{"meta":{"query_hash":"38188e1440f6","filters":{"venue":"Journal of Data Science Statistics and Visualisation"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"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/38188e1440f6","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Data+Science+Statistics+and+Visualisation"},"results":[{"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":"W3206048154","doi":"10.52933/jdssv.v1i2.11","title":"A Stepwise Approach for High-Dimensional Gaussian Graphical Models","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science Statistics and Visualisation","topic":"Bayesian Modeling and Causal Inference","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":"Graphical model; Partial correlation; Gaussian; Correlation; Stepwise regression; Lasso (programming language); Computer science; Algorithm; Graph; Relation (database); Minification; Exploit; Canonical correlation; Mathematics; Mathematical optimization; Artificial intelligence; Data mining; Machine learning; Theoretical computer science","score_opus":0.10528403620493945,"score_gpt":0.36120687609536717,"score_spread":0.25592283989042774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206048154","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004405598,0.00009096749,0.9946262,0.00038623216,0.00018616488,0.00005319658,0.00021716315,0.0000069729335,0.000027478376],"genre_scores_gemma":[0.46175385,0.000038251797,0.53800344,0.000102557075,0.000044530032,7.482223e-7,0.000049739385,0.0000023219895,0.000004582856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984269,0.000052198287,0.00037278017,0.00035332024,0.0006053994,0.00018936604],"domain_scores_gemma":[0.9982922,0.00013609673,0.0002443602,0.00037242277,0.0007796516,0.00017523892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001723533,0.0000866052,0.0001621484,0.00014559491,0.00024284926,0.00043328232,0.0007830953,0.000035025518,0.000001931274],"category_scores_gemma":[0.00026999364,0.00007103307,0.000017592989,0.00042458548,0.00019150079,0.0025855696,0.00029551602,0.000120144294,2.2695305e-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":[0.000010842331,0.00009772836,0.000019862835,0.0000197011,0.000009170111,0.000008810809,0.00019721848,0.0010573142,0.0017733966,0.9654498,0.00076756545,0.030588558],"study_design_scores_gemma":[0.00028318926,0.00012173003,0.00031630055,0.000018419978,0.000014718728,0.000090934875,0.000040763203,0.8634326,0.00023298548,0.13533251,0.00002938169,0.00008647657],"about_ca_topic_score_codex":0.000008433288,"about_ca_topic_score_gemma":0.000002024842,"teacher_disagreement_score":0.86237526,"about_ca_system_score_codex":0.000021016962,"about_ca_system_score_gemma":0.0006683354,"threshold_uncertainty_score":0.41781515},"labels":[],"label_agreement":null},{"id":"W4295106816","doi":"10.52933/jdssv.v2i5.56","title":"Network Comparison with Interpretable Contrastive Network Representation Learning","year":2022,"lang":"en","type":"article","venue":"Journal of Data Science Statistics and Visualisation","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","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 Waterloo","funders":"National Cancer Institute; National Science Foundation","keywords":"Computer science; Artificial intelligence; Representation (politics); Machine learning; Interpretability; Task (project management); Salient; Feature learning; Network analysis; Theoretical computer science; Natural language processing","score_opus":0.033044730395935265,"score_gpt":0.3409199049484037,"score_spread":0.30787517455246843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295106816","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":[0.09344566,0.0003835765,0.90538734,0.000059565562,0.0003037831,0.000117326235,0.00011016556,0.0000025252775,0.00019007885],"genre_scores_gemma":[0.9680779,0.000089840934,0.03100841,0.00012334397,0.00028798686,0.0000017411428,0.0003780497,0.0000063357706,0.000026380076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890596,0.00008299722,0.00034108103,0.0001682849,0.00031474396,0.00018695988],"domain_scores_gemma":[0.999001,0.00005101199,0.0005494877,0.00016723681,0.00016108323,0.00007015163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016946547,0.00007387528,0.00013707968,0.000039185317,0.0004979148,0.00011308566,0.00030458043,0.000019113952,0.0000137193065],"category_scores_gemma":[0.00009586812,0.00006300243,0.0000098490655,0.00021806719,0.00016804054,0.00006493802,0.0003458614,0.00018444621,1.9922862e-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":[0.0017058816,0.00017990624,0.070763685,0.000041296793,0.00023094723,0.000015624028,0.002423987,0.71677285,0.011282078,0.018077936,0.080841444,0.09766438],"study_design_scores_gemma":[0.0018623583,0.004930496,0.016459646,0.00006707875,0.00016067854,0.0002900186,0.004932573,0.92466116,0.00028702762,0.0041468334,0.041751623,0.00045048306],"about_ca_topic_score_codex":0.000009993464,"about_ca_topic_score_gemma":0.000011957765,"teacher_disagreement_score":0.87463224,"about_ca_system_score_codex":0.000022690696,"about_ca_system_score_gemma":0.0001807267,"threshold_uncertainty_score":0.38296083},"labels":[],"label_agreement":null},{"id":"W4353002908","doi":"10.52933/jdssv.v2i7.46","title":"A