{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":60,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":60,"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":"42798c2100f6","filters":{"venue":"The American Statistician"}},"results":[{"id":"W2140541004","doi":"10.1198/tas.2009.0033","title":"The History of the Cluster Heat Map","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":925,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Engineers Without Borders Canada","funders":"","keywords":"Row; Row and column spaces; Column (typography); Cluster (spacecraft); Computer science; TRACE (psycholinguistics); Matrix (chemical analysis); Tile; Hierarchical clustering; Computer graphics (images); Combinatorics; Data mining; Mathematics; Cluster analysis; Geometry; Artificial intelligence; Geography; Database; Archaeology; Materials science; Connection (principal bundle)","retraction":null,"screen_n_in":null,"score":{"opus":0.005116835551283146,"gpt":0.2190572762122446,"spread":0.2139404406609614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001916049,0.00008852927,0.0001017407,0.000006150309,0.0001227751,0.00001048184,0.0003908602,0.00002063221,0.000005420447],"category_scores_gemma":[0.00002722799,0.0000417112,0.00006149198,0.00004590178,0.0005840715,0.000001040202,0.00007252309,0.00008991764,0.000006781129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003127123,"about_ca_system_score_gemma":0.00008130173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008356035,"about_ca_topic_score_gemma":0.00008709664,"domain_scores_codex":[0.9993699,0.00007576281,0.00018229,0.00008758531,0.0001004513,0.0001840743],"domain_scores_gemma":[0.9992398,0.00004806358,0.000149524,0.0005006797,0.00003321939,0.00002872316],"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":[0.0002055977,0.00004148287,0.0002000502,0.00000946761,0.00009427833,6.823669e-7,0.0008129307,0.000353237,0.01576976,0.006350104,0.774787,0.2013754],"study_design_scores_gemma":[0.0002795778,0.0004694891,0.01604708,0.00001288006,0.00004855726,0.000009678674,0.0005410399,0.002109141,0.0007878497,0.00337341,0.9761358,0.0001854517],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6000227,0.02353098,0.1693709,0.07629038,0.009798353,0.003540531,0.0005658375,0.00009010654,0.1167902],"genre_scores_gemma":[0.987464,0.0001355268,0.0005971574,0.007498018,0.0001891969,0.000005009894,0.0000101473,0.000009503649,0.004091408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3874413,"threshold_uncertainty_score":0.2152036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978954330","doi":"10.1198/0003130043277","title":"Bootstrap Methods for Developing Predictive Models","year":2004,"lang":"en","type":"article","venue":"The American Statistician","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":620,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Resampling; Feature selection; Model selection; Computer science; Statistics; Predictive modelling; Selection (genetic algorithm); Bootstrap aggregating; Variables; Machine learning; Econometrics; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03567676071956769,"gpt":0.3619012094975819,"spread":0.3262244487780143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003553103,0.0001005357,0.0001815439,0.00002000263,0.0002474012,0.0000114421,0.0002238543,0.00001691408,0.0000697531],"category_scores_gemma":[0.0000680084,0.000071624,0.00004860015,0.0002776659,0.000711503,0.00007993823,0.00005986656,0.0000768824,0.00006205683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201646,"about_ca_system_score_gemma":0.00002497679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001382654,"about_ca_topic_score_gemma":0.0002855738,"domain_scores_codex":[0.9991741,0.0001124416,0.0001448554,0.0002119835,0.00009485089,0.0002618085],"domain_scores_gemma":[0.9993488,0.000294053,0.0001205277,0.000182587,0.000007601126,0.00004644114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003372935,0.0001069763,0.001961472,0.000009118893,0.0003765118,0.00001325365,0.006941964,0.4291057,0.002251995,0.08609217,0.002073311,0.4707302],"study_design_scores_gemma":[0.0004403414,0.0003614759,0.0214465,0.000007424278,0.0002247071,0.000009034681,0.0008415794,0.1293499,0.001227286,0.8417782,0.003972767,0.0003407157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0213008,0.00001497221,0.9730555,0.00115404,0.00003043284,0.0001637885,0.00002848215,0.00003192077,0.004220013],"genre_scores_gemma":[0.5878313,0.000009874397,0.410531,0.001470619,0.00002203521,0.00004431793,0.000005883106,0.000008767274,0.00007624539],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7556861,"threshold_uncertainty_score":0.2920742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030031047","doi":"10.1198/tast.2009.0001","title":"Splitting a Predictor at the Upper Quarter or Third and the Lower Quarter or Third","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Mathematics; Statistics; Voting; Linear regression; Econometrics; Simple (philosophy); Regression analysis; Simple linear regression; Regression; Geography; Political science; Philosophy; Politics","retraction":null,"screen_n_in":null,"score":{"opus":0.05089347011071178,"gpt":0.3687126660059382,"spread":0.3178191958952264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003427054,0.0003070034,0.000622344,0.00009290566,0.0009348925,0.0007997556,0.00134712,0.00004637711,0.0007477711],"category_scores_gemma":[0.002116003,0.0001020226,0.0001555922,0.0006039458,0.001823312,0.0001847618,0.0002180372,0.0003460881,0.00070803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006375643,"about_ca_system_score_gemma":0.0001050398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002925417,"about_ca_topic_score_gemma":0.0006352388,"domain_scores_codex":[0.9963413,0.0006680455,0.0009057528,0.0006270954,0.0009257186,0.0005320397],"domain_scores_gemma":[0.9882063,0.009394536,0.0007418272,0.001365871,0.0001492703,0.0001422406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003859212,0.0001308743,0.001492065,0.000001525823,0.00004864558,0.0002633535,0.009308543,0.00002803225,0.00002737224,0.00252347,0.24566,0.7366569],"study_design_scores_gemma":[0.006421682,0.007567975,0.32437,0.0002201797,0.000750447,0.002412589,0.0972733,0.02244152,0.00004258252,0.3262648,0.2101112,0.002123797],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9698534,0.00007690358,0.003931178,0.02064379,0.0005079752,0.000520065,0.0001838984,0.00006420234,0.004218561],"genre_scores_gemma":[0.9825507,0.00002472312,0.001432871,0.01126059,0.0002780979,0.00002545925,0.000002594386,0.00002069435,0.004404237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7345331,"threshold_uncertainty_score":0.910053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056003895","doi":"10.1198/0003130032431","title":"Detecting Dependence With Kendall Plots","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Plot (graphics); Copula (linguistics); Mathematics; Bivariate analysis; Curvature; Statistics; Scatter plot; Marginal distribution; Multivariate normal distribution; Multivariate statistics; Econometrics; Random variable; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.08951286293598788,"gpt":0.4099378926318419,"spread":0.320425029695854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004871966,0.0001907778,0.0003278859,0.00003308945,0.0002473139,0.00003220314,0.0001958946,0.00001456958,0.00005372107],"category_scores_gemma":[0.002437901,0.0001169758,0.00002794741,0.0002725963,0.0004403622,0.00005200639,0.00002667102,0.0002317819,0.0000185638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000040432,"about_ca_system_score_gemma":0.0000565092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001102463,"about_ca_topic_score_gemma":0.0001794053,"domain_scores_codex":[0.9983974,0.0003581275,0.0002391986,0.0002808796,0.0002971187,0.0004273328],"domain_scores_gemma":[0.9957008,0.0034333,0.0002710911,0.0003951038,0.00008040466,0.000119276],"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":[0.00007530247,0.00004815979,0.0001651284,0.00002329435,0.00004660994,0.00006129463,0.0006416054,0.00007063019,0.0003209639,0.8572058,0.0001654102,0.1411758],"study_design_scores_gemma":[0.0003087194,0.0004557655,0.0008269056,0.00004132063,0.0001017214,0.00008722275,0.002019661,0.001160811,0.0007868556,0.9924668,0.001381967,0.0003622698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02784179,0.00001773841,0.9663572,0.00006992277,0.0000411274,0.0002033889,0.00004253743,0.00008784779,0.005338449],"genre_scores_gemma":[0.4445409,0.000005030131,0.554997,0.0002414192,0.00001863396,0.00002070012,4.459268e-7,0.00003053005,0.00014536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4166991,"threshold_uncertainty_score":0.4770135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2033411871","doi":"10.1198/0003130031450","title":"Type I Error Inflation in the Presence of a Ceiling Effect","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Statistics; Ceiling (cloud); Econometrics; Statistical significance; Variables; Ceiling effect; Type I and type II errors; Mathematics; Standard error; Alcohol consumption; Variable (mathematics); Linear regression; Psychology; Medicine; Engineering; Biology; Alcohol","retraction":null,"screen_n_in":null,"score":{"opus":0.09602044591037069,"gpt":0.4371410127819303,"spread":0.3411205668715597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008896797,0.00009536771,0.0002132249,0.00004449302,0.00004506059,0.00000972187,0.0002235637,0.00001328733,0.00001592903],"category_scores_gemma":[0.003801747,0.00005403913,0.00001932902,0.000470798,0.0002885575,0.00004634567,0.0000178933,0.0001502585,0.000005147072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002511707,"about_ca_system_score_gemma":0.0000318152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001871691,"about_ca_topic_score_gemma":0.0001171337,"domain_scores_codex":[0.9987663,0.0005485257,0.0002312229,0.0001018742,0.0001894724,0.0001625868],"domain_scores_gemma":[0.9955008,0.00381803,0.0002707084,0.000344291,0.00005133187,0.0000148133],"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":[0.000147515,0.0001115732,0.01041875,0.000113708,0.00003161253,0.00001770157,0.008092303,0.0002201515,0.00779716,0.9355419,0.00105342,0.03645422],"study_design_scores_gemma":[0.0002724657,0.001174032,0.02410483,0.0001461339,0.00007346521,0.00001504421,0.003525422,0.001570609,0.01125593,0.9570352,0.000541589,0.000285317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8451185,0.00002736659,0.1494586,0.0001083464,0.00003708688,0.0005994744,0.00001170277,0.00006431257,0.00457461],"genre_scores_gemma":[0.9612555,0.000007696263,0.03856019,0.000102795,0.00001047485,0.00003029445,0.000001294119,0.00001193657,0.00001982586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.116137,"threshold_uncertainty_score":0.4551322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085360857","doi":"10.1198/tas.2011.11077","title":"An Overview of Current Software Procedures for Fitting Linear Mixed Models","year":2011,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Aging","funders":"National Institute on Aging","keywords":"Current (fluid); Software; Computer science; Statistics; Econometrics; Data science; Mathematics; Engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.3300457036600927,"gpt":0.4672241114054354,"spread":0.1371784077453427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005040065,0.0001830333,0.0004795519,0.0000453025,0.0001168758,0.00001362125,0.0003690998,0.0000197766,0.00004938161],"category_scores_gemma":[0.002746745,0.0001251407,0.00007024264,0.0001996545,0.0003915876,0.00006683644,0.00004398364,0.0001200534,0.000002853226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001639424,"about_ca_system_score_gemma":0.0001044334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001634161,"about_ca_topic_score_gemma":0.00005196844,"domain_scores_codex":[0.998547,0.0002273472,0.0004585689,0.0002452597,0.0002078968,0.0003139334],"domain_scores_gemma":[0.9963182,0.002435483,0.0005187125,0.0004166682,0.0002089342,0.0001020641],"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":[0.00007025249,0.0001433838,0.0001302352,0.0004005578,0.00002569666,9.692537e-7,0.001369237,0.000002029978,0.00003978672,0.6539303,0.0004041023,0.3434834],"study_design_scores_gemma":[0.0001521825,0.0004555122,0.002101716,0.0001674816,0.0001211653,0.000002159537,0.000576115,0.01247409,0.0003332759,0.9833855,0.00004528833,0.0001855123],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005948578,0.0001694461,0.9924949,0.00001743584,0.00008418477,0.000427946,0.0006573513,0.00006201707,0.0001380825],"genre_scores_gemma":[0.128801,0.00005744712,0.8708528,0.00009425575,0.00006772394,0.00007858867,0.000008629699,0.00003447166,0.000005068948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3432979,"threshold_uncertainty_score":0.5103088,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2922738421","doi":"10.1080/00031305.2018.1564697","title":"A Proposed Hybrid Effect Size Plus <i>p</i> -Value