{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":52,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":52,"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":"1acf23b356cc","filters":{"venue":"The Annals of Statistics"}},"results":[{"id":"W2172185584","doi":"10.1214/13-aos1175","title":"A significance test for the lasso","year":2014,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":561,"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 Institute of Biomedical Imaging and Bioengineering","keywords":"Mathematics; Test statistic; Lasso (programming language); Null distribution; Statistical hypothesis testing; Null hypothesis; Null (SQL); Linear model; Statistics; Design matrix; Applied mathematics; Algorithm; Computer science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.3167578092553975,"gpt":0.446753198473048,"spread":0.1299953892176505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00145938,0.0001025161,0.0002090677,0.00001265928,0.0001415783,0.00002515338,0.0003502132,0.00003008945,0.00006605431],"category_scores_gemma":[0.02970335,0.00005196155,0.00004464627,0.00008305212,0.0002589828,0.00001440727,0.00003968667,0.00009836766,0.000009914924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000317018,"about_ca_system_score_gemma":0.00002943104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002020522,"about_ca_topic_score_gemma":0.00001048892,"domain_scores_codex":[0.9990714,0.0001070778,0.000301519,0.0001105861,0.000195556,0.0002138975],"domain_scores_gemma":[0.9457298,0.05332883,0.0001942974,0.0003891024,0.0003188286,0.00003916381],"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":[0.00001678384,0.0000437246,0.00003651967,0.00007557325,0.00002036536,1.454846e-7,0.0001545536,0.000004706648,0.0001485593,0.8931127,0.05966416,0.04672223],"study_design_scores_gemma":[0.0001230929,0.0002219115,0.001259843,0.0000247218,0.00004945063,7.497378e-7,0.00007290943,0.01625655,0.001510914,0.9668395,0.01355941,0.0000809627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003751875,0.00004226916,0.9940295,0.002400681,0.0000904374,0.0003120747,0.0009772722,0.00001642752,0.001756165],"genre_scores_gemma":[0.2568543,0.00009774851,0.7409644,0.00105272,0.0001846031,0.00008081365,0.000004171864,0.00002768782,0.0007334892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2564791,"threshold_uncertainty_score":0.9784698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152704622","doi":"10.1214/009053604000000139","title":"Local Whittle estimation in nonstationary and unit root cases","year":2004,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":241,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Alfred P. Sloan Foundation; National Science Foundation","keywords":"Mathematics; Estimator; Unit root; Rate of convergence; Applied mathematics; Asymptotic distribution; Limit (mathematics); Distribution (mathematics); Polynomial; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1836871364158568,"gpt":0.3081281450371227,"spread":0.1244410086212659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002783026,0.00006664058,0.0001617255,0.00009758819,0.00004375368,0.00001469181,0.00007081212,0.0000284707,0.00008460546],"category_scores_gemma":[0.0001494641,0.00006511079,0.00001499419,0.0000721534,0.0001195834,0.0001214579,0.00001946548,0.00006095185,0.0000746221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001337616,"about_ca_system_score_gemma":0.00001501375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002023502,"about_ca_topic_score_gemma":0.0003050934,"domain_scores_codex":[0.999404,0.000008635722,0.0003383108,0.00009965044,0.00001583099,0.000133543],"domain_scores_gemma":[0.9995057,0.0001748117,0.0001540717,0.0001210625,0.00001024563,0.00003412835],"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":[0.00005535284,0.00009025931,0.01888967,0.00005382423,0.00003774522,0.0000133365,0.001670717,0.22868,0.000001608365,0.7417724,0.001705138,0.007030031],"study_design_scores_gemma":[0.0004989688,0.000138915,0.2872199,0.00002328713,0.000004144469,0.00002080534,0.0001909009,0.06712506,0.00008995721,0.6437498,0.0007930105,0.0001452918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8766903,0.0006679576,0.1174142,0.001993125,0.00005036091,0.00010684,0.00138307,0.000006118516,0.001688055],"genre_scores_gemma":[0.9959627,0.000206129,0.003441516,0.0002692358,0.00001114334,0.000002928785,0.00004038164,0.000006701524,0.00005930354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2683302,"threshold_uncertainty_score":0.3058943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092392156","doi":"10.1214/009053604000000201","title":"Mean squared error of empirical predictor","year":2004,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"National Science Foundation","keywords":"Mean squared error; Estimator; Mixed model; Linear model; Generalized linear mixed model; Best linear unbiased prediction; Term (time); Restricted maximum likelihood; Random effects model","retraction":null,"screen_n_in":null,"score":{"opus":0.3889641003180567,"gpt":0.4860981274318291,"spread":0.09713402711377245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006306945,0.0001269183,0.0003606073,0.00003881405,0.00004557825,0.000007945286,0.0002848824,0.00005638854,0.0001793376],"category_scores_gemma":[0.005056721,0.00008292411,0.00005973781,0.0001497404,0.0003542757,0.00002452662,0.0000641888,0.0001312531,0.000009159289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008558716,"about_ca_system_score_gemma":0.00009648158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004378191,"about_ca_topic_score_gemma":0.00001228058,"domain_scores_codex":[0.9985846,0.0001276961,0.0005580924,0.0001288497,0.0003843168,0.0002164887],"domain_scores_gemma":[0.9961218,0.002738691,0.0002838834,0.0003900712,0.0003829647,0.000082623],"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":[0.0000611973,0.0002010133,0.000160421,0.0001834945,0.00005290505,0.00000409613,0.001795963,0.0000211456,0.0002400607,0.9850392,0.008127712,0.004112828],"study_design_scores_gemma":[0.0003031158,0.0003576624,0.004035351,0.00008390325,0.00005272225,0.000002626378,0.0002363594,0.0004264091,0.005037254,0.9891338,0.0002356179,0.00009522727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09053833,0.00006605551,0.9045957,0.0009984706,0.0001032044,0.000216423,0.001725041,0.00002712339,0.001729648],"genre_scores_gemma":[0.4973734,0.00003174054,0.5022937,0.000175231,0.00003910809,0.00000522861,0.000005739316,0.00001616514,0.00005971853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.406835,"threshold_uncertainty_score":0.6053733,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080749331","doi":"10.1214/09-aos712","title":"Estimation for a partial-linear single-index model","year":2009,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":183,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China; Hong Kong Baptist University; Ministry of Education of the People's Republic of China; National Science Foundation","keywords":"Mathematics; Estimator; Asymptotic distribution; Single-index model; Applied mathematics; Nonparametric statistics; Linear model; Statistics; Delta method; Parametric statistics; Rate of convergence; Mathematical optimization; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.4180211576168986,"gpt":0.4749653535220209,"spread":0.05694419590512229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000596419,0.0001169508,0.0002461698,0.00002904493,0.00007992171,0.00001780305,0.0001686926,0.00004729475,0.00002251651],"category_scores_gemma":[0.005555209,0.00008224221,0.00004796331,0.00007938,0.0000885557,0.0000378014,0.0000166394,0.00007625295,0.000003795567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006437449,"about_ca_system_score_gemma":0.00004017486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003790508,"about_ca_topic_score_gemma":0.000001268667,"domain_scores_codex":[0.9989835,0.00005595765,0.0004026396,0.0001239312,0.0002126272,0.0002213442],"domain_scores_gemma":[0.9966663,0.002487432,0.0002115028,0.0002740528,0.0003033835,0.00005728891],"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":[0.0000702311,0.0001258267,0.00000213137,0.00005761257,0.00001346504,5.03851e-7,0.0002309406,0.002270371,0.0002736133,0.8751246,0.007676661,0.114154],"study_design_scores_gemma":[0.00009504268,0.0001741418,0.00003784412,0.00001916661,0.0000213093,5.376261e-7,0.00001231223,0.4819622,0.002152173,0.5154183,0.00005296653,0.00005394872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002646697,0.0000176394,0.994711,0.001039802,0.00003725274,0.0002736683,0.0006054834,0.00002769825,0.0006407411],"genre_scores_gemma":[0.3087672,0.000010148,0.6907021,0.0003613984,0.00003494566,0.000009180199,0.000008803471,0.000009834731,0.00009645251],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4796919,"threshold_uncertainty_score":0.6650506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969936152","doi":"10.1214/aos/1021379865","title":"Bootrapping robust estimates of regression","year":2002,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":177,"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":"Mathematics; Outlier; Quantile; Statistics; Robust regression; Monte Carlo method; Confidence interval; Representation (politics); Linear regression; Quantile regression; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5040113195782486,"gpt":0.4834673291782035,"spread":0.02054399040004512,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004019486,0.0001223471,0.0003293842,0.00003691159,0.00006816786,0.000006092318,0.0001855924,0.00004079641,0.0001529775],"category_scores_gemma":[0.003047113,0.00007664834,0.00004569543,0.0001021199,0.0002198433,0.0000444399,0.00004991585,0.0001101549,0.000003559696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003448699,"about_ca_system_score_gemma":0.000007502108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006652991,"about_ca_topic_score_gemma":0.00000171139,"domain_scores_codex":[0.9989154,0.00007641676,0.0004428361,0.0001177872,0.0002478371,0.0001997514],"domain_scores_gemma":[0.9955061,0.003560161,0.0003266276,0.0003144119,0.0002407838,0.00005188],"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":[0.0000278269,0.0001449661,0.0000219963,0.0003359093,0.00004767706,0.00000561193,0.0006457666,0.0004227826,0.001166067,0.9111853,0.01962085,0.06637526],"study_design_scores_gemma":[0.0001226213,0.0001003257,0.00007971039,0.0001794289,0.00004028626,0.000003028597,0.0000855755,0.04863856,0.007354892,0.9430899,0.0002132741,0.00009240029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001757664,0.0003512078,0.9950531,0.0002882181,0.0000441507,0.0001237842,0.0003239876,0.00001881697,0.002039032],"genre_scores_gemma":[0.07669339,0.0004121128,0.9225689,0.00007023873,0.0000229489,0.000004302938,0.000003228127,0.00001945968,0.0002054689],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07493573,"threshold_uncertainty_score":0.3647899,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007551061","doi":"10.1214/aos/1065705118","title":"Singular Wishart and multivariate beta distributions","year":2003,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Wishart distribution; Mathematics; Inverse-Wishart distribution; Matrix t-distribution; Matrix normal distribution; Scatter matrix; Lebesgue measure; Multivariate normal distribution; Estimation of covariance matrices; Normal-Wishart distribution; Covariance matrix; Combinatorics; Mathematical analysis; Pure mathematics; Lebesgue integration; Multivariate statistics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2629678781473607,"gpt":0.468045262083439,"spread":0.2050773839360783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006076003,0.0001141754,0.0002310206,0.0000181085,0.0001381129,0.00001633221,0.00009007501,0.00003612066,0.00004974833],"category_scores_gemma":[0.004405963,0.00007997581,0.00002774021,0.00007768756,0.0002350359,0.00004236843,0.00003771038,0.0001114962,0.000002791864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004427579,"about_ca_system_score_gemma":0.00002443129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009587041,"about_ca_topic_score_gemma":0.000002743492,"domain_scores_codex":[0.9990314,0.0001750837,0.0002898358,0.0001364238,0.0001532916,0.0002140145],"domain_scores_gemma":[0.996779,0.002545154,0.0001369098,0.000260481,0.0001984475,0.00008001128],"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":[0.00000861939,0.00005533994,0.0000143205,0.00004384897,0.00002929691,0.000003103625,0.0001857283,0.000004754574,0.0002127867,0.9912058,0.002329585,0.005906842],"study_design_scores_gemma":[0.0001604263,0.00005459611,0.0002755122,0.00002459506,0.00005008658,0.000005309385,0.00006265441,0.001196589,0.002361154,0.9915218,0.004187696,0.00009961004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002654307,0.0001372917,0.9941471,0.0002758465,0.00004570065,0.0001462063,0.001551221,0.00001649803,0.00102582],"genre_scores_gemma":[0.1404592,0.0001060217,0.8590758,0.00010196,0.0000148887,0.000006932831,0.00001455801,0.00001617271,0.0002045107],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1378049,"threshold_uncertainty_score":0.5274668,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964248738","doi":"10.1214/17-aos1568","title":"I-LAMM for sparse learning: Simultaneous control of algorithmic complexity and statistical