{"meta":{"query_hash":"12d2d8b97a75","filters":{"venue":"Journal of the American Statistical Association"},"cohort_total":156,"direct_labels_cover":1,"predictions_cover":156,"exported":156,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/12d2d8b97a75","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+the+American+Statistical+Association"},"results":[{"id":"W1737070927","doi":"10.1080/01621459.2015.1096787","title":"Accelerating Asymptotically Exact MCMC for Computationally Intensive Models via Local Approximations","year":2015,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Office of Science; Advanced Scientific Computing Research; U.S. Department of Energy","keywords":"Markov chain Monte Carlo; Ergodicity; Importance sampling; Inference; Monte Carlo method; Convergence (economics); Gaussian process; Ode; Rejection sampling","score_opus":0.11257881641235555,"score_gpt":0.3749705992627148,"score_spread":0.26239178285035925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1737070927","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018874299,0.000009053326,0.97718984,0.0027815863,0.00030033998,0.00026662997,0.00007164737,0.000015400477,0.0004911804],"genre_scores_gemma":[0.44817382,0.0000017417038,0.5506438,0.00077133416,0.00022849502,0.000009949819,0.0000067157757,0.000021321117,0.00014284273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975649,0.0004971581,0.00079204765,0.00013256365,0.0007643077,0.00024901837],"domain_scores_gemma":[0.989211,0.005487005,0.0018574847,0.00013396621,0.0031309885,0.00017952856],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024015207,0.00014544008,0.0005060807,0.00006943247,0.00012710648,0.000071913106,0.00023575735,0.000056104385,0.0000035146345],"category_scores_gemma":[0.015927022,0.000101617865,0.00019148183,0.0002179911,0.000116406656,0.00017965399,0.00006245836,0.00030269948,2.0137557e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091811817,0.0007809718,0.002658448,0.00015206663,0.0012442784,0.000016537502,0.004768325,0.034497198,0.00074145844,0.71975875,0.111113764,0.12335007],"study_design_scores_gemma":[0.0009971628,0.0004489685,0.0010872933,0.00004815039,0.0002418923,0.000035332283,0.0016458005,0.51063025,0.000070663096,0.48430365,0.00031372477,0.00017713274],"about_ca_topic_score_codex":0.000015469874,"about_ca_topic_score_gemma":0.000013223149,"teacher_disagreement_score":0.47613302,"about_ca_system_score_codex":0.00070701045,"about_ca_system_score_gemma":0.00027146636,"threshold_uncertainty_score":0.99236226},"labels":[],"label_agreement":null},{"id":"W1935711966","doi":"10.1080/01621459.2012.665615","title":"Comment","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute on Drug Abuse; National Institute of Mental Health","keywords":"Mathematics","score_opus":0.08176577088976356,"score_gpt":0.42506965710657935,"score_spread":0.3433038862168158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1935711966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1300977,0.000028524983,0.85379106,0.013944132,0.0004921654,0.00016164168,0.00003733841,0.000048890153,0.001398547],"genre_scores_gemma":[0.8379387,0.00001088967,0.16056642,0.0011976328,0.00018601367,0.000001939233,3.637943e-7,0.000009677964,0.000088319044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875945,0.00023406859,0.00034504308,0.000033864744,0.0004315652,0.00019603068],"domain_scores_gemma":[0.99625695,0.001958928,0.001438124,0.000107991946,0.00016289939,0.0000751289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010647823,0.00006668378,0.00023171358,0.000027479251,0.00004880929,0.00001301773,0.00015099708,0.00002011082,0.000037911846],"category_scores_gemma":[0.004995873,0.000041260428,0.0000683261,0.0001336407,0.000053818043,0.00013299071,0.000041976975,0.00023506032,0.0000070797014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051531446,0.00042906127,0.1277759,0.00001409625,0.00016254825,0.0000019835882,0.00046626196,0.0000021343296,0.0010639236,0.573217,0.27785024,0.018965358],"study_design_scores_gemma":[0.00027195073,0.00030498576,0.14119804,0.000045845816,0.000194979,0.000027070195,0.00031207022,0.0000489334,0.0025463358,0.8304043,0.02446724,0.00017829346],"about_ca_topic_score_codex":0.000006627248,"about_ca_topic_score_gemma":0.0000010429409,"teacher_disagreement_score":0.70784104,"about_ca_system_score_codex":0.00055377936,"about_ca_system_score_gemma":0.000022991197,"threshold_uncertainty_score":0.5980888},"labels":[],"label_agreement":null},{"id":"W1968917443","doi":"10.1198/016214508000000670","title":"Modeling Price Dynamics in eBay Auctions Using Differential Equations","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Smiths Detection (Canada)","funders":"","keywords":"Common value auction; Unique bid auction; Bidding; Auction theory; Generalized second-price auction; Computer science; Forward auction; English