{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06405109,0.001144529,0.002479255,0.003375871,0.0009293593,0.003856721,0.002985534,0.002623368,0.006267045],"category_scores_gemma":[0.3189662,0.0004496848,0.001752192,0.00314422,0.01223905,0.008838153,0.005103684,0.005211674,0.0009815141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0010317,"about_ca_system_score_gemma":0.002026577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002812331,"about_ca_topic_score_gemma":0.0001203874,"domain_scores_codex":[0.9302506,0.05415446,0.003124692,0.004523555,0.006738439,0.001208264],"domain_scores_gemma":[0.6209229,0.3297705,0.01501978,0.02358008,0.008830291,0.001876451],"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":[0.0006269207,0.0001220951,0.01058623,0.0005694726,0.0004888888,0.000387229,0.0005927646,0.01633036,0.001499316,0.8592465,0.002276224,0.1072741],"study_design_scores_gemma":[0.0001546732,0.0006564169,0.005631961,0.0002182135,0.00008028047,0.0006127894,0.0003733282,0.03345803,0.001907876,0.9511412,0.005687171,0.00007801774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0386706,0.001375431,0.9451764,0.001829237,0.0002960835,0.0002347688,0.0005108037,0.0002726728,0.01163402],"genre_scores_gemma":[0.7983986,0.0007177094,0.1954388,0.001208574,0.0005406798,0.00117422,0.0005548946,0.0001939452,0.001772529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06405109,"threshold_uncertainty_score":0.3387386,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02223228,0.004104285,0.004500605,0.003859695,0.00104252,0.004182342,0.008329513,0.005537601,0.03328589],"category_scores_gemma":[0.04720933,0.001729153,0.004836228,0.004667594,0.003343013,0.006727892,0.003436735,0.004930388,0.007026665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003182397,"about_ca_system_score_gemma":0.001846053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008691773,"about_ca_topic_score_gemma":0.007643634,"domain_scores_codex":[0.9842805,0.009662603,0.0006817787,0.003230301,0.001365555,0.0007792352],"domain_scores_gemma":[0.9601827,0.03127508,0.00320862,0.003156635,0.001672039,0.0005049481],"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":[0.0002129248,0.0001918244,0.002765501,0.0006353507,0.0005173016,0.0003269413,0.0004458227,0.1353787,0.0005175093,0.8164545,0.007125193,0.0354284],"study_design_scores_gemma":[0.0002058602,0.0001877413,0.001203901,0.0001614428,0.0003518522,0.0002159023,0.0001084789,0.2930423,0.0002348264,0.6894345,0.01478376,0.00006938801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009197623,0.001642107,0.9712877,0.002009638,0.000254088,0.0007274257,0.004280339,0.0007169845,0.009884069],"genre_scores_gemma":[0.44394,0.008233017,0.4451031,0.003452082,0.001249188,0.009193555,0.006736628,0.0005383485,0.08155409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03328589,"threshold_uncertainty_score":0.117577,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01141748,0.002087685,0.002119766,0.00249029,0.0005147647,0.001864024,0.002474816,0.001820135,0.0119494],"category_scores_gemma":[0.04717419,0.001345961,0.003403036,0.002224441,0.0009080349,0.001599828,0.002581429,0.003407631,0.00688381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006435887,"about_ca_system_score_gemma":0.002294468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007152129,"about_ca_topic_score_gemma":0.008692376,"domain_scores_codex":[0.9945447,0.003821727,0.0002624878,0.000563407,0.0006571187,0.0001504216],"domain_scores_gemma":[0.9835633,0.01246637,0.001097487,0.001777665,0.000907077,0.00018816],"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":[0.0005186326,0.0001461921,0.007965251,0.001633859,0.001432008,0.0006795193,0.000456771,0.5000411,0.004227091,0.1008764,0.07359408,0.3084291],"study_design_scores_gemma":[0.0001248457,0.00005217351,0.001034416,0.0001055232,0.00009332495,0.0002430378,0.00002906439,0.9165606,0.001623649,0.05861343,0.0214574,0.00006245072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001235291,0.000329996,0.9906974,0.0001683331,0.00003509351,0.00004435212,0.0008307752,0.006384766,0.0002741744],"genre_scores_gemma":[0.03799126,0.0004805488,0.9513947,0.0002615139,0.0001068803,0.0007502327,0.003822234,0.003719261,0.001473412],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0119494,"threshold_uncertainty_score":0.06038213,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009730639,0.001625678,0.001955316,0.001949332,0.004673076,0.004746497,0.003003366,0.0235904,0.07548752],"category_scores_gemma":[0.1684524,0.001047082,0.001838549,0.001772229,0.0040965,0.005531405,0.002762762,0.02346774,0.0877699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004409843,"about_ca_system_score_gemma":0.007217225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02189821,"about_ca_topic_score_gemma":0.01912174,"domain_scores_codex":[0.9900003,0.00181918,0.001633908,0.001112832,0.004777085,0.0006566096],"domain_scores_gemma":[0.9281703,0.02972456,0.004256501,0.003086536,0.03107758,0.003684587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001248312,0.000002637821,0.00006134244,0.00002105767,0.000002616812,0.0000417272,0.00002659895,0.000008119685,0.00003121139,0.0003460398,0.9987123,0.0007339183],"study_design_scores_gemma":[0.00005747682,0.00002136353,0.0008173846,0.0002809816,0.00001299191,0.0002059406,0.0003363353,0.0001824942,0.0003361745,0.002258764,0.9954376,0.00005251458],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0002697221,0.0008825871,0.001175595,0.8067262,0.1779554,0.0001093702,0.001178348,0.0009677615,0.01073508],"genre_scores_gemma":[0.003002741,0.0009901715,0.001288062,0.8651991,0.06572483,0.0002967273,0.0004660002,0.0008184484,0.062214],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.07548752,"threshold_uncertainty_score":0.2525309,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02532889,0.006058188,0.007888233,0.00692298,0.00403244,0.008460451,0.004613293,0.01193326,0.02772077],"category_scores_gemma":[0.1171893,0.002630734,0.004601713,0.003432728,0.003342129,0.004147632,0.001105963,0.01996491,0.02276069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002406385,"about_ca_system_score_gemma":0.005247454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001178295,"about_ca_topic_score_gemma":0.002389005,"domain_scores_codex":[0.9847865,0.003973334,0.003155733,0.001720377,0.0058128,0.0005513225],"domain_scores_gemma":[0.8495863,0.08654568,0.007612037,0.003887394,0.04617837,0.00619025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001207454,0.00001855415,0.00002287379,0.0006802916,0.00004770113,0.00005493729,0.000009095814,0.00005854428,0.00007686244,0.0003280338,0.9915335,0.007048923],"study_design_scores_gemma":[0.0006610163,0.0002094,0.0009115502,0.001887754,0.0003882534,0.0005459324,0.00007126276,0.0010041,0.0004948307,0.004587024,0.9891545,0.00008447334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.00002182438,0.002567542,0.0004786335,0.005563515,0.9906449,0.0000485972,0.0001429516,0.00008944797,0.0004426104],"genre_scores_gemma":[0.0005605885,0.005081919,0.001083546,0.01031762,0.9758459,0.0002162417,0.0001645309,0.0001290312,0.006600507],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.02772077,"threshold_uncertainty_score":0.1339536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}