemma":0.000039503986,"teacher_disagreement_score":0.8267694,"about_ca_system_score_codex":0.000119457116,"about_ca_system_score_gemma":0.00030234328,"threshold_uncertainty_score":0.9999228},"labels":[],"label_agreement":null},{"id":"W4366082911","doi":"10.1111/biom.13870","title":"Sparse Estimation in Semiparametric Finite Mixture of Varying Coefficient Regression Models","year":2023,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; University of Nevada, Las Vegas","keywords":"Covariate; Parametric statistics; Mathematics; Statistics; Regression analysis; Sample size determination; Regression; Feature selection; Computer science; Artificial intelligence","score_opus":0.05419783994451265,"score_gpt":0.3119173921996076,"score_spread":0.25771955225509496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366082911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012781884,0.0006582475,0.9850953,0.00014337558,0.00039489515,0.00018632997,0.000007665099,0.00013866123,0.0005936187],"genre_scores_gemma":[0.5400022,0.00012199473,0.45970306,0.00004425333,0.00001159133,0.000007430321,0.000008743025,0.000009190011,0.00009150922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998222,0.0001290854,0.00040200254,0.00040037677,0.00052245654,0.00032410235],"domain_scores_gemma":[0.99832857,0.0007356571,0.0001946021,0.0005371772,0.000113112466,0.000090904425],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0013455608,0.00015293898,0.0002693809,0.005978226,0.000054302087,0.000060936516,0.0006104608,0.00016241998,0.00000223869],"category_scores_gemma":[0.0008233938,0.00012913525,0.000074302574,0.035183627,0.000029020595,0.0003307815,0.0002796744,0.0001590792,0.000018372097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013841775,0.00023522413,0.0003451848,0.00014743302,0.000012749904,0.000053987962,0.0012916432,0.18046674,0.0024505623,0.025541387,0.0015693835,0.78787184],"study_design_scores_gemma":[0.00027215361,0.000048488862,0.00055434956,0.00007899415,0.000004304666,0.0000029130144,0.0000046643568,0.97667813,0.0028127537,0.019261237,0.00013943984,0.00014259138],"about_ca_topic_score_codex":0.000019351171,"about_ca_topic_score_gemma":4.136772e-7,"teacher_disagreement_score":0.79621136,"about_ca_system_score_codex":0.000063162384,"about_ca_system_score_gemma":0.00006264607,"threshold_uncertainty_score":0.985324},"labels":[],"label_agreement":null},{"id":"W4367182061","doi":"10.1007/s00704-023-04419-y","title":"Statistical modelling of precipitation data in Canadian Prairies with a dynamic mixture structure","year":2023,"lang":"en","type":"article","venue":"Theoretical and Applied Climatology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Precipitation; Cluster analysis; Volatility (finance); Environmental science; Computer science; Volatility clustering; Range (aeronautics); Econometrics; Mixture model; Maximum likelihood; Statistics; Meteorology; Autoregressive conditional heteroskedasticity; Mathematics; Geography; Engineering","score_opus":0.014290459186108053,"score_gpt":0.2700686996386967,"score_spread":0.2557782404525886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367182061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07950014,0.000027096852,0.9174954,0.0018853399,0.000025844121,0.00013775716,0.00009457272,0.000032553227,0.00080125144],"genre_scores_gemma":[0.7292442,0.000013879312,0.2705724,0.00008923313,0.0000039377205,0.0000050936555,0.00006342271,0.000005805004,0.0000020931298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99889153,0.00008294586,0.00018603812,0.0003808497,0.00010165634,0.0003569742],"domain_scores_gemma":[0.9989871,0.00042971288,0.000036832887,0.00039265433,0.000019492449,0.00013423228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003327572,0.000110745845,0.00026442218,0.00012561484,0.00004565729,0.000023716397,0.0003937393,0.00011897348,0.00000875559],"category_scores_gemma":[0.000039372648,0.00008091858,0.000006497494,0.0002968377,0.0004613188,0.0000687557,0.00016671505,0.00017639466,0.0000022273148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003160395,0.0000069126913,0.0002783451,0.000040466293,0.0000062885256,0.0000139513295,0.00043462554,0.0001804461,0.000048831807,0.9916894,0.00002158544,0.0072475616],"study_design_scores_gemma":[0.00016504008,0.000027333608,0.0004836026,0.000010469381,0.0000064102715,0.00002383476,0.000022865002,0.37732485,0.000039055274,0.62179476,0.00002657655,0.000075204334],"about_ca_topic_score_codex":0.000548321,"about_ca_topic_score_gemma":0.00887125,"teacher_disagreement_score":0.64974403,"about_ca_system_score_codex":0.000010084182,"about_ca_system_score_gemma":0.00010170308,"threshold_uncertainty_score":0.49503654},"labels":[],"label_agreement":null},{"id":"W4367319399","doi":"10.1016/j.eswa.2023.120262","title":"A context-enhanced Dirichlet model for online clustering in short text streams","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cluster analysis; Latent Dirichlet allocation; Inference; Data mining; Artificial intelligence; Topic model; Exploit; Machine learning","score_opus":0.042790149101430225,"score_gpt":0.3247153135910042,"score_spread":0.28192516448957394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367319399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011380601,0.00028176082,0.99557596,0.00048338916,0.000074944575,0.0017653839,0.000035334593,0.0003285561,0.00031662625],"genre_scores_gemma":[0.6257473,0.000029595796,0.36579046,0.00019329073,0.00011997033,0.007028979,0.000038127502,0.000027318767,0.0010249432],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985672,0.000039897008,0.0003361586,0.0005422138,0.00017277886,0.0003416985],"domain_scores_gemma":[0.9988883,0.00012885335,0.000050319326,0.00073263474,0.00009396065,0.00010594341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028214068,0.00016237711,0.0002747151,0.00013734146,0.00013670385,0.0001286012,0.0005719742,0.00007810845,5.5821397e-7],"category_scores_gemma":[0.000010007434,0.00014296056,0.000048050115,0.00071992504,0.000026550633,0.00019965558,0.00010444951,0.00009261362,0.000009746124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050255847,0.00052737974,0.00013200036,0.00026906832,0.000092084265,0.000008572695,0.011587258,0.07083287,0.014771814,0.12740621,0.009378562,0.7649439],"study_design_scores_gemma":[0.00032147978,0.000029697982,0.000042081207,0.00007079288,0.0000025813142,0.000005906537,0.00018139616,0.99254215,0.0001796785,0.0011078642,0.0053189406,0.0001974247],"about_ca_topic_score_codex":0.0002065597,"about_ca_topic_score_gemma":0.0008009969,"teacher_disagreement_score":0.9217093,"about_ca_system_score_codex":0.000062696796,"about_ca_system_score_gemma":0.000077430326,"threshold_uncertainty_score":0.5829763},"labels":[],"label_agreement":null},{"id":"W4376255225","doi":"10.1007/s11634-023-00542-w","title":"Model-based clustering of functional data via mixtures of t distributions","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Cluster analysis; Multivariate statistics; Mixture model; Computer science; Functional data analysis; Data mining; Expectation–maximization algorithm; Multivariate normal distribution; Mathematics; Pattern recognition (psychology); Artificial intelligence; Statistics; Machine learning; Maximum likelihood","score_opus":0.09709102288779793,"score_gpt":0.3592540555855143,"score_spread":0.2621630326977164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376255225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004974793,0.0005203408,0.9979611,0.00031598404,0.000037845657,0.00004857881,0.0005304995,0.000019244691,0.00006894475],"genre_scores_gemma":[0.69298977,0.0004966792,0.30325118,0.000012450278,0.000009296819,0.0000051626917,0.0032220539,0.0000023072246,0.000011103381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988616,0.000069636226,0.0003235128,0.00046736977,0.00017834455,0.00009951037],"domain_scores_gemma":[0.99774957,0.00013163645,0.00018631945,0.0018439309,0.00005971002,0.000028832923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007190524,0.0000714598,0.00019993963,0.00026534416,0.00004668143,0.00002051057,0.0010267118,0.000037074296,0.0000028849827],"category_scores_gemma":[0.000082495964,0.0000636797,0.000030738396,0.0017258943,0.00006953242,0.0009309011,0.00049261365,0.00005640831,5.5701054e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033085416,0.00021930301,0.009734415,0.00016765957,0.0002367004,0.0000013893662,0.000106713334,0.10722319,0.021126494,0.09392529,0.0006172267,0.76660854],"study_design_scores_gemma":[0.00009348555,0.000005314222,0.014002148,0.0000107902,0.000088948334,2.0509981e-7,0.000006484017,0.9751299,0.00025686427,0.010063786,0.00028119545,0.000060855164],"about_ca_topic_score_codex":0.000014611297,"about_ca_topic_score_gemma":0.00021276924,"teacher_disagreement_score":0.86790675,"about_ca_system_score_codex":0.000008898389,"about_ca_system_score_gemma":0.00003665416,"threshold_uncertainty_score":0.25967827},"labels":[],"label_agreement":null},{"id":"W4376877746","doi":"10.1007/s11749-022-00840-z","title":"Nonparametric estimation in mixture cure models with covariates","year":2023,"lang":"en","type":"article","venue":"Test","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Nonparametric statistics; Estimator; Econometrics; Statistics; Context (archaeology); Estimation; Mathematics; Economics; Geography","score_opus":0.019734207564590447,"score_gpt":0.27011770864570583,"score_spread":0.2503835010811154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376877746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032301333,0.00007161536,0.9929944,0.0011950793,0.000075044125,0.00015123532,0.0000027747242,0.00031178782,0.0019678879],"genre_scores_gemma":[0.38587293,0.000012973739,0.6137378,0.0001466708,0.000014957619,0.000017852843,0.0000046604564,0.000008307683,0.0001838133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906254,0.000045918187,0.00014006149,0.00030910235,0.00019283942,0.00024954506],"domain_scores_gemma":[0.99916023,0.00031396447,0.00004915901,0.00037555964,0.000043082975,0.000058026097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039314598,0.00011873241,0.00014861468,0.0003209817,0.00004883161,0.00009844389,0.00040142596,0.00007501769,0.000003713038],"category_scores_gemma":[0.000090306894,0.000091504524,0.00002252476,0.002698652,0.000019303605,0.00045425512,0.000084291925,0.0001582945,0.00006237767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011534935,0.00019690776,0.003169891,0.00006520062,0.00001680111,0.00017822972,0.0022056699,0.063537575,0.00047010352,0.7480049,0.00504228,0.17710093],"study_design_scores_gemma":[0.00020838797,0.000052836185,0.0031539283,0.000027482074,0.000002786184,0.000010794172,0.0000027011552,0.8087878,0.00018216642,0.18737918,0.0000753775,0.00011651978],"about_ca_topic_score_codex":0.000038100876,"about_ca_topic_score_gemma":0.000014251161,"teacher_disagreement_score":0.7452503,"about_ca_system_score_codex":0.000024134475,"about_ca_system_score_gemma":0.0000559647,"threshold_uncertainty_score":0.3731446},"labels":[],"label_agreement":null},{"id":"W4378221222","doi":"10.3390/risks11060099","title":"Estimating Territory Risk Relativity Using Generalized Linear Mixed Models and Fuzzy C-Means Clustering","year":2023,"lang":"en","type":"article","venue":"Risks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Cluster analysis; Fuzzy logic; Computer science; Set (abstract data type); Generalized linear model; Econometrics; Estimation; Fuzzy clustering; Data mining; Actuarial science; Mathematics; Economics; Artificial intelligence; Machine learning","score_opus":0.11065269454241132,"score_gpt":0.34690367362580676,"score_spread":0.23625097908339543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378221222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21716365,0.00011245685,0.78135407,0.00007807032,0.0005292869,0.0001209928,0.000006674434,0.00030973597,0.00032505384],"genre_scores_gemma":[0.21178806,0.000039562172,0.78783697,0.000044467168,0.0001932922,0.0000067388396,0.0000017718872,0.00002016218,0.000068953406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982482,0.00037803422,0.0002746497,0.00050759484,0.00021285722,0.00037866086],"domain_scores_gemma":[0.99901164,0.0001774238,0.00014760034,0.0004918392,0.00003537106,0.00013611889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012097378,0.00019369026,0.00026978503,0.00014496852,0.00036306237,0.00013077926,0.00032824618,0.00012563932,0.0000011633896],"category_scores_gemma":[0.00007885585,0.00018264525,0.00007648418,0.00032722062,0.00004763597,0.0005872625,0.00047655054,0.0003020216,0.000007823378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001245118,0.000031560245,0.0013623815,0.00008358478,0.000059181402,0.00003791211,0.0036154778,0.6698868,0.002926589,0.010453315,0.00027335776,0.31125736],"study_design_scores_gemma":[0.00030325633,0.00001670079,0.0010846816,0.00004843974,0.000017733384,0.000013170125,0.000007964271,0.92469877,0.00019326145,0.0733669,0.000043503573,0.00020561574],"about_ca_topic_score_codex":0.00052152603,"about_ca_topic_score_gemma":0.000029151142,"teacher_disagreement_score":0.31105176,"about_ca_system_score_codex":0.00003839743,"about_ca_system_score_gemma":0.00004131025,"threshold_uncertainty_score":0.7448057},"labels":[],"label_agreement":null},{"id":"W4378713334","doi":"10.48550/arxiv.2305.16464","title":"Flexible Variable Selection for Clustering and Classification","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Variable (mathematics); Skewness; Selection (genetic algorithm); Feature selection; Computer science; Mixture model; Cluster (spacecraft); Data mining; Gaussian; Transformation (genetics); Artificial intelligence; Pattern recognition (psychology); Machine learning; Mathematics; Statistics","score_opus":0.1737566016930563,"score_gpt":0.2371674064934387,"score_spread":0.06341080480038241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378713334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012358163,0.000019772759,0.996227,0.00013488035,0.00054716686,0.0003494694,0.000007474688,0.00039259176,0.0010858281],"genre_scores_gemma":[0.3312437,0.00008294783,0.6590719,0.00007156184,0.00011746556,0.0000068615745,0.000011655586,0.000025330644,0.009368517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868464,0.00008045032,0.00012395166,0.00084424665,0.000039111976,0.0002275959],"domain_scores_gemma":[0.9991207,0.00009214528,0.00013329039,0.0004558575,0.000112500806,0.00008547844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044222642,0.00016704755,0.00019173884,0.00019038872,0.00016941343,0.00014424363,0.0005029006,0.00024079699,0.0000023681112],"category_scores_gemma":[0.000028394354,0.00019920628,0.00006884137,0.00041049084,0.00002746993,0.00026126907,0.00070028455,0.00023777963,0.000009089185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014325356,0.000019630277,0.00017281741,0.00016786116,0.000040784995,0.0000032299315,0.00009351772,0.034249544,0.00040329006,0.95869696,0.00064705533,0.0054909913],"study_design_scores_gemma":[0.00014611745,0.000021026231,0.00029820862,0.00003404883,0.000023725659,0.0000017161183,0.0000053144536,0.6696231,0.0000744088,0.32911643,0.00050873606,0.00014717608],"about_ca_topic_score_codex":0.000065301116,"about_ca_topic_score_gemma":0.000023116592,"teacher_disagreement_score":0.63537353,"about_ca_system_score_codex":0.000100770914,"about_ca_system_score_gemma":0.00010906597,"threshold_uncertainty_score":0.81233966},"labels":[],"label_agreement":null},{"id":"W4379548466","doi":"10.48550/arxiv.2306.03064","title":"Directed Spatial Permutations on Asymmetric Tori","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Mathematics; Dirichlet distribution; Poisson distribution; Asymmetry; Random graph; Heuristics; Combinatorics; Statistical physics; Graph; Mathematical optimization; Boundary value problem; Statistics; Mathematical analysis; Physics","score_opus":0.1081741046824888,"score_gpt":0.22165613108001764,"score_spread":0.11348202639752884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379548466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005318708,0.000022347615,0.9829507,0.00028480025,0.0020043235,0.00026990488,0.000028869501,0.001007472,0.008112911],"genre_scores_gemma":[0.95183253,0.000102092956,0.04071101,0.00014004859,0.00021269011,0.0000023411874,0.000028108325,0.000032551485,0.0069386372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977764,0.00029061345,0.00018846546,0.001243383,0.00013832713,0.00036283044],"domain_scores_gemma":[0.9978448,0.00033943335,0.00018381514,0.0012684333,0.00016797919,0.00019551144],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003131157,0.00031445548,0.00033395915,0.0007287807,0.00019275416,0.00014627373,0.0015585452,0.0003250282,0.000015197085],"category_scores_gemma":[0.00014613527,0.00035031734,0.00024670042,0.0016561078,0.000050149305,0.00017917954,0.00122104,0.00066189974,0.00027153877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020199428,0.00013693202,0.00033793948,0.00004833706,0.00012018236,0.00054379634,0.00030550276,0.03095754,0.00001543907,0.9451096,0.00222091,0.020183634],"study_design_scores_gemma":[0.0003452792,0.000079296056,0.0044071735,0.00007317917,0.0000634663,0.0000024756714,0.00000906249,0.6652893,0.00011196726,0.32843268,0.00065884594,0.00052728644],"about_ca_topic_score_codex":0.00045905152,"about_ca_topic_score_gemma":0.00007651955,"teacher_disagreement_score":0.94651383,"about_ca_system_score_codex":0.00021391257,"about_ca_system_score_gemma":0.00020786513,"threshold_uncertainty_score":0.99989486},"labels":[],"label_agreement":null},{"id":"W4379620314","doi":"10.1145/3555776.3577650","title":"Finite Multivariate McDonald's Beta Mixture Model Learning Approach in Medical Applications","year":2023,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Generalization; Multivariate statistics; Computer science; Artificial intelligence; Expectation–maximization algorithm; Bounded function; Newton's method; Gaussian; Pattern recognition (psychology); Applied mathematics; Estimation theory; Mathematics; Algorithm; Maximum likelihood; Machine learning; Statistics; Nonlinear system","score_opus":0.03152315929536049,"score_gpt":0.3053002996401725,"score_spread":0.27377714034481204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379620314","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009097424,0.000042943735,0.9754919,0.0027076406,0.000042097243,0.00022744549,0.0000014632063,0.00044110275,0.02095446],"genre_scores_gemma":[0.08938035,0.00003964233,0.9060047,0.0007465094,0.00006797824,0.00019027243,0.000018957373,0.000016286562,0.0035352523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818647,0.00017614706,0.00026944236,0.00055260485,0.00043443442,0.00038089167],"domain_scores_gemma":[0.9990126,0.00025799926,0.000049325008,0.00045631127,0.000041099833,0.0001826686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012449541,0.00015221677,0.00020629034,0.00021766934,0.0001195225,0.00007633158,0.0009572011,0.00019199734,0.00002097937],"category_scores_gemma":[0.000068446105,0.00012622112,0.00007099199,0.0012135997,0.000035624736,0.00021791448,0.00042113036,0.00053123006,0.000091069895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025006245,0.000092653594,0.00012226553,0.000022834056,0.000012059658,0.000014433427,0.0009190307,0.054524694,0.00016727555,0.7437102,0.00088938733,0.19952266],"study_design_scores_gemma":[0.00024759947,0.0000070035667,0.0002298746,0.000009298307,0.0000022872548,0.000004899064,0.0000089318555,0.95006037,0.00003951026,0.047049176,0.0021882204,0.00015285806],"about_ca_topic_score_codex":0.00002649299,"about_ca_topic_score_gemma":0.000006734256,"teacher_disagreement_score":0.89553565,"about_ca_system_score_codex":0.000020042842,"about_ca_system_score_gemma":0.000120889265,"threshold_uncertainty_score":0.5147148},"labels":[],"label_agreement":null},{"id":"W4379878088","doi":"10.1093/biomet/asad037","title":"Interpolating discriminant functions in high-dimensional Gaussian latent mixtures","year":2023,"lang":"en","type":"article","venue":"Biometrika","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Cornell University; National Science Foundation","keywords":"Mathematics; Minimax; Hyperplane; Gaussian; Estimator; Simple (philosophy); Applied mathematics; Interpolation (computer graphics); Least-squares function approximation; Mathematical optimization; Statistics; Combinatorics; Artificial intelligence","score_opus":0.03152515681260725,"score_gpt":0.2860141994300425,"score_spread":0.25448904261743527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379878088","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06549725,0.00021464378,0.9297758,0.0021930926,0.0013544826,0.00013639803,0.000010024924,0.00024933962,0.00056898856],"genre_scores_gemma":[0.8259166,0.00000911282,0.17270234,0.00019623507,0.000093323164,0.00001887865,0.000013934613,0.00001233416,0.0010372237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998498,0.000109951725,0.00028288484,0.00043805284,0.00027426478,0.00039682264],"domain_scores_gemma":[0.99922705,0.00015587285,0.000066774584,0.00040102977,0.000033760003,0.000115522525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006586149,0.0001497829,0.00019401766,0.0016118925,0.000115084265,0.00010508861,0.00043094583,0.00008598285,0.000021246491],"category_scores_gemma":[0.00011528356,0.00011751231,0.00008118473,0.00481906,0.000034879195,0.00023113657,0.00035219692,0.00016292451,0.00015599887],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025435913,0.00025725013,0.0048328065,0.000054970733,0.000055512886,0.0002706571,0.0011876929,0.0001178399,0.04229803,0.16213167,0.015147292,0.77362084],"study_design_scores_gemma":[0.0027762712,0.0006430366,0.4022001,0.00047848295,0.00004494575,0.00011986998,0.00009623293,0.4325923,0.015380793,0.1325775,0.011273745,0.0018167312],"about_ca_topic_score_codex":0.00017982419,"about_ca_topic_score_gemma":0.000024062538,"teacher_disagreement_score":0.7718041,"about_ca_system_score_codex":0.0000565159,"about_ca_system_score_gemma":0.000046354067,"threshold_uncertainty_score":0.4792013},"labels":[],"label_agreement":null},{"id":"W4381190793","doi":"10.1111/jori.12436","title":"Improving risk classification and ratemaking using mixture‐of‐experts models with random effects","year":2023,"lang":"en","type":"article","venue":"Journal of Risk & Insurance","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Underwriting; Econometrics; Logistic regression; Profitability index; Actuarial science; Computer science; Categorization; Mixed logit; Economics; Mathematics; Statistics; Artificial intelligence; Finance","score_opus":0.019254552268925404,"score_gpt":0.2637129551929957,"score_spread":0.24445840292407028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381190793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41970044,0.0012410808,0.5786652,0.000022514161,0.0002423825,0.000090526155,0.000002163683,0.000018770888,0.000016900913],"genre_scores_gemma":[0.6690376,0.0007087944,0.33013025,0.000016570151,0.00009095472,0.0000018812481,1.0958569e-7,0.000011061028,0.0000027896563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982244,0.00045581348,0.00048318334,0.00024651515,0.0003622391,0.00022787874],"domain_scores_gemma":[0.9972982,0.00060159893,0.001313778,0.00030148888,0.00038565396,0.00009929143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017811614,0.0001674317,0.0004387258,0.0002356865,0.0001741374,0.00010535169,0.00035022432,0.000082290506,2.0504312e-7],"category_scores_gemma":[0.00035732347,0.0001160305,0.000100509635,0.0005868922,0.00006077208,0.00091781095,0.000064507236,0.00031043365,2.9997332e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077597843,0.00011182228,0.026791042,0.0003935318,0.00023529846,0.00016629734,0.006730735,0.0265559,0.075829566,0.011128626,0.000121335725,0.8511599],"study_design_scores_gemma":[0.0030122607,0.00020507301,0.030283773,0.0005985901,0.00007646039,0.00015634131,0.000053006894,0.9353194,0.0075454223,0.022452014,0.00003966332,0.00025797388],"about_ca_topic_score_codex":0.000050096296,"about_ca_topic_score_gemma":0.000004682966,"teacher_disagreement_score":0.9087635,"about_ca_system_score_codex":0.000038584538,"about_ca_system_score_gemma":0.0000894666,"threshold_uncertainty_score":0.47315863},"labels":[],"label_agreement":null},{"id":"W4382699702","doi":"10.1007/s10958-023-06534-7","title":"Estimating the Amount of Sparsity in Two-Point Mixture Models","year":2023,"lang":"en","type":"article","venue":"Journal of Mathematical Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Estimator; Minimax; Variable (mathematics); Selection (genetic algorithm); Applied mathematics; Fraction (chemistry); Model selection; Focus (optics); Minimax estimator; Mathematical optimization; Statistics; Minimum-variance unbiased estimator; Mathematical analysis; Computer science","score_opus":0.05897563886771148,"score_gpt":0.3426116625892489,"score_spread":0.2836360237215374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382699702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08286739,0.00006838793,0.9117094,0.0031434067,0.00016826723,0.00006982023,3.3002766e-7,0.000012257692,0.001960729],"genre_scores_gemma":[0.45872065,0.0000051465113,0.54114896,0.00006957612,0.000038745668,7.642505e-7,1.1762279e-8,0.0000017147433,0.00001441731],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981795,0.00018174388,0.00056337734,0.00014642374,0.0006836747,0.0002452733],"domain_scores_gemma":[0.99853176,0.00072431593,0.00036552726,0.0002122086,0.00009039,0.000075788375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071440805,0.000089570254,0.0002921836,0.00016623303,0.000110594854,0.00010153227,0.0013923579,0.000029707528,0.000009029955],"category_scores_gemma":[0.00042356135,0.00004522185,0.00010996415,0.0011100018,0.00023394056,0.00058821647,0.00022559836,0.00022381826,0.0000055122255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004716648,0.00010672392,0.00011740664,0.00006573052,0.0000113306005,0.00004022499,0.0041797743,0.02933936,0.0011033842,0.94139636,0.0005302776,0.023104718],"study_design_scores_gemma":[0.000070330585,0.000035790552,0.00011390344,0.00009133215,0.0000029667206,0.00004725482,0.000045794,0.47918752,0.0003398704,0.52002895,0.0000032269418,0.000033045493],"about_ca_topic_score_codex":0.000007409256,"about_ca_topic_score_gemma":0.0000037037175,"teacher_disagreement_score":0.44984815,"about_ca_system_score_codex":0.000020334737,"about_ca_system_score_gemma":0.00010538636,"threshold_uncertainty_score":0.25873703},"labels":[],"label_agreement":null},{"id":"W4382794929","doi":"10.1007/s41060-023-00422-8","title":"Cluster weighted model based on TSNE algorithm for high-dimensional data","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster (spacecraft); Computer science; Algorithm; Data mining","score_opus":0.08185738340875104,"score_gpt":0.3724881720827192,"score_spread":0.2906307886739682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382794929","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004751802,0.00001817526,0.9889569,0.009227345,0.0006667166,0.000059153102,0.0005264778,0.000015535967,0.000054499465],"genre_scores_gemma":[0.034241777,0.00004858513,0.9630077,0.0022007679,0.0002790581,6.558564e-7,0.0001314818,0.000006267538,0.000083706385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975087,0.000029210078,0.00036391764,0.00047829142,0.0013999236,0.00021994785],"domain_scores_gemma":[0.99743265,0.00028746028,0.00023862266,0.0009251062,0.0009633036,0.00015288364],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0038393354,0.00011007163,0.0001686965,0.0005616972,0.00013920874,0.00036894812,0.0058604046,0.00003676356,0.0000029226412],"category_scores_gemma":[0.0003456966,0.000082110215,0.000031321342,0.0005976085,0.00016119836,0.0028026036,0.0015407489,0.00014446254,0.0000037005184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036776586,0.00013213792,0.000016695692,0.00000580587,0.00007049762,0.00006212903,0.000058363144,0.005220727,0.0005260946,0.03223272,0.03452467,0.92711335],"study_design_scores_gemma":[0.0005849409,0.00007195515,0.00005121017,0.000041801602,0.00001756698,0.000030823143,0.000003851295,0.97521824,0.00016978696,0.02242375,0.001287626,0.00009847228],"about_ca_topic_score_codex":0.00000420053,"about_ca_topic_score_gemma":0.000001584926,"teacher_disagreement_score":0.96999747,"about_ca_system_score_codex":0.000043391385,"about_ca_system_score_gemma":0.0006767726,"threshold_uncertainty_score":0.9995184},"labels":[],"label_agreement":null},{"id":"W4383070247","doi":"10.1016/j.csda.2023.107816","title":"Potts-Cox survival regression","year":2023,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Mathematics; Markov chain Monte Carlo; Applied mathematics; Markov chain; Laplace's method; Monte Carlo method; Statistics; Bayesian probability","score_opus":0.07695381996116518,"score_gpt":0.3729217299482058,"score_spread":0.29596790998704064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383070247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014314272,0.000054145774,0.99650806,0.00063226797,0.0002702431,0.0000643419,0.0017711108,0.00021577447,0.0003409226],"genre_scores_gemma":[0.020796021,0.00005464215,0.9699264,0.00018569407,0.00008348929,0.0000044468475,0.008515921,0.000011929776,0.00042141543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756324,0.00024987484,0.00037478944,0.0007770624,0.00073514244,0.00029989646],"domain_scores_gemma":[0.9973272,0.0008121378,0.00016016263,0.0013202399,0.00022966761,0.0001505689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010913607,0.00017727449,0.00034018524,0.00048494904,0.000252411,0.0002705998,0.0016083169,0.00005637819,0.000060299706],"category_scores_gemma":[0.00024302643,0.00015733777,0.00008539628,0.0033765878,0.000053819367,0.0004169346,0.0010949987,0.00013555492,0.00021087709],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053058534,0.000053238702,0.0016917862,0.000017827155,0.0007039857,0.00010731618,0.00015559091,0.028008403,0.0000121191215,0.7103175,0.077492036,0.18143488],"study_design_scores_gemma":[0.00010649116,0.00000880674,0.021438502,0.000004632015,0.00018651,0.0000016815687,0.000002359034,0.75373363,0.000002041003,0.22208084,0.0022845552,0.0001499535],"about_ca_topic_score_codex":0.000104675535,"about_ca_topic_score_gemma":0.000052669297,"teacher_disagreement_score":0.72572523,"about_ca_system_score_codex":0.000028793273,"about_ca_system_score_gemma":0.000121190445,"threshold_uncertainty_score":0.6416048},"labels":[],"label_agreement":null},{"id":"W4383223029","doi":"10.11159/jmids.2023.001","title":"Practical Representations of Copula and Joint Density Estimates","year":2022,"lang":"en","type":"article","venue":"Journal of Machine Intelligence and Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Copula (linguistics); Econometrics; Joint (building); Mathematics; Statistics; Engineering; Structural engineering","score_opus":0.10829042436410957,"score_gpt":0.4166021916237322,"score_spread":0.3083117672596226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383223029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011973782,0.00043783683,0.98486173,0.0023706425,0.000183747,0.00004879676,0.000013565141,0.000004905506,0.0001049688],"genre_scores_gemma":[0.4609207,0.00017824197,0.53877443,0.000106836225,0.000012504586,3.6878666e-7,6.781964e-7,0.0000013781104,0.0000049018145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850833,0.00010490288,0.00040663508,0.00030087502,0.00053852436,0.00014074997],"domain_scores_gemma":[0.99846184,0.00029502652,0.00036506684,0.0005694551,0.00016973323,0.00013887284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041339854,0.00007190315,0.0001931522,0.00019017747,0.0003134979,0.000124552,0.0010752251,0.000012229854,0.0000134667],"category_scores_gemma":[0.001215213,0.000055386216,0.000022557468,0.0005053065,0.00039178645,0.001772746,0.002136518,0.00026593157,2.9828885e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007674886,0.00044746595,0.010320158,0.0000624089,0.00004285846,0.00029235735,0.0026698778,0.0006170123,0.023070145,0.5274008,0.002439752,0.4325604],"study_design_scores_gemma":[0.00018745878,0.0006608344,0.0091590015,0.000047312482,0.00004864343,0.007083514,0.00041487772,0.8032989,0.028120086,0.15005223,0.0006873177,0.00023984295],"about_ca_topic_score_codex":0.0000723428,"about_ca_topic_score_gemma":0.00000386308,"teacher_disagreement_score":0.80268186,"about_ca_system_score_codex":0.000014920503,"about_ca_system_score_gemma":0.0002575353,"threshold_uncertainty_score":0.2663017},"labels":[],"label_agreement":null},{"id":"W4383739011","doi":"10.4236/ojs.2023.134021","title":"Modeling Cyber Loss Severity Using a Spliced Regression Distribution with Mixture Components","year":2023,"lang":"en","type":"article","venue":"Open Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Burnaby Hospital","funders":"","keywords":"Expectation–maximization algorithm; Covariate; Mixture model; Range (aeronautics); Computer science; Aggregate (composite); Generalized linear model; Statistics; Econometrics; Heavy-tailed distribution; Data mining; Mathematics; Probability distribution; Maximum likelihood; Engineering","score_opus":0.057860217162524014,"score_gpt":0.3354950161118946,"score_spread":0.2776347989493706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383739011","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04141407,0.000026503776,0.9577833,0.00026486706,0.00023673866,0.00011788875,0.000093572344,0.000013654242,0.00004945113],"genre_scores_gemma":[0.20511517,0.00004296656,0.79466164,0.000054382082,0.00005423363,7.2162675e-7,0.000020249154,0.000010099264,0.000040539617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986343,0.00016548214,0.00036687485,0.00018788311,0.00041252092,0.00023295647],"domain_scores_gemma":[0.998819,0.00007687651,0.00031599644,0.00025358223,0.00038304957,0.0001514804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008924672,0.00013948177,0.00029208377,0.00006399505,0.00019648098,0.00032041763,0.0008317069,0.00005967212,0.0000053339318],"category_scores_gemma":[0.00005582441,0.0000967463,0.000035448884,0.00039863004,0.000030423185,0.000640348,0.0003249912,0.0002840748,0.0000036090992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015823422,0.0008135552,0.0025636333,0.00040713558,0.00065036694,0.008357974,0.0059736827,0.12399682,0.01917905,0.36938438,0.030041097,0.43704998],"study_design_scores_gemma":[0.0006760954,0.00009055698,0.0005600647,0.00032922122,0.00003133796,0.00040763034,0.00001885748,0.96401167,0.0002334537,0.033192746,0.00028365353,0.00016471102],"about_ca_topic_score_codex":0.00004217363,"about_ca_topic_score_gemma":0.0000048569386,"teacher_disagreement_score":0.8400149,"about_ca_system_score_codex":0.00007093685,"about_ca_system_score_gemma":0.00015256245,"threshold_uncertainty_score":0.39451995},"labels":[],"label_agreement":null},{"id":"W4383817481","doi":"10.1007/s11749-023-00871-0","title":"Rejoinder on: Nonparametric estimation in mixture cure models with covariates","year":2023,"lang":"en","type":"article","venue":"Test","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Covariate; Nonparametric statistics; Estimation; Econometrics; Statistics; Mathematics; Applied mathematics; Economics","score_opus":0.02452550954533264,"score_gpt":0.2756732035405634,"score_spread":0.25114769399523074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383817481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028281324,0.000044719633,0.9908105,0.0021242502,0.00009378715,0.0001802343,0.0000029417886,0.00029601032,0.0036194327],"genre_scores_gemma":[0.43174887,0.000011204501,0.5674548,0.00042598884,0.000023201657,0.000022762739,0.000005238276,0.000012006735,0.00029592193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887484,0.000058971265,0.00015611913,0.000381664,0.00025422662,0.0002741667],"domain_scores_gemma":[0.9989464,0.0004114122,0.00005718508,0.00047357896,0.000045576657,0.000065802495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043334562,0.00014510867,0.00016954418,0.00037445466,0.00005912808,0.00010238428,0.00039814165,0.00009485686,0.0000051282445],"category_scores_gemma":[0.000104865576,0.000109556866,0.000027243384,0.0025335546,0.00002135748,0.00036675602,0.000073799274,0.00022021157,0.00009301264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021477024,0.00025189487,0.0014493081,0.000049854185,0.000018249912,0.00020285785,0.0016795096,0.08690293,0.00020522425,0.7981055,0.008567764,0.10254545],"study_design_scores_gemma":[0.0002983793,0.000116816154,0.003504373,0.00004807896,0.0000031375064,0.000011648141,0.0000032232065,0.8141406,0.00021838375,0.18140301,0.00010284232,0.00014945565],"about_ca_topic_score_codex":0.000022481523,"about_ca_topic_score_gemma":0.000010075561,"teacher_disagreement_score":0.7272377,"about_ca_system_score_codex":0.000032938915,"about_ca_system_score_gemma":0.00006190563,"threshold_uncertainty_score":0.44675994},"labels":[],"label_agreement":null},{"id":"W4383895067","doi":"10.1016/j.cor.2023.106347","title":"Rankability and linear ordering problem: Probabilistic insight and algorithms","year":2023,"lang":"en","type":"article","venue":"Computers & Operations Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Mitacs","keywords":"Pairwise comparison; Algorithm; Probabilistic logic; Computer science; Perspective (graphical); Interpretation (philosophy); Probabilistic analysis of algorithms; Mathematics; Artificial intelligence","score_opus":0.09541336472098304,"score_gpt":0.3875000214888778,"score_spread":0.29208665676789475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383895067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019305613,0.00022303987,0.97570086,0.0034432102,0.0001269474,0.0006656595,0.000002386592,0.00019169439,0.00034057396],"genre_scores_gemma":[0.07527752,0.00018717827,0.9238347,0.000086301385,0.000101573445,0.000117973475,0.0000062614613,0.000013948805,0.0003745839],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977408,0.00055417675,0.00024043677,0.0006670927,0.00036837423,0.00042910155],"domain_scores_gemma":[0.998479,0.00045468766,0.000011035876,0.0005382311,0.00032234762,0.00019467062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025788343,0.00013278016,0.00019139715,0.0003208671,0.0006862419,0.00058153353,0.00046924426,0.00007316959,0.000003528839],"category_scores_gemma":[0.00020780868,0.00011472945,0.000024653693,0.0013105792,0.00024709475,0.00045885364,0.0010092604,0.00036493046,0.000020631382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007849924,0.00011050842,0.00020305584,0.0002201789,0.000031959622,0.000044858043,0.0070239734,0.0051051034,0.0016692624,0.16963686,0.0014360055,0.8145104],"study_design_scores_gemma":[0.00026981314,0.00010177558,0.0010877843,0.0000360098,0.000001941006,0.00002158068,0.000015635056,0.97971624,0.00014086586,0.015627082,0.0028398307,0.0001414557],"about_ca_topic_score_codex":0.00008862493,"about_ca_topic_score_gemma":0.000042742937,"teacher_disagreement_score":0.9746111,"about_ca_system_score_codex":0.00003811564,"about_ca_system_score_gemma":0.0001550784,"threshold_uncertainty_score":0.56077415},"labels":[],"label_agreement":null},{"id":"W4383913721","doi":"10.1111/coin.12593","title":"Online short text clustering using infinite extensions of discrete mixture models","year":2023,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Dirichlet distribution; Computer science; Multinomial distribution; Gibbs sampling; Prior probability; Artificial intelligence; Latent Dirichlet allocation; Benchmark (surveying); Outlier; Topic model; Pattern recognition (psychology); Machine learning; Mathematics; Statistics; Bayesian probability","score_opus":0.11313478187495078,"score_gpt":0.3644947936831115,"score_spread":0.2513600118081607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383913721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009354228,0.00014433639,0.9892987,0.00029403405,0.00031251318,0.00014315076,0.00002715995,0.00016189797,0.00026396036],"genre_scores_gemma":[0.47327086,0.00002635485,0.5264531,0.000127525,0.000041299678,0.0000026963583,0.000018994178,0.000010179916,0.00004900468],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983098,0.00009523718,0.00047563316,0.00043900305,0.00039356932,0.00028675934],"domain_scores_gemma":[0.9986733,0.0004054703,0.00010273019,0.00039450167,0.00030903943,0.00011496588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036762634,0.00018310074,0.0002523799,0.00027540713,0.00013600488,0.00006395503,0.0007174131,0.00008367057,0.000008270063],"category_scores_gemma":[0.00006579962,0.00017100804,0.00011723287,0.0011271626,0.00009420593,0.00045084386,0.00051167124,0.00019451905,0.000015326419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000349859,0.00003003179,0.000022914135,0.00002000276,0.00001467721,0.000010387431,0.00049739727,0.87164086,0.00038539054,0.08060743,0.00006341033,0.04670398],"study_design_scores_gemma":[0.000023578456,0.000021648711,0.0003683138,0.000075228236,0.0000058617857,0.00002552891,0.000024026558,0.75291055,0.00037735573,0.2459962,0.000030910316,0.00014076883],"about_ca_topic_score_codex":0.000018815492,"about_ca_topic_score_gemma":0.0000058136693,"teacher_disagreement_score":0.46391663,"about_ca_system_score_codex":0.000027879758,"about_ca_system_score_gemma":0.00011598361,"threshold_uncertainty_score":0.6973505},"labels":[],"label_agreement":null},{"id":"W4384834058","doi":"10.1093/jrsssc/qlad064","title":"A Tweedie Markov process and its application in fisheries stock assessment","year":2023,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Autoregressive model; Markov chain; Applied mathematics; Econometrics; Autocorrelation; Computer science; Mathematics; Statistics","score_opus":0.014285609518547317,"score_gpt":0.2886606889203223,"score_spread":0.274375079401775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384834058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002477674,0.000049537084,0.9944445,0.0018033595,0.00019327672,0.00031583075,0.00014391125,0.000036296962,0.0005356353],"genre_scores_gemma":[0.26415756,0.000085011234,0.73499155,0.00030106877,0.00010559451,0.000047163077,0.000006264294,0.000021528485,0.00028427495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797815,0.00013010118,0.000611329,0.0002981924,0.00060260674,0.0003795971],"domain_scores_gemma":[0.9985155,0.00057085766,0.00036353525,0.00020198601,0.00018176054,0.0001663534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010575145,0.0002111586,0.0003968107,0.00004195833,0.00024222862,0.00017146139,0.000654035,0.000105466876,0.000015387795],"category_scores_gemma":[0.00016595706,0.00015159244,0.00007098256,0.00048313604,0.00016476854,0.00019983147,0.00029401228,0.0005275824,0.0000031968789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007820445,0.000114398346,0.0008185776,0.00029402855,0.00009236675,0.000029424176,0.00225089,0.00044108316,0.0003927868,0.8671324,0.019232608,0.10912323],"study_design_scores_gemma":[0.0009907583,0.00024558775,0.08621175,0.000060882245,0.00006458067,0.000032466978,0.0003802029,0.3390705,0.00013163862,0.5701482,0.0022637588,0.00039962577],"about_ca_topic_score_codex":0.000010512275,"about_ca_topic_score_gemma":0.000014945634,"teacher_disagreement_score":0.33862942,"about_ca_system_score_codex":0.000105877894,"about_ca_system_score_gemma":0.000202769,"threshold_uncertainty_score":0.61817604},"labels":[],"label_agreement":null},{"id":"W4385581012","doi":"10.1080/07474938.2023.2237274","title":"Time-dependent shrinkage of time-varying parameter regression models","year":2023,"lang":"en","type":"article","venue":"Econometric Reviews","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Shrinkage; Heteroscedasticity; Latent variable; Econometrics; Prior probability; Bayesian probability; Statistics; Regression; Linear regression; Variance (accounting); Regression analysis; Shrinkage estimator; Mathematics; Computer science; Economics; Mean squared error","score_opus":0.06039282000779129,"score_gpt":0.30312878553982314,"score_spread":0.24273596553203186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385581012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015940653,0.011124592,0.9660462,0.00018379207,0.00026297543,0.00052916026,0.0000048040656,0.00014731387,0.020107113],"genre_scores_gemma":[0.020725382,0.030303597,0.9253001,0.00065691286,0.00021638616,0.00018482214,0.00002213316,0.00007196636,0.022518694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997691,0.0003380976,0.0008190219,0.0005913183,0.00020050381,0.00036007175],"domain_scores_gemma":[0.99785185,0.00040987975,0.00042761597,0.0011275912,0.000041069186,0.00014197474],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029395847,0.000226572,0.0007812759,0.00094869325,0.00007042877,0.00007710243,0.0010482863,0.00009813775,0.00022448442],"category_scores_gemma":[0.00029689513,0.00017000995,0.0002879544,0.0027924676,0.00003195037,0.00066772045,0.00044930674,0.00016034051,0.0024597202],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002525478,0.000044254484,0.000024411826,0.00013369008,0.000023396287,0.000010306671,0.00026377247,0.0005206175,0.00037919133,0.0031721303,0.010732985,0.9846927],"study_design_scores_gemma":[0.0004439498,0.00012068867,0.000100495425,0.00034442754,0.00002951654,0.00001911008,0.00000231529,0.904459,0.0016374799,0.059174553,0.033101756,0.000566733],"about_ca_topic_score_codex":0.0000044320163,"about_ca_topic_score_gemma":1.0458949e-7,"teacher_disagreement_score":0.984126,"about_ca_system_score_codex":0.000042811822,"about_ca_system_score_gemma":0.00003281768,"threshold_uncertainty_score":0.998317},"labels":[],"label_agreement":null},{"id":"W4385625456","doi":"10.1007/s10489-023-04888-8","title":"Unsupervised nested Dirichlet finite mixture model for clustering","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hierarchical Dirichlet process; Computer science; Dirichlet distribution; Mixture model; Generalized Dirichlet distribution; Latent Dirichlet allocation; Concentration parameter; Expectation–maximization algorithm; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Algorithm; Mathematics; Topic model; Dirichlet's principle; Statistics; Maximum likelihood","score_opus":0.05490856148407772,"score_gpt":0.30126505290702715,"score_spread":0.24635649142294944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385625456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023911128,0.000057738176,0.9950361,0.00064007286,0.00027628356,0.0005602972,0.000010276836,0.00062428904,0.0025558295],"genre_scores_gemma":[0.24450833,0.00007255313,0.75254524,0.0012752734,0.00009560735,0.0002792907,0.000015996915,0.00003414678,0.001173601],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981413,0.00003119193,0.00034361973,0.0006827909,0.00023667063,0.00056443893],"domain_scores_gemma":[0.99845445,0.00044167892,0.000078281795,0.0007914307,0.00008940838,0.00014475624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058725383,0.00025309212,0.00026791616,0.00017416777,0.00019167078,0.00015270595,0.0012842688,0.000150593,0.000007286535],"category_scores_gemma":[0.00006907327,0.00023287728,0.0001135197,0.001016756,0.000045277404,0.00020570126,0.0003794155,0.00018882922,0.00013758554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028315071,0.000036206,0.0000046697587,0.000089232126,0.000024085884,0.0000075987978,0.0029693353,0.07096064,0.0062304107,0.44769788,0.0026961053,0.46925554],"study_design_scores_gemma":[0.00008809265,0.00002125069,0.0000089082605,0.00001578071,0.0000063542207,0.0000023049756,0.00002050609,0.83118707,0.0060063554,0.16111816,0.0012763442,0.00024885059],"about_ca_topic_score_codex":0.0000040625096,"about_ca_topic_score_gemma":0.0000057156017,"teacher_disagreement_score":0.7602264,"about_ca_system_score_codex":0.000026436053,"about_ca_system_score_gemma":0.00006438717,"threshold_uncertainty_score":0.949646},"labels":[],"label_agreement":null},{"id":"W4385776757","doi":"10.1016/j.ecosta.2023.08.001","title":"A computationally efficient mixture innovation model for time-varying parameter regressions","year":2023,"lang":"en","type":"article","venue":"Econometrics and Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Mixture model; Block (permutation group theory); Computer science; Latent variable; Computation; Algorithm; Bayesian probability; Markov chain Monte Carlo; Statistics; Mathematics; Econometrics; Mathematical optimization","score_opus":0.05884570760446368,"score_gpt":0.3058741556124592,"score_spread":0.2470284480079955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385776757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016541358,0.000057606787,0.99675757,0.00055151375,0.00014705332,0.00020845496,0.0003378629,0.00007566261,0.00021012989],"genre_scores_gemma":[0.036245525,0.000019057215,0.96259004,0.00032388177,0.000028697226,0.000027211749,0.00011982339,0.000011371091,0.00063438003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990328,0.000024274368,0.00029032587,0.0003202637,0.00011719268,0.0002151182],"domain_scores_gemma":[0.9983669,0.001059603,0.00012681253,0.00018576972,0.0001936526,0.00006727111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005825479,0.000111842215,0.00016895075,0.0007524918,0.00018993954,0.00017780504,0.00019172685,0.00006376422,0.0000031144434],"category_scores_gemma":[0.00053717574,0.00010411922,0.000025640464,0.0017852783,0.000024252777,0.000092893715,0.000111283756,0.000082913,0.000012127475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034804007,0.000026912965,0.000036939724,0.00003081043,0.00001664895,0.0000027797425,0.00045509613,0.023930965,0.00004884534,0.85821074,0.011306288,0.10593047],"study_design_scores_gemma":[0.00017778532,0.000024321098,0.00046233984,0.0000063415664,0.000004504404,0.0000016730045,0.0000016863361,0.74508506,0.0000076125566,0.25378388,0.00034186104,0.00010293273],"about_ca_topic_score_codex":5.405119e-7,"about_ca_topic_score_gemma":1.4359782e-7,"teacher_disagreement_score":0.7211541,"about_ca_system_score_codex":0.000026192889,"about_ca_system_score_gemma":0.0000752681,"threshold_uncertainty_score":0.42458585},"labels":[],"label_agreement":null},{"id":"W4385884553","doi":"10.1007/978-981-99-2240-6_10","title":"On Likelihood Ratio Tests for Dimensionality Selection","year":2023,"lang":"en","type":"book-chapter","venue":"Behaviormetrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Curse of dimensionality; Likelihood-ratio test; Statistics; Statistic; Mathematics; Multivariate statistics; Model selection; Confusion; Dimension (graph theory); Asymptotic distribution; Test statistic; Selection (genetic algorithm); Statistical hypothesis testing; Econometrics; Chi-square test; Square (algebra); Computer science; Combinatorics; Psychology; Artificial intelligence; Estimator","score_opus":0.07602240418190635,"score_gpt":0.3278850327751892,"score_spread":0.25186262859328284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385884553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025475458,0.00008756302,0.9764683,0.00013388932,0.0014517746,0.00071062066,0.00008429259,0.00038600597,0.020652058],"genre_scores_gemma":[0.0008116191,0.00010530299,0.55810183,0.0005337301,0.00040855052,0.00014439729,0.00011490569,0.00015337308,0.43962625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99773854,0.0000329212,0.00041343158,0.00081858283,0.0006216341,0.00037489034],"domain_scores_gemma":[0.9978119,0.00073398737,0.00026538305,0.0006551986,0.00036890875,0.00016462666],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079364085,0.0003829739,0.00040954497,0.00083735446,0.00019967229,0.00014917515,0.000572978,0.0005384061,0.000018011513],"category_scores_gemma":[0.00023965689,0.0003657427,0.0002875854,0.0005153061,0.000026042006,0.00015551112,0.00017276815,0.00045012636,0.00014347758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005911182,0.000047678786,0.000008220352,0.00001966225,0.000014085696,0.000008113051,0.000015464535,0.000002792918,0.00005668712,0.8076193,0.010186792,0.18201533],"study_design_scores_gemma":[0.00057069305,0.0007752159,0.00073741423,0.00012735793,0.00017152764,0.000020751906,4.4959896e-7,0.0033370655,0.00055013306,0.96153647,0.031223051,0.0009498632],"about_ca_topic_score_codex":0.0000072331745,"about_ca_topic_score_gemma":0.000010930498,"teacher_disagreement_score":0.4189742,"about_ca_system_score_codex":0.00017934499,"about_ca_system_score_gemma":0.00021976022,"threshold_uncertainty_score":0.9998795},"labels":[],"label_agreement":null},{"id":"W4385974194","doi":"10.2139/ssrn.4545321","title":"Hierarchical Mixture of Discriminative Generalized Dirichlet Classifiers","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Discriminative model; Latent Dirichlet allocation; Mathematics; Pattern recognition (psychology); Artificial intelligence; Hierarchical Dirichlet process; Dirichlet distribution; Computer science; Topic model; Mathematical analysis","score_opus":0.031679312805601045,"score_gpt":0.3034732745624512,"score_spread":0.27179396175685017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385974194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027513641,0.0028662093,0.98651934,0.005131396,0.0015695201,0.00026533095,0.000017935714,0.00012612305,0.0007527979],"genre_scores_gemma":[0.23296864,0.021353224,0.732224,0.0005264835,0.0017371143,0.000079003425,0.00006886493,0.00019044471,0.010852238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941495,0.0008980629,0.00075912237,0.00080518477,0.0007524111,0.0026357253],"domain_scores_gemma":[0.99772155,0.00017492435,0.00070639385,0.0009205077,0.00024900437,0.00022764469],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0038153555,0.00048429446,0.00082778133,0.0004559246,0.00018994858,0.00019067853,0.0026977032,0.00052765274,0.0000066995904],"category_scores_gemma":[0.00018831786,0.00038938402,0.00061609084,0.0004574681,0.00016434916,0.00020924138,0.0013644366,0.0083433045,0.000009209128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003052019,0.00006526648,0.000026831576,0.000049222235,0.00038007624,0.000025388112,0.00091348594,0.00008812705,0.0004678604,0.93454,0.0007336886,0.06267959],"study_design_scores_gemma":[0.00047992176,0.00018852702,0.00016131929,0.00012807074,0.000079251215,0.00017493962,0.00008745183,0.009175,0.00026657563,0.98833996,0.00051343057,0.00040556586],"about_ca_topic_score_codex":0.00006299353,"about_ca_topic_score_gemma":0.00010793028,"teacher_disagreement_score":0.25429532,"about_ca_system_score_codex":0.00074021035,"about_ca_system_score_gemma":0.0049397117,"threshold_uncertainty_score":0.9998558},"labels":[],"label_agreement":null},{"id":"W4386099403","doi":"10.1007/s11222-023-10286-4","title":"Bayesian analysis for matrix-variate logistic regression with/without response misclassification","year":2023,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Logistic regression; Random variate; Covariate; Statistics; Bayesian probability; Computer science; Spurious relationship; Artificial intelligence; Machine learning; Econometrics; Mathematics; Random variable","score_opus":0.04327434835256558,"score_gpt":0.3505132172472381,"score_spread":0.30723886889467256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386099403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002262004,0.000041445805,0.996667,0.00047653134,0.000111339585,0.00019090547,0.000047766036,0.00015641784,0.00004656125],"genre_scores_gemma":[0.4153825,0.0000071939407,0.5842657,0.000037747424,0.000027731252,0.000006204005,0.00002142501,0.00000854838,0.00024293164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857986,0.00021131305,0.0002610648,0.00047077506,0.0001797655,0.00029720497],"domain_scores_gemma":[0.9982883,0.00094215,0.00017914448,0.00036189376,0.00012255553,0.000105978375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012901505,0.00015356457,0.0002646411,0.00026276766,0.0003329053,0.00022655897,0.00024774112,0.00005642823,0.0000015967829],"category_scores_gemma":[0.000194317,0.00011797275,0.000044063203,0.0009077682,0.000046931476,0.0000663329,0.00011542692,0.00009036786,0.0000019502938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034104826,0.0000471701,0.0031082223,0.00014971884,0.00033511576,0.000072661845,0.0018646084,0.004549298,0.0013022189,0.66951793,0.0014297082,0.3172823],"study_design_scores_gemma":[0.0002912179,0.00009869074,0.010183525,0.000032770382,0.00010253077,0.0000067926844,0.000021577564,0.94235045,0.000045366436,0.046503987,0.00019477967,0.00016834072],"about_ca_topic_score_codex":0.000012680473,"about_ca_topic_score_gemma":0.0000061383457,"teacher_disagreement_score":0.9378011,"about_ca_system_score_codex":0.000019547664,"about_ca_system_score_gemma":0.00006130769,"threshold_uncertainty_score":0.48107892},"labels":[],"label_agreement":null},{"id":"W4386134063","doi":"10.1080/01621459.2023.2250098","title":"Spectral Clustering, Bayesian Spanning Forest, and Forest Process","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Cluster analysis; Bayesian probability; Environmental science; Forestry; Mathematics; Statistics; Geography","score_opus":0.011162884816843674,"score_gpt":0.2962793568059756,"score_spread":0.2851164719891319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386134063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07732817,0.000011575019,0.9188895,0.0033305609,0.00021852215,0.00005711364,0.0000048278043,0.000025041621,0.00013467677],"genre_scores_gemma":[0.7851144,0.000017273935,0.21424825,0.00030446684,0.00015896586,0.0000015732847,4.537801e-7,0.000008214076,0.00014637358],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99867064,0.00019643636,0.0003057711,0.00013270898,0.00043639351,0.00025802603],"domain_scores_gemma":[0.99830014,0.0005885115,0.00075847487,0.00012846653,0.00012045744,0.00010395417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009628969,0.000092357914,0.00024798,0.00008391087,0.00011958868,0.00013278714,0.00037584864,0.000027342994,0.0000016523501],"category_scores_gemma":[0.00093608804,0.000062582156,0.000063357686,0.0005194022,0.00005751153,0.00022449536,0.0001107821,0.0002424948,0.0000024900028],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010717441,0.00012286747,0.54834664,0.000091132075,0.00028578183,0.0001564964,0.0035733923,0.003421571,0.0006104187,0.12860398,0.015634041,0.2990465],"study_design_scores_gemma":[0.0002267268,0.00018608569,0.58796895,0.00003447762,0.000030004014,0.000050324856,0.00004966079,0.26718402,0.000021424923,0.14396974,0.00016873084,0.00010989533],"about_ca_topic_score_codex":0.000021162496,"about_ca_topic_score_gemma":0.000028790239,"teacher_disagreement_score":0.70778626,"about_ca_system_score_codex":0.00011937737,"about_ca_system_score_gemma":0.00007246349,"threshold_uncertainty_score":0.25520262},"labels":[],"label_agreement":null},{"id":"W4386411825","doi":"10.1007/978-981-99-5834-4_30","title":"Finite Libby-Novick Beta Mixture Model: An MML-Based Approach","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; BETA (programming language); Artificial intelligence; Programming language","score_opus":0.03682749563201243,"score_gpt":0.2707176941050701,"score_spread":0.23389019847305764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386411825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000050050025,0.00019968447,0.9890464,0.0008970477,0.0013694408,0.00043780304,0.000021919546,0.00062964985,0.007393075],"genre_scores_gemma":[0.01088863,0.000023310156,0.9835996,0.0036683274,0.00055044325,0.000026817277,0.000033383454,0.00011693709,0.0010925691],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937368,0.00012226262,0.00067913986,0.002879586,0.0014568707,0.0011253506],"domain_scores_gemma":[0.9952201,0.0006339964,0.00035210533,0.0030576799,0.00028487286,0.0004512205],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001910354,0.00089306675,0.00080627436,0.0012081062,0.00039279502,0.0009738348,0.006059755,0.0008562116,0.00001099355],"category_scores_gemma":[0.00008627736,0.0008238269,0.00029803117,0.0012331059,0.0006922138,0.0009081239,0.0014095154,0.0016099755,0.0000482302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007438656,0.000053520755,0.0000031773043,0.000070602975,0.000012323399,0.000078451754,0.0006233314,0.44814947,0.000048983355,0.16269194,0.00006618905,0.38819456],"study_design_scores_gemma":[0.00020691908,0.00011994211,0.0000043108666,0.00014823605,0.000011469515,0.00001766106,5.2141516e-8,0.6955863,0.00040911778,0.30254525,0.00028156393,0.00066911994],"about_ca_topic_score_codex":0.000016844135,"about_ca_topic_score_gemma":0.000038312417,"teacher_disagreement_score":0.38752544,"about_ca_system_score_codex":0.00015738503,"about_ca_system_score_gemma":0.0011685529,"threshold_uncertainty_score":0.99942124},"labels":[],"label_agreement":null},{"id":"W4386496250","doi":"10.1038/s41598-023-41318-8","title":"Clustering microbiome data using mixtures of logistic normal multinomial models","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Simons Foundation","keywords":"Mixture model; Cluster analysis; Multinomial distribution; Computer science; Microbiome; Count data; Simplex; Bayesian probability; Latent variable; Multinomial logistic regression; Data mining; Variable (mathematics); Statistics; Artificial intelligence; Mathematics; Biology; Bioinformatics; Machine learning; Poisson distribution","score_opus":0.14319259496676276,"score_gpt":0.33953139770615126,"score_spread":0.1963388027393885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386496250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040612914,0.000090051035,0.9514257,0.00004210808,0.0071224156,0.00017962702,0.0000138716805,0.00016042957,0.00035292498],"genre_scores_gemma":[0.5519578,0.0000019335214,0.44749504,0.000013109226,0.000065568056,0.0000020596362,0.000045226272,0.0000109415105,0.000408322],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972364,0.00009627415,0.0006312159,0.0011584274,0.0004180133,0.0004597037],"domain_scores_gemma":[0.996401,0.00006323932,0.0003621229,0.0029194567,0.00013798599,0.000116170595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003269687,0.0001654289,0.00028189382,0.0003702726,0.0002633823,0.00036930808,0.0013566951,0.00008526044,0.0000071976365],"category_scores_gemma":[0.00012913781,0.00014949459,0.00008025681,0.0012024048,0.00022519023,0.0009312243,0.0020530543,0.00011332195,0.000007805055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012704525,0.0001252784,0.00024575507,0.00022676885,0.000055827255,0.0014870709,0.0021593568,0.04159287,0.8876827,0.0025356782,0.00904076,0.05483528],"study_design_scores_gemma":[0.0000924053,0.000008709245,0.000049763996,0.000044984838,0.000012424979,0.0002372589,0.000008932519,0.955217,0.01781152,0.025760371,0.0005659545,0.0001906594],"about_ca_topic_score_codex":0.0001099455,"about_ca_topic_score_gemma":0.000022365102,"teacher_disagreement_score":0.91362417,"about_ca_system_score_codex":0.000026989843,"about_ca_system_score_gemma":0.00021262988,"threshold_uncertainty_score":0.6096212},"labels":[],"label_agreement":null},{"id":"W4386608500","doi":"10.1080/10618600.2023.2257258","title":"Clustering Sequence Data with Mixture Markov Chains with Covariates Using Multiple Simplex Constrained Optimization Routine (MSiCOR)","year":2023,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Expectation–maximization algorithm; Cluster analysis; Computer science; Covariate; Context (archaeology); Maximization; Simplex; Markov chain; Mixture model; Mathematical optimization; Data mining; Artificial intelligence; Machine learning; Mathematics; Statistics; Maximum likelihood","score_opus":0.04511387327722369,"score_gpt":0.30332949743915777,"score_spread":0.2582156241619341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386608500","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003847301,0.000034114844,0.9948973,0.0007881108,0.00007367859,0.000094849274,0.00022887929,0.000029216639,0.000006534907],"genre_scores_gemma":[0.23299472,0.000027121885,0.7666654,0.00016292269,0.0000554694,5.1788766e-7,0.00008097281,0.000008779545,0.0000041211456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861544,0.00011879356,0.00037381222,0.00024988822,0.00044096584,0.00020109612],"domain_scores_gemma":[0.9981696,0.0007674664,0.00033395685,0.00016771677,0.00040491787,0.00015636413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005502633,0.00015514692,0.0002614376,0.00017257556,0.00017884717,0.00017680677,0.00036549213,0.00005344625,0.0000036966273],"category_scores_gemma":[0.00011774941,0.000106541214,0.000020707152,0.00063293555,0.00015720756,0.0003830329,0.00015504578,0.00021961662,1.4315667e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016631531,0.00005676716,0.0019957367,0.000063784304,0.00014111376,0.0003313609,0.0002416607,0.89602363,0.0000539092,0.06648555,0.00019713573,0.034243047],"study_design_scores_gemma":[0.00092129497,0.00022156184,0.0032626863,0.00008025047,0.000037012214,0.0006411871,0.000012691631,0.9712538,0.0000024167612,0.023379438,0.00003563079,0.00015202138],"about_ca_topic_score_codex":0.000010147304,"about_ca_topic_score_gemma":0.000009802628,"teacher_disagreement_score":0.22914742,"about_ca_system_score_codex":0.000015058216,"about_ca_system_score_gemma":0.00018707817,"threshold_uncertainty_score":0.43446246},"labels":[],"label_agreement":null},{"id":"W4386611389","doi":"10.2139/ssrn.4567660","title":"Composite Sorting","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Composite number; Mathematics; Composite material; Materials science","score_opus":0.012973014452106038,"score_gpt":0.27242051583376653,"score_spread":0.2594475013816605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386611389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01605533,0.00045302362,0.97839177,0.0019342827,0.00030555364,0.000041775544,1.468668e-7,0.00020347886,0.0026146553],"genre_scores_gemma":[0.8854456,0.0015444943,0.10835183,0.00042583837,0.00044067082,0.000004031622,0.0000011051068,0.000023445997,0.003762997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99719846,0.00011800517,0.00021311519,0.00020174551,0.00022568052,0.0020429953],"domain_scores_gemma":[0.9994764,0.00005275931,0.00010533099,0.00023239348,0.000046607627,0.00008655584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002794231,0.00010387144,0.00012965423,0.00014908527,0.0002689394,0.00014933951,0.00071836874,0.000045604833,0.0000027032406],"category_scores_gemma":[0.000025624597,0.000088058674,0.00009955922,0.00055645505,0.000015092026,0.00031579417,0.00013001134,0.0011408805,0.00011537636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016474473,0.0000066009516,0.0001087677,0.0000012684256,0.000022710174,0.000010694331,0.00015482579,0.000018198372,0.0011551984,0.69212735,0.0001518791,0.3062409],"study_design_scores_gemma":[0.00020460476,0.00008895887,0.0002764547,0.000009439197,0.0000051313,0.00052446563,0.00005352554,0.013546905,0.00031650238,0.98398566,0.0008604333,0.00012793185],"about_ca_topic_score_codex":0.0000066885545,"about_ca_topic_score_gemma":0.000016616437,"teacher_disagreement_score":0.87003994,"about_ca_system_score_codex":0.00018149645,"about_ca_system_score_gemma":0.00067022996,"threshold_uncertainty_score":0.49566212},"labels":[],"label_agreement":null},{"id":"W4386636102","doi":"10.1007/s44199-023-00062-8","title":"Smoothed Dirichlet Distribution","year":2023,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Winnipeg","funders":"","keywords":"Dirichlet distribution; Multinomial distribution; Mathematics; Generalized Dirichlet distribution; Categorical distribution; Concentration parameter; Distribution (mathematics); Marginal distribution; Applied mathematics; Joint probability distribution; Probability distribution; Statistics; Econometrics; Dirichlet's principle; Mathematical analysis; Random variable; Inverse-chi-squared distribution; Distribution fitting","score_opus":0.013350226702433096,"score_gpt":0.30740354703914374,"score_spread":0.29405332033671067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386636102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029205275,0.00007814373,0.9982161,0.00064654864,0.00004005067,0.00006206055,0.000043871587,0.000026897018,0.0005943121],"genre_scores_gemma":[0.4597492,0.00029561296,0.5389546,0.00034003844,0.00026672034,0.000030314002,0.000018661414,0.000009047503,0.0003358133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993472,0.00014485422,0.00020012358,0.00009516316,0.00010865114,0.00010398714],"domain_scores_gemma":[0.9987487,0.00086003094,0.00009109933,0.00012963182,0.000067679306,0.00010282772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011951907,0.000051662108,0.00010908922,0.000040474773,0.00010149625,0.000051111172,0.0002004014,0.000027804681,0.00000984712],"category_scores_gemma":[0.00013093154,0.000038571256,0.000027280848,0.00027836213,0.00006810124,0.00011176897,0.00004852574,0.000109017215,0.000014995595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055556816,0.000015395928,0.0000057922202,0.0000041489975,0.0000060992047,0.0000039968622,0.00003100259,0.0000017068078,0.00015577763,0.8063448,0.0011062069,0.19231948],"study_design_scores_gemma":[0.00010673036,0.000033659828,0.0015592978,0.0000059817844,0.000010867569,0.000036267586,0.000011081144,0.0012817662,0.0000963172,0.97590256,0.02090834,0.000047111218],"about_ca_topic_score_codex":1.9723765e-7,"about_ca_topic_score_gemma":4.1867267e-8,"teacher_disagreement_score":0.45945716,"about_ca_system_score_codex":0.00000830109,"about_ca_system_score_gemma":0.000023403823,"threshold_uncertainty_score":0.15728901},"labels":[],"label_agreement":null},{"id":"W4386716613","doi":"10.1007/978-3-031-42508-0_29","title":"Bayesian Inference in Infinite Multivariate McDonald’s Beta Mixture Model","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Dirichlet process; Computer science; Cluster analysis; Dirichlet distribution; Bayesian inference; Posterior probability; Inference; Markov chain Monte Carlo; Bayesian probability; Gaussian process; Artificial intelligence; Beta distribution; Machine learning; Multivariate statistics; Data mining; Pattern recognition (psychology); Gaussian; Mathematics; Statistics","score_opus":0.035021127345776434,"score_gpt":0.29140524731902884,"score_spread":0.2563841199732524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386716613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001323207,0.00023298372,0.99077296,0.0015695665,0.0015775745,0.00061060576,0.000022819806,0.00036333947,0.0048369328],"genre_scores_gemma":[0.05304282,0.000116966345,0.9426708,0.0022267692,0.0003257443,0.000029940784,0.000011569845,0.000095138574,0.001480247],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931688,0.0001376171,0.0010707575,0.0028369701,0.0014049339,0.0013809708],"domain_scores_gemma":[0.99502903,0.0014945559,0.00043444877,0.002373943,0.00029412765,0.00037386944],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0022375192,0.0010482189,0.0011347374,0.002114491,0.00025572267,0.00071868475,0.0055128955,0.000918824,0.000014311618],"category_scores_gemma":[0.00031194466,0.00096731924,0.00025463558,0.0018056325,0.00062445505,0.0010221009,0.002708204,0.002306356,0.00007096805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010180613,0.000043675504,0.00005558108,0.00006887633,0.000016092697,0.0002699088,0.001816043,0.1921928,0.00018650698,0.22120416,0.000025470274,0.5841107],"study_design_scores_gemma":[0.00025363872,0.000048222824,0.00008017887,0.00041502065,0.0000054769703,0.000012169497,5.4530872e-8,0.5677502,0.00016716361,0.43051717,0.00012298246,0.0006276939],"about_ca_topic_score_codex":0.000095818286,"about_ca_topic_score_gemma":0.00049666397,"teacher_disagreement_score":0.583483,"about_ca_system_score_codex":0.00035369332,"about_ca_system_score_gemma":0.0012696355,"threshold_uncertainty_score":0.99999535},"labels":[],"label_agreement":null},{"id":"W4386837887","doi":"10.3390/axioms12090887","title":"Bayesian Estimation of Variance-Based Information Measures and Their Application to Testing Uniformity","year":2023,"lang":"en","type":"article","venue":"Axioms","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Computer science; Bayesian probability; Machine learning; Nonparametric statistics; Variance (accounting); Artificial intelligence; Entropy (arrow of time); Data mining; Econometrics; Statistics; Mathematics","score_opus":0.020939424394505267,"score_gpt":0.25713114747189164,"score_spread":0.23619172307738637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386837887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030704,0.0000072288976,0.9953371,0.0005861062,0.00004819542,0.00022242135,0.0000034134357,0.0001574046,0.00056772836],"genre_scores_gemma":[0.6704692,7.1535686e-7,0.32934314,0.00014582758,0.00000877907,0.000021201271,0.000005147052,0.0000024634921,0.0000035151468],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993823,0.000041964482,0.00019175232,0.0001327366,0.00012751127,0.00012373771],"domain_scores_gemma":[0.9993359,0.0001313882,0.00009552314,0.00027756672,0.00010029454,0.000059343798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067249656,0.00007786945,0.000100825,0.00015690245,0.00007544341,0.00005659954,0.00020736227,0.00004237676,3.7808226e-7],"category_scores_gemma":[0.00017204185,0.00006487002,0.000017297863,0.0009087166,0.000017160068,0.00052976067,0.00006212405,0.000045104603,0.000011081825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002536025,0.0000056643357,0.000050621726,0.00002724335,0.0000025262348,1.0913682e-7,0.0007549483,0.0056423894,0.0011657537,0.065741315,0.00002544059,0.92658144],"study_design_scores_gemma":[0.000109096305,0.00003682032,0.0046004695,0.000022590473,0.0000019514687,0.0000016152638,0.000010986053,0.9613327,0.0050106016,0.028684756,0.00011356969,0.000074884134],"about_ca_topic_score_codex":0.000056807163,"about_ca_topic_score_gemma":0.0000035681787,"teacher_disagreement_score":0.95569026,"about_ca_system_score_codex":0.000014991972,"about_ca_system_score_gemma":0.000046545196,"threshold_uncertainty_score":0.2645323},"labels":[],"label_agreement":null},{"id":"W4387095339","doi":"10.1007/s11634-023-00558-2","title":"Parsimony