{"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","author_layer_release":"2026-06-26"},"query_hash":"26f1600d4d83","filters":{"venue":"The New England Journal of Statistics in Data Science"}},"results":[{"id":"W4392101232","doi":"10.51387/24-nejsds60","title":"Nonparametric E-tests of Symmetry","year":2024,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Symmetry (geometry); Statistical physics; Mathematics; Computer science; Physics; Econometrics; Geometry","authors":[{"name":"Vladimir Vovk","is_ca":true},{"name":"Ruodu Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.449767996736839,"gpt":0.56192055813586,"spread":0.112152561399021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0217223,0.0001187391,0.0004741533,0.0004435607,0.00005315878,0.0001253624,0.002547011,0.00004971899,0.0000796458],"category_scores_gemma":[0.2739315,0.00006873372,0.00003518582,0.002138008,0.0007926195,0.0003580007,0.0005016476,0.0005949019,0.000007153072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005388515,"about_ca_system_score_gemma":0.0007513599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002104228,"about_ca_topic_score_gemma":0.00001752082,"domain_scores_codex":[0.9966477,0.0003709561,0.001329659,0.0002585584,0.001125679,0.0002674794],"domain_scores_gemma":[0.886828,0.1112316,0.0005230942,0.0009512932,0.0002820177,0.0001839304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000104671,0.0001254161,0.0003997435,0.0002313054,0.00004707993,0.0001826749,0.0003656808,0.00001928343,0.0005784354,0.6982177,0.02364308,0.276085],"study_design_scores_gemma":[0.0008728016,0.0001803037,0.001511639,0.0003303702,0.00009221252,0.0001216699,0.0000425716,0.003869255,0.0003115725,0.9907423,0.001837447,0.00008791177],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01852148,0.000792896,0.974714,0.0007179375,0.002968378,0.000204102,0.001243597,0.00001375926,0.0008238413],"genre_scores_gemma":[0.1900735,0.0003570753,0.8090783,0.00002744833,0.0004015599,3.373506e-7,0.000001045289,0.00001127652,0.00004944352],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2925246,"threshold_uncertainty_score":0.7528558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367338397","doi":"10.51387/23-nejsds29","title":"General Additive Network Effect Models","year":2023,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Actua; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Inference; Specification; Outcome (game theory); Computer science; Network model; Range (aeronautics); Power (physics); Mathematical optimization; Mathematics; Artificial intelligence; Statistics; Engineering; Machine learning; Mathematical economics","authors":[{"name":"Trang Bui","is_ca":true},{"name":"Stefan H. Steiner","is_ca":true},{"name":"Nathaniel T. Stevens","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1717328755495937,"gpt":0.4322849311017763,"spread":0.2605520555521826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006204205,0.0001170527,0.0002482616,0.0001514577,0.0001422354,0.00007585801,0.001867439,0.00002996628,0.00001972389],"category_scores_gemma":[0.00433057,0.00007059722,0.00001533335,0.0009450638,0.0003526121,0.0008404232,0.0005605901,0.0003857154,0.000006110244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006424007,"about_ca_system_score_gemma":0.0002887338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001705082,"about_ca_topic_score_gemma":0.00005936969,"domain_scores_codex":[0.9982593,0.0001448198,0.000421083,0.000180053,0.0006322782,0.0003624734],"domain_scores_gemma":[0.9952887,0.003517293,0.0003181947,0.0006077206,0.0001580493,0.0001100638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001344059,0.00003061109,0.0001899664,0.00002786069,0.00002440448,0.0002531369,0.001167795,0.01191653,0.0006005281,0.6253851,0.2530173,0.1072523],"study_design_scores_gemma":[0.0006069391,0.0001580495,0.0002686761,0.00009809628,0.00001930618,0.00007063788,0.00003362798,0.05719533,0.000333172,0.9395201,0.001601969,0.00009414224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02333715,0.00006107896,0.9742931,0.0002890878,0.0004859249,0.0002162358,0.0005358536,0.0000567961,0.000724815],"genre_scores_gemma":[0.2876923,0.001095532,0.7095311,0.000104484,0.001213198,0.000004571833,0.00004761885,0.0000293651,0.0002818513],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.314135,"threshold_uncertainty_score":0.518441,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Farhad