{"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026972208,0.0008825871,0.0011755947,0.80672616,0.17795536,0.00010937019,0.0011783482,0.0009677615,0.010735082],"genre_scores_gemma":[0.003002741,0.0009901715,0.0012880617,0.8651991,0.065724835,0.00029672726,0.00046600017,0.0008184484,0.062214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900003,0.0018191801,0.0016339077,0.0011128323,0.004777085,0.0006566096],"domain_scores_gemma":[0.92817026,0.029724564,0.0042565013,0.0030865357,0.031077579,0.0036845873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009730639,0.001625678,0.0019553162,0.0019493316,0.004673076,0.004746497,0.0030033663,0.023590399,0.07548752],"category_scores_gemma":[0.16845238,0.0010470822,0.0018385488,0.0017722287,0.0040965,0.0055314046,0.0027627624,0.023467738,0.087769896],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012483121,0.000002637821,0.00006134244,0.000021057667,0.0000026168116,0.0000417272,0.000026598955,0.000008119685,0.00003121139,0.00034603983,0.9987123,0.00073391834],"study_design_scores_gemma":[0.00005747682,0.00002136353,0.00081738457,0.0002809816,0.000012991911,0.0002059406,0.00033633533,0.00018249416,0.0003361745,0.0022587636,0.99543756,0.000052514577],"about_ca_topic_score_codex":0.021898208,"about_ca_topic_score_gemma":0.019121738,"teacher_disagreement_score":0.07548752,"about_ca_system_score_codex":0.004409843,"about_ca_system_score_gemma":0.007217225,"threshold_uncertainty_score":0.25253093},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0091976235,0.0016421066,0.9712877,0.0020096384,0.00025408797,0.0007274257,0.0042803385,0.0007169845,0.009884069],"genre_scores_gemma":[0.44393998,0.008233017,0.4451031,0.0034520822,0.0012491875,0.009193555,0.0067366282,0.0005383485,0.08155409],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98428047,0.009662603,0.0006817787,0.0032303007,0.0013655549,0.00077923515],"domain_scores_gemma":[0.96018267,0.03127508,0.00320862,0.0031566345,0.0016720387,0.0005049481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02223228,0.004104285,0.004500605,0.003859695,0.00104252,0.0041823415,0.0083295135,0.0055376007,0.03328589],"category_scores_gemma":[0.047209326,0.0017291526,0.0048362277,0.004667594,0.0033430133,0.006727892,0.003436735,0.004930388,0.0070266654],"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":[0.00021292483,0.00019182444,0.002765501,0.0006353507,0.00051730155,0.00032694134,0.00044582275,0.13537866,0.0005175093,0.8164545,0.007125193,0.035428405],"study_design_scores_gemma":[0.00020586024,0.0001877413,0.0012039008,0.00016144277,0.00035185218,0.00021590228,0.00010847887,0.29304233,0.00023482642,0.68943447,0.014783761,0.000069388014],"about_ca_topic_score_codex":0.008691773,"about_ca_topic_score_gemma":0.007643634,"teacher_disagreement_score":0.03328589,"about_ca_system_score_codex":0.0031823975,"about_ca_system_score_gemma":0.001846053,"threshold_uncertainty_score":0.11757696},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012352905,0.00032999596,0.9906974,0.00016833308,0.00003509351,0.00004435212,0.00083077524,0.006384766,0.00027417438],"genre_scores_gemma":[0.037991256,0.00048054877,0.95139474,0.0002615139,0.00010688027,0.00075023266,0.0038222335,0.003719261,0.0014734123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99454474,0.0038217271,0.00026248777,0.000563407,0.00065711874,0.00015042156],"domain_scores_gemma":[0.9835633,0.012466375,0.0010974873,0.0017776649,0.000907077,0.00018816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011417478,0.0020876853,0.0021197663,0.00249029,0.0005147647,0.0018640236,0.0024748163,0.0018201354,0.011949404],"category_scores_gemma":[0.04717419,0.001345961,0.0034030364,0.0022244