and parameter estimation for mixtures of multivariate leptokurtic-normal distributions","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"NextGenerationEU; Ministero dell'Università e della Ricerca; Natural Sciences and Engineering Research Council of Canada; Università Cattolica del Sacro Cuore","keywords":"Kurtosis; Multivariate statistics; Statistics; Mathematics; Estimation; Multivariate normal distribution; Multivariate analysis; Estimation theory; Econometrics; Economics","score_opus":0.04852271423534097,"score_gpt":0.3659672425237264,"score_spread":0.31744452828838543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387095339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006040089,0.00047960656,0.99266106,0.00048419033,0.00003131881,0.000118716955,0.00014127532,0.000022462104,0.000021267813],"genre_scores_gemma":[0.5513983,0.0006426534,0.4473392,0.0000109627335,0.0000064560427,0.000024515952,0.0005630404,0.000001979357,0.000012900681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909043,0.00006982466,0.00025699695,0.00037368323,0.000089436115,0.00011961243],"domain_scores_gemma":[0.99887824,0.00034737008,0.00013624837,0.00056154124,0.000043203123,0.000033410917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005830365,0.0000734142,0.00017844903,0.00018733428,0.000072250325,0.00005477617,0.00030284643,0.000040803625,8.233116e-7],"category_scores_gemma":[0.00024820075,0.00006288299,0.000030488589,0.0009470413,0.000057411264,0.0009616387,0.00013944086,0.000041830805,3.955403e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012265539,0.000044694996,0.004828525,0.000044405937,0.00008932892,3.080383e-7,0.00018187962,0.00048346576,0.0023631426,0.19755495,0.00008864588,0.7943084],"study_design_scores_gemma":[0.00014322418,0.0000125558945,0.0627138,0.000007966669,0.00011655443,2.7605125e-7,0.000012969227,0.8876049,0.00046750478,0.04809254,0.0007584865,0.00006923314],"about_ca_topic_score_codex":0.000013692767,"about_ca_topic_score_gemma":0.00006461652,"teacher_disagreement_score":0.88712144,"about_ca_system_score_codex":0.0000071385825,"about_ca_system_score_gemma":0.000010599314,"threshold_uncertainty_score":0.25642937},"labels":[],"label_agreement":null},{"id":"W4387311761","doi":"10.1080/01621459.2023.2263202","title":"Copula Modeling of Serially Correlated Multivariate Data with Hidden Structures","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Computer science; Multivariate statistics; Hidden Markov model; Inference; Section (typography); Algorithm; Theoretical computer science; Econometrics; Data mining; Mathematics; Artificial intelligence; Machine learning","score_opus":0.02901518291234277,"score_gpt":0.3159927258049126,"score_spread":0.2869775428925698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387311761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030158337,0.000008686422,0.96806824,0.0012645975,0.00030541382,0.00006395401,0.00007253201,0.000018272383,0.000039948358],"genre_scores_gemma":[0.5444258,0.000009609165,0.45538002,0.00008243674,0.000056220848,3.1316918e-7,0.000004856598,0.0000064703977,0.000034304714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982216,0.00041868407,0.0004344982,0.00015340639,0.00059271575,0.00017911293],"domain_scores_gemma":[0.99736446,0.00057124044,0.0013194769,0.0003854435,0.00029579742,0.00006355683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011982303,0.000091485366,0.00033519504,0.00007054922,0.00006892316,0.000058752794,0.0009930877,0.000033668803,0.0000029323028],"category_scores_gemma":[0.0011086568,0.000054083637,0.000042995936,0.00062708766,0.000045007306,0.00024664126,0.00025723787,0.0002428372,0.0000016102027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012971214,0.00039856473,0.020010697,0.000112463254,0.0024418207,0.00019556869,0.004919397,0.05738173,0.018479815,0.32216507,0.030711487,0.54188627],"study_design_scores_gemma":[0.0004044937,0.000158552,0.0272799,0.00003412926,0.000077468525,0.000016382042,0.000031650015,0.91995037,0.00005178812,0.051862344,0.000041336098,0.00009157001],"about_ca_topic_score_codex":0.00013346804,"about_ca_topic_score_gemma":0.000008521875,"teacher_disagreement_score":0.8625687,"about_ca_system_score_codex":0.00009216281,"about_ca_system_score_gemma":0.00016786484,"threshold_uncertainty_score":0.22054666},"labels":[],"label_agreement":null},{"id":"W4387326446","doi":"10.1002/sim.9917","title":"Joint clustering multiple longitudinal features: A comparison of methods and software packages with practical guidance","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Cluster analysis; Computer science; Data mining; Machine learning; Software; Bayesian probability; Popularity; Feature (linguistics); Frequentist inference; Artificial intelligence; Data science; Bayesian inference","score_opus":0.09040215515519481,"score_gpt":0.4441058922588974,"score_spread":0.3537037371037026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387326446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056247343,0.0004762067,0.9974522,0.0009943979,0.00017963025,0.00015926245,0.000014663785,0.000061926956,0.00009922717],"genre_scores_gemma":[0.05411411,0.00009092346,0.94558835,0.00007618225,0.000045251218,0.000011803601,0.0000060956663,0.000011486644,0.00005580587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842525,0.00029291582,0.0003857945,0.0003597111,0.0002782018,0.00025816046],"domain_scores_gemma":[0.9972849,0.0019863944,0.00016534503,0.00035355406,0.000109383094,0.00010042943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016953918,0.00015059773,0.00047976038,0.00017320752,0.000055908815,0.000021391932,0.00019275951,0.00005929274,0.0000047707667],"category_scores_gemma":[0.0027221753,0.00010728144,0.000011941835,0.0005018225,0.00023494715,0.00009788334,0.00019820548,0.00029865943,8.442877e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012719151,0.00013298812,0.039048668,0.0008810379,0.000082733524,0.00045901214,0.011089373,0.00035102825,0.002774984,0.13353285,0.017237343,0.7942828],"study_design_scores_gemma":[0.0034081729,0.0016467227,0.25238103,0.001634272,0.000088696484,0.00024967152,0.00082709675,0.6341227,0.002172196,0.101897866,0.00096396136,0.0006075475],"about_ca_topic_score_codex":0.0000810979,"about_ca_topic_score_gemma":0.00017949105,"teacher_disagreement_score":0.79367524,"about_ca_system_score_codex":0.000020737492,"about_ca_system_score_gemma":0.00005255387,"threshold_uncertainty_score":0.43748102},"labels":[],"label_agreement":null},{"id":"W4387406002","doi":"10.1080/03610918.2023.2263182","title":"An EM algorithm for estimating the parameters of the skew generalized <i>t</i> -normal distribution with application to robust finite mixture modeling","year":2023,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Kurtosis; Skew; Generalized normal distribution; Constructive; Computer science; Mixture model; Algorithm; Distribution (mathematics); Normal distribution; Maximum likelihood; Mathematics; Model selection; Function (biology); Flexibility (engineering); Applied mathematics; Mathematical optimization; Statistics; Process (computing)","score_opus":0.08719294261119219,"score_gpt":0.39163423160508715,"score_spread":0.30444128899389494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387406002","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031628062,0.000027441381,0.9952228,0.00053188764,0.000063484054,0.00079597003,0.00012963418,0.0000602912,0.000005660396],"genre_scores_gemma":[0.39479026,0.000005682062,0.6047084,0.00009630658,0.000008971086,0.00009465068,0.00028629065,0.000006848172,0.000002617352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876827,0.00029924096,0.00037404953,0.00023147531,0.00018157098,0.000145414],"domain_scores_gemma":[0.9976766,0.0010097797,0.00019465384,0.0007861939,0.00028921245,0.00004355609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070367556,0.00011502066,0.00013685225,0.000081192346,0.0004452876,0.000132026,0.0006460103,0.000050969287,1.429925e-7],"category_scores_gemma":[0.00011827743,0.00008318552,0.000024637477,0.00085852586,0.000059905902,0.00020554959,0.00016837232,0.00012761306,5.1466765e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042307934,0.000017406219,0.000025701129,0.000007832301,0.0000038619314,3.440338e-8,0.00087863515,0.6718108,0.000010365777,0.018084096,0.000012769919,0.3091443],"study_design_scores_gemma":[0.0003235409,0.00004116421,0.0006108675,0.000030529216,0.000016141636,8.915443e-7,0.000063120206,0.9553491,0.000013385198,0.043420058,0.00002927782,0.00010196075],"about_ca_topic_score_codex":0.000034111366,"about_ca_topic_score_gemma":0.000048895752,"teacher_disagreement_score":0.39162746,"about_ca_system_score_codex":0.00003501088,"about_ca_system_score_gemma":0.000047793277,"threshold_uncertainty_score":0.34248373},"labels":[],"label_agreement":null},{"id":"W4387661504","doi":"10.1093/sysbio/syad063","title":"Is Over-parameterization a Problem for Profile Mixture Models?","year":2023,"lang":"en","type":"article","venue":"Systematic Biology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Simons Foundation","keywords":"Biology; Evolutionary biology; Statistical physics; Applied mathematics; Computational biology; Mathematics; Physics","score_opus":0.0442729476387585,"score_gpt":0.3134493499119861,"score_spread":0.2691764022732276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387661504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034760924,0.00012379563,0.9925666,0.0007721493,0.00035821955,0.002032701,0.000021659102,0.00029515437,0.0003536329],"genre_scores_gemma":[0.32707506,0.0000049314,0.6709726,0.00038957945,0.00005173823,0.0010784909,0.000021595684,0.00001409255,0.00039190816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984185,0.0002982215,0.00041690492,0.00044513124,0.00009257693,0.00032863076],"domain_scores_gemma":[0.9988446,0.00023368577,0.00019900026,0.00056898466,0.000094868126,0.00005885807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009399497,0.00015707493,0.00042479028,0.00014287926,0.00008901269,0.00007816205,0.0005443354,0.00019928269,0.000004881941],"category_scores_gemma":[0.00007781248,0.00011300661,0.00011419124,0.00043983848,0.000025806145,0.00016961654,0.00017633561,0.00007304692,0.000036542297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058114806,0.000025492243,0.00005751698,0.018185457,0.000070797556,0.0000014494101,0.002253206,0.00006180822,0.0056839227,0.96992254,0.0016173521,0.0021146357],"study_design_scores_gemma":[0.00014458668,0.000066860644,0.000015711339,0.0003882364,0.000010749577,0.00000644143,0.000008006742,0.56811523,0.0005442928,0.4305751,0.000019494197,0.0001052712],"about_ca_topic_score_codex":0.000005606449,"about_ca_topic_score_gemma":0.0000010472135,"teacher_disagreement_score":0.5680534,"about_ca_system_score_codex":0.000020505975,"about_ca_system_score_gemma":0.000048773523,"threshold_uncertainty_score":0.46082756},"labels":[],"label_agreement":null},{"id":"W4387885029","doi":"10.51387/23-nejsds49","title":"Sparse Estimation in Finite Mixture of Accelerated Failure Time and Mixture of Regression Models with R Package fmrs","year":2023,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University; Ohio State University","keywords":"Covariate; Censoring (clinical trials); Regression; Selection (genetic algorithm); Regression analysis; Population; Econometrics; Statistics; Mathematics; Variable (mathematics); Computer science; Artificial intelligence","score_opus":0.039591185034909555,"score_gpt":0.3056892963842625,"score_spread":0.26609811134935296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387885029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029407742,0.0001154527,0.9693833,0.0007103457,0.00007303366,0.00010472892,0.00016348148,0.0000057401753,0.00003618711],"genre_scores_gemma":[0.36927602,0.00021238909,0.6304251,0.00002307683,0.00001988364,3.2817107e-7,0.000013366945,0.000004847874,0.000024994148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828976,0.00017787269,0.0004739483,0.0002535735,0.00059075817,0.00021408433],"domain_scores_gemma":[0.9978971,0.00067878974,0.0004860286,0.00063177396,0.00020974533,0.00009657147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033876374,0.0001245782,0.00030031108,0.00036711234,0.000064586566,0.00008690978,0.0017406021,0.00005371787,0.0000031644984],"category_scores_gemma":[0.000628516,0.000069572,0.000010553399,0.0016819083,0.00027827368,0.0012873203,0.00042854514,0.00031713682,4.9944754e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007907105,0.0002861313,0.0012752535,0.0003473203,0.000066437824,0.00068512635,0.026114322,0.13160866,0.060989056,0.11422199,0.016272806,0.6473422],"study_design_scores_gemma":[0.0014552484,0.00015413474,0.0019291437,0.0004502548,0.0000130981725,0.000082343606,0.00003661189,0.9068331,0.0017392073,0.08714674,0.00005445791,0.00010562872],"about_ca_topic_score_codex":0.000032217587,"about_ca_topic_score_gemma":0.000073757124,"teacher_disagreement_score":0.77522445,"about_ca_system_score_codex":0.000017395949,"about_ca_system_score_gemma":0.00038027015,"threshold_uncertainty_score":0.32345006},"labels":[],"label_agreement":null},{"id":"W4387914368","doi":"10.1109/codit58514.2023.10284408","title":"A Fully Bayesian Inference Approach for Multivariate McDonald's Beta Mixture Model with Feature Selection","year":2023,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Artificial intelligence; Feature selection; Computer science; Gibbs sampling; Bayesian inference; Pattern recognition (psychology); Inference; Multivariate statistics; Gaussian process; Model selection; Bayesian probability; Machine learning; Anomaly detection; Feature (linguistics); Gaussian","score_opus":0.02692799960845288,"score_gpt":0.28787059173035934,"score_spread":0.26094259212190646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387914368","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001027837,0.000020820371,0.9917867,0.0025758606,0.00007754814,0.00064372626,0.000012102044,0.0007185085,0.0040619485],"genre_scores_gemma":[0.0638295,0.0000055673145,0.9272551,0.00055620546,0.000093560804,0.00019239337,0.000029916288,0.00002940315,0.008008355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803525,0.000090255155,0.00018333287,0.000821479,0.00031492332,0.0005547671],"domain_scores_gemma":[0.99888134,0.00012970729,0.000092219925,0.0005109599,0.00021422115,0.00017156385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053475756,0.00029938496,0.00029632176,0.00019736534,0.00025747874,0.0002340779,0.00072792853,0.00022862629,0.0000038029877],"category_scores_gemma":[0.000033522454,0.00021097131,0.00010949591,0.0011763352,0.000033455588,0.00052956503,0.00015396452,0.00030897598,0.00000589583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012033729,0.00016164963,0.00016438766,0.00014832341,0.000129167,0.0000075245985,0.0014932815,0.033920467,0.005294364,0.8473207,0.019078484,0.09216132],"study_design_scores_gemma":[0.0005590758,0.0001250415,0.00021173562,0.000015436126,0.000019132387,0.000016961938,0.000009514084,0.9600062,0.0011371828,0.036944885,0.00062984705,0.00032503338],"about_ca_topic_score_codex":0.000022974658,"about_ca_topic_score_gemma":0.000024755618,"teacher_disagreement_score":0.9260857,"about_ca_system_score_codex":0.000036254252,"about_ca_system_score_gemma":0.00019500832,"threshold_uncertainty_score":0.86031604},"labels":[],"label_agreement":null},{"id":"W4388073351","doi":"10.33137/utjph.v4i1.41676","title":"Relative Risk Regression for Clustered Data with Application to Oral Health Research","year":2023,"lang":"en","type":"article","venue":"University of Toronto Journal of Public Health","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Covariate; Poisson regression; Relative risk; Gee; Generalized estimating equation; Logistic regression; Medicine; Tooth loss; Odds ratio; Demography; Confidence interval; Poisson distribution; Statistics; Cluster (spacecraft); Dentistry; Mathematics; Internal medicine; Oral health; Population; Environmental health","score_opus":0.26711988214744203,"score_gpt":0.43540432009851154,"score_spread":0.1682844379510695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388073351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007548961,0.0003596353,0.9592291,0.038877007,0.00008343464,0.00043699364,0.00004276319,0.0000231568,0.00019298008],"genre_scores_gemma":[0.027116314,0.0007747562,0.9714076,0.00024092168,0.000067372166,3.74118e-7,0.000013397427,0.0000082653805,0.0003710072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707764,0.0013066548,0.00030080654,0.00030995204,0.0005658806,0.00043907706],"domain_scores_gemma":[0.9968716,0.0003619863,0.0006921035,0.00072129245,0.0007616385,0.0005913944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015575893,0.00008301908,0.00032583633,0.00022029292,0.0004457515,0.000038952716,0.0016443452,0.000052408668,0.0000051070037],"category_scores_gemma":[0.00025608082,0.00006829318,0.000046718473,0.00045044633,0.000056439356,0.0015053431,0.0004862556,0.00025156484,0.0000022262407],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009921039,0.00007590226,0.00015135894,0.000060135524,0.000041803578,0.0000035148878,0.009389508,0.000021485173,0.000009909398,0.018282862,0.05147311,0.9203912],"study_design_scores_gemma":[0.005324241,0.009485629,0.03282619,0.0007259329,0.000025951816,0.00006109861,0.008353339,0.123599835,0.000014788685,0.014190559,0.8049437,0.00044875752],"about_ca_topic_score_codex":0.005697975,"about_ca_topic_score_gemma":0.007178387,"teacher_disagreement_score":0.91994244,"about_ca_system_score_codex":0.00063595176,"about_ca_system_score_gemma":0.002141785,"threshold_uncertainty_score":0.86136717},"labels":[],"label_agreement":null},{"id":"W4388201598","doi":"10.3390/sym15111975","title":"Combination Test for Mean Shift and Variance Change","year":2023,"lang":"en","type":"article","venue":"Symmetry","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Variance (accounting); Statistics; Point (geometry); Time point; Mathematics; Analysis of variance; Computer science","score_opus":0.040724641524249955,"score_gpt":0.2968720769037123,"score_spread":0.2561474353794624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388201598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014033754,0.00012519133,0.9934534,0.003182999,0.00035132864,0.00022133473,0.00000689735,0.00017188863,0.0010835768],"genre_scores_gemma":[0.667616,0.000030799958,0.33086064,0.0007969994,0.00014932617,0.000078389065,0.0000054480606,0.000010983886,0.00045137515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99937,0.000033021246,0.00008418043,0.0002438697,0.000091810005,0.00017712377],"domain_scores_gemma":[0.9993688,0.00029211308,0.00003364493,0.00022431412,0.000027817017,0.00005334533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005640995,0.00007075482,0.000093418,0.00009914355,0.00008839956,0.00007167515,0.00022221675,0.00005536942,0.0000010159804],"category_scores_gemma":[0.00009826318,0.00006555075,0.000025287884,0.00043729038,0.000016195818,0.00024614157,0.000101150414,0.000057027763,0.00001457065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.91194e-7,0.000018333378,0.0003638559,0.00003011197,0.0000035690302,0.0000023197372,0.0006588223,4.6295945e-8,0.00015147043,0.75487566,0.0010309755,0.24286397],"study_design_scores_gemma":[0.00062192645,0.00016156334,0.039066043,0.00003336065,0.000008147241,0.0000057023053,0.000014140966,0.076103665,0.0010737901,0.87685597,0.0058211056,0.00023455829],"about_ca_topic_score_codex":0.000008881542,"about_ca_topic_score_gemma":0.0000035771423,"teacher_disagreement_score":0.6662127,"about_ca_system_score_codex":0.000008965505,"about_ca_system_score_gemma":0.000010487733,"threshold_uncertainty_score":0.26730818},"labels":[],"label_agreement":null},{"id":"W4388290228","doi":"10.1093/oso/9780198526155.003.0042","title":"Density Modeling and Clustering Using Dirichlet Diffusion Trees","year":2003,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hierarchical Dirichlet process; Dirichlet distribution; Cluster analysis; Dirichlet process; Mathematics; Hierarchical clustering; Markov chain Monte Carlo; Computer science; Inference; Artificial intelligence; Monte Carlo method; Statistics","score_opus":0.04290611279874024,"score_gpt":0.26092269732299245,"score_spread":0.2180165845242522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388290228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018625396,0.00053935184,0.8684031,0.00008776231,0.00024462797,0.00012708343,9.769481e-7,0.00009503823,0.13031586],"genre_scores_gemma":[0.001794725,0.00025336645,0.93049467,0.0006597707,0.000090630834,8.925506e-7,0.0000011869927,0.00003701533,0.06666776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985233,0.00003767223,0.0002820949,0.0006695123,0.00023200556,0.00025542924],"domain_scores_gemma":[0.99908316,0.00003958574,0.0001036801,0.0005698648,0.00006565518,0.00013805213],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030295295,0.00034882547,0.0004120724,0.00014637162,0.00018177417,0.00018244646,0.000323047,0.00030013872,0.000016590704],"category_scores_gemma":[0.0000084213525,0.00030022673,0.00010128051,0.00003074583,0.0000325498,0.00022233876,0.0005688172,0.00028361156,0.00000328021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061842934,0.000014311936,0.0000073043034,0.00006668964,0.000045380923,0.00006562908,0.0002879023,0.0008300302,0.0010501178,0.7904526,0.00016830242,0.20700555],"study_design_scores_gemma":[0.00011335823,0.000014562943,0.0000010544609,0.000107499414,0.000023156694,0.00008092575,0.0000010158286,0.8661308,0.000030942392,0.13184325,0.0013016401,0.0003517719],"about_ca_topic_score_codex":0.00003706218,"about_ca_topic_score_gemma":0.000043165554,"teacher_disagreement_score":0.8653008,"about_ca_system_score_codex":0.00004773064,"about_ca_system_score_gemma":0.000031129854,"threshold_uncertainty_score":0.999945},"labels":[],"label_agreement":null},{"id":"W4388448446","doi":"10.52843/cassyni.twgt9r","title":"Flexible hidden Markov models using hmmTMB and applications in ecology","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Hidden Markov model; Covariate; Computer science; Ecology; Markov model; Class (philosophy); Markov chain; Parametric statistics; Econometrics; Data science; Machine learning; Artificial intelligence; Statistics; Mathematics; Biology","score_opus":0.08202821677245688,"score_gpt":0.333079564558064,"score_spread":0.2510513477856071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388448446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011566397,0.00019796343,0.9916759,0.0006323967,0.00027261037,0.0005910102,0.0000067931574,0.00028018033,0.005186514],"genre_scores_gemma":[0.018954093,0.00014054836,0.9786474,0.00021853822,0.00008289302,0.00017470581,0.000007491808,0.0000233658,0.0017509786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819475,0.00014560863,0.00032479482,0.0008783691,0.00013091203,0.00032555524],"domain_scores_gemma":[0.99869406,0.0001671336,0.000103060614,0.000884879,0.000050405204,0.000100482095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063469744,0.00022673552,0.0003721688,0.00033541062,0.00007526743,0.00016456109,0.00087098137,0.00035307504,0.0000062313584],"category_scores_gemma":[0.000011075021,0.0002135965,0.00006329752,0.0003224036,0.00004693678,0.0001819403,0.0026024636,0.0004434018,0.0000059486324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025590293,0.00005787151,0.0005730721,0.00014535795,0.00003075293,0.000014112576,0.0005091618,0.004237705,0.000086766595,0.85784423,0.00039174795,0.13610666],"study_design_scores_gemma":[0.00006397014,0.000004520603,0.00039508435,0.000018656221,0.0000054897214,0.000004386882,0.000005653008,0.45654646,0.00005096221,0.5426955,0.000058590613,0.00015072135],"about_ca_topic_score_codex":0.00037820448,"about_ca_topic_score_gemma":0.00014320092,"teacher_disagreement_score":0.45230874,"about_ca_system_score_codex":0.00007509049,"about_ca_system_score_gemma":0.00020256461,"threshold_uncertainty_score":0.8710213},"labels":[],"label_agreement":null},{"id":"W4388622580","doi":"10.1093/jrsssc/qlad100","title":"A Bayesian latent class model for integrating multi-source longitudinal data: application to the CHILD cohort study","year":2023,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto; Queen's University","funders":"Institute of Circulatory and Respiratory Health; Natural Sciences and Engineering Research Council of Canada; AstraZeneca Canada; Canadian Institutes of Health Research; Canadian Lung Association; Canadian Allergy, Asthma and Immunology Foundation; AstraZeneca","keywords":"Cluster analysis; Longitudinal data; Computer science; Bayesian probability; Data set; Latent class model; Data mining; Longitudinal study; Set (abstract data type); Class (philosophy); Statistics; Artificial intelligence; Machine learning; Mathematics","score_opus":0.03344844872546207,"score_gpt":0.30899599874585554,"score_spread":0.27554755002039344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388622580","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012633554,0.000015965767,0.9939662,0.0029867622,0.00035389428,0.0015952392,0.0008351859,0.000064074164,0.000056301207],"genre_scores_gemma":[0.1722819,0.000009485545,0.8263176,0.0005627809,0.00022671063,0.00012923087,0.00003590787,0.00003634817,0.00039999196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968762,0.00019614596,0.0009103317,0.0006158379,0.0008553734,0.0005461296],"domain_scores_gemma":[0.9968373,0.0009066478,0.00053095445,0.0011479874,0.0003223663,0.00025473343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030800977,0.00032118356,0.000529283,0.000038960257,0.0009851836,0.000383269,0.0026451098,0.000098824574,0.00000461017],"category_scores_gemma":[0.0005415078,0.0001890696,0.00016127595,0.0005204576,0.00015857581,0.00017689256,0.0011114313,0.0006846701,0.000008586007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002743653,0.00070831744,0.00230444,0.00014173244,0.0008455098,0.000014565539,0.009220382,0.16109268,0.000084132604,0.54874736,0.15196437,0.12460218],"study_design_scores_gemma":[0.00055859797,0.00017995603,0.008978405,0.000020749096,0.00017136995,0.000012510958,0.0003549145,0.96680045,0.000008007903,0.020734558,0.0019489161,0.0002315797],"about_ca_topic_score_codex":0.00003897702,"about_ca_topic_score_gemma":0.00014245945,"teacher_disagreement_score":0.80570775,"about_ca_system_score_codex":0.00014277527,"about_ca_system_score_gemma":0.00016678164,"threshold_uncertainty_score":0.7710034},"labels":[],"label_agreement":null},{"id":"W4388630951","doi":"10.1007/s00357-023-09453-z","title":"Model-Based Clustering with Nested Gaussian Clusters","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Linear subspace; Pattern recognition (psychology); Artificial intelligence; Mathematics; Hierarchical clustering; Model selection; Single-linkage clustering; Mixture model; Bayesian information criterion; Gaussian; Computer science; Determining the number of clusters in a data set; Correlation clustering; CURE data clustering algorithm; Physics","score_opus":0.05773895718962707,"score_gpt":0.3019908204385257,"score_spread":0.24425186324889864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388630951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052537774,0.00001561036,0.9874095,0.0061464016,0.00019638616,0.00007576718,4.066858e-7,0.00006827138,0.0008339346],"genre_scores_gemma":[0.5659461,0.000007777114,0.43362364,0.00021316792,0.00006362073,0.000002804751,8.936834e-7,0.000008828161,0.00013316609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988919,0.00010219536,0.00034013222,0.00015846793,0.00033341194,0.0001738871],"domain_scores_gemma":[0.99891776,0.000070008,0.0003924678,0.00032399426,0.00018236593,0.0001134011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007934082,0.00010000658,0.00016646073,0.00029370227,0.000076760465,0.0001154777,0.00048013084,0.00005949392,0.0000013325025],"category_scores_gemma":[0.000028820026,0.00007231359,0.000068296395,0.0006310452,0.000027676599,0.00048683304,0.000030703337,0.00017105325,0.0000074333107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031066782,0.00021486686,0.0008343571,0.00015986014,0.00010431243,0.00015991976,0.002729619,0.23828313,0.045107007,0.07072105,0.006485363,0.63488984],"study_design_scores_gemma":[0.00043527165,0.00009950671,0.0035251775,0.00006422978,0.000011892002,0.000042262276,0.000022549739,0.991638,0.0005085725,0.003195755,0.0003615633,0.000095192314],"about_ca_topic_score_codex":7.7581376e-7,"about_ca_topic_score_gemma":0.0000030728295,"teacher_disagreement_score":0.7533549,"about_ca_system_score_codex":0.000056355293,"about_ca_system_score_gemma":0.0001954444,"threshold_uncertainty_score":0.29488626},"labels":[],"label_agreement":null},{"id":"W4388717896","doi":"10.48550/arxiv.2311.07762","title":"Finite Mixtures of Multivariate Poisson-Log Normal Factor Analyzers for Clustering Count Data","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Mixture model; Multivariate statistics; Context (archaeology); Poisson distribution; Computer science; Count data; Covariance matrix; Model selection; Factor analysis; Multivariate normal distribution; Gaussian; Mathematics; Data mining; Statistics; Algorithm; Artificial intelligence; Physics","score_opus":0.19210818096974885,"score_gpt":0.2653047640172036,"score_spread":0.07319658304745474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388717896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005059505,0.000051524894,0.99200237,0.00013074648,0.0011430719,0.00047836537,0.0007425612,0.0002058035,0.00018603214],"genre_scores_gemma":[0.7622558,0.00012266875,0.23596804,0.00007707843,0.0001179387,0.0000020154368,0.00016341628,0.000038480848,0.001254544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973081,0.0001884547,0.00035703563,0.0015330792,0.00013536276,0.00047799633],"domain_scores_gemma":[0.995917,0.0005825426,0.00046982412,0.0026343125,0.00021975192,0.00017656152],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007072553,0.00038398194,0.0005839108,0.00036855074,0.00014320371,0.00011739723,0.004268074,0.0003656158,0.0000102877775],"category_scores_gemma":[0.00018006148,0.0004096318,0.00026337398,0.00050724274,0.000096623895,0.0005132725,0.005687754,0.00045766574,0.000008626628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045159002,0.00037851237,0.0016452582,0.002004248,0.0017014525,0.0005515806,0.0026818966,0.73490286,0.0021961473,0.23221302,0.002851235,0.018422209],"study_design_scores_gemma":[0.0005519749,0.00004553506,0.00057372573,0.00012779146,0.00010184725,0.0000013368544,0.000012662711,0.96860355,0.00035963027,0.028642656,0.0005467633,0.0004325454],"about_ca_topic_score_codex":0.00054205256,"about_ca_topic_score_gemma":0.00016591384,"teacher_disagreement_score":0.7571963,"about_ca_system_score_codex":0.00009375838,"about_ca_system_score_gemma":0.00024668584,"threshold_uncertainty_score":0.99983555},"labels":[],"label_agreement":null},{"id":"W4388797385","doi":"10.1007/s11749-023-00899-2","title":"Application of the Cramér–Wold theorem to testing for invariance under group actions","year":2023,"lang":"en","type":"article","venue":"Test","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Agencia Nacional de Investigación e Innovación","keywords":"Mathematics; Invariant (physics); Dimension (graph theory); Group (periodic table); Multivariate statistics; Sign (mathematics); Applied mathematics; Statistical hypothesis testing; Discrete mathematics; Pure mathematics; Statistics; Mathematical analysis","score_opus":0.06941431106384507,"score_gpt":0.32000252639232646,"score_spread":0.2505882153284814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388797385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007718305,0.000004923961,0.99347943,0.0032347655,0.00012588261,0.0003429372,0.000005428304,0.00013320844,0.0019016162],"genre_scores_gemma":[0.5256003,3.898873e-7,0.47346866,0.00054277485,0.000055436783,0.00010147574,7.442908e-7,0.0000064052006,0.00022376853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994458,0.000026880358,0.0001121926,0.00019107129,0.00008811164,0.00013597535],"domain_scores_gemma":[0.9986039,0.000779855,0.000059963673,0.00046092487,0.000061526465,0.00003384663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040316797,0.0000572669,0.00007072018,0.000036470185,0.00012542102,0.000031012874,0.0005079605,0.000029693647,7.082567e-7],"category_scores_gemma":[0.00033471466,0.000041187428,0.000034069868,0.00088700984,0.000021653384,0.00008502381,0.00013929917,0.000053544267,0.00001359258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.5446346e-7,0.00001942775,0.00041268923,0.000009723379,0.0000022955505,6.536719e-8,0.00012707186,0.00017636795,0.031144189,0.8898844,0.00065126456,0.07757185],"study_design_scores_gemma":[0.00013293419,0.000066922556,0.03415256,0.000030507506,0.0000074113345,0.0000034456675,0.000015385514,0.15634073,0.004812667,0.80214643,0.002170998,0.00011997834],"about_ca_topic_score_codex":0.000024998422,"about_ca_topic_score_gemma":0.000014118089,"teacher_disagreement_score":0.5248285,"about_ca_system_score_codex":0.000014540622,"about_ca_system_score_gemma":0.000026574387,"threshold_uncertainty_score":0.16795745},"labels":[],"label_agreement":null},{"id":"W4388908050","doi":"10.1007/978-981-99-6141-2_7","title":"Finite Mixture MLE and EM Algorithm","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convergence (economics); Algorithm; Expectation–maximization algorithm; Mixture model; Computer science; Maximum likelihood; Mathematical optimization; Mathematics; Applied mathematics; Artificial intelligence; Statistics","score_opus":0.020247387970120517,"score_gpt":0.2637250609370861,"score_spread":0.24347767296696557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388908050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.689911e-8,0.0013102137,0.91204447,0.00015910239,0.00086545595,0.00022107908,0.0009812921,0.00015078126,0.08426755],"genre_scores_gemma":[5.6479496e-7,0.0028860513,0.59570456,0.00036779814,0.00011437805,0.000009397757,0.000052071322,0.000054478613,0.4008107],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806696,0.00005037962,0.00046907863,0.0006846305,0.0003510574,0.0003778722],"domain_scores_gemma":[0.9983193,0.00048154287,0.00020690692,0.00072425965,0.00012316827,0.00014480298],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031437518,0.00044893837,0.00055995095,0.00021364946,0.0001056741,0.0002264651,0.0005925704,0.00044472353,0.00006015703],"category_scores_gemma":[0.00008320825,0.000459543,0.000054956923,0.00007837378,0.00019056904,0.00036018033,0.0005551339,0.00067789137,0.000056317815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003983416,0.0000037889827,5.42223e-7,0.000062637766,0.00002054185,0.00043534482,0.00052418205,0.0000026708194,6.448217e-7,0.740556,0.009261258,0.24912839],"study_design_scores_gemma":[0.00015474507,0.00008043604,0.000007736836,0.00013635485,0.000018402061,0.000038355513,0.000005544587,0.0071360446,0.0000064179853,0.66408336,0.32791996,0.00041260978],"about_ca_topic_score_codex":0.000009048083,"about_ca_topic_score_gemma":0.000105252606,"teacher_disagreement_score":0.3186587,"about_ca_system_score_codex":0.00005227484,"about_ca_system_score_gemma":0.0001379343,"threshold_uncertainty_score":0.9997856},"labels":[],"label_agreement":null},{"id":"W4388908080","doi":"10.1007/978-981-99-6141-2_5","title":"Consistent Estimation Under Finite Gamma Mixture","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Maximum likelihood; Likelihood function; Mixture model; Function (biology); Mathematics; Applied mathematics; Computer science; Statistics; Econometrics","score_opus":0.03360898757418368,"score_gpt":0.28115790041213035,"score_spread":0.24754891283794667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388908080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.528591e-8,0.000482445,0.84884393,0.00049537094,0.001093688,0.00029157748,0.0004756032,0.00019381824,0.14812347],"genre_scores_gemma":[0.000009713201,0.00096234505,0.5947155,0.00067671906,0.00007716008,0.000016112175,0.0001321698,0.00006374919,0.40334654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997707,0.0000720186,0.0006652545,0.00067876186,0.00048302294,0.0003939577],"domain_scores_gemma":[0.9977003,0.00071076077,0.00033902316,0.0009237088,0.00019406919,0.00013213989],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036990864,0.00048717647,0.00058230985,0.00026265386,0.00011131819,0.00021133201,0.00066443445,0.00048553664,0.00011030177],"category_scores_gemma":[0.00014995574,0.0005041548,0.00009657992,0.00009615844,0.0002307877,0.00040294018,0.00037073912,0.0006589234,0.00017685232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008760857,0.00000779433,5.380051e-7,0.00010760331,0.00003518422,0.00026253588,0.00026727124,0.0003894246,0.0000020179586,0.9434037,0.012665766,0.04284938],"study_design_scores_gemma":[0.00017859919,0.00007874358,0.000013636433,0.00024504174,0.00003310292,0.00003102475,0.000004089149,0.02426557,0.000013235491,0.8298973,0.14475136,0.0004883385],"about_ca_topic_score_codex":0.000009650847,"about_ca_topic_score_gemma":0.00011967068,"teacher_disagreement_score":0.25522307,"about_ca_system_score_codex":0.00014607082,"about_ca_system_score_gemma":0.00027388483,"threshold_uncertainty_score":0.999741},"labels":[],"label_agreement":null},{"id":"W4388917310","doi":"10.1007/978-981-99-6141-2_11","title":"Modified Likelihood Ratio Test","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Likelihood-ratio test; Ratio test; Homogeneity (statistics); Likelihood principle; Likelihood function; Mathematics; Limiting; Score test; Identifiability; Statistics; Restricted maximum likelihood; Maximum likelihood; Econometrics; Quasi-maximum likelihood; Engineering","score_opus":0.028681725969750514,"score_gpt":0.2727089850591414,"score_spread":0.24402725908939085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388917310","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.835473e-8,0.0002853294,0.69404024,0.00020114808,0.0007883955,0.00024380597,0.0006515887,0.00019667328,0.30359277],"genre_scores_gemma":[0.0000104490055,0.0014085117,0.5043725,0.0004028297,0.00015588006,0.000021883341,0.00007081098,0.00007940705,0.49347776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975683,0.000046616904,0.00068545196,0.0007422076,0.0004680537,0.0004893591],"domain_scores_gemma":[0.9975578,0.000720497,0.00028887775,0.001088154,0.00018613102,0.00015849185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040850526,0.00050177856,0.00061916915,0.0002528298,0.000114148825,0.00023243179,0.0010160124,0.00043059612,0.00007720805],"category_scores_gemma":[0.00021985434,0.0005307445,0.00008414541,0.00010089894,0.00018147074,0.00046791477,0.00049891806,0.0006891051,0.00020503468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051684356,0.00001279133,0.0000014168427,0.00006986044,0.00001951069,0.00033419544,0.00027577186,0.000016230226,0.0000075510316,0.9417663,0.017297126,0.04019405],"study_design_scores_gemma":[0.0001985079,0.00013025732,0.000011538467,0.0001476992,0.000020690304,0.0000213463,0.0000028430554,0.007864055,0.000029762115,0.8567647,0.1342574,0.0005512296],"about_ca_topic_score_codex":0.000015144854,"about_ca_topic_score_gemma":0.00017158264,"teacher_disagreement_score":0.18988498,"about_ca_system_score_codex":0.000114645525,"about_ca_system_score_gemma":0.00034880242,"threshold_uncertainty_score":0.99971443},"labels":[],"label_agreement":null},{"id":"W4388917371","doi":"10.1007/978-981-99-6141-2_10","title":"Likelihood Ratio Test for Homogeneity","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Homogeneity (statistics); Likelihood-ratio test; Limiting; Computer science; Mathematics; Likelihood principle; Econometrics; Likelihood function; Statistics; Maximum likelihood; Machine learning; Engineering; Quasi-maximum likelihood; Mechanical engineering","score_opus":0.030332053576731365,"score_gpt":0.28661976918656185,"score_spread":0.2562877156098305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388917371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.052953e-8,0.00043397702,0.90302277,0.00024148835,0.0010456411,0.00057756,0.0027466912,0.00018074263,0.091751054],"genre_scores_gemma":[0.0000030059,0.0010072006,0.6348585,0.00033753493,0.00019505482,0.000059731115,0.00011441759,0.000075559146,0.36334902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978618,0.00003090136,0.00061013375,0.0007072426,0.00032246535,0.00046742594],"domain_scores_gemma":[0.9973842,0.0010395506,0.00027602032,0.000915176,0.00024999565,0.00013508291],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047925222,0.00044485833,0.00058526493,0.00018884827,0.00014066583,0.00018367334,0.0008717702,0.00038324692,0.000039792896],"category_scores_gemma":[0.00030656627,0.00047450894,0.00010869739,0.00007425958,0.0001541629,0.00036164164,0.0003611203,0.00040356247,0.0000646651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007281808,0.000013421442,0.0000032556475,0.000121358025,0.000022091263,0.00008273716,0.00016889954,0.000003483299,0.000010607638,0.92317754,0.023305872,0.05308348],"study_design_scores_gemma":[0.00020124404,0.00017790993,0.000011909772,0.0000964021,0.000024850477,0.000012280696,0.0000023039381,0.0030578088,0.00007892638,0.735821,0.26007873,0.0004366274],"about_ca_topic_score_codex":0.0000092615965,"about_ca_topic_score_gemma":0.00028722064,"teacher_disagreement_score":0.27159798,"about_ca_system_score_codex":0.000104825456,"about_ca_system_score_gemma":0.00036538733,"threshold_uncertainty_score":0.99977064},"labels":[],"label_agreement":null},{"id":"W4388919442","doi":"10.1007/978-981-99-6141-2","title":"Statistical Inference Under Mixture Models","year":2023,"lang":"en","type":"book","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"University of British Columbia; University of Waterloo","keywords":"Inference; Statistical inference; Statistical model; Mixture model; Computer science; Artificial intelligence; Econometrics; Mathematics; Statistics","score_opus":0.03866841912093741,"score_gpt":0.31401666434272063,"score_spread":0.27534824522178325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919442","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.501838e-8,0.00062843325,0.8405832,0.00023885204,0.0011477199,0.00035680732,0.0019862587,0.0002969339,0.15476173],"genre_scores_gemma":[0.0000063601215,0.0013880554,0.5510234,0.0006629941,0.00013550156,0.000035915582,0.00026622927,0.000086968284,0.44639453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99606854,0.00023939926,0.00091320986,0.0011353275,0.0008168926,0.0008266579],"domain_scores_gemma":[0.996121,0.0016272088,0.0003214497,0.001386305,0.000268452,0.00027558175],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005474577,0.0007307442,0.00096659584,0.00034345782,0.00013871763,0.0003487279,0.0016192757,0.00076803734,0.00012222289],"category_scores_gemma":[0.00024536546,0.0007475629,0.00008722508,0.00027950644,0.00040687452,0.000925501,0.00086947344,0.0013876328,0.00016839338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001099858,0.000020743077,9.604419e-7,0.000161072,0.000033683893,0.00043311893,0.0003736683,0.00035901586,0.0000012942091,0.84411705,0.13830924,0.016179146],"study_design_scores_gemma":[0.00020800153,0.00010483642,0.00002110371,0.00021490862,0.00003006201,0.000024239363,0.0000061647534,0.031446747,0.0000037598002,0.86916983,0.09805761,0.0007127252],"about_ca_topic_score_codex":0.000024652947,"about_ca_topic_score_gemma":0.0002508734,"teacher_disagreement_score":0.29163277,"about_ca_system_score_codex":0.00037270857,"about_ca_system_score_gemma":0.0015634728,"threshold_uncertainty_score":0.99949753},"labels":[],"label_agreement":null},{"id":"W4388919450","doi":"10.1007/978-981-99-6141-2_9","title":"Test of Homogeneity","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Homogeneity (statistics); Limiting; Likelihood-ratio test; Statistic; Mathematics; Parameter space; Test statistic; Applied mathematics; Statistics; Statistical physics; Statistical hypothesis testing; Physics; Engineering","score_opus":0.030193654559904595,"score_gpt":0.2799743042109505,"score_spread":0.2497806496510459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919450","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8126684e-7,0.0003918645,0.7657745,0.000065709064,0.0004906681,0.00015241552,0.00097500125,0.000076603,0.2320731],"genre_scores_gemma":[0.000011534444,0.0016332256,0.59854364,0.000106807194,0.000061645194,0.000006367802,0.00002954869,0.000045720684,0.3995615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99828565,0.00003195377,0.00058870396,0.00046517336,0.00035457785,0.0002739329],"domain_scores_gemma":[0.99791,0.0006160476,0.00031681545,0.0008989157,0.00017405077,0.00008412174],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034794956,0.00031948983,0.0005691674,0.00019484086,0.000046395922,0.00004701492,0.0008337157,0.00029338954,0.000066106724],"category_scores_gemma":[0.00018706967,0.0003359161,0.00007457037,0.00008296393,0.00024193613,0.00022795825,0.0004564643,0.0003864105,0.00004734093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003601099,0.000011719369,0.000011311748,0.00011928233,0.00001680988,0.00015812945,0.00016842266,0.0000034887769,0.000015968231,0.95730036,0.006364957,0.03582595],"study_design_scores_gemma":[0.00012158598,0.00013371132,0.00006308927,0.00017087864,0.00001902745,0.000016269394,0.0000016879903,0.0007873861,0.00017741256,0.8612381,0.1369125,0.00035832735],"about_ca_topic_score_codex":0.000018558181,"about_ca_topic_score_gemma":0.00014407995,"teacher_disagreement_score":0.16748838,"about_ca_system_score_codex":0.000055673532,"about_ca_system_score_gemma":0.00021933198,"threshold_uncertainty_score":0.9999093},"labels":[],"label_agreement":null},{"id":"W4388919456","doi":"10.1007/978-981-99-6141-2_16","title":"Order Selection of the Finite Mixture Models","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian information criterion; Akaike information criterion; Information Criteria; Model selection; Selection (genetic algorithm); Bayesian probability; Computer science; Regularization (linguistics); Finite set; Mathematics; Mathematical optimization; Machine learning; Artificial intelligence; Applied mathematics","score_opus":0.02678103894673379,"score_gpt":0.2619892762136214,"score_spread":0.2352082372668876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5719267e-7,0.00023090953,0.8640464,0.00018535761,0.00082074094,0.00025511303,0.00034416947,0.0000718302,0.1340453],"genre_scores_gemma":[0.000023328299,0.0009346444,0.54278725,0.00027678988,0.00007315073,0.000010945073,0.000017000963,0.000054658023,0.4558222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982367,0.000077447214,0.0005283066,0.00045207771,0.00043240085,0.0002730623],"domain_scores_gemma":[0.9981684,0.00034834718,0.00035841562,0.0007539719,0.0003183504,0.000052488358],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030264287,0.0003367013,0.00044992514,0.00015316338,0.00009547379,0.000063360574,0.0008786081,0.00038909222,0.000053506006],"category_scores_gemma":[0.0001096138,0.00027371835,0.000087297856,0.00020526767,0.00019066042,0.0003492762,0.00042238453,0.0006529025,0.000011922905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007672877,0.0000067265496,0.000001807859,0.00008826715,0.000026770775,0.00001539043,0.00040622248,0.0008010335,0.0000066155653,0.9792437,0.0066731474,0.012722661],"study_design_scores_gemma":[0.00010718712,0.00005306743,0.0000087176995,0.00018170514,0.000024329287,0.000011235081,0.0000020607552,0.04468534,0.00006143663,0.8802492,0.07434222,0.00027347263],"about_ca_topic_score_codex":0.00001948282,"about_ca_topic_score_gemma":0.00023593317,"teacher_disagreement_score":0.32177693,"about_ca_system_score_codex":0.00006853542,"about_ca_system_score_gemma":0.00030079542,"threshold_uncertainty_score":0.9999715},"labels":[],"label_agreement":null},{"id":"W4388919457","doi":"10.1007/978-981-99-6141-2_8","title":"Rate of Convergence","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Rate of convergence; Minimax; Convergence (economics); Order (exchange); Applied mathematics; Mathematics; Sample (material); Mathematical optimization; Computer science; Statistics; Thermodynamics; Physics; Economics","score_opus":0.03094015509816013,"score_gpt":0.27939007312121644,"score_spread":0.24844991802305633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8549984e-7,0.00035925343,0.82455957,0.000086033826,0.0009908266,0.00015970515,0.00041725757,0.000070062866,0.17335713],"genre_scores_gemma":[0.000010147064,0.0028263594,0.5061001,0.00019008665,0.000043946013,0.0000063270118,0.000021230382,0.000040462724,0.4907613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983845,0.000057011046,0.0005982868,0.00045418856,0.00023956066,0.00026649726],"domain_scores_gemma":[0.998258,0.00037259542,0.0003377884,0.0007740187,0.0001784529,0.00007915878],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045170804,0.0003019817,0.00054149854,0.00017501519,0.000038316633,0.000040458668,0.00080892706,0.00024862683,0.00013468188],"category_scores_gemma":[0.000096825956,0.00031748,0.000064067346,0.00007959365,0.00025097167,0.00027443178,0.000381986,0.0003587123,0.000075316246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007737167,0.0000044753065,0.0000021068572,0.00012361741,0.00002029735,0.00016900784,0.00024960173,0.0000068489717,0.000014530947,0.9769375,0.008228948,0.014235333],"study_design_scores_gemma":[0.000103337894,0.00007729006,0.00001640176,0.00016444857,0.0000131684865,0.000007665143,0.0000020541231,0.0015143956,0.00014406469,0.8420107,0.15564884,0.000297635],"about_ca_topic_score_codex":0.000018426692,"about_ca_topic_score_gemma":0.000063112624,"teacher_disagreement_score":0.31845942,"about_ca_system_score_codex":0.00004312991,"about_ca_system_score_gemma":0.00021610766,"threshold_uncertainty_score":0.9999277},"labels":[],"label_agreement":null},{"id":"W4388919464","doi":"10.1007/978-981-99-6141-2_15","title":"em-Test for Univariate Finite Gaussian Mixture Models","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Univariate; Likelihood-ratio test; Gaussian; Mixture model; Test statistic; Applied mathematics; Statistics; Null distribution; Statistic; Limiting; Null (SQL); Chi-square test; Statistical hypothesis testing; Statistical physics; Multivariate statistics; Computer science; Physics; Engineering","score_opus":0.035984570603963734,"score_gpt":0.27973661657053894,"score_spread":0.2437520459665752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919464","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.466915e-8,0.00039983666,0.85823655,0.00036633498,0.0010955727,0.0006222135,0.003453329,0.00023485912,0.13559125],"genre_scores_gemma":[0.000005769089,0.0011877432,0.5696724,0.0004476778,0.00017361177,0.00004405575,0.00019559628,0.00011960499,0.42815354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970979,0.000054533048,0.0007952321,0.00096700917,0.00042963942,0.0006556746],"domain_scores_gemma":[0.9963827,0.001514629,0.00040882203,0.0012301381,0.0002644329,0.00019923586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052501884,0.00068271154,0.00083833304,0.00033855156,0.00017584486,0.00029445856,0.001270504,0.00067829917,0.00004780856],"category_scores_gemma":[0.00023370238,0.0007052406,0.00015734338,0.00012759013,0.00016753338,0.00068916444,0.00048378677,0.0007355682,0.000047073372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019755373,0.000015049383,3.1055922e-7,0.00019481077,0.00004093015,0.00021738869,0.00077949243,0.0002437778,0.0000026550974,0.96194243,0.013671367,0.022872005],"study_design_scores_gemma":[0.00028133034,0.0001566366,0.0000018675668,0.00023349022,0.00003806208,0.000013416623,0.000005694588,0.059533793,0.000008524958,0.75076103,0.188369,0.00059713534],"about_ca_topic_score_codex":0.000011640648,"about_ca_topic_score_gemma":0.00023797652,"teacher_disagreement_score":0.29256228,"about_ca_system_score_codex":0.00013020642,"about_ca_system_score_gemma":0.00037253075,"threshold_uncertainty_score":0.99953985},"labels":[],"label_agreement":null},{"id":"W4388919478","doi":"10.1007/978-981-99-6141-2_14","title":"em-Test for Higher Order","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Presentation (obstetrics); Extension (predicate logic); Test (biology); Limiting; Range (aeronautics); Computer science; Null hypothesis; Null (SQL); Order (exchange); Likelihood-ratio test; Mathematics; Applied mathematics; Statistics; Engineering; Data mining; Mechanical engineering; Programming language; Ecology; Biology; Economics","score_opus":0.03627644799870371,"score_gpt":0.29648589773633977,"score_spread":0.26020944973763604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1292262e-8,0.00033699285,0.8337037,0.00030860872,0.0016045158,0.00040499517,0.001142544,0.00017098227,0.16232762],"genre_scores_gemma":[5.8778585e-7,0.00046880625,0.50194424,0.000423795,0.00015933656,0.000036117464,0.000064559514,0.000070425194,0.49683216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980081,0.000024364685,0.0005433362,0.0006672911,0.00031714502,0.00043979677],"domain_scores_gemma":[0.9976032,0.00093380926,0.00023718273,0.0008325832,0.00028259115,0.000110666995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003253238,0.0004373847,0.0005623687,0.0001838285,0.000101087295,0.00018298844,0.00082389696,0.00039722753,0.00015325955],"category_scores_gemma":[0.00017769737,0.00044921643,0.000082170554,0.00008865242,0.00014889584,0.00031871584,0.0003494987,0.0004117541,0.00009902317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007742897,0.000009579,9.723925e-7,0.00011614352,0.000022096618,0.000100759185,0.00019530216,0.0000041016883,0.000002078948,0.91087174,0.052013103,0.0366564],"study_design_scores_gemma":[0.00014574996,0.00009422634,0.0000065335257,0.00007608946,0.000015085312,0.000005223701,0.0000013310887,0.0007867317,0.0000061031315,0.52954644,0.46900767,0.00030880494],"about_ca_topic_score_codex":0.0000059969398,"about_ca_topic_score_gemma":0.00013740327,"teacher_disagreement_score":0.41699457,"about_ca_system_score_codex":0.00008541653,"about_ca_system_score_gemma":0.00022254392,"threshold_uncertainty_score":0.999796},"labels":[],"label_agreement":null},{"id":"W4388919496","doi":"10.1007/978-981-99-6141-2_3","title":"Maximum Likelihood Estimation Under Finite Mixture Models","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Maximum likelihood; Estimator; Mixture model; Consistency (knowledge bases); Restricted maximum likelihood; Expectation–maximization algorithm; Mathematics; Maximum likelihood sequence estimation; Statistics; Nonparametric statistics; Applied mathematics; Computer science; Econometrics; Artificial intelligence","score_opus":0.030596645491937087,"score_gpt":0.2730356842442617,"score_spread":0.24243903875232464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.1004616e-8,0.00058844086,0.83533245,0.00041458648,0.0010193837,0.00033952878,0.0006365523,0.0002728182,0.16139618],"genre_scores_gemma":[0.000011569378,0.0017143312,0.7448015,0.00075777696,0.00011524128,0.000025608226,0.00019422478,0.000116075236,0.25226367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971304,0.00007529529,0.0007591281,0.00086256757,0.00060802384,0.00056459225],"domain_scores_gemma":[0.99754894,0.0005415533,0.00036678757,0.0011455893,0.00022225175,0.0001748847],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004436684,0.0006250212,0.00068388233,0.0003545668,0.0001352743,0.00026808062,0.00097871,0.00067054236,0.0000787358],"category_scores_gemma":[0.00008201182,0.0006589409,0.00011173768,0.00013700673,0.00017783626,0.00095752755,0.0005140669,0.0008803669,0.00015677093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010354073,0.000011000178,1.6090054e-7,0.00011118277,0.000035029567,0.00018846276,0.00040995187,0.002497708,0.0000014673315,0.9052456,0.008175963,0.083313145],"study_design_scores_gemma":[0.00017980525,0.00007623439,0.000002432396,0.00022210088,0.000030736584,0.000019143332,0.0000036143672,0.17177425,0.0000083763225,0.79665226,0.030486764,0.0005442705],"about_ca_topic_score_codex":0.000015862819,"about_ca_topic_score_gemma":0.00012796931,"teacher_disagreement_score":0.16927654,"about_ca_system_score_codex":0.00016469053,"about_ca_system_score_gemma":0.0003356612,"threshold_uncertainty_score":0.99958616},"labels":[],"label_agreement":null},{"id":"W4388919513","doi":"10.1007/978-981-99-6141-2_12","title":"Modified Likelihood Ratio Test for Higher Order","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Likelihood-ratio test; Homogeneity (statistics); Null hypothesis; Null (SQL); Statistical hypothesis testing; Mathematics; Computer science; Statistics; Econometrics; Data mining","score_opus":0.036665055143839526,"score_gpt":0.28913830992886225,"score_spread":0.2524732547850227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1644407e-8,0.00028516364,0.82499015,0.00042881563,0.0014127404,0.00056258787,0.0013879775,0.00018876651,0.17074376],"genre_scores_gemma":[0.0000032654707,0.00045635997,0.5257232,0.0004621346,0.00019150255,0.00006662082,0.00010161957,0.00008251618,0.4729128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976898,0.00003226136,0.00065799116,0.00075189664,0.00035951167,0.0005085778],"domain_scores_gemma":[0.9972759,0.0010309104,0.0002855151,0.0009104772,0.00036384587,0.00013337699],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037452122,0.0004997119,0.00062762393,0.00020449654,0.00012824475,0.00021565417,0.0008455567,0.0004525164,0.000086595224],"category_scores_gemma":[0.00021401628,0.00051319145,0.00008924694,0.00010460678,0.00016440311,0.00039650616,0.00032918988,0.00045383905,0.00006910886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001222236,0.000015262285,7.3747367e-7,0.00011834795,0.000028654384,0.00007350375,0.00016377938,0.000023093455,0.000007291565,0.9376013,0.034522153,0.027433643],"study_design_scores_gemma":[0.000285606,0.00014492932,0.0000062176364,0.00009093835,0.000025147428,0.000005129595,0.0000013499232,0.0060425354,0.000017839351,0.6828513,0.31008384,0.0004451812],"about_ca_topic_score_codex":0.000010416201,"about_ca_topic_score_gemma":0.00011604335,"teacher_disagreement_score":0.30216902,"about_ca_system_score_codex":0.00010061816,"about_ca_system_score_gemma":0.00034768516,"threshold_uncertainty_score":0.99973196},"labels":[],"label_agreement":null},{"id":"W4388919539","doi":"10.1007/978-981-99-6141-2_2","title":"Non-Parametric MLE and Its Consistency","year":2023,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nonparametric statistics; Consistency (knowledge bases); Estimator; Parametric statistics; Mathematics; Context (archaeology); Mixing (physics); Independent and identically distributed random variables; Maximum likelihood; Mixture model; Strong consistency; Mathematical proof; Statistics; Econometrics; Random variable; Discrete mathematics; Geography","score_opus":0.03239981041930076,"score_gpt":0.2804750250303119,"score_spread":0.24807521461101115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388919539","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010076037,0.0019287302,0.74206156,0.00010612224,0.00074009615,0.00028683522,0.0003326323,0.00009883459,0.25444415],"genre_scores_gemma":[0.000047586487,0.005349027,0.4869376,0.0002951586,0.00007131654,0.000015379088,0.00002469939,0.000061577724,0.5071976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99803776,0.00003342019,0.000540115,0.0006720679,0.00034721103,0.00036941405],"domain_scores_gemma":[0.99831516,0.0004954123,0.00023898404,0.00063245115,0.0001686591,0.0001493582],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036177828,0.0004062046,0.0006092432,0.00041807094,0.00010583235,0.00016342616,0.0005749611,0.00035224942,0.000054904318],"category_scores_gemma":[0.00016622843,0.00042611113,0.00005338389,0.00016337159,0.00017852026,0.00036171637,0.000521676,0.00052978593,0.00009640145],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006169476,0.0000058008386,0.0000025213637,0.00013101126,0.000023313467,0.00032867797,0.00019964368,0.0000020503285,0.0000024537142,0.9662873,0.0049467883,0.028064277],"study_design_scores_gemma":[0.0002584517,0.00015007533,0.00004265098,0.0001979828,0.00003331252,0.00006250555,0.000004535471,0.005997261,0.000024603916,0.8624166,0.13021876,0.000593213],"about_ca_topic_score_codex":0.000010454334,"about_ca_topic_score_gemma":0.000051148938,"teacher_disagreement_score":0.25512394,"about_ca_system_score_codex":0.000063536616,"about_ca_system_score_gemma":0.00021779657,"threshold_uncertainty_score":0.99981904},"labels":[],"label_agreement":null},{"id":"W4389042830","doi":"10.1109/isncc58260.2023.10323873","title":"Generalized Probabilistic Clustering Projection Models for Discrete Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Cluster analysis; Perplexity; Prior probability; Dirichlet distribution; Projection (relational algebra); Mathematics; Pattern recognition (psychology); Generalized Dirichlet distribution; Computer science; Artificial intelligence; Probabilistic logic; Topic model; Algorithm; Bayesian probability; Dirichlet series; Language model","score_opus":0.14013733785215116,"score_gpt":0.3548434531343582,"score_spread":0.21470611528220707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389042830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001510631,0.000015875854,0.9958936,0.000995987,0.00038988178,0.00063605997,0.000016362656,0.00057199504,0.0013292041],"genre_scores_gemma":[0.0068201497,0.000013299315,0.99010766,0.00017219548,0.000114979885,0.00013000723,0.000050653085,0.000014125902,0.0025769246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876726,0.00006341746,0.00018334093,0.00056790264,0.00013783194,0.00028026343],"domain_scores_gemma":[0.99869215,0.000083148254,0.00004111352,0.0010768871,0.00004785228,0.000058848796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081967615,0.00010948416,0.00013659046,0.00008659395,0.00012275176,0.00016394806,0.0010010155,0.000048474936,0.0000024948163],"category_scores_gemma":[0.000059142298,0.00008518383,0.00004205557,0.00038381797,0.000014804061,0.0008198668,0.0007529151,0.00005165272,0.000008751467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014407083,0.000015937725,0.000002297854,0.00009041178,0.000018688006,0.0000025298627,0.00037138065,0.0062703784,0.00074627093,0.8619665,0.008822699,0.121678516],"study_design_scores_gemma":[0.00018227333,0.000021518279,0.0000032285152,0.0000067718584,0.0000046654036,0.0000035620617,0.0000027238195,0.7226302,0.000080469545,0.27596983,0.0009984839,0.000096279284],"about_ca_topic_score_codex":0.000047905196,"about_ca_topic_score_gemma":0.00005036629,"teacher_disagreement_score":0.7163598,"about_ca_system_score_codex":0.000018294462,"about_ca_system_score_gemma":0.00005074197,"threshold_uncertainty_score":0.34736958},"labels":[],"label_agreement":null},{"id":"W4389449694","doi":"10.1007/978-3-031-09034-9_2","title":"Model Based Clustering of Functional Data with Mild Outliers","year":2023,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Outlier; Cluster analysis; Computer science; Multivariate statistics; Data mining; Functional data analysis; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Correlation clustering; Machine learning","score_opus":0.24569123234731524,"score_gpt":0.36175186103108525,"score_spread":0.11606062868377001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389449694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016015905,0.0012814308,0.9922797,0.00027278627,0.00018601038,0.00018617543,0.0004835788,0.00008093536,0.0052277655],"genre_scores_gemma":[0.031763025,0.018972622,0.82544327,0.00017769297,0.00046918425,0.000028193575,0.033598594,0.0002459153,0.08930153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974398,0.0000761541,0.0006415103,0.0013414738,0.00032785317,0.00017319771],"domain_scores_gemma":[0.9952469,0.00022241591,0.0004531123,0.0031624013,0.0008534057,0.00006177086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010473046,0.0003190917,0.00067253294,0.0008218217,0.00019556186,0.00007184557,0.0014806368,0.00018731167,0.000008902075],"category_scores_gemma":[0.00027794065,0.0002799185,0.00003308734,0.0015913127,0.00026281513,0.0005286716,0.0017295873,0.00020266516,0.000006968673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063826206,0.0003109808,0.0089727165,0.0018253094,0.009053992,0.000009915544,0.004788445,0.00708527,0.0001116522,0.87344426,0.03556982,0.058763824],"study_design_scores_gemma":[0.00027610525,0.00001513076,0.0015934157,0.0001688792,0.001138381,9.4308535e-7,0.000050729257,0.98805666,0.0000051066795,0.007095604,0.001265369,0.00033367032],"about_ca_topic_score_codex":0.00001270735,"about_ca_topic_score_gemma":0.0021570688,"teacher_disagreement_score":0.9809714,"about_ca_system_score_codex":0.00008051838,"about_ca_system_score_gemma":0.00038611775,"threshold_uncertainty_score":0.9999653},"labels":[],"label_agreement":null},{"id":"W4389473849","doi":"10.1109/lsp.2023.3341001","title":"Population Monte Carlo With Normalizing Flow","year":2023,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Huawei Technologies (Canada)","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Monte Carlo method; Algorithm; Mathematical optimization; Sampling (signal processing); Importance sampling; Inference; Rejection sampling; Population; Markov chain; Hybrid Monte Carlo; Mathematics; Machine learning; Artificial intelligence; Statistics; Bayesian probability","score_opus":0.01798211009639149,"score_gpt":0.2484016818867318,"score_spread":0.2304195717903403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389473849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060805548,0.00005204593,0.9360762,0.0022287574,0.0001613924,0.00008874608,8.3454074e-7,0.00044176567,0.0001446709],"genre_scores_gemma":[0.68443453,0.000001172722,0.31355292,0.0017858347,0.0001427217,0.000011042008,0.0000016312084,0.000016788315,0.000053386866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864197,0.00007329164,0.00017703691,0.0003922183,0.000342085,0.00037340968],"domain_scores_gemma":[0.9995165,0.000036863985,0.00009404524,0.0002219801,0.00004790289,0.00008274888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037936645,0.00016293317,0.00016354785,0.0001671076,0.00024296589,0.00029158918,0.00039668576,0.00004783315,0.0000016681618],"category_scores_gemma":[0.000004396778,0.00013298214,0.000044234363,0.00076615403,0.00003093443,0.00081520726,0.000041952033,0.00016574573,0.000017532117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025439005,0.000020515006,0.0010981754,0.00014984286,0.000027825134,0.00021118521,0.0025768292,0.049276955,0.041516192,0.00050452974,0.0045622215,0.9000303],"study_design_scores_gemma":[0.00028438462,0.000041944342,0.001955631,0.00016101243,0.000013004502,0.00003523935,0.0000085878155,0.99271727,0.0028301796,0.0013226139,0.00028616862,0.00034398213],"about_ca_topic_score_codex":0.00006193057,"about_ca_topic_score_gemma":0.0000061109586,"teacher_disagreement_score":0.9434403,"about_ca_system_score_codex":0.00003484245,"about_ca_system_score_gemma":0.000037253638,"threshold_uncertainty_score":0.54228544},"labels":[],"label_agreement":null},{"id":"W4389985347","doi":"10.1101/2023.12.19.572366","title":"A functional perspective on the conditional covariance comparison problem in dementia analysis","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Janssen Alzheimer Immunotherapy Research And Development; Johnson and Johnson Pharmaceutical Research and Development; Janssen Research and Development; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Meso Scale Diagnostics; Johnson and Johnson; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Pfizer; BioClinica; Biogen; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Alzheimer's Drug Discovery Foundation; Merck; National Institute on Aging; Alzheimer's Association","keywords":"Perspective (graphical); Covariance; Dementia; Psychology; Econometrics; Cognitive psychology; Mathematics; Computer science; Statistics; Artificial intelligence; Medicine; Internal medicine; Disease","score_opus":0.03785780015133976,"score_gpt":0.26938164713679325,"score_spread":0.23152384698545347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389985347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055118413,0.00032415646,0.98830605,0.0040388284,0.0006695345,0.0006494849,0.00012871063,0.00032557634,0.000045809662],"genre_scores_gemma":[0.8078764,0.000026427591,0.19087137,0.00054786436,0.00020031547,0.0004243568,8.09479e-7,0.000040403418,0.000012010975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99626225,0.0005221997,0.0005783287,0.0014372306,0.0006941136,0.0005058705],"domain_scores_gemma":[0.9970749,0.00036709872,0.000437862,0.0014581236,0.00051867956,0.00014331385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017646658,0.0004631849,0.0006327474,0.000685262,0.00024539366,0.00043712382,0.0012911893,0.00032597015,0.00005418708],"category_scores_gemma":[0.00016072589,0.00039865868,0.00029885303,0.0024346965,0.00011716839,0.00018778283,0.0007082082,0.0011379621,0.000108851746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023547042,0.00027445098,0.005603255,0.000050418857,0.0015650351,0.000046008947,0.00007017008,0.009770379,0.0043697613,0.97556466,0.0026598596,0.0000024833732],"study_design_scores_gemma":[0.0010191009,0.00011555888,0.77888626,0.00041001412,0.0009000421,2.3494328e-8,0.000016322618,0.19335574,0.009407358,0.012930706,0.0011939454,0.0017649123],"about_ca_topic_score_codex":0.00013091801,"about_ca_topic_score_gemma":0.000023063334,"teacher_disagreement_score":0.9626339,"about_ca_system_score_codex":0.00046821262,"about_ca_system_score_gemma":0.00060472445,"threshold_uncertainty_score":0.9998465},"labels":[],"label_agreement":null},{"id":"W4389988630","doi":"10.1109/ictai59109.2023.00078","title":"Unsupervised Learning of Dirichlet Compound Negative Multinomial Mixture Model using Minorization-Maximization Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Computer science; Maximization; Mixture model; Latent Dirichlet allocation; Dirichlet distribution; Artificial intelligence; Statistics; Mathematical optimization; Topic model; Mathematics","score_opus":0.0395876110850217,"score_gpt":0.2798042658183521,"score_spread":0.2402166547333304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389988630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023147685,0.000016018615,0.9728114,0.000092748574,0.00010820303,0.0002227877,0.0000030006904,0.00024452503,0.0033536328],"genre_scores_gemma":[0.33826488,0.000005781827,0.66105396,0.00006343128,0.00003701694,0.0000048337165,0.000017696162,0.000012811255,0.00053956406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854815,0.00020724756,0.0003054844,0.00041445007,0.0002682251,0.00025644025],"domain_scores_gemma":[0.99912584,0.00015447692,0.0001483604,0.00030652358,0.0001895296,0.0000752816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039028682,0.00017045885,0.0002558887,0.00021946862,0.00018030228,0.00008310164,0.0004423526,0.000118736694,0.000005450388],"category_scores_gemma":[0.00010660725,0.00015289584,0.00007782668,0.0011895105,0.000048026723,0.00044320247,0.00020665748,0.00016508623,0.000003831753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011761582,0.00006951159,0.00029061604,0.000050939943,0.000029170467,0.000002582848,0.0041225576,0.90548706,0.013986032,0.0613884,0.00020343655,0.014357936],"study_design_scores_gemma":[0.0003952422,0.000018830282,0.00013727735,0.00001220057,0.000011039629,0.0000023506082,0.00006610309,0.9837421,0.0029527857,0.012473011,0.000014385905,0.0001746442],"about_ca_topic_score_codex":0.000046331937,"about_ca_topic_score_gemma":0.0000012648402,"teacher_disagreement_score":0.3151172,"about_ca_system_score_codex":0.000031504245,"about_ca_system_score_gemma":0.00009253035,"threshold_uncertainty_score":0.6234911},"labels":[],"label_agreement":null},{"id":"W4390244915","doi":"10.18280/ria.370605","title":"An Approximate Maximin-Directed Random Sampling for Clustering Applications","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Minimax; Sampling (signal processing); Computer science; Mathematics; Statistics; Mathematical