Criterion: Empirical Evidence Supporting its Use","year":2019,"lang":"en","type":"article","venue":"The American Statistician","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"","keywords":"Value (mathematics); Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.614450181809646,"gpt":0.5502659135980562,"spread":0.06418426821158973,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06153953,0.0004597173,0.004017862,0.0001440546,0.0002610645,0.001677578,0.002399755,0.00002621855,0.006475443],"category_scores_gemma":[0.1589336,0.0001957762,0.0009830205,0.001561334,0.0003278854,0.0004831362,0.0003019617,0.0003071622,0.01353331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009581132,"about_ca_system_score_gemma":0.0002244523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002310854,"about_ca_topic_score_gemma":0.00001813701,"domain_scores_codex":[0.9688624,0.01858743,0.005545392,0.001258878,0.00512157,0.000624338],"domain_scores_gemma":[0.9324388,0.05575102,0.006574212,0.004091651,0.0008670423,0.0002772954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0008330949,0.0001925208,0.2716956,0.0006092319,0.001099044,0.0005389761,0.005617876,0.001281552,0.008381963,0.004737464,0.4438483,0.2611645],"study_design_scores_gemma":[0.001763605,0.004475972,0.5084012,0.001064876,0.002785617,0.0005312678,0.004204973,0.2758874,0.001553356,0.00599697,0.1905814,0.002753461],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9719843,0.0001979089,0.02203308,0.002280387,0.0003534922,0.001956471,0.0000944587,0.00002428581,0.001075566],"genre_scores_gemma":[0.9820046,0.000013855,0.007077758,0.004121311,0.0001189946,0.00004299417,0.000004733851,0.00003081111,0.006584875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2746058,"threshold_uncertainty_score":0.9993588,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148939588","doi":"10.1198/tast.2009.0012","title":"Where's Waldo? Visualizing Collinearity Diagnostics","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Engineers Without Borders Canada","funders":"","keywords":"Collinearity; Biplot; Salient; Computer science; Rank (graph theory); Statistics; Software; Simple (philosophy); Matrix (chemical analysis); Data mining; Mathematics; Pattern recognition (psychology); Artificial intelligence; Combinatorics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.09706303419290631,"gpt":0.4670670415790503,"spread":0.370004007386144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005081649,0.0002384093,0.0004978385,0.00004323236,0.0002903626,0.0000576035,0.0003071495,0.00002815026,0.00005602451],"category_scores_gemma":[0.003567367,0.0001702217,0.00006298516,0.000340564,0.0004272332,0.00005827015,0.00004876681,0.0002776868,0.00003224202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000617323,"about_ca_system_score_gemma":0.0000466282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001287228,"about_ca_topic_score_gemma":0.0000790883,"domain_scores_codex":[0.9981226,0.0003204622,0.0004105984,0.0003022756,0.0003446245,0.0004994037],"domain_scores_gemma":[0.9933429,0.005575606,0.0003214419,0.0004737459,0.0001182974,0.0001679477],"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":[0.00005303482,0.0001262689,0.0000537607,0.00001894676,0.00002324304,0.00004206681,0.0003931054,0.00002125672,0.0001634394,0.7685071,0.008715265,0.2218825],"study_design_scores_gemma":[0.0002340948,0.0004793106,0.003227504,0.0000490448,0.0001037806,0.00001113658,0.0004669554,0.005068413,0.0001115189,0.9836532,0.006279771,0.0003152519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007438352,0.0001269931,0.9879232,0.001309027,0.00009277419,0.000298126,0.0002108519,0.000139625,0.00246107],"genre_scores_gemma":[0.1892274,0.0003213598,0.8076728,0.002255859,0.0001929068,0.00001894375,0.00000691523,0.00003798621,0.0002658602],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2215672,"threshold_uncertainty_score":0.6941439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158803120","doi":"10.1198/000313008x298439","title":"Survival Analysis","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Petro-Canada","funders":"","keywords":"Observational study; Econometrics; Mistake; Proportional hazards model; Estimator; Survival analysis; Psychology; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1038534569474199,"gpt":0.377329843071578,"spread":0.2734763861241581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001295088,0.00008383369,0.0003269915,0.00007362119,0.0001558511,0.000006980139,0.0001048501,0.000007988484,0.0001624995],"category_scores_gemma":[0.00009867788,0.00005510027,0.00009459106,0.001076865,0.0004570591,0.00002183174,0.00002205423,0.0001042572,0.0000858922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004238836,"about_ca_system_score_gemma":0.0000728468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004665972,"about_ca_topic_score_gemma":0.0003416292,"domain_scores_codex":[0.9991205,0.00005533156,0.0001428028,0.0001448284,0.0003219657,0.0002145714],"domain_scores_gemma":[0.9993124,0.0001290229,0.0001024719,0.0002885885,0.00006806918,0.00009941902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005990393,0.00007002598,0.9186898,0.000008207255,0.001613523,0.0008793333,0.001436866,0.0002274684,0.0003577401,0.004007764,0.01724891,0.05486127],"study_design_scores_gemma":[0.0001495667,0.0002062589,0.9942286,0.000004500416,0.0006585315,0.00005800593,0.0008385344,0.0006198271,0.00002938237,0.0001031379,0.00302254,0.00008110273],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.946492,0.0000894261,0.03603484,0.001211302,0.00005314974,0.0001006973,0.00004320974,0.00005707131,0.01591835],"genre_scores_gemma":[0.9928552,0.00005495628,0.003813341,0.002583842,0.0001154561,0.000005355893,0.00001678884,0.000008071053,0.0005470035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07553875,"threshold_uncertainty_score":0.7053586,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2924029102","doi":"10.1080/00031305.2018.1556735","title":"The <i>p</i> -value Function and Statistical Inference","year":2019,"lang":"en","type":"article","venue":"The American Statistician","topic":"Data Analysis with R","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Inference; Function (biology); Statistical inference; Scalar (mathematics); Value (mathematics); Mathematics; Power function; Statistics; Computer science; Artificial intelligence; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.006202599462732283,"gpt":0.2597219331783565,"spread":0.2535193337156242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004483401,0.0001201287,0.000179956,0.00003195403,0.0002808324,0.0003333157,0.0008141983,0.000009298768,0.00001626056],"category_scores_gemma":[0.0002184321,0.00006569122,0.00001805806,0.0004183025,0.0005062866,0.0001753975,0.0002905571,0.0001515528,0.0003310122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002117112,"about_ca_system_score_gemma":0.00006314892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000606121,"about_ca_topic_score_gemma":0.0001117143,"domain_scores_codex":[0.9986452,0.0002417983,0.0001910149,0.0003043102,0.0003261235,0.0002915869],"domain_scores_gemma":[0.996893,0.001965355,0.0001801141,0.0008316489,0.0000503652,0.00007948455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001695096,0.000009349311,0.002885681,0.000002489385,0.00003135307,0.000002449177,0.0001050351,0.0000332045,0.00008153482,0.7695325,0.002784161,0.2245153],"study_design_scores_gemma":[0.0003700695,0.0007513656,0.5829065,0.00001567056,0.0001094374,0.00001736441,0.0006482329,0.2287396,0.0000252814,0.1466296,0.03933896,0.000447874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01348197,0.0000517321,0.9830961,0.001549292,0.0001705531,0.0001418223,0.00005038737,0.00005839025,0.001399801],"genre_scores_gemma":[0.9767864,0.00004884646,0.02072718,0.002118343,0.00003658722,0.00001219294,0.000009563434,0.000008884737,0.0002519869],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9633045,"threshold_uncertainty_score":0.4254602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891886352","doi":"10.1080/00031305.2020.1717621","title":"Reconnecting <i>p</i> -Value and Posterior Probability Under One- and Two-Sided Tests","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistics; Mathematics; Posterior probability; Value (mathematics); p-value; Statistical hypothesis testing; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.525964131273974,"gpt":0.5256489015127478,"spread":0.0003152297612262212,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018306,0.000237275,0.0008128271,0.00002139466,0.0001887769,0.00009310053,0.0002084056,0.00003458124,0.0000559943],"category_scores_gemma":[0.09677657,0.0001771074,0.00004361076,0.0002694933,0.001187773,0.00004870069,0.0002362666,0.0003421158,0.00001254777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003121886,"about_ca_system_score_gemma":0.00005130587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000219514,"about_ca_topic_score_gemma":0.0000608507,"domain_scores_codex":[0.9966971,0.001431002,0.0007132387,0.0005341312,0.0002635874,0.0003609284],"domain_scores_gemma":[0.9282981,0.07047784,0.0004927663,0.0003708292,0.00007747733,0.0002830328],"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":[0.0009052863,0.0002053301,0.004813096,0.0004609226,0.0003044359,0.0000362214,0.003142217,0.00001092464,0.005712017,0.5524933,0.0009270115,0.4309892],"study_design_scores_gemma":[0.00066201,0.0005396953,0.02144363,0.00007034932,0.0001912291,0.00001668379,0.0007379218,0.0009709361,0.0002406994,0.9748377,0.00002699571,0.0002621408],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7734604,0.00004239079,0.2118101,0.01209574,0.0001220934,0.001020791,0.0002831542,0.0001787287,0.0009866225],"genre_scores_gemma":[0.4064288,0.00001172268,0.588656,0.00468286,0.0001566844,0.00002165235,7.752411e-7,0.00003373561,0.000007794532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4307271,"threshold_uncertainty_score":0.9108317,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386562232","doi":"10.1080/00031305.2023.2257237","title":"Statistical Challenges in Online Controlled Experiments: A Review of A/B Testing Methodology","year":2023,"lang":"en","type":"review","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"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":"","keywords":"Data science; The Internet; Computer science; Scale (ratio); Big data; World Wide Web; Marketing; Business; Data mining; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.9449757609267309,"gpt":0.7096567412494859,"spread":0.235319019677245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.01621939,0.0008837228,0.01484955,0.0003561169,0.00006813382,0.00001798054,0.001253209,0.0002053413,0.0002150135],"category_scores_gemma":[0.5453734,0.0005533636,0.0005939066,0.00163007,0.001626952,0.00002381242,0.0004297123,0.001243969,0.00007921427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001856553,"about_ca_system_score_gemma":0.0005422517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002239077,"about_ca_topic_score_gemma":0.00006504169,"domain_scores_codex":[0.9696804,0.0218228,0.00579107,0.0009955093,0.0008417498,0.00086841],"domain_scores_gemma":[0.5802326,0.4143905,0.00394371,0.001065724,0.0002143029,0.0001531469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009556975,0.0002442285,4.792701e-7,0.0940394,0.0005066429,0.00009889769,0.00005465731,6.520546e-8,2.083753e-7,0.07922193,0.0009111266,0.8248268],"study_design_scores_gemma":[0.002151677,0.001300287,0.00003586386,0.2674146,0.006674326,0.00005607423,0.0006784787,0.00006328825,2.979798e-7,0.6704901,0.05002152,0.00111348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.186626e-7,0.9472945,0.04454283,0.0002187574,0.0003551216,0.00362268,0.003222942,0.0001125046,0.0006301327],"genre_scores_gemma":[9.608961e-8,0.5375277,0.4614201,0.0001664506,0.0001685159,0.0005331427,0.00002594204,0.0001265825,0.00003149514],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8237133,"threshold_uncertainty_score":0.999776,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2159445569","doi":"10.1198/0003130032369","title":"Raindrop Plots","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Forest ecology and management","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Izaak Walton Killam Health Centre","funders":"","keywords":"Mathematics; Plot (graphics); Statistics; Cutoff; Range (aeronautics); Coverage probability; Normality; Confidence interval; Dimension (graph theory); Likelihood function; Maximum