407,0.00090803485,0.0015998282,0.0025814285,0.0034076306,0.0068838103],"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":[0.00051863265,0.00014619215,0.007965251,0.0016338594,0.0014320079,0.0006795193,0.00045677103,0.5000411,0.004227091,0.10087644,0.07359408,0.30842906],"study_design_scores_gemma":[0.00012484565,0.000052173513,0.0010344157,0.00010552323,0.00009332495,0.00024303778,0.000029064393,0.91656065,0.0016236487,0.058613427,0.0214574,0.00006245072],"about_ca_topic_score_codex":0.007152129,"about_ca_topic_score_gemma":0.008692376,"teacher_disagreement_score":0.011949404,"about_ca_system_score_codex":0.00064358866,"about_ca_system_score_gemma":0.0022944675,"threshold_uncertainty_score":0.060382128},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021824384,0.0025675418,0.0004786335,0.005563515,0.99064493,0.0000485972,0.00014295163,0.000089447974,0.00044261044],"genre_scores_gemma":[0.0005605885,0.0050819195,0.0010835463,0.010317617,0.97584593,0.00021624166,0.0001645309,0.00012903122,0.006600507],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98478645,0.0039733336,0.0031557325,0.0017203771,0.0058128,0.0005513225],"domain_scores_gemma":[0.8495863,0.086545676,0.0076120365,0.0038873935,0.046178374,0.00619025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025328891,0.006058188,0.007888233,0.0069229803,0.0040324396,0.008460451,0.0046132933,0.011933264,0.027720766],"category_scores_gemma":[0.11718929,0.0026307344,0.0046017133,0.0034327284,0.0033421286,0.004147632,0.0011059628,0.019964915,0.022760695],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012074539,0.00001855415,0.000022873788,0.0006802916,0.00004770113,0.00005493729,0.000009095814,0.00005854428,0.00007686244,0.0003280338,0.99153346,0.007048923],"study_design_scores_gemma":[0.00066101627,0.00020939998,0.00091155025,0.001887754,0.00038825342,0.00054593245,0.00007126276,0.0010041004,0.0004948307,0.004587024,0.9891545,0.00008447334],"about_ca_topic_score_codex":0.0011782949,"about_ca_topic_score_gemma":0.0023890052,"teacher_disagreement_score":0.027720766,"about_ca_system_score_codex":0.0024063853,"about_ca_system_score_gemma":0.005247454,"threshold_uncertainty_score":0.13395357},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0386706,0.0013754312,0.9451764,0.0018292366,0.0002960835,0.00023476878,0.0005108037,0.00027267283,0.011634024],"genre_scores_gemma":[0.7983986,0.0007177094,0.1954388,0.0012085744,0.00054067984,0.0011742197,0.0005548946,0.00019394525,0.0017725285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93025064,0.054154463,0.0031246918,0.0045235553,0.006738439,0.001208264],"domain_scores_gemma":[0.6209229,0.32977048,0.015019783,0.023580084,0.008830291,0.0018764512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06405109,0.001144529,0.0024792547,0.0033758713,0.0009293593,0.0038567209,0.0029855343,0.0026233678,0.006267045],"category_scores_gemma":[0.31896618,0.00044968483,0.0017521916,0.0031442195,0.01223905,0.0088381525,0.0051036836,0.0052116737,0.0009815141],"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":[0.0006269207,0.00012209511,0.010586231,0.0005694726,0.0004888888,0.00038722897,0.0005927646,0.016330356,0.0014993162,0.8592465,0.0022762236,0.107274055],"study_design_scores_gemma":[0.00015467324,0.00065641693,0.0056319614,0.00021821349,0.00008028047,0.0006127894,0.00037332816,0.03345803,0.0019078761,0.95114124,0.0056871707,0.000078017736],"about_ca_topic_score_codex":0.0002812331,"about_ca_topic_score_gemma":0.00012038739,"teacher_disagreement_score":0.06405109,"about_ca_system_score_codex":0.0010317002,"about_ca_system_score_gemma":0.002026577,"threshold_uncertainty_score":0.33873862},"labels":[],"label_agreement":null}]}