optimization","score_opus":0.08527324963410397,"score_gpt":0.3420994452585088,"score_spread":0.25682619562440484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390244915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035472657,0.000090423666,0.99609274,0.00043875078,0.00028409366,0.00090183585,0.000009611112,0.0010245616,0.0008032833],"genre_scores_gemma":[0.062133044,0.00007004722,0.9358637,0.00013398257,0.00019290073,0.00075228687,0.000029077852,0.000032548298,0.00079246325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827594,0.000074828786,0.00041237497,0.00064170815,0.00012474218,0.0004704105],"domain_scores_gemma":[0.9983108,0.00037164398,0.000104142106,0.0009415503,0.00012825402,0.00014358437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010437052,0.000174134,0.00024252702,0.00018317558,0.00035507308,0.0002158033,0.0009295171,0.00008649637,0.0000135793725],"category_scores_gemma":[0.00007232245,0.00017362427,0.00012186491,0.0009927792,0.00004194842,0.00030561455,0.00014332161,0.00012100262,0.00013249576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026123009,0.00008767731,0.000007973999,0.00012789038,0.000015569243,0.0000032733315,0.0017904219,0.036033273,0.015661776,0.07578892,0.00024658968,0.8702105],"study_design_scores_gemma":[0.00007672518,0.000043900665,0.000005887195,0.00002901417,0.000007361934,0.000010140395,0.000081509046,0.9211905,0.018212559,0.053788517,0.006347019,0.00020687532],"about_ca_topic_score_codex":0.0000072163134,"about_ca_topic_score_gemma":0.0000055763912,"teacher_disagreement_score":0.8851572,"about_ca_system_score_codex":0.000026880676,"about_ca_system_score_gemma":0.000033569533,"threshold_uncertainty_score":0.70801926},"labels":[],"label_agreement":null},{"id":"W4390608442","doi":"10.1017/s1748499523000271","title":"Nonparametric intercept regularization for insurance claim frequency regression models","year":2024,"lang":"en","type":"article","venue":"Annals of Actuarial Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Econometrics; Bayesian probability; Nonparametric statistics; Subgroup analysis; Property (philosophy); Computer science; Mathematics; Statistics; Economics; Actuarial science","score_opus":0.06737584058612839,"score_gpt":0.3634504486415092,"score_spread":0.29607460805538083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390608442","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067298845,0.0005651553,0.98544824,0.0021632947,0.0015225037,0.00031358167,0.000010227253,0.00012141939,0.0031257041],"genre_scores_gemma":[0.64734966,0.00009775724,0.35203484,0.00024729504,0.00011310772,0.000014826531,0.0000014452498,0.0000074772734,0.00013357043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99784154,0.000070983755,0.0003799637,0.00071537006,0.00057079084,0.0004213639],"domain_scores_gemma":[0.9984275,0.00024868973,0.00013560677,0.0006083979,0.0004345612,0.0001452455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021474075,0.00016786397,0.00023835548,0.0005239282,0.00020384179,0.00039278856,0.0015360627,0.00010779183,0.000007123426],"category_scores_gemma":[0.00044084896,0.0001274333,0.00014000447,0.0027636632,0.00028553457,0.0028195712,0.00021772768,0.00013964601,0.000005483511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014071525,0.000031515887,0.000006172574,0.00004297433,0.0000062389704,0.0000020029263,0.000798429,0.000119826225,0.02020729,0.676363,0.0010832679,0.30132523],"study_design_scores_gemma":[0.00011193479,0.00017891257,0.00015762207,0.00018216016,0.0000038905782,0.0000049509695,0.000004253747,0.27590376,0.04128265,0.6814857,0.00051630585,0.00016785345],"about_ca_topic_score_codex":0.000030304305,"about_ca_topic_score_gemma":0.0000014687885,"teacher_disagreement_score":0.6406198,"about_ca_system_score_codex":0.000030052945,"about_ca_system_score_gemma":0.00038376375,"threshold_uncertainty_score":0.51965797},"labels":[],"label_agreement":null},{"id":"W4390616616","doi":"10.1002/cjs.11803","title":"Clustering spatial functional data using a geographically weighted Dirichlet process","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science Foundation","keywords":"Cluster analysis; Dirichlet process; Markov chain Monte Carlo; Computer science; Spatial analysis; Spatial dependence; Bayesian probability; Nonparametric statistics; Autoregressive model; Algorithm; Mathematics; Data mining; Statistics; Artificial intelligence","score_opus":0.05541997002218578,"score_gpt":0.29104236599329586,"score_spread":0.23562239597111007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390616616","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050486706,0.0007340805,0.9962041,0.0004758496,0.001596746,0.00004604714,0.00031427003,0.000013473349,0.00011058066],"genre_scores_gemma":[0.1554588,0.000015744123,0.8438745,0.00019841321,0.00039740605,3.7358393e-7,0.000015275573,0.000013637603,0.000025809326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882185,0.00006371182,0.0003483028,0.00022782249,0.00026305314,0.00027523897],"domain_scores_gemma":[0.99869776,0.00011940218,0.00010570008,0.00030865803,0.00026484247,0.0005036614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054825965,0.000115970346,0.00016696546,0.000374422,0.0001342531,0.00045310735,0.00082387734,0.00005881769,0.000050587878],"category_scores_gemma":[0.00010480603,0.00010200162,0.0000351981,0.00040685118,0.00006622499,0.0004925573,0.000064751825,0.0003162443,0.0000026611322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020832596,0.00002991489,0.0010256275,0.00033492432,0.0003166825,0.0062402985,0.0013511456,0.0009657665,0.00024488274,0.14886166,0.021671219,0.81893706],"study_design_scores_gemma":[0.00012953326,0.00005366809,0.00070082,0.00015657055,0.00004788399,0.0008601435,0.0000073887772,0.9382606,0.000009469636,0.053077854,0.006539701,0.00015636417],"about_ca_topic_score_codex":0.0010065652,"about_ca_topic_score_gemma":0.0054594288,"teacher_disagreement_score":0.93729484,"about_ca_system_score_codex":0.00006889227,"about_ca_system_score_gemma":0.0025484702,"threshold_uncertainty_score":0.45208767},"labels":[],"label_agreement":null},{"id":"W4390639551","doi":"10.1007/s00357-023-09460-0","title":"Unsupervised Classification with a Family of Parsimonious Contaminated Shifted Asymmetric Laplace Mixtures","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Series (stratigraphy); Mathematics; Bayesian information criterion; Bayesian probability; Expectation–maximization algorithm; Artificial intelligence; Computer science; Convergence (economics); Pattern recognition (psychology); Model selection; Algorithm; Statistics; Maximum likelihood","score_opus":0.029639951270204308,"score_gpt":0.28335772333249026,"score_spread":0.25371777206228596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390639551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04169319,0.0024630798,0.95128626,0.0019703945,0.00039638265,0.00018127,0.0000038185044,0.0000652911,0.0019403268],"genre_scores_gemma":[0.84627855,0.00022579018,0.15317929,0.000086415734,0.000082858394,0.0000062592685,0.0000037158782,0.000016449154,0.000120679775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784815,0.00031186859,0.0007508222,0.0002991233,0.0005929951,0.00019702649],"domain_scores_gemma":[0.99781436,0.00036780757,0.00060294266,0.00043708333,0.0006553067,0.00012249872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001247521,0.00018123034,0.00035718762,0.00071750284,0.00005734936,0.00018933429,0.0006685243,0.00014974334,0.0000028509498],"category_scores_gemma":[0.00012227509,0.0001289207,0.0001364921,0.0018340747,0.00007411966,0.0007314997,0.000028710383,0.00035813748,0.0000055091236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018408829,0.00027086484,0.0004924477,0.00018384772,0.0002165911,0.00006126295,0.0013652154,0.000026036858,0.14575434,0.23714884,0.0025302183,0.6117663],"study_design_scores_gemma":[0.0036121109,0.002622273,0.27414733,0.0015470791,0.0005222424,0.0006022583,0.0006130379,0.59507024,0.06434594,0.040439244,0.015452038,0.0010261842],"about_ca_topic_score_codex":0.0000073523715,"about_ca_topic_score_gemma":0.000001871278,"teacher_disagreement_score":0.80458534,"about_ca_system_score_codex":0.00011218456,"about_ca_system_score_gemma":0.0003742388,"threshold_uncertainty_score":0.52572334},"labels":[],"label_agreement":null},{"id":"W4390740418","doi":"10.1214/23-ba1411","title":"Large Sample Asymptotic Analysis for Normalized Random Measures with Independent Increments","year":2024,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Mathematics; Estimator; Nonparametric statistics; Consistency (knowledge bases); Applied mathematics; von Mises yield criterion; Prior probability; Bayesian probability; Statistics; Discrete mathematics; Finite element method","score_opus":0.015993458135478627,"score_gpt":0.27723128086686905,"score_spread":0.2612378227313904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390740418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007259656,0.0008765985,0.99644196,0.0004280931,0.00010878766,0.00042311708,0.000095954856,0.00027498795,0.0006245474],"genre_scores_gemma":[0.59541494,0.000034410405,0.4037366,0.00021911514,0.000056741763,0.000095439995,0.00007430946,0.000020510304,0.00034796578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996486,0.0003627221,0.00056968344,0.0010896584,0.00082150684,0.0006704217],"domain_scores_gemma":[0.99780005,0.00048247701,0.00014759996,0.0010922288,0.00020384257,0.00027377083],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00225436,0.00037658282,0.001003693,0.0019660715,0.00026581308,0.0007810093,0.00093268364,0.00013534534,0.00015479977],"category_scores_gemma":[0.0000986064,0.0002819863,0.0012727338,0.0076923817,0.000037307094,0.0005110938,0.00015579286,0.00019240871,0.000011906339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009996321,0.0010948101,0.07779795,0.00051327224,0.22885875,0.00035355173,0.008386542,0.011518292,0.00078603846,0.4871347,0.0022808616,0.1802756],"study_design_scores_gemma":[0.0021444443,0.00010851811,0.0036221778,0.000028899025,0.01912388,0.00000538592,0.000036162746,0.95551145,0.00042382494,0.01331139,0.005071566,0.0006123237],"about_ca_topic_score_codex":0.00023740246,"about_ca_topic_score_gemma":0.0012345882,"teacher_disagreement_score":0.94399315,"about_ca_system_score_codex":0.00010407656,"about_ca_system_score_gemma":0.00014713427,"threshold_uncertainty_score":0.9999632},"labels":[],"label_agreement":null},{"id":"W4391117481","doi":"10.5539/jmr.v16n1p1","title":"Improved Method to Estimating Parameters of a Poisson Hidden Markov Model Using Bayesian Approach","year":2024,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Akaike information criterion; Deviance information criterion; Mathematics; Bayesian information criterion; Poisson distribution; Gibbs sampling; Hidden Markov model; Statistics; Expectation–maximization algorithm; Bayesian probability; Zero-inflated model; Count data; Applied mathematics; Maximum a posteriori estimation; Markov chain; Bayesian inference; Poisson regression; Maximum likelihood; Computer science; Artificial intelligence","score_opus":0.1428087899037147,"score_gpt":0.4437866514445857,"score_spread":0.300977861540871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391117481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003817747,0.00024268037,0.9942183,0.0005748618,0.00014311701,0.00029403061,0.000002409005,0.000022614133,0.00068427064],"genre_scores_gemma":[0.020565985,0.0000061432943,0.9791458,0.000025978365,0.00008621633,0.00000601269,1.2222033e-7,0.0000324133,0.0001313121],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964539,0.0005725097,0.0009288293,0.00031363062,0.0012389335,0.0004922445],"domain_scores_gemma":[0.99707025,0.0011895335,0.0002642617,0.0005506828,0.000629254,0.00029601867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01508463,0.00017633961,0.0005417324,0.00096015615,0.00009990737,0.0003994116,0.0013484756,0.00011482995,0.0000038527414],"category_scores_gemma":[0.0007943008,0.00013246138,0.00023111554,0.0010851815,0.000052698742,0.00044840528,0.00044583675,0.00081043935,0.0000015430256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034423545,0.00041313068,0.0000018572375,0.0024315151,0.0002518297,0.00009363433,0.015788516,0.012512798,0.09495056,0.043541096,0.00088008394,0.82910055],"study_design_scores_gemma":[0.000114015944,0.00014485807,5.09883e-7,0.0005007867,0.000021661472,0.00025960527,0.00014127261,0.8483483,0.0050081178,0.14534949,0.000004410188,0.00010696047],"about_ca_topic_score_codex":0.0000207512,"about_ca_topic_score_gemma":4.214212e-7,"teacher_disagreement_score":0.8358355,"about_ca_system_score_codex":0.0001572358,"about_ca_system_score_gemma":0.0005002628,"threshold_uncertainty_score":0.54016185},"labels":[],"label_agreement":null},{"id":"W4391508918","doi":"10.1016/j.patcog.2024.110310","title":"Regularization and optimization in model-based clustering","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Overfitting; Mixture model; Computer science; Cluster analysis; Maxima and minima; Algorithm; Regularization (linguistics); Covariance; Artificial intelligence; Mathematical optimization; Mathematics; Artificial neural network","score_opus":0.02747566009245926,"score_gpt":0.26302140999393,"score_spread":0.2355457499014707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391508918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013137826,0.0001070543,0.99730766,0.00050827273,0.0001512023,0.0001153473,0.0000023358516,0.00012442951,0.0003699137],"genre_scores_gemma":[0.35084003,0.000026302336,0.6487559,0.0002791836,0.000027970073,0.000019412118,0.000020791702,0.000008796151,0.000021618484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993593,0.00006294626,0.00012871512,0.00026593969,0.00007957861,0.00010350893],"domain_scores_gemma":[0.9997891,0.000031517764,0.000019834066,0.00010590939,0.000024152612,0.000029447405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002543864,0.00007366187,0.00006624813,0.00017078417,0.000027705666,0.00018378042,0.00007151239,0.000056052282,0.0000054987872],"category_scores_gemma":[0.00000991478,0.00007431293,0.000017230408,0.00020276834,0.000008389093,0.00042097486,0.000033778277,0.00007511493,0.000004200546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015211369,0.000009546709,0.00004002335,0.00006933363,0.0000017284192,0.000006549264,0.00019867264,0.06802045,0.00018779039,0.00031617846,0.000009681414,0.9311385],"study_design_scores_gemma":[0.0001269715,0.00001295291,0.00006324858,0.00016616103,0.0000036550618,0.0000057127754,0.0000011917108,0.9761597,0.00059568,0.022765506,0.0000055964942,0.00009361202],"about_ca_topic_score_codex":0.0000064708843,"about_ca_topic_score_gemma":0.000007591216,"teacher_disagreement_score":0.93104494,"about_ca_system_score_codex":0.00002584759,"about_ca_system_score_gemma":0.000020844067,"threshold_uncertainty_score":0.3030393},"labels":[],"label_agreement":null},{"id":"W4391619089","doi":"10.56801/jmasm.v23.i2.3","title":"The Performance of the Maximum Likelihood Estimator for the Bell Distribution for Count Data","year":2024,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Mathematics; Statistics; Count data; Estimator; Maximum likelihood; Econometrics; Poisson distribution","score_opus":0.041645820015966395,"score_gpt":0.37184505443846233,"score_spread":0.33019923442249594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391619089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025742349,0.0017171905,0.99336916,0.0026773862,0.0010746543,0.0005776978,0.0004850564,0.000013895751,0.00005919409],"genre_scores_gemma":[0.030481342,0.00012336405,0.96898085,0.000115809235,0.00021072953,0.00004462113,0.0000067741516,0.000016758071,0.000019728792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980702,0.00025557165,0.0006545262,0.00028102432,0.00041562624,0.00032304888],"domain_scores_gemma":[0.9888073,0.009684653,0.00030838017,0.0008958769,0.00021540611,0.00008836512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008279569,0.00016173573,0.0003017045,0.000022498969,0.00043986682,0.00024785276,0.0022697486,0.00007522224,0.0000018136388],"category_scores_gemma":[0.00076953106,0.000069554204,0.00013225144,0.00018566068,0.00018711279,0.00017340298,0.0003710074,0.0003788642,5.0635447e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006252495,0.00001773195,6.326828e-7,0.00007370514,0.0000548078,3.8777054e-7,0.00006601165,0.00006213281,0.00076356396,0.38349262,0.0024755502,0.61293036],"study_design_scores_gemma":[0.00016144403,0.000077104516,0.000048160153,0.000030767413,0.000096069205,0.000020066724,0.000005566317,0.55999225,0.0011630348,0.42071518,0.017634766,0.000055599525],"about_ca_topic_score_codex":0.0000012110492,"about_ca_topic_score_gemma":9.1877524e-7,"teacher_disagreement_score":0.61287475,"about_ca_system_score_codex":0.000054589596,"about_ca_system_score_gemma":0.00032386533,"threshold_uncertainty_score":0.42177954},"labels":[],"label_agreement":null},{"id":"W4391832947","doi":"10.48550/arxiv.2402.08018","title":"Nearest Neighbour Score Estimators for Diffusion Generative Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Alliance de recherche numérique du Canada; Compute Canada; Lawrence Berkeley National Laboratory; Canadian Institute for Advanced Research; U.S. Department of Energy","keywords":"Estimator; Econometrics; Diffusion; Generative grammar; Generative model; Statistics; Mathematics; Computer science; Artificial intelligence; Statistical physics; Geography; Physics; Thermodynamics","score_opus":0.11222227468159568,"score_gpt":0.22344637448325796,"score_spread":0.11122409980166229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391832947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027398456,0.00029490475,0.9670487,0.00029405157,0.0014291421,0.000685355,0.000069041336,0.00037508426,0.0024052544],"genre_scores_gemma":[0.7062654,0.00011343834,0.2903625,0.00018725084,0.00020226493,0.0000071804507,0.000022346381,0.000044457982,0.0027951873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733853,0.00015092162,0.00024218764,0.0016859173,0.000112216716,0.00047022206],"domain_scores_gemma":[0.9979799,0.00014295375,0.00018042092,0.0012400415,0.00019807837,0.00025864347],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032335747,0.0004781563,0.0004777796,0.00030551915,0.00023842078,0.00035650612,0.0016774635,0.0004426663,0.000009182027],"category_scores_gemma":[0.00002666679,0.00047879416,0.0004147683,0.00047462198,0.00009469394,0.00034760122,0.0032240436,0.0007244821,0.000032003416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018522336,0.000048655405,0.000026140344,0.00016060742,0.000071490074,0.00015384704,0.00037548138,0.11819035,0.000063035055,0.8755135,0.00090804737,0.004470356],"study_design_scores_gemma":[0.00016582411,0.000030983938,0.0000107689375,0.00010674569,0.000053204567,0.0000029989453,0.0000057743996,0.5202377,0.000112555885,0.4788808,0.000112666006,0.0002800012],"about_ca_topic_score_codex":0.000085720734,"about_ca_topic_score_gemma":0.000026285925,"teacher_disagreement_score":0.6788669,"about_ca_system_score_codex":0.00019618892,"about_ca_system_score_gemma":0.00038187584,"threshold_uncertainty_score":0.99976635},"labels":[],"label_agreement":null},{"id":"W4392169205","doi":"10.1007/s11749-024-00920-2","title":"The orthogonal skew model: computationally efficient multivariate skew-normal and skew-t distributions with applications to model-based clustering","year":2024,"lang":"en","type":"article","venue":"Test","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Skew; Skewness; Multivariate statistics; Skew normal distribution; Cluster analysis; Computation; Computer science; Multivariate normal distribution; Mathematics; Applied mathematics; Algorithm; Statistics","score_opus":0.01537852717219645,"score_gpt":0.2829466552657238,"score_spread":0.26756812809352737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392169205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008920993,0.000161837,0.9942943,0.0033344573,0.000055430926,0.00044582057,0.0001171196,0.00025690658,0.00044205014],"genre_scores_gemma":[0.4034163,0.0000017928272,0.5960583,0.00023355662,0.00003327264,0.00014357985,0.000014876595,0.000011410462,0.000086924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986937,0.00003994721,0.00021988984,0.00047491846,0.00026495484,0.00030656392],"domain_scores_gemma":[0.9987643,0.0004989689,0.000040400744,0.00039051904,0.00012615656,0.0001796967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038833017,0.00017750931,0.00012705893,0.00007205237,0.00056150707,0.00044400644,0.00042800186,0.00006148094,0.0000012743781],"category_scores_gemma":[0.000025848354,0.00012295887,0.00004692732,0.0004361172,0.0000831316,0.00012179686,0.00021478682,0.00024195209,0.000012541953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051616653,0.0000510207,0.0000134142165,0.000018926205,0.000011010576,0.0000030605943,0.00023811652,0.48187798,0.00021381151,0.48989746,0.00009414486,0.027575914],"study_design_scores_gemma":[0.00015694929,0.000040391777,0.00039129687,0.000045289973,0.000015707938,0.000013826811,0.000001490351,0.96259856,0.00005687083,0.035806432,0.00069934846,0.00017382823],"about_ca_topic_score_codex":0.0000108177765,"about_ca_topic_score_gemma":0.00002753882,"teacher_disagreement_score":0.48072058,"about_ca_system_score_codex":0.000051355284,"about_ca_system_score_gemma":0.00029307645,"threshold_uncertainty_score":0.50141174},"labels":[],"label_agreement":null},{"id":"W4392190837","doi":"10.1093/g3journal/jkad236","title":"Relatedness coefficients and their applications for triplets and quartets of genetic markers","year":2024,"lang":"en","type":"article","venue":"G3 Genes Genomes Genetics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Evolutionary biology; Genetics; Computational biology","score_opus":0.01404668061334974,"score_gpt":0.26098458316430595,"score_spread":0.2469379025509562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392190837","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030252698,0.35052893,0.6455576,0.00011597832,0.00016388673,0.00046008566,0.00002813607,0.000040462837,0.00007967184],"genre_scores_gemma":[0.2528545,0.047452413,0.6989693,0.0001045444,0.00010405706,0.00017469472,0.000008511594,0.00004053588,0.00029147736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987765,0.000059287206,0.00030057222,0.0005083835,0.00010347935,0.00025177776],"domain_scores_gemma":[0.9991229,0.0001672317,0.00006440103,0.000447169,0.000080552956,0.000117747084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028428886,0.00018520486,0.00022493892,0.00014175766,0.00010469401,0.00011862077,0.00033669654,0.00010352194,0.000001803738],"category_scores_gemma":[0.0000020289633,0.00015680346,0.000064010535,0.000303514,0.00010751911,0.000048954353,0.000159906,0.00006451846,0.0000015865328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004285548,0.000017598832,0.0001085719,0.00017236941,0.000035093177,0.0000010185676,0.0008015124,0.0000615949,0.0035913133,0.0065630763,0.00006361139,0.9885799],"study_design_scores_gemma":[0.0009636944,0.0005310033,0.0017350673,0.00009095252,0.00013802836,0.00013211132,0.00016723447,0.48163617,0.008384103,0.074070446,0.431342,0.0008091842],"about_ca_topic_score_codex":0.000001909034,"about_ca_topic_score_gemma":0.0000018050442,"teacher_disagreement_score":0.9877708,"about_ca_system_score_codex":0.000013319763,"about_ca_system_score_gemma":0.00007639959,"threshold_uncertainty_score":0.63942593},"labels":[],"label_agreement":null},{"id":"W4392566176","doi":"10.1137/1.9781611977820.ch13","title":"Chapter 13: Sequences of Random Variables","year":2024,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics","score_opus":0.05866226049220612,"score_gpt":0.2563368727603106,"score_spread":0.19767461226810445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392566176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008318681,0.0003036924,0.579453,0.00007674036,0.00026727188,0.0007787023,0.00007376761,0.00007588918,0.41896266],"genre_scores_gemma":[0.00042966154,0.000098968834,0.7787429,0.00012944484,0.0006840532,0.00011277844,0.000010452365,0.00008265803,0.2197091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829024,0.000003664789,0.0006203188,0.0005285926,0.0002959576,0.00026124876],"domain_scores_gemma":[0.99864626,0.0003787855,0.00037854855,0.00042558435,0.00006737877,0.00010346756],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084337144,0.0004240742,0.0008398587,0.000053747088,0.00012836135,0.00014644978,0.00048378468,0.0007692904,0.00001647946],"category_scores_gemma":[0.000008545612,0.00033112074,0.00061878114,0.000018954433,0.00024069594,0.00003916562,0.00028396267,0.00046518596,0.000004527262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011076625,0.000007617305,4.6672897e-9,0.0004182083,0.00022450817,6.8641776e-7,0.0011479969,7.754271e-7,0.0006547539,0.96083766,0.0009206145,0.03577611],"study_design_scores_gemma":[0.0009825525,0.000059611135,1.7612117e-9,0.00040662423,0.00026102306,0.0000077843915,0.000033318753,0.001172485,0.0024579454,0.9633038,0.030964553,0.0003502793],"about_ca_topic_score_codex":0.0000021623878,"about_ca_topic_score_gemma":5.822557e-7,"teacher_disagreement_score":0.19928992,"about_ca_system_score_codex":0.00002067164,"about_ca_system_score_gemma":0.00011637629,"threshold_uncertainty_score":0.9999141},"labels":[],"label_agreement":null},{"id":"W4392644692","doi":"10.1016/j.jeconom.2024.105717","title":"Score-type tests for normal mixtures","year":2024,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Statistics; Mathematics; Type (biology); Type I and type II errors; Econometrics; Geology","score_opus":0.1418808555572928,"score_gpt":0.31297743549819085,"score_spread":0.17109657994089805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392644692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046544285,0.008390079,0.98133105,0.0007946956,0.0031515881,0.00006679564,0.0000031646655,0.000022147156,0.0015860758],"genre_scores_gemma":[0.19647717,0.00030069443,0.80154765,0.0003762888,0.0007587823,0.0000013826985,4.3211844e-7,0.000012986333,0.0005246394],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99912,0.000025608379,0.0003863117,0.0001548681,0.00012208801,0.00019114841],"domain_scores_gemma":[0.9987835,0.0005465175,0.00015830669,0.00018084598,0.00020376481,0.00012701967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011475274,0.00009552036,0.00021364371,0.0009746808,0.00004230494,0.00034459663,0.0005967471,0.00006588865,0.000015167642],"category_scores_gemma":[0.00039666152,0.00007368836,0.00018274516,0.001327565,0.000015237596,0.00072968885,0.000063079395,0.00018934374,0.00000959436],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001965801,0.000069988695,0.000478572,0.00012827896,0.00011547134,0.00009202451,0.00024710142,0.00010541431,0.0004579033,0.25089037,0.03688213,0.71051306],"study_design_scores_gemma":[0.0010514657,0.002380866,0.003635263,0.00023245814,0.00011366869,0.0012957976,0.000010517368,0.084977694,0.005090145,0.45897076,0.441552,0.00068934646],"about_ca_topic_score_codex":7.0539954e-7,"about_ca_topic_score_gemma":4.1837612e-7,"teacher_disagreement_score":0.7098237,"about_ca_system_score_codex":0.000052688174,"about_ca_system_score_gemma":0.00018643925,"threshold_uncertainty_score":0.33229533},"labels":[],"label_agreement":null},{"id":"W4392733156","doi":"10.1017/9781108874144.011","title":"Multivariate Enumeration","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Enumeration; Multivariate statistics; Mathematics; Statistics; Combinatorics","score_opus":0.024637870201711168,"score_gpt":0.2237005627172767,"score_spread":0.19906269251556552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392733156","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.5732634e-7,0.0001310968,0.4817628,0.00003113037,0.00040470855,0.00013871794,0.000032115033,0.00019132272,0.51730776],"genre_scores_gemma":[0.00008870125,0.000044335615,0.04650561,0.00008703824,0.00016414675,5.572323e-7,0.000012668304,0.00003286939,0.9530641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862236,0.000041936277,0.00016049838,0.00071273604,0.00023083418,0.00023162112],"domain_scores_gemma":[0.9988201,0.00005116668,0.00011799422,0.0007597939,0.00010543477,0.00014547566],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015208116,0.00033027647,0.0003015417,0.00019566013,0.00013438625,0.00018411582,0.00088291237,0.0003554841,0.000001940291],"category_scores_gemma":[0.0000039182733,0.0003600513,0.00021710043,0.000011578802,0.000069384405,0.00019282303,0.00067557255,0.0005086214,0.00006008553],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006699792,0.0000030527965,1.4360276e-8,0.00004649134,0.00007361417,0.0003135853,0.000069618494,9.570945e-7,0.00009200849,0.97064036,0.012695378,0.016058221],"study_design_scores_gemma":[0.00019886033,0.000028737188,7.813767e-7,0.00014640231,0.000100968005,0.000021495202,0.0000010474779,0.005984502,0.00039156448,0.0029149908,0.98978835,0.00042231253],"about_ca_topic_score_codex":0.000057203393,"about_ca_topic_score_gemma":6.9437016e-7,"teacher_disagreement_score":0.977093,"about_ca_system_score_codex":0.00012829073,"about_ca_system_score_gemma":0.000102843216,"threshold_uncertainty_score":0.99988514},"labels":[],"label_agreement":null},{"id":"W4392826065","doi":"10.1134/s199508022311029x","title":"A Modified Mixture Model-Based Clustering Algorithm for Resolving the Problem of Mixed Pixels Available in Satellite Imagery","year":2023,"lang":"en","type":"article","venue":"Lobachevskii Journal of Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Pixel; Mathematics; Satellite; Cluster analysis; Algorithm; Remote sensing; Satellite imagery; Artificial intelligence; Computer science; Geography; Statistics","score_opus":0.04011663520160773,"score_gpt":0.2827471283570652,"score_spread":0.24263049315545748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392826065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015768151,0.0006001209,0.99607176,0.0005757536,0.00012961442,0.000399794,0.000007672571,0.00003527804,0.0006032206],"genre_scores_gemma":[0.0073084217,0.00011431976,0.9920441,0.000089369176,0.00006380207,0.000017637867,0.0000010697916,0.000027467293,0.00033382716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766016,0.00015334679,0.0010931244,0.00021520624,0.00046376314,0.0004143828],"domain_scores_gemma":[0.99743164,0.00083014695,0.00081014796,0.00052307773,0.00031118566,0.00009377738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004447063,0.0002178584,0.000566115,0.0003039837,0.00008851111,0.00012492258,0.001140564,0.00012762824,0.0000025611719],"category_scores_gemma":[0.00013933497,0.00014886721,0.00026736138,0.00072061893,0.000059237234,0.00034080396,0.00018740995,0.0003401332,0.000004419347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009205806,0.0009350416,0.00003831896,0.0031569856,0.00027589366,0.00016259175,0.014268996,0.19514516,0.015612075,0.04419481,0.008244673,0.7178734],"study_design_scores_gemma":[0.0006578436,0.00007403391,0.000007036562,0.0004893769,0.000027902055,0.00004987128,0.00006504869,0.88674086,0.0027840033,0.10878809,0.00017602897,0.00013987225],"about_ca_topic_score_codex":0.0000025735515,"about_ca_topic_score_gemma":0.0000042935944,"teacher_disagreement_score":0.7177335,"about_ca_system_score_codex":0.00005984445,"about_ca_system_score_gemma":0.0002251228,"threshold_uncertainty_score":0.6070629},"labels":[],"label_agreement":null},{"id":"W4393043332","doi":"10.1177/09622802231225963","title":"A latent class linear mixed model for monotonic continuous processes measured with error","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Western University","funders":"Alliance de recherche numérique du Canada; Innovation, Science and Economic Development Canada; National Institute of Mental Health; University of Toronto; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México","keywords":"Monotonic function; Latent class model; Bayesian probability; Mathematics; Statistics; Class (philosophy); Homogeneous; Computer science; Observational error; Applied mathematics; Econometrics; Artificial intelligence; Mathematical analysis; Combinatorics","score_opus":0.18046242781057098,"score_gpt":0.5227246603787071,"score_spread":0.34226223256813615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393043332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008688994,0.001220643,0.99180263,0.004442863,0.00021052969,0.0009901866,0.00004008091,0.00015979253,0.0010463819],"genre_scores_gemma":[0.022186415,0.00011341349,0.97611034,0.00018209532,0.00011044363,0.00074794545,0.0000053512235,0.000045825174,0.00049816654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99186367,0.0027517553,0.0006047958,0.0011692246,0.0023998267,0.0012107085],"domain_scores_gemma":[0.9807058,0.017103536,0.00003630996,0.0006156569,0.00076118775,0.00077753665],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02009535,0.00026178182,0.00060010003,0.00039541852,0.00014754216,0.00026418205,0.0013326185,0.0003246798,0.00006889178],"category_scores_gemma":[0.02682751,0.00017800996,0.000067602894,0.0016114542,0.0005728533,0.00019730405,0.0003810484,0.0016822779,0.000013463145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013907951,0.00016295821,0.000007470658,0.00075464445,0.000042218267,0.00029673893,0.000511194,0.000053893906,0.00020991908,0.40220448,0.0011810448,0.59443635],"study_design_scores_gemma":[0.0004166367,0.00032733887,0.000022414946,0.00036025367,0.000011015463,0.000019096615,0.000014584404,0.7064794,0.000545822,0.2903193,0.0013157316,0.00016844529],"about_ca_topic_score_codex":0.000025855672,"about_ca_topic_score_gemma":0.000063194486,"teacher_disagreement_score":0.7064255,"about_ca_system_score_codex":0.00015135942,"about_ca_system_score_gemma":0.0029638372,"threshold_uncertainty_score":0.9813699},"labels":[],"label_agreement":null},{"id":"W4393092636","doi":"10.1080/03610918.2024.2330709","title":"Bayesian inference of a queueing system with short- or long-tailed distributions based on Hamiltonian Monte Carlo","year":2024,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Hybrid Monte Carlo; Monte Carlo method; Statistical physics; Bayesian inference; Inference; Queueing theory; Bayesian probability; Markov chain Monte Carlo; Computer science; Applied mathematics; Mathematics; Physics; Statistics; Artificial intelligence","score_opus":0.09033911065417165,"score_gpt":0.41575685285366737,"score_spread":0.3254177421994957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393092636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001130402,0.00017054059,0.9974983,0.0002357781,0.000067138055,0.0003496868,0.000096506694,0.0001389189,0.0003127364],"genre_scores_gemma":[0.59278506,0.00001273017,0.4070855,0.000019868901,0.0000048805064,0.000024627383,0.000050054394,0.000008051192,0.000009199077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985196,0.00033966103,0.00046138692,0.00030561868,0.00022410427,0.0001496507],"domain_scores_gemma":[0.9969283,0.0019392432,0.00010199677,0.00073344074,0.00022791828,0.00006911809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003986828,0.00016025522,0.00021824733,0.00030182942,0.00019286665,0.0002205775,0.0004059522,0.0000689297,0.0000018935757],"category_scores_gemma":[0.00010094334,0.00013610546,0.000025000536,0.00079815986,0.000113307586,0.00025528905,0.00011163606,0.00021474053,0.0000013064129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027046584,0.000080114594,0.0012651078,0.00016890702,0.000015893776,0.000011431069,0.0007425733,0.55636406,0.000006241076,0.31087995,0.000010471495,0.13042821],"study_design_scores_gemma":[0.00026461514,0.00012607971,0.007568121,0.00055731647,0.00002026998,0.000003828903,0.00003788201,0.98752576,0.000007835653,0.0036926563,0.000041541793,0.00015406583],"about_ca_topic_score_codex":0.00006137811,"about_ca_topic_score_gemma":0.00032248363,"teacher_disagreement_score":0.59165466,"about_ca_system_score_codex":0.00012262088,"about_ca_system_score_gemma":0.00020320516,"threshold_uncertainty_score":0.555022},"labels":[],"label_agreement":null},{"id":"W4393186342","doi":"10.1109/vcc60689.2023.10474783","title":"Bridging Distribution Learning and Image Clustering in High-Dimensional Space","year":2023,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bridging (networking); Cluster analysis; Computer science; Space (punctuation); Distribution (mathematics); Artificial intelligence; Mathematics","score_opus":0.009836961242276428,"score_gpt":0.2611195943457958,"score_spread":0.25128263310351934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393186342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06595762,0.000022692915,0.9317292,0.0015799603,0.00010423155,0.000046217192,7.4035154e-7,0.00018140257,0.00037790908],"genre_scores_gemma":[0.6359635,0.000011609266,0.36318138,0.000056787747,0.000030001775,0.0000030703782,0.0000067234837,0.000004848139,0.00074205745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992367,0.00007884636,0.00010291867,0.00025727157,0.00011042541,0.00021385182],"domain_scores_gemma":[0.9997395,0.00006491515,0.000024177827,0.00010308044,0.00001734421,0.00005096918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054367527,0.00007344244,0.0000961994,0.000070138136,0.00008436829,0.000097668635,0.00010218638,0.000032425545,0.0000061395717],"category_scores_gemma":[0.000044466728,0.00006723386,0.000016306609,0.0003569007,0.000017213953,0.0002711001,0.00031699557,0.00013516351,0.000017290065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011599289,0.00002337701,0.0029029574,0.00005383338,0.000010408354,0.00020853747,0.0006179799,0.0030965942,0.028487803,0.21215306,0.002253649,0.7501802],"study_design_scores_gemma":[0.00019054992,0.000014561754,0.011131277,0.000024149105,9.483398e-7,0.000014963134,0.00000521589,0.98185265,0.0010125232,0.0053819907,0.00026937877,0.00010182026],"about_ca_topic_score_codex":0.00008379274,"about_ca_topic_score_gemma":0.000017449987,"teacher_disagreement_score":0.978756,"about_ca_system_score_codex":0.000022063046,"about_ca_system_score_gemma":0.000013425463,"threshold_uncertainty_score":0.2741717},"labels":[],"label_agreement":null},{"id":"W4393187229","doi":"10.21203/rs.3.rs-4142146/v1","title":"A mixture of experts regression model for functional response with functional covariates","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Covariate; Functional data analysis; Inference; Estimator; Computer science; Functional principal component analysis; Regression analysis; Regression; Data set; Functional dependency; Function (biology); Data mining; Set (abstract data type); Econometrics; Mathematics; Statistics; Machine learning; Artificial intelligence","score_opus":0.11225010700302686,"score_gpt":0.40207963134000496,"score_spread":0.2898295243369781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393187229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034151443,0.0020751473,0.98812944,0.0040494734,0.00054164225,0.0011671558,0.00019350518,0.00014179992,0.00028669692],"genre_scores_gemma":[0.25087062,0.000073983,0.73777837,0.0000943335,0.0004653526,0.001217671,0.000118054704,0.00008014325,0.00930145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99506867,0.00089211983,0.00040430768,0.0012917174,0.0017332797,0.00060988014],"domain_scores_gemma":[0.9952733,0.0014829297,0.00014208123,0.0012867072,0.0015893771,0.00022559134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004552698,0.00037109773,0.00048003363,0.0007597193,0.0002540155,0.00029375032,0.00089510856,0.0005389758,0.000030024305],"category_scores_gemma":[0.0004636853,0.00025213932,0.00029856878,0.0006190752,0.00018630736,0.00015604467,0.0021870667,0.0013701688,0.000007368531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.024103178,0.00078559044,0.000054690896,0.0067327376,0.00061761803,0.0001566367,0.008057271,0.035511095,0.019531058,0.6334589,0.22722055,0.043770675],"study_design_scores_gemma":[0.00045059883,0.00032286666,0.00015928489,0.0016014448,0.000016644646,0.00002108149,0.000036898786,0.6372323,0.0016157448,0.35716313,0.0011145667,0.00026540805],"about_ca_topic_score_codex":0.000017047647,"about_ca_topic_score_gemma":0.000007644858,"teacher_disagreement_score":0.6017212,"about_ca_system_score_codex":0.00020481272,"about_ca_system_score_gemma":0.002519293,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W4393354791","doi":"10.1101/2024.03.29.587376","title":"GTRpmix: A linked general-time reversible model for profile mixture models","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Division of Environmental Biology; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Mixture model; Computer science; Econometrics; Economics; Artificial intelligence","score_opus":0.022658395890291567,"score_gpt":0.24356045599405565,"score_spread":0.2209020601037641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393354791","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004300708,0.002591151,0.98555416,0.0013273328,0.0018281012,0.0021903722,0.0006900032,0.0014005874,0.000117578],"genre_scores_gemma":[0.06548206,0.00015388944,0.9305926,0.0007712898,0.0008945194,0.0010572256,0.0000012193478,0.0002523112,0.0007948654],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945813,0.00020641218,0.00081588305,0.0026423798,0.000622892,0.0011311274],"domain_scores_gemma":[0.9950839,0.000111722184,0.00041609252,0.0030686993,0.0008041958,0.00051533344],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014837739,0.0010477733,0.0010895592,0.0005211146,0.000266564,0.0009413668,0.002655977,0.0013051574,0.00001593667],"category_scores_gemma":[0.00010351703,0.0010479093,0.0006168399,0.00082196976,0.00009256879,0.0005144444,0.0026890181,0.0014860389,0.00013256197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006562513,0.0003266302,0.0000049659093,0.0030046091,0.0006392885,0.00012342568,0.00018195919,0.015854748,0.5326181,0.39529815,0.05177844,0.00010403883],"study_design_scores_gemma":[0.00040830317,0.00004647155,0.000012014478,0.0005120288,0.00016195876,4.939085e-8,1.7519811e-7,0.9515439,0.032147527,0.012544582,0.0014105113,0.0012124642],"about_ca_topic_score_codex":0.000015535374,"about_ca_topic_score_gemma":5.8901594e-7,"teacher_disagreement_score":0.93568915,"about_ca_system_score_codex":0.0003418855,"about_ca_system_score_gemma":0.0018680432,"threshold_uncertainty_score":0.99999136},"labels":[],"label_agreement":null},{"id":"W4393396549","doi":"10.1007/s13253-024-00618-w","title":"Faster Asymptotic Solutions for N-Mixtures on Large Populations","year":2024,"lang":"en","type":"article","venue":"Journal of Agricultural Biological and Environmental Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Computer science","score_opus":0.03916758347403679,"score_gpt":0.2661638471740937,"score_spread":0.2269962637000569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393396549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026897376,0.0008413229,0.9708166,0.00073368504,0.0003252275,0.000079812984,0.0002450395,0.000009118838,0.00005182624],"genre_scores_gemma":[0.70623535,0.00022620228,0.29303178,0.00016080742,0.00014729846,0.0000025242741,0.000023761702,0.0000022210436,0.00017006404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9993137,0.000045163084,0.0002170001,0.0001365155,0.00010278585,0.00018482588],"domain_scores_gemma":[0.9996044,0.00018859321,0.000063001666,0.00004572393,0.000009275965,0.000089019035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017012526,0.00010117634,0.00013255718,0.000025980802,0.00014319342,0.00009244006,0.00012184793,0.00006074317,0.000021173852],"category_scores_gemma":[0.000026547586,0.000047320435,0.0000737043,0.000043976273,0.000038411083,0.000135549,0.00006707014,0.00013056373,0.0000055048345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025630135,0.00028312329,0.00036424497,0.000026795335,0.00009287332,0.00004249982,0.00030528847,0.0001147724,0.018166043,0.79049903,0.023128372,0.16695133],"study_design_scores_gemma":[0.0013409245,0.0053196563,0.46976385,0.00020513736,0.00017744918,0.0011581598,0.00022015296,0.022394521,0.00076295657,0.4593082,0.038427126,0.00092186773],"about_ca_topic_score_codex":2.9601972e-7,"about_ca_topic_score_gemma":4.4052308e-7,"teacher_disagreement_score":0.679338,"about_ca_system_score_codex":0.000031013373,"about_ca_system_score_gemma":0.0000043245063,"threshold_uncertainty_score":0.19296713},"labels":[],"label_agreement":null},{"id":"W4394760812","doi":"10.1111/coin.12641","title":"Novel mixture allocation models for topic learning","year":2024,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Inference; Topic model; Dirichlet distribution; Computer science; Mixture model; Artificial intelligence; Prior probability; Latent variable; Categorization; Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.054653766304620065,"score_gpt":0.3294408408894598,"score_spread":0.27478707458483975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394760812","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022056916,0.0010154524,0.99462503,0.001905987,0.00062169944,0.00019887557,0.0000034374686,0.00025476588,0.0013526814],"genre_scores_gemma":[0.19741684,0.000017207292,0.8007954,0.00038015045,0.0001380843,0.000039289524,0.000016016813,0.000010579524,0.0011864637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989236,0.000034523735,0.0002233692,0.00043300053,0.00019959715,0.00018590181],"domain_scores_gemma":[0.9988667,0.0006849845,0.000036388978,0.00015717378,0.0001922203,0.00006253179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035710714,0.0001257541,0.000109240485,0.00011122132,0.00012356283,0.00028238224,0.00044461683,0.00006939118,0.000008046264],"category_scores_gemma":[0.00006945063,0.00011757439,0.00009056526,0.00032044726,0.000028443961,0.00052349,0.00007842169,0.0001744837,0.00002599127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010728758,0.000009690267,3.2216062e-7,0.000025164538,0.000008188862,9.499326e-7,0.00034798568,0.24898975,0.00008983326,0.5660193,0.00024042914,0.18426734],"study_design_scores_gemma":[0.000016425649,0.000022157417,0.0000036065749,0.000029265893,0.0000029349194,0.000013258023,0.0000040790014,0.54069626,0.00039908188,0.45626295,0.002472203,0.00007779329],"about_ca_topic_score_codex":0.000003830479,"about_ca_topic_score_gemma":7.424368e-7,"teacher_disagreement_score":0.2917065,"about_ca_system_score_codex":0.000041499585,"about_ca_system_score_gemma":0.000123751,"threshold_uncertainty_score":0.47945443},"labels":[],"label_agreement":null},{"id":"W4396244365","doi":"10.48550/arxiv.2404.19528","title":"Tree Pólya Splitting distributions for multivariate count data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Multivariate statistics; Tree (set theory); Mathematics; Statistics; Geography; Combinatorics","score_opus":0.16697835912166004,"score_gpt":0.2588823729926948,"score_spread":0.09190401387103475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396244365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012150434,0.0001841569,0.9924707,0.0005398287,0.0013798712,0.00052176975,0.001147759,0.00035863524,0.0021822306],"genre_scores_gemma":[0.5910247,0.000084402556,0.40591174,0.00008016491,0.00027341917,0.0000040998557,0.00039459238,0.000031853968,0.00219503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971767,0.00014141038,0.0002567169,0.0018916498,0.00008511821,0.0004483806],"domain_scores_gemma":[0.99626213,0.00029456784,0.00019181048,0.0029131952,0.000160395,0.00017789287],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008676557,0.0003462462,0.00037657502,0.00016299293,0.00023370865,0.00031892356,0.003707134,0.0003122656,0.000008376834],"category_scores_gemma":[0.00012141585,0.0003668465,0.00023239014,0.00046089577,0.00007779595,0.0003318414,0.008421073,0.0006587001,0.00004258251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012106969,0.000055015742,0.000016819635,0.00016955042,0.0001275789,0.00010429464,0.000111931404,0.0011150105,0.00005063505,0.98146486,0.0025144233,0.014257776],"study_design_scores_gemma":[0.00020477001,0.000014428737,0.000048811184,0.00010355144,0.00012249422,0.0000028922111,0.00000859178,0.61512285,0.000044923698,0.38026246,0.0037844693,0.00027978086],"about_ca_topic_score_codex":0.00015078508,"about_ca_topic_score_gemma":0.00004913326,"teacher_disagreement_score":0.61400783,"about_ca_system_score_codex":0.00016637899,"about_ca_system_score_gemma":0.00031770582,"threshold_uncertainty_score":0.99987835},"labels":[],"label_agreement":null},{"id":"W4396512454","doi":"10.3390/e26050376","title":"Fast Fusion Clustering via Double Random Projection","year":2024,"lang":"en","type":"article","venue":"Entropy","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; China Scholarship Council; Alberta Machine Intelligence Institute; Jinan Science and Technology Bureau; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Cluster analysis; Random projection; Computer science; Projection (relational algebra); Artificial intelligence; Mathematics; Algorithm","score_opus":0.014646873899156108,"score_gpt":0.27229428976634745,"score_spread":0.25764741586719137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396512454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000758162,0.0004249839,0.9924531,0.0007471568,0.0018519952,0.00018413125,3.6445462e-7,0.000340963,0.0032391388],"genre_scores_gemma":[0.27250212,0.00005436017,0.72290176,0.0001848232,0.0006300879,0.000038987895,0.0000022335691,0.000019865818,0.0036657823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991896,0.000055175813,0.00012421362,0.00030127703,0.00014527874,0.00018445973],"domain_scores_gemma":[0.99965376,0.000023506724,0.000019392146,0.0002348354,0.000018289958,0.000050230483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002892378,0.00009365684,0.000101447855,0.000086701126,0.00008406108,0.00025852513,0.00021986992,0.00004606123,0.000027340784],"category_scores_gemma":[0.0000036833244,0.00007336921,0.00006779027,0.00024704542,0.000010548294,0.0003373845,0.00013174058,0.00012443645,0.00008933039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007122338,0.000029021086,0.000009231385,0.000064822874,0.000021448814,0.000050910046,0.0015436874,0.0000876998,0.044580214,0.13583328,0.0027076977,0.8150008],"study_design_scores_gemma":[0.000994437,0.00005693209,0.000025742038,0.00006201723,0.000008858924,0.00006763192,0.0000045222,0.9491482,0.011346834,0.016783522,0.02134181,0.00015949419],"about_ca_topic_score_codex":0.000029583272,"about_ca_topic_score_gemma":0.000004102333,"teacher_disagreement_score":0.9490605,"about_ca_system_score_codex":0.000037545313,"about_ca_system_score_gemma":0.000027590742,"threshold_uncertainty_score":0.29919094},"labels":[],"label_agreement":null},{"id":"W4396529244","doi":"10.1007/s11634-024-00590-w","title":"Clustering functional data via variational inference","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Inference; Computer science; Artificial intelligence; Data mining; Machine learning","score_opus":0.08627126853721646,"score_gpt":0.3698520144562673,"score_spread":0.28358074591905086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396529244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021493992,0.003181879,0.9949618,0.00091866864,0.00019804314,0.00004581369,0.00008020679,0.000047695834,0.00054440607],"genre_scores_gemma":[0.31595886,0.0019782071,0.6797007,0.00009113339,0.00009721537,0.000010402698,0.0020766188,0.0000045260012,0.000082326835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847806,0.00008306338,0.00025803593,0.0008552686,0.00020871664,0.00011685765],"domain_scores_gemma":[0.99797016,0.00023492365,0.000060760445,0.001661822,0.000032073087,0.00004028079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008757208,0.00009231056,0.00013954146,0.000263785,0.00006868417,0.00028128963,0.001157301,0.00004215574,0.000023352282],"category_scores_gemma":[0.00007723209,0.000080551945,0.000020286032,0.0012707771,0.000033033022,0.0038363286,0.0007876622,0.00011566379,0.000008540397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025344384,0.00002267433,0.0021023245,0.00002214398,0.00008487708,0.000002220068,0.00004863716,0.0005393791,0.00018838084,0.16845778,0.00014921265,0.8283798],"study_design_scores_gemma":[0.000042185162,0.000003515567,0.027115336,0.000013021591,0.00008017376,0.0000025046768,0.000003991246,0.9366771,0.0000030722365,0.024563426,0.0114028575,0.0000928085],"about_ca_topic_score_codex":0.000016025499,"about_ca_topic_score_gemma":0.00032155516,"teacher_disagreement_score":0.93613774,"about_ca_system_score_codex":0.000021773058,"about_ca_system_score_gemma":0.000050667117,"threshold_uncertainty_score":0.3284813},"labels":[],"label_agreement":null},{"id":"W4396619048","doi":"10.32388/up77j3","title":"Review of: \"A New Index for Measuring the Difference Between Two Probability Distributions\"","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Index (typography); Statistics; Mathematics; Computer science; World Wide Web","score_opus":0.11954923595746078,"score_gpt":0.3715184383975957,"score_spread":0.2519692024401349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396619048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.273538e-8,0.29993543,0.6215312,0.07466329,0.00081590744,0.0017586227,0.00023921096,0.00008335825,0.00097289984],"genre_scores_gemma":[0.000029589453,0.097378485,0.7901713,0.008452261,0.001186704,0.00068617647,0.00036112286,0.000049633745,0.101684734],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967572,0.00037098714,0.0009789583,0.0009300091,0.0005624618,0.0004003985],"domain_scores_gemma":[0.9962397,0.00067019183,0.00037676728,0.0020359794,0.000506135,0.00017117901],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037753698,0.00043853445,0.0012544033,0.000052641615,0.00011218844,0.00012110146,0.0026935227,0.0001681992,0.00004445926],"category_scores_gemma":[0.0009465496,0.0002461215,0.00067494105,0.00072204357,0.00008497493,0.000100956284,0.0008232947,0.00067240186,0.000011477499],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.5289958e-7,0.000009481492,0.000004661943,0.04896777,0.00004458329,2.3017488e-7,0.000009227922,2.3549125e-8,5.1654337e-7,0.035094537,0.5021387,0.41372994],"study_design_scores_gemma":[0.000066507804,0.000024039231,0.00005526079,0.06331049,0.00031182735,0.000004251193,7.7871256e-8,0.00015361706,0.000037187812,0.2614094,0.67436606,0.00026127807],"about_ca_topic_score_codex":0.00021682786,"about_ca_topic_score_gemma":0.000056587276,"teacher_disagreement_score":0.41346866,"about_ca_system_score_codex":0.000109483764,"about_ca_system_score_gemma":0.00096776884,"threshold_uncertainty_score":0.9999991},"labels":[],"label_agreement":null},{"id":"W4396623789","doi":"10.1007/s11135-024-01879-w","title":"Unit-log-symmetric models: characterization, statistical properties and their applications to analyzing an internet access data","year":2024,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Characterization (materials science); The Internet; Unit (ring theory); Computer science; Mathematics; World Wide Web; Materials science; Nanotechnology","score_opus":0.36635213259943883,"score_gpt":0.43078288442495183,"score_spread":0.064430751825513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396623789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025484692,0.00037817404,0.9720302,0.0009822984,0.00013894099,0.00033078855,0.000285419,0.0002551019,0.000114384085],"genre_scores_gemma":[0.8128668,0.00004989441,0.186227,0.00044980925,0.00008568962,0.00004136232,0.00019171947,0.000014255184,0.00007347817],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978032,0.00049685594,0.000388514,0.0008801606,0.0001897227,0.00024152121],"domain_scores_gemma":[0.9981378,0.00019307,0.00005898057,0.0012813725,0.00012126875,0.0002075611],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019361947,0.00017525432,0.0002565284,0.0002491421,0.00013694105,0.0014723507,0.0017302813,0.000066771674,0.000006942727],"category_scores_gemma":[0.00012693698,0.00013424129,0.000023801536,0.0011335737,0.00007589959,0.0026851017,0.0011795888,0.00018794014,0.000012159353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004441167,0.00005368895,0.00022630583,0.00010321893,0.000020640511,0.000001150326,0.00074484857,0.000005869237,0.0008837072,0.7343088,0.00007738991,0.26356992],"study_design_scores_gemma":[0.00006290547,0.0000478588,0.005187552,0.00005251309,0.000017439957,0.0000065279946,0.0000275144,0.90529567,0.0005828363,0.08309016,0.0053197355,0.0003092946],"about_ca_topic_score_codex":0.000690284,"about_ca_topic_score_gemma":0.0002265111,"teacher_disagreement_score":0.9052898,"about_ca_system_score_codex":0.000023632769,"about_ca_system_score_gemma":0.000110995155,"threshold_uncertainty_score":0.99956423},"labels":[],"label_agreement":null},{"id":"W4396675678","doi":"10.1007/s00357-024-09470-6","title":"Skew Multiple Scaled Mixtures of Normal Distributions with Flexible Tail Behavior and Their Application to Clustering","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Science Council","keywords":"Cluster analysis; Skew; Mathematics; Skew normal distribution; Pattern recognition (psychology); Statistics; Normal distribution; Computer science; Statistical physics; Artificial intelligence; Physics","score_opus":0.021196143170225674,"score_gpt":0.28421407031829893,"score_spread":0.26301792714807326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396675678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04023567,0.00031315218,0.95785916,0.001198785,0.00010484164,0.0001628411,0.000008536945,0.000025736656,0.00009127647],"genre_scores_gemma":[0.7626197,0.000020438625,0.23722629,0.000020282989,0.000058212943,0.000016151094,0.0000022473785,0.0000051084203,0.00003157363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922305,0.000051194602,0.0003156477,0.00015613422,0.00015223192,0.00010172785],"domain_scores_gemma":[0.99923974,0.00008871563,0.00017760963,0.00020960675,0.00019120376,0.00009309731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004227879,0.00008701604,0.00014994577,0.0001426346,0.00006093058,0.00010676192,0.00024002497,0.000048544916,0.0000012749695],"category_scores_gemma":[0.000025096228,0.00005875392,0.000048906335,0.00033364818,0.00003374329,0.00038687687,0.000043172637,0.00013213913,0.0000011238078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050067567,0.00011029227,0.0011293032,0.000078261975,0.000032440166,0.000003389568,0.0010702106,0.000086100765,0.34562922,0.035021845,0.00022613259,0.6165627],"study_design_scores_gemma":[0.0013297834,0.0010410661,0.1866015,0.00075005693,0.00019839942,0.00079877255,0.00019952325,0.519261,0.26106068,0.015292253,0.012859499,0.0006074594],"about_ca_topic_score_codex":0.000005228114,"about_ca_topic_score_gemma":0.000005649018,"teacher_disagreement_score":0.72238404,"about_ca_system_score_codex":0.000037733716,"about_ca_system_score_gemma":0.00007375535,"threshold_uncertainty_score":0.23959154},"labels":[],"label_agreement":null},{"id":"W4396747415","doi":"10.3390/axioms13050307","title":"A Short Note on Generating a Random Sample from Finite Mixture Distributions","year":2024,"lang":"en","type":"article","venue":"Axioms","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sample (material); Mathematics; Statistics; Statistical physics; Physics; Thermodynamics","score_opus":0.020270940686935933,"score_gpt":0.2905169388670747,"score_spread":0.2702459981801388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396747415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019189124,0.00071113097,0.99393106,0.0014158558,0.0009034474,0.00013203316,0.00020820695,0.00028173014,0.000497618],"genre_scores_gemma":[0.5734265,0.000016861946,0.42546868,0.00048436987,0.000375791,0.000027308146,0.00006700078,0.000011641359,0.000121824734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874467,0.00011340498,0.00019220379,0.00049124216,0.00019775778,0.00026072827],"domain_scores_gemma":[0.99839973,0.00094967155,0.000018130337,0.00050050544,0.000029655394,0.00010232038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029871144,0.00016116284,0.00017860858,0.00006614671,0.00016620987,0.00039214955,0.00040840445,0.000097309974,0.000026960957],"category_scores_gemma":[0.00015550501,0.00012741276,0.00013450772,0.00038753706,0.000026271859,0.00020430074,0.00011863777,0.00025922846,0.00006437372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010569037,0.00003554288,0.0000051919683,0.000009993037,0.000043069667,0.00007539425,0.0010486721,0.00014551118,0.004613951,0.37638417,0.0019992457,0.6156287],"study_design_scores_gemma":[0.00031705262,0.000053741056,0.00011444986,0.000106371874,0.000025702837,0.000008719867,0.0000033187473,0.8977837,0.004597534,0.07823351,0.018469265,0.00028662776],"about_ca_topic_score_codex":0.000117140466,"about_ca_topic_score_gemma":0.00001874267,"teacher_disagreement_score":0.8976382,"about_ca_system_score_codex":0.00003721181,"about_ca_system_score_gemma":0.000055956727,"threshold_uncertainty_score":0.51957417},"labels":[],"label_agreement":null},{"id":"W4396800896","doi":"10.1007/s00362-024-01561-1","title":"Variation comparison between infinitely divisible distributions and the normal distribution","year":2024,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Variation (astronomy); Distribution (mathematics); Mathematics; Infinite divisibility; Statistics; Statistical physics; Mathematical analysis; Physics; Astrophysics","score_opus":0.016315451939615404,"score_gpt":0.29549111378229215,"score_spread":0.2791756618426767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396800896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023896692,0.00020932515,0.99303573,0.0026586016,0.00021665642,0.00013194315,0.00047355203,0.000119395176,0.0029158518],"genre_scores_gemma":[0.87733877,0.000016647567,0.12224444,0.000070213144,0.00008473321,0.000014898045,0.00017471735,0.000004669171,0.000050934672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885565,0.00021784625,0.00023060085,0.0002769162,0.00019859885,0.00022040616],"domain_scores_gemma":[0.99816537,0.0014758037,0.000028943821,0.0001969217,0.000029216466,0.000103763676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063543994,0.00010926042,0.00016716756,0.000023194643,0.00023518979,0.0003845812,0.00020606509,0.000056823555,0.000021628235],"category_scores_gemma":[0.00024042037,0.00007135956,0.00003840851,0.00027908254,0.00020773444,0.000194729,0.00012078874,0.00023097884,0.000022254295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045892893,0.0000065071295,0.00015105832,0.000013627812,0.00001791222,0.0000025551415,0.00022098426,0.0000020568252,0.000017729737,0.861248,0.0005935456,0.13772143],"study_design_scores_gemma":[0.0006695496,0.000084616935,0.17371419,0.000043222684,0.00012122751,0.000011204147,0.000017492599,0.21107525,0.000042596643,0.590726,0.023206556,0.00028807137],"about_ca_topic_score_codex":0.000050383827,"about_ca_topic_score_gemma":0.000003970646,"teacher_disagreement_score":0.87709975,"about_ca_system_score_codex":0.000040118863,"about_ca_system_score_gemma":0.00005075018,"threshold_uncertainty_score":0.37085253},"labels":[],"label_agreement":null},{"id":"W4398251147","doi":"10.1080/15326349.2024.2355537","title":"Fisher and Bayes-Fisher information measures for finite mixture distributions","year":2024,"lang":"en","type":"article","venue":"Stochastic Models","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Fisher information; Bayes' theorem; Statistics; Applied mathematics; Fisher kernel; Econometrics; Bayesian probability","score_opus":0.01963458787270645,"score_gpt":0.2560783967826912,"score_spread":0.23644380890998473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398251147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037171758,0.0007064797,0.994476,0.0017927932,0.00057360384,0.00042435108,0.00013328412,0.00023360361,0.0016227118],"genre_scores_gemma":[0.4456754,0.00001531753,0.55276674,0.00055072433,0.00017279173,0.00021594555,0.00005349966,0.000018780187,0.0005307806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988721,0.00003960561,0.00025077668,0.00032500358,0.00021416091,0.00029834989],"domain_scores_gemma":[0.9990761,0.00030115305,0.000039891587,0.00033001328,0.00012665486,0.00012613219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042489305,0.00018532107,0.00017738563,0.00012050119,0.00016476525,0.00052020437,0.00029132687,0.00012342237,0.000005067765],"category_scores_gemma":[0.000114647824,0.00015420878,0.00009208992,0.00024087922,0.00004419473,0.0017170967,0.00010666149,0.00016995726,0.0000073658985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007644318,0.000010286805,3.1511937e-7,0.00007255405,0.000031135896,0.0000014124975,0.0010988108,0.0029406194,0.00003012253,0.7818983,0.0068277824,0.20708102],"study_design_scores_gemma":[0.000127922,0.000031154632,0.000004846346,0.00004517443,0.00001933241,0.000010181665,0.000004783728,0.6284917,0.000014748613,0.36673364,0.004385588,0.00013090673],"about_ca_topic_score_codex":0.000011766059,"about_ca_topic_score_gemma":0.0000046492405,"teacher_disagreement_score":0.6255511,"about_ca_system_score_codex":0.000033107735,"about_ca_system_score_gemma":0.00009280627,"threshold_uncertainty_score":0.62884516},"labels":[],"label_agreement":null},{"id":"W4399158654","doi":"10.1007/s00357-024-09473-3","title":"Finding Outliers in Gaussian Model-based Clustering","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs","keywords":"Outlier; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Gaussian; Computer science; Statistics; Physics","score_opus":0.05584761604273475,"score_gpt":0.3315201195779214,"score_spread":0.27567250353518663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399158654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023546137,0.00025459356,0.99164337,0.0036419954,0.0004884013,0.000045626897,3.112279e-7,0.00002538339,0.0015457183],"genre_scores_gemma":[0.62439203,0.000012139382,0.3753906,0.00008069272,0.00005578778,0.000001342517,1.7876725e-7,0.0000050776816,0.0000621913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990753,0.000078028796,0.00037095379,0.00014422629,0.00020307243,0.00012843485],"domain_scores_gemma":[0.99950194,0.00006950654,0.00013971276,0.00017696862,0.000047321755,0.00006455803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010505695,0.00007363899,0.00012762594,0.00038570073,0.000029782694,0.00018846261,0.0003445548,0.000059824346,0.0000021870533],"category_scores_gemma":[0.000036577367,0.00006040191,0.00007756175,0.00035043093,0.0000137221905,0.0005459177,0.00002063885,0.00024887302,0.0000035338207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022404434,0.000068449466,0.00019590506,0.00010999118,0.000019556164,0.000085664666,0.0022271823,0.029846894,0.023879398,0.1958383,0.0007715416,0.7469347],"study_design_scores_gemma":[0.00013568862,0.00002635254,0.0008587963,0.00016450977,0.000005184045,0.000021659613,0.000013669968,0.9800603,0.0005967746,0.017569562,0.000481574,0.00006597536],"about_ca_topic_score_codex":8.547074e-7,"about_ca_topic_score_gemma":0.0000024825943,"teacher_disagreement_score":0.9502134,"about_ca_system_score_codex":0.00013029727,"about_ca_system_score_gemma":0.00019583298,"threshold_uncertainty_score":0.24631186},"labels":[],"label_agreement":null},{"id":"W4399263796","doi":"10.1007/978-3-031-43601-7_5","title":"Metrics on Probability Distributions Through Optimal Commuting Maps","year":2024,"lang":"en","type":"book-chapter","venue":"Studies in systems, decision and control","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Geography; Probability distribution; Computer science; Statistics; Cartography; Mathematics","score_opus":0.0882839730901866,"score_gpt":0.352575806046844,"score_spread":0.2642918329566574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399263796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008433815,0.05835515,0.8547517,0.00042588322,0.002255056,0.00086627214,0.00016158546,0.0001075524,0.08306838],"genre_scores_gemma":[0.2808117,0.018499369,0.53854066,0.0016887677,0.0019779308,0.00088835286,0.000060307488,0.00026036715,0.15727256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969655,0.00017239108,0.0009600821,0.00096684624,0.0005722715,0.0003628784],"domain_scores_gemma":[0.9960548,0.0023750677,0.00025689058,0.00095350854,0.00027116542,0.000088544555],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021410615,0.00048400954,0.0012002842,0.00024528304,0.00027801192,0.00026689496,0.00063096103,0.00032091697,0.0000028699255],"category_scores_gemma":[0.00048372996,0.0003566963,0.00020175093,0.00021679646,0.00021610003,0.0001365461,0.0006765065,0.0007215355,0.000039380866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023584731,0.000020883583,0.00000514228,0.00016930692,0.00015822412,0.000071032046,0.0004265548,0.000026933787,6.143838e-7,0.9512986,0.0034468705,0.044352267],"study_design_scores_gemma":[0.00088725303,0.00019311356,0.000007300556,0.00221332,0.000091061884,0.00006152534,0.00010447847,0.006864025,0.0000011328779,0.8195094,0.1695807,0.00048668636],"about_ca_topic_score_codex":0.000013416529,"about_ca_topic_score_gemma":0.000010047024,"teacher_disagreement_score":0.31621104,"about_ca_system_score_codex":0.0002831929,"about_ca_system_score_gemma":0.000059843802,"threshold_uncertainty_score":0.9998885},"labels":[],"label_agreement":null},{"id":"W4399721808","doi":"10.1002/sim.10151","title":"A sparse factor model for clustering high‐dimensional longitudinal data","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Categorical variable; Dirichlet process; Curse of dimensionality; Gibbs sampling; Clustering high-dimensional data; Data mining; Bayesian probability; Artificial intelligence; Machine learning","score_opus":0.12987540817975268,"score_gpt":0.39157382235535,"score_spread":0.2616984141755973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399721808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074184085,0.00055165536,0.9956971,0.0014993256,0.0011783929,0.00020064945,0.00063657935,0.00006695118,0.00009516774],"genre_scores_gemma":[0.054815207,0.000036013287,0.9440892,0.00029729857,0.00023996641,0.000014098235,0.00011675004,0.000015716907,0.0003757666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985048,0.00003693063,0.00030817097,0.0005796279,0.00029599495,0.00027443492],"domain_scores_gemma":[0.9986306,0.00049441075,0.000035995796,0.0006839758,0.000057458972,0.00009755045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007534227,0.00014901943,0.0002525354,0.00014778893,0.000048353366,0.00005212087,0.00072742894,0.000052105148,0.000027418033],"category_scores_gemma":[0.00026661652,0.00011550758,0.000014191595,0.00019771869,0.000071227354,0.00021438651,0.00039109343,0.00019751607,0.000005310759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015661615,0.00002361768,0.00001456944,0.00020097921,0.000024901186,0.0001600151,0.0007683227,0.0011005976,0.00019045938,0.6845121,0.02963815,0.28335068],"study_design_scores_gemma":[0.00028514976,0.00005596165,0.00009157783,0.00015834052,0.000012983018,0.0000148303725,0.0000018786749,0.77468055,0.000007175301,0.22390547,0.00068587,0.00010017769],"about_ca_topic_score_codex":0.000047371974,"about_ca_topic_score_gemma":0.00010475173,"teacher_disagreement_score":0.77357996,"about_ca_system_score_codex":0.0000425242,"about_ca_system_score_gemma":0.00013007414,"threshold_uncertainty_score":0.47102624},"labels":[],"label_agreement":null},{"id":"W4399827830","doi":"10.1002/sim.10144","title":"Bayesian mixture modelling with ranked set samples","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Bayesian probability; Ranking (information retrieval); Bayesian average; Computer science; Statistics; Sampling (signal processing); RSS; Simple random sample; Bayesian inference; Data mining; Variable-order Bayesian network; Mathematics; Artificial intelligence","score_opus":0.03274320391658409,"score_gpt":0.3164800722356023,"score_spread":0.28373686831901823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399827830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039529044,0.001631927,0.993467,0.0020828168,0.00049741805,0.00016210288,0.00004682761,0.00012934243,0.0019430728],"genre_scores_gemma":[0.056114737,0.00016986456,0.94270676,0.00046499757,0.00020513764,0.000012497375,0.000027075586,0.00002160637,0.0002773352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984085,0.00011800688,0.0002989683,0.00047756007,0.0003787057,0.00031823915],"domain_scores_gemma":[0.9988124,0.0005451204,0.00003846761,0.00041996196,0.000062729974,0.00012133898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079132966,0.00019745991,0.0003105909,0.00022038545,0.00005559964,0.00007741178,0.00041808473,0.00007335548,0.00004959834],"category_scores_gemma":[0.000047595935,0.00013187334,0.000017555616,0.00058541994,0.00012670405,0.00014310812,0.00005471412,0.00038182567,0.000006559386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011342304,0.000010319796,0.000035257744,0.00013619446,0.000029042867,0.0004777289,0.003288145,0.0009595926,0.000050428764,0.91692686,0.00733848,0.07073662],"study_design_scores_gemma":[0.00031221347,0.00011324004,0.000024075225,0.000374145,0.000018940042,0.000042914373,0.00003466525,0.60896695,0.000023199302,0.3825817,0.007359631,0.0001482854],"about_ca_topic_score_codex":0.00011219353,"about_ca_topic_score_gemma":0.000058773025,"teacher_disagreement_score":0.6080074,"about_ca_system_score_codex":0.000040827446,"about_ca_system_score_gemma":0.00010592051,"threshold_uncertainty_score":0.5377639},"labels":[],"label_agreement":null},{"id":"W4400011049","doi":"10.1007/s11634-024-00598-2","title":"Dirichlet