likelihood; Combinatorics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.006542340120135166,"gpt":0.2315617677636299,"spread":0.2250194276434947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000182477,0.00006529965,0.00008183591,0.00000987076,0.0001503006,0.000008747064,0.0001550939,0.0000063002,0.002611182],"category_scores_gemma":[0.00007458482,0.00004515256,0.00001493925,0.0001682067,0.0006956737,0.00002595986,0.00005265533,0.00005940119,0.002509023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000438908,"about_ca_system_score_gemma":0.000004558218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005631471,"about_ca_topic_score_gemma":0.0004977516,"domain_scores_codex":[0.9993718,0.0001058465,0.00007777179,0.0001286981,0.0001058222,0.0002101234],"domain_scores_gemma":[0.9996072,0.00008668446,0.00006727582,0.0001951773,0.00000161594,0.00004202597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00004103022,0.0001529381,0.04002414,0.000003731308,0.00005925889,0.0000888123,0.001578718,0.001328311,0.0002366387,0.7006115,0.1978931,0.05798177],"study_design_scores_gemma":[0.0001712172,0.0002053681,0.7163805,0.000001497103,0.00002855496,0.000009652042,0.0005520287,0.0002253057,0.00007333146,0.062067,0.2201037,0.0001818254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5227514,0.00001435027,0.07281795,0.001505998,0.0002640705,0.0003915025,0.00001520788,0.00009415776,0.4021454],"genre_scores_gemma":[0.9911212,0.000006406696,0.003542986,0.002966201,0.000008634387,0.00001605867,0.000001195638,0.00000780456,0.002329528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6763564,"threshold_uncertainty_score":0.9983006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1763804216","doi":"10.1198/0003130031072","title":"Statistics and Ethics","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"College of the North Atlantic","funders":"","keywords":"Advice (programming); Statistics; Work (physics); Sociology; Psychology; Computer science; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2657415008978894,"gpt":0.4875637517411046,"spread":0.2218222508432152,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001386828,0.0001511592,0.0002674983,0.00004867565,0.0002773779,0.00005463217,0.000139165,0.00002750074,0.0001485104],"category_scores_gemma":[0.02085653,0.0001076535,0.00001663347,0.0001996416,0.000914857,0.00001970088,0.00002916164,0.0003410976,0.00003443156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002631684,"about_ca_system_score_gemma":0.0001503274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009801687,"about_ca_topic_score_gemma":0.00008539726,"domain_scores_codex":[0.998091,0.000957773,0.0002497918,0.0001938458,0.0002346582,0.0002729739],"domain_scores_gemma":[0.9836054,0.01559612,0.0002543993,0.0003239759,0.0001244202,0.00009571738],"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":[0.000009029926,0.0000236399,0.0003060278,0.00002381452,0.00002279885,0.000004547775,0.001821679,4.744481e-7,0.00002786933,0.9423062,0.03818143,0.0172725],"study_design_scores_gemma":[0.0001377556,0.00009567642,0.006336242,0.000008752966,0.00007493922,0.00003076301,0.005035752,0.00005941727,0.00009848327,0.9552973,0.03263703,0.0001879219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009063623,0.0000688252,0.9832043,0.0009022836,0.0003915037,0.00019648,0.0004942443,0.00008227874,0.00559648],"genre_scores_gemma":[0.0758514,0.0001815541,0.9204137,0.001978939,0.00004503115,0.00002428781,0.000009156599,0.00003398519,0.001461961],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06678778,"threshold_uncertainty_score":0.9873912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025559840","doi":"10.1198/tast.2010.09147","title":"Strategies for Pulling the Goalie in Hockey","year":2010,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Ice hockey; League; Markov chain; Computer science; Bayesian probability; Estimation; Econometrics; Markov chain Monte Carlo; Operations research; Simulation; Engineering; Machine learning; Artificial intelligence; Mathematics; Economics; Physical medicine and rehabilitation; Management","retraction":null,"screen_n_in":null,"score":{"opus":0.02623175888914076,"gpt":0.2618707400671466,"spread":0.2356389811780059,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005179642,0.00008949739,0.0002145127,0.00006049336,0.000154825,0.0001110722,0.0002860985,0.0000150159,0.0001199801],"category_scores_gemma":[0.00005132392,0.0000607103,0.0000423146,0.0002087675,0.0002575447,0.00006437356,0.00002042523,0.0001869735,0.00006063538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001453995,"about_ca_system_score_gemma":0.00002906016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003569605,"about_ca_topic_score_gemma":0.003346691,"domain_scores_codex":[0.9992624,0.000005304097,0.0002999209,0.0001627694,0.00002583082,0.0002438004],"domain_scores_gemma":[0.9991934,0.0001776395,0.0002924445,0.0002909714,0.0000182335,0.00002728007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001661986,0.00001752,0.02173722,0.00000568544,0.000015544,0.000001335566,0.0006842035,0.0006095543,0.00001762184,0.9686002,0.001503778,0.006790762],"study_design_scores_gemma":[0.0003352081,0.000140002,0.3335536,0.000008004265,0.00001370788,0.000003707357,0.003931643,0.1138844,0.00001411477,0.3222334,0.2255289,0.0003532401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9278842,0.0002080692,0.05245462,0.003351763,0.0005464533,0.0003746644,0.0004897583,0.00002247607,0.014668],"genre_scores_gemma":[0.9973381,0.0000749371,0.001254355,0.0008755664,0.0001655125,0.00003734836,0.000009529449,0.00001531176,0.0002293864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6463668,"threshold_uncertainty_score":0.5396198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803189886","doi":"10.1080/00031305.2018.1497537","title":"Visualizing Tests for Equality of Covariance Matrices","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate analysis of variance; Covariance; Variety (cybernetics); Analysis of covariance; Multivariate statistics; Statistics; Covariance matrix; Test (biology); Econometrics; Plot (graphics); Computer science; Mathematics; Statistical hypothesis testing; Estimation of covariance matrices","retraction":null,"screen_n_in":null,"score":{"opus":0.2336259352287667,"gpt":0.5405334951375262,"spread":0.3069075599087596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000832668,0.0001399029,0.0004293145,0.00003468395,0.0001690824,0.00001535773,0.0002478881,0.0000167485,0.00002786667],"category_scores_gemma":[0.003422256,0.00009795982,0.00005004675,0.0002613561,0.0009346213,0.00004312929,0.00005207528,0.00007063158,0.000006136007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002439345,"about_ca_system_score_gemma":0.00004244187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001827604,"about_ca_topic_score_gemma":0.00006251048,"domain_scores_codex":[0.9986393,0.0002146424,0.0004153119,0.0002213156,0.0002019265,0.0003074431],"domain_scores_gemma":[0.9919134,0.006840448,0.0005719995,0.0003640452,0.0002439473,0.00006612821],"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":[0.0001346789,0.00005424103,0.00003475171,0.00009033972,0.00003425685,8.126848e-7,0.0005772457,0.000003045413,0.001328247,0.9052438,0.001263299,0.09123529],"study_design_scores_gemma":[0.0002219348,0.0005646497,0.0007981259,0.00004214012,0.00008713411,0.000002231195,0.0004853371,0.004135139,0.001137227,0.9904522,0.00190892,0.0001649482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008605765,0.00002550966,0.9892348,0.0001388627,0.00008547163,0.000338353,0.0005645773,0.00004308523,0.000963588],"genre_scores_gemma":[0.3015334,0.000007609819,0.6979372,0.0002604613,0.0001263767,0.00003107847,0.000002726336,0.00002239962,0.00007875479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2929276,"threshold_uncertainty_score":0.4097008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2752232660","doi":"10.1080/00031305.2017.1395365","title":"Modeling Offensive Player Movement in Professional Basketball","year":2017,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Offensive; Basketball; League; Computer science; Leverage (statistics); Movement (music); Ball (mathematics); Human–computer interaction; Artificial intelligence; Operations research; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04584094132041121,"gpt":0.2843950220958145,"spread":0.2385540807754032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003691758,0.0001063505,0.000287844,0.00007343422,0.0003056805,0.00008530808,0.0003592271,0.00001545496,0.0002319599],"category_scores_gemma":[0.00007621038,0.00008789454,0.00003776663,0.0000569175,0.000163146,0.00007509419,0.00009143246,0.0001449983,0.0001609598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005559913,"about_ca_system_score_gemma":0.00002329933,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01114148,"about_ca_topic_score_gemma":0.001044808,"domain_scores_codex":[0.999107,0.000007808982,0.0003534912,0.0002241557,0.00005007144,0.0002574438],"domain_scores_gemma":[0.9989736,0.00003278491,0.000438966,0.0004821569,0.00002586199,0.00004662149],"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":[0.0001229002,0.0001673298,0.3692911,0.00002308373,0.00009429795,0.00005085971,0.001922784,0.02889037,0.00001376396,0.5797459,0.005690162,0.01398744],"study_design_scores_gemma":[0.0002219097,0.0000417462,0.3992443,0.00001955224,0.00000362788,5.387406e-7,0.0002994437,0.5682976,0.000002969969,0.0276643,0.004035839,0.0001682149],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9717945,0.0001235097,0.009325729,0.002404973,0.0005879548,0.0001948422,0.0002534909,0.0000108795,0.01530407],"genre_scores_gemma":[0.9955748,0.0001104893,0.000484188,0.002070223,0.00009440031,0.00001673945,0.000007804804,0.00001488265,0.001626483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5520816,"threshold_uncertainty_score":0.9954434,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040022986","doi":"10.1080/00031305.2000.10474518","title":"Late-Game Reversals in Professional Basketball, Football, and Hockey","year":2000,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Okanagan University College; Okanagan College","funders":"","keywords":"Basketball; League; Football; Ice hockey; Poisson distribution; Period (music); Probabilistic logic; American football; Econometrics; Psychology; Applied psychology; Statistics; Mathematics; Geography; Physical medicine and rehabilitation","retraction":null,"screen_n_in":null,"score":{"opus":0.01589610530465191,"gpt":0.2376708641944213,"spread":0.2217747588897694,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003118113,0.0001214381,0.0003318049,0.00009072822,0.00008100046,0.00004296415,0.000176476,0.00002267534,0.001496954],"category_scores_gemma":[0.00002785483,0.0001017556,0.00002891532,0.0002772012,0.0002350749,0.00008923556,0.00003166456,0.0001577365,0.0002798617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003997454,"about_ca_system_score_gemma":0.00002055102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003122625,"about_ca_topic_score_gemma":0.0003491755,"domain_scores_codex":[0.9990316,0.0000171619,0.0003765856,0.0002534768,0.00004401636,0.0002771262],"domain_scores_gemma":[0.9993855,0.00008196602,0.0002240768,0.0002319552,0.00001081644,0.00006570853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002121287,0.0001736025,0.7278063,0.00003333051,0.00008600661,0.00005037287,0.002937725,0.0008630411,0.00001345405,0.1217914,0.01122969,0.134803],"study_design_scores_gemma":[0.0002999679,0.00009276803,0.8984141,0.00002081871,0.000005962417,0.00000343607,0.0002876093,0.01245023,0.000002214141,0.01785808,0.07034013,0.0002247278],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898606,0.0003594679,0.0001998586,0.001450934,0.0001208166,0.0001352144,0.0002138629,0.00001469343,0.007644534],"genre_scores_gemma":[0.9923623,0.0009702028,0.0003756397,0.001787803,0.00006563327,0.00001281887,0.00001280927,0.00001695445,0.004395867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1706078,"threshold_uncertainty_score":0.9994158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991138897","doi":"10.1198/tast.2009.0008","title":"Influence Measures for General Linear Models With Correlated Errors","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Generalized linear model; General linear model; Linear regression; Linear model; Mathematics; Hierarchical generalized linear model; Simple (philosophy); Proper linear model; Statistics; Log-linear model; Generalized linear mixed model; Standard error; Econometrics; Applied mathematics; Simple linear regression; Bayesian multivariate linear regression","retraction":null,"screen_n_in":null,"score":{"opus":0.07501124733594747,"gpt":0.3786968497289507,"spread":0.3036856023930032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000365848,0.0002079452,0.0003976718,0.0000420276,0.000186165,0.00003100085,0.0002817505,0.00002513454,0.00001227829],"category_scores_gemma":[0.001307181,0.0001253016,0.00003940564,0.0002865452,0.0004364423,0.00005521751,0.00001703329,0.0001779916,0.000007437755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000324391,"about_ca_system_score_gemma":0.00007430538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002507774,"about_ca_topic_score_gemma":0.0000357917,"domain_scores_codex":[0.998592,0.0001629213,0.0003083499,0.000253698,0.0002934597,0.0003895461],"domain_scores_gemma":[0.9972554,0.001750174,0.0002782274,0.00036428,0.000236212,0.0001156644],"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":[0.0003403199,0.00007235902,0.00006859549,0.00001338733,0.00005102042,0.000009463973,0.000608714,0.003532717,0.0003109287,0.8997861,0.001369789,0.09383662],"study_design_scores_gemma":[0.0003592694,0.001160144,0.006354511,0.00004108856,0.0001244221,0.0000108528,0.0001974498,0.135747,0.0001440277,0.8553542,0.0002315398,0.0002754286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1619841,0.00001243152,0.8360813,0.0003791374,0.00002338372,0.000369537,0.0001664182,0.0000789226,0.0009048505],"genre_scores_gemma":[0.422357,0.000006246213,0.5763606,0.00107058,0.00004416514,0.00002873286,0.00000427745,0.00001964421,0.0001087807],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2603729,"threshold_uncertainty_score":0.5109649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2094806835","doi":"10.1198/tast.2009.08042","title":"Teaching