error","year":2018,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institute of General Medical Sciences; National Institute of Mental Health; Science and Technology Commission of Shanghai Municipality; National Institutes of Health; National Science Foundation","keywords":"Sublinear function; Estimator; Mathematics; Mathematical optimization; Algorithm; Computational complexity theory; Rate of convergence; Sequence (biology); Minification; Convex optimization; Applied mathematics; Regular polygon; Computer science; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0968039069539006,"gpt":0.3350539315426729,"spread":0.2382500245887723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001752132,0.0001106665,0.0002569942,0.00003271112,0.00006118999,0.00001040257,0.0001101731,0.00004012436,0.00001811601],"category_scores_gemma":[0.000346489,0.00008937109,0.00002247219,0.00004295037,0.0005139938,0.00001806352,0.00002332079,0.0000936959,0.000001953188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003688107,"about_ca_system_score_gemma":0.00001147823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003109222,"about_ca_topic_score_gemma":0.00001163746,"domain_scores_codex":[0.9993191,0.00004004054,0.0002543006,0.00009219249,0.0001142356,0.0001801819],"domain_scores_gemma":[0.9981993,0.00119674,0.00008484865,0.0001581356,0.0003181744,0.00004279102],"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":[0.001873961,0.0003892192,0.000587,0.001114713,0.001406465,0.00007485683,0.004137366,0.04499913,0.04883387,0.4953939,0.1025051,0.2986844],"study_design_scores_gemma":[0.0003652546,0.0005767049,0.0006593377,0.00004341805,0.00005751531,0.000007317428,0.00009141265,0.9320769,0.01715577,0.04593597,0.002894044,0.0001362961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03255741,0.0001353345,0.9656794,0.00007274253,0.00005990548,0.0002306662,0.001001414,0.00008392481,0.0001792073],"genre_scores_gemma":[0.9268854,0.00006858791,0.07287215,0.00004877877,0.000064416,0.000004186488,0.00001626059,0.00002037725,0.00001979697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8943281,"threshold_uncertainty_score":0.3644447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046360729","doi":"10.1214/14-aos1208","title":"Community detection in dense random networks","year":2014,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Office of Naval Research; Agence Nationale de la Recherche","keywords":"Mathematics; Combinatorics; Bounded function; Graph; Random graph; Discrete mathematics; Clique; Upper and lower bounds; Induced subgraph isomorphism problem; Induced subgraph; Time complexity; Line graph; Voltage graph; Vertex (graph theory)","retraction":null,"screen_n_in":null,"score":{"opus":0.04442482537466764,"gpt":0.3184144351284185,"spread":0.2739896097537509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009468681,0.00007541626,0.0001864111,0.00003875463,0.0001074065,0.00001497866,0.0001883202,0.00001677115,0.00004946385],"category_scores_gemma":[0.00003978727,0.00005865442,0.00004704123,0.0001580197,0.00007384752,0.00002393261,0.00006050293,0.0002445191,0.000002701126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003507463,"about_ca_system_score_gemma":0.000005799156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00129284,"about_ca_topic_score_gemma":0.0003855927,"domain_scores_codex":[0.9990621,0.0004374336,0.0002285873,0.00005483632,0.00008120005,0.0001357966],"domain_scores_gemma":[0.9987296,0.000711885,0.0001343415,0.0003119287,0.00009031222,0.00002196012],"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":[0.0002941343,0.0003672762,0.01511651,0.00002412413,0.0002033691,6.013314e-7,0.001092196,0.02512978,0.0003418089,0.1213589,0.01607585,0.8199954],"study_design_scores_gemma":[0.0008666093,0.0001596019,0.02952963,0.0000504251,0.00007238679,4.477021e-7,0.0003007202,0.491785,0.004353151,0.4694897,0.003157764,0.0002345365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1414997,0.00002018277,0.8567861,0.00006923924,0.00002026797,0.00008273779,0.00001773365,0.0000143299,0.001489716],"genre_scores_gemma":[0.9984767,0.00001307403,0.00128451,0.00006751603,0.00008799674,0.000008206832,0.00002029928,0.000007749148,0.00003397592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.856977,"threshold_uncertainty_score":0.2391858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073388398","doi":"10.1214/aos/1043351254","title":"On depth and deep points: a calculus","year":2002,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Illinois at Urbana-Champaign; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV","keywords":"Mathematics; Differential calculus; Calculus (dental); Upper and lower bounds; Estimator; Point (geometry); Applied mathematics; Mathematical analysis; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.2925035512986743,"gpt":0.4538161063277666,"spread":0.1613125550290923,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003309786,0.0001211036,0.0002347055,0.00002887062,0.00007989647,0.00001209112,0.0001144713,0.00003592142,0.0001437705],"category_scores_gemma":[0.003315937,0.00007920839,0.00002641393,0.00006582803,0.0001831292,0.00003032372,0.00004326456,0.0001244841,0.00001439685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004558951,"about_ca_system_score_gemma":0.000003940744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006560512,"about_ca_topic_score_gemma":0.00001176828,"domain_scores_codex":[0.9990662,0.0001093709,0.0002662791,0.0001406587,0.0002064935,0.000211002],"domain_scores_gemma":[0.9955776,0.003833518,0.0001231692,0.0002662841,0.0001167508,0.00008271435],"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":[0.00002224732,0.00007521026,0.000002517283,0.00005020985,0.00002160751,0.000007859184,0.0005030277,0.0000125897,0.00001500423,0.9023836,0.007838725,0.08906735],"study_design_scores_gemma":[0.0001886343,0.0001990812,0.00008152252,0.00003136859,0.00002748144,0.000005705829,0.00007277422,0.02348776,0.0002391109,0.9749216,0.0006465748,0.00009838808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002195949,0.0002099186,0.9923438,0.0008127216,0.00003675838,0.0001391397,0.0002639804,0.00001915337,0.00397857],"genre_scores_gemma":[0.1500829,0.0006066263,0.8476261,0.001046538,0.00003438455,0.000009770386,0.000002653738,0.00002939329,0.0005616001],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.147887,"threshold_uncertainty_score":0.3969725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127831890","doi":"10.1214/009053605000000309","title":"Exact local Whittle estimation of fractional integration","year":2005,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Economic and Social Research Council; National Science Foundation","keywords":"Tapering; Estimator; Mathematics; Applied mathematics; Limit (mathematics); Distribution (mathematics); Estimation; Long memory; Mathematical optimization; Econometrics; Statistics; Mathematical analysis; Computer science; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.09679765184038333,"gpt":0.3121505688133448,"spread":0.2153529169729615,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004215174,0.00005604859,0.0001628802,0.00006036023,0.00004390311,0.000007970887,0.00008567097,0.0000380134,0.0001535531],"category_scores_gemma":[0.0003058776,0.00005136169,0.00003685866,0.0000847084,0.000074621,0.0001290399,0.00001371413,0.00007724291,0.00005331945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001367055,"about_ca_system_score_gemma":0.00001903175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002207727,"about_ca_topic_score_gemma":0.00003955691,"domain_scores_codex":[0.9993157,0.000009080006,0.0004585404,0.00008681132,0.0000445842,0.00008527179],"domain_scores_gemma":[0.9992931,0.0001378283,0.0003151687,0.0001373019,0.00009947382,0.00001710855],"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":[0.00004219048,0.0000870162,0.0007209859,0.00002452905,0.0000170753,9.191009e-8,0.0007008562,0.07533087,0.00001920534,0.7799853,0.003570006,0.1395018],"study_design_scores_gemma":[0.00009171086,0.00005113206,0.01380274,0.00001382565,0.000003524792,3.631078e-7,0.00005675882,0.7748639,0.001017122,0.2081274,0.001913117,0.00005836344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06597438,0.0003215884,0.93082,0.0006622926,0.00006417284,0.00005741008,0.0004984198,0.000005181112,0.001596502],"genre_scores_gemma":[0.9791468,0.0001972317,0.02039368,0.00008206798,0.00004770625,0.000002165687,0.00003685096,0.000005787416,0.0000877285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9131724,"threshold_uncertainty_score":0.2094469,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020371156","doi":"10.1214/08-aos627","title":"Covariate-adjusted nonlinear regression","year":2009,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; National Cancer Institute; Hong Kong Baptist University; National Science Foundation","keywords":"Mathematics; Covariate; Empirical likelihood; Statistics; Estimator; Coverage probability; Asymptotic distribution; Consistency (knowledge bases); Nonlinear regression; Nuisance parameter; Confidence interval; Econometrics; Delta method; Regression analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.4014581664040456,"gpt":0.4688267901976277,"spread":0.06736862379358205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006975306,0.0001353171,0.0002925649,0.00003510831,0.00008488718,0.00001837082,0.0002584626,0.00005867897,0.0002193157],"category_scores_gemma":[0.005024989,0.0000796186,0.00004135559,0.0001567758,0.0001208686,0.00002785403,0.00003619471,0.0001629332,0.00002079907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004607038,"about_ca_system_score_gemma":0.00003870384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001632919,"about_ca_topic_score_gemma":0.000002034374,"domain_scores_codex":[0.9987611,0.0001632267,0.0004162323,0.0001322328,0.0002988236,0.0002284555],"domain_scores_gemma":[0.9963978,0.002556922,0.0002404622,0.0003920983,0.0003395441,0.00007315593],"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":[0.00006026006,0.0001111196,0.00001158463,0.00003695503,0.00001601849,0.000006753953,0.0002284889,0.000002732792,0.0004067315,0.8995807,0.0282917,0.07124697],"study_design_scores_gemma":[0.000181224,0.0002952686,0.003840479,0.00009051844,0.00003662162,0.000003749574,0.0000648819,0.004730016,0.003402069,0.986174,0.00106445,0.0001167289],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01031685,0.00009638116,0.979349,0.002978143,0.0001455066,0.0002319695,0.0007458683,0.00005597885,0.006080303],"genre_scores_gemma":[0.1151656,0.0001481372,0.8834059,0.0008041362,0.00008361973,0.000002335008,0.00001328599,0.00001415567,0.0003628229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1048488,"threshold_uncertainty_score":0.6015744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071423894","doi":"10.1214/08-aos672","title":"Rank-based inference for bivariate extreme-value copulas","year":2009,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Estimator; Copula (linguistics); Bivariate analysis; Asymptotic distribution; Consistency (knowledge bases); Inference; Strong consistency; Marginal distribution; Limit (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.2269328032972133,"gpt":0.3426307297867081,"spread":0.1156979264894948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007284028,0.0001120064,0.0003140261,0.00007735383,0.000113337,0.00002872433,0.000233956,0.00005647057,0.00003883244],"category_scores_gemma":[0.0009859585,0.0001036933,0.00008008747,0.0001270171,0.00005819447,0.00006365527,0.00001382173,0.00008480751,0.00002687288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009601077,"about_ca_system_score_gemma":0.00004113334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001920511,"about_ca_topic_score_gemma":0.00001254634,"domain_scores_codex":[0.9989607,0.00001380061,0.0005613943,0.000184406,0.00004289963,0.0002368338],"domain_scores_gemma":[0.9988356,0.0003635063,0.0003227443,0.0003023818,0.0001350092,0.00004080559],"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":[0.00009779587,0.00007083001,0.001061979,0.0000320691,0.00001211656,3.96689e-7,0.0002324388,0.004001412,0.00002254347,0.9835453,0.002307892,0.008615212],"study_design_scores_gemma":[0.0003463386,0.0001863746,0.01241452,0.0000197408,0.000006738127,9.524727e-8,0.000008733391,0.2714173,0.0002466054,0.7104596,0.004768334,0.0001255667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03209905,0.0007174302,0.9620072,0.001893375,0.0001436878,0.0002581931,0.001867403,0.00001779084,0.0009958951],"genre_scores_gemma":[0.9690177,0.0002356608,0.029636,0.0008907435,0.00005897409,0.000007334071,0.00003693673,0.00001060217,0.0001059732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9369187,"threshold_uncertainty_score":0.4228491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031719988","doi":"10.1214/09-aos750","title":"Adjusted empirical likelihood with high-order precision","year":2010,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":84,"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; Mitacs","keywords":"Empirical likelihood; Mathematics; Likelihood function; Nonparametric statistics; Statistics; Restricted maximum likelihood; Likelihood principle; Likelihood-ratio test; Estimating equations; Parametric statistics; Econometrics; Sample size determination; Small area estimation; Maximum likelihood; Confidence