compound negative multinomial mixture models and applications","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Mathematics; Econometrics; Mathematical analysis","score_opus":0.04164186050322628,"score_gpt":0.3451560601491029,"score_spread":0.3035141996458766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400011049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021674736,0.010279588,0.9872217,0.0008912098,0.000041829648,0.00015917668,0.00007355732,0.000051266365,0.0010649074],"genre_scores_gemma":[0.5465232,0.0071497215,0.44572473,0.00011670979,0.000073436975,0.00007185662,0.00023620104,0.000006775919,0.000097377066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986279,0.00009406106,0.00024162364,0.00078161637,0.00012532309,0.00012949792],"domain_scores_gemma":[0.99875426,0.00024242667,0.000067614645,0.0008424127,0.000034163302,0.0000591437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041733618,0.00011983563,0.00020329586,0.00025270507,0.00009760929,0.00029488248,0.0005358549,0.000058235702,0.0000020838947],"category_scores_gemma":[0.000018915165,0.00010061124,0.000030512418,0.0012350893,0.0000871606,0.0021079006,0.000252333,0.00013706935,0.0000019875545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025877698,0.000025748044,0.0002887306,0.000027899297,0.000069881964,0.0000018245802,0.00025087388,0.00014744,0.00021554797,0.34713808,0.00009393197,0.65173745],"study_design_scores_gemma":[0.00007377808,0.000004952909,0.0015106347,0.000011897685,0.000110770015,0.0000019620695,0.000031184438,0.84317917,0.000023198158,0.13938989,0.015549164,0.000113401824],"about_ca_topic_score_codex":0.00002087851,"about_ca_topic_score_gemma":0.00020574113,"teacher_disagreement_score":0.8430317,"about_ca_system_score_codex":0.000020200405,"about_ca_system_score_gemma":0.000022628376,"threshold_uncertainty_score":0.41028073},"labels":[],"label_agreement":null},{"id":"W4400173342","doi":"10.1002/cjs.11814","title":"Estimation in a general mixture of Markov jump processes","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Markov chain; Estimator; Applied mathematics; Mathematics; Mixture model; Markov process; Population; Matrix (chemical analysis); Markov model; Fisher information; Computer science; Algorithm; Statistics","score_opus":0.012665424610951258,"score_gpt":0.25765778562845804,"score_spread":0.24499236101750677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400173342","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013845214,0.0018924342,0.9954073,0.000457034,0.00044341024,0.00004085593,0.00006948686,0.0000037342884,0.00030122278],"genre_scores_gemma":[0.20156571,0.00003899648,0.79815876,0.000074430034,0.00004818175,5.8359353e-7,0.0000016522577,0.0000058108717,0.00010585748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992557,0.000048410395,0.0003158783,0.00009285216,0.00012985276,0.0001573054],"domain_scores_gemma":[0.9992899,0.0001145544,0.000097920165,0.00009879816,0.00019191379,0.00020693959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003549739,0.000072883086,0.00015368684,0.00035108536,0.000022489196,0.00010507068,0.00028723569,0.000045827175,0.000015384416],"category_scores_gemma":[0.00023687322,0.00006330498,0.000024218816,0.0004414921,0.000036263486,0.00023039457,0.000008583402,0.00017473122,0.0000012780845],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000397926,0.000011615719,0.00030180434,0.00048946653,0.000029684135,0.0012407026,0.0025913152,0.00058595027,0.00011892616,0.32565773,0.020514695,0.6484541],"study_design_scores_gemma":[0.00034277036,0.00024399071,0.002809609,0.0009106285,0.000043467484,0.0006622572,0.000026469916,0.51648426,0.0009540293,0.4683228,0.00890384,0.00029582766],"about_ca_topic_score_codex":0.00052379025,"about_ca_topic_score_gemma":0.005077407,"teacher_disagreement_score":0.6481583,"about_ca_system_score_codex":0.000070660666,"about_ca_system_score_gemma":0.0024683515,"threshold_uncertainty_score":0.43787497},"labels":[],"label_agreement":null},{"id":"W4400767755","doi":"10.2139/ssrn.4899072","title":"Bayesian Adaptive Sparse Copula","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Copula (linguistics); Bayesian probability; Econometrics; Computer science; Mathematics; Artificial intelligence","score_opus":0.017513153367682544,"score_gpt":0.2739250269688807,"score_spread":0.25641187360119816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400767755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003107946,0.021562295,0.96552515,0.0027384486,0.0028126177,0.00026461724,0.0000066396115,0.00023192023,0.0065475055],"genre_scores_gemma":[0.5644217,0.009233443,0.4139115,0.00056485884,0.0024688349,0.000045398683,0.0000069368775,0.00014237562,0.009204947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939782,0.00045510146,0.00059361,0.000996087,0.0006002771,0.0033767207],"domain_scores_gemma":[0.9981531,0.00006421235,0.00034723888,0.0010058713,0.00015896534,0.0002706215],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003892754,0.0005621538,0.0005978733,0.00039377605,0.00021183287,0.00071992574,0.0024910858,0.00047952097,0.000015546026],"category_scores_gemma":[0.00003861473,0.00048138696,0.00054602884,0.0003532215,0.00006175825,0.00020642133,0.0021232523,0.012906061,0.00011820015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015695403,0.000030829953,0.0000029281034,0.000023484436,0.00026920348,0.000079121965,0.00027073082,0.00008489615,0.000016076337,0.8136305,0.00077572843,0.1848008],"study_design_scores_gemma":[0.00029074194,0.00018468368,0.000004553436,0.0002033743,0.00008761869,0.0012818758,0.000051234547,0.037970327,0.000058368565,0.95809764,0.0012707473,0.0004988327],"about_ca_topic_score_codex":0.00007121661,"about_ca_topic_score_gemma":0.0002217176,"teacher_disagreement_score":0.56411093,"about_ca_system_score_codex":0.0015496463,"about_ca_system_score_gemma":0.008685273,"threshold_uncertainty_score":0.9997638},"labels":[],"label_agreement":null},{"id":"W4400905217","doi":"10.1109/lra.2024.3432350","title":"A Hessian for Gaussian Mixture Likelihoods in Nonlinear Least Squares","year":2024,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hessian matrix; Least-squares function approximation; Nonlinear system; Non-linear least squares; Mathematics; Applied mathematics; Gaussian; Mixture model; Mathematical optimization; Statistics; Explained sum of squares; Chemistry; Physics; Computational chemistry","score_opus":0.012656731739097682,"score_gpt":0.2723217609700466,"score_spread":0.2596650292309489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400905217","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002058443,0.00035452438,0.9679385,0.028396187,0.0007590862,0.00022143932,0.0000070408887,0.0001844034,0.000080396974],"genre_scores_gemma":[0.13672736,0.000024966941,0.860722,0.0021825356,0.00023865057,0.000025405072,0.000006503782,0.000017971843,0.000054584096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989645,0.000057345784,0.00023478948,0.0003650192,0.00013322117,0.00024511485],"domain_scores_gemma":[0.9995615,0.00009385729,0.000040484585,0.00021051802,0.000018924602,0.00007473833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030221546,0.0001519622,0.0001670868,0.00020411228,0.00007641945,0.00041401444,0.00021364745,0.00008479924,0.0000013867825],"category_scores_gemma":[0.000011587841,0.00013037633,0.00006653259,0.00029502212,0.000029526644,0.0003750086,0.000029520572,0.00014644043,0.000004963746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011297976,0.00011047042,0.00013005301,0.0008672164,0.00006850065,0.0001258015,0.0042578233,0.011077109,0.019339304,0.35362402,0.013934486,0.5964539],"study_design_scores_gemma":[0.00022706273,0.000034457415,0.00034899364,0.0001862012,0.000009719141,0.000019517804,0.000006194204,0.9849164,0.00054658594,0.010272037,0.0032329704,0.00019987748],"about_ca_topic_score_codex":0.0000071270274,"about_ca_topic_score_gemma":0.000008920324,"teacher_disagreement_score":0.9738393,"about_ca_system_score_codex":0.00002842798,"about_ca_system_score_gemma":0.00003988708,"threshold_uncertainty_score":0.53165925},"labels":[],"label_agreement":null},{"id":"W4401009914","doi":"10.1145/3654522.3654551","title":"Data Clustering with Libby-Novick Beta-Liouville Mixture Models: A Minimum Message Length Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence","score_opus":0.058429898016514464,"score_gpt":0.2816727622763654,"score_spread":0.22324286425985093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401009914","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008077863,0.0020373235,0.90890986,0.0015497335,0.0002862132,0.0002936689,0.000036108453,0.0007351298,0.086071186],"genre_scores_gemma":[0.07253074,0.000066191686,0.9218531,0.0006184356,0.00018927356,0.000029749639,0.000040758892,0.000051379597,0.0046203174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970408,0.00014753897,0.00032134776,0.0014698029,0.00047208322,0.0005483974],"domain_scores_gemma":[0.9970382,0.000118392374,0.00005115727,0.0025319778,0.00005142614,0.0002088764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088745233,0.00037280493,0.00037773495,0.00019222389,0.00014080251,0.00084335415,0.0027811734,0.00016684366,0.000041630326],"category_scores_gemma":[0.000008159327,0.00024792404,0.00008334611,0.0007908661,0.00006353046,0.0020777965,0.0016685987,0.00044273224,0.000031564807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028645794,0.00019372237,0.0000033043536,0.00048579776,0.00030813197,0.0002442621,0.003000384,0.0016470692,0.00031945252,0.6586811,0.03655649,0.29853162],"study_design_scores_gemma":[0.00023909735,0.00006429607,0.0000022950428,0.00008652076,0.000041054696,0.00015587578,0.000048173948,0.9687923,0.00016094193,0.011397085,0.018607596,0.0004047602],"about_ca_topic_score_codex":0.00003576722,"about_ca_topic_score_gemma":0.00004139336,"teacher_disagreement_score":0.96714526,"about_ca_system_score_codex":0.00003331041,"about_ca_system_score_gemma":0.000179802,"threshold_uncertainty_score":0.9999973},"labels":[],"label_agreement":null},{"id":"W4401160419","doi":"10.1080/07362994.2024.2372605","title":"Mixtures of multivariate Gaussians","year":2024,"lang":"en","type":"article","venue":"Stochastic Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Multivariate statistics; Econometrics; Mixture model; Statistics; Applied mathematics","score_opus":0.009958612752616764,"score_gpt":0.28825010702172477,"score_spread":0.278291494269108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401160419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006572387,0.0010691622,0.9973232,0.0004171364,0.000019281855,0.00011002092,0.000013621167,0.00006098402,0.00092085067],"genre_scores_gemma":[0.7310779,0.000016125034,0.268522,0.000034948247,0.00003747408,0.000064035776,0.0000050178114,0.00000381872,0.00023864472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993164,0.000023624722,0.00016965954,0.0002950436,0.00009493533,0.00010036854],"domain_scores_gemma":[0.9994279,0.00011773144,0.000037905676,0.00032166782,0.00003409598,0.000060696104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016590035,0.00007895281,0.00017326405,0.00021648001,0.00006803389,0.000075052565,0.00020806638,0.000035027566,0.000010810821],"category_scores_gemma":[0.000006925529,0.000060757713,0.00011360225,0.0012188643,0.000048956448,0.00007427231,0.0000604461,0.000064029526,0.0000039733786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.27706e-7,0.000015406857,0.0000040770824,0.000012692889,0.00020508633,4.1475593e-7,0.00017591706,0.00020227527,0.0011879206,0.8908139,0.00003032076,0.10735169],"study_design_scores_gemma":[0.00006802713,0.000017206932,0.00065620424,0.00001938882,0.0007366722,0.0000045135275,0.000010876641,0.7713748,0.00040696058,0.22427979,0.0022639802,0.00016157524],"about_ca_topic_score_codex":0.000036999456,"about_ca_topic_score_gemma":0.0000057882594,"teacher_disagreement_score":0.7711725,"about_ca_system_score_codex":0.0000050640074,"about_ca_system_score_gemma":0.000024656543,"threshold_uncertainty_score":0.24776277},"labels":[],"label_agreement":null},{"id":"W4401203656","doi":"10.1002/cjs.11824","title":"Variable selection in modelling clustered data via within‐cluster resampling","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agency for Healthcare Research and Quality","keywords":"Resampling; Variable (mathematics); Cluster (spacecraft); Selection (genetic algorithm); Feature selection; Computer science; Data mining; Artificial intelligence; Mathematics; Computer network","score_opus":0.062435855855376546,"score_gpt":0.28113014918402784,"score_spread":0.2186942933286513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401203656","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000078291276,0.00055886526,0.99765366,0.00030733392,0.0010344753,0.000059337453,0.00008047815,0.000010222939,0.00021734489],"genre_scores_gemma":[0.041861344,0.000011397814,0.95763296,0.00020549505,0.00017229689,4.7790815e-7,0.0000055368187,0.000014454277,0.000096042786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874926,0.000105892155,0.00046212215,0.00023596172,0.00016237579,0.00028441777],"domain_scores_gemma":[0.9989688,0.00019458009,0.0001071663,0.00025633635,0.0001459905,0.00032712903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014837256,0.00010585972,0.00017712743,0.00040862834,0.00008487908,0.0004106575,0.00074718235,0.0000722327,0.000015723497],"category_scores_gemma":[0.00010883803,0.000100115045,0.000017889059,0.00047825061,0.000023965942,0.0006873836,0.000052956413,0.0004421083,0.0000036646475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011379404,0.00001153967,0.000090024325,0.0001445392,0.00006335779,0.00075105554,0.002668256,0.17059162,0.00010917954,0.72129864,0.012176422,0.09208401],"study_design_scores_gemma":[0.00009611115,0.000028582797,0.000012536908,0.00014837667,0.0000125730985,0.00025594738,0.0000067102374,0.7808161,0.000010620843,0.21552983,0.0029942354,0.000088432826],"about_ca_topic_score_codex":0.0028326889,"about_ca_topic_score_gemma":0.008203032,"teacher_disagreement_score":0.6102244,"about_ca_system_score_codex":0.00017833772,"about_ca_system_score_gemma":0.0018538914,"threshold_uncertainty_score":0.45774844},"labels":[],"label_agreement":null},{"id":"W4401462796","doi":"10.1007/978-3-031-65993-5_39","title":"Variable Selection for Clustering Three-Way Data","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cluster analysis; Computer science; Selection (genetic algorithm); Feature selection; Variable (mathematics); Artificial intelligence; Data mining; Mathematics","score_opus":0.048245494580308926,"score_gpt":0.3153061703362121,"score_spread":0.2670606757559032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401462796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.2510177e-7,0.042505905,0.89298433,0.000027117441,0.0032692146,0.00058534247,0.000018603081,0.00012951397,0.060479466],"genre_scores_gemma":[0.0015096844,0.0014578099,0.94989204,0.0000671547,0.0012235157,0.000028914275,0.000036215864,0.000085722866,0.045698915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997642,0.00002511132,0.00066664885,0.0011174709,0.00019942361,0.0003493473],"domain_scores_gemma":[0.998564,0.000337866,0.00025316828,0.0006948307,0.00007847844,0.00007163165],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011404388,0.0003571526,0.00053123786,0.00021316626,0.00014227639,0.0003860705,0.00093374547,0.00022134982,0.0000027404194],"category_scores_gemma":[0.000021334763,0.0003286752,0.000060994742,0.00010311852,0.000031267988,0.00047960773,0.0009915687,0.00038975058,0.000007359037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030140875,0.0000038349167,0.0000043347427,0.0006497035,0.000026843529,0.000004182728,0.00007580589,0.0025253145,0.000002830189,0.76145387,0.00007956791,0.2351707],"study_design_scores_gemma":[0.000043824824,0.000036329875,1.4902844e-7,0.0013873352,0.0000142217905,0.000052039046,0.00000465813,0.55447114,0.0000039390716,0.24230899,0.20145957,0.00021778003],"about_ca_topic_score_codex":0.00006353252,"about_ca_topic_score_gemma":0.00012663573,"teacher_disagreement_score":0.55194587,"about_ca_system_score_codex":0.00008956788,"about_ca_system_score_gemma":0.000047429774,"threshold_uncertainty_score":0.99991655},"labels":[],"label_agreement":null},{"id":"W4401548765","doi":"10.1111/insr.12588","title":"Clustering Longitudinal Data: A Review of Methods and Software Packages","year":2024,"lang":"en","type":"review","venue":"International Statistical Review","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Data mining; Software; Data science; Longitudinal data; Missing data; Machine learning","score_opus":0.19176435612279832,"score_gpt":0.5342241889714334,"score_spread":0.3424598328486351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401548765","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8907594e-11,0.49961323,0.49862185,0.00027780177,0.00039001388,0.00036028546,0.00048060657,0.00003032507,0.00022588621],"genre_scores_gemma":[9.198098e-10,0.51259,0.48665494,0.00037152937,0.00006851807,0.00004521514,0.00017598498,0.000018088818,0.0000757585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99588597,0.000842066,0.0014625756,0.0010914715,0.00047492303,0.0002430065],"domain_scores_gemma":[0.99616235,0.0017137757,0.0005007201,0.0012677099,0.00018592243,0.00016952574],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033270495,0.00046512944,0.0025151887,0.00012212503,0.000031398333,0.0001343565,0.0024933699,0.0001198899,0.00015698023],"category_scores_gemma":[0.0037717752,0.00031675913,0.0002985727,0.00038933402,0.00010378918,0.00027598065,0.0026749943,0.0005268409,0.00005361982],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.4898673e-7,0.000008564032,3.6584602e-8,0.3419728,0.00012095108,0.000029296456,0.0000010671524,1.4759846e-9,6.5723005e-9,0.037594505,0.012096007,0.6081766],"study_design_scores_gemma":[0.000015546868,0.000012564352,3.0403334e-7,0.399756,0.00095112255,0.00023375114,3.166103e-8,0.00025470273,1.716963e-8,0.0037765538,0.5948266,0.00017281472],"about_ca_topic_score_codex":0.000007731815,"about_ca_topic_score_gemma":0.0000011690848,"teacher_disagreement_score":0.6080038,"about_ca_system_score_codex":0.00006585644,"about_ca_system_score_gemma":0.00025698647,"threshold_uncertainty_score":0.9999285},"labels":[],"label_agreement":null},{"id":"W4401593958","doi":"10.3329/jsr.v58i1.75425","title":"Change point detection via Gaussian mixture model","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Change detection; Univariate; Cluster analysis; Series (stratigraphy); Mixture model; Computer science; Multivariate statistics; Gaussian; Scale (ratio); Gaussian process; Pattern recognition (psychology); Data mining; Point (geometry); Artificial intelligence; Algorithm; Mathematics; Machine learning; Geography; Cartography","score_opus":0.11596896893573344,"score_gpt":0.42967000359178975,"score_spread":0.3137010346560563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401593958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011717718,0.0009208965,0.99259377,0.004658986,0.00040347775,0.00010941652,0.000007734317,0.000025979352,0.0011625929],"genre_scores_gemma":[0.46051177,0.00011362384,0.538679,0.000106412146,0.00037473155,0.0000059069143,2.9333657e-7,0.000011451263,0.00019678898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974682,0.0004055668,0.00035144365,0.0002501196,0.0010949542,0.0004297488],"domain_scores_gemma":[0.9982146,0.00075448677,0.00004593709,0.0002370704,0.0003979245,0.0003499689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039445683,0.00010486457,0.0002005745,0.00044798962,0.000117816795,0.00037840745,0.0005644091,0.00010451489,0.000041886593],"category_scores_gemma":[0.0004236448,0.00007349287,0.00008469016,0.00060651306,0.00009493379,0.0006142673,0.00016156181,0.0012527971,0.000040113293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021369766,0.000032143424,7.666977e-7,0.000055455588,0.000016749938,0.00047116572,0.00045068053,0.000004768319,0.002995673,0.31211174,0.0022726706,0.68156683],"study_design_scores_gemma":[0.00008395396,0.00027383148,0.00011390645,0.00007832264,0.0000056716312,0.00026056505,0.0000057741822,0.5044209,0.0008349529,0.49251878,0.0013381939,0.00006519648],"about_ca_topic_score_codex":0.000015181748,"about_ca_topic_score_gemma":0.00000563906,"teacher_disagreement_score":0.6815016,"about_ca_system_score_codex":0.00013372487,"about_ca_system_score_gemma":0.00022326387,"threshold_uncertainty_score":0.54428494},"labels":[],"label_agreement":null},{"id":"W4401702501","doi":"10.1093/molbev/msae174","title":"GTRpmix: A Linked General Time-Reversible Model for Profile Mixture Models","year":2024,"lang":"en","type":"article","venue":"Molecular Biology and Evolution","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Division of Environmental Biology; National Science Foundation of Sri Lanka; Division of Mathematical Sciences; National Science Foundation; European Research Council; Natural Sciences and Engineering Research Council of Canada; Australian Research Council; Chan Zuckerberg Initiative; Simons Foundation","keywords":"Biology; Evolutionary biology; Computational biology","score_opus":0.012996730965960223,"score_gpt":0.2782532602500528,"score_spread":0.2652565292840926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401702501","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030891667,0.0038621945,0.99066156,0.0010704667,0.00022461823,0.00030317833,0.000026537553,0.00015276633,0.0006095375],"genre_scores_gemma":[0.2295733,0.000027034932,0.76783,0.00034027023,0.00007747094,0.00007083055,0.000038063423,0.00001204623,0.002030967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989417,0.000091220696,0.00013648569,0.0004987317,0.00005505732,0.0002767739],"domain_scores_gemma":[0.9995857,0.000029916386,0.000024907216,0.00023637227,0.00005354771,0.000069550835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003232034,0.00014622792,0.00015666433,0.0001065041,0.00011589226,0.000057323807,0.000217663,0.00025993903,0.0000027721667],"category_scores_gemma":[0.000013719938,0.00012458868,0.000097437725,0.00016181044,0.000054410943,0.0002138131,0.00010889236,0.00013428931,0.000010729418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000120009845,0.0000143825,0.0000029809444,0.000036318997,0.000033344964,0.0000043282303,0.00013783545,0.0014286378,0.08829515,0.89577556,0.0023574892,0.01190198],"study_design_scores_gemma":[0.00010158181,0.00004543034,0.0000044209514,0.000010719603,0.000012044499,0.000011150571,3.5363033e-7,0.58178157,0.0009046139,0.41675946,0.00027419624,0.00009446837],"about_ca_topic_score_codex":0.00000705027,"about_ca_topic_score_gemma":9.188655e-7,"teacher_disagreement_score":0.5803529,"about_ca_system_score_codex":0.000035051682,"about_ca_system_score_gemma":0.00009848946,"threshold_uncertainty_score":0.5080579},"labels":[],"label_agreement":null},{"id":"W4401959276","doi":"10.1177/09622802241259175","title":"Unsupervised Liu-type shrinkage estimators for mixture of regression models","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multicollinearity; Covariate; Estimator; Regression; Expectation–maximization algorithm; Computer science; Statistics; Shrinkage estimator; Regression analysis; Lasso (programming language); Artificial intelligence; Mathematics; Econometrics; Maximum likelihood","score_opus":0.13749339727712664,"score_gpt":0.5495093220074783,"score_spread":0.41201592473035165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401959276","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007070497,0.00223913,0.99112004,0.0023768402,0.0007134517,0.00052246277,0.000028923887,0.000090042624,0.0028383804],"genre_scores_gemma":[0.006810132,0.00028327238,0.9922533,0.0001362569,0.00012153777,0.00009467773,0.0000078928415,0.00003290564,0.00025999756],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99178594,0.0037373023,0.000715398,0.0009170252,0.0019622252,0.00088211923],"domain_scores_gemma":[0.9734642,0.024731081,0.000034952544,0.00072789454,0.00039694586,0.0006449499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02265529,0.0002219286,0.0005714008,0.00055594597,0.00010517677,0.00013505615,0.0015098349,0.00043800735,0.00026618293],"category_scores_gemma":[0.021166723,0.00015663788,0.00010322056,0.0018795414,0.0005437476,0.00024667534,0.00061663514,0.001567041,0.000009014393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032380212,0.000049572394,0.000003558697,0.00032645205,0.000009557574,0.00011048401,0.0002452309,0.0000046902937,0.0004758445,0.49359712,0.001553676,0.5035914],"study_design_scores_gemma":[0.00018633931,0.00016260747,0.00002364367,0.00042111095,0.0000038625626,0.000005530403,0.0000092142545,0.49515936,0.00096358743,0.50105286,0.001920055,0.00009183347],"about_ca_topic_score_codex":0.000045275297,"about_ca_topic_score_gemma":0.0000049631158,"teacher_disagreement_score":0.50349957,"about_ca_system_score_codex":0.00008643335,"about_ca_system_score_gemma":0.0009788347,"threshold_uncertainty_score":0.9870784},"labels":[],"label_agreement":null},{"id":"W4402053673","doi":"10.4064/aa231027-17-5","title":"The Mahler measure of a multivariate polynomial family with non-linear degree","year":2024,"lang":"en","type":"article","venue":"Acta Arithmetica","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Degree (music); Multivariate statistics; Measure (data warehouse); Polynomial; Pure mathematics; Discrete mathematics; Statistics; Mathematical analysis","score_opus":0.028808570452400154,"score_gpt":0.27589607275222433,"score_spread":0.24708750229982418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402053673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015673499,0.00052764616,0.9860255,0.0044310074,0.00044155397,0.00019708005,0.00000418708,0.0000961076,0.0067095337],"genre_scores_gemma":[0.48328516,0.00002233565,0.51571137,0.00015191738,0.00010421583,0.000013690513,4.293032e-7,0.000017195614,0.0006936513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985559,0.00012373779,0.00023613265,0.0004016961,0.00035689014,0.00032566686],"domain_scores_gemma":[0.99865395,0.00038185602,0.000054800865,0.00070166105,0.000109089284,0.000098661374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007389352,0.00017892696,0.00021028414,0.00007667048,0.00013264801,0.00020165408,0.00085748004,0.000086526255,0.000003603108],"category_scores_gemma":[0.00005952345,0.000098810066,0.00009449855,0.0004419567,0.00009611582,0.00021991892,0.00020404316,0.00028132563,0.00001463412],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092823,0.000102768616,0.000022054825,0.00006614931,0.00027878163,0.00009389181,0.0015119256,0.000011975064,0.0290689,0.11088429,0.0060791746,0.85178727],"study_design_scores_gemma":[0.0017418043,0.0008049884,0.0041811545,0.0005285163,0.00020671131,0.00017871878,0.000046050136,0.80949986,0.017559446,0.018029548,0.14623652,0.0009867088],"about_ca_topic_score_codex":0.000094674404,"about_ca_topic_score_gemma":0.000017654986,"teacher_disagreement_score":0.8508006,"about_ca_system_score_codex":0.000033219232,"about_ca_system_score_gemma":0.00020949515,"threshold_uncertainty_score":0.40293574},"labels":[],"label_agreement":null},{"id":"W4402276288","doi":"10.1080/03610918.2024.2394571","title":"Approximation of the lognormal distribution as a solution to the sum of lognormal variates","year":2024,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Log-normal distribution; Mathematics; Statistics; Distribution (mathematics); Applied mathematics; Mathematical analysis","score_opus":0.07658869868298761,"score_gpt":0.400739136454926,"score_spread":0.32415043777193836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402276288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003484635,0.0003196681,0.9937113,0.0016482557,0.00014395408,0.0003869278,0.00008480916,0.000030333214,0.00019011008],"genre_scores_gemma":[0.7663726,0.000030654614,0.23340751,0.000050758208,0.000009891445,0.000017247388,0.00009275237,0.0000041798553,0.000014418393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865746,0.00040016553,0.00045277836,0.00016565928,0.00021878435,0.00010513828],"domain_scores_gemma":[0.998059,0.00094634265,0.00015760351,0.0005661482,0.0002442694,0.000026654887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085363496,0.000091017944,0.000120908764,0.00010406321,0.00018181128,0.000091140784,0.00053981517,0.000059133912,0.0000016935129],"category_scores_gemma":[0.0002343279,0.00006650872,0.0000318704,0.0007561758,0.000113558024,0.00025539813,0.0003388308,0.00016163832,0.0000017238058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006299454,0.000044930788,0.00016913272,0.000043291933,0.000009065869,1.16554254e-7,0.0019904007,0.14251545,0.00008054908,0.72249866,0.00013194572,0.13251019],"study_design_scores_gemma":[0.00011100585,0.000034648812,0.009759717,0.00006516831,0.000014614003,0.000002495822,0.000030139297,0.88283515,0.00008828703,0.1065435,0.00045365418,0.00006163049],"about_ca_topic_score_codex":0.000096377466,"about_ca_topic_score_gemma":0.000056787365,"teacher_disagreement_score":0.76288795,"about_ca_system_score_codex":0.000045017016,"about_ca_system_score_gemma":0.000091066286,"threshold_uncertainty_score":0.2712147},"labels":[],"label_agreement":null},{"id":"W4402517390","doi":"10.1007/s00209-024-03548-y","title":"Modified Macdonald polynomials and the multispecies zero range process: II","year":2024,"lang":"en","type":"article","venue":"Mathematische Zeitschrift","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Zero (linguistics); Range (aeronautics); Process (computing); Macdonald polynomials; Pure mathematics; Orthogonal polynomials; Difference polynomials; Linguistics","score_opus":0.0172498833338723,"score_gpt":0.2744955872880872,"score_spread":0.2572457039542149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402517390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022034412,0.008576726,0.9455825,0.0067411256,0.00032507544,0.00048679547,0.000009113903,0.00036561576,0.035709623],"genre_scores_gemma":[0.7391957,0.00021657888,0.25541165,0.0007116127,0.00018678373,0.00015531697,0.000001302599,0.0000364795,0.0040845643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981973,0.00018517437,0.00036866864,0.0005489132,0.0003470208,0.00035290662],"domain_scores_gemma":[0.9985782,0.00056463253,0.00007897065,0.00061877473,0.00005262121,0.000106837164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014985633,0.00027426492,0.00039912763,0.00010857626,0.00034492102,0.00061622675,0.00082098844,0.00011588994,0.000039694605],"category_scores_gemma":[0.0001406678,0.0001569698,0.000132618,0.0003468005,0.00020929424,0.0005719714,0.00043936132,0.00030372132,0.000054169966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011670682,0.000022014236,0.0000018235494,0.00017875222,0.00004869557,0.000014778735,0.0059047574,0.000004234375,0.00030759105,0.94274807,0.0033613718,0.047396228],"study_design_scores_gemma":[0.0028603473,0.00010497151,0.00012400982,0.00068753265,0.00014196147,0.00045925713,0.00009725505,0.38544637,0.004657297,0.5233741,0.08108548,0.0009614472],"about_ca_topic_score_codex":0.00001925337,"about_ca_topic_score_gemma":0.0000032085015,"teacher_disagreement_score":0.73699224,"about_ca_system_score_codex":0.0000029807825,"about_ca_system_score_gemma":0.00006442314,"threshold_uncertainty_score":0.6401043},"labels":[],"label_agreement":null},{"id":"W4402556636","doi":"10.1111/jtsa.12775","title":"Mixing properties of non‐stationary multi‐variate count processes","year":2024,"lang":"en","type":"article","venue":"Journal of Time Series Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Mathematics; Mixing (physics); Random variate; Statistical physics; Applied mathematics; Statistics; Random variable","score_opus":0.014682092442291926,"score_gpt":0.2599298487632676,"score_spread":0.24524775632097565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402556636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006132083,0.0038016047,0.98880625,0.00090545893,0.00010284413,0.000039830924,0.000003931018,0.000019079222,0.0001889416],"genre_scores_gemma":[0.29080892,0.00035941988,0.70699024,0.000056279703,0.00007920653,0.0000018685998,9.233049e-7,0.000009632697,0.0016935079],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874216,0.00007748776,0.0005382077,0.00016292377,0.00034698175,0.0001322359],"domain_scores_gemma":[0.9988151,0.00006187956,0.00030618903,0.00019070387,0.0005649019,0.00006117957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007382554,0.00011606155,0.0004073364,0.00047024866,0.00006181136,0.00019576952,0.0004357185,0.00004203365,0.00003916934],"category_scores_gemma":[0.00008381155,0.000078232006,0.00027548664,0.0015614984,0.000045403096,0.0011838347,0.00007484981,0.00012780893,0.0000057530424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007152421,0.0014444306,0.0027657058,0.008089135,0.041834705,0.0015173316,0.06227465,0.07659216,0.49043798,0.029551577,0.0067965216,0.27798054],"study_design_scores_gemma":[0.00037448638,0.00041387163,0.0011875724,0.0008367639,0.002626648,0.00023831669,0.00025605652,0.9274271,0.05520948,0.0064087394,0.00454279,0.0004781744],"about_ca_topic_score_codex":0.000020529862,"about_ca_topic_score_gemma":0.000006552201,"teacher_disagreement_score":0.85083497,"about_ca_system_score_codex":0.000029937999,"about_ca_system_score_gemma":0.00029255307,"threshold_uncertainty_score":0.31902087},"labels":[],"label_agreement":null},{"id":"W4402632890","doi":"10.1007/s11222-024-10462-0","title":"Hidden Markov models for multivariate panel data","year":2024,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Multivariate statistics; Hidden Markov model; Multivariate analysis; Computer science; Markov model; Econometrics; Mathematics; Markov chain; Statistics; Artificial intelligence","score_opus":0.08365168828125646,"score_gpt":0.3399508047177183,"score_spread":0.25629911643646186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402632890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004617745,0.00082933006,0.99713224,0.00029108895,0.00058337115,0.00015683477,0.00034434118,0.00012778924,0.00048884813],"genre_scores_gemma":[0.072984725,0.000029848288,0.9264732,0.00013857943,0.00015537416,0.0000027574672,0.000043428747,0.000014302882,0.00015775791],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882823,0.000049253347,0.00020102209,0.0005559088,0.00011298888,0.00025258295],"domain_scores_gemma":[0.9987513,0.0006030866,0.00003787529,0.0004785442,0.000049298247,0.000079889745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006612097,0.00012600284,0.00015346638,0.000051127165,0.00015282031,0.00048107366,0.0005896172,0.00004124638,0.0000014667024],"category_scores_gemma":[0.000047798087,0.000110740824,0.000019276571,0.00010949592,0.000024652572,0.0002492248,0.00068192167,0.00010883885,0.0000019111476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.753961e-7,0.0000040012087,5.373756e-7,0.000053844404,0.000012307584,0.000010803261,0.00024200864,0.00001853326,0.000023153842,0.46974215,0.0018982972,0.5279934],"study_design_scores_gemma":[0.00008456949,0.000017204813,0.000018856097,0.00003922757,0.000010423404,0.000012532622,0.000004330113,0.6552806,0.0000063671887,0.34316638,0.0012590699,0.000100442376],"about_ca_topic_score_codex":0.000030918363,"about_ca_topic_score_gemma":0.0000023989944,"teacher_disagreement_score":0.65526205,"about_ca_system_score_codex":0.000009391672,"about_ca_system_score_gemma":0.00006178039,"threshold_uncertainty_score":0.46390042},"labels":[],"label_agreement":null},{"id":"W4402640531","doi":"10.1007/s10044-024-01341-5","title":"Hidden Markov models with multivariate bounded asymmetric student’s t-mixture model emissions","year":2024,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Bounded function; Hidden Markov model; Mixture model; Markov chain; Multivariate analysis; Mathematics; Pattern recognition (psychology); Markov model; Artificial intelligence; Computer science; Statistics; Econometrics; Mathematical analysis","score_opus":0.017264055253476147,"score_gpt":0.29756395414912024,"score_spread":0.2802998988956441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402640531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045223007,0.0008572061,0.9940324,0.001336142,0.000018335348,0.00030325065,0.000029638739,0.00019686604,0.0027739648],"genre_scores_gemma":[0.6385155,0.00013207736,0.359714,0.00028324334,0.000050005507,0.00024513877,0.00002179415,0.00001592195,0.0010223298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982677,0.00007014927,0.0002738278,0.0008053082,0.00031349127,0.00026952114],"domain_scores_gemma":[0.99875057,0.00010512922,0.00007075034,0.00077385653,0.00008462168,0.00021508276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003073285,0.00022708728,0.00031514405,0.0005669724,0.0002712531,0.0006471955,0.0005819217,0.00008775643,0.000010703214],"category_scores_gemma":[0.0000029005462,0.00016301771,0.00017043829,0.0028133844,0.00004040934,0.0003482147,0.00021223658,0.00021896046,0.000010010824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018643159,0.00013585675,0.00056248566,0.000036669422,0.000920927,0.000007877168,0.0007413796,0.0013819288,0.00023261551,0.20336021,0.00028770984,0.79233044],"study_design_scores_gemma":[0.00012088989,0.000011957132,0.0010961074,0.000018419156,0.0005953154,0.000005906628,0.000013719886,0.9470674,0.000068093716,0.050221194,0.0005466352,0.00023436258],"about_ca_topic_score_codex":0.00009444694,"about_ca_topic_score_gemma":0.000053782005,"teacher_disagreement_score":0.94568545,"about_ca_system_score_codex":0.000033460703,"about_ca_system_score_gemma":0.00006526403,"threshold_uncertainty_score":0.66476697},"labels":[],"label_agreement":null},{"id":"W4402782664","doi":"10.1007/978-3-031-71602-7_5","title":"Robust Clustering with McDonald’s Beta-Liouville Mixture Models for Proportional Data","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Cluster analysis; BETA (programming language); Artificial intelligence; Programming language","score_opus":0.06588708816020786,"score_gpt":0.2805819087748913,"score_spread":0.21469482061468345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402782664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000110647,0.0015837713,0.9877759,0.0028317804,0.0016851499,0.0009974322,0.00011838057,0.00025031454,0.004756125],"genre_scores_gemma":[0.0019447668,0.00005477863,0.9938326,0.0010566574,0.0008919921,0.000039740582,0.00007425791,0.00008582648,0.002019402],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939955,0.000029585193,0.0006514929,0.00319003,0.0012611066,0.0008723132],"domain_scores_gemma":[0.99574757,0.00037280386,0.00029709216,0.0029673486,0.00036418473,0.00025101833],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016110742,0.00078847416,0.00078330515,0.0007359642,0.00032983394,0.0010121706,0.005879944,0.0004423201,0.000013705376],"category_scores_gemma":[0.000024919384,0.00059370976,0.00016351102,0.00062441546,0.00055701955,0.0014481941,0.0034362937,0.0010557931,0.000011391935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029815485,0.000045864366,0.0000017114993,0.00032136156,0.00007519617,0.00016392743,0.00046117904,0.24100517,0.000035559082,0.34264624,0.0005601296,0.41465387],"study_design_scores_gemma":[0.00018531865,0.00013568993,9.3437774e-7,0.00047208008,0.000027313217,0.00015711533,6.638216e-8,0.6377426,0.00008395129,0.35757795,0.0030880878,0.00052890246],"about_ca_topic_score_codex":0.000014055308,"about_ca_topic_score_gemma":0.00015696003,"teacher_disagreement_score":0.41412497,"about_ca_system_score_codex":0.00022372224,"about_ca_system_score_gemma":0.0010688168,"threshold_uncertainty_score":0.99965143},"labels":[],"label_agreement":null},{"id":"W4403091085","doi":"10.1051/0004-6361/202451358","title":"Alcock–Paczyński effect on void-finding","year":2024,"lang":"en","type":"article","venue":"Astronomy and Astrophysics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Perimeter Institute; University of Waterloo","funders":"Science and Technology Facilities Council; Innovation, Science and Economic Development Canada; Institut Périmètre de physique théorique; Norges Forskningsråd; Government of Canada; Ministry of Colleges and Universities","keywords":"Physics; Void (composites); Astrophysics; Galaxy; The Void; Correlation; Astronomy; Statistical physics; Geometry","score_opus":0.009053660930889952,"score_gpt":0.25057567187878776,"score_spread":0.24152201094789782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403091085","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029746465,0.00018406789,0.96762115,0.0002821241,0.00042340154,0.00010708029,0.000003822841,0.00014931189,0.0014825552],"genre_scores_gemma":[0.47026694,0.0000032548046,0.5291149,0.00008119308,0.00030473684,0.000012250329,0.0000026479768,0.000013415031,0.00020067187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893767,0.00007949852,0.00011585667,0.00043412446,0.00014484345,0.0002880154],"domain_scores_gemma":[0.9994234,0.00013775838,0.000026190013,0.0002977173,0.000010087057,0.00010483669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021364045,0.00018945678,0.0001769203,0.00006990103,0.00012403095,0.00042137998,0.00031922458,0.00004161831,0.0000036456333],"category_scores_gemma":[0.0000038091684,0.0001544136,0.000093107454,0.00018628797,0.000032225384,0.00027291794,0.00015057472,0.00023919604,0.000055452543],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031090456,0.000009651877,0.000020681446,0.000013846957,0.000019692598,0.000008493458,0.00007548092,0.00001780455,0.0010338845,0.15729587,0.00013540938,0.8413661],"study_design_scores_gemma":[0.002812068,0.007896796,0.0044947923,0.0016231656,0.0002564566,0.00012908904,0.000093035516,0.104703285,0.119580194,0.13930938,0.6160289,0.00307286],"about_ca_topic_score_codex":0.0000051451934,"about_ca_topic_score_gemma":1.800529e-7,"teacher_disagreement_score":0.83829325,"about_ca_system_score_codex":0.00002109749,"about_ca_system_score_gemma":0.000033602428,"threshold_uncertainty_score":0.6296804},"labels":[],"label_agreement":null},{"id":"W4403162617","doi":"10.1093/imaiai/iaae023","title":"Statistical inference for sketching algorithms","year":2024,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Sketch; Inference; Computer science; Algorithm; Set (abstract data type); Data set; Sampling (signal processing); Statistical inference; Mathematics; Statistics; Artificial intelligence","score_opus":0.019625975934582,"score_gpt":0.32757539395024937,"score_spread":0.3079494180156674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403162617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000931181,0.0001880639,0.9955833,0.0020407704,0.0006572054,0.00007892795,0.000007897384,0.00001632401,0.0004963221],"genre_scores_gemma":[0.45379207,0.000095982505,0.54526156,0.0007456988,0.00007012228,0.0000030405984,5.779596e-7,0.0000023168268,0.000028640403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922293,0.000043430093,0.00037718966,0.000053728036,0.00018638266,0.00011633763],"domain_scores_gemma":[0.99908453,0.00040452028,0.0001487779,0.00012218826,0.00017406259,0.00006589973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073635334,0.00007455929,0.0001127511,0.00009758327,0.00009352503,0.0006111894,0.00039675197,0.000036273977,0.000006425302],"category_scores_gemma":[0.00041492863,0.000042836407,0.000057128203,0.00013984814,0.000036618374,0.002643498,0.000096150776,0.00019729312,0.0000041101825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031502482,0.0000030027145,0.000022531178,0.00003049931,0.0000086060545,7.3326913e-7,0.0010589954,0.000015893833,0.000030044754,0.3730684,0.00059320254,0.6251649],"study_design_scores_gemma":[0.00032886036,0.00016476886,0.0012915242,0.00027220833,0.000019184568,0.00020045348,0.000049614806,0.56181914,0.0005041946,0.39610875,0.039096266,0.0001450375],"about_ca_topic_score_codex":0.0000034101106,"about_ca_topic_score_gemma":4.590918e-7,"teacher_disagreement_score":0.6250199,"about_ca_system_score_codex":0.000018908471,"about_ca_system_score_gemma":0.00020141616,"threshold_uncertainty_score":0.5893714},"labels":[],"label_agreement":null},{"id":"W4403484320","doi":"10.3390/math12203260","title":"Robust Classification via Finite Mixtures of Matrix Variate Skew-t Distributions","year":2024,"lang":"en","type":"article","venue":"Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random variate; Skew; Mathematics; Matrix (chemical analysis); Applied mathematics; Computer science; Statistics; Materials science; Random variable; Composite material","score_opus":0.04507021192554705,"score_gpt":0.30044007698996317,"score_spread":0.2553698650644161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403484320","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019594931,0.00039090772,0.9960322,0.00068228575,0.00030966412,0.0001311377,0.00002928749,0.00018245258,0.0020461164],"genre_scores_gemma":[0.097768195,0.000023305423,0.90160877,0.000020607855,0.000052815085,0.00001427144,0.000009664054,0.000011375447,0.00049101224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999004,0.00005648301,0.00033954918,0.00023516564,0.00019583358,0.00016893243],"domain_scores_gemma":[0.99890006,0.00032792529,0.000092924514,0.00055160664,0.00007161884,0.000055851015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048317772,0.00012314963,0.00018507312,0.000094597846,0.00006380468,0.00014215997,0.00045328017,0.00008728019,0.000023923636],"category_scores_gemma":[0.00008391045,0.00009931092,0.00009901401,0.0004483483,0.000038389717,0.00018591358,0.00010332397,0.00013344642,0.000054152788],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.438239e-7,0.00008579371,0.0000015237237,0.00022783557,0.00002240856,0.000004248639,0.00077165605,0.00003444271,0.0034503946,0.9822909,0.000921108,0.012189224],"study_design_scores_gemma":[0.000035124012,0.00001719929,0.000025065478,0.00007193066,0.000021477274,0.000011072378,0.0000029876521,0.5104001,0.0023364222,0.48605692,0.00093874556,0.00008294436],"about_ca_topic_score_codex":0.000003977489,"about_ca_topic_score_gemma":7.5254815e-7,"teacher_disagreement_score":0.51036566,"about_ca_system_score_codex":0.00002579744,"about_ca_system_score_gemma":0.00005257212,"threshold_uncertainty_score":0.4049782},"labels":[],"label_agreement":null},{"id":"W4403485715","doi":"10.1080/00949655.2024.2409381","title":"Are information criteria good enough to choose the right number of regimes in hidden Markov models?","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Hidden Markov model; Econometrics; Markov chain; Markov model; Statistics; Artificial intelligence; Computer science","score_opus":0.020005469410142532,"score_gpt":0.3407577964266284,"score_spread":0.32075232701648587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403485715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010438709,0.00007413642,0.98689413,0.0017080631,0.00021023209,0.00011234707,0.000009277098,0.000011138345,0.0005419497],"genre_scores_gemma":[0.6242655,0.000005905573,0.3755206,0.00016276055,0.00002937974,7.502097e-7,0.000001789388,0.0000024458257,0.0000109122675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988307,0.00017719677,0.00053302565,0.00009384319,0.000273346,0.00009189644],"domain_scores_gemma":[0.99871975,0.0006911611,0.00022275603,0.0000749873,0.00022383565,0.00006752049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006955631,0.00008127406,0.00017631608,0.00015935549,0.000041227955,0.0002178532,0.00012599796,0.00004437419,0.000013107827],"category_scores_gemma":[0.00013768338,0.000054984255,0.000032104683,0.00028574097,0.000023062707,0.0011509456,0.000039744897,0.00014550716,0.0000033194485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055440003,0.000032060296,0.00006744374,0.00009454619,0.000017640932,0.00001954771,0.0034683784,0.08748969,0.000011645906,0.43281356,0.00069733715,0.47523272],"study_design_scores_gemma":[0.0001816101,0.000037101086,0.0068871104,0.0000902244,0.000008408063,0.000023099226,0.000030046516,0.7825267,0.000008325489,0.20983283,0.00032357505,0.00005101572],"about_ca_topic_score_codex":0.0000059650797,"about_ca_topic_score_gemma":0.0000011650231,"teacher_disagreement_score":0.69503695,"about_ca_system_score_codex":0.00003128246,"about_ca_system_score_gemma":0.0000429023,"threshold_uncertainty_score":0.22421928},"labels":[],"label_agreement":null},{"id":"W4403535217","doi":"10.1109/codit62066.2024.10708173","title":"A Nonparametric Bayesian Framework for Multivariate Libby-Novick Beta Mixture Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multivariate statistics; Nonparametric statistics; Bayesian probability; Computer science; Artificial intelligence; Statistics; Mathematics; Machine learning","score_opus":0.02982578544900683,"score_gpt":0.31207097872110756,"score_spread":0.28224519327210074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403535217","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002481653,0.0017510938,0.9836771,0.0048170523,0.0014205705,0.0006449076,0.000017861243,0.000915589,0.0067310315],"genre_scores_gemma":[0.08037966,0.000034218017,0.91530895,0.0014115882,0.00033461474,0.00011519946,0.000004395021,0.000049698014,0.0023616883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974078,0.00011875338,0.0003996651,0.0010807784,0.00033276543,0.000660269],"domain_scores_gemma":[0.99745244,0.0010871079,0.00006105381,0.0010221669,0.000111372,0.00026588907],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007789761,0.00036013246,0.0003950812,0.00044191116,0.00016057005,0.00084437145,0.0012581273,0.00038555506,0.000044072138],"category_scores_gemma":[0.000107995686,0.0002788662,0.00033426762,0.0017769266,0.000038463946,0.0009809152,0.0002795721,0.00048714358,0.000053118656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005925615,0.000040708106,0.0000013164462,0.00007299718,0.000049393788,0.000015562837,0.00049543194,0.00013366283,0.00009776137,0.80895317,0.0026949954,0.18743908],"study_design_scores_gemma":[0.0001124703,0.00005066057,0.0000050206777,0.00006294591,0.00001716342,0.00001154344,0.0000028639888,0.49460912,0.0005136634,0.4993735,0.0050187837,0.00022229114],"about_ca_topic_score_codex":0.000034597244,"about_ca_topic_score_gemma":0.0000039236343,"teacher_disagreement_score":0.49447545,"about_ca_system_score_codex":0.000055606048,"about_ca_system_score_gemma":0.00016482348,"threshold_uncertainty_score":0.9999663},"labels":[],"label_agreement":null},{"id":"W4404506273","doi":"10.1016/j.jspi.2024.106250","title":"Estimation and group-feature selection in sparse mixture-of-experts with diverging number of parameters","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Feature selection; Group (periodic table); Selection (genetic algorithm); Statistics; Feature (linguistics); Estimation; Pattern recognition (psychology); Combinatorics; Artificial intelligence; Computer science","score_opus":0.017100342885254048,"score_gpt":0.3144785818843017,"score_spread":0.2973782389990477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404506273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13031276,0.0003859232,0.86907214,0.00008171963,0.00004971406,0.00002443747,0.000002566612,0.000004908729,0.00006583362],"genre_scores_gemma":[0.54640406,0.000023688435,0.45354998,0.000011384263,0.00000639652,2.852236e-7,2.890613e-7,0.0000016194944,0.0000023102803],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993678,0.000060555747,0.00021657767,0.00011440373,0.00015118856,0.000089520625],"domain_scores_gemma":[0.99927264,0.00047819587,0.00010719519,0.000036286394,0.000049229016,0.000056477875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003104997,0.00007486736,0.00019335143,0.00010095338,0.00002115882,0.00006212628,0.00006719067,0.00004555384,0.0000015560852],"category_scores_gemma":[0.00011611948,0.00005121656,0.000012248701,0.00016460192,0.00006032468,0.00033440077,0.00002375234,0.00019614893,6.803414e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016339192,0.00008023516,0.04432928,0.0004910635,0.000072288916,0.0002475269,0.005822864,0.0014874892,0.002202963,0.25375366,0.00044171762,0.69090754],"study_design_scores_gemma":[0.00041455386,0.00064757554,0.043306604,0.0020965617,0.00004024642,0.00064232445,0.0000555905,0.8415482,0.00075734407,0.11028813,0.00003548013,0.00016736225],"about_ca_topic_score_codex":0.000018343848,"about_ca_topic_score_gemma":0.0000013790943,"teacher_disagreement_score":0.8400607,"about_ca_system_score_codex":0.000010615067,"about_ca_system_score_gemma":0.00003734449,"threshold_uncertainty_score":0.20885506},"labels":[],"label_agreement":null},{"id":"W4404637508","doi":"10.1214/24-ejs2315","title":"Conditional independence testing for discrete distributions: Beyond χ2- and G-tests","year":2024,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Mathematics; Conditional independence; Econometrics; Independence (probability theory); Statistics; Applied mathematics; Calculus (dental); Mathematical economics","score_opus":0.014699150073164908,"score_gpt":0.30296824841578857,"score_spread":0.28826909834262365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404637508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030819548,0.003749597,0.9947419,0.00062705274,0.00020245294,0.00008108844,0.00020671474,0.0000188584,0.00006411873],"genre_scores_gemma":[0.3237287,0.000105747014,0.6759008,0.000061979415,0.00012633234,0.0000035022565,0.000009565757,0.000006824096,0.000056504432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989185,0.000047840967,0.00029855937,0.00016340028,0.00023999576,0.00033170232],"domain_scores_gemma":[0.99837685,0.001045844,0.00013050524,0.00009149166,0.0002676052,0.00008771731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086578587,0.00010084872,0.00015093814,0.000079575635,0.00011433023,0.0002085235,0.00024283839,0.000044502765,0.0000036677402],"category_scores_gemma":[0.0004384007,0.00008393854,0.00003734854,0.0001838841,0.000053148626,0.00035876763,0.000044566197,0.0003925589,0.0000010392981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004059132,0.000008857046,0.00003384338,0.000031796546,0.000033466917,0.000028493885,0.0000541753,0.000007990895,0.00040993557,0.9279049,0.0014058396,0.070076615],"study_design_scores_gemma":[0.00018663223,0.0004224417,0.00041624857,0.00006428588,0.00003453155,0.0007578248,0.0000038804046,0.042781875,0.00018921756,0.9532135,0.0018292413,0.00010029143],"about_ca_topic_score_codex":0.0000015728386,"about_ca_topic_score_gemma":0.000003915774,"teacher_disagreement_score":0.32342052,"about_ca_system_score_codex":0.00010099606,"about_ca_system_score_gemma":0.00071639573,"threshold_uncertainty_score":0.3422914},"labels":[],"label_agreement":null},{"id":"W4404740406","doi":"10.1109/isncc62547.2024.10759059","title":"Multivariate Bounded Support Kotz Mixture Model with Minimum Message Length Criterion","year":2024,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; Concordia University","funders":"","keywords":"Multivariate statistics; Bounded function; Mathematics; Computer science; Statistics; Algorithm; Mathematical analysis","score_opus":0.018026440326977585,"score_gpt":0.2832877738917502,"score_spread":0.2652613335647726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404740406","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088094146,0.00019138903,0.9680629,0.002947631,0.0003931556,0.00021176286,0.000007861779,0.0006494083,0.026654989],"genre_scores_gemma":[0.20498618,0.000016729018,0.7782246,0.0010282716,0.000077154284,0.000022469794,0.000005173292,0.000029106646,0.015610294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805194,0.00010026479,0.0002548922,0.00079296494,0.00034666384,0.0004532879],"domain_scores_gemma":[0.9989165,0.00007827497,0.000037700804,0.00071232213,0.00007360136,0.00018162286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005282917,0.0002887256,0.00026459462,0.00014538509,0.00012135136,0.00068468816,0.00067310606,0.00014752593,0.0001259692],"category_scores_gemma":[0.0000112964635,0.00019273847,0.000104554565,0.00039085565,0.000052675565,0.00086655567,0.0002068692,0.00029884215,0.000071823095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032027732,0.00009847026,0.0000057343323,0.00012833539,0.00009240899,0.0003386036,0.0034582824,0.0001111547,0.010101181,0.8698341,0.01637983,0.09941983],"study_design_scores_gemma":[0.00030799638,0.00012891603,0.000017302234,0.00006434175,0.00002407554,0.00009088481,0.000009932777,0.9133105,0.0029252612,0.07453695,0.008219725,0.00036407364],"about_ca_topic_score_codex":0.000025484394,"about_ca_topic_score_gemma":0.000013356116,"teacher_disagreement_score":0.91319937,"about_ca_system_score_codex":0.000042882817,"about_ca_system_score_gemma":0.00024719842,"threshold_uncertainty_score":0.78596467},"labels":[],"label_agreement":null},{"id":"W4404740476","doi":"10.1109/isncc62547.2024.10758998","title":"Author Dirichlet Multinomial Allocation Model with Generalized Distribution (ADMAGD)","year":2024,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Latent Dirichlet allocation; Computer science; Mathematics; Applied mathematics; Statistics; Topic model; Artificial intelligence; Mathematical analysis","score_opus":0.02274558528963674,"score_gpt":0.2879128460755806,"score_spread":0.2651672607859439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404740476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023506756,0.0001326471,0.9902015,0.0047113528,0.0002605104,0.00016646224,0.000009873858,0.00048499624,0.0016820126],"genre_scores_gemma":[0.2929984,0.0000052679975,0.70183057,0.00020489175,0.00008253656,0.00002635092,0.000027406408,0.000009163161,0.004815425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888873,0.00007027195,0.00016699373,0.00044561527,0.00020309098,0.00022529675],"domain_scores_gemma":[0.99940586,0.000037946804,0.000026300622,0.0003653151,0.00006623308,0.000098331955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036203113,0.00014223217,0.00012544672,0.000050597388,0.000082525665,0.00030776655,0.00031632537,0.00007254077,0.000011116144],"category_scores_gemma":[0.000013242253,0.00009751666,0.000054041535,0.00032156555,0.000026014328,0.0004953332,0.00008242275,0.00011895602,0.000028466955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009770777,0.000023936307,0.0000052560313,0.000015864402,0.000015573329,0.000008769989,0.00022470587,0.001273203,0.00216375,0.8790962,0.01303632,0.10412662],"study_design_scores_gemma":[0.00019445042,0.000032021762,0.000044561933,0.00001597483,0.000011768232,0.000014448974,0.0000015121853,0.9671759,0.0029745677,0.023551354,0.005820263,0.00016314634],"about_ca_topic_score_codex":0.00003987462,"about_ca_topic_score_gemma":0.000008962992,"teacher_disagreement_score":0.96590275,"about_ca_system_score_codex":0.000057139016,"about_ca_system_score_gemma":0.00012582116,"threshold_uncertainty_score":0.3976614},"labels":[],"label_agreement":null},{"id":"W4404761272","doi":"10.1007/s12561-024-09467-0","title":"Generalized Linear Mixed Models with Censored Covariates and Measurement Errors, with Applications in HIV/AIDS Studies","year":2024,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Biostatistics; Econometrics; Human immunodeficiency virus (HIV); Statistics; Generalized linear model; Medicine; Generalized linear mixed model; Computer science; Mathematics; Epidemiology; Virology; Internal medicine","score_opus":0.05359051196322061,"score_gpt":0.3201356550565645,"score_spread":0.2665451430933439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404761272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016188,0.0017038661,0.9955026,0.00045550466,0.000099113684,0.00039554262,0.000049705846,0.00006689442,0.000107999826],"genre_scores_gemma":[0.15538684,0.0002775884,0.8441247,0.00005319139,0.000011908385,0.00009579066,0.0000024961748,0.00000865574,0.00003885065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982922,0.00013444226,0.0002469883,0.00061870454,0.00043289643,0.000274732],"domain_scores_gemma":[0.99929917,0.00018370508,0.00005420797,0.00025710385,0.00013668195,0.00006913508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011968648,0.00017107984,0.00025507296,0.0002183316,0.00010675684,0.00030246456,0.00057092455,0.000034183922,6.0253416e-7],"category_scores_gemma":[0.000044245917,0.00010615979,0.000008924579,0.0010892616,0.00034793562,0.0003949559,0.00018346519,0.00012163342,4.753629e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008159582,0.000034653116,0.00034323757,0.000044110824,0.000014270144,0.000016487284,0.0019574317,0.0005421229,0.00014365089,0.99113315,0.00009074636,0.005671966],"study_design_scores_gemma":[0.0004451474,0.00021318717,0.000592482,0.00020419955,0.000016024334,0.000009273945,0.0005144547,0.43415394,0.00041120406,0.5628208,0.00034518194,0.00027414758],"about_ca_topic_score_codex":0.00009489943,"about_ca_topic_score_gemma":0.00083181565,"teacher_disagreement_score":0.4336118,"about_ca_system_score_codex":0.000062536055,"about_ca_system_score_gemma":0.00021974486,"threshold_uncertainty_score":0.43290704},"labels":[],"label_agreement":null},{"id":"W4404934856","doi":"10.1017/asb.2024.34","title":"An Augmented Variable Dirichlet Process mixture model for the analysis of dependent lifetimes","year":2024,"lang":"en","type":"article","venue":"Astin Bulletin","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Variable (mathematics); Dirichlet process; Dirichlet distribution; Mathematics; Econometrics; Process (computing); Statistics; Applied mathematics; Computer science; Mathematical analysis; Bayesian probability","score_opus":0.014105366687493277,"score_gpt":0.29770988682195204,"score_spread":0.28360452013445875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404934856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037480964,0.001111641,0.9941718,0.0032182003,0.00016137265,0.000292126,0.000047681442,0.00012910533,0.0004932645],"genre_scores_gemma":[0.31496912,0.000020376776,0.6824455,0.00049687404,0.00007806322,0.00011836904,0.000014784414,0.000019071482,0.001837843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985372,0.00009931093,0.00029077462,0.0005111425,0.00028923101,0.0002723607],"domain_scores_gemma":[0.99855906,0.00049989583,0.00008005886,0.0006286027,0.00015201712,0.00008036992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010865141,0.00016993689,0.00028156795,0.00017714675,0.000118803015,0.00019683341,0.0009823074,0.00008555651,0.000083970604],"category_scores_gemma":[0.00008218842,0.00011106693,0.00015839087,0.000984133,0.000036956706,0.00009570773,0.00010034847,0.00014961384,0.0000056620734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009700208,0.0004202364,0.00012849763,0.00048324064,0.0030013467,0.000016555905,0.0057279253,0.4026946,0.004926714,0.31685305,0.040792,0.22485882],"study_design_scores_gemma":[0.000109271634,0.000041230225,0.000048987982,0.0000324513,0.00048967457,0.0000025045506,0.00001550028,0.98427093,0.00078443665,0.009461863,0.004605021,0.00013809933],"about_ca_topic_score_codex":0.000029167406,"about_ca_topic_score_gemma":0.0000053285944,"teacher_disagreement_score":0.58157635,"about_ca_system_score_codex":0.000016273676,"about_ca_system_score_gemma":0.00010900046,"threshold_uncertainty_score":0.4529178},"labels":[],"label_agreement":null},{"id":"W4404987082","doi":"10.1109/iccv51701.2025.00147","title":"Geometry Distributions","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Geometry; Geology; Mathematics","score_opus":0.02126051665113219,"score_gpt":0.30539152681041737,"score_spread":0.28413101015928516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404987082","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014996688,0.00032135725,0.91825354,0.0020511898,0.0012578802,0.00013200665,0.000058255366,0.00030072514,0.07761002],"genre_scores_gemma":[0.0025181419,0.00005004953,0.97802585,0.00048451926,0.000073823816,0.000029075774,0.000023321794,0.0000026272035,0.01879261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988469,0.00007837219,0.00019074685,0.00053344405,0.00013945802,0.00021111552],"domain_scores_gemma":[0.99846274,0.00007852114,0.00005622696,0.0012412507,0.000082845625,0.000078429795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029560746,0.00016812237,0.00022162318,0.0001460887,0.00007468353,0.00020107659,0.0014795514,0.00024212769,0.000044516026],"category_scores_gemma":[0.000047735408,0.00014497872,0.00015585443,0.00032519537,0.000021321457,0.000073640964,0.0030714232,0.00047583863,0.000022630142],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.7628345e-7,0.000017322069,0.0000089160785,0.000026339507,0.0000146431485,0.0000023087416,0.000016391708,0.0000050989543,0.0000037044347,0.8509374,0.011065643,0.137902],"study_design_scores_gemma":[0.000067089495,0.000006608414,0.00023745901,0.00006668243,0.000015149708,0.000003005018,5.435099e-7,0.024177412,0.0007675985,0.936656,0.03772602,0.00027641872],"about_ca_topic_score_codex":0.000040812327,"about_ca_topic_score_gemma":0.0000032055118,"teacher_disagreement_score":0.13762559,"about_ca_system_score_codex":0.000047679736,"about_ca_system_score_gemma":0.00025020217,"threshold_uncertainty_score":0.5912061},"labels":[],"label_agreement":null},{"id":"W4405355380","doi":"10.48550/arxiv.2412.09539","title":"Bayesian nonparametric mixtures of Archimedean copulas","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Nonparametric statistics; Bayesian probability; Econometrics; Mathematics; Economics; Statistics","score_opus":0.05360054579708571,"score_gpt":0.21413598654326457,"score_spread":0.16053544074617887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405355380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018596618,0.0006589391,0.9661243,0.00014777153,0.0011552153,0.00031097772,0.00002946264,0.00026065382,0.012716046],"genre_scores_gemma":[0.87637436,0.00016018027,0.121298656,0.000078488374,0.00009609975,9.4189e-7,0.000007408769,0.000029890334,0.0019539916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730337,0.0003079412,0.00034829712,0.0014341645,0.00016620502,0.0004400186],"domain_scores_gemma":[0.997312,0.0002219499,0.00028646394,0.0017884036,0.000137361,0.00025381523],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051114766,0.0004360839,0.0006211993,0.00094866095,0.00007822621,0.00013384546,0.0025350282,0.0004210139,0.000026993925],"category_scores_gemma":[0.00006098841,0.00044995392,0.00048103122,0.0016352411,0.00016780916,0.00013801467,0.0035592588,0.0010953835,0.000054020536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002360064,0.00012524634,0.00021371759,0.0005129115,0.00022939405,0.0005798636,0.0004019926,0.0100161955,0.00017454982,0.9684306,0.0013326633,0.017959302],"study_design_scores_gemma":[0.00017043878,0.00005498222,0.00009576895,0.0001812198,0.00010610829,0.000009392401,0.000006624085,0.3459333,0.001112857,0.6516838,0.00025777007,0.00038778115],"about_ca_topic_score_codex":0.00018003257,"about_ca_topic_score_gemma":0.000019489396,"teacher_disagreement_score":0.8577777,"about_ca_system_score_codex":0.00011465529,"about_ca_system_score_gemma":0.0003293584,"threshold_uncertainty_score":0.9997952},"labels":[],"label_agreement":null},{"id":"W4405575790","doi":"10.1080/00207160.2024.2443498","title":"Linear anchored Gaussian mixture model for location and width computations of objects in thick line shape","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computation; Mathematics; Gaussian; Line (geometry); Line width; Line segment; Algorithm; Geometry; Mathematical analysis; Physics; Optics","score_opus":0.02885945332940998,"score_gpt":0.32735267276142715,"score_spread":0.2984932194320172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405575790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034611705,0.00043889202,0.99341834,0.0018055177,0.0006574076,0.00014437188,0.000008619065,0.000020182228,0.00004550511],"genre_scores_gemma":[0.34569216,0.000045354645,0.6539015,0.000121860896,0.0002070327,0.0000021285075,0.0000021284668,0.000008580101,0.000019247445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986493,0.000039470444,0.0006835202,0.00016227558,0.00035283135,0.00011262989],"domain_scores_gemma":[0.99851155,0.0003794117,0.00029257828,0.00013404603,0.0006213754,0.0000610143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066416955,0.00012710884,0.00027060136,0.000386718,0.00002018414,0.00014327237,0.00057244045,0.00007452739,0.0000013633181],"category_scores_gemma":[0.000058068406,0.00010371719,0.0000992508,0.00022014308,0.0000345834,0.00042093807,0.000106303545,0.00019364012,6.359026e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037229165,0.0004368969,0.000023273193,0.00074717205,0.00028793103,0.000064176515,0.01789486,0.0926382,0.00074113713,0.6212336,0.00089014845,0.2650054],"study_design_scores_gemma":[0.00031159012,0.000079582715,0.000045100012,0.0005921074,0.000012781461,0.00012894164,0.000007829898,0.7516733,0.00020605749,0.24683379,0.00003857786,0.00007038126],"about_ca_topic_score_codex":9.660687e-7,"about_ca_topic_score_gemma":0.0000027580477,"teacher_disagreement_score":0.6590351,"about_ca_system_score_codex":0.00004068457,"about_ca_system_score_gemma":0.00017436067,"threshold_uncertainty_score":0.42294642},"labels":[],"label_agreement":null},{"id":"W4405760315","doi":"10.1007/s40314-024-03050-5","title":"EM algorithm for bounded generalized t mixture model with an application to image segmentation","year":2024,"lang":"en","type":"article","venue":"Computational and Applied Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bounded function; Expectation–maximization algorithm; Computer science; Algorithm; Kurtosis; Model selection; Image (mathematics); Mixture model; Maximum likelihood; Artificial intelligence; Pattern recognition (psychology); Mathematical optimization; Mathematics; Statistics","score_opus":0.01650098921130456,"score_gpt":0.2914055464694875,"score_spread":0.27490455725818297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405760315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014396515,0.00004017232,0.99682474,0.0005133385,0.00003229899,0.0007649119,0.000025112322,0.00018068118,0.00017911055],"genre_scores_gemma":[0.0033060606,0.0000020786076,0.99555933,0.0005413482,0.000070088616,0.00033777067,0.0000708973,0.000021281505,0.00009111955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905074,0.0000093542485,0.00019539923,0.00039238058,0.00020291968,0.0001492009],"domain_scores_gemma":[0.9994765,0.0000964572,0.00004714896,0.00017321942,0.00009763528,0.000109036155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022468367,0.0001556039,0.00016056196,0.000081176826,0.00013205319,0.00040485588,0.00018497978,0.000047908194,9.548606e-7],"category_scores_gemma":[0.0000024096294,0.00012256467,0.000028041053,0.00019981811,0.00002179543,0.00022721238,0.00004894579,0.000059941056,0.0000053190693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004406831,0.00005322711,1.754548e-8,0.00009754212,0.00001584058,5.1676267e-7,0.0015555063,0.008209926,0.0019668918,0.6999805,0.00024802558,0.2878676],"study_design_scores_gemma":[0.00016226839,0.000032290656,7.447215e-7,0.000011350749,0.00001145155,0.000008965181,0.000020352736,0.55852085,0.0005822681,0.44047028,0.00007819968,0.00010102014],"about_ca_topic_score_codex":4.616883e-7,"about_ca_topic_score_gemma":7.9777766e-7,"teacher_disagreement_score":0.5503109,"about_ca_system_score_codex":0.000023842398,"about_ca_system_score_gemma":0.00006631047,"threshold_uncertainty_score":0.49980423},"labels":[],"label_agreement":null},{"id":"W4405934663","doi":"10.1002/cjs.11834","title":"Probabilistic weighted Dirichlet process mixture with an application to stochastic volatility models","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; Seoul National University","keywords":"Stochastic volatility; Dirichlet process; Probabilistic logic; Econometrics; Volatility (finance); Mathematics; Applied mathematics; Computer science; Statistics; Bayesian probability","score_opus":0.014304348430197754,"score_gpt":0.2592108021920202,"score_spread":0.24490645376182243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405934663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022530667,0.00021343709,0.995975,0.0006709347,0.00023502974,0.00029916607,0.00018779236,0.000025249676,0.00014031769],"genre_scores_gemma":[0.4972801,6.826583e-7,0.5024122,0.00015917045,0.0000847188,0.000008319559,0.0000059731587,0.000014488847,0.000034349192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984711,0.00010290128,0.00042594955,0.0003400468,0.00033316953,0.00032682286],"domain_scores_gemma":[0.99756527,0.00013532393,0.00013556697,0.0004027535,0.00070982886,0.0010512586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062198273,0.0001826628,0.0002645773,0.000295665,0.000116871335,0.00038553873,0.0006906756,0.00007172146,0.00001194024],"category_scores_gemma":[0.000102050944,0.00013756238,0.00003168022,0.0006505459,0.00006428334,0.0005587659,0.000013422144,0.000327122,0.0000047523836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003576542,0.00004435698,0.00003816623,0.0002362956,0.000068404224,0.00043180675,0.005843054,0.016287,0.000040908115,0.7520427,0.0038412747,0.22109026],"study_design_scores_gemma":[0.000075077885,0.00025303577,0.00010745659,0.000082844555,0.000029858324,0.00014990346,0.000013234047,0.63266945,0.000010209069,0.3660069,0.00045806373,0.00014395124],"about_ca_topic_score_codex":0.0002891698,"about_ca_topic_score_gemma":0.0045348243,"teacher_disagreement_score":0.6163825,"about_ca_system_score_codex":0.00016983444,"about_ca_system_score_gemma":0.0022893657,"threshold_uncertainty_score":0.5609631},"labels":[],"label_agreement":null},{"id":"W4406101628","doi":"10.1214/24-ba1503","title":"A