Variation Reduction Using a Virtual Manufacturing Environment","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Design Education and Practice","field":"Engineering","cited_by":15,"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":"","keywords":"Login; Process (computing); Variation (astronomy); Computer science; Software; Plan (archaeology); Reduction (mathematics); Software engineering; Manufacturing engineering; Engineering; Operating system; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01388276651898451,"gpt":0.2648116070288507,"spread":0.2509288405098662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002187235,0.00009807669,0.00009587894,0.00005053844,0.00016404,0.00004494515,0.00008564327,0.00001116999,0.00005947746],"category_scores_gemma":[0.00002294929,0.00008669691,0.00001691226,0.00005470245,0.0000396909,0.0001355976,0.000005631963,0.0001861821,0.00006189173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364312,"about_ca_system_score_gemma":0.00001111784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000267927,"about_ca_topic_score_gemma":0.000001156455,"domain_scores_codex":[0.999354,0.000113319,0.0001393624,0.0001038465,0.0001293161,0.0001601495],"domain_scores_gemma":[0.9995998,0.00009489963,0.00008845273,0.0001682314,0.000004544147,0.00004404006],"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":[0.00003189925,0.00005307042,0.000006385398,0.000005174713,0.00004598608,0.000003487242,0.005540913,0.09623127,0.04178489,0.005364291,0.001035471,0.8498971],"study_design_scores_gemma":[0.0009850154,0.001128742,0.2237646,0.00008799328,0.0006307621,0.0003991416,0.01860972,0.6261373,0.01330736,0.01694638,0.09583808,0.002164984],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3461048,0.00002043271,0.6496926,0.0005950641,0.0002902836,0.0001262922,0.000008112236,0.0001538772,0.003008564],"genre_scores_gemma":[0.9827299,0.00001832417,0.01660316,0.0002831193,0.0002206591,0.000003355482,0.000005576989,0.00001560594,0.0001202978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8477322,"threshold_uncertainty_score":0.3535397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402407033","doi":"10.1080/00031305.2024.2402898","title":"When Heavy Tails Disrupt Statistical Inference","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Statistical inference; Inference; Econometrics; Computer science; Statistics; Mathematics; Statistical physics; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03880810499610163,"gpt":0.2962289158894527,"spread":0.2574208108933511,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000500641,0.0001789199,0.0004150652,0.0001143763,0.000175769,0.0002271893,0.0002916104,0.00002791222,0.0004365759],"category_scores_gemma":[0.0004852312,0.0001540429,0.00006495925,0.0003218502,0.0004450837,0.0001349139,0.00007371856,0.0002867235,0.001530012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008895768,"about_ca_system_score_gemma":0.0000633957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004652467,"about_ca_topic_score_gemma":0.0002240944,"domain_scores_codex":[0.9984975,0.00004055915,0.0005321571,0.0004436159,0.0000703062,0.000415828],"domain_scores_gemma":[0.9986528,0.0006914859,0.000152613,0.0003756989,0.00002521734,0.0001021951],"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":[0.00002868204,0.00002569834,0.004642788,0.00002925107,0.00003235956,0.00002213779,0.001355833,0.00005557896,0.000004683047,0.9121287,0.005083185,0.0765911],"study_design_scores_gemma":[0.0001049711,0.0002036766,0.05216502,0.00004149649,0.00002167382,0.000004771562,0.000289668,0.152432,0.000006674395,0.7212689,0.07307912,0.0003820263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06688552,0.001437239,0.9202366,0.001850283,0.0004298973,0.0001835742,0.00209073,0.0001351275,0.006751055],"genre_scores_gemma":[0.9867421,0.0001444769,0.01171242,0.0006354717,0.0001848248,0.00002737129,0.00003576248,0.00003443752,0.0004831708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9198565,"threshold_uncertainty_score":0.9992474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3114650575","doi":"10.1080/00031305.2020.1865199","title":"Hurdle Blockmodels for Sparse Network Modeling","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":13,"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":"Computer science; Model selection; Variety (cybernetics); Selection (genetic algorithm); Random graph; Goodness of fit; Exponential random graph models; Graph; Data mining; Theoretical computer science; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04329076685591112,"gpt":0.3001625163344384,"spread":0.2568717494785273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001311728,0.0001506469,0.0003206909,0.00001472262,0.0002193852,0.00004838741,0.0003074013,0.000006558869,0.00009768749],"category_scores_gemma":[0.00001013278,0.0001203181,0.000115265,0.000323028,0.0001096706,0.00003121189,0.00008104471,0.0001142995,0.00001799352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001129095,"about_ca_system_score_gemma":0.0000299066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006106545,"about_ca_topic_score_gemma":0.00001742395,"domain_scores_codex":[0.9989897,0.00006087274,0.0002432161,0.0002396661,0.0001191443,0.0003473868],"domain_scores_gemma":[0.9991959,0.0002049627,0.0001804834,0.0002623269,0.00005693805,0.00009936135],"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":[0.0001395496,0.000053452,0.001831437,0.000008581578,0.0003558046,0.000001510981,0.0007944487,0.5400743,0.000136254,0.1901683,0.05605223,0.2103841],"study_design_scores_gemma":[0.00009487433,0.00008245201,0.00004323834,0.000005798832,0.0001052466,9.854015e-8,0.0002779806,0.9330237,0.00002145256,0.06258649,0.00360377,0.0001549105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01763121,0.00002537215,0.979324,0.001044773,0.0000196386,0.0002702508,0.0001045925,0.00009293598,0.001487262],"genre_scores_gemma":[0.9334259,0.00000254524,0.06401696,0.001293469,0.001077779,0.00007389074,0.00004600327,0.00003067299,0.00003280329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9157947,"threshold_uncertainty_score":0.4906428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965544836","doi":"10.1198/000313002753631321","title":"Thoughts on the Origins, Concepts, and Pedagogy of Statistics as a “Separate Discipline”","year":2002,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Discipline; Subject (documents); Field (mathematics); Statistics; Statistics education; Mathematics education; Sociology; Epistemology; Mathematics; Social science; Computer science; Library science; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.1809986423800614,"gpt":0.4818281639538936,"spread":0.3008295215738321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000563086,0.0002088876,0.0004085261,0.00005521243,0.000241848,0.00004295183,0.0003003805,0.00002184484,0.0003377629],"category_scores_gemma":[0.004239709,0.0001149021,0.00003168831,0.0002505447,0.001497559,0.00002180914,0.00006765951,0.0002053418,0.00009331112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003670792,"about_ca_system_score_gemma":0.00006328618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002180289,"about_ca_topic_score_gemma":0.00009925562,"domain_scores_codex":[0.998139,0.000652958,0.0003865373,0.0002304226,0.0003033954,0.0002877409],"domain_scores_gemma":[0.9845389,0.01421336,0.0005440027,0.0005039161,0.0001185236,0.00008127701],"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":[0.00004514517,0.00008139226,0.00009235724,0.00002544339,0.00005311984,0.00000638984,0.004880731,0.000003237051,0.00006039094,0.8852592,0.08501903,0.02447356],"study_design_scores_gemma":[0.0004868142,0.0009290472,0.006095855,0.00006173665,0.0002680095,0.00003722799,0.01813286,0.00228465,0.0006916897,0.9242876,0.04627848,0.0004460637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3094814,0.0004619895,0.6508405,0.01250972,0.001472699,0.001637484,0.005660179,0.0002099869,0.0177261],"genre_scores_gemma":[0.7420344,0.0007373735,0.2490046,0.002058367,0.0003637839,0.00008227293,0.00002283795,0.00006513578,0.005631147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4325531,"threshold_uncertainty_score":0.5517818,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399726225","doi":"10.1080/00031305.2024.2368794","title":"High-Dimensional Propensity Score and Its Machine Learning Extensions in Residual Confounding Control","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"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":"Propensity score matching; Confounding; Residual; Computer science; Proxy (statistics); Exploit; Causal inference; Parametric statistics; Machine learning; Econometrics; Artificial intelligence; Data mining; Statistics; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1205700477072864,"gpt":0.3918923405365465,"spread":0.2713222928292602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005871254,0.0001814529,0.0003951644,0.0001172794,0.000171867,0.00006204726,0.0001149357,0.00002364561,0.00004902867],"category_scores_gemma":[0.001282953,0.0001256859,0.0000201018,0.00027522,0.0003356132,0.0000996306,0.00009714024,0.0005050414,0.0000176601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000704745,"about_ca_system_score_gemma":0.00006422827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006763979,"about_ca_topic_score_gemma":0.0003969213,"domain_scores_codex":[0.9986395,0.0002689905,0.0002865076,0.0002808539,0.0002296313,0.0002945532],"domain_scores_gemma":[0.9973034,0.002248378,0.0001386288,0.0001700152,0.00007175752,0.00006787832],"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":[0.0001990141,0.00005673265,0.002035495,0.0001144343,0.00008403204,0.0005437787,0.0009814316,0.0002190097,0.01283797,0.9527827,0.001108532,0.02903689],"study_design_scores_gemma":[0.001046325,0.001176459,0.05082829,0.00128762,0.0003059626,0.0002937412,0.000760612,0.08463199,0.002227633,0.8556846,0.0006973444,0.001059393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9411444,0.0003652164,0.05604637,0.00107467,0.00008331317,0.0005521816,0.0001321133,0.0004031305,0.0001986293],"genre_scores_gemma":[0.984448,0.00004180781,0.01485133,0.000332033,0.00005444919,0.00003162512,0.00001079526,0.00003753449,0.0001924919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09709805,"threshold_uncertainty_score":0.5125324,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209485542","doi":"10.1080/00031305.2021.2000495","title":"Comparative Probability Metrics: Using Posterior Probabilities to Account for Practical Equivalence in A/B tests","year":2021,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":12,"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":"Mathematics; Statistics; Equivalence (formal languages); Posterior probability; Bayesian probability; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2844714646661516,"gpt":0.5027176178365009,"spread":0.2182461531703493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001186372,0.0002439,0.000767624,0.00009723903,0.0001515002,0.0001242303,0.0002495657,0.00003117548,0.00007166648],"category_scores_gemma":[0.02264453,0.0001829341,0.0000627429,0.001079166,0.0005891947,0.0001026401,0.0001715645,0.0002253553,0.00001027544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002655622,"about_ca_system_score_gemma":0.0005647173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003181767,"about_ca_topic_score_gemma":0.0006315158,"domain_scores_codex":[0.9972322,0.0007306961,0.0006154346,0.0005067688,0.0003673367,0.0005475927],"domain_scores_gemma":[0.9818524,0.01666597,0.0003039644,0.0005302334,0.0004994,0.0001479995],"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":[0.0004156463,0.0005682789,0.002488759,0.0004036205,0.00006777311,0.00005992771,0.004614784,0.00002049251,0.002788653,0.9409472,0.0006368591,0.04698803],"study_design_scores_gemma":[0.0002435843,0.0004625357,0.01607747,0.0001244516,0.00008837808,0.00003956751,0.003470222,0.004710563,0.0008051866,0.9735093,0.0001432154,0.0003255125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.205436,0.00001562577,0.79144,0.001179018,0.00008387363,0.001086911,0.0004647404,0.00003252271,0.0002613399],"genre_scores_gemma":[0.2337232,0.000001639912,0.7655104,0.0005017131,0.00005012004,0.0001693046,0.000003674608,0.00001923099,0.00002074825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04666252,"threshold_uncertainty_score":0.9855881,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2614013743","doi":"10.1080/00031305.2018.1459315","title":"Simple