{"meta":{"query_hash":"26f1600d4d83","filters":{"venue":"The New England Journal of Statistics in Data Science"},"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/26f1600d4d83","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+New+England+Journal+of+Statistics+in+Data+Science"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16893621089889096,"score_gpt":0.429298967957509,"score_spread":0.260362757058618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312515328","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063846037,0.00033318822,0.98301077,0.0053179143,0.00076191704,0.00036270198,0.0034557227,0.00001789813,0.000355296],"genre_scores_gemma":[0.15069434,0.0007278677,0.84639686,0.0011871735,0.0003439374,0.000014903828,0.00007070231,0.00005651695,0.0005076879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959117,0.0004205397,0.000965032,0.0005490095,0.0014910429,0.00066266244],"domain_scores_gemma":[0.99538034,0.0023369857,0.0007033524,0.0009575259,0.00019606999,0.0004257323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070610843,0.00030842377,0.0005681724,0.00021716295,0.0008626785,0.0002608333,0.0022635353,0.00004944558,0.000105320316],"category_scores_gemma":[0.003133859,0.00021962772,0.000033618457,0.00062431325,0.00045579567,0.0005632371,0.0012555717,0.0011615141,0.0000017044764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012690374,0.0010612541,0.0004364699,0.000126707,0.00011551477,0.00034892262,0.0054586134,0.0017589164,0.0013857362,0.72083884,0.14501786,0.1221821],"study_design_scores_gemma":[0.0073867743,0.0009857327,0.0003279837,0.00013857806,0.00016097103,0.00038879947,0.002029269,0.022271993,0.00015951082,0.7734149,0.19219157,0.0005438924],"about_ca_topic_score_codex":0.00013370936,"about_ca_topic_score_gemma":0.000038700146,"teacher_disagreement_score":0.14430973,"about_ca_system_score_codex":0.00021052954,"about_ca_system_score_gemma":0.0004209772,"threshold_uncertainty_score":0.8956159},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.17173287554959368,"score_gpt":0.4322849311017763,"score_spread":0.26055205555218264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367338397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023337152,0.00006107896,0.97429305,0.00028908777,0.00048592492,0.00021623576,0.0005358536,0.0000567961,0.000724815],"genre_scores_gemma":[0.2876923,0.0010955319,0.70953107,0.00010448397,0.0012131982,0.000004571833,0.000047618847,0.0000293651,0.00028185133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982593,0.0001448198,0.000421083,0.000180053,0.00063227816,0.00036247342],"domain_scores_gemma":[0.99528867,0.0035172934,0.00031819468,0.00060772063,0.00015804933,0.00011006379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062042046,0.00011705273,0.00024826164,0.00015145767,0.00014223538,0.000075858006,0.0018674387,0.00002996628,0.00001972389],"category_scores_gemma":[0.0043305703,0.00007059722,0.000015333353,0.0009450638,0.0003526121,0.0008404232,0.00056059007,0.00038571542,0.0000061102437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013440591,0.00003061109,0.0001899664,0.00002786069,0.00002440448,0.00025313685,0.001167795,0.011916532,0.00060052815,0.6253851,0.25301734,0.10725232],"study_design_scores_gemma":[0.0006069391,0.00015804952,0.00026867606,0.00009809628,0.000019306177,0.00007063788,0.000033627977,0.057195332,0.00033317204,0.93952006,0.0016019687,0.00009414224],"about_ca_topic_score_codex":0.000017050816,"about_ca_topic_score_gemma":0.000059369693,"teacher_disagreement_score":0.31413496,"about_ca_system_score_codex":0.00006424007,"about_ca_system_score_gemma":0.00028873378,"threshold_uncertainty_score":0.518441},"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":"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.39248641983575977,"score_gpt":0.5391577650210972,"score_spread":0.14667134518533748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389063115","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008192393,0.00021507767,0.97877055,0.00019196214,0.011134857,0.00024981349,0.0011892356,0.0000049223263,0.00005120795],"genre_scores_gemma":[0.07311686,0.0002670997,0.92464614,0.00002722377,0.0018563069,0.0000016034555,0.000026470785,0.000007660106,0.000050662733],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99421805,0.00032660202,0.0010190525,0.0006292117,0.0034468928,0.00036020615],"domain_scores_gemma":[0.98633885,0.009876181,0.0007531497,0.0020450298,0.0007603096,0.00022648678],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.072105676,0.000116698924,0.0004362185,0.0015082777,0.00031226463,0.0004901935,0.0101941535,0.000029066938,0.000021063597],"category_scores_gemma":[0.044099625,0.000069074835,0.000022542066,0.008318181,0.0019342473,0.002735078,0.0025588037,0.00015612294,0.0000027204228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012147019,0.00022906114,0.003284176,0.000015888249,0.00025395965,0.000033319153,0.008037365,0.014253333,0.27055597,0.01348602,0.44034892,0.24828728],"study_design_scores_gemma":[0.0025442743,0.0004621377,0.006650323,0.000038793773,0.0002874329,0.000019403686,0.0016940738,0.927683,0.010348177,0.03336464,0.016675228,0.00023250963],"about_ca_topic_score_codex":0.000047604655,"about_ca_topic_score_gemma":0.000009379649,"teacher_disagreement_score":0.9134297,"about_ca_system_score_codex":0.000045984954,"about_ca_system_score_gemma":0.0011847633,"threshold_uncertainty_score":0.9951612},"labels":[],"label_agreement":null},{"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,"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":"Nonparametric statistics; Symmetry (geometry); Statistical physics; Mathematics; Computer science; Physics; Econometrics; Geometry","score_opus":0.449767996736839,"score_gpt":0.56192055813586,"score_spread":0.11215256139902097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392101232","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018521484,0.00079289597,0.974714,0.00071793754,0.0029683781,0.00020410198,0.0012435968,0.0000137592615,0.00082384126],"genre_scores_gemma":[0.19007346,0.00035707533,0.80907834,0.000027448328,0.00040155987,3.373506e-7,0.000001045289,0.000011276522,0.000049443515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99664766,0.0003709561,0.0013296589,0.0002585584,0.0011256794,0.00026747936],"domain_scores_gemma":[0.886828,0.11123164,0.0005230942,0.00095129316,0.00028201772,0.00018393039],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021722296,0.0001187391,0.0004741533,0.00044356065,0.000053158783,0.00012536242,0.0025470105,0.000049718994,0.000079645804],"category_scores_gemma":[0.27393147,0.00006873372,0.000035185818,0.002138008,0.00079261954,0.00035800066,0.00050164765,0.0005949019,0.0000071530717],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104671046,0.0001254161,0.0003997435,0.00023130536,0.000047079928,0.00018267486,0.0003656808,0.000019283434,0.00057843537,0.6982177,0.023643082,0.27608496],"study_design_scores_gemma":[0.00087280164,0.00018030367,0.001511639,0.00033037024,0.00009221252,0.00012166987,0.000042571595,0.003869255,0.0003115725,0.99074227,0.0018374469,0.000087911765],"about_ca_topic_score_codex":0.000021042282,"about_ca_topic_score_gemma":0.000017520819,"teacher_disagreement_score":0.29252458,"about_ca_system_score_codex":0.00005388515,"about_ca_system_score_gemma":0.0007513599,"threshold_uncertainty_score":0.7528558},"labels":[],"label_agreement":null}]}