Differential Geometric Approach to Bayesian Marginalization","year":2025,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Bayesian probability; Mathematics; Differential (mechanical device); Computer science; Applied mathematics; Artificial intelligence; Econometrics; Physics","score_opus":0.010101761938530964,"score_gpt":0.26127061877982616,"score_spread":0.2511688568412952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406101628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018918594,0.00011989247,0.9663638,0.0010937032,0.000167914,0.00026751368,0.000004420646,0.00020026395,0.031593323],"genre_scores_gemma":[0.47470084,0.000009521769,0.5210486,0.00066056463,0.000046273435,0.000041513875,0.00001878696,0.000010059426,0.0034638592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973456,0.0002741201,0.00046702885,0.0009805494,0.00043013008,0.0005025616],"domain_scores_gemma":[0.998133,0.00007316248,0.00011399577,0.0012730408,0.00013853268,0.0002682747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004148151,0.00030190658,0.0006034567,0.0038106672,0.00020800372,0.00042692918,0.001308614,0.00014918964,0.00009017552],"category_scores_gemma":[0.000081716134,0.0002791147,0.00046303298,0.018011274,0.00002984015,0.00027322126,0.00032009784,0.00016486089,0.000021176571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002410305,0.00051449076,0.0047820043,0.0000797515,0.0019125203,0.000012383224,0.000562666,0.0013881464,0.00030506935,0.70689416,0.008553236,0.2749715],"study_design_scores_gemma":[0.0004893732,0.00004804993,0.018409323,0.000022525539,0.0013361403,0.000004146397,0.000024763738,0.95030075,0.0007955927,0.024926314,0.0029998454,0.0006431699],"about_ca_topic_score_codex":0.00009406351,"about_ca_topic_score_gemma":0.000023120347,"teacher_disagreement_score":0.9489126,"about_ca_system_score_codex":0.00010001849,"about_ca_system_score_gemma":0.000096645614,"threshold_uncertainty_score":0.9999661},"labels":[],"label_agreement":null},{"id":"W4406462651","doi":"10.1016/0967-0653(96)83388-6","title":"10.1016/0967-0653(96)83388-6","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Environmental science","score_opus":0.00832743777727498,"score_gpt":0.19489015339867974,"score_spread":0.18656271562140475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406462651","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007824779,0.00006958102,0.13714595,0.0007355012,0.0000042115007,0.00012840805,0.0000029269693,0.00021776579,0.86168784],"genre_scores_gemma":[0.0000135315,2.2252402e-7,0.13928743,0.00017868841,0.000120650744,0.000012716077,0.0000018263958,0.0000137580655,0.8603712],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987076,0.00010558833,0.00018456018,0.0004190807,0.00021829091,0.00036490118],"domain_scores_gemma":[0.9989323,0.00005639904,0.000028576434,0.00071415986,0.00004219916,0.0002263647],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00034420067,0.00016481358,0.00019178858,0.000075806536,0.00009533818,0.00013615243,0.00090062385,0.00007649484,0.9752708],"category_scores_gemma":[0.000019829125,0.00014956371,0.00007950298,0.00036319692,0.000023798928,0.00026690983,0.00012826058,0.0001323761,0.99052227],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007184955,0.000025058449,9.307142e-9,0.0000022544295,0.000005994912,0.000008051028,0.00003642679,0.000012981864,0.000024775552,0.00026397718,0.12679532,0.872818],"study_design_scores_gemma":[0.00013723988,0.00009145378,0.000004520975,0.000011236322,0.0000052617634,0.000018305149,8.777987e-8,0.0051418818,0.0002562919,0.001604705,0.992518,0.00021101607],"about_ca_topic_score_codex":0.0000114531185,"about_ca_topic_score_gemma":8.1379575e-8,"teacher_disagreement_score":0.87260693,"about_ca_system_score_codex":0.00002444099,"about_ca_system_score_gemma":0.00003941003,"threshold_uncertainty_score":0.6099031},"labels":[],"label_agreement":null},{"id":"W4406514352","doi":"10.1016/s0967-0653(97)84946-0","title":"10.1016/s0967-0653(97)84946-0","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stock assessment; Fishery; Bayesian probability; Stock (firearms); Sampling (signal processing); Adaptive sampling; Computer science; Econometrics; Environmental science; Statistics; Artificial intelligence; Economics; Geography; Mathematics; Biology; Fishing; Monte Carlo method","score_opus":0.0100537794134845,"score_gpt":0.2005238599425419,"score_spread":0.1904700805290574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406514352","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023324383,0.000081261736,0.14545283,0.0006202667,0.000003581185,0.00012318765,0.0000024427175,0.00022130729,0.8534928],"genre_scores_gemma":[0.000004645153,2.6839578e-7,0.13947411,0.00018035773,0.00011470941,0.000009948684,0.0000017235702,0.000014479372,0.86019975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873453,0.000101055404,0.00018228889,0.00041320582,0.00021293868,0.00035597695],"domain_scores_gemma":[0.9989472,0.000051430252,0.00002882925,0.00070741144,0.00004094502,0.00022419816],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003240189,0.00016451608,0.00019054575,0.000075027354,0.00010154399,0.00014285806,0.00091883197,0.000077120625,0.9884292],"category_scores_gemma":[0.000019086723,0.00014912896,0.00008000666,0.0003443268,0.000019185456,0.00026758562,0.00013478672,0.00013217711,0.9987493],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008848977,0.0000261995,2.6427494e-9,0.000002356191,0.000006369209,0.000008568622,0.000036772177,0.000011174271,0.000008168463,0.00030712466,0.044711385,0.954873],"study_design_scores_gemma":[0.00015047478,0.00009139226,0.000001037135,0.000011244136,0.000005355609,0.000019021763,9.029278e-8,0.0042528957,0.00019927006,0.0013019602,0.9937572,0.0002100616],"about_ca_topic_score_codex":0.000010965409,"about_ca_topic_score_gemma":7.235552e-8,"teacher_disagreement_score":0.954663,"about_ca_system_score_codex":0.000024201816,"about_ca_system_score_gemma":0.000033038377,"threshold_uncertainty_score":0.6081302},"labels":[],"label_agreement":null},{"id":"W4406565461","doi":"10.1016/j.endend.2013.01.010","title":"10.1016/j.endend.2013.01.010","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Mathematics; Statistics; Binary number; Exponential function; Regression; Econometrics; Computer science; Mathematical analysis; Arithmetic","score_opus":0.0077652363165672915,"score_gpt":0.19700997621133864,"score_spread":0.18924473989477136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406565461","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000095182895,0.000074117845,0.1555205,0.0009895867,0.0000047674152,0.000120415054,0.0000029476846,0.00022189191,0.84305626],"genre_scores_gemma":[0.000016361242,3.9586905e-7,0.16764435,0.00016311096,0.00011818562,0.00001159554,0.0000013975493,0.0000137942825,0.83203083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987253,0.000097480595,0.00017845567,0.00041390114,0.00022397593,0.0003608895],"domain_scores_gemma":[0.9989385,0.000053587697,0.000028605584,0.0007181915,0.000035960158,0.00022518214],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032358992,0.00016278398,0.0001858644,0.00008062567,0.000088070396,0.00012993172,0.0008883334,0.00007974622,0.97281706],"category_scores_gemma":[0.000014589353,0.00014784635,0.000076814526,0.000323848,0.000023068738,0.0002688898,0.00013216556,0.00014324361,0.9815428],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068406116,0.000022265025,7.448935e-9,0.000001905282,0.0000056734957,0.000007585969,0.000029185288,0.000012186075,0.00004214122,0.00017998915,0.20370486,0.79598737],"study_design_scores_gemma":[0.00013845217,0.000083176456,0.000006735988,0.000009451917,0.0000051116685,0.00002199376,8.737105e-8,0.0058455123,0.0001981043,0.0012033976,0.99228245,0.00020550788],"about_ca_topic_score_codex":0.00001989616,"about_ca_topic_score_gemma":1.960973e-7,"teacher_disagreement_score":0.79578185,"about_ca_system_score_codex":0.000022234506,"about_ca_system_score_gemma":0.00003775035,"threshold_uncertainty_score":0.60289997},"labels":[],"label_agreement":null},{"id":"W4406596694","doi":"10.1080/24709360.2025.2451519","title":"Finite Markov chains with absorbing states and mis-specified random effects: application to cognitive data","year":2025,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Center for Advancing Translational Sciences; National Institute on Aging","keywords":"Markov chain; Statistical physics; Cognition; Computer science; Mathematics; Physics; Psychology; Statistics","score_opus":0.03042029286051502,"score_gpt":0.33965049095912536,"score_spread":0.30923019809861035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406596694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003351633,0.0011918702,0.9945172,0.002355382,0.00016408505,0.00066660927,0.00021946625,0.00007228476,0.00047791045],"genre_scores_gemma":[0.042280924,0.00042421932,0.95076376,0.0060609546,0.000049091457,0.00008386126,0.0002008272,0.000011588891,0.0001247868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745226,0.000846405,0.00039457815,0.0008536254,0.000072576826,0.00038055234],"domain_scores_gemma":[0.98280674,0.016010052,0.0001575182,0.00076133094,0.000120990844,0.00014334539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002126764,0.0002086542,0.0005237465,0.00014293853,0.00014494314,0.000038466274,0.00059644855,0.00010462909,0.0000017369929],"category_scores_gemma":[0.0038663798,0.00016629056,0.00001791901,0.0003175547,0.0001488162,0.00009928662,0.00036150223,0.00016978057,0.00000807166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025571306,0.00003541918,0.001078029,0.00010749812,0.000086194865,0.000017017848,0.0004324734,0.000033145105,0.0001302566,0.4233112,0.0039226916,0.5705904],"study_design_scores_gemma":[0.0032777924,0.00035571412,0.017758423,0.00033246537,0.00013166554,0.000018585282,0.000054426822,0.75498694,0.00034670276,0.21242198,0.009743415,0.0005719062],"about_ca_topic_score_codex":0.00008879394,"about_ca_topic_score_gemma":0.000052950436,"teacher_disagreement_score":0.7549538,"about_ca_system_score_codex":0.000022224256,"about_ca_system_score_gemma":0.00006465093,"threshold_uncertainty_score":0.6781132},"labels":[],"label_agreement":null},{"id":"W4406627004","doi":"10.1080/10543406.2025.2450321","title":"A Bayesian joint bent-cable model for longitudinal measurements and survival time with heterogeneous random-effects distributions","year":2025,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences; Shahid Beheshti University of Medical Sciences","keywords":"Bayesian probability; Bent molecular geometry; Random effects model; Statistics; Joint (building); Mathematics; Longitudinal data; Bayesian inference; Statistical physics; Computer science; Econometrics; Applied mathematics; Physics; Medicine; Structural engineering; Data mining; Engineering; Internal medicine","score_opus":0.053857505023373976,"score_gpt":0.33619105566594615,"score_spread":0.28233355064257215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406627004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044004206,0.0005980679,0.99751526,0.000618807,0.00026265814,0.00035393497,0.00011508798,0.000016772881,0.000079345584],"genre_scores_gemma":[0.23455532,0.000056559707,0.7650364,0.00018404023,0.000045565776,0.000010645824,0.0000035768355,0.000009391725,0.000098506454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835896,0.00015177533,0.00048597038,0.00025972875,0.00038314634,0.00036041994],"domain_scores_gemma":[0.9984482,0.0004409924,0.00020804555,0.00018023199,0.00042300433,0.0002995414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009726714,0.00020277176,0.00046879594,0.000112583104,0.00019586994,0.00017160083,0.00029420745,0.00007015526,0.0000064407127],"category_scores_gemma":[0.00022726916,0.00015012971,0.000095488984,0.00019747308,0.00010363892,0.0001610722,0.000098770695,0.00023667784,7.887779e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067262906,0.00309418,0.0028592292,0.002206593,0.0042225146,0.0010395795,0.00063582964,0.022784954,0.03705155,0.4252814,0.016378202,0.47771966],"study_design_scores_gemma":[0.0042270445,0.00031427067,0.00016607116,0.00010943231,0.00029795157,0.00010951735,8.750295e-7,0.9392512,0.004990461,0.05019375,0.00016499685,0.00017444883],"about_ca_topic_score_codex":0.00000187406,"about_ca_topic_score_gemma":0.0000018817825,"teacher_disagreement_score":0.91646624,"about_ca_system_score_codex":0.00008924198,"about_ca_system_score_gemma":0.0002162191,"threshold_uncertainty_score":0.61221117},"labels":[],"label_agreement":null},{"id":"W4406975251","doi":"10.3204/pubdb-2025-00422","title":"A universal bound on the duration of a kination era","year":2025,"lang":"en","type":"preprint","venue":"Desy publication database (The Deutsches Elektronen-Synchrotron)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Azrieli Foundation; Generalitat Valenciana; Deutsche Forschungsgemeinschaft","keywords":"Duration (music); Mathematics; Physics","score_opus":0.029230100597793223,"score_gpt":0.27639080734977434,"score_spread":0.24716070675198112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406975251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049602618,0.00033259302,0.9483506,0.039776754,0.0005222637,0.001764372,0.000398815,0.0002193291,0.003674991],"genre_scores_gemma":[0.6263328,0.0005422323,0.35901383,0.004994161,0.00069723197,0.0018506966,0.0039860797,0.00008603152,0.0024969198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951437,0.0012462599,0.00094219326,0.0012160226,0.0009391777,0.0005126492],"domain_scores_gemma":[0.99246067,0.00093951594,0.0011896397,0.0043440405,0.00093755097,0.00012857668],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029700412,0.00055270386,0.00050687464,0.00055371865,0.00052918115,0.0007406211,0.003933904,0.00034204125,0.00006693505],"category_scores_gemma":[0.0008008906,0.00038371634,0.0002972546,0.001143598,0.00028826666,0.001160571,0.0019392965,0.0013550699,0.00005740357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038292932,0.00021423431,0.000023907978,0.00012478868,0.00016743233,0.0000015158203,0.000638598,0.00015868396,0.0012979567,0.9417669,0.013265168,0.04230248],"study_design_scores_gemma":[0.0026619323,0.0004114326,0.004887153,0.0013865452,0.00071120815,0.000042734497,0.0002677938,0.57002103,0.06085607,0.12540966,0.23068787,0.0026565557],"about_ca_topic_score_codex":0.0002348162,"about_ca_topic_score_gemma":0.000051882267,"teacher_disagreement_score":0.81635725,"about_ca_system_score_codex":0.00035216077,"about_ca_system_score_gemma":0.0011560215,"threshold_uncertainty_score":0.9998615},"labels":[],"label_agreement":null},{"id":"W4407023510","doi":"10.1002/cjs.11838","title":"Balanced longitudinal data clustering with a copula kernel mixture model","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University; McMaster University","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Copula (linguistics); Cluster analysis; Longitudinal data; Econometrics; Mathematics; Computer science; Statistics; Data mining","score_opus":0.03733963041055525,"score_gpt":0.28007279890809333,"score_spread":0.2427331684975381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407023510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001572568,0.00037755904,0.9970268,0.00072987215,0.00035822796,0.000060966482,0.00025651068,0.00000707221,0.0010257047],"genre_scores_gemma":[0.10814456,0.000019563426,0.8908335,0.000521139,0.00005025988,5.9388816e-7,0.000008225219,0.0000084489575,0.00041369224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989324,0.00004946101,0.00030482854,0.00023056648,0.00017410128,0.0003086085],"domain_scores_gemma":[0.99843335,0.00007467173,0.00017342069,0.00062880846,0.00027492354,0.00041481745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038897013,0.0001372175,0.00025327597,0.00021027272,0.0001312646,0.00021455421,0.0014218694,0.000059035418,0.00000826148],"category_scores_gemma":[0.00011187756,0.00011278893,0.000022533988,0.0002720347,0.00006880745,0.00033517907,0.00009562703,0.000299379,0.0000010664813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006191125,0.000037217404,0.004639876,0.00018960258,0.00028252992,0.0028425953,0.0009553513,0.0137961665,0.000092404596,0.5858942,0.18604451,0.2051636],"study_design_scores_gemma":[0.0005337097,0.000076949094,0.0016488401,0.00022687056,0.00005618003,0.00030232975,0.000012934551,0.9449103,0.000018907787,0.049050577,0.0029707456,0.00019167172],"about_ca_topic_score_codex":0.0005638663,"about_ca_topic_score_gemma":0.013167759,"teacher_disagreement_score":0.93111414,"about_ca_system_score_codex":0.000099054916,"about_ca_system_score_gemma":0.0025064007,"threshold_uncertainty_score":0.7347919},"labels":[],"label_agreement":null},{"id":"W4407242198","doi":"10.1016/j.neucom.2025.129357","title":"Mixture of experts models for multilevel data: Modeling framework and approximation theory","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Power Generation; University of Toronto","funders":"","keywords":"Computer science; Multilevel model; Artificial intelligence; Econometrics; Data mining; Machine learning; Mathematics","score_opus":0.05886404320432947,"score_gpt":0.33066260798563507,"score_spread":0.2717985647813056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407242198","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002138904,0.00057302037,0.99590075,0.00030172465,0.0002811277,0.00037856138,0.00000521765,0.000093748684,0.0003269398],"genre_scores_gemma":[0.34432667,0.000011169654,0.6550966,0.00048183842,0.000048494578,0.000008781166,0.0000026239038,0.0000077436825,0.000016080632],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986056,0.00013843701,0.00031683707,0.0005964999,0.00012244022,0.00022019034],"domain_scores_gemma":[0.9982627,0.0007298638,0.00010839267,0.00076128036,0.00009568867,0.000042051295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008514105,0.00014853374,0.00023770005,0.00011225502,0.0001530632,0.000091013295,0.00081505114,0.00011318597,1.8626083e-7],"category_scores_gemma":[0.00019455206,0.00013608887,0.000044390705,0.00016038804,0.000024643105,0.00045836726,0.0007051684,0.00014968157,6.7322674e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008071916,0.000020306348,0.0000025076695,0.00009498267,0.0000092993705,4.2860108e-7,0.0007413136,0.014125234,0.0005157707,0.587234,0.000049312905,0.39719874],"study_design_scores_gemma":[0.00013231205,0.000008742909,0.0000026381624,0.00009753607,0.0000065189915,0.0000018071216,0.000009551079,0.6034998,0.00036619234,0.3957688,0.000039547365,0.000066502565],"about_ca_topic_score_codex":0.000002627492,"about_ca_topic_score_gemma":1.6256062e-7,"teacher_disagreement_score":0.5893746,"about_ca_system_score_codex":0.0000076094943,"about_ca_system_score_gemma":0.00004370646,"threshold_uncertainty_score":0.5549543},"labels":[],"label_agreement":null},{"id":"W4407903965","doi":"10.1080/01621459.2025.2468011","title":"Class-Specific Joint Feature Screening in Ultrahigh-Dimensional Mixture Regression","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Key Research and Development Program of China","keywords":"Feature (linguistics); Class (philosophy); Regression; Joint (building); Artificial intelligence; Pattern recognition (psychology); Computer science; Statistics; Mathematics; Engineering","score_opus":0.011068565266198049,"score_gpt":0.28065491987849067,"score_spread":0.26958635461229263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407903965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007263701,0.00019345914,0.9704194,0.021074768,0.0006146323,0.0000759144,0.000009354789,0.0000112853795,0.00033749777],"genre_scores_gemma":[0.23136975,0.0000450915,0.765837,0.0019098378,0.00013760025,0.0000016036239,0.0000013348266,0.00000690653,0.00069088815],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978052,0.0006870312,0.00045293692,0.00019258757,0.00061894656,0.0002432961],"domain_scores_gemma":[0.99761605,0.00083913136,0.0010018479,0.00022999808,0.00024090517,0.0000720495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013227223,0.00013165516,0.0003984827,0.00016607638,0.00011381806,0.00009977778,0.00049289584,0.00007933523,0.0000048945158],"category_scores_gemma":[0.0008020011,0.00008009526,0.0001364434,0.0008333107,0.00005752523,0.00019241807,0.00012294122,0.0007615979,0.000001568344],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019166563,0.0002477097,0.016703706,0.00001968143,0.00015813397,0.00008512614,0.00039247796,0.00040636203,0.010297746,0.2089557,0.29014102,0.47240067],"study_design_scores_gemma":[0.0012963847,0.00020718106,0.81555337,0.00057540624,0.000057458907,0.00005771376,0.000050658826,0.020105299,0.0017878262,0.14452614,0.0154737355,0.00030884566],"about_ca_topic_score_codex":0.000014218967,"about_ca_topic_score_gemma":0.0000057931993,"teacher_disagreement_score":0.79884964,"about_ca_system_score_codex":0.0003040243,"about_ca_system_score_gemma":0.00013341982,"threshold_uncertainty_score":0.3308806},"labels":[],"label_agreement":null},{"id":"W4408035483","doi":"10.22541/au.174073683.37707806/v1","title":"A Bayesian Coalescent Model of the DNA Barcode Gap","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Coalescent theory; Barcode; Bayesian probability; Computational biology; DNA barcoding; Computer science; Evolutionary biology; Biology; Genetics; Artificial intelligence; Gene; Phylogenetics","score_opus":0.0407102596664418,"score_gpt":0.28930688440476704,"score_spread":0.24859662473832522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408035483","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000055783144,0.00015607568,0.9342319,0.0027639808,0.00073416467,0.0004540046,0.00003153143,0.0001043227,0.06146826],"genre_scores_gemma":[0.09289868,0.00005428262,0.8964447,0.001350137,0.00004242758,0.00003371363,0.0000015105958,0.000010174677,0.009164406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784935,0.00026048764,0.00045654245,0.0007258852,0.0004009268,0.00030681794],"domain_scores_gemma":[0.9969824,0.00007189387,0.00022036006,0.0024951,0.00013600217,0.00009424096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004746896,0.00030806844,0.000456623,0.000112502996,0.00008119281,0.00009433419,0.0035076982,0.00029979896,0.000011559654],"category_scores_gemma":[0.00003754525,0.00020045319,0.00039225086,0.0002316034,0.00008118416,0.00007261319,0.0047937213,0.0006246135,0.0000019313272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003925573,0.00009217635,0.00002497303,0.00029415337,0.000048758895,0.0000013533124,0.0005753978,0.0105329715,0.00066168886,0.94735223,0.004018443,0.03639392],"study_design_scores_gemma":[0.00008051876,0.000004461041,0.000018406085,0.00018508927,0.000017230179,0.0000010533544,0.0000017284792,0.6518857,0.0046436465,0.34286952,0.00014235111,0.00015034252],"about_ca_topic_score_codex":0.0000593823,"about_ca_topic_score_gemma":0.000027590977,"teacher_disagreement_score":0.6413527,"about_ca_system_score_codex":0.000058696507,"about_ca_system_score_gemma":0.0007900576,"threshold_uncertainty_score":0.81742436},"labels":[],"label_agreement":null},{"id":"W4408047762","doi":"10.1007/s42081-025-00298-x","title":"Application of machine learning methods in the imputation of heterogeneous co-missing data","year":2025,"lang":"en","type":"article","venue":"Japanese Journal of Statistics and Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Canadian Institutes of Health Research; McLaughlin Centre, University of Toronto","keywords":"Imputation (statistics); Missing data; Computer science; Machine learning; Artificial intelligence; Data mining","score_opus":0.04797112399033372,"score_gpt":0.4199266282748576,"score_spread":0.3719555042845239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408047762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051653264,0.00020628572,0.9942375,0.00018942029,0.000038072438,0.00005802934,0.00004517241,0.0000017246638,0.000058497502],"genre_scores_gemma":[0.4065149,0.000042322044,0.59339535,0.000035029134,0.0000040651116,1.9995936e-7,0.0000065937143,8.1601877e-7,7.2478497e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869144,0.00024593397,0.00043797083,0.00021968513,0.00030314107,0.00010179988],"domain_scores_gemma":[0.99795145,0.0007330042,0.0004063822,0.00069406955,0.00017812295,0.000036968137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008062416,0.00005570119,0.00016127319,0.00017920606,0.00010449589,0.00008896501,0.0022559774,0.000015186385,5.016219e-7],"category_scores_gemma":[0.00096171914,0.00003622057,0.000008056644,0.00065722,0.00020807228,0.0007978548,0.0004907674,0.00012435933,4.5246644e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012578954,0.000047707963,0.0011932738,0.00003999022,0.0000059974136,0.000004794082,0.0014170177,0.0005527546,0.043426197,0.04048116,0.000017437238,0.9128011],"study_design_scores_gemma":[0.00016435563,0.000059959188,0.004483919,0.00002520601,0.00001081494,0.000065594264,0.00008535796,0.96806777,0.0016689352,0.025194978,0.00013411984,0.000039017148],"about_ca_topic_score_codex":0.00006220733,"about_ca_topic_score_gemma":0.000005375159,"teacher_disagreement_score":0.967515,"about_ca_system_score_codex":0.000008691977,"about_ca_system_score_gemma":0.0001415471,"threshold_uncertainty_score":0.41922045},"labels":[],"label_agreement":null},{"id":"W4408085363","doi":"10.1007/978-3-031-64350-7_24","title":"Cluster-Weighted Disjoint Factor Analyzers for Exploring the Impact of Socioeconomic Factors on Crime Rates","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Disjoint sets; Socioeconomic status; Cluster (spacecraft); Factor (programming language); Statistics; Geography; Computer science; Econometrics; Mathematics; Demography; Sociology; Combinatorics; Computer network","score_opus":0.06553413450151578,"score_gpt":0.31987916797498306,"score_spread":0.25434503347346726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408085363","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013842516,0.000095588286,0.92090434,0.0002667215,0.00056602637,0.0007048887,0.00013911702,0.000087696484,0.07585136],"genre_scores_gemma":[0.17731094,0.00047961567,0.2874382,0.00097644405,0.0006572998,0.00022803662,0.0001233774,0.00024455844,0.5325415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823296,0.000058487767,0.00055125233,0.0006549869,0.00015717416,0.0003451512],"domain_scores_gemma":[0.99733776,0.001090912,0.00035485314,0.0009971085,0.00010969455,0.00010964392],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029526232,0.0005351668,0.0007630549,0.000293132,0.00014457657,0.00013698892,0.0011307363,0.00021825828,0.00017701671],"category_scores_gemma":[0.000025483763,0.00030012432,0.0010827474,0.000039827446,0.00008386411,0.0002545339,0.00025760476,0.00033315973,0.000011289451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004214682,0.000031182484,0.000032614455,0.0000749827,0.0007893153,9.446473e-7,0.0008853488,0.000039376282,0.00010638782,0.9229837,0.0066694953,0.06834448],"study_design_scores_gemma":[0.0016979451,0.0016065877,0.0028993515,0.0006532865,0.00035041274,0.0000035357436,0.000069972564,0.070443265,0.0154552655,0.89505625,0.009230142,0.0025339911],"about_ca_topic_score_codex":0.00008795777,"about_ca_topic_score_gemma":0.000007514893,"teacher_disagreement_score":0.6334661,"about_ca_system_score_codex":0.00023136035,"about_ca_system_score_gemma":0.00024652938,"threshold_uncertainty_score":0.9999451},"labels":[],"label_agreement":null},{"id":"W4408144537","doi":"10.1080/10618600.2025.2475139","title":"High-Dimensional Covariate-Dependent Gaussian Graphical Models","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Graphical model; Computer science; Gaussian; Econometrics; Mathematics; Statistics; Artificial intelligence","score_opus":0.01453389678061359,"score_gpt":0.2733778907991399,"score_spread":0.2588439940185263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408144537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002871747,0.0003223299,0.99195844,0.004050948,0.0005437242,0.00006936638,0.000041463754,0.000018101066,0.0001239079],"genre_scores_gemma":[0.38973013,0.00004198995,0.60925597,0.0008809152,0.00004924797,0.0000010528998,0.0000043540163,0.0000042019374,0.000032119795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980182,0.00020041096,0.00068085926,0.00024969573,0.0006351511,0.00021565091],"domain_scores_gemma":[0.9981286,0.0007384434,0.00026161326,0.00013136333,0.00051341264,0.00022659708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069119746,0.0001762374,0.00037441586,0.0003628944,0.00018133067,0.00015250621,0.00037491063,0.000115208204,0.000008698089],"category_scores_gemma":[0.00007613051,0.00013667828,0.00010314639,0.0004621603,0.00014738903,0.00028062018,0.00013989588,0.0004373023,9.963913e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004609189,0.0001151437,0.000070991795,0.000017260892,0.000088814566,0.00007947768,0.00003404586,0.012906568,0.000016807659,0.9563967,0.0016823773,0.028545743],"study_design_scores_gemma":[0.0006530848,0.00012067446,0.0055633583,0.00003646727,0.00003050746,0.00012148782,0.0000013349901,0.24830106,0.000009298961,0.74495393,0.00010285529,0.00010591655],"about_ca_topic_score_codex":0.00001173622,"about_ca_topic_score_gemma":0.0000028071934,"teacher_disagreement_score":0.38685837,"about_ca_system_score_codex":0.000020761554,"about_ca_system_score_gemma":0.00022009424,"threshold_uncertainty_score":0.55735785},"labels":[],"label_agreement":null},{"id":"W4408201762","doi":"10.1214/25-ejs2359","title":"Resistant convex clustering: How does the fusion penalty enhance resistance?","year":2025,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Penalty method; Cluster analysis; Regular polygon; Mathematical optimization; Statistics","score_opus":0.006119107416195306,"score_gpt":0.26281211828054496,"score_spread":0.25669301086434965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408201762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026872623,0.0029898796,0.9834694,0.011393183,0.00058136333,0.00010625323,0.000008629979,0.000015216445,0.0011673188],"genre_scores_gemma":[0.4470205,0.0018120176,0.541949,0.0007284686,0.00015063994,0.000003674043,8.127355e-7,0.000012099223,0.008322826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981767,0.00028659563,0.00042528272,0.00021414034,0.0003924878,0.0005047743],"domain_scores_gemma":[0.9982109,0.0004789312,0.00043983723,0.00044590473,0.0003563447,0.000068061534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016475816,0.00015894606,0.0002928167,0.00010548315,0.0002391715,0.00021871174,0.0010907793,0.000058259597,0.000008661626],"category_scores_gemma":[0.0002587631,0.000089559086,0.00008053972,0.00034126829,0.000087728986,0.00020682432,0.00011466937,0.00064552063,0.000001178518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010222932,0.000029024955,0.000007353812,0.00004665111,0.0000637552,0.000037415288,0.00031070455,0.000006685402,0.0031664795,0.93684894,0.012545277,0.04683548],"study_design_scores_gemma":[0.00053639326,0.00027244113,0.0003534322,0.00020058364,0.00006219642,0.00005044009,0.00006667729,0.004663326,0.0064436817,0.90750206,0.07963713,0.00021165633],"about_ca_topic_score_codex":0.0000041440953,"about_ca_topic_score_gemma":0.00022889585,"teacher_disagreement_score":0.44675177,"about_ca_system_score_codex":0.00020170395,"about_ca_system_score_gemma":0.00080004946,"threshold_uncertainty_score":0.36521137},"labels":[],"label_agreement":null},{"id":"W4408533419","doi":"10.1093/biomtc/ujaf018","title":"Jointly modeling means and variances for nonlinear mixed effects models with measurement errors and outliers","year":2025,"lang":"en","type":"article","venue":"Biometrics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Inference; Random effects model; Variance (accounting); Computer science; Mixed model; Statistical inference; Statistics; Statistical model; Nonlinear system; Human immunodeficiency virus (HIV); Econometrics; Data mining; Mathematics; Machine learning; Artificial intelligence","score_opus":0.041374461524431166,"score_gpt":0.2666058924521734,"score_spread":0.22523143092774225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408533419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022166222,0.0028953156,0.993341,0.000469173,0.00030467234,0.00046543064,0.0000052904115,0.00010503683,0.00019742432],"genre_scores_gemma":[0.17173217,0.00012336734,0.8278375,0.00021166101,0.000022075821,0.000031221494,7.920683e-7,0.000012519548,0.000028645805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861383,0.000068618814,0.00019985443,0.0005074006,0.00032782197,0.00028246178],"domain_scores_gemma":[0.9990931,0.00018672261,0.000063124746,0.00030106338,0.000237168,0.00011880003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011966819,0.00018527551,0.00027520314,0.00086965977,0.00013890318,0.00018263068,0.00027620327,0.000091666305,5.555018e-8],"category_scores_gemma":[0.00019618229,0.00014315225,0.000039851588,0.0020344583,0.000047030917,0.00028378313,0.0001311719,0.000085683176,1.1847338e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008384455,0.00016325813,0.00013093835,0.000782685,0.00024952568,0.000008582785,0.0009028526,0.003554826,0.0013128815,0.33778307,0.00035965565,0.6546679],"study_design_scores_gemma":[0.00079671585,0.0001683766,0.000041828178,0.000084088366,0.000047946185,0.000002948856,0.000016785365,0.9517626,0.0008264708,0.045704182,0.00036521105,0.00018285585],"about_ca_topic_score_codex":0.000018830131,"about_ca_topic_score_gemma":0.0000068464933,"teacher_disagreement_score":0.94820774,"about_ca_system_score_codex":0.000049408318,"about_ca_system_score_gemma":0.00009397584,"threshold_uncertainty_score":0.583758},"labels":[],"label_agreement":null},{"id":"W4408585636","doi":"10.1214/24-aoas1958","title":"Poisson cluster process models for detecting ultra-diffuse galaxies","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Computer science; Cluster (spacecraft); Poisson distribution; Statistical physics; Statistics; Mathematics; Physics","score_opus":0.05633146807322464,"score_gpt":0.34934960217812083,"score_spread":0.2930181341048962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408585636","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008778773,0.00008776939,0.9929473,0.0010896573,0.00010290567,0.00047243945,0.000051219275,0.000055508644,0.0043153623],"genre_scores_gemma":[0.47606134,0.000027847555,0.5229937,0.0006736569,0.000025546244,0.000058642516,0.0000024185522,0.000009430526,0.00014741054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887264,0.000043744505,0.00032297135,0.00027475206,0.00018263931,0.00030327885],"domain_scores_gemma":[0.99824333,0.0007877488,0.00017099023,0.00049752643,0.00025634415,0.000044043274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008319571,0.00015453275,0.00025334643,0.00007791069,0.00018397706,0.00008453341,0.0007890146,0.000063367,0.0000010290836],"category_scores_gemma":[0.00010521674,0.00011236085,0.000052507792,0.00025486026,0.00007602385,0.00010808124,0.00006278367,0.0001298819,0.0000010107888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007106003,0.000044966433,0.0000015780959,0.00017231677,0.000035796933,2.6116265e-7,0.001938158,0.0010974624,0.00083969434,0.90894496,0.001996434,0.08485731],"study_design_scores_gemma":[0.00027586997,0.000034338176,0.000030129722,0.000025388785,0.00001560688,6.3357305e-7,0.000049133076,0.18539885,0.03805694,0.7758914,0.0001200495,0.00010164037],"about_ca_topic_score_codex":0.0000062860095,"about_ca_topic_score_gemma":0.000004903586,"teacher_disagreement_score":0.47518346,"about_ca_system_score_codex":0.0000061518417,"about_ca_system_score_gemma":0.00007946326,"threshold_uncertainty_score":0.45819426},"labels":[],"label_agreement":null},{"id":"W4408704162","doi":"10.1016/j.csbj.2025.03.017","title":"Multivariate Poisson lognormal distribution for modeling counts from modern biological data: An overview","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Log-normal distribution; Multivariate statistics; Poisson distribution; Statistics; Count data; Multivariate analysis; Poisson regression; Computer science; Mathematics; Econometrics; Medicine; Population","score_opus":0.09113025458818509,"score_gpt":0.3611899497235986,"score_spread":0.2700596951354135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408704162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026903598,0.0019216873,0.9683104,0.0022784572,0.00028583655,0.000073088515,0.00015945705,0.00005766634,0.000009775566],"genre_scores_gemma":[0.5488713,0.00012438823,0.4505148,0.00020954812,0.00006299605,0.0000012961914,0.00020765187,0.0000019725837,0.00000607899],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921197,0.000055465083,0.00019754797,0.00030849775,0.000074263786,0.00015226507],"domain_scores_gemma":[0.9995447,0.000073518386,0.000066885914,0.00018415108,0.00008525715,0.000045516907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021195084,0.000102801074,0.00014924,0.000057350877,0.00025900867,0.00010583038,0.0005292147,0.00019487373,0.000003854964],"category_scores_gemma":[0.000048415463,0.00007594082,0.000029873057,0.00009501277,0.000057391426,0.0003029955,0.00023251626,0.00023300813,5.932627e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020849215,0.000009571245,0.00005119678,0.0000051850193,0.00003845455,0.0000035548767,0.000025954385,0.0029855622,0.00032443187,0.4938409,0.00022073003,0.5024736],"study_design_scores_gemma":[0.0001712418,0.000019720317,0.0005104589,0.000008822447,0.000004901294,0.000035209243,0.000001644456,0.5392526,0.0000237604,0.45966193,0.00026066988,0.000049055754],"about_ca_topic_score_codex":0.00000667116,"about_ca_topic_score_gemma":8.589159e-7,"teacher_disagreement_score":0.53626704,"about_ca_system_score_codex":0.000022392564,"about_ca_system_score_gemma":0.00005793808,"threshold_uncertainty_score":0.3096777},"labels":[],"label_agreement":null},{"id":"W4408755504","doi":"10.1093/jrsssc/qlaf021","title":"Bayesian inference for the Markov-modulated Poisson process with an outcome process","year":2025,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outcome (game theory); Inference; Bayesian inference; Poisson process; Process (computing); Computer science; Bayesian probability; Poisson distribution; Econometrics; Artificial intelligence; Statistics; Mathematics; Mathematical economics","score_opus":0.01172868295093676,"score_gpt":0.3128658715645225,"score_spread":0.30113718861358574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408755504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002943018,0.000049125694,0.9957315,0.0022530963,0.00036344465,0.0006097463,0.00029775786,0.00003895694,0.00036207263],"genre_scores_gemma":[0.30319735,0.000008062653,0.6953005,0.0009039407,0.000084674975,0.000042146574,0.0000069626794,0.00002147621,0.0004348495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997479,0.00014275083,0.0008067727,0.00039244944,0.0006666788,0.0005123084],"domain_scores_gemma":[0.9965176,0.0014498171,0.00056488614,0.0005522589,0.00071757974,0.00019786999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010904269,0.00033978318,0.00054442533,0.00003221296,0.0007503085,0.00041112924,0.0018119351,0.00013996105,0.000023742708],"category_scores_gemma":[0.00044394555,0.00017569111,0.00012902035,0.00051171554,0.00041121183,0.00026669612,0.00015926732,0.00066479493,6.5251555e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078108284,0.000268882,0.00045791574,0.00052572397,0.0004465944,0.000012381823,0.0024396747,0.0048066517,0.000046415502,0.9147662,0.008214923,0.06723358],"study_design_scores_gemma":[0.0013105249,0.0006078492,0.005159911,0.00009876475,0.00032270805,0.000022914222,0.00048562448,0.3737007,0.00024241909,0.6164472,0.001197085,0.0004042507],"about_ca_topic_score_codex":0.000012243875,"about_ca_topic_score_gemma":0.000027914268,"teacher_disagreement_score":0.36889407,"about_ca_system_score_codex":0.00009497525,"about_ca_system_score_gemma":0.00056126254,"threshold_uncertainty_score":0.71644753},"labels":[],"label_agreement":null},{"id":"W4408798893","doi":"10.28924/2291-8639-23-2025-67","title":"New Modified Estimators for the Spatial Lag Model with Randomly Missing Data in Dependent Variable: Methods and Simulation Study","year":2025,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Lag; Missing data; Mathematics; Variable (mathematics); Econometrics; Statistics; Computer science","score_opus":0.03404382875866673,"score_gpt":0.41403507589175964,"score_spread":0.3799912471330929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408798893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005049778,0.00021782944,0.99725324,0.001669381,0.000031877855,0.00025723956,0.0000068947347,0.0000040658247,0.00005451169],"genre_scores_gemma":[0.37349188,0.000021562453,0.6263272,0.00006901886,0.00003301986,0.0000113030665,0.0000025091192,0.0000018837198,0.00004159562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909115,0.00008528593,0.0003496381,0.00021339509,0.00019536821,0.00006516287],"domain_scores_gemma":[0.99843895,0.0007657456,0.0002176156,0.0003005675,0.00023385891,0.000043273303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014877219,0.00007577966,0.00020273824,0.00029530437,0.00009478911,0.00024156136,0.00069112325,0.000024750143,8.1491453e-7],"category_scores_gemma":[0.000077758465,0.00004822604,0.00003621528,0.00042841976,0.000017126575,0.00026400675,0.00015422299,0.00009303016,1.7097925e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084123254,0.00009879799,0.0012541683,0.0000029420703,0.0008758547,6.4764873e-7,0.00019788154,0.4112825,0.000073793104,0.031114426,0.000017283459,0.55499756],"study_design_scores_gemma":[0.0011318485,0.000016859372,0.0019358181,0.000010924671,0.00048923056,0.0000028118764,0.00002274914,0.95719767,0.000025794849,0.03895116,0.00016821171,0.00004689961],"about_ca_topic_score_codex":0.0001466794,"about_ca_topic_score_gemma":0.000082779945,"teacher_disagreement_score":0.55495065,"about_ca_system_score_codex":0.000019454952,"about_ca_system_score_gemma":0.00014253071,"threshold_uncertainty_score":0.23293819},"labels":[],"label_agreement":null},{"id":"W4408821831","doi":"10.1016/j.physa.2025.130536","title":"CALF-SBM: A covariate-assisted latent factor stochastic block model","year":2025,"lang":"en","type":"article","venue":"Physica A Statistical Mechanics and its Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; National Science Foundation","keywords":"Covariate; Mathematics; Stochastic block model; Factor (programming language); Block (permutation group theory); Statistics; Latent variable; Block model; Factor analysis; Applied mathematics; Econometrics; Computer science; Combinatorics; Engineering","score_opus":0.03331380240376257,"score_gpt":0.30567309836004203,"score_spread":0.27235929595627945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408821831","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000062391664,0.00008521289,0.9971966,0.0013883678,0.00005559318,0.00058417674,0.00023824554,0.00011662175,0.00027278202],"genre_scores_gemma":[0.61169285,0.000019987969,0.38744777,0.00035198528,0.000019151497,0.00031949967,0.000009767722,0.000009741003,0.00012925077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986107,0.000050835566,0.00027752965,0.00057781226,0.00018213814,0.00030102237],"domain_scores_gemma":[0.9988136,0.00031468194,0.00007311188,0.00046305737,0.00014626408,0.00018923794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010945089,0.00019872705,0.0002730286,0.000072915755,0.00024889232,0.00013514045,0.00041662532,0.000076211974,0.000004703682],"category_scores_gemma":[0.000054066313,0.000178678,0.000047884496,0.00041092376,0.00001843898,0.00010527333,0.00025460025,0.00019341272,0.000016552973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038503304,0.00014899127,9.915749e-8,0.00002650314,0.000027394251,5.780189e-7,0.000056064742,0.0001496019,0.0029335392,0.9601069,0.0002229507,0.03632351],"study_design_scores_gemma":[0.00013875705,0.000018983905,0.000030135487,0.000009881559,0.000026256683,0.0000013631374,9.126349e-7,0.56255174,0.00010358851,0.43683666,0.00017236624,0.00010932804],"about_ca_topic_score_codex":0.000008155077,"about_ca_topic_score_gemma":0.0000033701394,"teacher_disagreement_score":0.61163044,"about_ca_system_score_codex":0.00003556062,"about_ca_system_score_gemma":0.00012522643,"threshold_uncertainty_score":0.72862774},"labels":[],"label_agreement":null},{"id":"W4408924401","doi":"10.3390/jrfm18040177","title":"Finite Mixture at Quantiles and Expectiles","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quantile; Econometrics; Environmental science; Computer science; Mathematics","score_opus":0.006399639355968047,"score_gpt":0.23644458991039596,"score_spread":0.23004495055442792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408924401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020590853,0.0048872135,0.97237414,0.00036724805,0.00043160355,0.000063229585,0.0000014030005,0.000008840371,0.0012754496],"genre_scores_gemma":[0.571308,0.012476171,0.41467664,0.0005417288,0.00013653487,0.0000030737049,1.6156216e-7,0.00000503286,0.00085265073],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99930006,0.000061743136,0.00023467347,0.00015840231,0.00011971607,0.0001254027],"domain_scores_gemma":[0.9995092,0.00009503421,0.00015423186,0.0001452253,0.000043478813,0.000052831172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041339156,0.00009851327,0.00019778893,0.0001961574,0.00015389993,0.00008479684,0.00021448405,0.000048428254,0.0000017244196],"category_scores_gemma":[0.00005277865,0.000075197895,0.00005876615,0.00018305758,0.000034689045,0.0001583575,0.00028067848,0.00013557836,5.801474e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030184137,0.000026014815,0.0013050395,0.00003796838,0.000016988386,0.000060543527,0.0005949837,0.000008884897,0.000015820979,0.22581892,0.0027356008,0.76934904],"study_design_scores_gemma":[0.0017947924,0.00026953933,0.117178045,0.0003644414,0.00017264485,0.000071355076,0.00013873972,0.0028842175,0.0005081365,0.46242124,0.413842,0.000354873],"about_ca_topic_score_codex":0.0000047385047,"about_ca_topic_score_gemma":0.000008656634,"teacher_disagreement_score":0.76899415,"about_ca_system_score_codex":0.000016081793,"about_ca_system_score_gemma":0.000015224989,"threshold_uncertainty_score":0.3066481},"labels":[],"label_agreement":null},{"id":"W4409158425","doi":"10.1145/3690624.3709230","title":"Dynamic Deep Clustering of High-Dimensional Directional Data via Hyperspherical Embeddings with Bayesian Nonparametric Mixtures","year":2025,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Nonparametric statistics; Cluster analysis; Computer science; Bayesian probability; Artificial intelligence; Pattern recognition (psychology); Data mining; Algorithm; Mathematics; Econometrics","score_opus":0.00941075573566347,"score_gpt":0.26902626869097024,"score_spread":0.25961551295530677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409158425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011878401,0.00026194847,0.9944057,0.00078714045,0.00035972387,0.00014441741,0.000005648029,0.0001222927,0.0027252727],"genre_scores_gemma":[0.26116243,0.0000049520404,0.7378732,0.00040220298,0.000015077474,0.0000055293976,0.00001002917,0.000008614384,0.0005179795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981711,0.0001028482,0.0003088786,0.00073948916,0.0003843653,0.00029335002],"domain_scores_gemma":[0.9983305,0.00028801025,0.000101779195,0.0010562605,0.00012317712,0.000100300735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039235057,0.00020993744,0.0003393312,0.00024370202,0.00011839574,0.000076990524,0.0012726946,0.00010322886,0.000052558295],"category_scores_gemma":[0.000059925464,0.0001573372,0.00005541487,0.0013764078,0.000094713505,0.00042197166,0.00087019877,0.00020185145,0.000003465026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002007491,0.00053375313,0.0004453445,0.00014399657,0.00039868103,0.000052679618,0.00020021373,0.0095477635,0.0069406168,0.10314128,0.0025289252,0.875866],"study_design_scores_gemma":[0.0003951737,0.00007344434,0.001195802,0.000039034392,0.000026934957,0.00005521298,0.000004261141,0.98534197,0.0008379036,0.011664506,0.00016985592,0.00019592879],"about_ca_topic_score_codex":0.00021818253,"about_ca_topic_score_gemma":0.00009135374,"teacher_disagreement_score":0.9757942,"about_ca_system_score_codex":0.000054370208,"about_ca_system_score_gemma":0.00012739291,"threshold_uncertainty_score":0.64160246},"labels":[],"label_agreement":null},{"id":"W4409374172","doi":"10.1016/b978-0-443-15888-9.00015-7","title":"Advanced probabilistic methods","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Probabilistic logic; Computer science; Artificial intelligence","score_opus":0.01810385271897022,"score_gpt":0.30732363347988395,"score_spread":0.2892197807609137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374172","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.833127e-8,0.0012007816,0.4827182,0.00010475238,0.000656041,0.00041167252,0.000004948405,0.00015598827,0.5147476],"genre_scores_gemma":[6.894646e-7,0.000037717735,0.48963022,0.00050913315,0.00008120656,0.00004214357,0.000002263167,0.000026414467,0.5096702],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973291,0.00020391692,0.0005923207,0.0011188368,0.00031883118,0.0004369861],"domain_scores_gemma":[0.99706465,0.00036495706,0.00028429384,0.0019165477,0.00018590277,0.0001836676],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001013101,0.00059996976,0.0008492085,0.00025144638,0.0001397988,0.00014558417,0.0016399652,0.00046545148,0.00004786947],"category_scores_gemma":[0.000100302364,0.00053876283,0.00038838293,0.000042520376,0.00011817104,0.00010564087,0.00072152645,0.0007352701,0.000056367207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020050272,0.0000029028768,1.3708231e-8,0.00007171756,0.000030366842,0.000012282782,0.0000521186,3.879439e-7,0.000015882471,0.4415839,0.00014324379,0.55808514],"study_design_scores_gemma":[0.000101047684,0.000028616922,2.8963927e-7,0.00026858135,0.000041047995,0.000009011574,1.6714584e-7,0.00036843983,0.00006451053,0.45754522,0.5412589,0.00031421185],"about_ca_topic_score_codex":1.4105032e-7,"about_ca_topic_score_gemma":0.0000024423703,"teacher_disagreement_score":0.55777097,"about_ca_system_score_codex":0.00011617833,"about_ca_system_score_gemma":0.00039897315,"threshold_uncertainty_score":0.9997064},"labels":[],"label_agreement":null},{"id":"W4409374177","doi":"10.1016/b978-0-443-15888-9.00014-5","title":"Probabilistic methods: fundamentals","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Probabilistic logic; Computer science; Artificial intelligence","score_opus":0.024574599804604993,"score_gpt":0.3097624615499279,"score_spread":0.28518786174532296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374177","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.9623125e-8,0.0012817265,0.456984,0.00012747188,0.000653624,0.0004785841,0.000009332219,0.00014870052,0.5403165],"genre_scores_gemma":[0.0000011692297,0.00003658612,0.4649634,0.0008004232,0.00010697619,0.00004293999,0.000003332769,0.000027669817,0.5340175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715376,0.00023932711,0.0006587463,0.0011276884,0.00036662677,0.00045383355],"domain_scores_gemma":[0.9971673,0.0003679149,0.00030791838,0.0018189579,0.00013909355,0.00019883075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012590915,0.0006248733,0.0008768359,0.0002791468,0.00016121149,0.00024682467,0.0016671747,0.00047475027,0.00010615922],"category_scores_gemma":[0.00006611833,0.0005602234,0.0004301902,0.000039465216,0.00014600382,0.00010253081,0.00087235175,0.0006790985,0.00010796854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014735649,0.000004245382,3.3544598e-8,0.00008177512,0.000049526425,0.000014193484,0.00007186085,9.4375046e-8,0.00001232345,0.43192858,0.0004197617,0.56741613],"study_design_scores_gemma":[0.000088197696,0.00002870445,3.336321e-7,0.0002914491,0.00005355955,0.000012648628,3.241416e-7,0.00020907943,0.000065819324,0.45371068,0.54521745,0.00032172128],"about_ca_topic_score_codex":3.4612472e-7,"about_ca_topic_score_gemma":0.0000029346452,"teacher_disagreement_score":0.5670944,"about_ca_system_score_codex":0.00016250556,"about_ca_system_score_gemma":0.00038120936,"threshold_uncertainty_score":0.99968493},"labels":[],"label_agreement":null},{"id":"W4409374942","doi":"10.1016/b978-0-443-15888-9.00013-3","title":"Beyond supervised and unsupervised learning","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Unsupervised learning; Machine learning; Supervised learning; Artificial neural network","score_opus":0.012083153019176262,"score_gpt":0.23703897130708287,"score_spread":0.22495581828790662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374942","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003946883,0.00382771,0.14657657,0.00022635948,0.00037186567,0.00034490376,0.0000055081446,0.0001976286,0.8484455],"genre_scores_gemma":[0.00007148362,0.00030044018,0.15928005,0.0008802621,0.00014402204,0.000017963963,0.0000070457413,0.00004313855,0.8392556],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977702,0.0001143501,0.00043658447,0.00095497625,0.0003292035,0.00039467617],"domain_scores_gemma":[0.9984483,0.00017552976,0.00014040204,0.0009073643,0.00011960443,0.0002087644],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005228289,0.0005445313,0.0006995854,0.00028292887,0.00026382707,0.00025522796,0.0008827286,0.00047044328,0.000055267563],"category_scores_gemma":[0.000027542923,0.0005126769,0.00022428737,0.00003344589,0.00012575385,0.00012470313,0.0007255619,0.0009125772,0.00003363071],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024743842,0.0000022327658,0.0000015929153,0.00007553365,0.00004184232,0.00003096842,0.00020163934,1.4477823e-7,0.000021432523,0.30827644,0.00011664861,0.69122905],"study_design_scores_gemma":[0.00032936723,0.000058682843,0.000006525951,0.00033893427,0.00006288774,0.000019611325,0.0000016179999,0.0014141197,0.000045197787,0.2915616,0.7056473,0.00051414256],"about_ca_topic_score_codex":5.8664034e-7,"about_ca_topic_score_gemma":0.0000038844164,"teacher_disagreement_score":0.70553064,"about_ca_system_score_codex":0.000043655997,"about_ca_system_score_gemma":0.00020481566,"threshold_uncertainty_score":0.9997325},"labels":[],"label_agreement":null},{"id":"W4409589724","doi":"10.1007/978-3-031-85870-3_2","title":"A Multivariate Functional Data Clustering Method Using Parsimonious Cluster Weighted Models","year":2025,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; MacEwan University","funders":"","keywords":"Multivariate statistics; Cluster analysis; Cluster (spacecraft); Computer science; Data mining; Statistics; Artificial intelligence; Mathematics","score_opus":0.23402062003701513,"score_gpt":0.4014019355760586,"score_spread":0.16738131553904345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409589724","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.78704e-7,0.006060737,0.98350406,0.00032009702,0.00063163514,0.00037101336,0.00045042436,0.000112765876,0.008548406],"genre_scores_gemma":[0.0019266764,0.010212811,0.94921666,0.0001626569,0.00040966942,0.000011526689,0.008782639,0.00007478039,0.02920258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956095,0.00037689615,0.0010494818,0.0023184053,0.00033734165,0.0003083467],"domain_scores_gemma":[0.9935202,0.00052405504,0.0005837509,0.0041555683,0.0011225631,0.000093840885],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020122402,0.000547651,0.0010358028,0.0011992088,0.00049617887,0.00025121772,0.0021131835,0.00040362668,0.000018214],"category_scores_gemma":[0.0003991408,0.0005245975,0.00006627733,0.001978297,0.00016970279,0.0013343664,0.0056699887,0.0003961826,0.000006285655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039365324,0.00026559675,0.0009786524,0.00092269114,0.01024535,0.000012721651,0.0046652537,0.0011850455,0.00010223711,0.8037777,0.018936228,0.15886915],"study_design_scores_gemma":[0.00036454786,0.0000064958463,0.00025319296,0.00021072569,0.0020409015,0.0000057704833,0.00003892414,0.94869626,0.0000047517924,0.041339554,0.0065483563,0.00049052323],"about_ca_topic_score_codex":0.00008537967,"about_ca_topic_score_gemma":0.001394296,"teacher_disagreement_score":0.9475112,"about_ca_system_score_codex":0.00025909414,"about_ca_system_score_gemma":0.00046185357,"threshold_uncertainty_score":0.9997206},"labels":[],"label_agreement":null},{"id":"W4409676269","doi":"10.1002/cjs.70010","title":"A multivariate Poisson model based on a triangular comonotonic shock construction","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"HEC Montréal; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Poisson distribution; Mathematics; Poisson regression; Statistics; Medicine","score_opus":0.01530098882850674,"score_gpt":0.2602314608039323,"score_spread":0.24493047197542553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409676269","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002243712,0.000095416384,0.99654895,0.0011430446,0.0006565483,0.00009784744,0.00008763757,0.000007956135,0.0011382522],"genre_scores_gemma":[0.1508202,0.0000071748505,0.8480471,0.0009674785,0.000028044726,0.0000013419273,0.0000016626934,0.0000064635497,0.000120582605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989413,0.0001304049,0.00035748535,0.0001551597,0.00016065399,0.00025498273],"domain_scores_gemma":[0.9987125,0.00016616556,0.00019616132,0.00027047822,0.0002773606,0.00037734353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004854677,0.00012471322,0.00023956911,0.00045593223,0.0001358847,0.00013456449,0.00043643106,0.000079032725,0.00000969801],"category_scores_gemma":[0.00024350152,0.00011658578,0.00006618811,0.00027905582,0.000061707105,0.000119180746,0.000011223926,0.0002801971,0.0000020465475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025668376,0.00001709867,0.00007094266,0.000014923315,0.000030941057,0.00018498074,0.00021406294,0.010714423,0.00007298401,0.81049645,0.004784212,0.17337331],"study_design_scores_gemma":[0.0008252751,0.000093678165,0.00020240547,0.00008433504,0.000025748112,0.0000262691,0.000007146678,0.86012995,0.00017139474,0.13696912,0.001363684,0.00010100315],"about_ca_topic_score_codex":0.0005073773,"about_ca_topic_score_gemma":0.000920186,"teacher_disagreement_score":0.84941554,"about_ca_system_score_codex":0.00022321023,"about_ca_system_score_gemma":0.0031358683,"threshold_uncertainty_score":0.55628955},"labels":[],"label_agreement":null},{"id":"W4410031989","doi":"10.1016/j.ins.2025.122254","title":"Improving confidence intervals and central value estimation in small datasets through hybrid parametric bootstrapping","year":2025,"lang":"en","type":"article","venue":"Information Sciences","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nuclear Laboratories","funders":"","keywords":"Bootstrapping (finance); Confidence interval; Parametric statistics; Value (mathematics); Statistics; Computer science; Estimation; Robust confidence intervals; Econometrics; Mathematics","score_opus":0.02868751015281328,"score_gpt":0.3120221090664929,"score_spread":0.2833345989136796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410031989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013972186,0.00012394223,0.9828261,0.000591114,0.00026682724,0.00018822029,0.00000758014,0.00004768337,0.001976331],"genre_scores_gemma":[0.617262,0.000022602095,0.38184175,0.0008517193,0.0000039497663,0.0000075256157,0.00000525763,6.5245e-7,0.0000045102342],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883145,0.00008145728,0.00041590605,0.00021963603,0.00018644905,0.00026509637],"domain_scores_gemma":[0.99932265,0.00021666431,0.0001669946,0.00021270015,0.000039269242,0.00004170954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011490147,0.000100096564,0.00013036256,0.0003922427,0.00017497402,0.0007714454,0.0006259932,0.000033618187,0.0000015902624],"category_scores_gemma":[0.00043354215,0.0000867981,0.000020806683,0.0011485505,0.00013403835,0.005819787,0.00021263472,0.00010605865,0.0000038795565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021302599,0.000008680763,0.0002851659,0.00005564624,0.0000027397386,0.0000012218167,0.0012643199,0.0024814487,0.000054641274,0.3733728,0.00013790013,0.62233335],"study_design_scores_gemma":[0.00016900443,0.000024434814,0.0029855878,0.000095182244,0.0000023854311,0.000009086146,0.00007822476,0.92295825,0.001441453,0.071713254,0.00041778266,0.00010535104],"about_ca_topic_score_codex":0.00042663226,"about_ca_topic_score_gemma":0.000013624541,"teacher_disagreement_score":0.9204768,"about_ca_system_score_codex":0.00003609062,"about_ca_system_score_gemma":0.00015821245,"threshold_uncertainty_score":0.7439066},"labels":[],"label_agreement":null},{"id":"W4410062502","doi":"10.1101/2025.05.02.25326890","title":"A Quantitative Comparison of Structural and Distributional Properties of Synthetic Tabular Data in Parkinson’s Disease","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Parkinson's disease; Disease; Econometrics; Psychology; Computer science; Economics; Medicine; Pathology","score_opus":0.07936323153758752,"score_gpt":0.34601189885501965,"score_spread":0.26664866731743214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410062502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4018118,0.004769108,0.592337,0.00030929162,0.00015042163,0.00020124072,0.0003977556,0.000010513,0.00001283657],"genre_scores_gemma":[0.87724125,0.000048309514,0.122622564,0.000008468884,0.000008428461,0.000014794481,0.000042948992,0.0000035016803,0.000009707044],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998141,0.0003312782,0.00048354725,0.00061495625,0.000275416,0.00015382093],"domain_scores_gemma":[0.99827117,0.00012493941,0.00026371295,0.0011666666,0.00010285121,0.000070687835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005836107,0.00018573145,0.00053413777,0.00012892013,0.00002961108,0.000034204055,0.0013711402,0.000087764885,0.000002047826],"category_scores_gemma":[0.000347761,0.00014902576,0.00005074146,0.00016438139,0.00020551532,0.00012861799,0.002533251,0.00027972992,1.5070641e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003283807,0.00037211637,0.48311198,0.0048685395,0.00021195493,0.000024939724,0.0047216155,0.0006816154,0.0023802745,0.47928265,0.00008382325,0.023932131],"study_design_scores_gemma":[0.00027111682,0.000043713884,0.16746457,0.001559592,0.000064293294,9.720961e-7,0.000044835087,0.7686274,0.0037186134,0.057771806,0.00013716111,0.00029591864],"about_ca_topic_score_codex":0.000104508246,"about_ca_topic_score_gemma":0.000029017481,"teacher_disagreement_score":0.76794577,"about_ca_system_score_codex":0.000021742528,"about_ca_system_score_gemma":0.00029094995,"threshold_uncertainty_score":0.6077094},"labels":[],"label_agreement":null},{"id":"W4410579275","doi":"10.1016/j.idm.2025.05.005","title":"State-space modelling for infectious disease surveillance data: Stochastic simulation techniques and structural change detection","year":2025,"lang":"en","type":"article","venue":"Infectious Disease Modelling","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Sanofi","keywords":"Infectious disease (medical specialty); Change detection; State space; Computer science; Data mining; Statistics; Artificial intelligence; Mathematics; Disease; Medicine","score_opus":0.040485485280795465,"score_gpt":0.31218182433303404,"score_spread":0.27169633905223856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410579275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028143546,0.0015732129,0.9672365,0.00015928828,0.0005473599,0.0014238699,0.000101925856,0.00078153523,0.000032717515],"genre_scores_gemma":[0.9467203,0.00014379388,0.052370783,0.00014256942,0.00024384307,0.0002622005,0.000043182612,0.000037374662,0.000035942136],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976115,0.00017224207,0.00039074977,0.0010992107,0.00024255905,0.00048370313],"domain_scores_gemma":[0.99774724,0.0004254694,0.00018231569,0.0010358612,0.00027007583,0.0003390173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055919593,0.000380727,0.00033894533,0.00037146255,0.0005918683,0.0004194709,0.0004367798,0.000103742284,7.012176e-7],"category_scores_gemma":[0.000093326045,0.000391643,0.00010656073,0.00053592393,0.00006513378,0.0014224709,0.00033257043,0.00023314648,8.756241e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010457597,0.00003630585,0.00038064882,0.00018491683,0.00003495579,0.0000058844666,0.0001796684,0.91012895,0.000014837038,0.0055437377,0.0000033379172,0.0833822],"study_design_scores_gemma":[0.00042205612,0.000040311144,0.00010701951,0.00008987904,0.000057839152,0.000002541121,0.0000012564841,0.8387281,0.00003835792,0.16001168,0.00015854252,0.00034244815],"about_ca_topic_score_codex":0.00020405914,"about_ca_topic_score_gemma":0.000056157172,"teacher_disagreement_score":0.9185768,"about_ca_system_score_codex":0.00013612045,"about_ca_system_score_gemma":0.00013971714,"threshold_uncertainty_score":0.99985355},"labels":[],"label_agreement":null},{"id":"W4410738626","doi":"10.1002/cjs.70009","title":"Random discrete probability measures based on a negative binomial process","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Negative binomial distribution; Statistics; Mathematics; Binomial (polynomial); Binomial distribution; Econometrics; Poisson distribution","score_opus":0.019258362624743813,"score_gpt":0.26696769923316316,"score_spread":0.24770933660841934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410738626","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041831468,0.00006221652,0.9952909,0.0014612015,0.00052253465,0.00017945844,0.000091721595,0.0000063537495,0.001967324],"genre_scores_gemma":[0.37015742,0.0000018787207,0.629093,0.00062403403,0.00004837988,0.000003735232,8.009381e-7,0.000004943209,0.00006579256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876314,0.00023458363,0.00035582724,0.00017454583,0.00021634542,0.0002555534],"domain_scores_gemma":[0.99825406,0.00040878952,0.00018750038,0.00023945022,0.0005066466,0.00040355066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082767557,0.00012990799,0.00026861264,0.00027327202,0.00015214649,0.00016263065,0.00056571705,0.000056052846,0.000011901318],"category_scores_gemma":[0.0012337147,0.00010343128,0.00006363854,0.00032547393,0.00011655606,0.00013822257,0.000009744897,0.0002802929,0.0000011894608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004265619,0.00008615437,0.0020592064,0.00023545299,0.00015624611,0.00057975994,0.002921038,0.006921153,0.000064278494,0.55940866,0.022074256,0.40506724],"study_design_scores_gemma":[0.0033158618,0.00040854298,0.0024338288,0.0003186304,0.000066717526,0.000022837685,0.000032524687,0.107978165,0.0011720401,0.88124496,0.002692484,0.00031342034],"about_ca_topic_score_codex":0.00040034868,"about_ca_topic_score_gemma":0.0034138162,"teacher_disagreement_score":0.4047538,"about_ca_system_score_codex":0.0001661591,"about_ca_system_score_gemma":0.004441754,"threshold_uncertainty_score":0.7879481},"labels":[],"label_agreement":null},{"id":"W4410778781","doi":"10.1111/2041-210x.70025","title":"Improved order selection method for hidden Markov models: A case study with movement data","year":2025,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Fisheries and Oceans Canada; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; Hidden Markov model; Model selection; Movement (music); Markov model; Artificial intelligence; Markov chain; Machine learning","score_opus":0.03580765663956218,"score_gpt":0.3840237380415576,"score_spread":0.3482160814019954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410778781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004901658,0.00019135572,0.9925954,0.00045253287,0.0003347327,0.0012702335,0.0000041306585,0.00006183319,0.00018816376],"genre_scores_gemma":[0.026804613,0.00000984199,0.97221035,0.00033673435,0.000026340827,0.00033939595,0.0000031801746,0.000008296741,0.0002612301],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966914,0.0017748908,0.00032061298,0.000829473,0.000061727435,0.00032187995],"domain_scores_gemma":[0.99832517,0.0007581592,0.00010059789,0.00063396327,0.00013602295,0.000046064935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065205647,0.00017542824,0.0003242367,0.00028668597,0.0002439983,0.000050004488,0.0004106839,0.0001658653,0.0000016307271],"category_scores_gemma":[0.00022106786,0.00014824505,0.00002121673,0.00069874135,0.000038575403,0.000491954,0.00042743376,0.00022120232,9.41419e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023188099,0.00049893296,0.0052966774,0.000064923326,0.00015232872,0.00004530764,0.00090395304,0.00031713033,0.00067178014,0.055817578,0.00020074751,0.93579876],"study_design_scores_gemma":[0.0012536631,0.0004774477,0.0025038787,0.000008688203,0.00006392568,0.00012531408,0.00027913292,0.84102046,0.00008267988,0.1539909,0.000054338405,0.00013959353],"about_ca_topic_score_codex":0.0006428744,"about_ca_topic_score_gemma":0.003637468,"teacher_disagreement_score":0.93565917,"about_ca_system_score_codex":0.0001355136,"about_ca_system_score_gemma":0.0001957871,"threshold_uncertainty_score":0.60452574},"labels":[],"label_agreement":null},{"id":"W4411036701","doi":"10.3390/jrfm18060304","title":"Dirichlet Mixed Process Integrated Bayesian Estimation for Individual Securities","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Dirichlet process; Estimation; Bayesian probability; Econometrics; Dirichlet distribution; Bayes estimator; Process (computing); Mathematics; Computer science; Economics; Statistics; Mathematical analysis; Programming language","score_opus":0.0073024988646830805,"score_gpt":0.260053197103493,"score_spread":0.2527506982388099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411036701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004991084,0.00071212876,0.9929166,0.00030016017,0.0004980404,0.00019575076,0.000008228547,0.000014435077,0.0003635818],"genre_scores_gemma":[0.31803694,0.00037472937,0.6811933,0.00021830047,0.000062401225,0.000014309123,0.0000015408249,0.0000037985449,0.00009467763],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991742,0.000058016518,0.0003254399,0.00014395628,0.00015553745,0.0001428967],"domain_scores_gemma":[0.9994143,0.00007563286,0.00022064478,0.00010933985,0.00013760524,0.00004244297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007965981,0.00010515338,0.0002047741,0.00027567358,0.00013914033,0.0001504172,0.00033515686,0.000051503477,7.1918157e-7],"category_scores_gemma":[0.00011190819,0.00008338328,0.00006930576,0.0003178458,0.000026357606,0.00029591928,0.000081095735,0.00013708942,1.5785392e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028749055,0.00003691115,0.000113426,0.00009338551,0.000019603634,0.000006441029,0.0006239515,0.000045309567,9.2723593e-7,0.18383704,0.0018324387,0.8133618],"study_design_scores_gemma":[0.0015701976,0.00025727606,0.0155220395,0.00037619052,0.00018606806,0.000012296719,0.000201843,0.03336824,0.0002674514,0.9095138,0.03851034,0.00021428458],"about_ca_topic_score_codex":0.0000032200878,"about_ca_topic_score_gemma":0.0000046608375,"teacher_disagreement_score":0.81314754,"about_ca_system_score_codex":0.000019096708,"about_ca_system_score_gemma":0.000059543523,"threshold_uncertainty_score":0.34002715},"labels":[],"label_agreement":null},{"id":"W4411140718","doi":"10.1007/s42519-025-00463-1","title":"On Predicting a Future Observation of the Inverse Gaussian Distribution","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Practice","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; York University","funders":"","keywords":"Mathematics; Inverse Gaussian distribution; Inverse; Distribution (mathematics); Applied mathematics; Gaussian; Statistics; Econometrics; Mathematical