Spatial SEIR Model for COVID-19 in South Africa","year":2022,"lang":"en","type":"article","venue":"Journal of Data Science Statistics and Visualisation","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":7,"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":"Center for High Performance Computing; National Research Foundation; International Development Research Centre","keywords":"Coronavirus disease 2019 (COVID-19); Geography; Context (archaeology); Vulnerability (computing); Socioeconomic status; Psychological intervention; Econometrics; Infectious disease (medical specialty); Environmental health; Computer science; Disease; Medicine; Mathematics; Population","score_opus":0.5796472677540995,"score_gpt":0.5319713933174229,"score_spread":0.047675874436676535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353002908","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019019196,0.000041781284,0.9775783,0.0007418668,0.000081582846,0.00019130427,0.0023316883,0.000005328948,0.000008940112],"genre_scores_gemma":[0.85129803,0.00002223111,0.1481553,0.00042203788,0.0000454479,0.000009837233,0.000029144847,0.000004805315,0.000013174297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984211,0.000111978574,0.0005398561,0.00023231724,0.0005007803,0.00019400108],"domain_scores_gemma":[0.99670815,0.0022988303,0.00054236385,0.00018629737,0.0001364323,0.00012794182],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007106637,0.00007864075,0.000238667,0.00018069247,0.0004518983,0.000050885355,0.00047636635,0.0000164857,0.000019530145],"category_scores_gemma":[0.022531845,0.000062317435,0.000018125453,0.00027405185,0.00020389952,0.0003517005,0.00051102793,0.00013977128,1.3017629e-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":[0.0009698244,0.0010138649,0.021624042,0.00067240477,0.00008180537,0.00005678325,0.093961135,0.030092515,0.0012466192,0.7617856,0.063702874,0.024792496],"study_design_scores_gemma":[0.00048822648,0.00022220446,0.00086719723,0.000005206249,0.0000221803,0.0000051371976,0.0012328859,0.73186284,0.0000016256633,0.26338002,0.001838293,0.00007416615],"about_ca_topic_score_codex":0.000043475902,"about_ca_topic_score_gemma":0.00006164355,"teacher_disagreement_score":0.83227885,"about_ca_system_score_codex":0.00027143015,"about_ca_system_score_gemma":0.00061860343,"threshold_uncertainty_score":0.9857018},"labels":[],"label_agreement":null},{"id":"W4399330943","doi":"10.52933/jdssv.v4i3.83","title":"An Efficient Way to Find Optimal Crossover Designs Using CVX for Precision Medicine","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science Statistics and Visualisation","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","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; Ontario Medical Association","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Crossover; Crossover study; Optimal design; Mathematical optimization; Regular polygon; Construct (python library); Computer science; Convex optimization; Algorithm; Mathematics; Medicine; Artificial intelligence; Machine learning","score_opus":0.5004361897846052,"score_gpt":0.6208016945122043,"score_spread":0.1203655047275991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399330943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20920868,0.00014956265,0.7890254,0.00011997206,0.00081287295,0.00020358349,0.0004584463,0.00000498123,0.000016450598],"genre_scores_gemma":[0.3944041,0.000009566946,0.60529816,0.000058591522,0.0001869779,9.013856e-7,0.000012375813,0.000008048167,0.000021295042],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958621,0.00019753315,0.00094859244,0.00058366376,0.002152477,0.00025562764],"domain_scores_gemma":[0.99549025,0.0024139027,0.00035217626,0.00047890475,0.00092158257,0.00034319115],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.021281537,0.00013475458,0.0002798651,0.000726102,0.00037254344,0.0013849548,0.0011856285,0.000040090334,0.00009130341],"category_scores_gemma":[0.008488682,0.000087830565,0.00002509314,0.0011415152,0.00046833052,0.0025421437,0.00023525173,0.000107199216,0.0000048102065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037241488,0.00012180344,0.00007558949,0.00002126648,0.000013596872,0.000018324276,0.005091198,0.0230985,0.7017424,0.022345722,0.0057431883,0.24135597],"study_design_scores_gemma":[0.00033629627,0.001475871,0.0018151272,0.00010527362,0.000034503235,0.000058581856,0.0011718324,0.9832632,0.0050872536,0.005054726,0.0014677076,0.00012965832],"about_ca_topic_score_codex":0.000017654023,"about_ca_topic_score_gemma":0.0000013568423,"teacher_disagreement_score":0.96016467,"about_ca_system_score_codex":0.00011909458,"about_ca_system_score_gemma":0.00033650623,"threshold_uncertainty_score":0.99986327},"labels":[],"label_agreement":null}]}