interval; Quasi-maximum likelihood; Estimator","retraction":null,"screen_n_in":null,"score":{"opus":0.2125625606067208,"gpt":0.4328748447960444,"spread":0.2203122841893236,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007445785,0.0001654384,0.0003193797,0.00004108172,0.00009031172,0.00002795524,0.0003108209,0.00008614876,0.0005159089],"category_scores_gemma":[0.005932098,0.00009121493,0.00002761583,0.0002335825,0.0002936292,0.00003681049,0.00007738833,0.0003794612,0.00002689992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002892585,"about_ca_system_score_gemma":0.00009002674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004578747,"about_ca_topic_score_gemma":0.00007501719,"domain_scores_codex":[0.9985604,0.0001409588,0.0003949461,0.0001855308,0.0004253901,0.0002928044],"domain_scores_gemma":[0.9930472,0.005375887,0.0002145296,0.0005304093,0.0007155942,0.0001163986],"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":[0.0001440833,0.0002552392,0.0003987274,0.00008817941,0.00006220194,0.000009663803,0.0004926136,0.000002951275,0.0007886604,0.8587639,0.02910244,0.1098914],"study_design_scores_gemma":[0.0003227461,0.0004663641,0.01219188,0.00005084576,0.00006946037,0.000009270871,0.00008858355,0.001150871,0.003575754,0.9801096,0.001787152,0.000177422],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1337599,0.00001842811,0.8610922,0.001380777,0.0001927995,0.0002685454,0.0005847623,0.00004393658,0.002658672],"genre_scores_gemma":[0.2612453,0.00002584268,0.7381734,0.0003008265,0.0000722062,0.000009650617,0.000008220702,0.00002426163,0.0001402914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1274854,"threshold_uncertainty_score":0.7101704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104259225","doi":"10.1214/aos/1015345957","title":"A Canonical Process for Estimation of Convex Functions: The \"Invelope\" of Integrated Brownian Motion $+t^4$","year":2001,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"National Institute of Allergy and Infectious Diseases; National Science Foundation","keywords":"Mathematics; Monotone polygon; Brownian motion; Regular polygon; Limit (mathematics); Estimator; Applied mathematics; Mathematical analysis; Convex function; Mathematical optimization; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.3348386118966338,"gpt":0.4598259911638058,"spread":0.1249873792671721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009916227,0.0001080815,0.0003113633,0.00004084762,0.00007151288,0.000008613662,0.0002155394,0.00005347928,0.0001098163],"category_scores_gemma":[0.009788212,0.00006077249,0.00004861425,0.000253424,0.0003599631,0.00003740251,0.0000222145,0.0001052494,0.000001571218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008325025,"about_ca_system_score_gemma":0.0001551381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009564463,"about_ca_topic_score_gemma":0.00002643831,"domain_scores_codex":[0.9987273,0.0001439397,0.0006267005,0.0001054401,0.0002455373,0.000151075],"domain_scores_gemma":[0.9940633,0.004105275,0.0004771467,0.0002657505,0.001053916,0.00003465064],"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":[0.000295224,0.0002557918,0.000229847,0.0006888068,0.0001090315,5.428296e-7,0.001365055,0.0003518489,0.0003190272,0.8743118,0.005430057,0.116643],"study_design_scores_gemma":[0.0002806,0.0003383723,0.002148483,0.0001473314,0.0001168441,0.000004177675,0.0007132057,0.07633369,0.004922437,0.9146591,0.0002481706,0.00008761695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03639726,0.00003729123,0.9608749,0.0006127128,0.0000604758,0.0004310954,0.001218791,0.00001069041,0.000356773],"genre_scores_gemma":[0.7724768,0.00006440715,0.2270934,0.00009853277,0.00002234584,0.00004620339,0.00004170768,0.00001578569,0.0001408055],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7360795,"threshold_uncertainty_score":0.9985527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1986887417","doi":"10.1214/13-aos1129","title":"Quantile and quantile-function estimations under density ratio model","year":2013,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":53,"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":"Quantile; Mathematics; Estimator; Statistics; Econometrics; Quantile function; Representation (politics); Quantile regression; Function (biology); Probability density function; Cumulative distribution function","retraction":null,"screen_n_in":null,"score":{"opus":0.3253218028897376,"gpt":0.4266953906177025,"spread":0.1013735877279649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004047024,0.0001220633,0.0002281095,0.00003580976,0.0001516903,0.00005165171,0.0001072086,0.00004905018,0.000191128],"category_scores_gemma":[0.002086761,0.00008513831,0.00002564139,0.00008662304,0.0002183926,0.00009453161,0.00005507397,0.0001193411,0.00003164331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004661846,"about_ca_system_score_gemma":0.00004123083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001240502,"about_ca_topic_score_gemma":0.00001963281,"domain_scores_codex":[0.9990172,0.0001038752,0.0003517012,0.0001378542,0.0002108621,0.0001784495],"domain_scores_gemma":[0.996439,0.00258887,0.0001768563,0.000280206,0.0004437098,0.00007130299],"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":[0.00001147039,0.00005088188,0.00005647807,0.00005834535,0.00002664913,2.385733e-7,0.0002027022,0.0003193312,0.0005010918,0.9761809,0.01590685,0.006685079],"study_design_scores_gemma":[0.00006444563,0.00005532228,0.004279399,0.00001565384,0.00003588096,0.000001446651,0.00009777053,0.3593443,0.0003668206,0.6356627,0.000009381503,0.0000668138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05989142,0.00002928886,0.9383025,0.0007204398,0.00005057282,0.0002235752,0.0001893367,0.00002573426,0.0005671614],"genre_scores_gemma":[0.5357422,0.00004472715,0.4637128,0.00028184,0.00001544975,0.00001330171,0.000006995923,0.00001127536,0.0001714175],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4758507,"threshold_uncertainty_score":0.3471839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040079214","doi":"10.1214/10-aos862","title":"Intrinsic inference on the mean geodesic of planar shapes and tree discrimination by leaf growth","year":2011,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Mathematics; Geodesic; Computation; Euclidean space; Curvature; Principal component analysis; Consistency (knowledge bases); Landmark; Geometry; Mathematical analysis; Algorithm; Statistics; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2079470030563552,"gpt":0.3348959056202895,"spread":0.1269489025639342,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003335964,0.00008516409,0.0001526355,0.00003174652,0.00006540821,0.000008891852,0.000178467,0.00003263521,0.00008957387],"category_scores_gemma":[0.00110802,0.0000432683,0.00002045417,0.00008566954,0.0001723263,0.00003229475,0.00003505082,0.0000877209,0.000003136054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002529037,"about_ca_system_score_gemma":0.000009425635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009874176,"about_ca_topic_score_gemma":0.00002402327,"domain_scores_codex":[0.9993181,0.00009089961,0.0002405989,0.00008654854,0.0001634459,0.0001004104],"domain_scores_gemma":[0.9977286,0.001725922,0.0002198601,0.0001618298,0.0001401283,0.00002367773],"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":[0.00002404472,0.0001185892,0.0002117391,0.00004504865,0.00002631778,6.35407e-7,0.001091481,1.704733e-7,0.0001812961,0.9782898,0.01435532,0.005655507],"study_design_scores_gemma":[0.0001242017,0.0003090054,0.02804177,0.00004688248,0.00005229734,9.180666e-7,0.0005556406,0.0003049704,0.005921424,0.9645057,0.00005296885,0.00008421994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6581239,0.0001867211,0.3225504,0.003297922,0.00005903345,0.0005834041,0.001723669,0.00003735755,0.01343764],"genre_scores_gemma":[0.9894146,0.0002182926,0.01007404,0.0001927974,0.000009894897,0.000004975298,0.000009495337,0.000006624818,0.00006926361],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3312908,"threshold_uncertainty_score":0.176443,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054184868","doi":"10.1214/13-aos1143","title":"Empirical likelihood on the full parameter space","year":2013,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","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 Victoria","funders":"","keywords":"Empirical likelihood; Mathematics; Likelihood principle; Likelihood function; Parameter space; Inference; Statistics; Sample (material); Generalization; Maximum likelihood; Maximum likelihood sequence estimation; Sample size determination; Quasi-maximum likelihood; Computer science; Artificial intelligence; Estimator; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.3311022371903225,"gpt":0.4419531342249771,"spread":0.1108508970346546,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008070469,0.0001622187,0.0002658308,0.0000253051,0.0001091979,0.0000539567,0.0003828097,0.00005586859,0.001412704],"category_scores_gemma":[0.01122014,0.00007639657,0.00006055359,0.0001285777,0.0002957909,0.00002767024,0.00008408343,0.0002638076,0.0003136769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005742824,"about_ca_system_score_gemma":0.00003361238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004075673,"about_ca_topic_score_gemma":0.000004147849,"domain_scores_codex":[0.998436,0.0003447625,0.0003679589,0.0001542934,0.0003711667,0.0003258232],"domain_scores_gemma":[0.978717,0.02012292,0.0001867378,0.0005765039,0.0003080585,0.00008874253],"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":[0.00002095836,0.00009446624,0.00005175897,0.00002828179,0.00003592384,0.000001493917,0.0003768783,8.756724e-7,0.0001052893,0.7224634,0.2603258,0.01649489],"study_design_scores_gemma":[0.00007686354,0.0003343131,0.002631774,0.00003583933,0.00002722004,0.000002305855,0.000191079,0.002093822,0.001380798,0.9916397,0.001474201,0.0001120543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1278786,0.00005711404,0.8288828,0.03106553,0.0001979674,0.0007557296,0.0005304958,0.00005111114,0.01058065],"genre_scores_gemma":[0.3774872,0.00009472932,0.6165504,0.004999803,0.000133843,0.00007374552,0.000004260601,0.00004256324,0.000613443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2691764,"threshold_uncertainty_score":0.9995002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127939736","doi":"10.1214/20-aos1960","title":"Singular vector and singular subspace distribution for the matrix denoising model","year":2021,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Random Matrices and Applications","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Hong Kong University of Science and Technology; University of Toronto; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Singular value; Singular solution; Rank (graph theory); Random matrix; Subspace topology; Distribution (mathematics); Matrix (chemical analysis); Singular spectrum analysis; Singular value decomposition; Multivariate random variable; Singular function; Unit vector; Outlier; Mathematical analysis; Applied mathematics; Eigenvalues and eigenvectors; Combinatorics; Singular integral; Algorithm; Random variable; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1154349579096464,"gpt":0.3934978064602662,"spread":0.2780628485506198,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004401235,0.00009448867,0.0001724308,0.000009787501,0.0003054338,0.00006667788,0.0001271037,0.00003492961,0.000006107938],"category_scores_gemma":[0.0008556778,0.00005990036,0.00005336311,0.0001190634,0.0001018284,0.00003292997,0.00004886231,0.00006947541,0.000001027187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007550052,"about_ca_system_score_gemma":0.0000515879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001271271,"about_ca_topic_score_gemma":0.000009683596,"domain_scores_codex":[0.9992889,0.00003659784,0.0002345543,0.0001187373,0.0001594725,0.0001617333],"domain_scores_gemma":[0.9970574,0.002071023,0.0001720289,0.0003216045,0.0003456814,0.00003225715],"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":[0.00004606651,0.00006956804,0.00001038536,0.0001995474,0.00008061832,0.000001456058,0.0007193271,0.001142148,0.001948726,0.9727649,0.02005104,0.002966206],"study_design_scores_gemma":[0.0003909455,0.00002536687,0.0001227717,0.00003549873,0.0002451061,0.000007404499,0.0003097457,0.2266169,0.00664393,0.7616922,0.003796008,0.0001141115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04500965,0.00144693,0.9482383,0.004035758,0.00002668536,0.0003052142,0.0008902836,0.00001580012,0.00003143532],"genre_scores_gemma":[0.8440204,0.001066877,0.1536677,0.0001635211,0.0001195116,0.00004636281,0.0001235448,0.00003763594,0.0007544359],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7990107,"threshold_uncertainty_score":0.2442666,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2595579230","doi":"10.1214/17-aos1676","title":"Think globally, fit locally under the manifold setup: Asymptotic analysis of locally linear embedding","year":2018,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":39,"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":"University of Toronto","keywords":"Mathematics; Manifold (fluid mechanics); Embedding; Applied mathematics; Regularization (linguistics); Nonlinear dimensionality reduction; Laplace transform; Kernel (algebra); Markov chain; Mathematical