analysis; Geometry","score_opus":0.01680178048688536,"score_gpt":0.31817705795353673,"score_spread":0.3013752774666514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411140718","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019504979,0.00010345548,0.98963934,0.005528516,0.00045972932,0.00004961805,0.000012649327,0.0000035076248,0.0022527135],"genre_scores_gemma":[0.4260048,0.00012909243,0.571008,0.0024866506,0.00016812244,0.0000011169294,0.0000012954981,0.0000035518187,0.00019735066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810916,0.0013067315,0.00025993574,0.000081828206,0.0001695846,0.00007277857],"domain_scores_gemma":[0.9938213,0.005509823,0.00033877077,0.00013649814,0.00015186834,0.000041703966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035222706,0.000057421556,0.00011726017,0.000025945585,0.000101189624,0.000044643162,0.0001950435,0.000047406338,0.0000055168484],"category_scores_gemma":[0.006331078,0.00003402919,0.00003358124,0.00019697711,0.00006186878,0.0004203834,0.00005258132,0.00029924972,3.3980075e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003010581,0.000042415697,0.00003665503,0.00001970989,0.000024900955,0.0000063794414,0.00019272667,0.0000071195664,0.00011629966,0.9417039,0.0013031672,0.05624567],"study_design_scores_gemma":[0.00029423388,0.00015835604,0.0052571506,0.00012140106,0.00007572057,0.00008092302,0.00014878517,0.0026927607,0.00024108168,0.98440343,0.006484163,0.00004200903],"about_ca_topic_score_codex":0.0000012532455,"about_ca_topic_score_gemma":3.6600446e-7,"teacher_disagreement_score":0.4240543,"about_ca_system_score_codex":0.000018180664,"about_ca_system_score_gemma":0.00008210779,"threshold_uncertainty_score":0.75793487},"labels":[],"label_agreement":null},{"id":"W4411230494","doi":"10.1007/s11222-025-10650-6","title":"Unbalanced Longitudinal Data Clustering with a Copula Kernel Mixture Model","year":2025,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Copula (linguistics); Cluster analysis; Mathematics; Longitudinal data; Computer science; Statistics; Econometrics; Data mining","score_opus":0.02776951725213305,"score_gpt":0.3091943249308728,"score_spread":0.28142480767873973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411230494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064926,0.00023629205,0.99719477,0.00019702643,0.00014407413,0.00010139015,0.000056851837,0.00007083386,0.0013495175],"genre_scores_gemma":[0.2582183,0.0000138003315,0.74129605,0.00025301197,0.00002593305,0.0000010125129,0.000015226472,0.000006275226,0.00017041218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987954,0.000043464002,0.00019463309,0.0005548084,0.00014264576,0.00026908383],"domain_scores_gemma":[0.99898154,0.00012787178,0.00007843085,0.00066689245,0.00007474565,0.00007052636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031111675,0.00015951088,0.00021616602,0.00005770582,0.00021855206,0.00025399803,0.0006867189,0.0000450298,8.2395223e-7],"category_scores_gemma":[0.00003046111,0.00013267316,0.000010721327,0.00021214031,0.000048609152,0.00013917958,0.0009944029,0.00017662681,5.4129424e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015606447,0.000028650795,0.00074275455,0.00012919656,0.00005060138,0.000056764064,0.00030345103,0.0047285617,0.00006718425,0.6232634,0.0027764384,0.36783734],"study_design_scores_gemma":[0.00030465805,0.000025685456,0.00075083214,0.000113895614,0.00001749613,0.00002382234,0.0000065646445,0.95024276,0.000012412301,0.048219476,0.00012781566,0.00015457871],"about_ca_topic_score_codex":0.000025156576,"about_ca_topic_score_gemma":0.00002726395,"teacher_disagreement_score":0.9455142,"about_ca_system_score_codex":0.000014528628,"about_ca_system_score_gemma":0.0000979859,"threshold_uncertainty_score":0.5410254},"labels":[],"label_agreement":null},{"id":"W4411439993","doi":"10.1007/978-3-662-69359-9_442","title":"Generalized Quasi-Likelihood (GQL) Inferences, On","year":2025,"lang":"en","type":"book-chapter","venue":"International Encyclopedia of Statistical Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Econometrics; Mathematics","score_opus":0.015266545911471342,"score_gpt":0.29745780901517194,"score_spread":0.2821912631037006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411439993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000021580397,0.000040427934,0.50913435,0.0004683118,0.0012412443,0.000104896535,0.00014692996,0.000032655895,0.48882902],"genre_scores_gemma":[0.0015336345,0.00094238465,0.7850152,0.0007536625,0.00025249342,0.000018435932,0.00003473697,0.000017008346,0.21143244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961527,0.000040506104,0.00068134,0.0010063774,0.0017168646,0.0004021914],"domain_scores_gemma":[0.9974405,0.00072195305,0.0003316524,0.00065964763,0.0005855374,0.00026068997],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007953455,0.00035904467,0.00047089843,0.0005177259,0.000120922494,0.000169907,0.0032009054,0.00019212897,0.00043769748],"category_scores_gemma":[0.00069391297,0.00030850372,0.000118478405,0.00020240137,0.0007065981,0.0003424898,0.0006876404,0.00043892564,0.00007665182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008375902,0.000040877196,0.0000039053393,0.000012262706,0.00001730574,0.000017986007,0.000031459145,0.0000021167914,0.000013994212,0.73440284,0.0034367584,0.26201215],"study_design_scores_gemma":[0.00023423391,0.00016782993,0.00012423296,0.00021545893,0.000017187742,0.000006112217,7.153818e-7,0.008112607,0.000058358724,0.84621197,0.14451802,0.00033325603],"about_ca_topic_score_codex":0.000063329695,"about_ca_topic_score_gemma":0.000013320178,"teacher_disagreement_score":0.27739656,"about_ca_system_score_codex":0.000181058,"about_ca_system_score_gemma":0.0011991091,"threshold_uncertainty_score":0.9999367},"labels":[],"label_agreement":null},{"id":"W4411639396","doi":"10.1007/s13253-025-00703-8","title":"Bayesian Nonparametric Mixtures of Archimedean Copulas","year":2025,"lang":"en","type":"article","venue":"Journal of Agricultural Biological and Environmental Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Mathematics; Econometrics; Bayesian probability; Statistics; Copula (linguistics)","score_opus":0.009345191383725955,"score_gpt":0.2305796762722999,"score_spread":0.22123448488857395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411639396","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14397097,0.0008915103,0.8544802,0.00021115805,0.00012913079,0.000054186745,0.000034994606,0.000003203156,0.00022466065],"genre_scores_gemma":[0.6494917,0.0005805508,0.34974924,0.00008180263,0.00002275091,3.98424e-7,0.0000046093746,8.7173726e-7,0.000068061614],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990634,0.00010888318,0.00039667662,0.00013927017,0.00014918802,0.00014263214],"domain_scores_gemma":[0.99932843,0.00024040876,0.00023828243,0.00007858339,0.000017112563,0.00009718431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018839656,0.00012253608,0.00028329997,0.00006474109,0.000058775095,0.000029112214,0.00028873477,0.000076169454,0.000017471983],"category_scores_gemma":[0.000062514395,0.000060172275,0.00007232336,0.00016029109,0.00014089856,0.00008171158,0.00014118788,0.00017087845,8.716137e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009684416,0.00064854725,0.020266382,0.00006384017,0.00024047258,0.00007722302,0.00034114651,0.00007327369,0.13367373,0.098638475,0.0060920604,0.739788],"study_design_scores_gemma":[0.0008782648,0.0015123694,0.863929,0.00008007386,0.00006861135,0.00028885997,0.00012509963,0.0010589276,0.013893259,0.116407044,0.0014241174,0.00033438942],"about_ca_topic_score_codex":0.0000026718521,"about_ca_topic_score_gemma":3.9839438e-7,"teacher_disagreement_score":0.8436626,"about_ca_system_score_codex":0.000024454961,"about_ca_system_score_gemma":0.000008173577,"threshold_uncertainty_score":0.24537542},"labels":[],"label_agreement":null},{"id":"W4411990884","doi":"10.1007/s00362-025-01723-9","title":"Handling skewness and directional tails in model-based clustering","year":2025,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; National Science Foundation","keywords":"Skewness; Cluster analysis; Computer science; Econometrics; Statistics; Statistical physics; Mathematics; Artificial intelligence; Physics","score_opus":0.00959192071079757,"score_gpt":0.28385415082257015,"score_spread":0.2742622301117726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411990884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028470682,0.000064515916,0.98947424,0.0005291578,0.00014223563,0.000069669455,0.000006149955,0.00003913688,0.009390193],"genre_scores_gemma":[0.37412328,0.0000034007205,0.6252707,0.00044403353,0.000006874837,0.000009198111,0.0000010857277,0.000002650352,0.0001387866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922127,0.00006654416,0.00014233713,0.00028738062,0.00009859212,0.00018385971],"domain_scores_gemma":[0.999444,0.000327886,0.000014799092,0.00013240622,0.000018525852,0.000062398954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002506472,0.000085906846,0.00013043704,0.00008527489,0.000073426265,0.00007182678,0.00013700959,0.0000452834,0.000004979004],"category_scores_gemma":[0.00010610739,0.00007895251,0.000015900989,0.00017267784,0.000058322632,0.00007375132,0.00007532726,0.00011807156,8.829679e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014340509,0.000023102211,0.00020519854,0.0000459479,0.0000053949057,0.000012829793,0.000090057765,0.0048398827,0.00096391997,0.74079263,0.000049851165,0.25295684],"study_design_scores_gemma":[0.00026791968,0.000009720783,0.0016877137,0.000039165032,0.0000031596185,9.858351e-7,0.000003009688,0.85066783,0.000107477776,0.14698264,0.00014832651,0.00008207167],"about_ca_topic_score_codex":0.000021322245,"about_ca_topic_score_gemma":0.000046634865,"teacher_disagreement_score":0.84582794,"about_ca_system_score_codex":0.000032594307,"about_ca_system_score_gemma":0.000086260436,"threshold_uncertainty_score":0.321959},"labels":[],"label_agreement":null},{"id":"W4412049208","doi":"10.1016/j.neucom.2025.130768","title":"Fdmclust: Functional data model-based clustering using approximation of probability density for a random function in a reproducing Kernel Hilbert space framework","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reproducing kernel Hilbert space; Mathematics; Cluster analysis; Kernel (algebra); Probability density function; Pattern recognition (psychology); Variable kernel density estimation; Kernel embedding of distributions; Hilbert space; Kernel method; Artificial intelligence; Computer science; Statistics; Mathematical analysis; Discrete mathematics; Support vector machine","score_opus":0.0671315858041287,"score_gpt":0.31063126915663347,"score_spread":0.24349968335250477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412049208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051527396,0.00003984289,0.9463821,0.0004435792,0.00050173595,0.00093772187,0.0000024967917,0.00010040394,0.00006472318],"genre_scores_gemma":[0.43550315,2.7820278e-7,0.5642312,0.000179043,0.00005731846,0.0000105270465,0.000004957757,0.000007801263,0.000005739212],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974405,0.0002600905,0.00056904025,0.0012015307,0.00022444715,0.00030439414],"domain_scores_gemma":[0.9973554,0.0007377063,0.0002782162,0.0014027138,0.0001843106,0.000041650477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028004397,0.00019253841,0.00036421747,0.00021998746,0.00020513007,0.00009053035,0.0005715217,0.00012644185,4.26621e-7],"category_scores_gemma":[0.0010637026,0.00020153439,0.00008931179,0.0007035767,0.000034723613,0.00041186303,0.0006843279,0.0003018566,1.4606438e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033071038,0.00012692275,0.0013325743,0.0005207261,0.000015236818,9.542124e-7,0.00026458316,0.91511625,0.0050404016,0.019976068,0.000030371977,0.05724521],"study_design_scores_gemma":[0.0010554444,0.000022530581,0.0010412002,0.00029603322,0.000022122256,0.000003189705,0.0000037743944,0.9246263,0.0012757112,0.071509264,0.000009796837,0.0001346434],"about_ca_topic_score_codex":0.00004538595,"about_ca_topic_score_gemma":0.000015520203,"teacher_disagreement_score":0.38397574,"about_ca_system_score_codex":0.00009846471,"about_ca_system_score_gemma":0.00025662212,"threshold_uncertainty_score":0.82183343},"labels":[],"label_agreement":null},{"id":"W4412707181","doi":"10.1016/j.spl.2025.110507","title":"A mixture model for skewed mixed-type data","year":2025,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Killam Trusts; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Mathematics; Type (biology); Statistics; Mixed model; Mixture model; Generalized linear mixed model; Econometrics","score_opus":0.05268007306429695,"score_gpt":0.3265854740996846,"score_spread":0.27390540103538763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412707181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022826968,0.00007470629,0.9879451,0.009264488,0.0007628742,0.0007947016,0.0006218391,0.00013849536,0.00016956944],"genre_scores_gemma":[0.0018334736,0.0000063584916,0.99152094,0.0060410704,0.00004674392,0.000048572976,0.00016392684,0.000013406609,0.00032553112],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776584,0.00017595584,0.0003928834,0.0009936885,0.00022516794,0.0004464577],"domain_scores_gemma":[0.99668413,0.00051411986,0.000095825904,0.002391472,0.00021562107,0.00009883639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011322882,0.00023574698,0.00031199626,0.000085036205,0.00018065188,0.00018664138,0.002067605,0.00010136412,0.0000030485287],"category_scores_gemma":[0.0007549643,0.00022018143,0.00005597054,0.00036899443,0.00012722662,0.00030504787,0.0006945296,0.00022595956,0.0000044765056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023220933,0.000059884227,0.000029882814,0.00016666621,0.000035955818,0.000002658301,0.00018304026,0.000066523695,0.0008856937,0.821565,0.12479338,0.052188147],"study_design_scores_gemma":[0.00020023987,0.000016176276,0.00004972565,0.0000137074785,0.00002495567,8.25649e-7,2.0511021e-7,0.4364786,0.000079496436,0.56014377,0.0028574597,0.00013478404],"about_ca_topic_score_codex":0.000016919132,"about_ca_topic_score_gemma":0.000058888083,"teacher_disagreement_score":0.4364121,"about_ca_system_score_codex":0.00007793356,"about_ca_system_score_gemma":0.00030591138,"threshold_uncertainty_score":0.8978738},"labels":[],"label_agreement":null},{"id":"W4413128106","doi":"10.3390/stats8030073","title":"A Mixture Integer GARCH Model with Application to Modeling and Forecasting COVID-19 Counts","year":2025,"lang":"en","type":"article","venue":"Stats","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Ministry of Higher Education, Malaysia","keywords":"Coronavirus disease 2019 (COVID-19); Autoregressive conditional heteroskedasticity; 2019-20 coronavirus outbreak; Econometrics; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Integer (computer science); Mathematics; Computer science; Virology; Internal medicine; Medicine; Volatility (finance)","score_opus":0.03689804308090749,"score_gpt":0.3290919629729618,"score_spread":0.2921939198920543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413128106","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006680878,0.00008916818,0.99201894,0.001248573,0.000029928775,0.0001727645,0.0000031192485,0.00005112677,0.0057182694],"genre_scores_gemma":[0.2596033,0.000004459204,0.73754746,0.0021567098,0.000011814095,0.00002810965,0.0000011944783,0.0000046937225,0.00064224383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939555,0.000021619448,0.00008871608,0.00026477297,0.000096602314,0.00013274568],"domain_scores_gemma":[0.9995777,0.000040172705,0.000019449935,0.00021485219,0.00005519657,0.00009263383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024017978,0.00007213274,0.00008523411,0.00007287508,0.00007670116,0.000054765216,0.00017586356,0.000033773176,9.802452e-7],"category_scores_gemma":[0.00003252112,0.000057495214,0.000010720855,0.00020709187,0.000011909542,0.00008119343,0.00009341157,0.00008318022,0.0000024550993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003278067,0.000017451192,0.00004819425,0.00009799885,0.000015327007,0.0000040943187,0.002021002,0.06345176,0.0005545092,0.4590652,0.0023680392,0.47232366],"study_design_scores_gemma":[0.000093182396,0.000009982355,0.0000021107662,0.000017830616,0.0000026518314,0.000003004545,0.0000068976574,0.8935932,0.00003391536,0.10512004,0.0010535698,0.00006364874],"about_ca_topic_score_codex":0.000019370595,"about_ca_topic_score_gemma":0.000015137463,"teacher_disagreement_score":0.8301414,"about_ca_system_score_codex":0.00003276494,"about_ca_system_score_gemma":0.00013971525,"threshold_uncertainty_score":0.23445867},"labels":[],"label_agreement":null},{"id":"W4413129810","doi":"10.3390/stats8030071","title":"Individual Homogeneity Learning in Density Data Response Additive Models","year":2025,"lang":"en","type":"article","venue":"Stats","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Humanities and Social Science Fund of Ministry of Education of China; Ministry of Education of the People's Republic of China; National Natural Science Foundation of China","keywords":"Covariate; Estimator; Homogeneity (statistics); Bivariate analysis; Mathematics; Bivariate data; Additive model; Compositional data; Spline (mechanical); Cluster analysis; Euclidean space; Hierarchical clustering; Computer science; Statistics","score_opus":0.061666432780128115,"score_gpt":0.3340903468106706,"score_spread":0.2724239140305425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413129810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050901886,0.00015529305,0.94619673,0.000589037,0.00016096472,0.000121531295,0.0000610834,0.00008716537,0.0017262745],"genre_scores_gemma":[0.6053345,0.000023596194,0.39355025,0.00047089584,0.000016832937,0.000006674887,0.000027752374,0.0000053189187,0.0005641345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979456,0.0008185048,0.000182773,0.00057254935,0.00019631567,0.00028422422],"domain_scores_gemma":[0.99848825,0.0004293934,0.000050616043,0.00091656944,0.000054047156,0.00006113512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022578149,0.00011895832,0.00017806068,0.00018731179,0.000118513424,0.00010077278,0.0012959896,0.00007427529,0.0000041253224],"category_scores_gemma":[0.00031730466,0.00011778028,0.000025946852,0.0005338907,0.000042786643,0.0006453322,0.0014442608,0.00032575612,0.0000065564905],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002232248,0.0001067491,0.0009145272,0.000014717431,0.000047555135,0.00015173899,0.0032059574,0.00057015807,0.00051381014,0.14098725,0.0055158534,0.84774846],"study_design_scores_gemma":[0.0010390722,0.00010009711,0.058063995,0.00011469061,0.000022166643,0.000012350945,0.00010151983,0.47308332,0.003288759,0.45804533,0.005661768,0.0004669176],"about_ca_topic_score_codex":0.00006946307,"about_ca_topic_score_gemma":0.0001057689,"teacher_disagreement_score":0.8472815,"about_ca_system_score_codex":0.000041132276,"about_ca_system_score_gemma":0.00031392605,"threshold_uncertainty_score":0.48029402},"labels":[],"label_agreement":null},{"id":"W4413182436","doi":"10.1214/25-aap2202","title":"Unconditional large deviation principles for Dirichlet posterior and Bayesian bootstrap","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Probability","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Dirichlet distribution; Bayesian probability; Mathematics; Latent Dirichlet allocation; Statistics; Econometrics; Computer science; Artificial intelligence; Topic model; Mathematical analysis","score_opus":0.0836380330588424,"score_gpt":0.34682048480490246,"score_spread":0.26318245174606003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413182436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03693271,0.00010067282,0.9515759,0.007347667,0.000053092986,0.0008169875,0.000052898184,0.000039576564,0.003080538],"genre_scores_gemma":[0.7214141,0.000008855252,0.27691728,0.0014197726,0.000025337213,0.00013520171,0.000011960081,0.000004138443,0.000063379135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895936,0.00006981259,0.00030467435,0.00032707312,0.00012888883,0.00021017058],"domain_scores_gemma":[0.99891144,0.00027241165,0.00013344437,0.00050108123,0.00014005615,0.000041595507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018524898,0.000115919756,0.00019801516,0.00004516236,0.00015982082,0.00005496869,0.00042767677,0.00006301612,0.000004162379],"category_scores_gemma":[0.00006988374,0.00008218556,0.00006922512,0.00018936496,0.00009550506,0.00011630621,0.00019797796,0.000077489036,5.2180553e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005948902,0.00006818977,0.00013187746,0.0001230039,0.000024264664,5.630149e-8,0.00025433226,0.000015520855,0.0005484014,0.96062744,0.00037749804,0.037769925],"study_design_scores_gemma":[0.000271894,0.000040973686,0.011740016,0.00001785125,0.000010790105,7.186601e-7,0.000007791329,0.0049441177,0.010227766,0.9691165,0.003531047,0.000090546026],"about_ca_topic_score_codex":0.000002914678,"about_ca_topic_score_gemma":0.000009264128,"teacher_disagreement_score":0.6844814,"about_ca_system_score_codex":0.000009242316,"about_ca_system_score_gemma":0.00009753405,"threshold_uncertainty_score":0.33514297},"labels":[],"label_agreement":null},{"id":"W4413391710","doi":"10.1021/acs.jctc.5c00462","title":"k-Nearest Neighbor Adaptive Sampling, a Simple Tool to Efficiently Explore Conformational Space","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Theory and Computation","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Québec Consortium for Drug Discovery; Alliance de recherche numérique du Canada; Agence Nationale de la Recherche; Canadian Institute for Advanced Research","keywords":"Simple (philosophy); k-nearest neighbors algorithm; Computer science; Sampling (signal processing); Space (punctuation); Data mining; Artificial intelligence","score_opus":0.026368831409671122,"score_gpt":0.317349989613227,"score_spread":0.2909811582035559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413391710","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.168077,0.00008111241,0.8306732,0.0005406494,0.00012788636,0.00007343758,0.0000012326427,0.000012943261,0.00041254258],"genre_scores_gemma":[0.7062831,0.0000027112635,0.29289755,0.0007367954,0.000057979752,0.0000018446375,0.0000010977978,0.0000024621168,0.000016472304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991888,0.00008903829,0.0003154766,0.0001254016,0.0001608698,0.00012041895],"domain_scores_gemma":[0.99893826,0.00050173927,0.00015981174,0.00008403613,0.00022990754,0.00008624507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008689333,0.00009287641,0.00017328115,0.00011896703,0.000061001272,0.00010958906,0.00022426959,0.000049975923,0.000003851094],"category_scores_gemma":[0.00018819925,0.00007563367,0.00006417454,0.00024103482,0.00003262579,0.00030461507,0.00009703871,0.00015596388,0.0000019743059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019358497,0.000040596315,0.0000067909054,0.000013105658,0.000025365605,0.000002726601,0.0010793565,0.001433168,0.004867581,0.8513525,0.00042708876,0.14055811],"study_design_scores_gemma":[0.0005851887,0.00013662677,0.00021162996,0.00009321763,0.000016483507,0.000041369032,0.00009114064,0.055150826,0.015938604,0.92678356,0.0008254859,0.0001258628],"about_ca_topic_score_codex":3.3749933e-7,"about_ca_topic_score_gemma":3.1008735e-8,"teacher_disagreement_score":0.5382061,"about_ca_system_score_codex":0.000030537143,"about_ca_system_score_gemma":0.000082774175,"threshold_uncertainty_score":0.30842516},"labels":[],"label_agreement":null},{"id":"W4413681322","doi":"10.1007/s10994-025-06858-2","title":"Cluster weighted models for functional data","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster (spacecraft); Computer science; Data mining; Artificial intelligence; Programming language","score_opus":0.04294268084520292,"score_gpt":0.30349957117040394,"score_spread":0.260556890325201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413681322","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007104886,0.00038932468,0.987549,0.0035344888,0.0004071737,0.00015820992,0.000007527909,0.00016863519,0.0077145663],"genre_scores_gemma":[0.043013554,0.000009465713,0.94621456,0.0017893106,0.00011360999,0.000022147575,0.00009662359,0.000010986105,0.008729733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890184,0.00012819053,0.00016366347,0.00047313428,0.00012070012,0.00021248712],"domain_scores_gemma":[0.99893737,0.00024769982,0.000048939728,0.0006692668,0.00005522738,0.000041516305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007454389,0.000113637616,0.00014252131,0.00010878488,0.00023325543,0.00012541427,0.00085631845,0.000059461905,0.0000125461665],"category_scores_gemma":[0.00008569294,0.000097614386,0.000048518807,0.00023526726,0.000014480424,0.0004757016,0.0006883919,0.00021486632,0.000005034952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028468174,0.000031314605,0.000232303,0.00003419262,0.000043272103,0.0000013989239,0.00011709468,0.0057890154,0.00013057371,0.587388,0.0113401245,0.39486426],"study_design_scores_gemma":[0.00036821573,0.000015894635,0.00006126173,0.000012832466,0.000009034032,0.0000025384497,0.0000011169794,0.8125688,0.000037338406,0.12994634,0.056890566,0.00008610082],"about_ca_topic_score_codex":0.000018601155,"about_ca_topic_score_gemma":0.00000815887,"teacher_disagreement_score":0.80677974,"about_ca_system_score_codex":0.000016671846,"about_ca_system_score_gemma":0.000059736583,"threshold_uncertainty_score":0.3980599},"labels":[],"label_agreement":null},{"id":"W4413872284","doi":"10.5267/j.ijiec.2025.7.001","title":"Bayesian inference for zero-inflated negative binomial lindley model of overdispersed count data with excess zeros","year":2025,"lang":"en","type":"article","venue":"International Journal of Industrial Engineering Computations","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Count data; Negative binomial distribution; Bayesian probability; Statistics; Mathematics; Inference; Bayesian inference; Zero-inflated model; Econometrics; Zero (linguistics); Binomial (polynomial); Binomial distribution; Statistical inference; Quasi-likelihood; Poisson distribution; Computer science; Poisson regression; Artificial intelligence","score_opus":0.050390455601554265,"score_gpt":0.3227864682970722,"score_spread":0.27239601269551794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413872284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005917159,0.000019996447,0.99158686,0.0008059164,0.0012559912,0.00020877256,0.00011347705,0.000026106914,0.0000656882],"genre_scores_gemma":[0.5939793,0.000004425889,0.40578255,0.00004458176,0.00014860998,0.0000037435723,0.000013358439,0.0000072555235,0.00001616507],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985495,0.00003693679,0.0006530552,0.00022079296,0.0003881672,0.00015155428],"domain_scores_gemma":[0.99743015,0.00068569416,0.00044199626,0.00028591976,0.0010785762,0.00007766588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047549335,0.00015887366,0.00030686447,0.00045895897,0.000049499275,0.00014947279,0.0016216406,0.00011201424,0.0000016517146],"category_scores_gemma":[0.0005563738,0.00013897519,0.0000848417,0.00035912584,0.000038527618,0.00070654764,0.00021256127,0.00031787928,1.9306893e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013035334,0.0000722394,0.00005987943,0.000009779951,0.00035259375,0.00000623528,0.00028380423,0.93224406,0.0010806646,0.050481822,0.00043040063,0.014848192],"study_design_scores_gemma":[0.0023301279,0.0001030054,0.000062434745,0.00032308022,0.00004396693,0.0000114527,0.00000991761,0.9865751,0.0017702306,0.00853356,0.00011182336,0.00012526108],"about_ca_topic_score_codex":0.000021019941,"about_ca_topic_score_gemma":0.0000024293543,"teacher_disagreement_score":0.58806217,"about_ca_system_score_codex":0.000109031906,"about_ca_system_score_gemma":0.00086299155,"threshold_uncertainty_score":0.56672436},"labels":[],"label_agreement":null},{"id":"W4413964683","doi":"10.2139/ssrn.5400512","title":"An Explicit Expression for the Expectation of a Product of Quadratic Forms in Multivariate Normal Random Variables","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Expression (computer science); Mathematics; Multivariate statistics; Multivariate normal distribution; Product (mathematics); Statistics; Quadratic equation; Random variable; Econometrics; Computer science; Geometry","score_opus":0.01403925193459583,"score_gpt":0.3016596072596959,"score_spread":0.2876203553251001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413964683","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011152013,0.0022546272,0.9848888,0.00028846864,0.00035112057,0.0009785318,0.0000069895113,0.000015406104,0.00006406347],"genre_scores_gemma":[0.76646763,0.0008046523,0.2323289,0.000019041805,0.00012673426,0.00015217073,0.0000051299317,0.000012082123,0.00008362624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970516,0.00044420338,0.0008180524,0.0004220543,0.0002995984,0.0009644943],"domain_scores_gemma":[0.9977384,0.00044123788,0.0008175469,0.0007173643,0.00024466042,0.000040776213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054084715,0.00024265928,0.00054497516,0.00028234284,0.00012110145,0.00006984069,0.0014585208,0.0001566649,0.0000016046769],"category_scores_gemma":[0.00021452349,0.00015479857,0.00022039431,0.0002552199,0.000027984808,0.00039835923,0.00025086803,0.0014661727,6.903138e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010582465,0.0004997256,0.00016923004,0.00049855997,0.00032310298,0.0000012039814,0.010744856,0.013770803,0.043746118,0.7218407,0.000025982457,0.20732148],"study_design_scores_gemma":[0.0024168233,0.00027653654,0.0001540182,0.00047542824,0.00006220939,0.00002108446,0.00036383697,0.1548288,0.023167018,0.81801057,0.000012378268,0.00021127805],"about_ca_topic_score_codex":0.00017204248,"about_ca_topic_score_gemma":0.00022041495,"teacher_disagreement_score":0.75531566,"about_ca_system_score_codex":0.0002224423,"about_ca_system_score_gemma":0.0030353863,"threshold_uncertainty_score":0.63698727},"labels":[],"label_agreement":null},{"id":"W4414140358","doi":"10.1002/pst.70022","title":"Finding the Optimal Number of Splits and Repetitions in Double Cross‐Fitting Targeted Maximum Likelihood Estimators","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Estimator; Range (aeronautics); Sample size determination; Selection (genetic algorithm); Maximum likelihood; Sample (material); Design of experiments","score_opus":0.03203732618303272,"score_gpt":0.3995152458703245,"score_spread":0.36747791968729177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414140358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013132475,0.00017964459,0.98325986,0.0006163221,0.00021752997,0.00017892465,0.000040496056,0.0000333309,0.0023414004],"genre_scores_gemma":[0.26116467,0.000039255392,0.73842585,0.0002541282,0.000015464293,0.0000105903955,0.0000025879708,0.000006017354,0.000081455764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872583,0.00011509825,0.0003653578,0.00029429712,0.00016783754,0.00033160605],"domain_scores_gemma":[0.9988456,0.0006691689,0.000071593866,0.00023570785,0.00008195681,0.00009599526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007271021,0.00012764637,0.00018894987,0.000058900805,0.00014498904,0.00013317355,0.0003402099,0.00005812763,0.000034172186],"category_scores_gemma":[0.00019299205,0.00010176058,0.000028792972,0.00043057647,0.00016593462,0.00013647298,0.00028737288,0.00030673222,0.000005163801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023930512,0.00005945152,0.009803436,0.00008800824,0.000021271206,0.000020229183,0.00029244088,0.000080234124,0.0002231066,0.9321417,0.00025309782,0.056993097],"study_design_scores_gemma":[0.0016065035,0.00002151482,0.011991146,0.0001166481,0.00004966691,0.000028440174,0.000014863736,0.59460175,0.004889579,0.38423657,0.0021977045,0.0002456334],"about_ca_topic_score_codex":0.000028466331,"about_ca_topic_score_gemma":0.000003323551,"teacher_disagreement_score":0.5945215,"about_ca_system_score_codex":0.000030468545,"about_ca_system_score_gemma":0.000082148,"threshold_uncertainty_score":0.41496763},"labels":[],"label_agreement":null},{"id":"W4414149740","doi":"10.1016/j.jmva.2025.105507","title":"Tree Pólya Splitting distributions for multivariate count data","year":2025,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Count data; Multivariate statistics; Tree (set theory); Multivariate analysis; Distribution (mathematics)","score_opus":0.04255664234839855,"score_gpt":0.3625917236788698,"score_spread":0.32003508133047126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414149740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005709776,0.00030548382,0.9949317,0.0030175028,0.00044591978,0.00015119353,0.00010922658,0.000029146182,0.0004388748],"genre_scores_gemma":[0.1820354,0.000041978215,0.8171768,0.00019209438,0.00015182735,0.000005009366,0.000037695117,0.0000075286302,0.00035167122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975166,0.000286824,0.0010200517,0.00048524485,0.00033309392,0.0003582038],"domain_scores_gemma":[0.99617434,0.0008761687,0.0008121625,0.0013023979,0.00068894844,0.00014600562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034019025,0.00021594884,0.0007377855,0.00066670025,0.0002804397,0.00028498267,0.0023214752,0.00012039179,0.00001036344],"category_scores_gemma":[0.0010720587,0.00016912827,0.0005816978,0.0020320085,0.000036915306,0.0008587534,0.000526436,0.00028111518,0.0000016500162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018917104,0.00081299955,0.001244946,0.00008999724,0.012877061,0.00008258858,0.000877197,0.0018551686,0.010261518,0.49196824,0.006038637,0.4737025],"study_design_scores_gemma":[0.0015066614,0.00005793021,0.0077991216,0.0000727528,0.0029798665,0.000011491691,0.000032829816,0.95027435,0.00077573216,0.02476906,0.011477775,0.00024242037],"about_ca_topic_score_codex":0.0001396546,"about_ca_topic_score_gemma":0.00004518684,"teacher_disagreement_score":0.9484192,"about_ca_system_score_codex":0.00009509662,"about_ca_system_score_gemma":0.00023942027,"threshold_uncertainty_score":0.68968505},"labels":[],"label_agreement":null},{"id":"W4414179287","doi":"10.1007/s11222-025-10720-9","title":"Finite mixtures of multivariate Poisson-log normal factor analyzers for clustering count data","year":2025,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Princess Margaret Cancer Centre; McMaster University; University of Toronto; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Mixture model; Context (archaeology); Multivariate statistics; Multivariate normal distribution; Count data; Expectation–maximization algorithm; Gaussian","score_opus":0.035203899328216194,"score_gpt":0.3331413392277453,"score_spread":0.2979374398995291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414179287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005397334,0.00019361942,0.99797297,0.00012028706,0.00038631744,0.00014942727,0.00041954764,0.00002754244,0.00019055002],"genre_scores_gemma":[0.26254174,0.000011058153,0.7371966,0.0001385528,0.000030148283,0.0000010703552,0.000026261863,0.000004760649,0.00004978856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891603,0.00005693759,0.0003046477,0.00037868912,0.00010886369,0.00023485736],"domain_scores_gemma":[0.99838614,0.0008527841,0.00014546275,0.00044923727,0.000114104994,0.000052255524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004526012,0.00012859922,0.00024133704,0.00008758465,0.00016459991,0.00012225253,0.00061031646,0.000047095557,0.0000014079004],"category_scores_gemma":[0.00020120686,0.00011789725,0.000024563633,0.00015573148,0.000042160245,0.00011020331,0.00072639395,0.000093543415,1.4495187e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019126239,0.000034330373,0.00021682878,0.000294954,0.000094103096,0.0000062658637,0.00080018514,0.0011123752,0.0009387625,0.35386804,0.0008803496,0.64173466],"study_design_scores_gemma":[0.00035051082,0.000035717698,0.00096764887,0.0000688609,0.000019605288,0.0000016240147,0.000008291764,0.9771813,0.00027477831,0.020183098,0.0007875829,0.000120965065],"about_ca_topic_score_codex":0.00008748856,"about_ca_topic_score_gemma":0.000019605839,"teacher_disagreement_score":0.9760689,"about_ca_system_score_codex":0.000010507956,"about_ca_system_score_gemma":0.00007178198,"threshold_uncertainty_score":0.48077103},"labels":[],"label_agreement":null},{"id":"W4414222720","doi":"10.1016/j.eswa.2025.129739","title":"Clustering-based brain functional segmentation via deep collapsed nonparametric von Mises-Fisher mixture models","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Mixture model; Autoencoder; Generative model; Pattern recognition (psychology); Segmentation; Functional magnetic resonance imaging; Bayes' theorem; Inference; Prior probability","score_opus":0.014589231231754207,"score_gpt":0.26399298747321814,"score_spread":0.24940375624146394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414222720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030896033,0.0012287262,0.9902065,0.0021539573,0.0003593061,0.0017859411,0.0000069278367,0.000286957,0.0039408347],"genre_scores_gemma":[0.23962454,0.000008332161,0.7490047,0.0029961977,0.0002017089,0.005535101,0.00006536747,0.000035105735,0.0025289028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979518,0.00019055388,0.00041247212,0.00073200266,0.0003949531,0.00031818767],"domain_scores_gemma":[0.9981656,0.00029374397,0.00018306776,0.0009554457,0.00025986892,0.00014228554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035009877,0.00027597332,0.000299244,0.00038793622,0.0003646175,0.00028782382,0.0005863351,0.00016400687,0.000010810868],"category_scores_gemma":[0.000013328242,0.00023466199,0.00008453901,0.0018986727,0.0000504661,0.00037960376,0.00007359284,0.00015980027,0.00001930459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031470708,0.0014593553,0.00046889036,0.0007290696,0.00057762046,0.000017914308,0.0025808658,0.32685095,0.02485755,0.2964682,0.10626489,0.23940998],"study_design_scores_gemma":[0.00093538885,0.00005277767,0.000100504905,0.00006187747,0.00001675735,0.000016365919,0.000043976594,0.97955716,0.00076034135,0.002859268,0.015292288,0.00030330793],"about_ca_topic_score_codex":0.000108332,"about_ca_topic_score_gemma":0.00005092833,"teacher_disagreement_score":0.6527062,"about_ca_system_score_codex":0.00019794473,"about_ca_system_score_gemma":0.00023406342,"threshold_uncertainty_score":0.95692384},"labels":[],"label_agreement":null},{"id":"W4414252035","doi":"10.1080/0020739x.2025.2543835","title":"A gentle introduction to the Poisson process assumptions in a probability course","year":2025,"lang":"en","type":"article","venue":"International Journal of Mathematical Education in Science and Technology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Course (navigation); Process (computing); Calculus (dental); Poisson distribution; Poisson process; Applied probability; Probability theory","score_opus":0.011775685613157545,"score_gpt":0.37397420014164257,"score_spread":0.362198514528485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414252035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14472172,0.000075590215,0.6245817,0.22953245,0.000566222,0.00014140215,1.7151278e-7,0.000007649076,0.0003731308],"genre_scores_gemma":[0.8227642,0.00001720769,0.17654116,0.00049827085,0.00007590469,0.00003042167,6.379173e-8,0.0000013067422,0.00007142911],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990235,0.000034480807,0.00032946054,0.00017712952,0.00032435407,0.00011110399],"domain_scores_gemma":[0.9987711,0.00006809812,0.000103163446,0.00018960371,0.000836219,0.000031850766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021147712,0.000050863433,0.000102888,0.00082892866,0.000045498666,0.00009575607,0.0010592979,0.000041973966,0.000004963151],"category_scores_gemma":[0.0016591243,0.000034405573,0.000013597521,0.0015622873,0.00020076944,0.00035949773,0.00012697579,0.0001873258,0.0000026140037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003991752,0.0002490965,0.0006669794,0.000008930319,0.0000033310826,9.2498254e-7,0.00063517905,0.00001626825,0.0003671451,0.83460057,0.0003717671,0.16307579],"study_design_scores_gemma":[0.00011637945,0.00003363673,0.0028546187,0.00010113575,0.000002547811,0.00009025872,0.0003260997,0.002569468,0.0011143865,0.99174905,0.0010028942,0.000039538452],"about_ca_topic_score_codex":0.0000027333085,"about_ca_topic_score_gemma":0.000011448259,"teacher_disagreement_score":0.67804253,"about_ca_system_score_codex":0.00016136019,"about_ca_system_score_gemma":0.0013207089,"threshold_uncertainty_score":0.23428808},"labels":[],"label_agreement":null},{"id":"W4414540631","doi":"10.1287/mnsc.2023.00218","title":"A Global Optimization Algorithm for <i>K</i> -Center Clustering of One Billion Samples","year":2025,"lang":"en","type":"article","venue":"Management Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Global optimization; Branch and bound; Convergence (economics); Heuristic; Function (biology); Acceleration","score_opus":0.021057572578634606,"score_gpt":0.2898229472542968,"score_spread":0.2687653746756622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414540631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022971972,0.00003336071,0.989857,0.00046473442,0.00040359612,0.00037822136,0.000005660383,0.000051517636,0.008782913],"genre_scores_gemma":[0.007429024,0.0000267635,0.9918437,0.00043568015,0.000011004706,0.000027029893,0.0000012872,0.0000019822114,0.00022353067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988648,0.000022143371,0.00019179314,0.00041947042,0.000259616,0.0002421473],"domain_scores_gemma":[0.99937886,0.00002203611,0.000071373935,0.0004046493,0.00008515382,0.000037900623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007987762,0.000083330895,0.00011610691,0.0001943326,0.00015153848,0.00014057316,0.0009785298,0.00001981011,0.0000017285316],"category_scores_gemma":[0.000016500868,0.00007699279,0.00004244097,0.0014542597,0.00010906705,0.0004300001,0.0006167444,0.000019263898,5.4593386e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026396765,0.00006251888,0.00005968629,0.000054583666,0.000009485435,4.41105e-7,0.000030933945,0.0060004084,0.000072209754,0.24360009,0.0001859429,0.7499211],"study_design_scores_gemma":[0.0003585497,0.000029256995,0.00038569118,0.00006897722,0.000009318957,5.401246e-7,0.0000076119304,0.97595334,0.00046907843,0.021575069,0.0010597056,0.000082870814],"about_ca_topic_score_codex":0.000009416636,"about_ca_topic_score_gemma":0.000002298659,"teacher_disagreement_score":0.96995294,"about_ca_system_score_codex":0.00006533171,"about_ca_system_score_gemma":0.000029501613,"threshold_uncertainty_score":0.31396747},"labels":[],"label_agreement":null},{"id":"W4414579925","doi":"10.1002/bimj.70078","title":"A New Logistic Model with Subject‐Specific and Serially Correlated Time‐Specific Distribution‐Free Random Effects on the Unit Interval for Longitudinal Binary Data","year":2025,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Fredericton; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Random effects model; Multiplicative function; Unit interval; Binary data; Logistic regression; Interval (graph theory); Parametric statistics; Interpretation (philosophy); Mixed model; Fixed effects model","score_opus":0.07264096169874608,"score_gpt":0.30569108823568714,"score_spread":0.23305012653694107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414579925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016266981,0.0017523773,0.9912572,0.0040277317,0.00057835405,0.0004735325,0.00008623004,0.000056037792,0.00014182134],"genre_scores_gemma":[0.25733984,0.0005968638,0.7391425,0.0005805891,0.0007169068,0.000027159425,0.00010640388,0.000040764655,0.0014490178],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978297,0.00034144276,0.00040075203,0.00060426904,0.0004039777,0.00041989356],"domain_scores_gemma":[0.9958188,0.0024519146,0.00017953222,0.0010963712,0.00019023685,0.00026313332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017122364,0.00027135067,0.00041736453,0.0005897699,0.0004479625,0.00072734134,0.0022064482,0.00013748195,0.000011550507],"category_scores_gemma":[0.0007556482,0.00015689823,0.00010063822,0.0030641134,0.00012033939,0.0003200781,0.00070491695,0.0005100353,0.0000073198303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005145329,0.00043334643,0.00020959496,0.000076050004,0.00049374707,0.0002804208,0.00010096726,0.00030157244,0.0026137126,0.20491458,0.4040182,0.3814125],"study_design_scores_gemma":[0.013913155,0.0022007294,0.004100248,0.0005292574,0.00020404792,0.0006316074,0.000007307223,0.8645102,0.0005808146,0.098426424,0.014224874,0.00067134935],"about_ca_topic_score_codex":0.000004107334,"about_ca_topic_score_gemma":6.7612143e-7,"teacher_disagreement_score":0.86420864,"about_ca_system_score_codex":0.000097704666,"about_ca_system_score_gemma":0.00029169823,"threshold_uncertainty_score":0.7013769},"labels":[],"label_agreement":null},{"id":"W4414631669","doi":"10.48550/arxiv.2504.15558","title":"Dynamical mean-field analysis of adaptive Langevin diffusions: Replica-symmetric fixed point and empirical Bayes","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Abdus Salam International Centre for Theoretical Physics; National Science Foundation","keywords":"Langevin dynamics; Limit (mathematics); Langevin equation; Bayesian probability; Posterior probability; Scalar (mathematics); Dynamical systems theory; Trajectory; Kalman filter; Fixed point","score_opus":0.05557580835663348,"score_gpt":0.33298949417023155,"score_spread":0.27741368581359804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414631669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15589356,0.0010117234,0.8383481,0.001978156,0.00023419187,0.00028189673,0.000047262467,0.00010656977,0.0020985361],"genre_scores_gemma":[0.68825334,0.00041236737,0.30949393,0.0011831074,0.00006579517,0.000057778732,0.000024487546,0.000014263825,0.0004949458],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967564,0.00045456502,0.00070378074,0.0013399451,0.0003834736,0.00036184944],"domain_scores_gemma":[0.9960708,0.0013339483,0.00035713406,0.001835829,0.00020290428,0.00019938782],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008484649,0.00039598352,0.0011567834,0.0011578185,0.000096701995,0.000075791475,0.0012147207,0.00052967883,0.000027565766],"category_scores_gemma":[0.0006677038,0.00033230358,0.00051765214,0.002307021,0.000091072594,0.00012154013,0.003191793,0.00085443066,0.0000037676064],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025672078,0.0014805285,0.445218,0.00068288296,0.008057362,0.00017245045,0.006241963,0.00030543568,0.0016452371,0.16849253,0.0055631883,0.3618837],"study_design_scores_gemma":[0.0007182289,0.00037369475,0.42999482,0.00046649075,0.0025100058,0.000009253505,0.00008604768,0.52256304,0.0019442288,0.03963755,0.0005101087,0.0011865518],"about_ca_topic_score_codex":0.0003434879,"about_ca_topic_score_gemma":0.00013355093,"teacher_disagreement_score":0.5323598,"about_ca_system_score_codex":0.00007948669,"about_ca_system_score_gemma":0.0001767408,"threshold_uncertainty_score":0.9999129},"labels":[],"label_agreement":null},{"id":"W4415248400","doi":"10.48550/arxiv.2505.03582","title":"Maximum likelihood estimation for the $λ$-exponential family","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exponential family; Maximum likelihood; Dirichlet distribution; Monotone polygon; Regular polygon; Expectation–maximization algorithm; Maximum likelihood sequence estimation; Duality (order theory); Exponential distribution","score_opus":0.046737657529482855,"score_gpt":0.30929371889767554,"score_spread":0.2625560613681927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415248400","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049972334,0.0009779814,0.98412687,0.0035599477,0.004065547,0.0009451996,0.00002613627,0.00021311983,0.001087983],"genre_scores_gemma":[0.10505004,0.0001476401,0.8910641,0.0018255494,0.0005265784,0.00045612486,0.000031378717,0.00002290928,0.0008756947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980277,0.00014280378,0.0003894278,0.0007957383,0.00024630464,0.0003980432],"domain_scores_gemma":[0.99763525,0.00038018732,0.00021655446,0.0015243869,0.00016519256,0.000078420075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008594435,0.00031771464,0.00033685195,0.00011119559,0.00026812303,0.00024694426,0.00202302,0.00031441118,0.0000050744497],"category_scores_gemma":[0.00011943601,0.00023742659,0.000310488,0.0001945393,0.00004914806,0.00017400042,0.0015411772,0.0005313625,0.000028079343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002948682,0.00011885919,0.00070991926,0.00031707322,0.00022412528,0.0000066214157,0.0009281185,0.0008892893,0.0006181232,0.05953256,0.0080499435,0.9285759],"study_design_scores_gemma":[0.0005722487,0.000064256456,0.011898047,0.00022936384,0.00017056878,0.0000039016913,0.0000121938565,0.42680764,0.0019991752,0.54868096,0.008982532,0.000579106],"about_ca_topic_score_codex":0.00007755481,"about_ca_topic_score_gemma":0.0000072084044,"teacher_disagreement_score":0.92799675,"about_ca_system_score_codex":0.00005593444,"about_ca_system_score_gemma":0.0003313813,"threshold_uncertainty_score":0.9681975},"labels":[],"label_agreement":null},{"id":"W4415357184","doi":"10.3390/math13203341","title":"Bayesian Approach to Simultaneous Variable Selection and Estimation in a Linear Regression Model with Applications in Driver Telematics","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Telematics; Feature selection; Bayesian probability; Selection (genetic algorithm); Variable (mathematics); Model selection; Estimation; Linear regression","score_opus":0.010691160253841144,"score_gpt":0.2732125250102268,"score_spread":0.26252136475638566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415357184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019149671,0.000014171234,0.99489087,0.00011809204,0.000010396038,0.0007039225,8.618697e-7,0.000057990357,0.0022887448],"genre_scores_gemma":[0.0973531,0.0000025882441,0.9021288,0.000073142844,0.0000037858351,0.000120027726,0.0000017997353,0.000008621949,0.00030809853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990639,0.000042534004,0.00028351645,0.0002933365,0.00013997691,0.00017672461],"domain_scores_gemma":[0.9993173,0.00019033437,0.00006988757,0.00031669458,0.000054794084,0.000050990722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037757243,0.00013970427,0.00022757705,0.0002675892,0.00006684239,0.00006818574,0.00022365889,0.00008775016,3.940645e-7],"category_scores_gemma":[0.0000851218,0.000107546315,0.00001185505,0.0010600542,0.000014235275,0.00015302462,0.00009090694,0.0001453334,9.079528e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005057225,0.000329681,0.00009050657,0.0003748652,0.0000063200723,0.000001120983,0.0034939842,0.44991356,0.0002129608,0.53438455,0.000032969147,0.011154434],"study_design_scores_gemma":[0.00016584099,0.000015807622,0.000010837507,0.00017110798,0.000006563739,0.0000054485154,0.000032086085,0.79331833,0.00012740167,0.20603997,0.000014289616,0.00009233578],"about_ca_topic_score_codex":0.000008525861,"about_ca_topic_score_gemma":0.000015489364,"teacher_disagreement_score":0.34340474,"about_ca_system_score_codex":0.00006476933,"about_ca_system_score_gemma":0.00007442441,"threshold_uncertainty_score":0.43856114},"labels":[],"label_agreement":null},{"id":"W4415371968","doi":"10.1002/cjs.70024","title":"An observation‐driven state‐space model for claims size modelling","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea","keywords":"Class (philosophy); Variance (accounting); Popularity; Work (physics); Statistical model; Mathematical model; Outcome (game theory)","score_opus":0.04187778621466294,"score_gpt":0.2822576087166886,"score_spread":0.24037982250202566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415371968","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006712924,0.00011302406,0.9971256,0.0012067513,0.00043291287,0.00012617157,0.00021590026,0.000009215,0.00009908229],"genre_scores_gemma":[0.061499637,0.000024318602,0.9368277,0.00077047374,0.00004770671,0.0000028698819,0.0000034794716,0.000011472908,0.00081231294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989023,0.00006118296,0.00039829893,0.00017568689,0.0001373933,0.0003251105],"domain_scores_gemma":[0.9980256,0.00030097077,0.00020000433,0.00029023562,0.00068746146,0.00049573055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004818116,0.00012730049,0.00023296165,0.00019081151,0.00019690755,0.00022306234,0.00070410076,0.000064702595,0.0000034257218],"category_scores_gemma":[0.00013592103,0.00012506926,0.000056017532,0.00022256664,0.000043466243,0.000413155,0.000012791734,0.00019193291,5.540538e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006698422,0.000009674355,0.00007074339,0.000025375373,0.000026331536,0.000024597555,0.0010272436,0.36129603,0.000057190457,0.60644954,0.0079118,0.02309479],"study_design_scores_gemma":[0.00018742266,0.00004550066,0.00005019293,0.000027302032,0.000014297655,0.000004850237,0.000009189772,0.6237367,0.000028890629,0.37462336,0.0011929561,0.000079345795],"about_ca_topic_score_codex":0.00036634426,"about_ca_topic_score_gemma":0.0028838795,"teacher_disagreement_score":0.26244068,"about_ca_system_score_codex":0.00014486889,"about_ca_system_score_gemma":0.002827765,"threshold_uncertainty_score":0.51001763},"labels":[],"label_agreement":null},{"id":"W4415853390","doi":"10.1007/s00357-025-09526-1","title":"Extending Cluster-Weighted Factor Analyzers for Multivariate Prediction and Interpretability","year":2025,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Canada Excellence Research Chairs, Government of Canada","keywords":"Interpretability; Disjoint sets; Multivariate statistics; Maximization; Latent variable; Set (abstract data type); Support vector machine; Expectation–maximization algorithm; Factor analysis","score_opus":0.028036922328684596,"score_gpt":0.33200583274420276,"score_spread":0.30396891041551816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415853390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020289145,0.00013856652,0.9768464,0.0017022856,0.00063078065,0.00016564602,0.0000044373337,0.0000183378,0.00020438098],"genre_scores_gemma":[0.65802133,0.000025565387,0.34178478,0.00006308432,0.000045932757,0.0000043736904,6.421052e-7,0.0000023400498,0.000051920662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990617,0.00014229857,0.00041955608,0.0001706385,0.000110489935,0.000095307165],"domain_scores_gemma":[0.9989172,0.0002571135,0.0003328927,0.00019117698,0.00024739665,0.0000542027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008680017,0.000075982665,0.00016604863,0.00020191782,0.000078152894,0.00009880346,0.00022622659,0.000068597124,0.0000015489297],"category_scores_gemma":[0.0001947672,0.000059643746,0.00008151997,0.00019537385,0.00002605014,0.0005313146,0.0000349124,0.00012197997,1.5173957e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012551295,0.00009356703,0.0026890107,0.00007781176,0.0000921218,5.028776e-7,0.00084713515,0.000010474872,0.06269575,0.09184448,0.00043924115,0.8410844],"study_design_scores_gemma":[0.0008622014,0.00012504036,0.10375128,0.000111554764,0.00004992449,0.000011027264,0.00003426795,0.81515783,0.0050754705,0.072936684,0.0017959995,0.00008872017],"about_ca_topic_score_codex":0.0000015116419,"about_ca_topic_score_gemma":7.394852e-7,"teacher_disagreement_score":0.84099567,"about_ca_system_score_codex":0.000081680795,"about_ca_system_score_gemma":0.00006828355,"threshold_uncertainty_score":0.24322014},"labels":[],"label_agreement":null},{"id":"W4415958133","doi":"10.3102/10769986251379738","title":"Valid Standard Errors for Bayesian Quantile Regression With Clustered and Independent Data","year":2025,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Jackknife resampling; Frequentist inference; Markov chain Monte Carlo; Estimator; Quantile; Quantile regression; Standard error; Bayesian probability; Point estimation; Outlier","score_opus":0.06763164808331662,"score_gpt":0.405548800795139,"score_spread":0.3379171527118224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415958133","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013932263,0.00034907408,0.9823108,0.0026929795,0.00034139623,0.0001151766,0.00023440491,0.0000025172758,0.000021421749],"genre_scores_gemma":[0.13836925,0.00005364655,0.8610973,0.0001009365,0.000058220707,0.0000028510597,0.000022851003,0.0000042856004,0.00029066482],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991559,0.000048771137,0.00027911313,0.00018892542,0.00021478215,0.000112500704],"domain_scores_gemma":[0.99897915,0.00022486002,0.00022431441,0.00020101175,0.00026784392,0.000102832026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040236878,0.00009852087,0.00018904163,0.00009743737,0.00013056013,0.00013471546,0.00032030165,0.000041572777,0.000008681649],"category_scores_gemma":[0.000056490142,0.00006587434,0.000015527427,0.00009218474,0.000054991204,0.00030316363,0.00012404606,0.000120680656,5.1394416e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054059236,0.0006437496,0.025099302,0.00021100558,0.000090656926,0.000026205858,0.001116701,0.000010400049,0.00037350794,0.42127842,0.04488628,0.5057232],"study_design_scores_gemma":[0.0065312125,0.003986557,0.1061385,0.0013351621,0.00087645923,0.000959446,0.00058001693,0.047078673,0.0007036491,0.8089248,0.021882929,0.0010025884],"about_ca_topic_score_codex":0.0000133472295,"about_ca_topic_score_gemma":0.000027395276,"teacher_disagreement_score":0.50472057,"about_ca_system_score_codex":0.000025859381,"about_ca_system_score_gemma":0.00038196947,"threshold_uncertainty_score":0.26862776},"labels":[],"label_agreement":null},{"id":"W4416943890","doi":"10.1007/s00357-025-09522-5","title":"Implications of Different Encodings of Binned Data when Clustering","year":2025,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Encoding (memory); Latent class model; ENCODE; Class (philosophy); Pattern recognition (psychology); Medoid; Latent variable; Single-linkage clustering","score_opus":0.088042672940701,"score_gpt":0.3476281171019941,"score_spread":0.2595854441612931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416943890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005843073,0.00012997477,0.98680097,0.0052623204,0.00020208729,0.00006785444,0.0000044651842,0.0000062870536,0.0016829437],"genre_scores_gemma":[0.69577974,0.0000750279,0.3039989,0.00004958895,0.0000246135,0.0000011276377,0.0000018641123,0.0000022537554,0.00006689803],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893117,0.000083849176,0.0006151246,0.00013647419,0.0001582336,0.00007515172],"domain_scores_gemma":[0.99801064,0.0001391744,0.000760181,0.00076222763,0.00029191066,0.000035862413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006536663,0.000062898034,0.0002148752,0.00021244552,0.000031083582,0.00002694438,0.0012474846,0.000045825764,0.0000030122128],"category_scores_gemma":[0.00011864037,0.000049214992,0.000058835245,0.00023542107,0.00003252217,0.0003754964,0.00019768406,0.00010271172,2.3591538e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001970893,0.00016671896,0.0015541295,0.00008912861,0.000058554757,2.935418e-7,0.0005066506,0.000009971957,0.2663858,0.3499724,0.002227678,0.37900895],"study_design_scores_gemma":[0.0012649992,0.00024904133,0.24907629,0.00066975254,0.00017439606,0.000036730715,0.0001099894,0.21117005,0.06963415,0.4628275,0.0045343027,0.00025279835],"about_ca_topic_score_codex":0.000003186197,"about_ca_topic_score_gemma":0.0000032315481,"teacher_disagreement_score":0.6899367,"about_ca_system_score_codex":0.00003166405,"about_ca_system_score_gemma":0.00010603595,"threshold_uncertainty_score":0.23181576},"labels":[],"label_agreement":null},{"id":"W4417090136","doi":"10.48550/arxiv.2504.12683","title":"Cluster weighted models with multivariate skewed distributions for functional data","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Cluster analysis; Functional data analysis; Functional principal component analysis; Mixture model; Expectation–maximization algorithm; Cluster (spacecraft); Multivariate normal distribution; Gaussian","score_opus":0.12558118425078116,"score_gpt":0.3258934414331883,"score_spread":0.20031225718240717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417090136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011025008,0.00015882945,0.99032956,0.0031135567,0.0013435371,0.0009947984,0.0018335743,0.00026068813,0.00086294545],"genre_scores_gemma":[0.062173318,0.000024230942,0.9319496,0.0006664582,0.00033577485,0.00033011078,0.0023167592,0.00002459436,0.0021791284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970233,0.00019437844,0.00043200265,0.0015963804,0.00028623085,0.00046772932],"domain_scores_gemma":[0.99566215,0.00036342436,0.00023903736,0.0032105064,0.0003741112,0.00015079115],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068345555,0.00042863234,0.0004796335,0.00013745594,0.0003074423,0.00019643997,0.0025129274,0.00036109216,0.000010215089],"category_scores_gemma":[0.000079737314,0.0003442876,0.00015234687,0.00029552545,0.00007521655,0.0005874746,0.003974632,0.00064341136,0.000010328513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004301496,0.00078547816,0.0028254418,0.0006756076,0.001377074,0.000024124267,0.00066316116,0.006495696,0.00023233585,0.9056381,0.038162775,0.042690046],"study_design_scores_gemma":[0.0010176743,0.000037652248,0.0029093158,0.00019486465,0.0001395887,0.0000061534565,0.0000022141953,0.84075373,0.00017362814,0.14869207,0.0055804383,0.00049267197],"about_ca_topic_score_codex":0.00008875842,"about_ca_topic_score_gemma":0.000031474112,"teacher_disagreement_score":0.834258,"about_ca_system_score_codex":0.00009415718,"about_ca_system_score_gemma":0.0006716266,"threshold_uncertainty_score":0.99990094},"labels":[],"label_agreement":null},{"id":"W4417277027","doi":"10.1214/25-ejs2473","title":"Randomization tests for conditional group symmetry","year":2025,"lang":"","type":"article","venue":"Electronic Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Symmetry (geometry); Nonparametric statistics; Kernel (algebra); Statistical hypothesis testing; Randomization; Symmetry group; Conditional probability distribution; Group (periodic table)","score_opus":0.009871048850013858,"score_gpt":0.30044869407079305,"score_spread":0.2905776452207792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417277027","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052040057,0.008084405,0.9884564,0.001103121,0.0014100607,0.0004313764,0.00014079154,0.0000095457835,0.00031221757],"genre_scores_gemma":[0.18473163,0.002019398,0.81118816,0.0006929857,0.00043665688,0.00000971387,0.00003575202,0.000020350706,0.0008653483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968145,0.000376724,0.0012368006,0.00030923737,0.00045761588,0.0008051206],"domain_scores_gemma":[0.9954529,0.0019463564,0.001020308,0.00025956988,0.0011802104,0.00014068467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029923578,0.00028128136,0.0006782263,0.00042406484,0.00027032348,0.00023631826,0.00071927794,0.00017107102,0.000030610656],"category_scores_gemma":[0.0011615416,0.00026621533,0.00024045222,0.00059824775,0.00011811593,0.0003957631,0.00007127473,0.0007401929,0.0000022696538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040674518,0.00015555872,0.000017435703,0.00010425229,0.00030066198,0.000009909337,0.0000739229,0.00008677499,0.00018570374,0.8103599,0.015726717,0.17257239],"study_design_scores_gemma":[0.007815683,0.001011432,0.00022049759,0.00015289597,0.00034639818,0.00012453341,0.00000911202,0.08077111,0.0002828403,0.90046775,0.0085803075,0.00021742638],"about_ca_topic_score_codex":0.0000022211345,"about_ca_topic_score_gemma":0.000009656892,"teacher_disagreement_score":0.1846796,"about_ca_system_score_codex":0.00044231245,"about_ca_system_score_gemma":0.002661085,"threshold_uncertainty_score":0.999979},"labels":[],"label_agreement":null},{"id":"W577913126","doi":"10.71781/17003","title":"Un calcul algébrique détaillé de la fonction de partition du modèle d'Ising bidimensionnel","year":2007,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Mathematics; Combinatorics; Ising model; Physics; Statistical physics","score_opus":0.009249196748774256,"score_gpt":0.20956934057185128,"score_spread":0.20032014382307703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W577913126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21036159,0.0062247557,0.7641812,0.0005453747,0.0013602497,0.00030287268,0.000015254365,0.0001739204,0.016834788],"genre_scores_gemma":[0.69705397,0.000846294,0.2874801,0.00046668624,0.0006057138,0.000030818155,0.00018464157,0.00006327783,0.013268517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995813,0.0010247543,0.0005743685,0.0009896454,0.0007126023,0.0008856213],"domain_scores_gemma":[0.99736166,0.0003882987,0.00055398286,0.00056685857,0.00049318216,0.0006360177],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0015894893,0.00060549646,0.00049640477,0.00046376395,0.0071171825,0.00024994876,0.00061469356,0.0011681878,0.000030369854],"category_scores_gemma":[0.00015803633,0.0007322984,0.00046585407,0.0006521909,0.00035231185,0.0009369,0.00023142897,0.00088829757,0.000034595298],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079306023,0.00071691116,0.0036350472,0.0003241415,0.0004295152,0.0100084925,0.062251445,0.021958096,0.11508368,0.66661674,0.0007552387,0.11742763],"study_design_scores_gemma":[0.00328223,0.0003872055,0.05951533,0.0012812329,0.0010115735,0.014361607,0.008848961,0.6661002,0.14949684,0.050888315,0.042370442,0.0024560338],"about_ca_topic_score_codex":0.030124936,"about_ca_topic_score_gemma":0.0020167453,"teacher_disagreement_score":0.64414215,"about_ca_system_score_codex":0.007718524,"about_ca_system_score_gemma":0.0028110323,"threshold_uncertainty_score":0.9995128},"labels":[],"label_agreement":null},{"id":"W583942930","doi":"10.1017/cbo9780511609725.010","title":"Order parameter correlation function","year":2009,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Order (exchange); Correlation; Function (biology); Mathematics; Statistical physics; Applied mathematics; Physics; Economics; Geometry; Biology; Evolutionary biology","score_opus":0.020998267127448407,"score_gpt":0.20389891417149877,"score_spread":0.18290064704405037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W583942930","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.903675e-7,0.000056652392,0.5021737,0.000018362505,0.00028789556,0.00015592387,0.000007789765,0.00013376889,0.49716488],"genre_scores_gemma":[0.00009250028,0.00003750677,0.066593975,0.00028700294,0.0001140164,3.7806495e-7,0.00002022326,0.000021932781,0.9328325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855095,0.00007152609,0.00018201987,0.000664305,0.0002751756,0.0002560159],"domain_scores_gemma":[0.9985058,0.00008284073,0.0002255662,0.0008256689,0.00021188843,0.00014826194],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015119377,0.0003445396,0.00032970693,0.000201285,0.00017086271,0.00010328239,0.00069216575,0.00048411998,0.0000033600338],"category_scores_gemma":[0.000010165036,0.0003859533,0.00018930275,0.000018829263,0.00007296276,0.00027387476,0.00026116017,0.0005070144,0.000025534833],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024077339,0.0000054048814,1.7265955e-7,0.00001071066,0.00004043559,0.000056862922,0.000020074232,0.0000058144783,0.000008923832,0.852146,0.013925572,0.13375594],"study_design_scores_gemma":[0.0003847456,0.000113180264,0.000019156256,0.00007751541,0.00013803334,0.000019986408,9.572831e-7,0.0073522385,0.0000438738,0.0025988591,0.98875237,0.0004990698],"about_ca_topic_score_codex":0.000019883768,"about_ca_topic_score_gemma":5.5521684e-7,"teacher_disagreement_score":0.9748268,"about_ca_system_score_codex":0.00012390995,"about_ca_system_score_gemma":0.0000979654,"threshold_uncertainty_score":0.9998592},"labels":[],"label_agreement":null},{"id":"W58761036","doi":"10.1007/978-3-642-55032-4_29","title":"An Infinite Mixture Model of Generalized Inverted Dirichlet Distributions for High-Dimensional Positive Data Modeling","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet distribution; Gibbs sampling; Computer science; Cluster analysis; Hierarchical Dirichlet process; Artificial intelligence; Mixture model; Pattern recognition (psychology); Latent Dirichlet allocation; Dirichlet process; Bayesian information criterion; Covariance; Feature (linguistics); Model selection; Algorithm; Data mining; Bayesian probability; Machine learning; Mathematics; Topic model; Statistics","score_opus":0.04482043867279158,"score_gpt":0.29381239697545397,"score_spread":0.2489919583026624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W58761036","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000096389434,0.0002319893,0.9963457,0.0010731564,0.0006899974,0.0006034307,0.000776533,0.00010507452,0.00007773487],"genre_scores_gemma":[0.0857428,0.000019467954,0.911422,0.0018702389,0.0002874838,0.000013538159,0.00055070897,0.000039602688,0.000054158736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954055,0.00011782737,0.00079386984,0.00214267,0.00086756586,0.00067254406],"domain_scores_gemma":[0.9947988,0.0004955079,0.00042308675,0.003241919,0.0007701856,0.00027052447],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016999306,0.0006325012,0.0009010271,0.00058567605,0.00033458008,0.00027257082,0.0053338907,0.0005117254,0.0000036831464],"category_scores_gemma":[0.00014030328,0.000559019,0.0001519562,0.00042280805,0.00047947245,0.00080192514,0.0018634115,0.0006611544,0.0000017584173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021145408,0.00004260189,9.185115e-7,0.000035032677,0.000025234522,0.0000041491508,0.00017966458,0.5009276,0.0013376636,0.34060284,0.00006904558,0.15675406],"study_design_scores_gemma":[0.00032668552,0.00009381762,0.00000124734,0.00014769252,0.000023965016,0.000008956823,1.1858766e-8,0.61502224,0.0007186268,0.38323635,0.000029142233,0.0003912598],"about_ca_topic_score_codex":0.000050286653,"about_ca_topic_score_gemma":0.000041048534,"teacher_disagreement_score":0.1563628,"about_ca_system_score_codex":0.00013609749,"about_ca_system_score_gemma":0.0008132276,"threshold_uncertainty_score":0.9996861},"labels":[],"label_agreement":null},{"id":"W611014095","doi":"","title":"Recent Advances in Statistical Methods: Proceedings of Statistics 2001 Canada : The 4th Conference in Applied Statistics Montreal, Canada 6-8 July 2001","year":2003,"lang":"en","type":"book","venue":"Medical Entomology and Zoology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Statistics; Econometrics; Order statistic; Series (stratigraphy); Goodness of fit","score_opus":0.014340231638965396,"score_gpt":0.28504371159435815,"score_spread":0.27070347995539273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W611014095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007362341,0.0034957686,0.91415876,0.0011518581,0.00072072307,0.0003852072,0.00035937296,0.000008743071,0.079712205],"genre_scores_gemma":[0.00018001175,0.02690902,0.9409135,0.005520941,0.00007740021,0.00012619644,0.00015534503,0.000042223764,0.02607536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960456,0.0005646296,0.0010341434,0.0007950262,0.0006422178,0.0009184201],"domain_scores_gemma":[0.9955375,0.003139048,0.00041429713,0.00028473564,0.00021625156,0.0004081548],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021574039,0.00041889952,0.0011902857,0.00014909418,0.000066473,0.000018138464,0.0009200198,0.00062669674,0.00033659168],"category_scores_gemma":[0.0013435934,0.00032271017,0.000016111526,0.00022885451,0.0008115233,0.000045895402,0.00025567776,0.0014347289,7.9133486e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034603854,0.000043062482,0.000105253515,0.00011796543,0.000025428362,0.0004263749,0.000107355176,0.000002167754,6.5157064e-7,0.5014154,0.14316577,0.35455602],"study_design_scores_gemma":[0.0010210796,0.00019393298,0.0008047595,0.000096587624,0.000052353727,0.0002219994,0.00003272821,0.0071918806,0.000007885573,0.74314255,0.24675484,0.0004793831],"about_ca_topic_score_codex":0.6581254,"about_ca_topic_score_gemma":0.99372923,"teacher_disagreement_score":0.35407662,"about_ca_system_score_codex":0.00040787586,"about_ca_system_score_gemma":0.014698695,"threshold_uncertainty_score":0.9999225},"labels":[],"label_agreement":null},{"id":"W6854689","doi":"10.1007/3-540-45065-3_15","title":"Novel Mixtures Based on the Dirichlet Distribution: Application to Data and Image Classification","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Dirichlet distribution; Multinomial distribution; Mixture model; Pattern recognition (psychology); Flexibility (engineering); Computer science; Generalized Dirichlet distribution; Gaussian; Artificial intelligence; Latent Dirichlet allocation; Distribution (mathematics); Mathematics; Mixture distribution; Algorithm; Data mining; Statistics; Probability density function; Dirichlet series; Topic model; Mathematical