Measures of Individual Cluster-Membership Certainty for Hard Partitional Clustering","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simple (philosophy); Cluster (spacecraft); Cluster analysis; Mathematics; Certainty; Econometrics; Statistics; Computer science; Philosophy; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.07860951827381393,"gpt":0.3351475650468765,"spread":0.2565380467730626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009724729,0.0001344742,0.000263083,0.00005876959,0.0002061081,0.00007880863,0.0008280101,0.00001985135,0.00001879129],"category_scores_gemma":[0.0002071076,0.00009926502,0.00006830096,0.0002586696,0.0005560757,0.0001001354,0.0001840251,0.00008262629,0.000006762878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002216845,"about_ca_system_score_gemma":0.00008263801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001747403,"about_ca_topic_score_gemma":0.0001909876,"domain_scores_codex":[0.9985335,0.0002621711,0.0002699817,0.0002726952,0.0003251782,0.0003364314],"domain_scores_gemma":[0.9982967,0.0007203399,0.0002762167,0.0004424004,0.0001786902,0.00008566432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001547252,0.00005784723,0.0002423992,0.0000334035,0.0001197463,0.000002138961,0.003821492,0.00008853478,0.0006943055,0.2844943,0.01463144,0.6956598],"study_design_scores_gemma":[0.001245109,0.001998345,0.03773396,0.00006376797,0.0001518788,0.00003101851,0.0005653207,0.2224377,0.003629107,0.7172788,0.01411077,0.0007541919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004583224,0.00001473917,0.9932465,0.0007873701,0.0001559372,0.0002375694,0.0001861881,0.00004436856,0.0007441108],"genre_scores_gemma":[0.5352708,0.000001417002,0.4631307,0.001357683,0.0001656094,0.00002568708,0.000007043264,0.00000917378,0.00003188822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6949055,"threshold_uncertainty_score":0.404791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034554153","doi":"10.1198/000313001317098158","title":"The National Hockey League Entry Draft, 1969–1995","year":2001,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"League; Rank (graph theory); Championship; Statistics; Mathematics; Econometrics; Demographic economics; Operations research; Operations management; Advertising; Economics; Combinatorics; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.03020837967535613,"gpt":0.2569900151265436,"spread":0.2267816354511875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005348629,0.0001247231,0.0002304942,0.00006422918,0.0004819422,0.0001277921,0.0003622076,0.00001622429,0.0003618308],"category_scores_gemma":[0.0001175919,0.00008761189,0.00006494865,0.0003491897,0.0003895846,0.00006466509,0.00004421766,0.0001553977,0.0007848063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000781916,"about_ca_system_score_gemma":0.00003536933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001822526,"about_ca_topic_score_gemma":0.0003606913,"domain_scores_codex":[0.9989446,0.00001405404,0.0004005603,0.0002184176,0.00009386523,0.0003284393],"domain_scores_gemma":[0.9989514,0.0002235523,0.0004518238,0.0002595643,0.0000502306,0.00006339473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006785384,0.00006641387,0.09950565,0.00000468518,0.0001311294,0.00001310725,0.0005685096,0.0008143574,0.0000035776,0.7983314,0.07063151,0.02986182],"study_design_scores_gemma":[0.0001492453,0.00006243236,0.2209782,0.000004170292,0.000007510783,0.00001037283,0.0002571548,0.01718964,0.000002379765,0.02914449,0.7320065,0.0001878609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5264875,0.002950374,0.03183145,0.0192028,0.001467686,0.0005927299,0.001477288,0.0001316822,0.4158584],"genre_scores_gemma":[0.9887099,0.001555862,0.0002310055,0.002672964,0.0003640983,0.00001699594,0.00001806741,0.00001978901,0.006411331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7691869,"threshold_uncertainty_score":0.9999932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101508305","doi":"10.1198/000313008x269602","title":"Student's<i>z</i>,<i>t</i>, and<i>s</i>","year":2008,"lang":"he","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":10,"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":"Statistic; Documentation; Rework; Mathematics education; Mathematics; Work (physics); Calculus (dental); Statistics; Computer science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1477300252802811,"gpt":0.4293276293051706,"spread":0.2815976040248895,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0009316673,0.0004281486,0.0008111768,0.0001102158,0.0008339832,0.00009715475,0.0005421583,0.0000482074,0.0003521157],"category_scores_gemma":[0.002753067,0.0003158035,0.00008298441,0.0005194502,0.003479596,0.00005171492,0.0002443126,0.0004455088,0.0004790912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007936099,"about_ca_system_score_gemma":0.0002663832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005855783,"about_ca_topic_score_gemma":0.00007447587,"domain_scores_codex":[0.9965292,0.001111761,0.000653972,0.0004885315,0.0005519982,0.0006645781],"domain_scores_gemma":[0.9895038,0.008475929,0.0007652024,0.0008188302,0.0001847686,0.0002514475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002026274,0.0006045653,0.01151012,0.0001999224,0.000491786,0.0002387851,0.03970823,0.000004946412,0.0002870931,0.2535766,0.609801,0.08337429],"study_design_scores_gemma":[0.001945985,0.001651647,0.5455676,0.0001975991,0.001480579,0.001176659,0.06753068,0.0003667125,0.0004339894,0.1495878,0.2278724,0.002188286],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7160688,0.004045756,0.2265956,0.01095445,0.005210354,0.002336273,0.003611651,0.0005612127,0.0306159],"genre_scores_gemma":[0.6771259,0.009399987,0.2871499,0.009614871,0.0008640917,0.0001017751,0.00003980842,0.0001776286,0.0155261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5340575,"threshold_uncertainty_score":0.9999294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1609447734","doi":"10.1080/00031305.2015.1033985","title":"Advanced Placement Statistics: Expanding the Scope of Statistics Education","year":2015,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Statistics; Statistics education; Scope (computer science); Quarter (Canadian coin); Descriptive statistics; Summary statistics; Mathematics education; Computer science; Psychology; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1709054815060601,"gpt":0.4657031647904276,"spread":0.2947976832843675,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001455635,0.0002490332,0.0004642102,0.0001013013,0.0002191026,0.00005926259,0.0005137947,0.00002295759,0.0001188804],"category_scores_gemma":[0.009009567,0.0001564168,0.00003400553,0.0004069007,0.000967911,0.00005255744,0.0001060796,0.000211915,0.00005209199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000161774,"about_ca_system_score_gemma":0.0009270976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004172191,"about_ca_topic_score_gemma":0.0001456946,"domain_scores_codex":[0.9973729,0.0007461756,0.0006579412,0.0002612123,0.0005856818,0.0003760635],"domain_scores_gemma":[0.9903797,0.007155,0.001026442,0.0006994466,0.0005797549,0.0001596486],"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":[0.0001628422,0.0001810623,0.0001521865,0.00006835621,0.00007364569,0.000002159613,0.00391454,0.00007100596,0.0001766124,0.5014018,0.3040787,0.1897171],"study_design_scores_gemma":[0.0008562151,0.0008307693,0.004958822,0.0001213115,0.0003899822,0.00002349551,0.06464148,0.0004954318,0.001617406,0.9028283,0.02267407,0.00056274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00914921,0.000259152,0.9816647,0.0005253345,0.001330737,0.0007019465,0.002257369,0.00006658319,0.004045002],"genre_scores_gemma":[0.06846176,0.0002024984,0.9283324,0.0007918397,0.0001720819,0.0001572609,0.0001255838,0.00005749747,0.00169908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4014265,"threshold_uncertainty_score":0.999338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2994409524","doi":"10.1080/00031305.2020.1816214","title":"Null Hypothesis Significance Testing Interpreted and Calibrated by Estimating Probabilities of Sign Errors: A Bayes-Frequentist Continuum","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Bayes factor; Frequentist inference; Posterior probability; Bayesian probability; Statistics; Bayes' theorem; Mathematics; p-value; Statistical hypothesis testing; Sign (mathematics); Null hypothesis; Prior probability; Alternative hypothesis; Statistical power; Econometrics; Bayesian inference; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.3681754553938135,"gpt":0.4518311482418546,"spread":0.08365569284804114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001482716,0.0003422981,0.001252717,0.0000377161,0.0001402364,0.00008238522,0.0004764592,0.00005224674,0.00009949881],"category_scores_gemma":[0.2038962,0.0002600042,0.00007684228,0.0006448548,0.002303437,0.00007323117,0.0001581667,0.0003551701,0.000007222949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003968157,"about_ca_system_score_gemma":0.00009418105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005778697,"about_ca_topic_score_gemma":0.0000247433,"domain_scores_codex":[0.9955253,0.00171395,0.001362503,0.0005524341,0.0003943502,0.0004514423],"domain_scores_gemma":[0.8925856,0.1051249,0.001406964,0.0004294578,0.0002136232,0.000239461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002390892,0.0007315489,0.008218993,0.003684911,0.001319089,0.000130817,0.01375035,0.00007439631,0.1036711,0.07198223,0.05973429,0.7343113],"study_design_scores_gemma":[0.001055002,0.001891505,0.002400536,0.000559864,0.0005195353,0.00001135761,0.002924074,0.05728111,0.005282698,0.9271859,0.00009929095,0.0007891363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1011124,0.00004973148,0.8932944,0.001440707,0.0001261186,0.001129726,0.00174927,0.0002456828,0.0008519814],"genre_scores_gemma":[0.3673545,0.000002462898,0.6318411,0.000588876,0.00008349469,0.00005224842,0.000002143413,0.00005214943,0.00002310593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8552037,"threshold_uncertainty_score":0.9999852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387362492","doi":"10.1080/00031305.2023.2267597","title":"Causal Quartets: Different Ways to Attain the Same Average Treatment Effect","year":2023,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Science North","funders":"","keywords":"Variation (astronomy); Context (archaeology); Simple (philosophy); Epistemology; Mathematical economics; Mathematics; Computer science; Econometrics; Sociology; Philosophy; History; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1062671461788742,"gpt":0.4161824036868427,"spread":0.3099152575079684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004452567,0.000374517,0.0005718151,0.0001003835,0.0003163132,0.00006437115,0.000463023,0.00002486943,0.00007694253],"category_scores_gemma":[0.0008135668,0.0001777233,0.00009719453,0.0006172624,0.0003727666,0.00003738588,0.0001348388,0.0001939923,0.0003833767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002980437,"about_ca_system_score_gemma":0.00003220067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009384574,"about_ca_topic_score_gemma":0.0007961535,"domain_scores_codex":[0.9979881,0.0003721944,0.0003308891,0.0003299473,0.0003682099,0.0006106565],"domain_scores_gemma":[0.992121,0.006597991,0.0002261863,0.0008960207,0.00004226254,0.0001165734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003712386,0.0002787744,0.001028484,0.0000770482,0.0004306315,0.0002399105,0.01276988,0.0003111847,0.005822466,0.4155166,0.08387211,0.4792817],"study_design_scores_gemma":[0.0009944552,0.01109065,0.02729815,0.0001810887,0.0004747386,0.00003615129,0.004123634,0.003624126,0.009862268,0.9261406,0.01480205,0.001372087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5336497,0.0000134592,0.4585511,0.003394282,0.0001484333,0.00176232,0.0004363986,0.001149264,0.0008950378],"genre_scores_gemma":[0.9893496,0.00004539617,0.007827071,0.001204652,0.0001642111,0.0007153351,0.00003576782,0.00008523885,0.0005727437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.510624,"threshold_uncertainty_score":0.7247347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1966264920","doi":"10.1198/000313008x269738","title":"Confidence Intervals for a Discrete Population Median","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Confidence interval; CDF-based nonparametric confidence interval; Robust confidence intervals; Statistics; Population; Confidence distribution; Confidence region; Statistic; Sign test; Mathematics; Credible interval; Sign (mathematics); Computer science; Medicine; Mann–Whitney U test; Wilcoxon