analysis; Statistics; Pure mathematics; Dimensionality reduction; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.07745280808389232,"gpt":0.3689493101509729,"spread":0.2914965020670806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001797531,0.0001913089,0.00042192,0.000120337,0.0001781532,0.00008371286,0.001869495,0.00007880525,0.00005055424],"category_scores_gemma":[0.0001690985,0.0001114893,0.0001642355,0.001082859,0.0003547669,0.0001234362,0.000409894,0.0001699093,0.00001566851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001219662,"about_ca_system_score_gemma":0.0001282464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001232877,"about_ca_topic_score_gemma":0.00007866245,"domain_scores_codex":[0.9979211,0.0002998337,0.0005408539,0.0002937471,0.0006005603,0.0003438731],"domain_scores_gemma":[0.9968412,0.0008282635,0.0003887848,0.001142964,0.0007148053,0.00008398333],"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":[0.0000276863,0.00007288247,0.00002954836,0.00003018172,0.0009354065,0.000006248455,0.001907834,0.005286214,0.0001368538,0.9621399,0.006422784,0.02300447],"study_design_scores_gemma":[0.0001269202,0.0002437259,0.002537735,0.00004241396,0.0004144706,0.000005312629,0.0001121379,0.7919691,0.0009112308,0.2031276,0.0003391861,0.0001701508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002124621,0.000191412,0.9936551,0.002233869,0.0001427137,0.0001419134,0.000148155,0.00003054914,0.001331664],"genre_scores_gemma":[0.451123,0.0001161003,0.5456223,0.00279015,0.00009522362,0.000001597784,0.000005384959,0.00001285653,0.000233311],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7866829,"threshold_uncertainty_score":0.4546402,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1557964549","doi":"10.1214/07-aos522","title":"Moments of minors of Wishart matrices","year":2008,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Random Matrices and Applications","field":"Mathematics","cited_by":35,"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; National Science Foundation","keywords":"Wishart distribution; Mathematics; Estimation of covariance matrices; Scatter matrix; Matrix t-distribution; Inverse-Wishart distribution; Covariance matrix; Multivariate normal distribution; Matrix (chemical analysis); Covariance; Sample mean and sample covariance; Combinatorics; Applied mathematics; Statistics; Multivariate statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2207505105461682,"gpt":0.3968837078444125,"spread":0.1761331972982443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002028417,0.00006845298,0.000244524,0.00004468055,0.00004240725,0.000002031763,0.0002265875,0.00002324588,0.00007083983],"category_scores_gemma":[0.0001771989,0.00004741137,0.00005123037,0.0001757402,0.0001596385,0.00002800043,0.00003621013,0.00003870382,0.000005433266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001764986,"about_ca_system_score_gemma":0.00002429862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005758313,"about_ca_topic_score_gemma":0.000002646047,"domain_scores_codex":[0.9991483,0.00002496131,0.0004275525,0.00006270776,0.0002376889,0.00009880178],"domain_scores_gemma":[0.9982425,0.0007369681,0.0004847185,0.0002778033,0.0002332418,0.00002478213],"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":[0.0002207037,0.00120256,0.002777173,0.001682856,0.0004046384,0.000005217797,0.0070929,0.0001528958,0.003312861,0.5917282,0.3863032,0.005116873],"study_design_scores_gemma":[0.001590893,0.0003690664,0.01234556,0.0001577944,0.000290312,0.00001332502,0.0008544682,0.001295615,0.06947134,0.9077386,0.00556857,0.0003045157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811078,0.000371988,0.01342034,0.0002898899,0.000029266,0.0002923008,0.001155178,0.00001142256,0.003321795],"genre_scores_gemma":[0.9718457,0.001131103,0.02634324,0.00002479296,0.00002045166,0.000008093327,0.000008374061,0.00001102134,0.0006072496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3807346,"threshold_uncertainty_score":0.193338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971293584","doi":"10.1214/009053607000000479","title":"Discussion: The Dantzig selector: Statistical estimation when p is much larger than n","year":2007,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":32,"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":"Mathematics; Estimation; Statistics; Combinatorics; Applied mathematics; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.216065325410545,"gpt":0.4463648548292522,"spread":0.2302995294187072,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002865636,0.0002387313,0.0003736352,0.00005051017,0.0002913403,0.00006406807,0.0004798774,0.00008806156,0.0009350081],"category_scores_gemma":[0.006632078,0.0001052189,0.00006434436,0.000210314,0.0004635258,0.00006166543,0.000119781,0.0003405315,0.00005420535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001649941,"about_ca_system_score_gemma":0.00008805065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006434087,"about_ca_topic_score_gemma":0.00004253917,"domain_scores_codex":[0.9974712,0.0003088008,0.0007506947,0.0002459013,0.0007121886,0.000511176],"domain_scores_gemma":[0.9886172,0.009873195,0.0003380437,0.0006291468,0.0004029961,0.0001393842],"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":[0.00009093426,0.0001147189,0.0001811078,0.00009816932,0.00005894655,0.000007955272,0.002388109,0.00000168376,0.00008296222,0.8011785,0.1259248,0.06987212],"study_design_scores_gemma":[0.0001619769,0.0001657396,0.007698047,0.00005848085,0.00008795711,0.000009514456,0.0004246242,0.008195262,0.001837167,0.978915,0.002261032,0.0001851369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003796413,0.00005257338,0.9876856,0.00469864,0.0001686162,0.0003417468,0.001538227,0.00003858525,0.001679651],"genre_scores_gemma":[0.3139783,0.00004511588,0.6840759,0.001033756,0.0001370543,0.00001353117,0.00003335,0.00003905318,0.000643965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3101819,"threshold_uncertainty_score":0.9999782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011873007","doi":"10.1214/13-aos1184","title":"Inference of weighted $V$-statistics for nonstationary time series and its applications","year":2014,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Series (stratigraphy); Nonparametric statistics; Inference; Statistical inference; Mathematics; Limit (mathematics); Degenerate energy levels; Central limit theorem; Nonlinear system; Class (philosophy); Fourier transform; Periodogram; Statistics; Fourier series; Time series; Applied mathematics; Statistical physics; Mathematical analysis; Computer science; Physics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.07731272900107805,"gpt":0.2985594076842854,"spread":0.2212466786832074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004272204,0.00007881827,0.0002526277,0.0000591654,0.00009525895,0.0000111015,0.0001236455,0.00003879017,0.00002823572],"category_scores_gemma":[0.0006790193,0.00007636334,0.00002307298,0.00008992956,0.0001147537,0.00007657436,0.00003111026,0.00004745618,0.0000177419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003420821,"about_ca_system_score_gemma":0.00002362725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000291765,"about_ca_topic_score_gemma":0.000007918903,"domain_scores_codex":[0.9992132,0.00001213348,0.0004895357,0.0001320549,0.00003385215,0.0001192526],"domain_scores_gemma":[0.9982914,0.0008835142,0.0003579399,0.0001655564,0.0002715903,0.00003002552],"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":[0.00003106369,0.00002881018,0.0005171354,0.0001152913,0.00001540763,2.847995e-8,0.0002308585,0.0001021179,0.00003168752,0.9919107,0.0009925808,0.006024329],"study_design_scores_gemma":[0.0001352197,0.0001375702,0.003565751,0.0000129504,0.000009032014,3.02653e-7,0.00001893515,0.204602,0.0002719029,0.7829356,0.008219655,0.00009109966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01036092,0.0005756121,0.9765661,0.0003328387,0.0000286181,0.0002805525,0.01114915,0.000007380064,0.0006988117],"genre_scores_gemma":[0.8615823,0.001204827,0.1364119,0.0001060201,0.00004801715,0.00005092564,0.0001964604,0.00001632619,0.000383196],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8512214,"threshold_uncertainty_score":0.3114007,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971762149","doi":"10.1214/aos/996986507","title":"Maximum Bias Curves for Robust Regression with Non-elliptical Regressors","year":2001,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":28,"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":"Mathematics; Robustness (evolution); Regression; Statistics; Regression analysis; Distribution (mathematics); Omitted-variable bias; Robust regression; Econometrics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.4379254856168624,"gpt":0.4772454733798135,"spread":0.03931998776295109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008552995,0.0002245911,0.0004706998,0.00004267118,0.000144425,0.00001697292,0.0002678499,0.00006702032,0.00005713655],"category_scores_gemma":[0.003262833,0.000122877,0.00006514067,0.000155137,0.0003586122,0.00006887339,0.00005591253,0.0001736844,0.00000269287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008842225,"about_ca_system_score_gemma":0.00004813887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001102087,"about_ca_topic_score_gemma":0.00001185069,"domain_scores_codex":[0.9983948,0.0001148753,0.0004633228,0.0002440879,0.0003852143,0.0003976317],"domain_scores_gemma":[0.993358,0.00522765,0.0003259139,0.0004795026,0.000480509,0.0001284159],"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":[0.001414781,0.0004569336,0.00009023819,0.001759406,0.0001745628,0.00006452238,0.0004488638,0.0008667488,0.0001294964,0.7763808,0.1244422,0.09377153],"study_design_scores_gemma":[0.0005170092,0.0005570061,0.00006604114,0.0009085782,0.0001345999,0.00002023777,0.0001295333,0.02967881,0.0008838201,0.9638276,0.003040479,0.0002362562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008972824,0.000247244,0.9951718,0.001496805,0.00006318527,0.0005342396,0.0006458516,0.00003041849,0.0009131998],"genre_scores_gemma":[0.006514953,0.001590805,0.9897128,0.0004458123,0.00007327644,0.00004497132,0.00002661619,0.00005331394,0.001537414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1874469,"threshold_uncertainty_score":0.5010779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051362865","doi":"10.1214/aos/1016120373","title":"The density of multivariate $M$-estimates","year":2000,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Mathematics; Corollary; Multivariate statistics; Applied mathematics; Inverse; Function (biology); Density estimation; Point process; Derivative (finance); Probability density function; Statistics; Mathematical analysis; Combinatorics; Estimator; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.1222524648003014,"gpt":0.3877540269358391,"spread":0.2655015621355377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004390139,0.0001150689,0.0002642751,0.00001086078,0.0001581611,0.00001335969,0.0002888126,0.00003214354,0.0002949277],"category_scores_gemma":[0.001908463,0.00005702402,0.00005385585,0.0001222067,0.000475789,0.00002197248,0.00004487773,0.0001106806,0.00003047052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003037022,"about_ca_system_score_gemma":0.00002010046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001399895,"about_ca_topic_score_gemma":0.00001077857,"domain_scores_codex":[0.9988756,0.00008573693,0.0004234232,0.00009973723,0.0002890755,0.0002263915],"domain_scores_gemma":[0.9923213,0.006893431,0.000173347,0.0003193613,0.0002380576,0.00005447063],"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":[0.0001912451,0.0002065799,0.0001554026,0.00009517831,0.0001333892,0.000006537277,0.0005270134,0.00002129282,0.0001914391,0.7674352,0.02178998,0.2092467],"study_design_scores_gemma":[0.0001502619,0.0001269566,0.008005821,0.0000275476,0.00005354961,0.000003631298,0.00004749282,0.008071766,0.004432852,0.9771581,0.001831962,0.00009004691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.234532,0.0006075797,0.7452852,0.006111208,0.0003493087,0.0009600295,0.002831527,0.0001356018,0.009187507],"genre_scores_gemma":[0.6356119,0.0008538092,0.3602321,0.0003379926,0.0001040358,0.00001429246,0.00001600159,0.00004335223,0.002786574],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4010799,"threshold_uncertainty_score":0.3229252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134641264","doi":"10.1214/009053606000000164","title":"Strong invariance principles for sequential Bahadur–Kiefer and Vervaat error processes of long-range dependent sequences","year":2006,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Range (aeronautics); Invariance principle; Limit (mathematics); Limiting; Process (computing); Large deviations theory; Applied mathematics; Statistical physics; Statistics; Mathematical