Shokoohi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03959118503490956,"gpt":0.3056892963842625,"spread":0.266098111349353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003387637,0.0001245782,0.0003003111,0.0003671123,0.00006458657,0.00008690978,0.001740602,0.00005371787,0.000003164498],"category_scores_gemma":[0.000628516,0.000069572,0.0000105534,0.001681908,0.0002782737,0.00128732,0.0004285451,0.0003171368,4.994475e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001739595,"about_ca_system_score_gemma":0.0003802702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003221759,"about_ca_topic_score_gemma":0.00007375712,"domain_scores_codex":[0.9982898,0.0001778727,0.0004739483,0.0002535735,0.0005907582,0.0002140843],"domain_scores_gemma":[0.9978971,0.0006787897,0.0004860286,0.000631774,0.0002097453,0.00009657147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007907105,0.0002861313,0.001275253,0.0003473203,0.00006643782,0.0006851263,0.02611432,0.1316087,0.06098906,0.114222,0.01627281,0.6473422],"study_design_scores_gemma":[0.001455248,0.0001541347,0.001929144,0.0004502548,0.00001309817,0.00008234361,0.00003661189,0.9068331,0.001739207,0.08714674,0.00005445791,0.0001056287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02940774,0.0001154527,0.9693833,0.0007103457,0.00007303366,0.0001047289,0.0001634815,0.000005740175,0.00003618711],"genre_scores_gemma":[0.369276,0.0002123891,0.6304251,0.00002307683,0.00001988364,3.281711e-7,0.00001336694,0.000004847874,0.00002499415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7752244,"threshold_uncertainty_score":0.3234501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312515328","doi":"10.51387/22-nejsds6c","title":"Comment on “Double Your Variance, Dirtify Your Bayes, Devour Your Pufferfish, and Draw Your Kidstogram,” by Xiao-Li Meng","year":2022,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Variance (accounting); Bayes' theorem; Naive Bayes classifier; Psychology; Statistics; Mathematics; Artificial intelligence; Computer science; Bayesian probability; Business","authors":[{"name":"Eric D. Kolaczyk","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.168936210898891,"gpt":0.429298967957509,"spread":0.260362757058618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007061084,0.0003084238,0.0005681724,0.0002171629,0.0008626785,0.0002608333,0.002263535,0.00004944558,0.0001053203],"category_scores_gemma":[0.003133859,0.0002196277,0.00003361846,0.0006243133,0.0004557957,0.0005632371,0.001255572,0.001161514,0.000001704476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002105295,"about_ca_system_score_gemma":0.0004209772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001337094,"about_ca_topic_score_gemma":0.00003870015,"domain_scores_codex":[0.9959117,0.0004205397,0.000965032,0.0005490095,0.001491043,0.0006626624],"domain_scores_gemma":[0.9953803,0.002336986,0.0007033524,0.0009575259,0.00019607,0.0004257323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001269037,0.001061254,0.0004364699,0.000126707,0.0001155148,0.0003489226,0.005458613,0.001758916,0.001385736,0.7208388,0.1450179,0.1221821],"study_design_scores_gemma":[0.007386774,0.0009857327,0.0003279837,0.0001385781,0.000160971,0.0003887995,0.002029269,0.02227199,0.0001595108,0.7734149,0.1921916,0.0005438924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006384604,0.0003331882,0.9830108,0.005317914,0.000761917,0.000362702,0.003455723,0.00001789813,0.000355296],"genre_scores_gemma":[0.1506943,0.0007278677,0.8463969,0.001187174,0.0003439374,0.00001490383,0.00007070231,0.00005651695,0.0005076879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1443097,"threshold_uncertainty_score":0.8956159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389063115","doi":"10.51387/23-nejsds13edi","title":"Editorial. Design and Analysis of Experiments for Data Science","year":2023,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Data science; Statistical analysis; New england; Library science; Computer science; Statistics; Political science; Mathematics; Law","authors":[{"name":"HaiYing Wang","is_ca":false},{"name":"Xinwei Deng","is_ca":false},{"name":"Devon Lin","is_ca":true},{"name":"Ming‐Hui Chen","is_ca":false},{"name":"Minge Xie","is_ca":false},{"name":"Jing Wu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3924864198357598,"gpt":0.5391577650210972,"spread":0.1466713451853375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07210568,0.0001166989,0.0004362185,0.001508278,0.0003122646,0.0004901935,0.01019415,0.00002906694,0.0000210636],"category_scores_gemma":[0.04409963,0.00006907483,0.00002254207,0.008318181,0.001934247,0.002735078,0.002558804,0.0001561229,0.000002720423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004598495,"about_ca_system_score_gemma":0.001184763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004760466,"about_ca_topic_score_gemma":0.000009379649,"domain_scores_codex":[0.9942181,0.000326602,0.001019052,0.0006292117,0.003446893,0.0003602061],"domain_scores_gemma":[0.9863389,0.009876181,0.0007531497,0.00204503,0.0007603096,0.0002264868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001214702,0.0002290611,0.003284176,0.00001588825,0.0002539596,0.00003331915,0.008037365,0.01425333,0.270556,0.01348602,0.4403489,0.2482873],"study_design_scores_gemma":[0.002544274,0.0004621377,0.006650323,0.00003879377,0.0002874329,0.00001940369,0.001694074,0.927683,0.01034818,0.03336464,0.01667523,0.0002325096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008192393,0.0002150777,0.9787706,0.0001919621,0.01113486,0.0002498135,0.001189236,0.000004922326,0.00005120795],"genre_scores_gemma":[0.07311686,0.0002670997,0.9246461,0.00002722377,0.001856307,0.000001603456,0.00002647079,0.000007660106,0.00005066273],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9134297,"threshold_uncertainty_score":0.9951612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}