signed-rank test","retraction":null,"screen_n_in":null,"score":{"opus":0.5415881943883241,"gpt":0.581522353994503,"spread":0.03993415960617896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00167686,0.0002031731,0.0007232482,0.00005086162,0.0002690107,0.0000274724,0.0004198055,0.00003581541,0.0001253654],"category_scores_gemma":[0.07583276,0.0001381713,0.0001323391,0.00025654,0.001046701,0.00004897544,0.00006866048,0.0001870691,0.00003665268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005458709,"about_ca_system_score_gemma":0.00004655448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000544664,"about_ca_topic_score_gemma":0.00009604495,"domain_scores_codex":[0.9973236,0.000769955,0.0008036396,0.0003331472,0.0003736427,0.0003959586],"domain_scores_gemma":[0.9370082,0.06155063,0.0006466418,0.0005223149,0.0001267605,0.0001454462],"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":[0.000405165,0.00007580064,0.001011387,0.00006883101,0.0001181582,0.00002475402,0.0009375227,0.0000033486,0.0001110375,0.915164,0.01659982,0.06548019],"study_design_scores_gemma":[0.0003734095,0.0003486236,0.01524994,0.00004203184,0.0001029863,0.00001535553,0.0001970076,0.001055782,0.00008294741,0.9819951,0.0003347839,0.0002020373],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01603796,0.00000951914,0.9797811,0.001675471,0.0003523802,0.000818594,0.0006053085,0.0001053945,0.0006142992],"genre_scores_gemma":[0.4084019,0.00001702747,0.5901673,0.0007966327,0.00027044,0.0001155584,0.000007511937,0.00003541985,0.0001882152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3923639,"threshold_uncertainty_score":0.9319519,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071800806","doi":"10.1080/00031305.2012.755361","title":"A Few Counter Examples Useful in Teaching Central Limit Theorems","year":2012,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Sequence (biology); Limit (mathematics); Convergence (economics); Probabilistic logic; Central limit theorem; Distribution (mathematics); Convergence of random variables; Weak convergence; Applied mathematics; Random variable; Calculus (dental); Mathematical economics; Statistics; Mathematical analysis; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.0851317892525428,"gpt":0.3890453679611939,"spread":0.3039135787086511,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005037866,0.0001552531,0.0002476433,0.00004931333,0.0001928294,0.00004936683,0.0002215049,0.00001905876,0.0002965472],"category_scores_gemma":[0.001208054,0.0001129351,0.00003847733,0.0002342714,0.0004090429,0.00008712054,0.00004303778,0.0002462469,0.0001417718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001100934,"about_ca_system_score_gemma":0.00002956208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004134247,"about_ca_topic_score_gemma":0.0001186673,"domain_scores_codex":[0.9984808,0.0002573468,0.0003399886,0.0001559611,0.0002345089,0.0005314106],"domain_scores_gemma":[0.9971554,0.0021323,0.0002110269,0.0003175976,0.00003468257,0.0001489382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001548279,0.0001655814,0.005485751,0.000009832023,0.00001384187,0.000001239021,0.001524954,0.000003922365,0.00004131002,0.9739381,0.006138838,0.01266117],"study_design_scores_gemma":[0.0003786552,0.0000578318,0.7208341,0.00004535469,0.00008039347,0.00001671642,0.003750388,0.003398415,0.00003903337,0.2548957,0.01613301,0.0003703306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2031247,0.00002159781,0.7893384,0.0009914027,0.00007233871,0.0003130842,0.0005862587,0.00009631017,0.005456004],"genre_scores_gemma":[0.9739221,0.00000664883,0.02479487,0.0008956198,0.0001115274,0.00007228233,0.00005802243,0.00002369272,0.0001151778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7707975,"threshold_uncertainty_score":0.460536,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803912231","doi":"10.1080/00031305.2018.1475304","title":"Two-Tailed <i>p</i> -Values and Coherent Measures of Evidence","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Null hypothesis; p-value; Null (SQL); Statistical hypothesis testing; Interpretation (philosophy); Alternative hypothesis; Econometrics; Mathematics; Value (mathematics); Statistics; Set (abstract data type); Measure (data warehouse); Statistical evidence; Statistical significance; Mathematical economics; Computer science; Data mining; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.3190207158526712,"gpt":0.4897757391841812,"spread":0.17075502333151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006533041,0.000146559,0.0004040087,0.00003025242,0.0001302796,0.00001633229,0.0001878982,0.00001126754,0.0000360595],"category_scores_gemma":[0.003228705,0.00008368707,0.0000286201,0.0001643843,0.001914845,0.00004918238,0.00007857529,0.00009721339,0.00000655214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001764888,"about_ca_system_score_gemma":0.00003382205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002196051,"about_ca_topic_score_gemma":0.00009157609,"domain_scores_codex":[0.9985713,0.000362592,0.000313248,0.0002179206,0.0002933331,0.0002415992],"domain_scores_gemma":[0.9947106,0.004327714,0.0003337478,0.0003500772,0.0001899736,0.00008789181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002949295,0.00007185863,0.0005944262,0.00007849379,0.00008465396,0.000006455753,0.002113816,0.000003473133,0.005175688,0.4341122,0.001935048,0.5555289],"study_design_scores_gemma":[0.0002208635,0.0006447245,0.002088167,0.0001353976,0.0001305287,0.000006529671,0.0008823166,0.001411824,0.001532514,0.9924193,0.000349123,0.0001787234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04431131,0.0001403248,0.9537832,0.0002237489,0.00006004407,0.0002366212,0.00008892934,0.00003557203,0.001120294],"genre_scores_gemma":[0.515821,0.00006785402,0.483686,0.0002199844,0.00007123846,0.00001328382,4.302085e-7,0.0000163591,0.0001038721],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5583071,"threshold_uncertainty_score":0.7055326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320057135","doi":"10.1080/00031305.2022.2139293","title":"Bayes Factors and Posterior Estimation: Two Sides of the Very Same Coin","year":2022,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayes factor; Bayes' rule; Prior probability; Bayes' theorem; Bayesian probability; Posterior probability; Odds; Point estimation; Bayes estimator; Estimation; Statistics; Mathematics; Econometrics; Computer science; Economics; Logistic regression","retraction":null,"screen_n_in":null,"score":{"opus":0.04192648487641282,"gpt":0.3594317233608289,"spread":0.3175052384844161,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003698,0.0001473049,0.0003503233,0.00003593671,0.0003669777,0.00003172745,0.0003084492,0.000007585057,0.0002277647],"category_scores_gemma":[0.001512101,0.00008387035,0.00004546211,0.0002944579,0.0008230847,0.00002974678,0.0002595887,0.0001871329,0.000001649961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003656279,"about_ca_system_score_gemma":0.0000613731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000996338,"about_ca_topic_score_gemma":0.00008870038,"domain_scores_codex":[0.9984157,0.000574591,0.0003107533,0.0001727434,0.0003273784,0.0001987957],"domain_scores_gemma":[0.9942155,0.00494008,0.0003958449,0.0003570875,0.00004110729,0.00005040121],"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":[0.0001124923,0.0001038596,0.01658842,0.00009321286,0.00009448727,0.00001077343,0.004171534,0.00002028171,0.001023876,0.7488186,0.001472301,0.2274902],"study_design_scores_gemma":[0.000224538,0.0003471829,0.1592072,0.0000315363,0.0001308371,0.00003138953,0.004187852,0.003025681,0.0004195978,0.8320454,0.000146796,0.0002020061],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6626723,0.00003096553,0.3345881,0.0007676806,0.0001479659,0.0002988617,0.0009856737,0.00003290789,0.0004755496],"genre_scores_gemma":[0.7732601,0.000002586179,0.2262781,0.0003604888,0.00001744947,0.00002238666,0.000003274549,0.00001654617,0.00003918461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2272882,"threshold_uncertainty_score":0.3420134,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064662029","doi":"10.1198/000313001317098239","title":"A Computer-Based Lab Supplement to Courses in Introductory Statistics","year":2001,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University","funders":"","keywords":"Frequentist inference; Computer science; Curriculum; Mathematics education; Simple (philosophy); Mathematics; Psychology; Artificial intelligence; Pedagogy; Bayesian probability; Bayesian inference","retraction":null,"screen_n_in":null,"score":{"opus":0.1108184185375485,"gpt":0.4304344429762325,"spread":0.3196160244386839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008786457,0.0002188361,0.0004290393,0.000201407,0.0001142467,0.00005419281,0.0003608312,0.00001701886,0.0004099556],"category_scores_gemma":[0.002244959,0.0001739096,0.00002711888,0.0005701019,0.0003559645,0.00002063341,0.00007081447,0.0001780508,0.00009754147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001614993,"about_ca_system_score_gemma":0.0002090329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008001318,"about_ca_topic_score_gemma":0.001380444,"domain_scores_codex":[0.9978474,0.0005749532,0.0004572216,0.0003154006,0.0003332273,0.0004718471],"domain_scores_gemma":[0.9935303,0.005403697,0.0002665343,0.000515965,0.000145376,0.0001380828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002294996,0.0004013412,0.005502691,0.00004836553,0.00004538913,0.00007673356,0.002692377,0.000415159,0.00009645248,0.245614,0.6193991,0.125479],"study_design_scores_gemma":[0.002604724,0.00252154,0.2417617,0.0001776908,0.0003009365,0.00005825658,0.01594844,0.01297271,0.0004482029,0.4031719,0.3181723,0.001861617],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04128487,0.00001177931,0.951768,0.004228474,0.0006635094,0.0004817633,0.00125146,0.00008426626,0.000225861],"genre_scores_gemma":[0.1024263,0.00002071816,0.8931417,0.003560606,0.0002722995,0.00009014209,0.00007303012,0.00004050891,0.0003746084],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3012268,"threshold_uncertainty_score":0.7091826,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060343609","doi":"10.1198/000313007x188414","title":"Early Evidence-Based Medicine","year":2007,"lang":"en","type":"article","venue":"The American Statistician","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Representativeness heuristic; Medical statistics; Statistician; Sample size determination; Population; Randomization; Sample (material); Statistics; History; Randomized controlled trial; Medicine; Demography; Mathematics; Sociology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.2140236339624821,"gpt":0.4641380792322393,"spread":0.2501144452697572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003427949,0.0001568885,0.000353722,0.0000878401,0.0002115119,0.00002841025,0.0004641987,0.00002202601,0.0003655993],"category_scores_gemma":[0.01673163,0.00009518897,0.00004242243,0.0005825597,0.002163554,0.00005614776,0.00005616286,0.0003109874,0.0001196967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009843356,"about_ca_system_score_gemma":0.0001052781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001942297,"about_ca_topic_score_gemma":0.0004480593,"domain_scores_codex":[0.9976629,0.0003151688,0.0004154965,0.0002522681,0.0007782074,0.0005759305],"domain_scores_gemma":[0.976558,0.02230537,0.0001882705,0.0005511616,0.0001766084,0.000220648],"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":[0.0004993133,0.00008984635,0.001387858,0.00007495684,0.00003427448,0.00008115197,0.0007366408,0.000001615449,0.0003946988,0.7880495,0.009975994,0.1986742],"study_design_scores_gemma":[0.0003495598,0.001184648,0.1560891,0.0001986286,0.00007273388,0.00000472752,0.0005943622,0.0007620209,0.0001980876,0.8388015,0.001510478,0.0002341555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1116046,0.00007698969,0.8765008,0.005739371,0.00006792607,0.0003563247,0.00004418263,0.00009502977,0.005514785],"genre_scores_gemma":[0.9446499,0.00001294073,0.05325352,0.001559098,0.0001658691,0.00001545465,0.000002670826,0.00002344286,0.0003170571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8330454,"threshold_uncertainty_score":0.9915509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2014058093","doi":"10.1198/000313006x89947","title":"The PDF of a Function of a Random Variable","year":2006,"lang":"en","type":"article","venue":"The American Statistician","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Probability density function; Random variable; Mathematics; Probability mass function; Variable (mathematics); Inverse function; Function (biology); Inverse; Analogy; Applied mathematics; Statistical physics; Statistics; Mathematical