analysis; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1583858325860961,"gpt":0.3098544299166485,"spread":0.1514685973305524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002993778,0.0001095367,0.0002859959,0.00005332009,0.0001046417,0.00002665388,0.0002263346,0.0000478597,0.00001662705],"category_scores_gemma":[0.0003070503,0.00009867499,0.00003288512,0.0001470366,0.000202721,0.00009440141,0.00005091616,0.00005163328,0.000004215018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008606556,"about_ca_system_score_gemma":0.00007513991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006334704,"about_ca_topic_score_gemma":0.0004410607,"domain_scores_codex":[0.9989898,0.000003468695,0.0005587718,0.0002059821,0.00005584474,0.0001861716],"domain_scores_gemma":[0.9987631,0.0002383599,0.0005486202,0.0001819949,0.0002400038,0.00002791089],"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":[0.00003821247,0.00006698951,0.004010334,0.0004232756,0.00002596555,5.283034e-7,0.0001502009,0.0003156194,0.00002276045,0.9941849,0.000192925,0.0005683096],"study_design_scores_gemma":[0.0004630099,0.000190674,0.05811713,0.00006528048,0.00003523958,0.000005073525,0.0001036724,0.00274286,0.001593046,0.9347345,0.001710256,0.0002392958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04320136,0.003198763,0.9471619,0.000570589,0.00006210295,0.0003892921,0.00474284,0.000009289184,0.0006638746],"genre_scores_gemma":[0.9866513,0.0002962036,0.01262194,0.00006083393,0.00008317409,0.00008082992,0.00004577536,0.00001387467,0.0001460687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9434499,"threshold_uncertainty_score":0.4023849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4307356996","doi":"10.1214/22-aos2215","title":"A study of orthogonal array-based designs under a broad class of space-filling criteria","year":2022,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":18,"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":"Orthogonal array; Orthogonality; Mathematics; Partition (number theory); Class (philosophy); Space (punctuation); Orthogonal basis; Computer experiment; Orthogonal transformation; Design of experiments; Algorithm; Combinatorics; Geometry; Computer science; Statistics; Taguchi methods; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5178728409424104,"gpt":0.5247503710326535,"spread":0.006877530090243167,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006114163,0.0001608094,0.0005468748,0.0002445795,0.0001741547,0.00003433788,0.0009811302,0.00002799856,0.001000214],"category_scores_gemma":[0.001646308,0.000116668,0.0001081422,0.000860403,0.0003180234,0.00007193448,0.0002338867,0.0001770477,0.000004881406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001751782,"about_ca_system_score_gemma":0.0002022969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009796396,"about_ca_topic_score_gemma":0.00001098355,"domain_scores_codex":[0.9943187,0.001970488,0.001080071,0.0003061315,0.002085937,0.0002387004],"domain_scores_gemma":[0.9925161,0.005176709,0.0008889165,0.0007103641,0.0006369301,0.00007098236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004322606,0.006910407,0.004967376,0.0001040278,0.0005057586,0.00006142569,0.03242025,0.1728299,0.6585302,0.08171975,0.02438611,0.01324214],"study_design_scores_gemma":[0.004388446,0.01671072,0.03013539,0.00009289961,0.0002654539,0.00002222935,0.1815473,0.06240736,0.4162118,0.2858886,0.001358397,0.0009714519],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5409648,0.0001465205,0.4565025,0.000296863,0.0001692447,0.0004286202,0.0009187717,0.000008953834,0.0005637045],"genre_scores_gemma":[0.8687698,0.000004276039,0.1308823,0.0001831466,0.00001320178,0.00001454019,0.000005023554,0.00001668214,0.0001110464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.327805,"threshold_uncertainty_score":0.999913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3049037101","doi":"10.1214/19-aos1894","title":"Estimation and inference for precision matrices of nonstationary time series","year":2020,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Series (stratigraphy); Estimator; Applied mathematics; Cholesky decomposition; Inference; Nonlinear system; Algorithm; Statistics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2352570567788969,"gpt":0.4420139439186695,"spread":0.2067568871397726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003613625,0.00008175317,0.0002270163,0.00002273306,0.00004835245,0.00001269281,0.0001127555,0.00002917693,0.00005540087],"category_scores_gemma":[0.009978381,0.00005745403,0.00001984367,0.00009687088,0.0001660747,0.00007049593,0.0000474213,0.00004516094,0.000002787762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001521935,"about_ca_system_score_gemma":0.00003604354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005073081,"about_ca_topic_score_gemma":5.172834e-7,"domain_scores_codex":[0.9992081,0.00006851201,0.0003652793,0.00009789534,0.0001694038,0.00009080134],"domain_scores_gemma":[0.9916061,0.007646901,0.0002693319,0.0001082541,0.0003242937,0.00004511134],"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":[0.0001875962,0.00003506134,0.00005008599,0.0006209716,0.00002695683,4.104772e-7,0.001167162,0.00006061575,0.0007096386,0.8560888,0.006497977,0.1345547],"study_design_scores_gemma":[0.0001228329,0.0004270274,0.0006803559,0.00006374555,0.00003898235,8.488767e-7,0.00009859737,0.09962454,0.003795326,0.8949808,0.00009956172,0.00006732545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01056072,0.00007940829,0.9860917,0.001063414,0.00001580866,0.0002603982,0.001681425,0.00001180917,0.0002352666],"genre_scores_gemma":[0.1114905,0.0001459371,0.8881804,0.0001005879,0.00001581657,0.000009750765,0.00001757017,0.000008618356,0.00003076961],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1344874,"threshold_uncertainty_score":0.998361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1593939745","doi":"10.1214/aos/1009210688","title":"Weak convergence of the empirical process of residuals in linear models with many parameters","year":2001,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Simon Fraser University","funders":"","keywords":"Mathematics; Residual; Statistics; Least-squares function approximation; Applied mathematics; Bounded function; Mathematical analysis; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.4139628941752223,"gpt":0.4604917540459453,"spread":0.04652885987072308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007961497,0.0001274697,0.0004074895,0.00004089686,0.00002853914,0.000004239512,0.0004038578,0.0000501763,0.00004095193],"category_scores_gemma":[0.002524502,0.00006683818,0.00003711057,0.0003514982,0.0005322528,0.0000392248,0.00006233243,0.0001614282,6.83479e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004653634,"about_ca_system_score_gemma":0.0001011436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007485398,"about_ca_topic_score_gemma":0.00002453294,"domain_scores_codex":[0.9983565,0.0002299588,0.0006365615,0.0001369451,0.0004335366,0.0002064976],"domain_scores_gemma":[0.9955412,0.003122176,0.0004421952,0.0004222047,0.0004304253,0.00004184901],"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":[0.0005090051,0.0004486554,0.009676835,0.0008098872,0.00009698814,0.00000745989,0.004561811,0.00351265,0.0002185136,0.9740727,0.002866761,0.003218719],"study_design_scores_gemma":[0.0002364504,0.0002613465,0.006215422,0.0002724482,0.00004446931,0.000004238246,0.0006869978,0.02772255,0.007266833,0.9571698,0.00001681235,0.0001026186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5269866,0.00004465602,0.4705763,0.000504354,0.00003700467,0.0002978168,0.0004007882,0.000006162441,0.001146311],"genre_scores_gemma":[0.7444467,0.0001301061,0.2552113,0.0001003676,0.000006601472,0.00000849662,0.000001082591,0.00001306702,0.00008225499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2174601,"threshold_uncertainty_score":0.3022247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4360879278","doi":"10.1214/22-aos2246","title":"Sharp global convergence guarantees for iterative nonconvex optimization with random data","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":16,"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":"Mathematics; Initialization; Subgradient method; Mathematical optimization; Sequence (biology); Rate of convergence; Gaussian; Applied mathematics; Algorithm; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1322722702975442,"gpt":0.3511768969101887,"spread":0.2189046266126445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001428039,0.00008837911,0.0001418692,0.00002097985,0.00004705965,0.00002256707,0.0002678658,0.00002259592,0.00001280845],"category_scores_gemma":[0.0001288955,0.00006191157,0.00001328334,0.0001647833,0.00006686349,0.00008290869,0.0000502094,0.00003568345,0.000004207527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003790753,"about_ca_system_score_gemma":0.00001555609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001410082,"about_ca_topic_score_gemma":0.0000100096,"domain_scores_codex":[0.9994963,0.00001705183,0.0001451519,0.0001021618,0.00010751,0.0001318292],"domain_scores_gemma":[0.9990942,0.0002344452,0.00004864627,0.0003287116,0.0002760066,0.00001797598],"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":[0.0003140174,0.0000164751,0.00009487729,0.00009019482,0.0002142028,0.000009116247,0.0004273311,0.6116167,0.0002377741,0.007436089,0.3748192,0.004724008],"study_design_scores_gemma":[0.0003212192,0.00006807104,0.0001695915,0.00006700199,0.00002673154,0.000001434428,0.00006809087,0.9896573,0.004373812,0.003911112,0.001242091,0.00009353481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002341354,0.0001268445,0.9936303,0.0001335478,0.0001095022,0.0002434831,0.002945805,0.0002109616,0.0002581788],"genre_scores_gemma":[0.8635741,0.00128378,0.1337,0.0001967112,0.0001227198,0.00002756776,0.0009928545,0.00003693416,0.00006531445],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8612328,"threshold_uncertainty_score":0.252468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093380516","doi":"10.1214/20-aos1957","title":"Multiple block sizes and overlapping blocks for multivariate time series extremes","year":2021,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","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 Toronto","funders":"","keywords":"Maxima; Mathematics; Estimator; Extreme value theory; Block (permutation group theory); Series (stratigraphy); Multivariate statistics; Disjoint sets; Range (aeronautics); Applied mathematics; Block size; Asymptotic distribution; Statistics; Combinatorics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.09808045666761966,"gpt":0.2838336576436338,"spread":0.1857532009760142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003856887,0.0001040642,0.0003180995,0.00003672995,0.0001520179,0.00004010356,0.00009239044,0.00005021997,0.00003987567],"category_scores_gemma":[0.001450592,0.0001009504,0.00005433814,0.00007827529,0.00008047449,0.00009022711,0.00006646494,0.00006651099,0.000008870886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005316982,"about_ca_system_score_gemma":0.00002517823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001527199,"about_ca_topic_score_gemma":0.0000442858,"domain_scores_codex":[0.9991304,0.00001250434,0.00042789,0.0002042753,0.00003044226,0.0001945077],"domain_scores_gemma":[0.9988399,0.0005413094,0.0002191851,0.0002043258,0.0001608035,0.00003449828],"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":[0.0005897094,0.0003982477,0.03066578,0.0006811041,0.0004963591,0.00001290908,0.00931552,0.003263572,0.005893137,0.9079686,0.01561208,0.02510293],"study_design_scores_gemma":[0.00110801,0.0001823664,0.03811762,0.00009095128,0.00003277653,0.000006155474,0.0003977631,0.3820396,0.003779856,0.5384517,0.03532969,0.0004634511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7344848,0.009250707,0.2422305,0.002847159,0.000315647,0.0005093451,0.008907278,0.00004445351,0.001410106],"genre_scores_gemma":[0.954567,0.001193588,0.04231825,0.0001796965,0.00008207728,0.0000118382,0.00003867641,0.00001998836,0.001588847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3787761,"threshold_uncertainty_score":0.4116639,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3203906057","doi":"10.1214/20-aos2026","title":"On extended admissible procedures and their nonstandard Bayes risk","year":2021,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":15,"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; Simons Institute for the Theory of Computing, University of California Berkeley; U.S. Air Force","keywords":"Mathematics; Equivalence (formal languages); Bayes' theorem; Nonparametric statistics; Generality; Decision theory; Applied mathematics; Statistical inference; Decision problem; Calculus (dental); Bayesian probability; Discrete mathematics; Statistics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.09026552470322853,"gpt":0.29352432014077,"spread":0.2032587954375415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002158112,0.00008529684,0.0001271451,0.0000297243,0.000467575,0.00006562162,0.0001211925,0.00001345075,0.0005297561],"category_scores_gemma":[0.0003717901,0.00005219202,0.00002640387,0.00002575289,0.000696987,0.00006949725,0.00003142726,0.00009020769,0.000008859623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000033356,"about_ca_system_score_gemma":0.0001113799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002455181,"about_ca_topic_score_gemma":0.0002430253,"domain_scores_codex":[0.9994291,0.00004505965,0.0001317532,0.0001256471,0.0001461409,0.0001223173],"domain_scores_gemma":[0.9991794,0.0002962233,0.00009866591,0.0001585108,0.0002158622,0.00005133891],"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":[0.00006332224,0.00006098295,0.000005455867,0.00003967557,0.00002300226,0.000004693298,0.01652793,0.000005988564,0.0000827922,0.9404851,0.03457325,0.008127841],"study_design_scores_gemma":[0.0001472975,0.0003185713,0.0005073777,0.00009365351,0.00001832349,0.000004372961,0.00329597,0.0001144389,0.002280583,0.9239142,0.06917067,0.0001345453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2693208,0.01259202,0.005118439,0.01619585,0.001270831,0.0005620033,0.01733037,0.0001618988,0.6774478],"genre_scores_gemma":[0.9963195,0.0007927507,0.0003495378,0.0008043018,0.0001018892,0.000002558511,0.00000647867,0.000006586147,0.00161638],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7269987,"threshold_uncertainty_score":0.5800458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3032483209","doi":"10.1214/19-aos1836","title":"Inference