{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":5,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":5,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"38188e1440f6","filters":{"venue":"Journal of Data Science Statistics and Visualisation"}},"results":[{"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5796472677540995,"gpt":0.5319713933174229,"spread":0.04767587443667654,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007106637,0.00007864075,0.000238667,0.0001806925,0.0004518983,0.00005088536,0.0004763663,0.0000164857,0.00001953015],"category_scores_gemma":[0.02253184,0.00006231743,0.00001812545,0.0002740519,0.0002038995,0.0003517005,0.0005110279,0.0001397713,1.301763e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002714302,"about_ca_system_score_gemma":0.0006186034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000434759,"about_ca_topic_score_gemma":0.00006164355,"domain_scores_codex":[0.9984211,0.0001119786,0.0005398561,0.0002323172,0.0005007803,0.0001940011],"domain_scores_gemma":[0.9967082,0.00229883,0.0005423639,0.0001862974,0.0001364323,0.0001279418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009698244,0.001013865,0.02162404,0.0006724048,0.00008180537,0.00005678325,0.09396113,0.03009252,0.001246619,0.7617856,0.06370287,0.0247925],"study_design_scores_gemma":[0.0004882265,0.0002222045,0.0008671972,0.000005206249,0.0000221803,0.000005137198,0.001232886,0.7318628,0.000001625663,0.26338,0.001838293,0.00007416615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0190192,0.00004178128,0.9775783,0.0007418668,0.00008158285,0.0001913043,0.002331688,0.000005328948,0.000008940112],"genre_scores_gemma":[0.851298,0.00002223111,0.1481553,0.0004220379,0.0000454479,0.000009837233,0.00002914485,0.000004805315,0.0000131743],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8322788,"threshold_uncertainty_score":0.9857018,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03304473039593527,"gpt":0.3409199049484037,"spread":0.3078751745524684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001694655,0.00007387528,0.0001370797,0.00003918532,0.0004979148,0.0001130857,0.0003045804,0.00001911395,0.00001371931],"category_scores_gemma":[0.00009586812,0.00006300243,0.000009849065,0.0002180672,0.0001680405,0.00006493802,0.0003458614,0.0001844462,1.992286e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000226907,"about_ca_system_score_gemma":0.0001807267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009993464,"about_ca_topic_score_gemma":0.00001195777,"domain_scores_codex":[0.998906,0.00008299722,0.000341081,0.0001682849,0.000314744,0.0001869599],"domain_scores_gemma":[0.999001,0.00005101199,0.0005494877,0.0001672368,0.0001610832,0.00007015163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001705882,0.0001799062,0.07076368,0.00004129679,0.0002309472,0.00001562403,0.002423987,0.7167729,0.01128208,0.01807794,0.08084144,0.09766438],"study_design_scores_gemma":[0.001862358,0.004930496,0.01645965,0.00006707875,0.0001606785,0.0002900186,0.004932573,0.9246612,0.0002870276,0.004146833,0.04175162,0.0004504831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09344566,0.0003835765,0.9053873,0.00005956556,0.0003037831,0.0001173262,0.0001101656,0.000002525278,0.0001900788],"genre_scores_gemma":[0.9680779,0.00008984093,0.03100841,0.000123344,0.0002879869,0.000001741143,0.0003780497,0.000006335771,0.00002638008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8746322,"threshold_uncertainty_score":0.3829608,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1328505588997095,"gpt":0.375986123003733,"spread":0.2431355641040234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00381623,0.00006299432,0.0001099906,0.0002101707,0.0004487743,0.0002658465,0.001330558,0.00001004846,0.000006699991],"category_scores_gemma":[0.0001520708,0.00005564067,0.00001108013,0.000389204,0.0001042835,0.001776239,0.0007163778,0.0001459734,1.52966e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005477175,"about_ca_system_score_gemma":0.0004793678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005169816,"about_ca_topic_score_gemma":0.000001964274,"domain_scores_codex":[0.9986089,0.00009132096,0.0002849174,0.0002287075