analysis; Geometry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.004906086841960577,"gpt":0.221514498969025,"spread":0.2166084121270644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002283804,0.00004774223,0.0001083504,0.00001836655,0.0001676641,0.00001386262,0.0003759758,0.000005176168,0.00001018602],"category_scores_gemma":[0.00002406036,0.00002770632,0.00002486762,0.0004773068,0.0003384565,0.00004212093,0.00004853711,0.00004150962,0.00001500196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009311309,"about_ca_system_score_gemma":0.00005038947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00164712,"about_ca_topic_score_gemma":0.0000343687,"domain_scores_codex":[0.9993964,0.00006759963,0.0001890116,0.00009156553,0.0001458043,0.0001096266],"domain_scores_gemma":[0.9987417,0.0005669383,0.0002568841,0.0003405842,0.00008030156,0.00001362931],"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":[0.00002657814,0.00004889182,0.00008031757,0.000002698234,0.00001534093,1.869946e-7,0.00005070266,0.0006200672,0.001119858,0.9366482,0.004760877,0.05662628],"study_design_scores_gemma":[0.0009398217,0.0004688418,0.2086363,0.00001944913,0.00007172714,0.000008929263,0.0004052345,0.187802,0.000532435,0.5589947,0.04190984,0.0002107767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002705529,0.00009138419,0.9922117,0.000535177,0.00004364132,0.0001069521,0.00001854817,0.00001540013,0.004271645],"genre_scores_gemma":[0.8937675,0.00002390262,0.1051563,0.0001251874,0.0000665935,0.00004166908,0.000004644754,0.000004619945,0.0008095932],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.891062,"threshold_uncertainty_score":0.2489964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4251610920","doi":"10.1198/tas.2009.0021","title":"Comment","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1836444922536196,"gpt":0.4710982106444673,"spread":0.2874537183908477,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004283001,0.00009832217,0.0001949803,0.0000339802,0.0001263343,0.00002800248,0.0002086702,0.000007906397,0.0001127913],"category_scores_gemma":[0.001670631,0.00006476352,0.00002664603,0.0001701298,0.0002250917,0.00001302634,0.00001672029,0.00009683095,0.00006993909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003239644,"about_ca_system_score_gemma":0.000031921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005199794,"about_ca_topic_score_gemma":0.000008495586,"domain_scores_codex":[0.9990999,0.0002497208,0.0001793186,0.0001148452,0.0001520882,0.0002041928],"domain_scores_gemma":[0.9967167,0.002677771,0.0001863942,0.0003183704,0.00004608256,0.00005468778],"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":[0.00001362773,0.00004439591,0.00003630971,0.000002170068,0.000009238032,0.000002264376,0.0005340975,4.231329e-7,0.00003642713,0.6165805,0.260874,0.1218665],"study_design_scores_gemma":[0.0001047761,0.0001922446,0.01711251,0.000006334075,0.00003821537,0.000006511294,0.002026112,0.00007553431,0.0001291838,0.9253308,0.05485064,0.0001271801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01158619,0.00003248964,0.9238104,0.0472973,0.0004485551,0.0003044101,0.0001549523,0.0002153053,0.01615037],"genre_scores_gemma":[0.3048522,0.00003121094,0.6677116,0.02638429,0.0001302348,0.00001578953,0.00001052976,0.00001557632,0.0008486172],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3087502,"threshold_uncertainty_score":0.264098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967757406","doi":"10.1198/tast.2009.0028","title":"Design Effect Caveats","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Water Quality and Resources Studies","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Statistics Canada","funders":"","keywords":"Simple (philosophy); Variance (accounting); Statistics; Computer science; Design of experiments; Econometrics; Mathematics; Economics; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.0334271747039749,"gpt":0.2676757398685364,"spread":0.2342485651645615,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002918976,0.00009933006,0.0001528483,0.000009187614,0.0002423464,0.0000194702,0.0001979468,0.000007084269,0.0001375258],"category_scores_gemma":[0.00003823555,0.0000553565,0.00002313588,0.00016488,0.0005988172,0.00002388771,0.00004883408,0.00007291781,0.0006374442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004102724,"about_ca_system_score_gemma":0.000001911291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009560414,"about_ca_topic_score_gemma":0.00003213899,"domain_scores_codex":[0.9990434,0.0002955779,0.00009651491,0.0001446936,0.000181883,0.000237938],"domain_scores_gemma":[0.9994109,0.0002876607,0.00007227029,0.0001806824,0.000001955915,0.00004658912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003090477,0.0001124332,0.01022738,0.000005940116,0.0000620775,0.00007271884,0.01031601,0.004482415,0.007652356,0.0006540599,0.05255489,0.9135507],"study_design_scores_gemma":[0.0003583534,0.00271872,0.9683888,0.0000131262,0.00008554079,0.00001793027,0.0007123686,0.001375218,0.00299539,0.00897019,0.01391056,0.0004538397],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8572154,0.0000642372,0.1088862,0.004400434,0.00008812136,0.0005096715,0.00001755006,0.0001354003,0.02868302],"genre_scores_gemma":[0.9938837,0.00001076295,0.003359348,0.002171699,0.00003538678,0.000006146319,0.000001134385,0.000005394065,0.0005264345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9581614,"threshold_uncertainty_score":0.8193268,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2801323879","doi":"10.1080/00031305.2018.1438699","title":"Introduction: Special Issue on Data Science","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Data science; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.07468234379272098,"gpt":0.3439921917675001,"spread":0.2693098479747791,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005232627,0.0001291418,0.0001433533,0.0001485777,0.0006373925,0.0004048862,0.00169534,0.000008465171,0.003703366],"category_scores_gemma":[0.0006019471,0.00008828378,0.0000105288,0.001631011,0.003243328,0.001074395,0.0006092309,0.0001085533,0.007758349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002335957,"about_ca_system_score_gemma":0.00004596712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001154393,"about_ca_topic_score_gemma":0.0002522481,"domain_scores_codex":[0.9986095,0.000009177653,0.0001626449,0.0004751308,0.0004243275,0.0003191498],"domain_scores_gemma":[0.9982478,0.0000517858,0.0002212765,0.001233646,0.0002323878,0.00001312298],"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":[0.00006229798,0.0000306043,0.000168418,0.000005862074,0.000005421128,0.000002765729,0.000028786,0.0000019785,0.0000980493,0.05835161,0.5950428,0.3462014],"study_design_scores_gemma":[0.00003950729,0.00003238436,0.01156185,0.000007983961,0.00002269539,0.000002631809,0.0002686838,0.001466045,0.00008987907,0.00148153,0.984886,0.0001408407],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07538558,0.00003529242,0.04360405,0.1000076,0.02264618,0.00103958,0.0006204318,0.0006159968,0.7560453],"genre_scores_gemma":[0.6255146,0.00001867301,0.002094503,0.01563408,0.3551821,0.00000742437,0.0001884519,0.00003729313,0.001322909],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7547224,"threshold_uncertainty_score":0.9994693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790711374","doi":"10.1080/00031305.2018.1555101","title":"The World of Research Has Gone Berserk: Modeling the Consequences of Requiring “Greater Statistical Stringency” for Scientific Publication","year":2019,"lang":"en","type":"preprint","venue":"The American Statistician","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Reliability (semiconductor); Publication; Incentive; Odds; Statistical power; Sample size determination; Sample (material); Econometrics; Statistical model; Affect (linguistics); Management science; Actuarial science; Computer science; Power (physics); Operations research; Psychology; Statistics; Economics; Political science; Mathematics; Law; Microeconomics; Logistic regression","retraction":null,"screen_n_in":null,"score":{"opus":0.8567728382291895,"gpt":0.5943493876722813,"spread":0.2624234505569082,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.1860069,0.0003317175,0.002619644,0.0006610028,0.001656676,0.002479822,0.006272939,0.00004104473,0.001270774],"category_scores_gemma":[0.05299664,0.0001234254,0.0007104693,0.002757643,0.006463753,0.0000912727,0.001308729,0.0007153363,0.0001151779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000109708,"about_ca_system_score_gemma":0.0009066565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009796015,"about_ca_topic_score_gemma":0.0006328837,"domain_scores_codex":[0.9665165,0.01592731,0.007642181,0.001343119,0.007921984,0.0006489392],"domain_scores_gemma":[0.9310172,0.04639962,0.009766219,0.007156698,0.005548027,0.0001122423],"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":[0.0004011633,0.0001676773,0.005121108,0.00077146,0.001995147,0.000003269314,0.010074,0.05376052,0.0006176151,0.5767694,0.2171894,0.1331292],"study_design_scores_gemma":[0.0002262596,0.0002625296,0.003040362,0.0002524424,0.0009347516,0.00000500055,0.02223201,0.5892829,0.0001692168,0.3377242,0.04539951,0.0004708767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08738007,0.001394741,0.8778241,0.01411515,0.001426386,0.007045175,0.004094555,0.00001313962,0.006706711],"genre_scores_gemma":[0.9795583,0.00003409235,0.01337869,0.00007764501,0.00007869353,0.000309771,0.0000729876,0.0000255664,0.006464284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8921782,"threshold_uncertainty_score":0.999643,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318485822","doi":"10.1080/00031305.2022.2160590","title":"Object Oriented Data Analysis","year":2023,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":2,"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":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03783203117561788,"gpt":0.3352063899743726,"spread":0.2973743587987547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000404211,0.0001047064,0.000249358,0.0001638025,0.0002114017,0.0000451915,0.001162874,0.000005653678,0.00001155862],"category_scores_gemma":[0.0001879906,0.00007026732,0.00003333956,0.004718603,0.0002263482,0.0002690152,0.0008411965,0.00007369256,0.000254967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001554297,"about_ca_system_score_gemma":0.00004693654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001708362,"about_ca_topic_score_gemma":0.0005805711,"domain_scores_codex":[0.9987004,0.0001358857,0.0001881499,0.0004108293,0.0002726736,0.0002920141],"domain_scores_gemma":[0.9970443,0.0003757096,0.0001823573,0.002292423,0.00004148273,0.0000637123],"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":[0.00002117047,0.00003286086,0.003699198,0.00001324802,0.0007846866,0.0001863031,0.001837272,0.001089561,0.0001948546,0.6914719,0.04776929,0.2528997],"study_design_scores_gemma":[0.0002235323,0.0001681402,0.1859312,0.00001553779,0.0003291655,0.00001312701,0.002734073,0.4884602,0.00005961672,0.002810254,0.3186731,0.0005819954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003194632,0.00001961024,0.9943684,0.0005163492,0.0001327529,0.00008134496,0.0009473404,0.0002943068,0.0004453106],"genre_scores_gemma":[0.5182633,0.0001025542,0.4771327,0.001582438,0.0002202705,0.00004172111,0.001470851,0.0000309935,0.001155123],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6886616,"threshold_uncertainty_score":0.327717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392662318","doi":"10.1080/00031305.2024.2327535","title":"Thick Data Analytics (TDA): An Iterative and Inductive Framework for Algorithmic Improvement","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Machine Learning in Healthcare","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":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; School of Medicine, Stanford University; National Institutes of Health; Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; SAFER; Subject-matter expert; USable; Data science; Analytics; Domain (mathematical analysis); Machine learning; Data mining; Domain knowledge; Frame (networking); Artificial intelligence; Risk analysis (engineering); Expert system","retraction":null,"screen_n_in":null,"score":{"opus":0.0671994435639882,"gpt":0.4028620339116792,"spread":0.335662590347691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005984974,0.0001721952,0.0002309088,0.00008660072,0.0002690413,0.0004459015,0.001183456,0.00002762986,0.000005647475],"category_scores_gemma":[0.0003644418,0.0001238364,0.00001889058,0.0004924327,0.0003122531,0.0003387626,0.0004941343,0.0004620234,0.000007735952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006297875,"about_ca_system_score_gemma":0.0001627837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001185674,"about_ca_topic_score_gemma":0.00009805004,"domain_scores_codex":[0.9983098,0.0002194017,0.0002287963,0.0006689309,0.0002464792,0.0003265781],"domain_scores_gemma":[0.9969935,0.00147899,0.0001513677,0.001164103,0.00009125167,0.0001207171],"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":[0.0000100759,0.00001832824,0.0001172358,0.00004669596,0.00005920242,0.00001321568,0.004751384,0.00003488834,0.00002267709,0.3549637,0.0005003568,0.6394622],"study_design_scores_gemma":[0.00006337857,0.0009578747,0.003836826,0.00005897081,0.00003618714,0.000007548812,0.001067523,0.8903852,0.00001320063,0.1001067,0.003262794,0.0002038599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00526478,0.0001726043,0.9870006,0.006109431,0.0003100148,0.0004471759,0.0005067501,0.0001465114,0.00004207963],"genre_scores_gemma":[0.3998801,0.00003029064,0.5977347,0.001899948,0.0003042706,0.00004632037,0.0000443928,0.00002386387,0.00003604536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8903502,"threshold_uncertainty_score":0.5049903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412709116","doi":"10.1080/00031305.2025.2539241","title":"A