for Archimax copulas","year":2020,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Lyon; Agence Nationale de la Recherche","keywords":"Tail dependence; Copula (linguistics); Estimator; Nonparametric statistics; Maxima; Mathematics; Inference; Parametric statistics; Extreme value theory; Applied mathematics; Econometrics; Statistical physics; Statistics; Computer science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.0989639609323345,"gpt":0.3443577484987851,"spread":0.2453937875664506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001349355,0.00004926865,0.000100557,0.000004954425,0.00006382748,0.000004332926,0.0001924356,0.0000182199,0.000699334],"category_scores_gemma":[0.0003377775,0.00003403874,0.00003116539,0.00008813756,0.0002191759,0.00002753051,0.0000650571,0.0000486196,0.000150992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000188938,"about_ca_system_score_gemma":0.000005634162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005532713,"about_ca_topic_score_gemma":0.0000382931,"domain_scores_codex":[0.9995416,0.00002775955,0.0001250936,0.00008997632,0.00009837627,0.0001171443],"domain_scores_gemma":[0.9994558,0.0003150095,0.0000623758,0.0001071673,0.00001122301,0.00004843089],"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":[0.0006963289,0.0002538209,0.07374556,0.0001360722,0.0003362512,0.00001626529,0.0110732,0.044805,0.006330537,0.1368223,0.6307216,0.09506299],"study_design_scores_gemma":[0.0008255787,0.001275374,0.06656405,0.00001411456,0.0002712469,0.000002354238,0.0002951623,0.2950793,0.01448639,0.47897,0.1416817,0.0005347242],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.178219,0.00006404973,0.7911311,0.02111203,0.00004601752,0.0002777803,0.0006942847,0.00002709264,0.008428732],"genre_scores_gemma":[0.9878772,0.00004206103,0.008859501,0.003046301,0.00002142248,0.000004793824,0.00001435845,0.000003847265,0.0001304874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8096583,"threshold_uncertainty_score":0.7657217,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133822646","doi":"10.1214/009053607000000794","title":"High breakdown point robust regression with censored data","year":2008,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Agencia Nacional de Promoción Científica y Tecnológica; Natural Sciences and Engineering Research Council of Canada; Universidad de Buenos Aires; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Estimator; Outlier; Robust regression; Bounded function; Linear regression; M-estimator; Robust statistics; Influence function; Censored regression model","retraction":null,"screen_n_in":null,"score":{"opus":0.3818418898554746,"gpt":0.4502328539103301,"spread":0.06839096405485551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005426136,0.000193712,0.0004041316,0.00003405953,0.0001876976,0.00001019038,0.0005372118,0.00005018748,0.0000871638],"category_scores_gemma":[0.001922161,0.0001051492,0.00002353716,0.0001260563,0.0004128321,0.0001183633,0.0002148677,0.0001910254,0.000004649113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006801674,"about_ca_system_score_gemma":0.00005950344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007524843,"about_ca_topic_score_gemma":0.00001994649,"domain_scores_codex":[0.9984164,0.0001599619,0.0004180494,0.0002821407,0.0004237457,0.0002996887],"domain_scores_gemma":[0.9956042,0.002425771,0.000317107,0.001233902,0.0003149383,0.0001041507],"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":[0.0003603911,0.0002146768,0.00002044674,0.0001226829,0.0001051914,0.0001065813,0.0005835188,0.0005817793,0.0001320512,0.855537,0.1271667,0.01506899],"study_design_scores_gemma":[0.0005367281,0.0002926496,0.0003939461,0.0001479504,0.00009195042,0.00008403057,0.0001578576,0.01219984,0.001398684,0.9833482,0.001093716,0.0002544392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002706317,0.00007168627,0.9922324,0.0008263421,0.00005463415,0.0002142907,0.003450348,0.00003744824,0.0004065171],"genre_scores_gemma":[0.0395806,0.0004314832,0.9589996,0.0002067591,0.00006269464,0.000005503127,0.0001163191,0.00003738051,0.0005596312],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1278112,"threshold_uncertainty_score":0.4287861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066935960","doi":"10.1214/aos/1079120127","title":"Three papers on boosting: an introduction","year":2004,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Boosting (machine learning); AdaBoost; Artificial intelligence; Mathematics; Machine learning; Learnability; Probably approximately correct learning; Generalization; Computational learning theory; Gradient boosting; Generalization error; Algorithm; Computer science; Classifier (UML); Artificial neural network; Unsupervised learning","retraction":null,"screen_n_in":null,"score":{"opus":0.05352995986453116,"gpt":0.3204967371722752,"spread":0.266966777307744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003295477,0.00006997392,0.00008036599,0.00003154645,0.0001123603,0.00004125826,0.0004085994,0.00001671234,0.00001131966],"category_scores_gemma":[0.0002042513,0.00004802684,0.00001760568,0.0001213084,0.00005575857,0.00007562512,0.00004717972,0.0001315528,0.00001788042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005125132,"about_ca_system_score_gemma":0.00002779087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007773897,"about_ca_topic_score_gemma":0.0000160857,"domain_scores_codex":[0.999347,0.00003301306,0.0001237212,0.0001532666,0.0002060607,0.0001369136],"domain_scores_gemma":[0.9992912,0.00009284286,0.00009013079,0.0004050988,0.00007948246,0.0000412875],"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":[0.000008444697,0.00006528801,0.00002749813,0.00000686282,0.000009795582,0.000003861587,0.0006157192,0.01391167,0.000240528,0.7868009,0.002808747,0.1955007],"study_design_scores_gemma":[0.00076399,0.003018793,0.03541538,0.00005553366,0.00002056091,0.0000376477,0.0001583507,0.1134815,0.007247615,0.8105937,0.02869428,0.0005125724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0134925,0.00002497115,0.9624435,0.02245852,0.0003003053,0.00006394987,0.00001668708,0.00007752562,0.001122005],"genre_scores_gemma":[0.7999135,0.00003097179,0.1978996,0.00134448,0.0006257353,0.000002781444,0.00001298801,0.00001256773,0.0001574086],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.786421,"threshold_uncertainty_score":0.1958477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2302323532","doi":"10.1214/18-aos1710","title":"Approximating faces of marginal polytopes in discrete hierarchical models","year":2019,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polytope; Dimension (graph theory); Inference; Boundary (topology); Face (sociological concept); Marginal likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.08220102202442651,"gpt":0.3216365608593375,"spread":0.239435538834911,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005313798,0.00008167017,0.0002019244,0.00005533535,0.00002303485,0.00002711221,0.0006534863,0.00002848685,0.00000670054],"category_scores_gemma":[0.00005546702,0.00005698095,0.00002565924,0.0001634539,0.00009096324,0.000161309,0.0001638755,0.0001401757,0.000005085085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002750046,"about_ca_system_score_gemma":0.0000529946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009782367,"about_ca_topic_score_gemma":0.000004105282,"domain_scores_codex":[0.9990035,0.00007815902,0.0003297817,0.0001471329,0.0002476032,0.0001937695],"domain_scores_gemma":[0.9991028,0.0002844294,0.0001530209,0.0003342708,0.00009322891,0.00003225105],"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":[0.00001430492,0.00002843934,0.0003736679,0.00006467179,0.000008727074,0.000001268925,0.00135555,0.01333667,0.0005280893,0.9671904,0.00009135282,0.01700688],"study_design_scores_gemma":[0.00006717059,0.00006785809,0.0008424512,0.00005852623,0.000001478242,0.000001175747,0.00005100888,0.6788802,0.001120294,0.3188461,0.00000679194,0.00005700028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1015166,0.0000977919,0.8962905,0.0006983983,0.00003178728,0.0000794311,0.00004955069,0.00001064343,0.001225292],"genre_scores_gemma":[0.8505696,0.00004631543,0.1492111,0.00009119436,0.000006300344,0.000001833298,0.000001844447,0.000003763801,0.00006798864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7490531,"threshold_uncertainty_score":0.2323616,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4307446720","doi":"10.1214/22-aos2203","title":"Asymptotic analysis of synchrosqueezing transform—toward statistical inference with nonlinear-type time-frequency analysis","year":2022,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Gaussian; Nonlinear system; Statistical inference; Random variable; Central limit theorem; Inference; Series (stratigraphy); Applied mathematics; Statistics; Statistical hypothesis testing; Normal distribution; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.029312804191754,"gpt":0.3263515417794092,"spread":0.2970387375876551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005730062,0.0002246487,0.0007569112,0.0006063134,0.00009112809,0.00002010063,0.00047495,0.0000388765,0.000756209],"category_scores_gemma":[0.0002225823,0.0001790122,0.0001410138,0.003204735,0.0001715827,0.00006636012,0.00006561291,0.0002985281,0.000003790547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003855362,"about_ca_system_score_gemma":0.00006826672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003626118,"about_ca_topic_score_gemma":0.0001294543,"domain_scores_codex":[0.9981299,0.0001392554,0.0006274048,0.0002039026,0.0006010814,0.0002984398],"domain_scores_gemma":[0.9977821,0.001179612,0.0001763218,0.0004957629,0.000288586,0.00007768817],"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":[0.0001399515,0.0003871626,0.02451729,0.000437981,0.0185995,0.00004434042,0.002247206,0.9194872,0.001297797,0.02070941,0.002931338,0.009200804],"study_design_scores_gemma":[0.0001736189,0.0006277653,0.02778621,0.00002334581,0.007708118,0.000002267729,0.000114642,0.9560456,0.003151355,0.003838275,0.0001605788,0.0003682573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1450292,0.0002677873,0.8435828,0.0001851578,0.00003666068,0.0003550634,0.00934734,0.0002905809,0.0009054522],"genre_scores_gemma":[0.94678,0.0002413688,0.05230701,0.00005325702,0.00000933442,0.00003054639,0.0005250293,0.00004018564,0.00001330389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8017508,"threshold_uncertainty_score":0.8279958,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079299242","doi":"10.1214/aos/1079120135","title":"On the forward and backward algorithms of projection pursuit","year":2004,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Optical Sensing Technologies","field":"Physics and Astronomy","cited_by":6,"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":"Projection pursuit; Mathematics; Projection (relational algebra); Context (archaeology); Algorithm; Discriminant; Nonparametric statistics; Block (permutation group theory); Artificial intelligence; Statistics; Combinatorics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05702103796346973,"gpt":0.3234504554417389,"spread":0.2664294174782691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001115271,0.00006320122,0.000101452,0.00001564699,0.00005659452,0.000008819631,0.0001123372,0.00001625193,0.000009189496],"category_scores_gemma":[0.0001021787,0.00003427566,0.00002035238,0.00007461535,0.0002714188,0.00002161085,0.00004924188,0.0000926986,0.000002921561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003197921,"about_ca_system_score_gemma":0.00001308997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005794866,"about_ca_topic_score_gemma":0.000001460597,"domain_scores_codex":[0.9995787,0.00001247762,0.0001228712,0.00006898434,0.0001152681,0.000101735],"domain_scores_gemma":[0.999323,0.0003029834,0.0001004428,0.0001740665,0.00008795412,0.0000115421],"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":[0.00001683,0.00003859256,0.00005149798,0.00000598184,0.00003132506,2.185907e-7,0.0001249913,0.00037398,0.0002495629,0.9316539,0.0007017091,0.06675143],"study_design_scores_gemma":[0.0001165047,0.0001895042,0.0007359799,0.00002658769,0.00001307147,3.278439e-7,0.0003710901,0.0004251203,0.03020013,0.9676303,0.0002433139,0.00004804936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2832137,0.00004506569,0.708196,0.005899654,0.00006041898,0.0003271904,0.0003454561,0.00003277457,0.001879681],"genre_scores_gemma":[0.968722,0.0000221255,0.0311297,0.00005734559,0.00002084504,0.000003202609,0.000003631185,0.000006423531,0.0000347046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6855083,"threshold_uncertainty_score":0.1397721,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3118438270","doi":"10.1214/23-aos2315","title":"Relaxing