analysis","score_opus":0.05029383037741484,"score_gpt":0.30807569770767884,"score_spread":0.257781867330264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6854689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000031814495,0.000103139944,0.98757976,0.008944713,0.00040020642,0.0006696894,0.00008052707,0.0000852272,0.0021335708],"genre_scores_gemma":[0.03577399,0.000011573184,0.95703757,0.006645951,0.0003639672,0.00001956577,0.000073702744,0.00002108296,0.00005262048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965324,0.000048975868,0.00037815183,0.0017919434,0.00081745407,0.00043107884],"domain_scores_gemma":[0.9951593,0.00096522935,0.00021627572,0.0032758354,0.000205975,0.00017737233],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025654042,0.00039679295,0.0002972367,0.00031106357,0.00033864946,0.0005899936,0.0042480584,0.00024277432,0.000004683863],"category_scores_gemma":[0.00021652902,0.0002823869,0.00004713096,0.0006843997,0.0004733006,0.00034769415,0.0013161569,0.0006186207,0.000015319767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007872673,0.00003076164,0.000004281755,0.0000144075275,0.0000034809473,0.0000048078227,0.00010284856,0.00051641307,0.0013154089,0.13482592,0.00029721815,0.8628766],"study_design_scores_gemma":[0.000119951925,0.000067934496,0.0002925804,0.00011101226,0.000007094779,0.000016218175,6.746011e-8,0.9311416,0.00083713676,0.060771562,0.0062749474,0.00035987282],"about_ca_topic_score_codex":0.000011547409,"about_ca_topic_score_gemma":0.000021307,"teacher_disagreement_score":0.9306252,"about_ca_system_score_codex":0.00015506572,"about_ca_system_score_gemma":0.00023232255,"threshold_uncertainty_score":0.9999628},"labels":[],"label_agreement":null},{"id":"W6891829986","doi":"10.48550/arxiv.2106.10660","title":"Bayesian inference for continuous-time hidden Markov models with an unknown number of states","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Inference; Hidden Markov model; Reversible-jump Markov chain Monte Carlo; Markov chain Monte Carlo; Bayesian inference; Hidden semi-Markov model; Bayesian probability; Context (archaeology); Markov process","score_opus":0.04133180057113238,"score_gpt":0.22116701276284875,"score_spread":0.1798352121917164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6891829986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05406804,0.000037246773,0.9419766,0.000054722263,0.00014119517,0.0004952255,0.000051798463,0.0001413037,0.0030338408],"genre_scores_gemma":[0.54998875,0.00006153767,0.44841582,0.000053179443,0.000028850352,0.0000031321724,0.000045751593,0.000025137475,0.001377864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973393,0.00031933293,0.00031420824,0.0014175277,0.00014068157,0.00046891323],"domain_scores_gemma":[0.99677896,0.0002616512,0.00040877945,0.0016521172,0.0006326857,0.0002658221],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004438188,0.00044639423,0.0007733,0.0001564944,0.000110224384,0.00018012643,0.0018432979,0.00034653206,0.00004447635],"category_scores_gemma":[0.000024463692,0.00044690404,0.00023747313,0.00042888866,0.00016008601,0.00089869724,0.0010912931,0.00041299718,0.00000406195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033758263,0.00053256855,0.001500949,0.0005288026,0.00051565137,0.00037147556,0.0020290453,0.06611542,0.00015106564,0.89825445,0.00017080184,0.029492183],"study_design_scores_gemma":[0.0005335419,0.0001271444,0.00004729621,0.00017840158,0.00009338641,0.000007587947,0.000047369438,0.72028667,0.0003507044,0.2778217,0.000038797672,0.00046741118],"about_ca_topic_score_codex":0.0002173549,"about_ca_topic_score_gemma":0.00007265452,"teacher_disagreement_score":0.6541712,"about_ca_system_score_codex":0.000086473396,"about_ca_system_score_gemma":0.0005326447,"threshold_uncertainty_score":0.9997983},"labels":[],"label_agreement":null},{"id":"W6902027445","doi":"10.6084/m9.figshare.24532011","title":"Additional file 1 of A model-based clustering via mixture of hierarchical models with covariate adjustment for detecting differentially expressed genes from paired design","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Covariate; Cluster analysis; Hierarchical clustering; Pattern recognition (psychology); Mixture model","score_opus":0.08305012066462882,"score_gpt":0.2610435987936934,"score_spread":0.17799347812906458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902027445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004992908,0.000012473381,0.520905,0.00001345218,0.000012128053,0.00024637254,0.4787251,0.00006797465,0.000012523855],"genre_scores_gemma":[0.0045002936,3.4879838e-7,0.8025172,0.000051510204,0.00005452027,0.0014853751,0.1913348,0.000024793071,0.000031208478],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985225,0.00012987498,0.00030232305,0.00044804078,0.0003122065,0.00028504233],"domain_scores_gemma":[0.99626946,0.0027756076,0.00024240372,0.0004153217,0.0002033921,0.00009381727],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000076533535,0.00020143937,0.00032358326,0.00011802609,0.00008537044,0.000034956072,0.00054409384,0.00012388176,0.09056981],"category_scores_gemma":[0.000324484,0.00017294582,0.00013817922,0.00026529632,0.00001217727,0.0001768145,0.00019257679,0.00011277789,0.000007602073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023521557,0.000103430866,5.3953663e-8,0.00038859723,0.00010541293,0.000008983242,0.00042263328,0.3177505,0.007827154,0.00010467808,0.59428716,0.07876619],"study_design_scores_gemma":[0.00050824654,0.00012714122,0.000022459522,0.0014815906,0.0000122101055,9.874618e-7,0.0000021885999,0.9711107,0.009320732,0.01689591,0.00032781524,0.00018999836],"about_ca_topic_score_codex":0.0000042146353,"about_ca_topic_score_gemma":0.0000059207173,"teacher_disagreement_score":0.6533602,"about_ca_system_score_codex":0.000020053101,"about_ca_system_score_gemma":0.00023348328,"threshold_uncertainty_score":0.9102615},"labels":[],"label_agreement":null},{"id":"W6911865299","doi":"10.5281/zenodo.13772908","title":"Hymenoptera","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cooke Aquaculture (Canada)","funders":"","keywords":"Hymenoptera; Nest (protein structural motif); Key (lock); Burrow; Predation","score_opus":0.033382729450432753,"score_gpt":0.2658754224415468,"score_spread":0.23249269299111408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6911865299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018557264,0.00027544537,0.80500716,0.0014985964,0.00020716194,0.00011432811,0.000014899189,0.0014911111,0.19120571],"genre_scores_gemma":[0.7001355,0.00029265287,0.28384605,0.0014064466,0.0008065467,8.601004e-8,0.0003896407,0.0028563957,0.010266648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99868286,0.00022789722,0.0001447884,0.00043107758,0.00023914922,0.00027422345],"domain_scores_gemma":[0.9991824,0.000023020324,0.000022032993,0.0004912693,0.00014821714,0.00013303944],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00069833186,0.00010029661,0.000087122666,0.00018740712,0.00088100217,0.0022349418,0.001372386,0.0000425849,0.0024076647],"category_scores_gemma":[0.00009319217,0.00009452447,0.00004665034,0.00059429073,0.000052761505,0.0004910215,0.0010825637,0.00021310746,0.007618911],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019248698,0.00001700144,3.84902e-8,0.000024055425,0.000011769202,0.000025487347,0.0006307715,0.00000255282,0.0014115105,0.30513385,0.0846372,0.6081038],"study_design_scores_gemma":[0.0000840132,0.00008215961,0.000017776834,0.00002766552,0.0000037766952,0.00015276897,0.000008773383,0.010410641,0.00052604085,0.012591379,0.9759761,0.000118875854],"about_ca_topic_score_codex":0.0000025965687,"about_ca_topic_score_gemma":2.0654184e-8,"teacher_disagreement_score":0.89133894,"about_ca_system_score_codex":0.00006188896,"about_ca_system_score_gemma":0.0000034740838,"threshold_uncertainty_score":0.9988008},"labels":[],"label_agreement":null},{"id":"W6924733613","doi":"10.1594/pangaea.854956","title":"Table 1. Pressure, temperature and isotope ratios between H2O and CO2 for all experiments","year":2015,"lang":"en","type":"dataset","venue":"Figshare","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Seventh Framework Programme","keywords":"Stable isotope ratio; Isotope; Isotopes of carbon; Carbon dioxide; Fraction (chemistry); CO2 content; Table (database); Oxygen-18","score_opus":0.07036425040929359,"score_gpt":0.3317233447283388,"score_spread":0.26135909431904525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924733613","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.10572e-7,0.0056746155,0.0023867982,0.00007876974,0.00011013489,0.00089051906,0.9907567,0.000043190717,0.000058781814],"genre_scores_gemma":[0.0000037263796,0.000028908134,0.030050443,0.00047291312,0.00034627027,0.00045835442,0.96804446,0.000019458817,0.0005754564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842715,0.00009204182,0.00021881855,0.0007055924,0.00023695108,0.00031944455],"domain_scores_gemma":[0.9985742,0.00014779277,0.00015845044,0.0007011755,0.00017486885,0.0002435065],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016655386,0.00033699282,0.00044757407,0.00007094003,0.00011728924,0.00053622044,0.00076560694,0.00046506428,0.0011359341],"category_scores_gemma":[0.00027070852,0.00029129907,0.00004118696,0.000096780794,0.000009332737,0.00039315922,0.0006382644,0.0002949758,0.00003396044],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032724897,0.000011132677,5.6359175e-7,0.00035484403,0.00005136451,0.0000046080395,0.00006129308,2.3102596e-7,0.000012314432,0.000022577695,0.99840623,0.0010715475],"study_design_scores_gemma":[0.00039346394,0.00009362,0.00000921032,0.00048455698,0.000039905226,0.000008327215,0.0000014947029,0.00018317257,0.00031820766,0.0005471114,0.997572,0.0003488973],"about_ca_topic_score_codex":0.000013312345,"about_ca_topic_score_gemma":0.0000053136387,"teacher_disagreement_score":0.027663646,"about_ca_system_score_codex":0.000011030842,"about_ca_system_score_gemma":0.00014355205,"threshold_uncertainty_score":0.9999539},"labels":[],"label_agreement":null},{"id":"W6928677192","doi":"10.35680/2372-0247.1735","title":"Patients’ and family caregivers’ experiences with a newly implemented hospital at home program in British Columbia, Canada: Preliminary results","year":2023,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Timeline; Observational study; Data collection; Scale (ratio); Research program; Work (physics)","score_opus":0.07555166632109231,"score_gpt":0.4260538064078654,"score_spread":0.35050214008677305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6928677192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99329066,0.001998415,0.0026018668,0.00015649614,0.00043505867,0.0010471079,0.0000916504,0.00007089233,0.00030786535],"genre_scores_gemma":[0.989395,0.0010512692,0.008844271,0.00013684094,0.000032420434,0.00022534694,0.000024437368,0.00002689156,0.00026351048],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968601,0.0002589014,0.0006753588,0.00077602384,0.00083400396,0.0005956444],"domain_scores_gemma":[0.9982533,0.0001962118,0.00051099586,0.00043790825,0.0002765426,0.0003250344],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007556567,0.00022716424,0.00057022885,0.00027916458,0.00033230867,0.0024758633,0.0024534795,0.00007581261,0.00008624889],"category_scores_gemma":[0.00010025553,0.00026965755,0.00006007076,0.0017005309,0.00014746547,0.0020836678,0.0019207025,0.00024158733,6.3772677e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018464688,0.00027340194,0.6553666,0.00005540001,0.00007958947,0.00066839997,0.006235201,0.000013417409,0.00014199485,0.000011098701,0.097189054,0.23978117],"study_design_scores_gemma":[0.0016856227,0.00021938517,0.99300194,0.00030758002,0.000014399016,0.000015846717,0.0014179411,0.00046656115,0.00010552429,0.0004940754,0.0018297677,0.0004413556],"about_ca_topic_score_codex":0.6465966,"about_ca_topic_score_gemma":0.6229971,"teacher_disagreement_score":0.3376353,"about_ca_system_score_codex":0.00020819766,"about_ca_system_score_gemma":0.00050290447,"threshold_uncertainty_score":0.99997556},"labels":[],"label_agreement":null},{"id":"W6929717818","doi":"10.5061/dryad.4xgxd259s","title":"Shedding light on the threespine stickleback circadian clock","year":2021,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Population; Ectotherm; Proteogenomics; Limiting","score_opus":0.04141001852900082,"score_gpt":0.31968377226576916,"score_spread":0.2782737537367683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929717818","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063760344,0.0005249696,0.30761105,0.0089642545,0.0016450852,0.0008351963,0.6658145,0.000004599384,0.014593926],"genre_scores_gemma":[0.000013130842,0.00022039452,0.5041106,0.00430431,0.0009936715,0.000083769075,0.4861692,0.00004326606,0.004061701],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99739444,0.0003711272,0.00037124573,0.0010223412,0.000394469,0.00044637764],"domain_scores_gemma":[0.99654776,0.0002803498,0.00022363524,0.0026905704,0.00007654201,0.0001811214],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001203269,0.0003817667,0.0004867009,0.00010006941,0.00028326528,0.0017555418,0.0057266066,0.00030248438,0.002388081],"category_scores_gemma":[0.00018362618,0.00025701142,0.0001395554,0.00044759695,0.00004197887,0.00025779376,0.0019455277,0.0007777483,0.0015361786],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002521136,0.000043464028,1.08690735e-7,0.000008435051,0.00003533564,0.0001276639,0.000073861665,0.000001814966,0.000017807299,0.0022967944,0.90227,0.09512217],"study_design_scores_gemma":[0.00013952513,0.00006407207,0.0000031434963,0.00024531173,0.000033104658,0.000026760448,0.000008272557,0.0003158707,0.0005259716,0.0013215664,0.9969572,0.0003592038],"about_ca_topic_score_codex":0.000057836085,"about_ca_topic_score_gemma":0.00015386181,"teacher_disagreement_score":0.19649951,"about_ca_system_score_codex":0.00005969749,"about_ca_system_score_gemma":0.0003781276,"threshold_uncertainty_score":0.9999882},"labels":[],"label_agreement":null},{"id":"W6929728640","doi":"10.48619/ais.v6i1.1171","title":"Exploring the Architecture 2.0 for the Future of Building Design and Technology","year":2025,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Mass customization; Panacea (medicine); Architecture; Production (economics); Consumption (sociology); Personalization; Identification (biology)","score_opus":0.27734510559036263,"score_gpt":0.518479236461664,"score_spread":0.24113413087130142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929728640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011230116,0.0373611,0.9440113,0.0057688514,0.00074349786,0.00070344046,0.0000032374944,0.000030470188,0.00014800523],"genre_scores_gemma":[0.4168615,0.015547082,0.566071,0.0007560945,0.00027967035,0.000319022,3.2518238e-7,0.000032327654,0.00013299886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983621,0.00029373544,0.00045085544,0.00036180933,0.00024669664,0.00028477033],"domain_scores_gemma":[0.9970854,0.00151192,0.00037898452,0.0007463805,0.00022008305,0.000057241476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024603421,0.00020482374,0.00044906145,0.0005960472,0.00043679637,0.00067364937,0.0051071486,0.00008555009,0.000021754291],"category_scores_gemma":[0.00021829389,0.00011466172,0.000113238144,0.0015786312,0.00018194572,0.0009326919,0.0014787994,0.00043588862,1.0473769e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050749182,0.00003156388,0.0014259042,0.00007079091,0.00015072741,0.00000292995,0.00033109667,0.0004255674,0.040064905,0.072444245,0.0038202303,0.8811813],"study_design_scores_gemma":[0.00051863835,0.00002306859,0.015343688,0.0005147013,0.00011809939,0.00003126386,0.00012441514,0.0074082883,0.13596842,0.81408584,0.025542052,0.00032150498],"about_ca_topic_score_codex":0.00003047884,"about_ca_topic_score_gemma":0.0000062205027,"teacher_disagreement_score":0.8808598,"about_ca_system_score_codex":0.000020494948,"about_ca_system_score_gemma":0.00011721408,"threshold_uncertainty_score":0.94904375},"labels":[],"label_agreement":null},{"id":"W6929743059","doi":"10.5061/dryad.sc0nf","title":"Data from: Clones or clans: the genetic structure of a deep-sea sponge, Aphrocallistes vastus, in unique sponge reefs of British Columbia, Canada","year":2016,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reef; Genetic structure; Biological dispersal; Population; Sponge; Trawling; Coral reef","score_opus":0.01754972884278086,"score_gpt":0.24461092207007099,"score_spread":0.22706119322729013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929743059","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008128535,0.0030022894,0.075519346,0.00006566573,0.00038592063,0.00041160965,0.91245526,0.000019653953,0.000011706326],"genre_scores_gemma":[0.003146064,0.0060325954,0.06324061,0.00045047206,0.00047147347,0.000012136274,0.92654896,0.000043935357,0.000053774063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99528325,0.0010482243,0.0009454595,0.0015406209,0.0005767303,0.00060570316],"domain_scores_gemma":[0.9910216,0.0016378853,0.00069325464,0.0063924505,0.00006753903,0.00018727018],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00078062766,0.00041885622,0.0009809752,0.000084816464,0.00016543103,0.00031043333,0.012501993,0.00026406776,0.00004208296],"category_scores_gemma":[0.000058375146,0.00036091355,0.00004540291,0.0004896178,0.00023809617,0.00045726149,0.006216629,0.0006332152,3.800915e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001274222,0.00009180199,0.004105346,0.0017291938,0.0003358029,0.00042530632,0.00036918046,0.000037456073,0.000079896214,0.000016741642,0.8927733,0.099908605],"study_design_scores_gemma":[0.0015145065,0.00019290844,0.11620816,0.0084150545,0.00052143773,0.00038087042,0.00017606438,0.13955042,0.000008788768,0.006143202,0.72499734,0.0018912387],"about_ca_topic_score_codex":0.92315847,"about_ca_topic_score_gemma":0.9989313,"teacher_disagreement_score":0.16777588,"about_ca_system_score_codex":0.000034001445,"about_ca_system_score_gemma":0.0006340496,"threshold_uncertainty_score":0.9998843},"labels":[],"label_agreement":null},{"id":"W6930266120","doi":"10.5281/zenodo.12934895","title":"strategic compensation in canada 7th edition free","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Compensation (psychology); Government (linguistics); Compensation of employees; Work (physics); Executive compensation; Strategic planning","score_opus":0.03698087540899617,"score_gpt":0.24018707576846113,"score_spread":0.20320620035946496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930266120","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000063739462,0.00024417505,0.32417506,0.0005524904,0.00042649868,0.00025694093,0.00018543203,0.0005616625,0.6735914],"genre_scores_gemma":[0.07210868,0.0014479561,0.17133467,0.002555903,0.005071931,8.682708e-7,0.009922078,0.04747667,0.69008124],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99811244,0.00035322487,0.00022754406,0.00056816346,0.0004272004,0.0003113988],"domain_scores_gemma":[0.99887806,0.000013106968,0.000112776455,0.0007598525,0.000113112124,0.00012309318],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004665625,0.00018889087,0.0001947129,0.00039378254,0.00022635757,0.00071631203,0.0017906923,0.00010948261,0.006091769],"category_scores_gemma":[0.00007251166,0.00019653984,0.00003453569,0.0006143418,0.00004023187,0.00013911669,0.0010525894,0.00041157214,0.0025276737],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021545534,0.000017294537,8.56872e-8,0.00008821568,0.000014914326,0.000045077493,0.000118057476,0.000005922765,0.000039687973,0.08173531,0.8844684,0.033464894],"study_design_scores_gemma":[0.00020950614,0.00004251809,0.000015822805,0.0001558853,0.0000068351446,0.000041855474,0.000037370388,0.0031089704,0.00001934111,0.017656626,0.97848177,0.00022349133],"about_ca_topic_score_codex":0.069545135,"about_ca_topic_score_gemma":0.016157383,"teacher_disagreement_score":0.15284039,"about_ca_system_score_codex":0.00046805467,"about_ca_system_score_gemma":0.000052878,"threshold_uncertainty_score":0.998249},"labels":[],"label_agreement":null},{"id":"W6930641680","doi":"10.5281/zenodo.12700082","title":"Tube_Bioassay_Power_Simulation_Calculator","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Sample size determination; Statistical power; Sample (material); Variance (accounting); Range (aeronautics); Power (physics); Multiple comparisons problem","score_opus":0.03132543009425944,"score_gpt":0.27219030046174,"score_spread":0.24086487036748053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930641680","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8953826e-7,0.0005029217,0.49650297,0.0003474944,0.00035508772,0.00017549595,0.000075903685,0.002010281,0.5000296],"genre_scores_gemma":[0.0008367441,0.00018675654,0.086138286,0.0005061116,0.0009858881,6.339414e-8,0.00071582745,0.016291425,0.8943389],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979895,0.00029735386,0.00022098846,0.0007524941,0.00040497334,0.0003347019],"domain_scores_gemma":[0.9985371,0.000011598009,0.000104625535,0.0009800831,0.00016555315,0.00020104116],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00057926896,0.00023581395,0.00021622404,0.0004906608,0.0004227234,0.0015399395,0.0019786158,0.00021458034,0.014515895],"category_scores_gemma":[0.000121984325,0.00023068929,0.00010767385,0.00060029887,0.00008349217,0.00013846802,0.0017203261,0.000358103,0.03671975],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015362358,0.000021091379,1.1430309e-8,0.00006427106,0.000037374168,0.000014818677,0.00012711168,8.5376877e-7,0.000041422278,0.11716129,0.7643764,0.1181538],"study_design_scores_gemma":[0.00014308948,0.000050824052,0.000001541328,0.000096779884,0.0000140127195,0.000055958495,0.0000040292175,0.0018284579,0.00002619936,0.0042074365,0.99331397,0.00025767752],"about_ca_topic_score_codex":0.00000786819,"about_ca_topic_score_gemma":1.0564757e-7,"teacher_disagreement_score":0.4103647,"about_ca_system_score_codex":0.00008167714,"about_ca_system_score_gemma":0.000004776727,"threshold_uncertainty_score":0.9994966},"labels":[],"label_agreement":null},{"id":"W6931343020","doi":"10.5281/zenodo.5325787","title":"Theognete schaubeli Anderson 2010, new species","year":2010,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Aedeagus; Holotype; Dorsum; Litter; Plant litter","score_opus":0.0423276114352732,"score_gpt":0.2500941978408701,"score_spread":0.20776658640559692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931343020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009951168,0.000048246195,0.8212814,0.0025501929,0.00040966534,0.0001742893,0.000010471762,0.0007247843,0.17380585],"genre_scores_gemma":[0.32032746,0.000257082,0.5920086,0.0019068124,0.0018281189,7.073884e-8,0.0003158939,0.002709525,0.08064641],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848807,0.0002085999,0.00017380332,0.00044441875,0.0003183897,0.00036670777],"domain_scores_gemma":[0.9986091,0.000025742751,0.000074550844,0.0007781467,0.00024342311,0.00026901104],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007884656,0.0001389561,0.00013022612,0.00016909046,0.0012752878,0.0013548578,0.0019332025,0.00008053065,0.006279684],"category_scores_gemma":[0.00029755553,0.00013015556,0.00005534215,0.0004575269,0.0001126057,0.0005268189,0.0011858627,0.00042220732,0.0041733463],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008225957,0.000036092224,9.901613e-7,0.00000973903,0.000012252957,0.000007721525,0.00096215727,0.0000017008562,0.02365489,0.30427435,0.30327064,0.36776122],"study_design_scores_gemma":[0.00030450895,0.000098965036,0.00032920644,0.000009292721,0.0000043185555,0.000098701894,0.000026633708,0.001664973,0.0022003485,0.012843502,0.9822405,0.00017904618],"about_ca_topic_score_codex":0.000014900051,"about_ca_topic_score_gemma":6.1126104e-7,"teacher_disagreement_score":0.67896986,"about_ca_system_score_codex":0.000024906585,"about_ca_system_score_gemma":0.000007545757,"threshold_uncertainty_score":0.99968183},"labels":[],"label_agreement":null},{"id":"W6931383193","doi":"10.5281/zenodo.7420672","title":"CHEERSPORT Greensboro State Classic 2022 live streaming online Cheer &amp; Dance free","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dance; Studio; Event (particle physics); Doors; Upload; State (computer science); Dance education; Choreography; The Internet","score_opus":0.0337520650538884,"score_gpt":0.2598104352596421,"score_spread":0.2260583702057537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931383193","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005457498,0.0006556795,0.5467853,0.00070189533,0.0003510904,0.0005595038,0.0013580922,0.0019460763,0.44758782],"genre_scores_gemma":[0.0003561009,0.0011503849,0.15692696,0.0008193886,0.0007878803,3.8745188e-7,0.0066730925,0.0123889875,0.8208968],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640554,0.00062598335,0.00036439518,0.0011233985,0.0008559266,0.00062472536],"domain_scores_gemma":[0.9969351,0.000030243618,0.0003739278,0.002117352,0.0002663751,0.00027694608],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009554743,0.00038464132,0.00039190508,0.0005069469,0.0011712109,0.0006007961,0.004701154,0.00015626526,0.059213385],"category_scores_gemma":[0.0003387149,0.00041379587,0.00012369957,0.0009150951,0.00015543953,0.00025200244,0.005678635,0.00093676976,0.0027676139],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009652615,0.00012429123,0.0000014617347,0.000062584135,0.000069943766,0.000052789703,0.0007936035,0.0000075785147,0.00016604454,0.0044683376,0.8054362,0.1888075],"study_design_scores_gemma":[0.0004002916,0.000111995774,0.00011733802,0.0000589793,0.000018320909,0.000077800665,0.000040715167,0.0005921189,0.000012096735,0.0013040161,0.99682975,0.00043658263],"about_ca_topic_score_codex":0.00010996262,"about_ca_topic_score_gemma":0.000016190288,"teacher_disagreement_score":0.3898583,"about_ca_system_score_codex":0.00028634287,"about_ca_system_score_gemma":0.000021494932,"threshold_uncertainty_score":0.9998314},"labels":[],"label_agreement":null},{"id":"W6931451278","doi":"10.5281/zenodo.6405980","title":"208. Incidental findings on PET/CT in patients with large vessel vasculitis","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Etiology; Vasculitis; Pathological; Cohort; Retrospective cohort study; Disease; Medical record","score_opus":0.01264196330829608,"score_gpt":0.22512111693254397,"score_spread":0.21247915362424788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931451278","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018002401,0.00008592952,0.11486397,0.00024228917,0.00027555128,0.001050499,0.00056296587,0.001237252,0.8798813],"genre_scores_gemma":[0.17094554,0.0006646663,0.1312371,0.004417274,0.0011007863,0.000002551365,0.021111619,0.055846315,0.61467415],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973544,0.0005317753,0.00020574628,0.0007419492,0.0007065741,0.00045955228],"domain_scores_gemma":[0.9988235,0.00001811931,0.00012973501,0.00078940974,0.00009423801,0.00014497765],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006420857,0.0002466998,0.0002509214,0.00059510826,0.00074926193,0.00055057165,0.0020354702,0.000028697637,0.027891494],"category_scores_gemma":[0.00011599059,0.00023887455,0.000057458492,0.00076280214,0.000056852674,0.00020001127,0.0020038236,0.0005516338,0.002136177],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034939818,0.0004046204,0.00005678399,0.0000632861,0.000052018462,0.00023954977,0.0004187821,0.0000042512106,0.0000045580928,0.027059544,0.9328796,0.03878201],"study_design_scores_gemma":[0.0011691606,0.00034806549,0.0017674835,0.00008027448,0.0000067629844,0.00007234439,0.000020318073,0.00011654986,0.0000051034394,0.00020387911,0.9959132,0.00029683975],"about_ca_topic_score_codex":0.000034737106,"about_ca_topic_score_gemma":0.0000017304463,"teacher_disagreement_score":0.26520717,"about_ca_system_score_codex":0.00025788156,"about_ca_system_score_gemma":0.000007749054,"threshold_uncertainty_score":0.9986408},"labels":[],"label_agreement":null},{"id":"W6931533842","doi":"10.5281/zenodo.7629399","title":"Fig. 22 in Revision of the Nearctic species of the Lasioglossum (Dialictus) gemmatum species complex (Hymenoptera: Halictidae)","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Nearctic ecozone; Species complex; Scale (ratio); Taxonomy (biology); Ecological succession","score_opus":0.04976969421768035,"score_gpt":0.25964248420949243,"score_spread":0.20987278999181208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931533842","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001606373,0.00024129092,0.06874438,0.0021973585,0.00069378084,0.0011104947,0.0002726301,0.00065645785,0.925923],"genre_scores_gemma":[0.058184464,0.0019525152,0.023608984,0.0006617394,0.0009329327,2.6173015e-7,0.00020454467,0.011837135,0.90261745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99716437,0.00092388113,0.00043139711,0.00047039278,0.00067648635,0.00033347882],"domain_scores_gemma":[0.99777025,0.00005585106,0.00041191542,0.0014661856,0.00022747603,0.000068304835],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008923333,0.00022534675,0.00036568815,0.0003073464,0.0005023431,0.00030214156,0.0036388899,0.00013348949,0.0052529215],"category_scores_gemma":[0.00050655147,0.00015414726,0.00015343128,0.0014054128,0.0004224331,0.00012083249,0.0036353737,0.00041145016,0.00048190646],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011410564,0.00008802837,0.000016460475,0.00026172158,0.00004742364,0.000005031001,0.001515274,0.000014695072,0.0013317275,0.093284756,0.867575,0.03584849],"study_design_scores_gemma":[0.00022844905,0.000052449534,0.0027123857,0.0004568763,0.000011494084,0.000012071438,0.000042390504,0.00038968696,0.00032871024,0.00084427145,0.99476826,0.00015297618],"about_ca_topic_score_codex":0.00009891924,"about_ca_topic_score_gemma":0.00000804477,"teacher_disagreement_score":0.12719326,"about_ca_system_score_codex":0.00009931097,"about_ca_system_score_gemma":0.000012243904,"threshold_uncertainty_score":0.99565643},"labels":[],"label_agreement":null},{"id":"W6931775414","doi":"10.5281/zenodo.7910380","title":"Entedonomphale esenini S. Triapitsyn 2005, sp. n.","year":2005,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Seta; Ovipositor; Wing; Petiole (insect anatomy); Appendage; Antenna (radio)","score_opus":0.03307052653362845,"score_gpt":0.25941234204155117,"score_spread":0.2263418155079227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931775414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079212425,0.00019110573,0.8640486,0.0033535052,0.00012600323,0.00024355881,0.000022203683,0.000917288,0.1303056],"genre_scores_gemma":[0.38689297,0.00050294015,0.59008664,0.002268799,0.0015936123,1.8323192e-7,0.00047641178,0.0026461417,0.015532267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997943,0.00041489315,0.0002756746,0.00053356076,0.00033730885,0.00049557217],"domain_scores_gemma":[0.99858195,0.000030518702,0.00009757199,0.0007544186,0.00026648707,0.00026907504],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001127829,0.00015737306,0.00016821247,0.00021931564,0.0012437603,0.00097037345,0.002032255,0.00007096369,0.0048024454],"category_scores_gemma":[0.0002245638,0.00015856247,0.00007733092,0.00048941205,0.00008558871,0.0006581072,0.0013003733,0.00025146792,0.008915487],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014755676,0.000109859015,5.000982e-7,0.000010406889,0.000020007321,0.000009663966,0.0006342966,0.000026648706,0.0015597895,0.08501728,0.23246449,0.6801323],"study_design_scores_gemma":[0.00052602927,0.000083955514,0.00006809605,0.0000117017635,0.000005398156,0.0001274917,0.0000165454,0.008231865,0.0013524087,0.0014893949,0.98790056,0.00018653776],"about_ca_topic_score_codex":0.0000050573626,"about_ca_topic_score_gemma":2.8163345e-7,"teacher_disagreement_score":0.75543606,"about_ca_system_score_codex":0.00011308078,"about_ca_system_score_gemma":0.000006414052,"threshold_uncertainty_score":0.9961073},"labels":[],"label_agreement":null},{"id":"W6931937961","doi":"10.5683/sp3/gcry1u","title":"Search strategies for transnational families and pregnancy, childbirth and postpartum care / Stratégies de recherche sur les familles transnationales, la grossesse, l'accouchement et les soins postnataux","year":2025,"lang":"fr","type":"dataset","venue":"Borealis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"PsycINFO; CINAHL; MEDLINE; Childbirth; Health care; Postpartum period","score_opus":0.10894962371598046,"score_gpt":0.36936542367579883,"score_spread":0.26041579995981834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931937961","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004781131,0.01795805,0.43985403,0.006608231,0.00006290854,0.00077025883,0.53369194,0.000050602965,0.0005258617],"genre_scores_gemma":[0.0070152734,0.03155559,0.29654938,0.00036950587,0.00011193631,0.0004152526,0.66370463,0.00004872275,0.00022972772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952222,0.0016394416,0.0006472929,0.0011916333,0.00062556274,0.0006738362],"domain_scores_gemma":[0.9949907,0.003178153,0.0001772142,0.00059249037,0.0008583793,0.00020306915],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018360793,0.00076340267,0.0007217991,0.0003610838,0.00060675817,0.0013223533,0.0008929325,0.0011185267,0.0000070489345],"category_scores_gemma":[0.00020477161,0.0007438095,0.00021318349,0.00030369774,0.0006385822,0.0008980151,0.0002075176,0.0011141995,4.5961034e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055777073,0.00016653261,0.00010801058,0.0039696605,0.0002214911,0.000030314011,0.0058166506,0.00005928129,0.000082008235,0.87276167,0.031591512,0.08513712],"study_design_scores_gemma":[0.00557846,0.0012560976,0.0442173,0.006077726,0.00097158906,0.0003403696,0.023902643,0.008180204,0.0014046083,0.20408782,0.70035297,0.0036302079],"about_ca_topic_score_codex":0.007865992,"about_ca_topic_score_gemma":0.03994295,"teacher_disagreement_score":0.66876143,"about_ca_system_score_codex":0.0001649503,"about_ca_system_score_gemma":0.0043279636,"threshold_uncertainty_score":0.9997144},"labels":[],"label_agreement":null},{"id":"W6932201494","doi":"10.5683/sp3/accmz2","title":"Census of Population, 1971 [Canada]: Basic Summary Tabulations, Enumeration Area Level (Short Form)","year":2023,"lang":"en","type":"dataset","venue":"Borealis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Enumeration; Sampling (signal processing); Population; Statistical analysis","score_opus":0.058575056445447166,"score_gpt":0.2922788620146812,"score_spread":0.233703805569234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6932201494","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035904754,0.000085285705,0.24960512,0.0002510354,0.00045576497,0.0002434047,0.74921703,0.000053232845,0.00008555658],"genre_scores_gemma":[0.000033647342,0.00018947941,0.031015124,0.00018820206,0.00023337842,0.00003736635,0.96808046,0.00002323273,0.00019911712],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977228,0.00014970919,0.00065398525,0.00054957846,0.000596994,0.0003269055],"domain_scores_gemma":[0.99778795,0.00018887671,0.00029210365,0.0013811323,0.00021808302,0.00013184315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004249364,0.00033038424,0.00049469114,0.00025248973,0.0001596076,0.000088435634,0.00081169384,0.00027879016,0.0000043775467],"category_scores_gemma":[0.00014150681,0.00031021432,0.00012644699,0.000473976,0.000024899588,0.0002593177,0.00017585924,0.00020124287,0.000002593531],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034106686,0.000021176245,0.000030439274,0.000052949323,0.000033178352,0.000014500006,0.000018579445,0.000033774035,0.0000032697403,0.0026025914,0.9792783,0.017907819],"study_design_scores_gemma":[0.00012113235,0.000034321878,0.0056084483,0.000081228194,0.000051906427,0.000007725387,0.0000027426445,0.0035908152,0.00003221695,0.005074734,0.98503906,0.00035564674],"about_ca_topic_score_codex":0.8901312,"about_ca_topic_score_gemma":0.8978095,"teacher_disagreement_score":0.21886344,"about_ca_system_score_codex":0.00020443974,"about_ca_system_score_gemma":0.0005949386,"threshold_uncertainty_score":0.999935},"labels":[],"label_agreement":null},{"id":"W6944930720","doi":"10.22004/ag.econ.274712","title":"Bootstrap and Asymptotic Inference with Multiway Clustering","year":2017,"lang":"en","type":"article","venue":"AgEcon Search (University of Minnesota, USA)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Queen's University; Canada Research Chairs; Danmarks Grundforskningsfond; National Research Foundation","keywords":"Inference; Estimator; Cluster analysis; Regression; Statistical inference; Variance (accounting); Regression analysis; Cluster (spacecraft)","score_opus":0.05304024226592325,"score_gpt":0.28598185899725687,"score_spread":0.23294161673133362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6944930720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.300073,0.000024993824,0.6959626,0.00071991445,0.000034936347,0.00009270251,0.0000028130057,0.000017790358,0.003071257],"genre_scores_gemma":[0.75103414,0.00007101062,0.2479098,0.000024032326,0.00001057285,1.4193272e-7,4.4444562e-7,0.0000042942233,0.00094558566],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989653,0.00008446802,0.00007625408,0.00037708596,0.00021744409,0.00027944057],"domain_scores_gemma":[0.9987406,0.00011461736,0.0001122728,0.00075848924,0.00010313056,0.00017085327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004137027,0.00012129982,0.00021514048,0.000109475506,0.0005319272,0.00014366968,0.0011077638,0.00006904262,0.000036271056],"category_scores_gemma":[0.00002782407,0.00012339762,0.000040176245,0.00007547813,0.00034823254,0.0011202577,0.0006747774,0.00017111591,0.00001440237],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010391421,0.00012781961,0.027717657,0.0002392152,0.00013462451,0.0005429343,0.00984218,0.00007386419,0.0049654827,0.04975091,0.00024247899,0.90625894],"study_design_scores_gemma":[0.0040734406,0.00093471684,0.7178371,0.00037427022,0.000059419726,0.00012868861,0.00089963013,0.2662689,0.0023794663,0.0035505015,0.0025209617,0.0009729004],"about_ca_topic_score_codex":0.00068046903,"about_ca_topic_score_gemma":0.00087289547,"teacher_disagreement_score":0.905286,"about_ca_system_score_codex":0.000017465678,"about_ca_system_score_gemma":0.000072579955,"threshold_uncertainty_score":0.5032009},"labels":[],"label_agreement":null},{"id":"W6954560525","doi":"10.57757/iugg23-3624","title":"Spatial and temporal coverage of a cargo-ship GNSS network to detect tsunamis","year":2023,"lang":"en","type":"article","venue":"Publication Database GFZ (GFZ German Research Centre for Geosciences)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"3v Geomatics (Canada)","funders":"","keywords":"GNSS applications; Limiting; Focus (optics); Hazard; Geodetic datum; Tracking (education)","score_opus":0.05801103294083396,"score_gpt":0.3644085141816554,"score_spread":0.3063974812408214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6954560525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009737508,0.00007098164,0.9754874,0.01175697,0.00028946306,0.0012316674,0.0008286827,0.00015465396,0.00044264193],"genre_scores_gemma":[0.5442666,0.00017347108,0.4483734,0.00086389965,0.0005411281,0.0005146084,0.0012192522,0.00004766537,0.0039999597],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954934,0.0005275206,0.00045402956,0.0010455,0.0012834796,0.0011960351],"domain_scores_gemma":[0.99627906,0.0008749711,0.00015607971,0.0012427048,0.0008302421,0.0006169437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008426102,0.00019347962,0.00027015075,0.0007140724,0.0006414276,0.0005467018,0.0018413254,0.00008359794,0.00003702922],"category_scores_gemma":[0.0018126399,0.00017457182,0.000078208344,0.004425501,0.00024676538,0.0011235939,0.0013052077,0.0002553133,0.000042176536],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009192345,0.00012668734,0.0057447464,0.0002562562,0.000027898472,0.000014046994,0.0015437104,0.000047685495,0.0014544061,0.15822996,0.29141256,0.5410501],"study_design_scores_gemma":[0.0013010165,0.0004310075,0.02835941,0.00013204623,0.000014962058,0.00001739553,0.00007983184,0.32949194,0.0030772344,0.06247488,0.57385504,0.0007652463],"about_ca_topic_score_codex":0.00092370604,"about_ca_topic_score_gemma":0.0006276035,"teacher_disagreement_score":0.5402849,"about_ca_system_score_codex":0.00006929485,"about_ca_system_score_gemma":0.00043396634,"threshold_uncertainty_score":0.71188325},"labels":[],"label_agreement":null},{"id":"W6958507133","doi":"10.6084/m9.figshare.14213793.v1","title":"Assessing the variability of posterior probabilities in Gaussian model-based clustering","year":2021,"lang":"en","type":"other","venue":"Figshare","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate statistics; Posterior probability; Percentile; Gaussian; Cluster analysis; Confidence interval; Pattern recognition (psychology)","score_opus":0.057470035103793275,"score_gpt":0.322011505431299,"score_spread":0.26454147032750575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958507133","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000034804955,0.0005478027,0.82340544,0.0002137751,0.00012467107,0.00055472885,0.008520055,0.000104592815,0.16652544],"genre_scores_gemma":[0.0059122224,0.000002134062,0.963115,0.0005328197,0.00019070589,0.00043524406,0.005226338,0.00026728955,0.024318246],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982315,0.00042911258,0.00031955275,0.000529367,0.00023006598,0.00026044488],"domain_scores_gemma":[0.99822575,0.00024042776,0.0002476095,0.0011743221,0.00006349243,0.00004841106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038112298,0.00024589367,0.00040159616,0.00011940233,0.000035857032,0.00022291888,0.0009923237,0.00025915666,0.013157464],"category_scores_gemma":[0.0004278795,0.0001818095,0.00012783993,0.0002872094,0.000019133879,0.00013111494,0.0004620009,0.00029577853,0.000006402471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002053755,0.00084854366,0.00019598371,0.035652056,0.00020322096,0.00021628068,0.0056855823,0.009401899,0.00065970985,0.009648429,0.5513254,0.38614237],"study_design_scores_gemma":[0.00033068148,0.00002814195,0.00034723425,0.019222131,0.000011375929,0.000011164231,0.000020379937,0.9527694,0.00026613084,0.0056654825,0.020701207,0.0006266571],"about_ca_topic_score_codex":0.000031483138,"about_ca_topic_score_gemma":0.0000988804,"teacher_disagreement_score":0.94336754,"about_ca_system_score_codex":0.000057495934,"about_ca_system_score_gemma":0.000490368,"threshold_uncertainty_score":0.9877446},"labels":[],"label_agreement":null},{"id":"W6977229820","doi":"10.6084/m9.figshare.24532011.v1","title":"Additional file 1 of A model-based clustering via mixture of hierarchical models with covariate adjustment for detecting differentially expressed genes from paired design","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Covariate; Cluster analysis; Hierarchical clustering; Pattern recognition (psychology); Mixture model","score_opus":0.08305012066462882,"score_gpt":0.2610435987936934,"score_spread":0.17799347812906458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977229820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004992908,0.000012473381,0.520905,0.00001345218,0.000012128053,0.00024637254,0.4787251,0.00006797465,0.000012523855],"genre_scores_gemma":[0.0045002936,3.4879838e-7,0.8025172,0.000051510204,0.00005452027,0.0014853751,0.1913348,0.000024793071,0.000031208478],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985225,0.00012987498,0.00030232305,0.00044804078,0.0003122065,0.00028504233],"domain_scores_gemma":[0.99626946,0.0027756076,0.00024240372,0.0004153217,0.0002033921,0.00009381727],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000076533535,0.00020143937,0.00032358326,0.00011802609,0.00008537044,0.000034956072,0.00054409384,0.00012388176,0.09056981],"category_scores_gemma":[0.000324484,0.00017294582,0.00013817922,0.00026529632,0.00001217727,0.0001768145,0.00019257679,0.00011277789,0.000007602073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023521557,0.000103430866,5.3953663e-8,0.00038859723,0.00010541293,0.000008983242,0.00042263328,0.3177505,0.007827154,0.00010467808,0.59428716,0.07876619],"study_design_scores_gemma":[0.00050824654,0.00012714122,0.000022459522,0.0014815906,0.0000122101055,9.874618e-7,0.0000021885999,0.9711107,0.009320732,0.01689591,0.00032781524,0.00018999836],"about_ca_topic_score_codex":0.0000042146353,"about_ca_topic_score_gemma":0.0000059207173,"teacher_disagreement_score":0.6533602,"about_ca_system_score_codex":0.000020053101,"about_ca_system_score_gemma":0.00023348328,"threshold_uncertainty_score":0.9102615},"labels":[],"label_agreement":null},{"id":"W6977731907","doi":"10.7298/s72q-8b68","title":"Heteroscedastic Functional Data Models","year":2022,"lang":"en","type":"article","venue":"eCommons (Cornell University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; National Aeronautics and Space Administration; Langley Research Center; University of Toronto; National Science Foundation","keywords":"","score_opus":0.11504318774182604,"score_gpt":0.2218560307140897,"score_spread":0.10681284297226368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977731907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030101356,0.000037759386,0.9787718,0.00021697648,0.0005385625,0.00008630062,0.00006787789,0.00016163061,0.01710893],"genre_scores_gemma":[0.9046721,0.000007643948,0.09078786,0.0003225513,0.000046728626,0.0000010667775,0.000051133735,0.000011616402,0.0040993225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857545,0.0002516542,0.00010884727,0.00064703793,0.0001540026,0.00026300704],"domain_scores_gemma":[0.9981652,0.00009931166,0.00006566837,0.0015187957,0.000027484492,0.00012354142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033132223,0.00012750723,0.00014081132,0.00020265573,0.000490409,0.00005597576,0.0025780515,0.000032266613,0.00018975802],"category_scores_gemma":[0.000008056227,0.00015250623,0.0000655989,0.0006574287,0.000036094934,0.00090477004,0.0036697213,0.00029494741,0.000028556287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023243712,0.00015968489,0.00020923806,0.000004961931,0.000036109595,0.00016223794,0.00011899392,0.07565619,0.000060520266,0.9058045,0.011424725,0.00633957],"study_design_scores_gemma":[0.0003388588,0.000052739622,0.00030717556,0.0000018568414,0.000014595243,0.000039392027,0.0000262105,0.8943387,0.000009740049,0.08995791,0.014710717,0.00020210318],"about_ca_topic_score_codex":0.000029701092,"about_ca_topic_score_gemma":0.000018664014,"teacher_disagreement_score":0.90166193,"about_ca_system_score_codex":0.000107720945,"about_ca_system_score_gemma":0.00009783093,"threshold_uncertainty_score":0.62190235},"labels":[],"label_agreement":null},{"id":"W6979247723","doi":"","title":"Two statistical problems for multivariate mixture distributions","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Agencia Nacional de Investigación e Innovación","keywords":"Univariate; Multivariate statistics; Set (abstract data type); Multivariate normal distribution; Univariate distribution; Gaussian; Multivariate analysis; Mixture model; Statistical parameter","score_opus":0.03368575498561898,"score_gpt":0.3329479365117014,"score_spread":0.2992621815260824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979247723","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024574792,0.000118398064,0.9920528,0.0029434871,0.0005204086,0.00040413233,0.000092923,0.00014197968,0.0012683751],"genre_scores_gemma":[0.32881755,0.00000459617,0.6694565,0.0005044066,0.0000648633,0.000105057276,0.00002825762,0.000006861798,0.0010119419],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987858,0.00009628022,0.00023148849,0.00044280261,0.00009470135,0.00034891444],"domain_scores_gemma":[0.9989218,0.00032877043,0.000051531097,0.0004850417,0.00011698532,0.00009585492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035173507,0.00014831124,0.00019231628,0.00005415343,0.00022087444,0.00008272646,0.0005149065,0.000079783924,0.000009657859],"category_scores_gemma":[0.00021379204,0.00012501529,0.00007747134,0.00031800356,0.000053582917,0.00017556008,0.00017399523,0.00017076723,0.000020576836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060565026,0.000076846205,0.0030582338,0.000032959102,0.00002943727,0.0000034517577,0.00009674534,0.000009240542,0.002326915,0.96574247,0.003711127,0.024906505],"study_design_scores_gemma":[0.0023655463,0.00014202119,0.06683935,0.00013091296,0.00008532911,0.000009381548,0.000009436316,0.083871044,0.0068180757,0.769261,0.069875605,0.0005923066],"about_ca_topic_score_codex":0.000037193317,"about_ca_topic_score_gemma":0.000013176497,"teacher_disagreement_score":0.32636008,"about_ca_system_score_codex":0.000039115122,"about_ca_system_score_gemma":0.000109329216,"threshold_uncertainty_score":0.5097976},"labels":[],"label_agreement":null},{"id":"W6979277440","doi":"","title":"Cluster weighted models for functional data","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Functional data analysis; Multivariate statistics; Benchmark (surveying); Functional principal component analysis; Cluster (spacecraft); Clustering high-dimensional data; Construct (python library); Expectation–maximization algorithm","score_opus":0.10763125312125821,"score_gpt":0.31876034128998826,"score_spread":0.21112908816873005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979277440","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032965,0.00021669574,0.9866047,0.0044406974,0.00092394627,0.00023820887,0.000017854392,0.00012033498,0.004141085],"genre_scores_gemma":[0.1757113,0.000016505568,0.8124829,0.005438363,0.00022442796,0.00005271587,0.000057563862,0.000012494343,0.0060037063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876916,0.000062420615,0.00020192501,0.0005889416,0.00012443111,0.00025311738],"domain_scores_gemma":[0.99827766,0.0001975154,0.000046008467,0.0013212176,0.00009731196,0.000060260423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048274468,0.00012833797,0.00015615503,0.000087431894,0.00014968072,0.00007122255,0.0012121107,0.00008543945,0.000010594965],"category_scores_gemma":[0.000042004478,0.00010949157,0.000060635117,0.00027272315,0.000028997454,0.0007523513,0.0006787609,0.000114807925,0.000022445704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046512265,0.000111752,0.0030318988,0.00004982696,0.00009769881,0.0000030946865,0.0001225725,0.0001364538,0.00057939626,0.7913612,0.1043185,0.100141086],"study_design_scores_gemma":[0.00058680464,0.000020885518,0.0027539087,0.000021576217,0.00002020511,0.0000029006442,0.0000022798688,0.74440753,0.000551033,0.22075348,0.030721564,0.00015783879],"about_ca_topic_score_codex":0.0000079616375,"about_ca_topic_score_gemma":0.000005743261,"teacher_disagreement_score":0.7442711,"about_ca_system_score_codex":0.000021495316,"about_ca_system_score_gemma":0.000121436424,"threshold_uncertainty_score":0.44649366},"labels":[],"label_agreement":null},{"id":"W6986452753","doi":"","title":"On prediction and estimation problems for some multivariate distributions","year":2023,"lang":"en","type":"dissertation","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Minimax; Multivariate statistics; Minimax estimator; Univariate; Bayes' theorem; Estimator; Bayes estimator; Multivariate normal distribution; Scale parameter; Density estimation","score_opus":0.016205884640484544,"score_gpt":0.2403950380567098,"score_spread":0.22418915341622525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986452753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014854395,0.00070182304,0.98152804,0.00007245247,0.0009500661,0.00061827136,0.00009400611,0.00006958442,0.0011113635],"genre_scores_gemma":[0.7096467,0.0004901633,0.2822161,0.000011318345,0.00009905188,0.000012559707,0.0005418371,0.000028012513,0.006954238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989793,0.00007019666,0.00023233997,0.00034904658,0.00022294732,0.00014617879],"domain_scores_gemma":[0.9991603,0.0001306159,0.00017451723,0.00030131024,0.00017598913,0.000057302535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022662559,0.00018408327,0.00026050516,0.00016016353,0.0005212028,0.000024103058,0.0005719511,0.00019091489,0.0000012022671],"category_scores_gemma":[0.00009341203,0.00016800384,0.00019570075,0.00024385618,0.00014107776,0.00029522748,0.00011917171,0.00017022136,0.000004560485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014659551,0.00030355187,0.00003218639,0.005262778,0.00021500509,0.0000019343497,0.0052353726,0.015948996,0.011554958,0.91988975,0.0013946205,0.040014256],"study_design_scores_gemma":[0.0014206358,0.0002641462,0.02697372,0.0074393894,0.00032727313,0.000008640639,0.00004959703,0.798526,0.022003038,0.1411999,0.0013962447,0.00039145458],"about_ca_topic_score_codex":0.00018010737,"about_ca_topic_score_gemma":0.0008106541,"teacher_disagreement_score":0.782577,"about_ca_system_score_codex":0.00031326123,"about_ca_system_score_gemma":0.00016084586,"threshold_uncertainty_score":0.6850998},"labels":[],"label_agreement":null},{"id":"W6986511404","doi":"","title":"Presidentieel vliegtuig Mexico eindelijk verkocht","year":2023,"lang":"nl","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Liberian dollar; Quarter (Canadian coin)","score_opus":0.010189031799015565,"score_gpt":0.210531242597458,"score_spread":0.20034221079844244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986511404","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010088175,0.00082857016,0.003915471,0.00059843704,0.00285812,0.0009455645,0.00015159957,0.0006733112,0.99001884],"genre_scores_gemma":[0.00016585716,0.001069282,0.044546474,0.0007131269,0.00043092135,0.00003913524,0.00004381972,0.00030406791,0.9526873],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946364,0.00041837574,0.0017810898,0.0008224281,0.0013483034,0.0009933978],"domain_scores_gemma":[0.9956459,0.0004197629,0.0014251864,0.001591818,0.0004957174,0.00042165953],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012401448,0.00090557593,0.001143851,0.0002594019,0.00024962408,0.00042702115,0.002082734,0.001125777,0.3271275],"category_scores_gemma":[0.00038587922,0.00095501496,0.0006066647,0.00005055894,0.0002897094,0.0000014928459,0.0007392368,0.00084623025,0.1581386],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006746686,0.00008702652,0.0000024070582,0.0005893209,0.00019817121,0.000092106784,0.00039640267,0.00033366538,7.506738e-7,0.0015711929,0.96995264,0.02670885],"study_design_scores_gemma":[0.0008950417,0.00027324536,0.000043247906,0.00075714674,0.0001418444,0.00012934225,0.000037900445,0.0013525386,0.000043478758,0.0006462192,0.99473816,0.00094185775],"about_ca_topic_score_codex":0.0043281177,"about_ca_topic_score_gemma":0.00080828444,"teacher_disagreement_score":0.16898888,"about_ca_system_score_codex":0.00014365317,"about_ca_system_score_gemma":0.0001795381,"threshold_uncertainty_score":0.99929005},"labels":[],"label_agreement":null},{"id":"W6991592060","doi":"","title":"Hyperbolic Distributions and Transformations for Clustering Incomplete Data with Extensions to Matrix Variate Normality","year":2023,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Cluster analysis; Normality; Transformation (genetics); Computation; Set (abstract data type); Data set; Random variate","score_opus":0.03453736489314859,"score_gpt":0.2752885511418369,"score_spread":0.24075118624868833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991592060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046121803,0.000033771106,0.9828713,0.00048430674,0.00028974246,0.0007782912,0.001037292,0.00021601644,0.0138280885],"genre_scores_gemma":[0.004510664,0.00007869316,0.85026807,0.0001379058,0.00010184518,0.000020359379,0.0026460479,0.00006870541,0.14216773],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99829423,0.00010087694,0.0002474838,0.0007648717,0.0001934912,0.00039902542],"domain_scores_gemma":[0.9984165,0.00013711314,0.00012677322,0.0009144111,0.00016363403,0.00024158877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002509482,0.00031251137,0.00037519308,0.00023695164,0.0005334256,0.00022429187,0.0012960602,0.00017531685,0.00019416213],"category_scores_gemma":[0.000021869824,0.00030933565,0.0000733171,0.0009044157,0.00002932126,0.00080531696,0.00045903286,0.00023499077,0.000014883787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002918703,0.0000875967,0.00003773438,0.00065191806,0.00028087382,0.00006950101,0.0039216196,0.0002828459,0.00035878553,0.100222096,0.0017551495,0.89204],"study_design_scores_gemma":[0.004166836,0.000608523,0.009403381,0.0011957594,0.001202728,0.000097884615,0.0026492153,0.26651725,0.0002029835,0.010531155,0.7005265,0.00289782],"about_ca_topic_score_codex":0.00019379282,"about_ca_topic_score_gemma":0.0034478756,"teacher_disagreement_score":0.8891422,"about_ca_system_score_codex":0.000069121335,"about_ca_system_score_gemma":0.00015373793,"threshold_uncertainty_score":0.99993587},"labels":[],"label_agreement":null},{"id":"W7015263742","doi":"","title":"Statistical Analysis of Spherical Data:&#13;\\nClustering, Feature Selection and&#13;\\nApplications","year":2014,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Concordia University","keywords":"Feature (linguistics); Frame (networking); Probabilistic logic; Feature selection; Selection (genetic algorithm); Set (abstract data type)","score_opus":0.029240714182181795,"score_gpt":0.3188399201044142,"score_spread":0.2895992059222324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015263742","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05326608,0.00013174007,0.9219264,0.00027549418,0.0002754424,0.00037546986,0.000060394017,0.000100232006,0.023588791],"genre_scores_gemma":[0.91134906,0.000279214,0.061088495,0.000016412283,0.0003161822,0.000008747269,0.00086783676,0.000049864906,0.026024204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9959936,0.0009538824,0.00032626753,0.0013602024,0.0008090986,0.0005569441],"domain_scores_gemma":[0.9968345,0.00051905116,0.0002883585,0.0016215633,0.0003758091,0.00036071384],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000973139,0.00030058052,0.00071137387,0.0014337429,0.00055105734,0.00023918683,0.0021316153,0.00044810213,0.000022551163],"category_scores_gemma":[0.000114967166,0.00032298715,0.00016053015,0.0036500623,0.00019793013,0.00043968073,0.00075571245,0.0011399921,0.000004548979],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016860988,0.0012515336,0.087104514,0.0020243214,0.010981557,0.0008756749,0.003402853,0.00044138718,0.030622905,0.6818326,0.025846181,0.15393037],"study_design_scores_gemma":[0.0012126666,0.0010213433,0.6391614,0.00020714782,0.0029598635,0.000063396285,0.0005041198,0.26469493,0.0072102877,0.009547833,0.071736634,0.00168039],"about_ca_topic_score_codex":0.008787651,"about_ca_topic_score_gemma":0.03326405,"teacher_disagreement_score":0.8608379,"about_ca_system_score_codex":0.00023201566,"about_ca_system_score_gemma":0.00063565315,"threshold_uncertainty_score":0.9999222},"labels":[],"label_agreement":null},{"id":"W7017419279","doi":"","title":"Bayesian Methods for Data Integration and High Dimensional Linear Model with Non-Sparsity","year":2025,"lang":"en","type":"other","venue":"York University Digital Library (York University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Markov chain Monte Carlo; Model selection; Bayesian probability; Consistency (knowledge bases); Information Criteria; Data integration; Bayesian inference; Marginal likelihood; Bayesian linear regression; Importance sampling","score_opus":0.020267789495494036,"score_gpt":0.23171543933857325,"score_spread":0.2114476498430792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017419279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003097884,0.00008826376,0.78348213,0.00033458116,0.00012550264,0.0004445109,0.0015492989,0.00041542755,0.21355718],"genre_scores_gemma":[0.00014185252,0.000051588893,0.59427065,0.000105179955,0.000044792483,1.2067969e-7,0.00073294056,0.00006148995,0.4045914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772054,0.00015806862,0.00014696397,0.0013737171,0.00020215893,0.0003985271],"domain_scores_gemma":[0.9977819,0.00023466891,0.0002475928,0.0013825039,0.000052575084,0.0003008094],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010582437,0.0005081645,0.00058871787,0.00096284697,0.00030616045,0.00031206946,0.0026725726,0.00046649083,0.000032055766],"category_scores_gemma":[0.000014664386,0.0005247903,0.00013151276,0.0010530954,0.0002296841,0.0029933392,0.0024690486,0.00037193016,0.0000052786636],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046506882,0.00022385207,0.000087551714,0.00018546764,0.00048557835,0.00015972737,0.00012970241,0.00018073646,0.000007732287,0.42985332,0.38094246,0.1872788],"study_design_scores_gemma":[0.0013752745,0.00015735524,0.000010427268,0.0004015106,0.00021732146,0.000008261043,0.00007388088,0.34310004,0.000038774557,0.006196169,0.64756036,0.00086065393],"about_ca_topic_score_codex":0.00008395819,"about_ca_topic_score_gemma":0.000029545687,"teacher_disagreement_score":0.42365715,"about_ca_system_score_codex":0.00006757904,"about_ca_system_score_gemma":0.00070171704,"threshold_uncertainty_score":0.9997204},"labels":[],"label_agreement":null},{"id":"W7019357830","doi":"","title":"Functional assessment of articular cartilage using injury-induced changes in solute transport and improved mechanical characterization","year":2014,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cartilage; Osteoarthritis; Articular cartilage; Articular cartilage damage; Cartilage damage; Extracellular matrix; Matrix (chemical analysis)","score_opus":0.02386394731891035,"score_gpt":0.2718387119487964,"score_spread":0.24797476462988605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019357830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9474511,0.000021845553,0.050130982,0.000028786564,0.001020245,0.00063934707,0.00014400443,0.00008775542,0.00047592347],"genre_scores_gemma":[0.9434936,0.000045020734,0.055684537,0.00014147758,0.00004418359,0.00007679689,0.00029811426,0.00006806008,0.0001482057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964815,0.0004788761,0.00084390084,0.0010847978,0.0006020912,0.00050885364],"domain_scores_gemma":[0.99814755,0.00008076454,0.00063567655,0.00064870797,0.0002809836,0.00020634131],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016414741,0.00052908796,0.0008329134,0.00045985891,0.00029153607,0.000063985375,0.0004683178,0.00068104384,0.000016475939],"category_scores_gemma":[0.000085118045,0.0005518459,0.00017578028,0.0005205789,0.00002526965,0.000702026,0.0001064559,0.0008243736,0.000001579986],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004468166,0.0000848318,0.000010828957,0.00017266988,0.000032403994,0.000009366204,0.00001052501,0.0000019584077,0.8425222,0.0757017,4.0573724e-8,0.08140878],"study_design_scores_gemma":[0.0012035813,0.00041374852,0.013094691,0.0005583782,0.0002067801,0.00002163633,0.000020955098,0.026007958,0.93695974,0.020063575,0.00031312948,0.0011358184],"about_ca_topic_score_codex":0.000089989684,"about_ca_topic_score_gemma":0.000621072,"teacher_disagreement_score":0.094437525,"about_ca_system_score_codex":0.00024372278,"about_ca_system_score_gemma":0.000104793355,"threshold_uncertainty_score":0.9996933},"labels":[],"label_agreement":null},{"id":"W7023609750","doi":"","title":"Petroleum potential of cretaceous and tertiary sedements of the Mackenzie Delta (Canada) influence of organic facies variations and gas system","year":2010,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Delta; Facies; Cretaceous; Petroleum; Fossil fuel; Petroleum system","score_opus":0.0038109675565598604,"score_gpt":0.19403219453752804,"score_spread":0.1902212269809682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023609750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4862204,0.00003778736,0.51325256,0.00023792646,0.00007514038,0.00006361736,0.000012939643,0.0000061110427,0.00009352877],"genre_scores_gemma":[0.93459016,0.0000066116204,0.065310754,0.000052978656,0.0000060590105,0.0000015021307,3.8396973e-7,0.0000032939388,0.00002826307],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991658,0.00007018627,0.00025842717,0.00016038868,0.00023788962,0.0001073615],"domain_scores_gemma":[0.99924755,0.000053841995,0.000169273,0.000371657,0.00011059593,0.000047077556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023857711,0.00008177645,0.00016380519,0.000035091518,0.000063935404,0.000018904753,0.00037944672,0.00004506127,0.000004724174],"category_scores_gemma":[0.00003347667,0.00005474901,0.000023366913,0.00011428414,0.00009044801,0.00012646875,0.00026462678,0.00008428133,4.2668233e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011006274,0.000064717984,0.026632879,0.00044241146,0.00012531977,0.000004711569,0.00072375144,0.00016117474,0.79343003,0.16859443,0.00013864477,0.009670893],"study_design_scores_gemma":[0.0012363152,0.0001576366,0.52074194,0.00018688453,0.00017586462,0.00021180543,0.00016215765,0.23001313,0.23497906,0.011564545,0.0001355132,0.00043514735],"about_ca_topic_score_codex":0.006599348,"about_ca_topic_score_gemma":0.012129077,"teacher_disagreement_score":0.558451,"about_ca_system_score_codex":0.0000069668195,"about_ca_system_score_gemma":0.00016382927,"threshold_uncertainty_score":0.99762845},"labels":[],"label_agreement":null},{"id":"W7023949744","doi":"","title":"Practical issues in modern Monte Carlo integration","year":2007,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal likelihood; Monte Carlo method; Monte Carlo integration; Grid; Bayesian probability; Importance sampling; Model selection; Selection (genetic algorithm); Adaptive quadrature","score_opus":0.03154417034936258,"score_gpt":0.3359818055873327,"score_spread":0.30443763523797013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023949744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46803054,0.0037770432,0.16491911,0.0008493056,0.010937918,0.004377615,0.00046389966,0.0021607953,0.34448376],"genre_scores_gemma":[0.5006368,0.00042379857,0.48690757,0.0005521463,0.00011565429,0.00013449436,0.00014999691,0.00016743185,0.010912087],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99413705,0.00080621237,0.0011979106,0.0017291991,0.0011491802,0.0009804216],"domain_scores_gemma":[0.9967223,0.0004047751,0.00058687443,0.001392754,0.0005059481,0.00038737376],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0027612962,0.0008824896,0.000957497,0.0008744098,0.0004756394,0.000316008,0.0014057959,0.0013607417,0.000029719406],"category_scores_gemma":[0.001069397,0.00088362675,0.0003537974,0.0010419972,0.00004457191,0.0024387788,0.00022923741,0.0028494147,0.000100561505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079953345,0.00017194565,0.0000033851545,0.00007500109,0.00004072525,0.00021491348,0.00006106212,0.000017808221,0.0053336774,0.37991253,0.000018206312,0.6140708],"study_design_scores_gemma":[0.0021094442,0.00051458663,0.0011155498,0.0016577234,0.00021674449,0.00021389242,0.0004384828,0.03860271,0.1382903,0.7760631,0.03673986,0.004037634],"about_ca_topic_score_codex":0.00075590936,"about_ca_topic_score_gemma":0.0046752845,"teacher_disagreement_score":0.61003315,"about_ca_system_score_codex":0.00068090996,"about_ca_system_score_gemma":0.00013385723,"threshold_uncertainty_score":0.9999357},"labels":[],"label_agreement":null},{"id":"W7024306702","doi":"","title":"A reversible jump MCMC for mixture of t factor analyzers","year":2024,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Markov chain Monte Carlo; Cluster analysis; Outlier; Reversible-jump Markov chain Monte Carlo; Field (mathematics); Bayesian probability; Mixture model; Monte Carlo method; Markov chain","score_opus":0.016483573533467497,"score_gpt":0.24500356463958542,"score_spread":0.22851999110611793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024306702","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002744963,0.00057027274,0.75632966,0.00010900953,0.0011516812,0.0004362094,0.000107235974,0.00012399149,0.24089746],"genre_scores_gemma":[0.0011161637,0.00006375619,0.21828058,0.00005495751,0.00008687976,0.0000022794338,0.00009352347,0.000042767613,0.7802591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981774,0.00009594754,0.00027178245,0.0008090601,0.00028001852,0.00036575957],"domain_scores_gemma":[0.99870574,0.00010153657,0.00026628486,0.0005644434,0.00021618218,0.00014582355],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012766792,0.00039363143,0.00055843237,0.0004701724,0.00009995331,0.00010730825,0.0013185468,0.0004806888,0.0045357267],"category_scores_gemma":[0.000016918359,0.000402093,0.00051320106,0.0010705593,0.000034389086,0.00037789877,0.00015967835,0.00036817073,0.000024319885],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018473277,0.00006943784,0.000035191555,0.0018378999,0.00048024138,0.000090018715,0.0036337501,0.000012249256,0.0017105832,0.0797028,0.01007371,0.9021694],"study_design_scores_gemma":[0.00121297,0.00030725877,0.0001294628,0.0009193494,0.000608841,0.0000044022136,0.0011588223,0.006905308,0.00871729,0.015650153,0.96323717,0.0011489686],"about_ca_topic_score_codex":0.000059244823,"about_ca_topic_score_gemma":0.00027015214,"teacher_disagreement_score":0.95316344,"about_ca_system_score_codex":0.00012285105,"about_ca_system_score_gemma":0.00026674967,"threshold_uncertainty_score":0.9998431},"labels":[],"label_agreement":null},{"id":"W7024781488","doi":"","title":"Three Essays in Cluster Robust Machine Learning and High-Dimensional Econometrics","year":2020,"lang":"en","type":"dissertation","venue":"Discover Archive (Vanderbilt University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of North Carolina at Chapel Hill; University of Illinois at Urbana-Champaign; Erasmus Universiteit Rotterdam; University College London; McGill University; Johns Hopkins University; Queen Mary University of London; Vanderbilt University","keywords":"Cluster (spacecraft); Cluster analysis; Feature (linguistics); Robustness (evolution); Statistical learning","score_opus":0.01686901899542301,"score_gpt":0.21290110267197337,"score_spread":0.19603208367655037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024781488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004588288,0.0003293183,0.96946436,0.0003016028,0.00032282155,0.0002784555,0.000038933365,0.000070948925,0.024605298],"genre_scores_gemma":[0.26379305,0.0015499924,0.71024746,0.00070982205,0.0002785063,0.000007987455,0.0024038765,0.00017582955,0.020833474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979981,0.00020209407,0.00024448422,0.00095164636,0.0002507865,0.000352846],"domain_scores_gemma":[0.99897325,0.00030180975,0.00020345746,0.00028646312,0.000039868144,0.00019517445],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019204106,0.0003776726,0.00050405005,0.0010691055,0.00019762473,0.00014816651,0.00067204057,0.00018921391,0.000022495176],"category_scores_gemma":[0.000055688044,0.00039097504,0.00013726679,0.0008405495,0.000059771897,0.00059080706,0.0004868377,0.0008885226,0.00000947211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066262274,0.0002539376,0.006097163,0.00048606846,0.00029755762,0.0008741402,0.0048547746,0.005281891,0.00019424592,0.9011503,0.0008809938,0.078966334],"study_design_scores_gemma":[0.005596511,0.00048482406,0.017567849,0.00046604473,0.00021400854,0.00002985852,0.00039047387,0.7761673,0.00015194705,0.18141952,0.015202938,0.0023087393],"about_ca_topic_score_codex":0.000289131,"about_ca_topic_score_gemma":0.0026789652,"teacher_disagreement_score":0.7708854,"about_ca_system_score_codex":0.00009201784,"about_ca_system_score_gemma":0.0002107814,"threshold_uncertainty_score":0.9998542},"labels":[],"label_agreement":null},{"id":"W7025387184","doi":"","title":"The World’s Best Typography: The 65th Annual Exhibition of the Type Directors Club (USA)","year":2019,"lang":"en","type":"other","venue":"Document Server@UHasselt (UHasselt)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Exhibition; Typography; Club; Type (biology)","score_opus":0.012129620036306374,"score_gpt":0.2761208074421951,"score_spread":0.2639911874058887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025387184","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025307059,0.01628746,0.12813088,0.016363239,0.024854474,0.0085528605,0.00031130467,0.001096448,0.8018726],"genre_scores_gemma":[0.020487348,0.0017901087,0.014756198,0.0014787428,0.0012051185,0.00019933327,0.00004855144,0.00060487597,0.95942974],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943356,0.0012901275,0.0008224841,0.0011544294,0.0014406218,0.0009567456],"domain_scores_gemma":[0.9937696,0.0006329441,0.0011836871,0.003941346,0.00029039543,0.00018206665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020889223,0.0008763526,0.00082717626,0.0003840591,0.0005929942,0.0005570581,0.004922919,0.0004599701,0.00030826562],"category_scores_gemma":[0.00008347585,0.0004595409,0.0007120397,0.0022613208,0.0003735892,0.00045157003,0.0010958612,0.0010065376,0.0002975796],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040862695,0.00024697444,0.0009868413,0.00019311724,0.0005673365,0.000008205501,0.00051155634,0.000018519448,0.00010678764,0.25893822,0.7226574,0.015724188],"study_design_scores_gemma":[0.00066200754,0.00022366227,0.0019455448,0.0006048987,0.00021238804,0.000013436541,0.00007047239,0.0002062794,0.000566297,0.012772494,0.98188883,0.0008336768],"about_ca_topic_score_codex":0.0011703908,"about_ca_topic_score_gemma":0.0037137945,"teacher_disagreement_score":0.25923145,"about_ca_system_score_codex":0.00014841025,"about_ca_system_score_gemma":0.0003827034,"threshold_uncertainty_score":0.99978566},"labels":[],"label_agreement":null},{"id":"W7026722033","doi":"","title":"On asymptotics results for a Poisson mixture model [working paper]","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mixture model; Poisson