,0.0006403239,0.0001457614],"domain_scores_gemma":[0.9989591,0.00009453363,0.0003028798,0.0003688381,0.0001708532,0.0001038074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002492605,0.0001192946,0.00008219908,0.0000291364,0.000008829107,0.00003004306,0.001274984,0.1196169,0.004091626,0.4700702,0.002770267,0.4018816],"study_design_scores_gemma":[0.0001919985,0.0001362325,0.000115952,0.000005754742,0.000007237945,0.00004497646,0.00002971166,0.9799493,0.00006546614,0.01906335,0.0003201812,0.00006985855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007960652,0.00004223347,0.9983438,0.0003133872,0.000271965,0.00004215673,0.0001287029,0.00000608245,0.00005561262],"genre_scores_gemma":[0.2079739,0.00001363997,0.7917354,0.0002284152,0.00002957433,6.644835e-7,0.000008667085,0.000002780843,0.000007068791],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8603324,"threshold_uncertainty_score":0.3451654,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1052840362049395,"gpt":0.3612068760953672,"spread":0.2559228398904277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001723533,0.0000866052,0.0001621484,0.0001455949,0.0002428493,0.0004332823,0.0007830953,0.00003502552,0.000001931274],"category_scores_gemma":[0.0002699936,0.00007103307,0.00001759299,0.0004245855,0.0001915008,0.00258557,0.000295516,0.0001201443,2.26953e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002101696,"about_ca_system_score_gemma":0.0006683354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008433288,"about_ca_topic_score_gemma":0.000002024842,"domain_scores_codex":[0.9984269,0.00005219829,0.0003727802,0.0003533202,0.0006053994,0.000189366],"domain_scores_gemma":[0.9982922,0.0001360967,0.0002443602,0.0003724228,0.0007796516,0.0001752389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001084233,0.00009772836,0.00001986283,0.0000197011,0.000009170111,0.000008810809,0.0001972185,0.001057314,0.001773397,0.9654498,0.0007675654,0.03058856],"study_design_scores_gemma":[0.0002831893,0.00012173,0.0003163005,0.00001841998,0.00001471873,0.00009093487,0.0000407632,0.8634326,0.0002329855,0.1353325,0.00002938169,0.00008647657],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004405598,0.00009096749,0.9946262,0.0003862322,0.0001861649,0.00005319658,0.0002171631,0.000006972934,0.00002747838],"genre_scores_gemma":[0.4617538,0.0000382518,0.5380034,0.0001025571,0.00004453003,7.482223e-7,0.00004973938,0.00000232199,0.000004582856],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8623753,"threshold_uncertainty_score":0.4178151,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5004361897846052,"gpt":0.6208016945122043,"spread":0.1203655047275991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02128154,0.0001347546,0.0002798651,0.000726102,0.0003725434,0.001384955,0.001185628,0.00004009033,0.00009130341],"category_scores_gemma":[0.008488682,0.00008783057,0.00002509314,0.001141515,0.0004683305,0.002542144,0.0002352517,0.0001071992,0.000004810207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001190946,"about_ca_system_score_gemma":0.0003365062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001765402,"about_ca_topic_score_gemma":0.000001356842,"domain_scores_codex":[0.9958621,0.0001975332,0.0009485924,0.0005836638,0.002152477,0.0002556276],"domain_scores_gemma":[0.9954903,0.002413903,0.0003521763,0.0004789048,0.0009215826,0.0003431911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003724149,0.0001218034,0.00007558949,0.00002126648,0.00001359687,0.00001832428,0.005091198,0.0230985,0.7017424,0.02234572,0.005743188,0.241356],"study_design_scores_gemma":[0.0003362963,0.001475871,0.001815127,0.0001052736,0.00003450323,0.00005858186,0.001171832,0.9832632,0.005087254,0.005054726,0.001467708,0.0001296583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2092087,0.0001495626,0.7890254,0.0001199721,0.000812873,0.0002035835,0.0004584463,0.00000498123,0.0000164506],"genre_scores_gemma":[0.3944041,0.000009566946,0.6052982,0.00005859152,0.0001869779,9.013856e-7,0.00001237581,0.000008048167,0.00002129504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9601647,"threshold_uncertainty_score":0.9998633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}