the i.i.d. assumption: Adaptively minimax optimal regret via root-entropic regularization","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Regret; Minimax; Mathematics; Mathematical optimization; Regularization (linguistics); Entropy (arrow of time); Adversarial system; Computer science; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.3214253860286645,"gpt":0.4722292110110216,"spread":0.1508038249823571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00399619,0.0001507093,0.0002631421,0.0002094887,0.0004780352,0.0001670131,0.001205576,0.00006638638,0.0002424743],"category_scores_gemma":[0.007074946,0.00008143314,0.00007952615,0.001634909,0.0005279714,0.0002612623,0.0003434772,0.0002871674,0.0005294697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000221613,"about_ca_system_score_gemma":0.00009412037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001622301,"about_ca_topic_score_gemma":0.00002069151,"domain_scores_codex":[0.9957457,0.0005067955,0.0006784822,0.0003440525,0.002297171,0.0004278486],"domain_scores_gemma":[0.9926569,0.004838029,0.0004380071,0.0008413785,0.001145139,0.0000804996],"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":[0.0005077708,0.0001244015,0.001478806,0.00003899744,0.000213215,0.000113814,0.005397922,0.09701305,0.001443783,0.06985162,0.4522492,0.3715675],"study_design_scores_gemma":[0.0005076634,0.0003981547,0.09779119,0.00005273684,0.00003157512,0.00002061242,0.002496164,0.4056778,0.002779147,0.4565051,0.03343838,0.0003014227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01007596,0.0001982746,0.9800175,0.008340136,0.0002500227,0.0003420785,0.0003429041,0.00005401528,0.0003790429],"genre_scores_gemma":[0.924117,0.0008707478,0.04112681,0.000422012,0.0006813922,0.00006743817,0.000146734,0.00008510833,0.03248273],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9388908,"threshold_uncertainty_score":0.8469883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404603191","doi":"10.1214/24-aos2434","title":"On the existence of powerful p-values and e-values for composite hypotheses","year":2024,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Composite number; Mathematics; Statistics; Psychology; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1020206208146769,"gpt":0.3544260630360375,"spread":0.2524054422213606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002643008,0.00006288054,0.00009425456,0.00001820517,0.00008606645,0.00006625189,0.0004016084,0.00001166344,0.000002780448],"category_scores_gemma":[0.00006817436,0.00003261554,0.00002453721,0.0001175988,0.0001945386,0.00004669634,0.00007683514,0.00004958191,0.000002901715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001256409,"about_ca_system_score_gemma":0.00001355817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007204615,"about_ca_topic_score_gemma":7.021849e-7,"domain_scores_codex":[0.9994816,0.00003281897,0.0001467025,0.0001175523,0.0001245821,0.00009675274],"domain_scores_gemma":[0.9967948,0.002752815,0.00006335771,0.0002800782,0.00009029107,0.00001865354],"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":[0.000006204478,0.00001564839,0.00000298798,0.00003571757,0.00001597167,4.652079e-7,0.0004196579,0.0001073132,0.0006288295,0.958859,0.02610979,0.01379836],"study_design_scores_gemma":[0.00002875266,0.000190771,0.0005458658,0.00009573848,0.00001116309,0.000002454128,0.00004472924,0.08733535,0.00685616,0.9030637,0.001768578,0.00005677166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09091081,0.00222392,0.8871565,0.01722273,0.0001607405,0.0004892084,0.000537113,0.00005209245,0.001246921],"genre_scores_gemma":[0.9738038,0.000508301,0.02462534,0.000685077,0.00003681235,0.00001226794,0.000002009775,0.000006747664,0.0003195961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.882893,"threshold_uncertainty_score":0.1330023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312072439","doi":"10.1214/22-aos2229","title":"Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations","year":2022,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Bayesian Methods and Mixture Models","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":"University of Toronto","funders":"","keywords":"Mathematics; Estimator; Minimax; Applied mathematics; Context (archaeology); Matrix (chemical analysis); Combinatorics; Multinomial distribution; Matrix norm; Statistics; Eigenvalues and eigenvectors; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.06472341957351041,"gpt":0.3489276257576649,"spread":0.2842042061841545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003762445,0.00006648245,0.0001319836,0.00005973284,0.0001313824,0.00001799536,0.0003126458,0.00001428711,0.000005632356],"category_scores_gemma":[0.00004810769,0.00005896505,0.00001965792,0.0003638421,0.00002522508,0.0001115369,0.0001946242,0.00008017996,5.312359e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002171907,"about_ca_system_score_gemma":0.00004919549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004853456,"about_ca_topic_score_gemma":0.00002989869,"domain_scores_codex":[0.9991515,0.0001036839,0.0002778475,0.0001512677,0.0001833707,0.0001322779],"domain_scores_gemma":[0.9992439,0.000191225,0.0001091486,0.000313856,0.00009367025,0.00004819825],"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":[0.000002783563,0.00004508933,0.00001170148,0.00001981763,0.000005647339,4.999398e-7,0.0007410827,0.02280748,0.00007549208,0.9376302,0.0001501555,0.03851008],"study_design_scores_gemma":[0.0000863304,0.00004921125,0.0008732511,0.00001052138,0.000007326214,0.000001262995,0.00003563943,0.3881383,0.0005314849,0.6098167,0.0003880428,0.00006190248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005911399,0.0002482494,0.9902484,0.002720011,0.0000280677,0.0003524593,0.0003658603,0.00000886659,0.0001167321],"genre_scores_gemma":[0.7178592,0.00004206205,0.2818373,0.00008593012,0.000005316806,0.0001006308,0.00001640998,0.000002587723,0.0000505249],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7119478,"threshold_uncertainty_score":0.2404525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403142669","doi":"10.1214/24-aos2374","title":"Optimal estimation of Schatten norms of a rectangular matrix","year":2024,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Point processes and geometric inequalities","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":"Safran Electronics (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Estimation; Matrix (chemical analysis); Mathematics; Statistics; Applied mathematics; Economics; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.1193557613056694,"gpt":0.4155716114297706,"spread":0.2962158501241012,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000773722,0.00009066591,0.0002760923,0.0001628632,0.00002267108,0.00001399019,0.0001724407,0.00003990084,0.00008502744],"category_scores_gemma":[0.001443013,0.00005997111,0.00006140186,0.0004313488,0.0001161343,0.00007772393,0.0000492205,0.00007821372,0.000005641218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004782523,"about_ca_system_score_gemma":0.00006641789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005517133,"about_ca_topic_score_gemma":0.000001928794,"domain_scores_codex":[0.9989248,0.00003328482,0.0005126712,0.00008237041,0.0003154743,0.0001313796],"domain_scores_gemma":[0.9978713,0.00133125,0.0002450242,0.0002190242,0.0003125092,0.00002088341],"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":[0.00005527566,0.00008450821,0.000009506049,0.005060398,0.0001788572,0.000005320515,0.003577661,0.001296239,0.0003407786,0.9659507,0.01102205,0.01241868],"study_design_scores_gemma":[0.0001410025,0.0003530014,0.00008770506,0.0005650152,0.0001470344,0.000009961495,0.001205056,0.0489325,0.03079785,0.9172061,0.0004160721,0.0001386937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3153132,0.002771848,0.6780643,0.0006812199,0.0001326636,0.0002242,0.001731128,0.00004160609,0.001039862],"genre_scores_gemma":[0.8756041,0.0003210928,0.1233436,0.00001740911,0.00003314624,0.000004496407,0.00001894925,0.00001819316,0.000639049],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5602909,"threshold_uncertainty_score":0.2445551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7081950268","doi":"10.1214/25-aos2518","title":"Optimal vintage factor analysis with deflation varimax","year":2025,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":1,"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":"Vintage; Deflation; Varimax rotation; Stability (learning theory); Factor (programming language)","retraction":null,"screen_n_in":null,"score":{"opus":0.04031880077168957,"gpt":0.3033544768350438,"spread":0.2630356760633542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001683139,0.00006769885,0.0001289497,0.00005931547,0.00007489128,0.00003755648,0.0004089001,0.0000236284,0.00003669328],"category_scores_gemma":[0.0001119769,0.00004387064,0.00003178424,0.0005772998,0.00006239794,0.00005997518,0.0001020381,0.00006447057,0.000003110245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003743912,"about_ca_system_score_gemma":0.00004552049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003218549,"about_ca_topic_score_gemma":0.000007971828,"domain_scores_codex":[0.99944,0.0000322174,0.0001435003,0.0001317178,0.0001292686,0.00012331],"domain_scores_gemma":[0.9990515,0.0002404789,0.0001022036,0.0003567802,0.000228328,0.00002071131],"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":[0.00006932686,0.0001370608,0.009985598,0.0001431559,0.001441187,0.00002196676,0.002064196,0.1063819,0.001135358,0.8421723,0.01044512,0.02600275],"study_design_scores_gemma":[0.0003774079,0.0002278955,0.1853642,0.00005254729,0.0003871761,0.000004405726,0.000229553,0.6840457,0.03215472,0.0869569,0.009829365,0.0003702122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01115945,0.000025489,0.9801321,0.002309401,0.00002119681,0.00004442439,0.0000434369,0.00002065744,0.006243833],"genre_scores_gemma":[0.9215596,0.00001181048,0.07684631,0.0002361579,0.000006560265,0.000002076513,0.00001009984,6.878842e-7,0.001326706],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9104002,"threshold_uncertainty_score":0.1788993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401499779","doi":"10.1214/24-aos2382","title":"Change acceleration and detection","year":2024,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Change detection; Acceleration; Computer science; Computation; False alarm; Point (geometry); Markov process; Algorithm; Stopping time; Mathematical optimization; Mathematics; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5681217268817803,"gpt":0.529184183419226,"spread":0.03893754346255429,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008810689,0.0000634165,0.0001045316,0.00007974673,0.00009886569,0.0001640079,0.0001517543,0.00002311184,0.00003813824],"category_scores_gemma":[0.002648778,0.00003844761,0.00001394217,0.0003004704,0.0001212464,0.0002772911,0.00005582755,0.00009359644,0.00004007725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004750116,"about_ca_system_score_gemma":0.00001266165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000148303,"about_ca_topic_score_gemma":0.00001607845,"domain_scores_codex":[0.9988995,0.00005495043,0.0002765624,0.0001688511,0.0004890113,0.00011117],"domain_scores_gemma":[0.996932,0.002540701,0.00006910008,0.0001572277,0.0002611593,0.00003977731],"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":[0.00001253471,0.000004812225,0.00004569739,0.00002560863,0.000006301707,0.000004761553,0.0007145446,0.00001889764,0.000501718,0.06322747,0.001075539,0.9343621],"study_design_scores_gemma":[0.00003878147,0.00009298079,0.007118448,0.00003023967,0.00001059735,0.000006499089,0.0002970878,0.03975141,0.006186624,0.9380611,0.008326487,0.00007980855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01385897,0.001214571,0.9827775,0.001052145,0.0003941318,0.0001091108,0.0001894728,0.0000290267,0.0003750978],"genre_scores_gemma":[0.9927323,0.0002480441,0.006540352,0.00009772597,0.000169454,0.000009370772,0.000001727443,0.000007330923,0.0001937261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9788733,"threshold_uncertainty_score":0.3171026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386035721","doi":"10.1214/23-aos2284","title":"Pairwise interaction function estimation of stationary Gibbs point processes using basis expansion","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Point processes and geometric inequalities","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Pairwise comparison; Mathematics; Point process; Logarithm; Asymptotic distribution; Conditional probability distribution; Consistency (knowledge bases); Event (particle physics); Applied mathematics; Statistics; Mathematical