Fisher’s Exact Test Justification of the TF–IDF Term-Weighting Scheme","year":2025,"lang":"en","type":"article","venue":"The American Statistician","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","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 Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Weighting; Statistics; Mathematics; Test (biology); Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.07572393262271854,"gpt":0.4222604066798787,"spread":0.3465364740571601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00421148,0.0001723609,0.0003989124,0.0001800044,0.0004139657,0.0001387739,0.001745126,0.00002618737,0.0001471373],"category_scores_gemma":[0.04418897,0.00009172234,0.0001117202,0.002682966,0.001123542,0.00007549428,0.000321376,0.0002437572,0.00003791252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000679752,"about_ca_system_score_gemma":0.0001996409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004167809,"about_ca_topic_score_gemma":0.00009681709,"domain_scores_codex":[0.9965428,0.001033039,0.000779644,0.0004223765,0.0009112916,0.000310897],"domain_scores_gemma":[0.9767629,0.02023924,0.001166265,0.001433696,0.00034478,0.0000531124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004830358,0.00005711124,0.08662386,0.0000118504,0.00003065791,0.000001537489,0.0007132344,0.00002332559,0.008158942,0.006201546,0.02437134,0.8737583],"study_design_scores_gemma":[0.0001556199,0.00008457971,0.9542444,0.00007993625,0.00006562736,0.000004819077,0.00181503,0.01130055,0.001461286,0.02459729,0.006035996,0.000154807],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.690428,0.00009295605,0.2243945,0.00674784,0.0009569836,0.000780937,0.000221836,0.0001003653,0.07627667],"genre_scores_gemma":[0.9556899,0.00000371839,0.03948314,0.0008420637,0.00007315548,0.00002680278,0.000001903019,0.00001568974,0.003863642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8736035,"threshold_uncertainty_score":0.9638622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129813332","doi":"10.1080/00031305.2014.904250","title":"On a Simple Construction of a Bivariate Probability Function With a Common Marginal","year":2014,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Bivariate analysis; Simple (philosophy); Mathematics; Statistics; Econometrics; Function (biology); Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.009802170898168941,"gpt":0.2512180360990115,"spread":0.2414158652008426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004942711,0.0001078144,0.0002347513,0.00004676909,0.00009903138,0.00003259341,0.0002774912,0.00001183719,0.000006099558],"category_scores_gemma":[0.00005796387,0.00006584241,0.00002532908,0.0003625985,0.0004006058,0.00006369584,0.00004287403,0.0001111944,0.000004137697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002188453,"about_ca_system_score_gemma":0.00004115267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005425708,"about_ca_topic_score_gemma":0.00007320219,"domain_scores_codex":[0.9987831,0.0004480156,0.0001672793,0.0002330742,0.0001973471,0.0001712462],"domain_scores_gemma":[0.9986652,0.000415527,0.00028516,0.000521665,0.00006325087,0.00004927103],"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":[0.000120051,0.00002508658,0.0002206737,0.000006991475,0.00001140467,5.501463e-7,0.0001314221,0.00002861266,0.00008114501,0.6722826,0.00006594848,0.3270255],"study_design_scores_gemma":[0.0002584222,0.001751766,0.02978255,0.00001744471,0.00002897906,0.00001502242,0.00002810703,0.03061003,0.0001343446,0.9369582,0.0002896615,0.0001254663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05920851,0.000001820056,0.9382883,0.000351201,0.00005187207,0.0001563055,0.00001105793,0.00004375196,0.001887211],"genre_scores_gemma":[0.5726255,5.167134e-7,0.4269993,0.0003387637,0.0000167887,0.000008685995,0.000001282738,0.000004329223,0.000004821723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.513417,"threshold_uncertainty_score":0.2684976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042412758","doi":"10.1198/000313008x303928","title":"Is the Overtime Period in an NHL Game Long Enough? An Example for Teaching Estimation and Hypothesis Testing in the Presence of Censored Data","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Overtime; League; Estimation; Econometrics; Statistics; Computer science; Operations research; Psychology; Mathematics; Economics; Management; Labour economics","retraction":null,"screen_n_in":null,"score":{"opus":0.1606660608038529,"gpt":0.3040503304835622,"spread":0.1433842696797093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001177461,0.0001037675,0.0002670454,0.00008112637,0.0002060705,0.00005758569,0.0005470749,0.00001450627,0.00001390461],"category_scores_gemma":[0.000548505,0.00006950986,0.00001549295,0.0002439806,0.0003559438,0.0002580843,0.00005592671,0.0001316518,0.000001987152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002012031,"about_ca_system_score_gemma":0.00002261385,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0204335,"about_ca_topic_score_gemma":0.001674316,"domain_scores_codex":[0.9989809,0.00005561605,0.0004089769,0.0002848626,0.00005724964,0.000212384],"domain_scores_gemma":[0.9979395,0.0009031445,0.0004155899,0.0006963962,0.00001915301,0.00002625983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001269536,0.0003002694,0.7308013,0.0000631038,0.00004173245,0.00001473174,0.0832994,0.008095992,0.0000488359,0.0267904,0.0004331166,0.1499842],"study_design_scores_gemma":[0.00009849757,0.0000957122,0.5189772,0.00000983692,0.000005353662,0.000005460397,0.001391885,0.4768298,0.000002092537,0.002269578,0.0002419989,0.00007263415],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886354,0.0001159124,0.009836302,0.0004819783,0.00001630809,0.0002799152,0.0004367397,0.000005573252,0.0001918377],"genre_scores_gemma":[0.9876812,0.00006134986,0.01176287,0.0003794676,0.00003790848,0.00001778517,0.00002757959,0.0000144032,0.00001745822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4687338,"threshold_uncertainty_score":0.9860895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766225997","doi":"10.1080/00031305.2017.1377111","title":"Bayesian Analysis on a Noncentral Fisher–Student’s Hypersphere","year":2017,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hypersphere; Mathematics; False discovery rate; Statistical hypothesis testing; Bayes factor; Null distribution; Null hypothesis; Bayesian probability; p-value; Bayes' theorem; Multiple comparisons problem; Weibull distribution; Statistics; Applied mathematics; Test statistic; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.3520839162328059,"gpt":0.5716076458469133,"spread":0.2195237296141074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001640504,0.000312042,0.001157748,0.00006952746,0.0007773218,0.0003252469,0.001482967,0.00005145881,0.0008453594],"category_scores_gemma":[0.03607605,0.0002111469,0.0003161087,0.0003676011,0.001574598,0.00005662706,0.0002018908,0.0004088952,0.0001352458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009523822,"about_ca_system_score_gemma":0.00005302451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007169673,"about_ca_topic_score_gemma":0.0003778852,"domain_scores_codex":[0.9964729,0.0009752191,0.0007063585,0.0005416048,0.0006961641,0.000607752],"domain_scores_gemma":[0.9716646,0.02463855,0.001191658,0.002161432,0.00009644981,0.0002473016],"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":[0.0008952403,0.0009719179,0.05284845,0.00005648274,0.004960492,0.0003205887,0.001410347,0.00006371406,0.00007591253,0.5133632,0.03444737,0.3905863],"study_design_scores_gemma":[0.0007595912,0.0004752699,0.4285171,0.00004352485,0.002551258,0.000002794009,0.0009135375,0.001830235,0.0000403027,0.5634103,0.0009688507,0.0004871661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1123093,0.00001411635,0.8242672,0.005538635,0.0009453871,0.0009905735,0.001108223,0.0002290856,0.05459746],"genre_scores_gemma":[0.6248642,0.00001602445,0.3728736,0.001239515,0.0003377876,0.0000352375,0.000002491654,0.00004350048,0.0005876486],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5125549,"threshold_uncertainty_score":0.9720435,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021098222","doi":"10.1198/tast.2011.11018","title":"Statistics in the News","year":2011,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","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 Toronto; HEC Montréal","funders":"","keywords":"Mathematics education; Statistics education; Course (navigation); Information literacy; Computer science; Key (lock); Literacy; Data science; Statistics; Library science; Sociology; Mathematics; Pedagogy; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.3374795160313217,"gpt":0.4504248488064071,"spread":0.1129453327750854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104139,0.0001576363,0.0002657988,0.00007253021,0.0001320819,0.0000353526,0.0005676241,0.00001637472,0.0002770707],"category_scores_gemma":[0.003725066,0.00008752365,0.00002785932,0.0004033585,0.0006323236,0.00002534842,0.00004276439,0.0002313137,0.0001020961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003261536,"about_ca_system_score_gemma":0.00008265043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002002371,"about_ca_topic_score_gemma":0.001282699,"domain_scores_codex":[0.9980145,0.0008759946,0.0003468486,0.0001818951,0.0002526733,0.0003281527],"domain_scores_gemma":[0.9924728,0.006552,0.0003031816,0.0005614056,0.00006446422,0.00004609433],"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":[0.000040672,0.0001137315,0.001653004,0.00001225963,0.00001937097,0.00002482382,0.01482023,3.784072e-7,0.000007672984,0.8112239,0.1175405,0.05454349],"study_design_scores_gemma":[0.0001493424,0.0001457204,0.09006525,0.000008441894,0.00005982085,0.00001846378,0.02567238,0.00007485447,0.0000257111,0.8771122,0.006492853,0.0001750037],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02057801,0.00003483518,0.9511117,0.001071168,0.0005420608,0.0005521207,0.0006359494,0.00008737199,0.02538678],"genre_scores_gemma":[0.2056532,0.00006827898,0.7898271,0.003637475,0.00009530348,0.00009318287,0.00001704031,0.00003373909,0.0005747291],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1850751,"threshold_uncertainty_score":0.4459521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224213250","doi":"10.1080/00031305.2022.2066725","title":"Bias Analysis for Misclassification Errors in both the Response Variable and Covariate","year":2022,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Variable (mathematics); Econometrics; Inference; Computer science; Observational error; Variables; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1336462309730049,"gpt":0.3955855856048989,"spread":0.2619393546318941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00342097,0.0001245023,0.0003493216,0.0001338641,0.0004569264,0.00005269695,0.0002815127,0.00001108497,0.0001405003],"category_scores_gemma":[0.003845636,0.00007844736,0.0000443824,0.001304296,0.000360388,0.00002082614,0.00008864312,0.0001882939,0.000001250948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007520691,"about_ca_system_score_gemma":0.00008698043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000935539,"about_ca_topic_score_gemma":0.0001596669,"domain_scores_codex":[0.9971955,0.001726555,0.0003387734,0.0002492996,0.0002273519,0.0002625581],"domain_scores_gemma":[0.9833933,0.01578174,0.0003386632,0.0004005427,0.00003954959,0.00004627755],"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":[0.0009562863,0.000080485,0.001658862,0.00001645565,0.0001912124,0.000004860276,0.00201311,0.0001103253,0.0002969607,0.9703206,0.001348719,0.02300211],"study_design_scores_gemma":[0.0002943348,0.0002982027,0.1421232,0.000005554041,0.0004994793,0.000004789313,0.004269882,0.0443432,0.0000077143,0.8051922,0.002784501,0.0001768686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03439834,0.00001585405,0.9621208,0.00203642,0.00004217881,0.000418253,0.0007267834,0.0000217695,0.0002196297],"genre_scores_gemma":[0.4618998,0.000005274641,0.5369026,0.0006521707,0.0000175302,0.0003074608,0.00001217901,0.0000180169,0.0001849876],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4275014,"threshold_uncertainty_score":0.4603863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}