distribution; Mixture theory; Work (physics); Sequence (biology)","score_opus":0.02567007750615567,"score_gpt":0.2658759117407112,"score_spread":0.24020583423455552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7026722033","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003128817,0.000030405348,0.9471728,0.006546224,0.0002323885,0.00041726587,0.0000031200072,0.00018086396,0.045104034],"genre_scores_gemma":[0.14462756,0.000006117093,0.8454729,0.004695698,0.000089464156,0.000047059708,0.000002564199,0.000013561028,0.0050451024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986234,0.00004850002,0.0002504852,0.0004938082,0.00020112205,0.00038270638],"domain_scores_gemma":[0.99870646,0.00029547536,0.00007361353,0.00068649434,0.00010166912,0.00013626192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039245488,0.0001790148,0.00018169351,0.000065443404,0.00012453125,0.00022727167,0.0006549969,0.0001410336,0.000008397722],"category_scores_gemma":[0.0001118247,0.00013156924,0.00010684921,0.0001614584,0.000015340393,0.0003364165,0.000114191535,0.0001509397,0.000040200128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013452592,0.000039609917,8.305257e-7,0.0000063907214,0.000008519499,8.1980824e-7,0.00030343718,0.0008546852,0.00090640533,0.84247065,0.035727456,0.11966776],"study_design_scores_gemma":[0.00035988961,0.000075590935,0.000012593836,0.000018899984,0.0000030165922,0.0000019517804,0.0000020355506,0.60880756,0.0008645325,0.3878463,0.0018665802,0.00014106797],"about_ca_topic_score_codex":0.0000149215175,"about_ca_topic_score_gemma":0.0000057861807,"teacher_disagreement_score":0.60795283,"about_ca_system_score_codex":0.000027266808,"about_ca_system_score_gemma":0.000041561958,"threshold_uncertainty_score":0.5365238},"labels":[],"label_agreement":null},{"id":"W7026971958","doi":"","title":"AVG ~~~ 18O`O88`2O652 AVG ``customer ```service``` phone number, 18O~O88~2O~652 AvG antivirus tech support number","year":2016,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; Telephone number; Toll; Service (business); Phone call","score_opus":0.014840188947361528,"score_gpt":0.2851260976773956,"score_spread":0.27028590873003405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7026971958","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046089383,0.0000072894204,0.3824188,0.0005230343,0.0013353644,0.0012261968,0.00009144657,0.00095352455,0.61339825],"genre_scores_gemma":[0.00071103143,0.00060043635,0.13399684,0.0012580921,0.00072548905,0.00050925615,0.000047395024,0.000730885,0.8614206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863458,0.0017846067,0.0017169274,0.006229615,0.0018055028,0.002117492],"domain_scores_gemma":[0.98585933,0.00070962554,0.0015580205,0.010378667,0.0004900562,0.0010043061],"candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0061805,0.0018580725,0.0020616287,0.0006845894,0.00041622852,0.00069018925,0.007672272,0.0019528734,0.8625676],"category_scores_gemma":[0.0006360726,0.0017716681,0.00091276184,0.0014742443,0.00042386798,0.00092847546,0.0060907067,0.0019179094,0.9924085],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064611515,0.00064605434,0.0010093383,0.00034293655,0.0005101899,0.00026869262,0.0006329872,0.0000035314993,0.0014720351,0.018345999,0.9177051,0.05899848],"study_design_scores_gemma":[0.0014821095,6.9607853e-7,0.0002310464,0.00044677025,0.00019870375,0.00042700578,0.000023471715,0.00026583302,0.0036830676,0.014660868,0.9763913,0.0021891138],"about_ca_topic_score_codex":0.0012907933,"about_ca_topic_score_gemma":0.00022016442,"teacher_disagreement_score":0.24842198,"about_ca_system_score_codex":0.000551886,"about_ca_system_score_gemma":0.00093424873,"threshold_uncertainty_score":0.99941635},"labels":[],"label_agreement":null},{"id":"W7027369374","doi":"","title":"Count Data Modeling and Classification Using Statistical &#13;\\nHierarchical Approaches and Multi-topic Models","year":2014,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nucleofection; TSG101; Gestational period; Hyporeflexia; Dysgeusia; Articular cartilage damage","score_opus":0.18376229121590074,"score_gpt":0.34133859552774315,"score_spread":0.1575763043118424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7027369374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088546194,0.00040935146,0.9035606,0.0001596196,0.00025711578,0.0004236489,0.000024512277,0.00007375866,0.006545208],"genre_scores_gemma":[0.8708395,0.00040093207,0.12604895,0.000010027921,0.00020959263,0.000003209449,0.00019136892,0.000042453,0.0022539673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954369,0.0011909697,0.00033824486,0.0016599064,0.0007252369,0.00064874964],"domain_scores_gemma":[0.9974007,0.00036672372,0.00015031155,0.0014600847,0.0001839918,0.00043817153],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014976459,0.00034189827,0.0004901485,0.0007466764,0.00081739516,0.0005721116,0.0015957091,0.00044623984,0.0000014835721],"category_scores_gemma":[0.00008268999,0.00036388653,0.000051692332,0.00042895172,0.0003036077,0.0009972396,0.00090639136,0.0013248464,0.000001601397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032854947,0.00023143648,0.0010245416,0.00080653327,0.00024374263,0.00039929,0.0017770891,0.0007487296,0.0024670064,0.92390305,0.000117845164,0.06795219],"study_design_scores_gemma":[0.00043076786,0.00008224685,0.0015909619,0.00009666047,0.00005550209,0.000032301992,0.00019783466,0.976547,0.00009152221,0.020231737,0.00028464626,0.00035882957],"about_ca_topic_score_codex":0.0029153414,"about_ca_topic_score_gemma":0.002158816,"teacher_disagreement_score":0.97579825,"about_ca_system_score_codex":0.00023365948,"about_ca_system_score_gemma":0.00077111897,"threshold_uncertainty_score":0.9998813},"labels":[],"label_agreement":null},{"id":"W7030255779","doi":"","title":"Model Selection via Minimum Description Length","year":2011,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Minimum description length; Model selection; Categorical variable; Bayesian information criterion; Context (archaeology); Lasso (programming language); Population; Selection (genetic algorithm); Bayesian probability; Statistical model","score_opus":0.007966905076340727,"score_gpt":0.16530633258286434,"score_spread":0.1573394275065236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030255779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064500654,0.0003274185,0.7146323,0.00029421036,0.00067578035,0.00020979595,0.000035205554,0.000029423072,0.2773458],"genre_scores_gemma":[0.6436525,0.00030084344,0.26939145,0.0008748515,0.00010323977,0.000025802268,0.00004686966,0.000050766874,0.08555369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976805,0.00008334862,0.0003314977,0.0004393834,0.001165028,0.00030026928],"domain_scores_gemma":[0.99916655,0.00005985028,0.00027841856,0.0002729176,0.0000014199129,0.0002208565],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000017270111,0.00028420804,0.00031447652,0.000048295446,0.00017037278,0.000046154593,0.00047764028,0.000091132926,0.000009735958],"category_scores_gemma":[0.0000016668806,0.0002840919,0.000046726567,0.00010360503,0.000020250343,0.00073977717,0.00007939175,0.00024858236,2.2316828e-9],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040546345,0.000060053993,0.00033923096,0.0004854472,0.00013736219,0.0000328201,0.000764185,0.00008884608,0.0552175,0.7194975,0.0017359207,0.22123565],"study_design_scores_gemma":[0.00046236592,0.00016816946,0.005843977,0.00031459166,0.0000872271,0.00001855279,0.00041744564,0.62079114,0.20485508,0.16264677,0.0033313893,0.0010633107],"about_ca_topic_score_codex":0.0022278891,"about_ca_topic_score_gemma":0.046389125,"teacher_disagreement_score":0.63720244,"about_ca_system_score_codex":0.000008715318,"about_ca_system_score_gemma":0.0021204508,"threshold_uncertainty_score":0.99996114},"labels":[],"label_agreement":null},{"id":"W7036856622","doi":"","title":"A decision theoretic approach for segmental classification using Hidden Markov models","year":2009,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; Hospital for Sick Children","keywords":"Hidden Markov model; Hidden semi-Markov model; Sequence (biology); Probabilistic logic; Markov chain; Markov model; Statistical model; Variable-order Markov model; Set (abstract data type); Flexibility (engineering)","score_opus":0.056928478082331875,"score_gpt":0.29293362445545307,"score_spread":0.2360051463731212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036856622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017965639,0.000033138593,0.95032597,0.0004748074,0.000046022098,0.0008558631,0.000084560554,0.00008057867,0.030133406],"genre_scores_gemma":[0.22607529,0.00028059032,0.7728921,0.00002658462,0.0000243341,2.2794741e-7,0.000039582283,0.000010961912,0.00065032515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968139,0.0005883459,0.00017966186,0.0008681479,0.0007880337,0.00076192076],"domain_scores_gemma":[0.9977104,0.0004608071,0.000177402,0.00087948306,0.00041125994,0.00036066302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015334105,0.00024255837,0.00038786526,0.00095429696,0.0011137681,0.000085327694,0.0025950952,0.00016896824,0.00001711087],"category_scores_gemma":[0.000049008988,0.00028924772,0.0003040532,0.0010767682,0.000525576,0.00146738,0.00087049237,0.00042075475,0.0000010241877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010484675,0.00038719925,0.000110033114,0.000068290574,0.00006643864,0.00004440723,0.0025033117,0.0003142807,0.004004253,0.69160444,0.0012816025,0.29856727],"study_design_scores_gemma":[0.0014641682,0.00047384834,0.0007327086,0.00005744386,0.00003447343,0.000015457286,0.002118613,0.76101214,0.00008405247,0.23066397,0.0030544468,0.0002886596],"about_ca_topic_score_codex":0.00007824182,"about_ca_topic_score_gemma":0.000027521963,"teacher_disagreement_score":0.7606979,"about_ca_system_score_codex":0.0003386917,"about_ca_system_score_gemma":0.0003460351,"threshold_uncertainty_score":0.99995595},"labels":[],"label_agreement":null},{"id":"W7042764309","doi":"","title":"A Review of the Expectation-Maximization Algorithm and its Applications to Mixture Models","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mixture model; Expectation–maximization algorithm; Pattern recognition (psychology); Feature (linguistics)","score_opus":0.022588868436226144,"score_gpt":0.2787487058412923,"score_spread":0.25615983740506615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042764309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064796065,0.094533816,0.799815,0.0021918442,0.0066782655,0.02310009,0.004196911,0.0023260945,0.06067835],"genre_scores_gemma":[0.016363965,0.05201361,0.90366596,0.006943189,0.0001988187,0.004567495,0.001023888,0.00050728256,0.014715775],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965362,0.00044567563,0.0008424872,0.0010861959,0.0006981729,0.00039128767],"domain_scores_gemma":[0.99681747,0.0002709293,0.00063797476,0.0011999093,0.00082885823,0.00024488464],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091082236,0.0005031413,0.00065974676,0.0002985803,0.0006668167,0.00007806522,0.0015290523,0.00042173924,0.000010908963],"category_scores_gemma":[0.00049723894,0.00042640805,0.00026830318,0.00202175,0.000021800479,0.0007058019,0.00033227634,0.00067473785,0.00003702193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054660113,0.000052932264,1.376224e-7,0.0026188267,0.00006266113,0.000002362619,0.000053761996,0.000064480846,0.0016382791,0.2965523,0.000057003548,0.69889176],"study_design_scores_gemma":[0.0009365133,0.00019900806,0.0002055224,0.025710324,0.00065083284,0.00006488916,0.00016784741,0.026880417,0.040767472,0.84961206,0.051996745,0.0028083478],"about_ca_topic_score_codex":0.000026895264,"about_ca_topic_score_gemma":0.000059584472,"teacher_disagreement_score":0.6960834,"about_ca_system_score_codex":0.00014397682,"about_ca_system_score_gemma":0.000095233685,"threshold_uncertainty_score":0.9998188},"labels":[],"label_agreement":null},{"id":"W7043192342","doi":"","title":"Review of <i>Saskatchewan: The Luminous Landscape</i> ByCourtney Milne","year":2008,"lang":"en","type":"article","venue":"Lincoln (University of Nebraska)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Beauty; Passion; Photography; Character (mathematics); Poetry; CLARITY; Studio; Painting","score_opus":0.014683731578514887,"score_gpt":0.20803045137556964,"score_spread":0.19334671979705476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043192342","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066505224,0.018766915,0.9592669,0.0054812743,0.00017363857,0.0003112068,0.000011763227,0.00006151652,0.009276261],"genre_scores_gemma":[0.22321391,0.028486123,0.73693067,0.0042313514,0.00013930607,0.0000012516527,0.000008996753,0.000020669828,0.006967692],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890125,0.00016021845,0.00017738256,0.00027579837,0.0002908322,0.00019449972],"domain_scores_gemma":[0.9986472,0.00013708916,0.00023712052,0.00071957114,0.00016787567,0.00009112238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046683027,0.00012445933,0.0003617468,0.00006845962,0.0002007267,0.000005767673,0.0013144561,0.00007842762,0.00006032304],"category_scores_gemma":[0.0000243441,0.00010816274,0.00020524529,0.0005251373,0.00019050547,0.00023510808,0.00032076048,0.0001590659,0.000014920976],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001364784,0.0012442283,0.0040557645,0.0073979585,0.00049598,0.0006552192,0.045473017,0.00004944546,0.0041221315,0.046383087,0.41600645,0.47398022],"study_design_scores_gemma":[0.010021559,0.0022585834,0.038709834,0.015690694,0.0009255478,0.0020539963,0.006542219,0.032686114,0.008571503,0.033832747,0.84483474,0.0038724814],"about_ca_topic_score_codex":0.00019067098,"about_ca_topic_score_gemma":0.000057128513,"teacher_disagreement_score":0.47010776,"about_ca_system_score_codex":0.000014226101,"about_ca_system_score_gemma":0.00022259598,"threshold_uncertainty_score":0.44107485},"labels":[],"label_agreement":null},{"id":"W7071671934","doi":"","title":"Some new computational methods in high-dimensional statistical learning in biostatistics","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Biostatistics; Statistical learning; Statistical analysis; Statistical model; Feature (linguistics)","score_opus":0.02595892979567063,"score_gpt":0.3236612293358971,"score_spread":0.2977022995402265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071671934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14361352,0.0016097097,0.82252765,0.0005556712,0.015233251,0.0033179875,0.002530275,0.0025007087,0.008111217],"genre_scores_gemma":[0.02231987,0.00008752212,0.9707681,0.00035294637,0.00008889917,0.00006646169,0.0015451594,0.00017750137,0.004593547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992297,0.0021814865,0.0015174181,0.0018140061,0.0011432788,0.0010468396],"domain_scores_gemma":[0.9950126,0.003074184,0.0005390973,0.0006186881,0.0002594066,0.00049602863],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032832446,0.0008253844,0.0011644657,0.0013572373,0.00044307232,0.00020373303,0.0012007682,0.00085422385,0.000067415676],"category_scores_gemma":[0.0022591974,0.00091926276,0.00018464771,0.0016879715,0.00006144317,0.00085981376,0.00038413325,0.0030839513,0.00022434449],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004413082,0.00008500246,0.000013042758,0.00009084271,0.000035921777,0.0002890339,0.000020165284,0.0032558937,0.00083407643,0.60495365,0.000022358026,0.3903559],"study_design_scores_gemma":[0.001309864,0.00014600369,0.0077304305,0.00041915345,0.000040023973,0.000024623867,0.00002534706,0.037170682,0.0011079193,0.94953024,0.0014202688,0.0010754314],"about_ca_topic_score_codex":0.0011363669,"about_ca_topic_score_gemma":0.0010330669,"teacher_disagreement_score":0.38928047,"about_ca_system_score_codex":0.0006728915,"about_ca_system_score_gemma":0.000449647,"threshold_uncertainty_score":0.9993258},"labels":[],"label_agreement":null},{"id":"W7093957261","doi":"","title":"Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach","year":2023,"lang":"en","type":"article","venue":"Aaltodoc (Aalto University)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Horizon 2020 Framework Programme; Finnish Center for Artificial Intelligence","keywords":"Artificial neural network; Process (computing); Bayesian probability; Dirichlet process; Pattern recognition (psychology); Maximum likelihood","score_opus":0.021168226878031608,"score_gpt":0.22885855634797075,"score_spread":0.20769032946993915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7093957261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014434123,0.000020563728,0.9781579,0.00019933716,0.00026268407,0.00024136339,0.0000030489064,0.00029479057,0.0063862163],"genre_scores_gemma":[0.8472876,0.000014805916,0.15180689,0.00040553347,0.00013853532,0.0000033230956,0.00006950559,0.000017346025,0.00025643173],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983816,0.00019947298,0.00026922632,0.00037966899,0.00029014252,0.00047986637],"domain_scores_gemma":[0.9991394,0.000083184255,0.00018487147,0.00032366277,0.00011490277,0.00015393655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005486251,0.00020077445,0.00022210287,0.0008998422,0.00026603194,0.00014489182,0.00062500016,0.0001442752,0.0000042725637],"category_scores_gemma":[0.000030307041,0.00022004418,0.00007639846,0.0036866947,0.000046415487,0.0028827912,0.0003474607,0.00034993453,0.0000100768475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018730116,0.00026849253,0.014105603,0.00033774733,0.000091114314,0.00042808344,0.00448178,0.5034088,0.00017863065,0.22977208,0.0022842716,0.24445611],"study_design_scores_gemma":[0.0004864886,0.00003035719,0.0012538587,0.000030309839,0.000008982191,0.000017831637,0.00020740269,0.9919126,0.000012631326,0.0053322134,0.0004568375,0.0002505009],"about_ca_topic_score_codex":0.00007985923,"about_ca_topic_score_gemma":0.000019708174,"teacher_disagreement_score":0.8328535,"about_ca_system_score_codex":0.00014154108,"about_ca_system_score_gemma":0.00018388311,"threshold_uncertainty_score":0.89731413},"labels":[],"label_agreement":null},{"id":"W7096569112","doi":"","title":"Canadian Microdata 1","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.011125172556957589,"score_gpt":0.23557037162535532,"score_spread":0.22444519906839774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096569112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002202016,0.000036395744,0.93246096,0.0073707663,0.00012788767,0.000030923944,9.980552e-7,0.0000524159,0.05969947],"genre_scores_gemma":[0.07368989,0.000002801873,0.9219541,0.0031785087,0.000023447687,0.0000011431741,6.6702484e-7,0.0000023372818,0.0011471057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995561,0.000010026267,0.000050516985,0.00015862244,0.000046135974,0.00017859771],"domain_scores_gemma":[0.9994202,0.0000048597885,0.0000067799742,0.00038039798,0.000014722251,0.00017302387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110754154,0.000044323126,0.00004306386,0.000052639094,0.000050210107,0.000066748406,0.0005246913,0.00002617034,0.000028232478],"category_scores_gemma":[0.000005599869,0.00003637534,0.000017400305,0.00013004233,0.0000064563,0.00017082457,0.000052257918,0.000042809803,0.00013784348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.888409e-8,0.000003197099,0.00000767866,5.1365004e-7,0.000001360728,0.000013180683,0.000070502254,0.0000021296953,0.00025130386,0.94652504,0.0019715969,0.05115344],"study_design_scores_gemma":[0.0003202591,0.00002749519,0.0006557147,0.000008125202,0.0000020964033,0.00008192096,0.0000036320846,0.0009788007,0.012998612,0.8761813,0.10847153,0.00027051975],"about_ca_topic_score_codex":0.09851089,"about_ca_topic_score_gemma":0.10531369,"teacher_disagreement_score":0.106499925,"about_ca_system_score_codex":0.000059350165,"about_ca_system_score_gemma":0.000253989,"threshold_uncertainty_score":0.911012},"labels":[],"label_agreement":null},{"id":"W7097228829","doi":"","title":"Statistical evidence for rule ordering DAVID SANKOFF Centre de recherches mathematiques Universite de Montreal","year":2015,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistical analysis; Context (archaeology); Statistical evidence","score_opus":0.20540669420404623,"score_gpt":0.3890087076656144,"score_spread":0.18360201346156818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097228829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022818518,0.00013467226,0.99098927,0.0015658188,0.000045354485,0.00015292087,0.0000043173377,0.00016265907,0.0046631475],"genre_scores_gemma":[0.012732613,0.000027188302,0.9843042,0.0002558329,0.000040646304,0.000005601985,0.0000012030604,0.000009132012,0.0026235834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890554,0.00022397912,0.00012780474,0.00027674536,0.00012171901,0.0003442105],"domain_scores_gemma":[0.9984911,0.0008245023,0.000040880976,0.00028731805,0.00010654393,0.00024964253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013106432,0.00011380531,0.0001505462,0.000040140887,0.000056248304,0.000109543544,0.0004770449,0.00008597398,0.000009638282],"category_scores_gemma":[0.0005354285,0.00009888765,0.000040902178,0.00010948066,0.000031432344,0.00042957097,0.00014757231,0.00010110018,0.000007820081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000594179,0.000084670035,0.00040798093,0.00011837106,0.000030175837,0.000046857087,0.015173491,0.00005646931,0.001313883,0.7397873,0.023322046,0.21959934],"study_design_scores_gemma":[0.00042845754,0.0000969339,0.0005443055,0.000113168884,0.000028357266,0.000033729324,0.00033356593,0.24774465,0.00608623,0.7434525,0.00087389635,0.00026421287],"about_ca_topic_score_codex":0.0004866723,"about_ca_topic_score_gemma":0.00007071417,"teacher_disagreement_score":0.24768819,"about_ca_system_score_codex":0.00020959279,"about_ca_system_score_gemma":0.00037791644,"threshold_uncertainty_score":0.40325212},"labels":[],"label_agreement":null},{"id":"W7098064594","doi":"","title":"Statistics Canada.","year":2014,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.005862264493216319,"score_gpt":0.21118007719761092,"score_spread":0.20531781270439461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098064594","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013020862,0.000005124836,0.9573862,0.00066300016,0.00019160754,0.000014858327,0.000001543058,0.00003142941,0.04169322],"genre_scores_gemma":[0.022404881,6.653126e-7,0.972705,0.002250921,0.00002749743,7.4904545e-7,4.950045e-7,0.0000017819481,0.0026079987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9996152,0.000034463887,0.000054289972,0.000101486636,0.00009354707,0.00010102473],"domain_scores_gemma":[0.9996196,0.000061566556,0.000011901811,0.00022383028,0.0000255707,0.000057524856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012929829,0.000035966583,0.000047045174,0.0000086592445,0.000028070132,0.000028438284,0.00025415167,0.000010870751,0.000018310926],"category_scores_gemma":[0.000027101813,0.000027983446,0.0000043671707,0.000059539343,0.0000048180796,0.000043785854,0.000043750464,0.000030326451,0.000005883429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.0485667e-8,0.0000011412153,0.000008547678,7.291655e-7,5.88843e-7,8.350417e-7,0.000006242599,9.087114e-7,0.000012150135,0.7582941,0.0618715,0.17980318],"study_design_scores_gemma":[0.00011869678,0.0000234945,0.0010259507,0.0000020947787,0.0000017310066,0.0000073992555,9.781737e-7,0.27272898,0.0011171754,0.39079368,0.33401027,0.00016951664],"about_ca_topic_score_codex":0.06481459,"about_ca_topic_score_gemma":0.19487123,"teacher_disagreement_score":0.36750045,"about_ca_system_score_codex":0.000010908653,"about_ca_system_score_gemma":0.000122012425,"threshold_uncertainty_score":0.94141287},"labels":[],"label_agreement":null},{"id":"W7099234205","doi":"","title":"MultivariateLagrangeInversion UniversityofWaterloo,Canada [summarybyDanieleGardy] BruceRichmond May25,1998","year":2008,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vertex (graph theory); Product (mathematics); Ball (mathematics)","score_opus":0.010771192479051799,"score_gpt":0.17570624878264113,"score_spread":0.16493505630358932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099234205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007152116,0.0000759887,0.9441717,0.001369108,0.0005015378,0.00013348505,0.000002482519,0.00017512383,0.046418447],"genre_scores_gemma":[0.27112988,0.0001373755,0.70230126,0.0023342946,0.00008842339,0.000001828014,0.000004506782,0.000013576325,0.02398883],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99847066,0.00015829895,0.00015859731,0.00042914847,0.00038120046,0.00040209535],"domain_scores_gemma":[0.99900454,0.000082240294,0.00005672381,0.0005370275,0.00006388452,0.00025560323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019605702,0.00017507187,0.00019379517,0.00010279607,0.0004542827,0.000047990212,0.00087958213,0.00009438462,0.00005818229],"category_scores_gemma":[0.000014521345,0.00015790421,0.000071438066,0.00033071835,0.000054653698,0.0005695849,0.0002881375,0.00016212575,0.000036082707],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007315838,0.0002639556,0.0028955338,0.00004886201,0.00016126267,0.003678958,0.0053962492,0.00005425047,0.0042258683,0.40135303,0.41447794,0.16737093],"study_design_scores_gemma":[0.0026730895,0.00019073042,0.006651431,0.000042644686,0.000037487796,0.00023665621,0.00018063538,0.054337878,0.010085592,0.01285607,0.91110086,0.0016069446],"about_ca_topic_score_codex":0.25521815,"about_ca_topic_score_gemma":0.067115664,"teacher_disagreement_score":0.4966229,"about_ca_system_score_codex":0.00017124893,"about_ca_system_score_gemma":0.0005688242,"threshold_uncertainty_score":0.94990706},"labels":[],"label_agreement":null},{"id":"W7099807161","doi":"","title":"Bayesian Spatio-temporal models based on discrete convolutions Canadian","year":2008,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Convolution (computer science); Bayesian inference; Bayes estimator; Feature (linguistics); Pattern recognition (psychology)","score_opus":0.029211270336747506,"score_gpt":0.2469987221647522,"score_spread":0.21778745182800469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099807161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001442122,0.000017395801,0.9001889,0.00395658,0.00019110243,0.00016589276,0.000011985927,0.00015247226,0.09517142],"genre_scores_gemma":[0.5734995,0.0000022086,0.423017,0.002226385,0.000032842723,0.000011579833,0.00000959385,0.000008317803,0.0011925845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985355,0.00012117701,0.00020166671,0.00043600285,0.00025085759,0.00045479534],"domain_scores_gemma":[0.9985599,0.00005630838,0.000041997777,0.0007504842,0.00006942528,0.0005219018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022749873,0.00017898408,0.00017457243,0.0002428832,0.00039714613,0.000065088236,0.0005937932,0.00009511391,0.00010455384],"category_scores_gemma":[0.000015559748,0.0001535879,0.000097810254,0.00035993068,0.00006947475,0.0004160133,0.00004023038,0.00016061647,0.000049430462],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070280194,0.00004916132,0.0006669003,0.000005037247,0.00001111727,0.00011262119,0.0003855218,0.009625593,0.000007849132,0.9664069,0.015187195,0.0075350767],"study_design_scores_gemma":[0.00021853243,0.00005663632,0.00037118065,0.000008508385,0.00000257095,0.000015087951,0.0000021062694,0.953817,0.000089955654,0.041612197,0.0035885947,0.00021761525],"about_ca_topic_score_codex":0.044265024,"about_ca_topic_score_gemma":0.04907531,"teacher_disagreement_score":0.9441914,"about_ca_system_score_codex":0.00011533067,"about_ca_system_score_gemma":0.0007261664,"threshold_uncertainty_score":0.96827656},"labels":[],"label_agreement":null},{"id":"W7100262508","doi":"","title":"The Hodrick-Prescott (HP) filter as a Bayesian regression model. WP 11-46, The Rimini Centre for Economic Analysis","year":2011,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Acknowledgement; Economic analysis; Filter (signal processing); Bayesian probability; Economic model; Regression analysis","score_opus":0.034720344211510344,"score_gpt":0.27849451354708177,"score_spread":0.24377416933557142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100262508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079578697,0.000106244865,0.9756177,0.0045265607,0.0002749904,0.0003973827,0.0000073920155,0.00009304148,0.018180907],"genre_scores_gemma":[0.20042005,0.00006423204,0.7856064,0.0013522028,0.00011952376,0.00006530784,0.0000035467435,0.000023730407,0.01234503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980679,0.00023635694,0.0003773708,0.0006280438,0.00017733156,0.000513007],"domain_scores_gemma":[0.9975437,0.00037820011,0.00019348241,0.0016693451,0.00006014025,0.00015512602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010300425,0.00025745443,0.00030769283,0.00011447216,0.0005491779,0.00028158663,0.002016157,0.00011799353,0.00014995175],"category_scores_gemma":[0.000036324043,0.00012058567,0.00045777689,0.00024629242,0.00008832868,0.00035132284,0.0004023622,0.00014804213,0.000040033112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005819848,0.000070670765,0.00028106963,0.000009732228,0.00038138597,0.0000045936736,0.004456008,0.0007549678,0.00007710856,0.83421415,0.0318341,0.12785803],"study_design_scores_gemma":[0.0001990828,0.000032686665,0.00014309796,0.0000071379536,0.00015404586,0.0000037160676,0.00006458912,0.8495193,0.0015293205,0.14317243,0.0049756155,0.00019896851],"about_ca_topic_score_codex":0.00026513645,"about_ca_topic_score_gemma":0.0005334273,"teacher_disagreement_score":0.84876436,"about_ca_system_score_codex":0.00004425727,"about_ca_system_score_gemma":0.0001067844,"threshold_uncertainty_score":0.4917341},"labels":[],"label_agreement":null},{"id":"W7100490835","doi":"","title":"University of British Columbia Owed to a Martingale: A Fast Bayesian On-Line EM Algorithm for Multinomial Models","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multinomial distribution; Hyperparameter; Bayesian probability; Expectation–maximization algorithm; Convergence (economics); Dirichlet distribution; Bayesian inference; Online learning","score_opus":0.019114352458394962,"score_gpt":0.23995643881379858,"score_spread":0.22084208635540362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100490835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040604146,0.000006584528,0.99364245,0.0003306592,0.00014896948,0.00053424126,0.00008413503,0.000114501156,0.0010780613],"genre_scores_gemma":[0.08043662,0.00000191667,0.9155191,0.0004492019,0.00005612663,0.000004245345,0.0000026379826,0.0000118568805,0.0035182568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987009,0.000049234997,0.0002235012,0.0005062955,0.00018651132,0.0003335616],"domain_scores_gemma":[0.9990791,0.00006162712,0.000087670494,0.00039631393,0.00016383358,0.000211444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003675762,0.0001078496,0.0002825451,0.00005220834,0.00013492214,0.00014326915,0.000631632,0.00009153328,0.00002002635],"category_scores_gemma":[0.00002135729,0.00016841042,0.00013509048,0.000279281,0.000032106727,0.00025593146,0.00018889781,0.00009630843,0.000004577088],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016808506,0.00018879546,0.000004742521,0.0000133143085,0.000018724746,0.00002886021,0.00071720424,0.0037078632,0.00018887265,0.004257269,0.0024998204,0.9883577],"study_design_scores_gemma":[0.0025623485,0.00053099723,0.00012639581,0.00008048135,0.000011842021,0.000024083278,0.00008099264,0.96172374,0.00044231882,0.033560324,0.0005333726,0.00032308823],"about_ca_topic_score_codex":0.0067220675,"about_ca_topic_score_gemma":0.014031833,"teacher_disagreement_score":0.98803467,"about_ca_system_score_codex":0.00006222974,"about_ca_system_score_gemma":0.00012700756,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W7103235250","doi":"","title":"Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond","year":2024,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"Deutsche Forschungsgemeinschaft; Austrian Science Fund; European Commission; Institute of Science and Technology Austria","keywords":"Sensitivity (control systems); Foundation (evidence); Relation (database); Noise (video); Field (mathematics)","score_opus":0.03772344390659249,"score_gpt":0.27740884589685594,"score_spread":0.23968540199026345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103235250","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002379996,0.0005161545,0.9860809,0.004890259,0.0002299748,0.00018742305,0.000011895979,0.0004109611,0.0052924575],"genre_scores_gemma":[0.4887967,0.000025787924,0.5106113,0.000111264104,0.000015954945,0.000006867779,0.000077009296,0.000016499695,0.0003386108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99515045,0.0031128111,0.0002826331,0.00085912505,0.00031091613,0.00028406768],"domain_scores_gemma":[0.99611294,0.0016357912,0.00011365506,0.0015287107,0.00046169414,0.00014717768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008323007,0.00019519453,0.00019122372,0.00016575186,0.00039401607,0.0009635593,0.00071242836,0.000080782236,0.000010100517],"category_scores_gemma":[0.00040023736,0.00019616655,0.000058839516,0.00047079337,0.000115289964,0.0005676738,0.000949326,0.0003320485,0.000014881861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043866617,0.0001359426,0.00002481468,0.0000996953,0.000025919617,0.00001052652,0.0031905037,0.010384441,0.0039178226,0.40114787,0.00010118025,0.5809569],"study_design_scores_gemma":[0.00015096247,4.819083e-7,0.0000734691,0.00022791936,0.000013961951,0.000027782135,0.0000100793495,0.9815631,0.0021042817,0.010091354,0.0055329353,0.00020367678],"about_ca_topic_score_codex":0.00013217551,"about_ca_topic_score_gemma":0.00032031973,"teacher_disagreement_score":0.97117865,"about_ca_system_score_codex":0.00005369964,"about_ca_system_score_gemma":0.00015237946,"threshold_uncertainty_score":0.92916244},"labels":[],"label_agreement":null},{"id":"W7104447653","doi":"10.71781/15299","title":"Apprentissage statistique des modèles de graphes aléatoires exponentiels : théorie et méthodes","year":2024,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Université de Montréal","keywords":"Statistical analysis; Markov chain; Maximum likelihood","score_opus":0.08284640837798504,"score_gpt":0.3817906372720472,"score_spread":0.29894422889406214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104447653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0473323,0.008303896,0.9126124,0.000366176,0.0017591992,0.00092149316,0.000259839,0.00001887141,0.028425852],"genre_scores_gemma":[0.04771365,0.0010590445,0.9070861,0.000065951856,0.00012675232,0.00018552189,0.0003450969,0.00009363726,0.043324277],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99464536,0.0015746282,0.00079891295,0.0016224458,0.0004832231,0.00087543513],"domain_scores_gemma":[0.9974442,0.0006666954,0.00036846072,0.00091408065,0.0002353229,0.00037123804],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002766124,0.0007955896,0.000840543,0.00029334484,0.00048597725,0.004411407,0.0026394054,0.0005782474,0.0009672417],"category_scores_gemma":[0.00019903285,0.0007731572,0.0003168089,0.000694366,0.0002882074,0.0016408523,0.0007821997,0.0008276489,0.00025434472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042185453,0.00018527647,0.00014277581,0.00043794463,0.00021770514,0.00032173982,0.033731658,0.00006843103,0.0039839493,0.23679793,0.00095595024,0.72311443],"study_design_scores_gemma":[0.00045320543,0.00023081304,0.0018328077,0.0034294091,0.00041087778,0.00010829492,0.002656258,0.04261214,0.05707565,0.8767447,0.012942064,0.0015038248],"about_ca_topic_score_codex":0.00095070014,"about_ca_topic_score_gemma":0.0019721624,"teacher_disagreement_score":0.7216106,"about_ca_system_score_codex":0.00011007407,"about_ca_system_score_gemma":0.0011059183,"threshold_uncertainty_score":0.999946},"labels":[],"label_agreement":null},{"id":"W7104451122","doi":"10.71781/15696","title":"Application des méthodes de partitionnement de données fonctionnelles aux trajectoires de voiture","year":2020,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Intersection (aeronautics); Order (exchange); Decision system","score_opus":0.02063411576062507,"score_gpt":0.22372791318865776,"score_spread":0.20309379742803269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104451122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08618835,0.015465156,0.88934,0.0020354304,0.00061070436,0.0005077729,0.000040711915,0.00024273302,0.0055691446],"genre_scores_gemma":[0.57336104,0.0020221488,0.41532996,0.0005860422,0.000627963,0.00017781282,0.00023049577,0.000052425454,0.0076121385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961501,0.00078203186,0.00054275955,0.0010469678,0.0006099087,0.0008682526],"domain_scores_gemma":[0.99757224,0.00026798906,0.0004786076,0.000537013,0.00041951225,0.00072462764],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0007110369,0.00062438427,0.0005088361,0.00025017574,0.009284303,0.00029051196,0.0009467971,0.00069598574,0.00003062808],"category_scores_gemma":[0.00016740123,0.0007300605,0.0004658042,0.0005835737,0.000460161,0.00075641094,0.00021099857,0.00066782994,0.0000311183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046794838,0.0004410706,0.0063575315,0.00064195227,0.00041692329,0.00094219984,0.10244604,0.009583887,0.06784386,0.7412843,0.000843915,0.068730354],"study_design_scores_gemma":[0.0028244962,0.0005688064,0.08638682,0.0015650436,0.0015251986,0.0033831773,0.035690933,0.459385,0.12344087,0.21275842,0.069849074,0.0026221403],"about_ca_topic_score_codex":0.023090934,"about_ca_topic_score_gemma":0.009369716,"teacher_disagreement_score":0.5285259,"about_ca_system_score_codex":0.0069152927,"about_ca_system_score_gemma":0.0047458587,"threshold_uncertainty_score":0.99951506},"labels":[],"label_agreement":null},{"id":"W7104472137","doi":"10.71781/15521","title":"Modèles de Markov à variables latentes : matrice de transition non-homogène et reformulation hiérarchique","year":2021,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Markov chain; Random variable; Markov process; Branching process; Probability theory","score_opus":0.008280589878699104,"score_gpt":0.20207787050240464,"score_spread":0.19379728062370555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104472137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11677153,0.008998446,0.8502403,0.00132635,0.0008589993,0.00040491368,0.00007353628,0.0001392247,0.0211867],"genre_scores_gemma":[0.38191053,0.0025444503,0.5794355,0.0006394207,0.00036595916,0.000058817423,0.0009763289,0.000072123694,0.033996835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590385,0.000923686,0.00061813655,0.0010361399,0.0007010273,0.0008171771],"domain_scores_gemma":[0.99750894,0.00029242953,0.0004989742,0.00062785926,0.0005691109,0.0005026661],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010362193,0.0006402594,0.0006060901,0.00044232153,0.0044147405,0.00031779511,0.0007620387,0.0008865975,0.00003359863],"category_scores_gemma":[0.00007259324,0.00075438904,0.00049061497,0.0007472326,0.00016099533,0.001324666,0.00021074442,0.000869957,0.000012754806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009143887,0.00066644524,0.0014848527,0.0010497025,0.0006387706,0.0052035903,0.12396988,0.04217066,0.13141,0.65723526,0.00032326777,0.034933195],"study_design_scores_gemma":[0.0023586787,0.00028220995,0.055395234,0.0022486309,0.00093879143,0.0050464277,0.010682654,0.8349018,0.04514448,0.035192378,0.0058808737,0.0019278206],"about_ca_topic_score_codex":0.03990341,"about_ca_topic_score_gemma":0.0047099763,"teacher_disagreement_score":0.79273117,"about_ca_system_score_codex":0.0055894307,"about_ca_system_score_gemma":0.005076639,"threshold_uncertainty_score":0.99949074},"labels":[],"label_agreement":null},{"id":"W7104489099","doi":"10.71781/15763","title":"Modélisation des bi-grappes et sélection des variables pour des données de grande dimension : application aux données d’expression génétique","year":2012,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lebesgue covering dimension; Diaphragm muscle","score_opus":0.11067115725874509,"score_gpt":0.3530840163582807,"score_spread":0.24241285909953558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104489099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33010635,0.0022309814,0.6630589,0.00017198033,0.00042762823,0.0011034422,0.00002027784,0.000025880227,0.0028545826],"genre_scores_gemma":[0.4339266,0.0010745446,0.56227446,0.000049643226,0.00021670751,0.0002701905,0.00033983274,0.000064262706,0.0017837278],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9945271,0.0016377481,0.0009157604,0.0014040718,0.00052113645,0.0009941616],"domain_scores_gemma":[0.9965475,0.00050736434,0.0008467589,0.000875337,0.0007989019,0.00042411694],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003430039,0.0008366485,0.00075879175,0.00042249364,0.0019663614,0.0015907121,0.001458574,0.0009796044,0.00021478253],"category_scores_gemma":[0.0002931192,0.00078566355,0.00025205032,0.00093100965,0.000404067,0.0041918945,0.00042376845,0.0006384459,0.00011245162],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019153293,0.00043992445,0.0015067692,0.00036921195,0.00006559223,0.0000038744965,0.031952307,0.00093681907,0.38696402,0.013558298,0.0000652246,0.5639464],"study_design_scores_gemma":[0.0011938547,0.0002604124,0.021864915,0.003677139,0.00038137494,0.00011197363,0.0012167247,0.08888908,0.5677963,0.31097385,0.0022740278,0.001360353],"about_ca_topic_score_codex":0.0041649397,"about_ca_topic_score_gemma":0.0055009713,"teacher_disagreement_score":0.56258607,"about_ca_system_score_codex":0.00039540575,"about_ca_system_score_gemma":0.0008458515,"threshold_uncertainty_score":0.99945945},"labels":[],"label_agreement":null},{"id":"W7105913978","doi":"10.23952/jano.7.2025.3.07","title":"Variable Bregman majorization-minimization algorithm and its application to Dirichlet maximum likelihood estimation","year":2025,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Berlin Mathematics Research Center MATH+; Deutsche Forschungsgemeinschaft","keywords":"Maximum likelihood; Variable (mathematics); Expectation–maximization algorithm; Estimation; Dirichlet distribution; Estimation theory; Maximum likelihood sequence estimation","score_opus":0.00387340013188319,"score_gpt":0.2353775001156472,"score_spread":0.231504099983764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105913978","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004299779,0.00015708125,0.99688554,0.0013290395,0.0001478866,0.00029687068,0.0000017537602,0.000035720626,0.0011031047],"genre_scores_gemma":[0.02341238,0.00010580744,0.97560245,0.00075151486,0.0000648943,0.000016500484,0.000008749236,0.000009768556,0.000027919335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885947,0.000047907066,0.0004511884,0.0002729554,0.00020859197,0.00015990337],"domain_scores_gemma":[0.99907976,0.00008444006,0.00028250073,0.00014792725,0.00025620623,0.00014917523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038137773,0.00014414516,0.00025502415,0.00027283037,0.00014631986,0.00015884079,0.0002003362,0.00010423635,0.0000039277074],"category_scores_gemma":[0.000057087156,0.00013065145,0.000025289308,0.0008557859,0.000013191769,0.0004541619,0.00009438912,0.00012251503,0.0000012644888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032789307,0.000072582734,0.000007884701,0.000029537814,0.000023818147,7.3410956e-7,0.00020996878,0.16776963,0.0006274508,0.16260883,0.00019647497,0.6684203],"study_design_scores_gemma":[0.00041902892,0.00007696444,0.000103890125,0.000030518408,0.000033841774,0.000011920012,0.000007642636,0.9139967,0.00061464193,0.083948776,0.0006352238,0.00012083459],"about_ca_topic_score_codex":0.0000018100376,"about_ca_topic_score_gemma":4.251845e-8,"teacher_disagreement_score":0.7462271,"about_ca_system_score_codex":0.00004186401,"about_ca_system_score_gemma":0.00007486126,"threshold_uncertainty_score":0.5327811},"labels":[],"label_agreement":null},{"id":"W7106850333","doi":"10.1016/j.jspi.2025.106369","title":"Homogeneity testing under finite mixtures of multivariate Poisson distributions","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Social Science Fund of China","keywords":"Homogeneity (statistics); Identifiability; Poisson distribution; Asymptotic distribution; Estimator; Multivariate statistics; Resampling; Consistency (knowledge bases); Null distribution","score_opus":0.04507503910597101,"score_gpt":0.3555337143192451,"score_spread":0.3104586752132741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106850333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006036897,0.00039024718,0.9925108,0.00029618212,0.00013477854,0.00002740114,0.000030501182,0.000009343064,0.00056388095],"genre_scores_gemma":[0.56399655,0.0000068505133,0.43591338,0.00005476838,0.000013746262,3.0244635e-7,8.212142e-7,0.0000011311535,0.000012455514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99908787,0.00011071648,0.00038793153,0.00012578651,0.00014128014,0.00014641634],"domain_scores_gemma":[0.9969235,0.0023945796,0.00021984329,0.0001150155,0.00025612974,0.00009091224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004882463,0.00009133931,0.0002442307,0.0000940709,0.00009768623,0.00006949094,0.00023207955,0.00005512935,0.0000023321886],"category_scores_gemma":[0.0020739534,0.000069568945,0.000028967728,0.00023254346,0.00008523698,0.00016691956,0.000093328454,0.00025459996,2.1362494e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030389985,0.00009864072,0.005999069,0.000076799566,0.00006200072,0.000045572124,0.0002848818,0.00073714706,0.0063493974,0.8724397,0.00073998806,0.1131364],"study_design_scores_gemma":[0.0006959669,0.00037603182,0.169807,0.0008731804,0.00007337843,0.00006053384,0.000018822278,0.12104233,0.0040028244,0.70252645,0.00030405144,0.00021940297],"about_ca_topic_score_codex":0.000024480738,"about_ca_topic_score_gemma":4.4798136e-7,"teacher_disagreement_score":0.5579597,"about_ca_system_score_codex":0.000013755194,"about_ca_system_score_gemma":0.00013896612,"threshold_uncertainty_score":0.2836939},"labels":[],"label_agreement":null},{"id":"W7106854986","doi":"10.1016/j.jspi.2025.106368","title":"On deriving Liouville process from Liouville distribution and its application in nonparametric Bayesian inference","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet process; Dirichlet distribution; Generalized Dirichlet distribution; Limit (mathematics); Generalization; Dirichlet form; Point process; Distribution (mathematics); Concentration parameter; Probability distribution","score_opus":0.01420803089490907,"score_gpt":0.3282765268560097,"score_spread":0.31406849596110065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106854986","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084584706,0.00054737664,0.9141409,0.00022788272,0.00007480685,0.00007876421,0.000019595518,0.000011807786,0.0003141588],"genre_scores_gemma":[0.9389057,0.00008579231,0.060843542,0.0001259041,0.000020704958,0.0000047091125,0.0000048514653,0.0000029386322,0.0000058468995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988485,0.000100169236,0.0004085577,0.00025873072,0.00019968119,0.00018433489],"domain_scores_gemma":[0.99772465,0.0017047425,0.00019279425,0.00011684877,0.0001394656,0.000121482364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004466047,0.00013202502,0.00027974823,0.00023852875,0.00009147225,0.00014901544,0.00024350222,0.0000897082,0.0000028193792],"category_scores_gemma":[0.0015629706,0.00010969556,0.000015851861,0.0005278948,0.00004308591,0.00034118153,0.000075847514,0.0003821718,7.9159554e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008338692,0.00013984574,0.020819861,0.0001079981,0.000024808507,0.000050845545,0.0007505869,0.00056365534,0.0003641385,0.65907395,0.00017769088,0.31784323],"study_design_scores_gemma":[0.0006068028,0.00028113872,0.10815899,0.0007942514,0.000018740722,0.000014417249,0.00003649107,0.39907092,0.00046987057,0.49026516,0.000073918214,0.0002093071],"about_ca_topic_score_codex":0.000025645071,"about_ca_topic_score_gemma":0.0000034769937,"teacher_disagreement_score":0.854321,"about_ca_system_score_codex":0.000036266865,"about_ca_system_score_gemma":0.00011361192,"threshold_uncertainty_score":0.44732553},"labels":[],"label_agreement":null},{"id":"W7112133878","doi":"","title":"A Sampling-Based Domain Generalization Study with Diffusion Generative Models","year":2025,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Generalization; Domain (mathematical analysis); Diffusion; Feature (linguistics); Generative grammar; Bounded function; Generative model","score_opus":0.016720363238365045,"score_gpt":0.2548562814055518,"score_spread":0.23813591816718674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7112133878","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03600522,0.0001793279,0.9465547,0.0052676587,0.00007935251,0.00052975456,0.000003804255,0.00021350075,0.011166685],"genre_scores_gemma":[0.36560956,0.000014158736,0.63239175,0.00033468968,0.0000062591434,0.000060328795,0.000020502881,0.000012066933,0.0015506981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928311,0.0055276724,0.00032448702,0.0006974496,0.00034503255,0.00027423576],"domain_scores_gemma":[0.99631226,0.00066356896,0.0001797262,0.0015800012,0.0011557201,0.00010874434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004148179,0.00022955128,0.0002461815,0.00022398496,0.00049599883,0.00041875275,0.0010464125,0.00008664989,0.000010034082],"category_scores_gemma":[0.00017982481,0.00019686464,0.00007241192,0.0009925776,0.000087563036,0.0003322574,0.00035174645,0.00018117404,0.0000031425916],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002381514,0.00093265,0.00086913933,0.000019921741,0.000040551575,0.0000041440253,0.007654354,0.0016110754,0.0034497313,0.9383483,0.00018965278,0.046856653],"study_design_scores_gemma":[0.0017005295,0.0000036051201,0.0015843894,0.00038545503,0.00002923179,0.0000032218322,0.00009377406,0.8793179,0.021442039,0.093699686,0.001358099,0.00038211324],"about_ca_topic_score_codex":0.00025750574,"about_ca_topic_score_gemma":0.0008435591,"teacher_disagreement_score":0.87770677,"about_ca_system_score_codex":0.00007654963,"about_ca_system_score_gemma":0.0002566879,"threshold_uncertainty_score":0.8027907},"labels":[],"label_agreement":null},{"id":"W7117242493","doi":"10.1109/tit.2025.3648620","title":"On Minimax Empirical Bayes Predictive Densities","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Minimax; Bayes' theorem; Bayesian probability; Probability density function; Density estimation; Simple (philosophy); Point estimation","score_opus":0.012692391255983067,"score_gpt":0.28108394665545344,"score_spread":0.26839155539947035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117242493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000623807,0.00008088699,0.9495108,0.0015239223,0.004623234,0.00061344734,0.00013827629,0.0002672209,0.04261841],"genre_scores_gemma":[0.9430382,0.00016711983,0.03770652,0.012892614,0.000079049394,0.00016232113,0.000006644678,0.00002047206,0.0059270374],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99660456,0.00083950325,0.0009897748,0.0004549215,0.00058048544,0.00053072924],"domain_scores_gemma":[0.9967232,0.0015037088,0.00026164987,0.00095528824,0.00036110406,0.00019509258],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014308046,0.0004976333,0.00045301244,0.0011182092,0.00087042875,0.0005307237,0.00073262095,0.00042516334,0.00028763502],"category_scores_gemma":[0.00006394758,0.00046982066,0.0003734863,0.0010220775,0.00033183736,0.0027155706,0.000008881575,0.0009185994,0.00048105107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008816746,0.0002699605,6.705343e-7,0.00011853969,0.00022457521,0.000003967252,0.010987744,0.009420991,0.0000126361465,0.34560007,0.0041762185,0.62830293],"study_design_scores_gemma":[0.0021107704,0.0014067902,0.00011135487,0.00084801664,0.00028208594,0.00004200175,0.0012973452,0.46378908,0.018465953,0.5042753,0.0064449217,0.00092637754],"about_ca_topic_score_codex":0.000006249867,"about_ca_topic_score_gemma":0.000002330127,"teacher_disagreement_score":0.9424144,"about_ca_system_score_codex":0.00028179938,"about_ca_system_score_gemma":0.0005412409,"threshold_uncertainty_score":0.99977535},"labels":[],"label_agreement":null},{"id":"W7119354289","doi":"","title":"Simulation of warping processes with applications to temperature data","year":2025,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"Centre National de la Recherche Scientifique","keywords":"Image warping; Dynamic time warping; Quantile; Focus (optics); Process (computing); Functional data analysis; Distribution (mathematics)","score_opus":0.02846550004425567,"score_gpt":0.2919075692370362,"score_spread":0.2634420691927805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7119354289","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044019995,0.0007068066,0.98296684,0.0057055866,0.00006738493,0.00086110824,0.00015024522,0.00019306444,0.008908749],"genre_scores_gemma":[0.1405222,0.00012565503,0.856531,0.00015956537,0.000018753566,0.00013339221,0.0003384321,0.000016473648,0.0021544977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615854,0.0016600381,0.00044676714,0.0011174341,0.00038035447,0.00023687728],"domain_scores_gemma":[0.98876864,0.0020884806,0.00040789263,0.0053117652,0.0032870513,0.0001362003],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030576366,0.00027552497,0.00036754107,0.0002476173,0.00022593702,0.00037875117,0.004244955,0.00022123728,0.0000059415156],"category_scores_gemma":[0.0014132675,0.00025568006,0.000057704146,0.0011680787,0.0000821453,0.0003008426,0.0038214312,0.00043310536,0.0000035087576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025283762,0.0009368221,0.00035502313,0.0032643662,0.000221702,0.0000032654077,0.015879812,0.03154185,0.0022885397,0.55628705,0.001109953,0.38808635],"study_design_scores_gemma":[0.00078677066,0.0000019279964,0.0005067013,0.012370463,0.00016884849,0.0000075274106,0.00006954239,0.82242143,0.075093664,0.051971734,0.035189595,0.0014118253],"about_ca_topic_score_codex":0.0001568194,"about_ca_topic_score_gemma":0.0005565238,"teacher_disagreement_score":0.79087955,"about_ca_system_score_codex":0.000045898985,"about_ca_system_score_gemma":0.0010672593,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W7125884919","doi":"","title":"Common structure in panels of short ecological time-series.","year":2000,"lang":"en","type":"article","venue":"PubMed Central","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Regression; Sample (material); Statistical hypothesis testing; Regression analysis; Test (biology); Linear regression; Food chain","score_opus":0.013802774908599666,"score_gpt":0.2304740131242806,"score_spread":0.21667123821568093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125884919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87571174,0.000108803324,0.11375485,0.000604019,0.00034631754,0.00041025493,0.000017068305,0.00008213993,0.0089648105],"genre_scores_gemma":[0.91263354,0.000028775361,0.08659234,0.00020627819,0.00007870153,0.000015968059,0.0000039177326,0.000005874602,0.00043461804],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983409,0.00014018362,0.00024972094,0.00027323022,0.0001634703,0.0008324888],"domain_scores_gemma":[0.99939615,0.000038525355,0.000028971024,0.00032471254,0.000010835102,0.00020083113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032738378,0.00012196788,0.00025667806,0.000044660934,0.000025859303,0.000034483735,0.00057098485,0.00011890853,0.0003082725],"category_scores_gemma":[0.000018449697,0.00009938977,0.000059299622,0.00024406107,0.000058112775,0.00025235364,0.000068522764,0.00018414797,0.000004794563],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030274834,0.00012437426,0.0120960735,0.0000106270445,0.00001185981,0.000049432012,0.0004828753,0.0001629791,0.0006115975,0.019022036,0.00029860376,0.96709925],"study_design_scores_gemma":[0.0002879797,0.000054908087,0.9571137,0.0000073753154,0.000005713291,0.000035638586,0.0000024129795,0.004518316,0.004836876,0.029453965,0.0034737017,0.0002094289],"about_ca_topic_score_codex":0.000013272209,"about_ca_topic_score_gemma":0.000021328335,"teacher_disagreement_score":0.96688986,"about_ca_system_score_codex":0.00006054727,"about_ca_system_score_gemma":0.000043502914,"threshold_uncertainty_score":0.40529972},"labels":[],"label_agreement":null},{"id":"W7135009206","doi":"10.1109/camsap66162.2025.11423963","title":"Coupled Gaussian Mixtures For Modal Analysis: EM Inference and CramÉr-Rao Bounds","year":2025,"lang":"","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Gaussian process; Gaussian; Modal; Inference; Noise (video); Expectation–maximization algorithm","score_opus":0.01727537560492633,"score_gpt":0.32052608712457886,"score_spread":0.30325071151965255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135009206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029141717,0.0032860858,0.98211867,0.003900254,0.00087771175,0.00083361036,0.00002489325,0.00013449558,0.0059101065],"genre_scores_gemma":[0.5539945,0.00019612417,0.43548653,0.0017810396,0.00009477764,0.000074984644,0.000006553892,0.000013216903,0.008352286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956628,0.00030429778,0.0009265956,0.0016987441,0.00040746358,0.0010000884],"domain_scores_gemma":[0.996733,0.0007681665,0.00025442848,0.0014336562,0.0004058089,0.00040490425],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015547137,0.00064993225,0.0011878996,0.00089561933,0.000729516,0.002139329,0.0013410574,0.00047064,0.000106221705],"category_scores_gemma":[0.00027469298,0.0005571436,0.0005545373,0.0029083684,0.00027487343,0.0006608075,0.0006862998,0.0004082434,0.0000044750527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088062014,0.0001875409,0.00076214795,0.00022542293,0.0016320545,0.000008764164,0.0014925635,0.0001728434,0.00060978293,0.7651675,0.0012507389,0.22840261],"study_design_scores_gemma":[0.00091206166,0.0001763594,0.0030385116,0.00008037772,0.0011851388,0.0000029281398,0.00005981159,0.7809095,0.0006784061,0.21123879,0.0011872455,0.00053091574],"about_ca_topic_score_codex":0.0002348715,"about_ca_topic_score_gemma":0.00054481346,"teacher_disagreement_score":0.7807366,"about_ca_system_score_codex":0.00007221909,"about_ca_system_score_gemma":0.00062265934,"threshold_uncertainty_score":0.999688},"labels":[],"label_agreement":null},{"id":"W7150184825","doi":"10.1134/s1995080225612846","title":"On the Computation of Quantiles of Finite Mixtures with Stochastically Ordered Components","year":2025,"lang":"en","type":"article","venue":"Lobachevskii Journal of Mathematics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Quantile; Computation; Weibull distribution; Mixture model; Component (thermodynamics)","score_opus":0.024308529220014707,"score_gpt":0.280337160350824,"score_spread":0.2560286311308093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7150184825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038423155,0.00013988996,0.9594391,0.0007703714,0.00009842773,0.0001251117,0.0000023424977,0.0000067040737,0.0009949242],"genre_scores_gemma":[0.55150723,0.000006476297,0.4483834,0.00007879258,0.0000071635304,5.610332e-7,1.6762091e-7,0.000003701637,0.000012527601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998535,0.00013783868,0.00066911493,0.00009504124,0.0004420118,0.00012098781],"domain_scores_gemma":[0.9969714,0.0014684404,0.00081320445,0.00029158362,0.00041507487,0.000040256775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000886579,0.00012967589,0.00040856315,0.00014981766,0.000044850032,0.00003474461,0.00068363064,0.000054153916,0.0000032026915],"category_scores_gemma":[0.00036204947,0.000071144896,0.00010644427,0.00033003182,0.00010793492,0.00009145029,0.00007587388,0.00019629562,7.1813616e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006401277,0.0005390659,0.000026013793,0.00029302924,0.0001957363,0.000008422931,0.001525154,0.0039284406,0.0032891612,0.98289603,0.0003492842,0.006885627],"study_design_scores_gemma":[0.001069431,0.0007302083,0.00035205582,0.0023017563,0.00012096294,0.00006696442,0.00013498301,0.22435948,0.014329729,0.75636613,0.000016879232,0.00015142928],"about_ca_topic_score_codex":0.000002035008,"about_ca_topic_score_gemma":7.650129e-7,"teacher_disagreement_score":0.51308405,"about_ca_system_score_codex":0.00001344034,"about_ca_system_score_gemma":0.0001054653,"threshold_uncertainty_score":0.29012048},"labels":[],"label_agreement":null},{"id":"W7161780267","doi":"10.82308/36630","title":"Latent multi-state models for non-equidistant longitudinal observations with finite and infinite mixture model-based clustering","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Markov chain Monte Carlo; Bayesian probability; Inference; Covariate; Markov chain; Bayesian inference; Trajectory; Statistical inference; Markov process","score_opus":0.06374121359342386,"score_gpt":0.29514610440519545,"score_spread":0.2314048908117716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161780267","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016491669,0.00015907675,0.9955999,0.00020463669,0.00032592638,0.0013200112,0.00016724791,0.00012396679,0.00045001652],"genre_scores_gemma":[0.051981226,0.000051435596,0.938987,0.00048851146,0.000027001914,0.00023527481,0.0006762375,0.0000770255,0.007476261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748784,0.000045673445,0.0005157218,0.0010773074,0.00034314807,0.000530335],"domain_scores_gemma":[0.99796945,0.00022859058,0.0003402098,0.000824166,0.00044770807,0.00018989133],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036538008,0.0005966421,0.0006255406,0.00026058318,0.00024164951,0.00038986508,0.0006477773,0.0003277526,0.000002137798],"category_scores_gemma":[0.000019171404,0.00047241937,0.00015096496,0.0002882334,0.00003255017,0.00068946293,0.00009891595,0.00036620203,0.0000021437004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049117656,0.00019006379,0.0001462016,0.0016667383,0.00019850383,0.000020031935,0.0032961513,0.9535447,0.0009583138,0.023697712,0.00027210364,0.015518325],"study_design_scores_gemma":[0.0013789964,0.00016815182,0.00028265145,0.00035824635,0.00007669979,0.0000028472616,0.000016990045,0.98973024,0.00028821314,0.006967989,0.000053019074,0.00067597424],"about_ca_topic_score_codex":0.00004975442,"about_ca_topic_score_gemma":0.0004851639,"teacher_disagreement_score":0.056612927,"about_ca_system_score_codex":0.000058507332,"about_ca_system_score_gemma":0.00043738142,"threshold_uncertainty_score":0.9997727},"labels":[],"label_agreement":null},{"id":"W7162140302","doi":"10.82308/49407","title":"Aggregation-Tree Copula Models in Extreme-Value Theory","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Copula (linguistics); Multivariate statistics; Independence (probability theory); Conditional independence; Tree (set theory)","score_opus":0.03946570366233129,"score_gpt":0.2927939431635581,"score_spread":0.25332823950122685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162140302","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003037574,0.002794848,0.7804382,0.00013414616,0.0016073736,0.0002579272,0.0000022970255,0.0002083532,0.21425313],"genre_scores_gemma":[0.025143972,0.0002550694,0.8208861,0.0004482238,0.00022131727,0.00011819862,0.00015647903,0.0000792713,0.15269142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976402,0.00027115006,0.0004760843,0.00086721714,0.0004032355,0.0003421413],"domain_scores_gemma":[0.9987576,0.00015932496,0.0001180145,0.0007849066,0.00008418109,0.0000959672],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00096686126,0.00036868826,0.000395654,0.0004698537,0.000054975848,0.0002970807,0.0010479315,0.00040998447,0.000049413888],"category_scores_gemma":[0.000039178718,0.00031294313,0.00017834321,0.0006123054,0.000017075437,0.00051128166,0.00009919786,0.00053818733,0.00010097113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007278012,0.000020868845,8.007279e-7,0.00007841963,0.000015323572,0.000047506623,0.0016786726,0.00009272625,0.000057006113,0.7517959,0.0010036096,0.24520189],"study_design_scores_gemma":[0.00010548251,0.000014010973,0.000024674515,0.00028267017,0.000016606034,0.00000715839,0.00006452772,0.21154654,0.00046987447,0.7868065,0.00035482048,0.0003071142],"about_ca_topic_score_codex":0.00010253369,"about_ca_topic_score_gemma":0.0006642473,"teacher_disagreement_score":0.24489477,"about_ca_system_score_codex":0.00008416219,"about_ca_system_score_gemma":0.0002581555,"threshold_uncertainty_score":0.9999323},"labels":[],"label_agreement":null},{"id":"W7163696499","doi":"10.13182/t130-39681","title":"Real Variance Estimation in the iDTMC-Based Depletion Analysis Using Correlated Sampling","year":2022,"lang":"","type":"article","venue":"Transactions of the American Nuclear Society","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Sampling (signal processing); Variance (accounting); Estimation; Estimation theory; Importance sampling","score_opus":0.026211883158869787,"score_gpt":0.2935966892980287,"score_spread":0.2673848061391589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163696499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12953681,0.000036726367,0.86810887,0.001641233,0.00024038488,0.0003218662,0.000037336038,0.00003841236,0.000038357386],"genre_scores_gemma":[0.6349439,0.000044178105,0.36436602,0.00059667154,0.0000094556,0.000010313581,0.000001952467,0.000017661345,0.000009836275],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962174,0.0016225997,0.00058914133,0.0005172852,0.00068500364,0.00036853759],"domain_scores_gemma":[0.99755144,0.00034138744,0.0008034039,0.0011695838,0.00008332845,0.000050841503],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0018756903,0.00023615379,0.00048575248,0.00015279133,0.0016052459,0.00011223516,0.0014812767,0.00006199362,0.00009355508],"category_scores_gemma":[0.000016453689,0.00019405948,0.0010820657,0.007900708,0.0004992429,0.00023975942,0.00007254365,0.0009418753,0.0000010418536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046590416,0.0002690708,0.00016501301,0.000016753524,0.00034618226,7.287931e-7,0.011721008,0.9531741,0.0015421258,0.0008152975,0.00002500905,0.031878088],"study_design_scores_gemma":[0.00029786513,0.00013211399,0.0076413606,0.00002022488,0.0009885144,0.0000099779845,0.001731678,0.9883333,0.00002823546,0.00055713474,0.000057852336,0.00020175267],"about_ca_topic_score_codex":0.003924827,"about_ca_topic_score_gemma":0.000038554324,"teacher_disagreement_score":0.5054071,"about_ca_system_score_codex":0.00037198627,"about_ca_system_score_gemma":0.00023818992,"threshold_uncertainty_score":0.9996945},"labels":[],"label_agreement":null},{"id":"W852382289","doi":"10.71781/15607","title":"Une famille de distributions symétriques et leptocurtiques représentée par la différence de deux variables aléatoires gamma","year":2008,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Humanities; Philosophy; Physics","score_opus":0.006053962119518987,"score_gpt":0.2121876494233377,"score_spread":0.20613368730381873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W852382289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07729462,0.007302808,0.85301256,0.0006375615,0.0005062239,0.00035456682,0.00009286536,0.00045751288,0.060341254],"genre_scores_gemma":[0.59311193,0.008715174,0.35568503,0.00040707228,0.00030367824,0.00016124421,0.0008748369,0.00007833102,0.040662736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679875,0.00064200716,0.00044670893,0.00090127555,0.00056196237,0.00064928946],"domain_scores_gemma":[0.99773425,0.000326103,0.00041986947,0.0007944539,0.00032204748,0.0004032879],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005348762,0.00051444146,0.0005005685,0.00026517123,0.0040829508,0.00019247316,0.0011427584,0.0006366145,0.0000062371746],"category_scores_gemma":[0.00016720293,0.00055791036,0.0003513091,0.00053529936,0.00025236592,0.0006605427,0.00026519506,0.0006748671,0.000007720454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031546684,0.0005339143,0.0044783223,0.00022084928,0.00049187493,0.0053611114,0.054497875,0.0009638934,0.023632841,0.8849535,0.009466211,0.015084148],"study_design_scores_gemma":[0.0043386286,0.0006613744,0.19020206,0.0033357919,0.0012375711,0.013714291,0.0109897675,0.05585254,0.19976398,0.2278606,0.28547254,0.0065708603],"about_ca_topic_score_codex":0.026185967,"about_ca_topic_score_gemma":0.0039470308,"teacher_disagreement_score":0.65709287,"about_ca_system_score_codex":0.00254514,"about_ca_system_score_gemma":0.003723309,"threshold_uncertainty_score":0.99968725},"labels":[],"label_agreement":null},{"id":"W893442476","doi":"10.1007/978-3-319-19833-0_6","title":"Variational Learning of Finite Inverted Dirichlet Mixture Models and Applications","year":2015,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Mixture model; Inference; Cluster analysis; Artificial intelligence; Computer science; Suite; Categorization; Dirichlet distribution; Machine learning; Statistical inference; Latent Dirichlet allocation; Statistical model; Unsupervised learning; Topic model; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.1335650067507193,"score_gpt":0.36201003706189716,"score_spread":0.22844503031117785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W893442476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9049138e-7,0.00963806,0.9466785,0.00024657152,0.00015724133,0.00030611365,0.000024212011,0.00004482348,0.042904083],"genre_scores_gemma":[0.013178007,0.002417582,0.96523947,0.00027974293,0.00019417156,0.00009463886,0.00007066981,0.00003868238,0.018487018],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979891,0.000081884165,0.00063404377,0.00059838453,0.0005169364,0.00017963296],"domain_scores_gemma":[0.9969557,0.001395179,0.00037594014,0.00026666746,0.0009288681,0.00007764452],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006420821,0.00030595562,0.00051878364,0.00031240284,0.000107248365,0.0000329704,0.0005272175,0.00019714006,0.000009100528],"category_scores_gemma":[0.00014331177,0.00029996436,0.000074462085,0.00020142189,0.00032516074,0.00022685458,0.0005431642,0.000495044,0.000009212698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038072606,0.000013419499,0.0000039621473,0.000060888913,0.00007728138,0.0000035518228,0.0008897744,0.20751208,2.8057332e-7,0.75027317,0.00025742166,0.04090436],"study_design_scores_gemma":[0.00004494795,0.000029664958,0.000003504016,0.00011258919,0.00001146927,0.000006903653,0.000016859094,0.4022867,0.0000015638755,0.59450114,0.0028229528,0.00016170983],"about_ca_topic_score_codex":0.0000056816407,"about_ca_topic_score_gemma":0.000005231509,"teacher_disagreement_score":0.19477463,"about_ca_system_score_codex":0.00009771254,"about_ca_system_score_gemma":0.00020926831,"threshold_uncertainty_score":0.9999452},"labels":[],"label_agreement":null},{"id":"W982949649","doi":"10.1007/978-3-319-11656-3_7","title":"Hidden Markov Models Based on Generalized Dirichlet Mixtures for Proportional Data Modeling","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hidden Markov model; Dirichlet distribution; Hierarchical Dirichlet process; Latent Dirichlet allocation; Computer science; Extension (predicate logic); Generalized Dirichlet distribution; Gaussian; Algorithm; Applied mathematics; Mixture model; Pattern recognition (psychology); Artificial intelligence; Mathematics; Topic model; Dirichlet series; Mathematical analysis","score_opus":0.056716862866662915,"score_gpt":0.297604837853413,"score_spread":0.2408879749867501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W982949649","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035663152,0.00043784062,0.9927544,0.002240638,0.0014714602,0.0010154613,0.000077587705,0.00019522145,0.0018037955],"genre_scores_gemma":[0.010356154,0.000034741548,0.98177445,0.0062521584,0.0009890706,0.0000455544,0.00012421572,0.00007166903,0.00035198685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935781,0.00012262617,0.0008112524,0.0030972224,0.0014821475,0.0009086712],"domain_scores_gemma":[0.99428254,0.00066043116,0.00039730332,0.003969692,0.00041298295,0.0002770663],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0031147636,0.00081509503,0.0008710083,0.00085232937,0.0003899838,0.0006793375,0.0070140217,0.0005147028,0.000013166976],"category_scores_gemma":[0.00013680702,0.00068103947,0.00023243488,0.00033937386,0.00033735708,0.0006721671,0.0017074044,0.0007877663,0.0000065254994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003087329,0.000030326175,5.4572115e-7,0.000059451086,0.000012617545,0.0000145873755,0.00006322371,0.34384754,0.00003398979,0.13752036,0.00028480295,0.5181017],"study_design_scores_gemma":[0.0003701935,0.000103312705,3.776009e-7,0.00019563505,0.000012797436,0.000010935318,6.628681e-9,0.6146726,0.00010433724,0.3834383,0.00057742355,0.0005141106],"about_ca_topic_score_codex":0.000017299613,"about_ca_topic_score_gemma":0.000014919649,"teacher_disagreement_score":0.5175876,"about_ca_system_score_codex":0.00020947734,"about_ca_system_score_gemma":0.0009823462,"threshold_uncertainty_score":0.99956405},"labels":[],"label_agreement":null}]}