analysis; Estimator; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2776146523690608,"gpt":0.4205660198143607,"spread":0.1429513674452999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008112923,0.0001161108,0.0002223825,0.00029465,0.0001038737,0.00001793323,0.000105136,0.00004278849,0.00007503997],"category_scores_gemma":[0.003796353,0.00008847158,0.00004035077,0.000999284,0.00007008044,0.0002876185,0.00004894476,0.00007824339,0.000009485911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001501203,"about_ca_system_score_gemma":0.0001275625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008045477,"about_ca_topic_score_gemma":0.00000888704,"domain_scores_codex":[0.9986812,0.00007678365,0.0005611912,0.0001193615,0.0003995523,0.0001619513],"domain_scores_gemma":[0.9962158,0.002122207,0.0005499093,0.000194351,0.0008904105,0.0000273089],"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":[0.001961797,0.001290649,0.0005251379,0.03065064,0.0007759466,0.00001839421,0.03376893,0.102911,0.004254006,0.4087638,0.1096652,0.3054145],"study_design_scores_gemma":[0.0002658639,0.000365149,0.001069392,0.0004408039,0.0001386712,0.000006466587,0.007328962,0.1385349,0.01773665,0.8337306,0.0001919047,0.0001906372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4072942,0.0001034134,0.5911782,0.0003468906,0.0001605147,0.0002106186,0.0004698902,0.0000689261,0.0001674275],"genre_scores_gemma":[0.9791737,0.0003283029,0.02003548,0.00006239901,0.00004634439,0.00001219134,0.0001294117,0.00002176869,0.0001904123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5718795,"threshold_uncertainty_score":0.4544863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7082035578","doi":"10.1214/24-aos2474","title":"Entropic covariance models","year":2025,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Covariance matrix; Estimation of covariance matrices; Covariance; Covariance intersection; Law of total covariance; Matérn covariance function; Rational quadratic covariance function; Covariance function","retraction":null,"screen_n_in":null,"score":{"opus":0.07252840629356987,"gpt":0.3063386029729196,"spread":0.2338101966793498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001812961,0.00005169625,0.00008705061,0.00001580528,0.00006360628,0.00002271443,0.0006165574,0.00002077806,0.00001215512],"category_scores_gemma":[0.0001688864,0.00003727394,0.00001775646,0.0001607676,0.00006313494,0.00005657001,0.0001566179,0.00006110698,0.000005651649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000205138,"about_ca_system_score_gemma":0.00004725343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001291575,"about_ca_topic_score_gemma":9.010042e-7,"domain_scores_codex":[0.9995118,0.00002838982,0.0001352169,0.0001042847,0.00009212826,0.0001281937],"domain_scores_gemma":[0.9991494,0.0002139005,0.00006434914,0.0003764687,0.0001796001,0.00001632551],"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":[0.000002429469,0.00001303498,0.00001680166,0.00002640503,0.00001247696,0.000002073293,0.000137345,0.004666437,0.000118595,0.9634558,0.02481456,0.006734035],"study_design_scores_gemma":[0.00005716892,0.00001187157,0.0003664356,0.00001854514,0.000002986909,9.487773e-7,0.00001488768,0.1593657,0.003414904,0.8232697,0.01343786,0.00003894615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002063695,0.0001556765,0.9643236,0.01193848,0.00008788531,0.00004218699,0.00001715685,0.0000197928,0.02320882],"genre_scores_gemma":[0.9113972,0.0001478129,0.08017842,0.001878988,0.00001947384,0.0000048258,0.000003077528,8.956044e-7,0.006369266],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9111909,"threshold_uncertainty_score":0.1519987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392591541","doi":"10.1214/23-aos2344","title":"Erratum: Improved multivariate normal mean estimation with unknown covariance when p is greater than n","year":2024,"lang":"en","type":"erratum","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Mathematics; Covariance; Multivariate statistics; Statistics; Multivariate normal distribution; Estimation of covariance matrices; Estimation; Covariance function; Econometrics; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1569993051470586,"gpt":0.4160429657399978,"spread":0.2590436605929392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008956357,0.000694437,0.001077248,0.0001307539,0.0001842539,0.0001309557,0.0005882394,0.0003854346,0.0001556767],"category_scores_gemma":[0.001106538,0.000433522,0.000138996,0.0002114599,0.0004152315,0.0001517748,0.0002148128,0.001281998,0.00003572914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003924895,"about_ca_system_score_gemma":0.0003465811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002468097,"about_ca_topic_score_gemma":0.000132741,"domain_scores_codex":[0.9967747,0.0002527935,0.0009636148,0.0006495551,0.0007112924,0.0006479991],"domain_scores_gemma":[0.9956803,0.001471118,0.000840557,0.001036032,0.0008016353,0.0001702967],"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":[0.0002656795,0.00008677453,3.431372e-7,0.001929155,0.0005255679,0.00005049829,0.004343795,0.00007689155,0.00002794851,0.2026112,0.7701421,0.01994004],"study_design_scores_gemma":[0.0003161155,0.0003790453,0.00001132463,0.0009289029,0.0005946578,0.00001567236,0.00006067943,0.1198244,0.0001946353,0.8596858,0.01746957,0.0005191781],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001351135,0.0003491199,0.9806226,0.001041032,0.002868331,0.0007563677,0.008206004,0.00009883005,0.006044191],"genre_scores_gemma":[0.0003595696,0.0002747459,0.8880684,0.0004151812,0.000457135,0.00007630743,0.0003713941,0.0002025668,0.1097747],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7526726,"threshold_uncertainty_score":0.9998116,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7116834253","doi":"10.1214/25-aos2558","title":"Optimal sequencing depth for single-cell RNA-sequencing in Wasserstein space","year":2025,"lang":"","type":"article","venue":"The Annals of Statistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"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":"Nonparametric statistics; Context (archaeology); Empirical distribution function; Upper and lower bounds; Probability distribution; Distribution (mathematics); Space (punctuation)","retraction":null,"screen_n_in":null,"score":{"opus":0.07784741182568422,"gpt":0.3091679179887126,"spread":0.2313205061630284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009002257,0.0004437798,0.0005894495,0.0001599712,0.0002076046,0.00008632493,0.0006351492,0.0003553133,0.00001018384],"category_scores_gemma":[0.0005678147,0.0004139727,0.0002315321,0.0003439421,0.0003825154,0.00001250926,0.000150405,0.0003236572,0.000002324779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000163324,"about_ca_system_score_gemma":0.001215893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004004258,"about_ca_topic_score_gemma":0.0004899876,"domain_scores_codex":[0.9972448,0.0001910959,0.0009655627,0.0005821253,0.0002404208,0.0007759477],"domain_scores_gemma":[0.9978721,0.0004209411,0.000412205,0.0006552065,0.0005300981,0.0001094992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008189463,0.0002172743,0.0003052443,0.0008760887,0.0001965705,0.00001543485,0.0009352351,0.01599479,0.9673089,0.004065881,0.002385746,0.006879816],"study_design_scores_gemma":[0.001536189,0.0009723846,0.00005650067,0.0003834505,0.0001765752,0.000004821516,0.002138028,0.01841513,0.9698164,0.001967721,0.004056917,0.0004758903],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.598556,0.006197954,0.3842644,0.001097254,0.0007508147,0.001047585,0.001047656,0.00001343904,0.007024907],"genre_scores_gemma":[0.9659973,0.002355903,0.02926614,0.00066327,0.0001564571,0.00002440334,0.0001458141,0.00005639565,0.001334266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3674414,"threshold_uncertainty_score":0.9998312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7116982847","doi":"10.1214/25-aos2550","title":"Semi-supervised U-statistics","year":2025,"lang":"","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Science North","funders":"","keywords":"","retraction":null,"screen_n_in":null,"score":{"opus":0.1395012079858714,"gpt":0.4292025418087274,"spread":0.289701333822856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002296369,0.0007065178,0.001438853,0.0002514168,0.0004837153,0.0002002491,0.001353701,0.0003278626,0.002091358],"category_scores_gemma":[0.01564592,0.0005455969,0.0002033582,0.001005152,0.001606772,0.00009615483,0.0004868911,0.0008380163,0.0001389818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004361912,"about_ca_system_score_gemma":0.0007572951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001283235,"about_ca_topic_score_gemma":0.00003142541,"domain_scores_codex":[0.994136,0.001032631,0.002248924,0.0006160738,0.000916622,0.001049735],"domain_scores_gemma":[0.9740157,0.02137582,0.0008738667,0.001614565,0.001862857,0.0002571832],"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":[0.0001466819,0.0003336658,0.00008427911,0.001601235,0.0003705525,0.00002571663,0.0006589036,0.000005329295,0.0001021787,0.6677966,0.1714964,0.1573784],"study_design_scores_gemma":[0.0006398585,0.0003478278,0.001369244,0.0009005059,0.0007465657,0.000005633297,0.0006001882,0.02440293,0.002111762,0.9615633,0.006806867,0.0005053554],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001901896,0.001162747,0.9606664,0.002887076,0.001026943,0.0007962891,0.01940418,0.00004684164,0.01381934],"genre_scores_gemma":[0.01913381,0.003334795,0.9711072,0.002055714,0.0001714328,0.00003530683,0.00007583702,0.00007889891,0.004007013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2937666,"threshold_uncertainty_score":0.9996995,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950189778","doi":"10.1214/009053606000000669","title":"Discussion","year":2006,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"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":"Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2522521128923341,"gpt":0.4806907557014626,"spread":0.2284386428091285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003797645,0.00008988246,0.0001818429,0.00001960146,0.00007326082,0.000008326901,0.0001364686,0.0000270535,0.00006250964],"category_scores_gemma":[0.0008548123,0.00004233218,0.00003416195,0.00007033499,0.0001380242,0.00003143018,0.00004205777,0.00008099982,0.000006851841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003364858,"about_ca_system_score_gemma":0.00001372281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002208456,"about_ca_topic_score_gemma":0.00001005869,"domain_scores_codex":[0.9991392,0.00008248158,0.0002968631,0.00009824397,0.0002052386,0.0001778983],"domain_scores_gemma":[0.9979561,0.001482592,0.0001440513,0.0002517551,0.0001327922,0.0000327189],"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":[0.0000165768,0.00005693601,0.000009217939,0.00003660901,0.000006640102,0.000002633746,0.00006512646,0.00004095661,0.0002431237,0.9405693,0.03312133,0.02583158],"study_design_scores_gemma":[0.0000866968,0.00004616287,0.0003320267,0.00001987439,0.00001749423,0.000001468967,0.00004363115,0.001281744,0.00173906,0.9929162,0.003443224,0.00007241253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001102686,0.00004126837,0.9934372,0.001049773,0.00005238815,0.000104474,0.0004262476,0.0000210582,0.003764874],"genre_scores_gemma":[0.107953,0.00003512706,0.8895977,0.000123538,0.00008010609,0.000006108166,0.00001132416,0.00001910932,0.002174021],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1068503,"threshold_uncertainty_score":0.1726256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386035726","doi":"10.1214/23-aos2289","title":"Optimal discriminant analysis in high-dimensional latent factor models","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Minimax; Mathematics; Linear discriminant analysis; Discriminant; Classifier (UML); Pattern recognition (psychology); Principal component analysis; Latent variable; Artificial intelligence; Dimension (graph theory); Sample size determination; Dimensionality reduction; Logarithm; Latent variable model; Statistics; Mathematical optimization; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.0983438622062266,"gpt":0.3423473871007673,"spread":0.2440035248945407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000140104,0.00007251179,0.0001176104,0.00009313275,0.00003260965,0.000007074333,0.0001323089,0.00004188338,0.00002344729],"category_scores_gemma":[0.00003460547,0.00005023244,0.00005135321,0.0003052312,0.00005037562,0.00000223852,0.00007242132,0.00004183427,0.000006191095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000308669,"about_ca_system_score_gemma":0.00003575817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000541899,"about_ca_topic_score_gemma":0.00003337035,"domain_scores_codex":[0.9993222,0.00004553278,0.0001871683,0.0001532937,0.000152451,0.0001393503],"domain_scores_gemma":[0.9995276,0.00002179694,0.00008159612,0.0002436577,0.00009122818,0.00003417072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003514471,0.000183551,0.003202257,0.00004034367,0.0004645905,0.000008618207,0.0006101843,0.5347303,0.3915132,0.009645108,0.05058184,0.008668616],"study_design_scores_gemma":[0.0007723875,0.000338871,0.5555357,0.00003277239,0.0001999611,0.000001459785,0.0003612956,0.212358,0.2194605,0.008536263,0.001973405,0.0004293512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708564,0.0001212384,0.02766926,0.0006991985,0.00005549474,0.00007330039,0.000479396,0.00000563554,0.00004012284],"genre_scores_gemma":[0.9975156,0.0004286315,0.001050734,0.0001120286,0.00002379531,0.00001030962,0.0003764699,0.00000739401,0.0004750484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5523334,"threshold_uncertainty_score":0.204842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}