auction; Microeconomics; Econometrics; Economics","score_opus":0.08454357743727206,"score_gpt":0.3867247648725179,"score_spread":0.3021811874352458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968917443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40700763,0.0000032755927,0.5917246,0.0008793469,0.00019350805,0.00004889588,0.00003258811,0.0000040958375,0.00010608608],"genre_scores_gemma":[0.9920492,0.000008814561,0.0072848722,0.00009179934,0.0001578951,0.0000024639123,0.0000019334657,0.0000070933306,0.00039588523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971397,0.0005256513,0.0009163262,0.00014078725,0.0010993724,0.00017815713],"domain_scores_gemma":[0.99556476,0.0021861074,0.0014301388,0.00019710198,0.00054383563,0.00007805685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013634915,0.00008408498,0.00028934146,0.00020947754,0.00040786987,0.00006183511,0.0003821579,0.000035908382,0.000068624824],"category_scores_gemma":[0.007824248,0.000057434474,0.00013134899,0.0012372189,0.00014027854,0.00024644472,0.000057590394,0.00034103976,0.000019220544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019244125,0.00086044683,0.14635468,0.0000033189156,0.00016494752,0.000011969543,0.0015771443,0.63355166,0.0013334928,0.20068254,0.0026265117,0.012640834],"study_design_scores_gemma":[0.00020588202,0.000033174932,0.048640613,0.000007220938,0.000035243796,0.00003580305,0.0009275854,0.88944435,0.000011905686,0.060487855,0.000089931294,0.00008041129],"about_ca_topic_score_codex":0.000098454686,"about_ca_topic_score_gemma":0.00005466302,"teacher_disagreement_score":0.5850416,"about_ca_system_score_codex":0.001081759,"about_ca_system_score_gemma":0.00017548798,"threshold_uncertainty_score":0.93669206},"labels":[],"label_agreement":null},{"id":"W1969142716","doi":"10.1198/016214508000001075","title":"Order Selection in Finite Mixture Models With a Nonsmooth Penalty","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"","keywords":"Selection (genetic algorithm); Applied mathematics; Mathematics; Mathematical optimization; Order (exchange); Model selection; Penalty method; Computer science; Artificial intelligence; Statistics; Economics","score_opus":0.011308483516022382,"score_gpt":0.2514568721316176,"score_spread":0.24014838861559523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969142716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01867895,0.000017723049,0.9787699,0.002089509,0.000076514865,0.000069046306,0.0000050173976,0.000009491732,0.00028386328],"genre_scores_gemma":[0.450462,0.000025985168,0.5487872,0.00053442176,0.000052762727,0.0000016081623,2.3530599e-7,0.0000055829746,0.00013022477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832827,0.00044234234,0.0003279645,0.00013668538,0.00055145286,0.00021326527],"domain_scores_gemma":[0.99802256,0.00059214345,0.00086751697,0.00010958963,0.0003367224,0.0000714549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067639095,0.000101634214,0.00028973477,0.0000944399,0.00010363867,0.00004123403,0.000336762,0.000036630154,0.0000039914958],"category_scores_gemma":[0.0004887182,0.000060643848,0.000054432567,0.00095308607,0.000057324803,0.00033774046,0.000041326686,0.00041957528,0.0000015872123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012879802,0.00192721,0.21817742,0.000059852773,0.00077535305,0.00051396474,0.01055421,0.0686668,0.0023228645,0.34482208,0.05209501,0.29879725],"study_design_scores_gemma":[0.0015381804,0.0009899996,0.3137843,0.00008593863,0.000072942574,0.0004749391,0.00003549651,0.5155862,0.0001958432,0.1661356,0.00070959906,0.00039095824],"about_ca_topic_score_codex":0.00007910571,"about_ca_topic_score_gemma":0.0000470488,"teacher_disagreement_score":0.44691938,"about_ca_system_score_codex":0.00030484993,"about_ca_system_score_gemma":0.0002595698,"threshold_uncertainty_score":0.24729843},"labels":[],"label_agreement":null},{"id":"W1969168383","doi":"10.1198/016214506000000447","title":"Evaluating Kindergarten Retention Policy","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"School Choice and Performance","field":"Social Sciences","cited_by":377,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Grade retention; Propensity score matching; Retention rate; Psychology; Covariate; Multilevel model; Average treatment effect; Affect (linguistics); Developmental psychology; Demography; Mathematics; Econometrics; Academic achievement; Statistics; Computer science; Sociology","score_opus":0.03241118186837891,"score_gpt":0.39650135583418095,"score_spread":0.364090173965802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969168383","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96370536,0.000029323714,0.003443901,0.023263497,0.0005213329,0.000092757284,0.000016219805,0.000015309877,0.008912315],"genre_scores_gemma":[0.992539,0.00002841788,0.0029557652,0.00046288958,0.0024291135,0.0000010727612,0.0000013859387,0.0000052753726,0.0015771193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99789786,0.0005266496,0.00032859005,0.000059890546,0.0009553787,0.00023163225],"domain_scores_gemma":[0.9976632,0.00057662127,0.0012918657,0.000064291096,0.00034739656,0.000056613513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002213277,0.000051213527,0.00014881999,0.00006029631,0.00034766278,0.00007797641,0.00018177845,0.000030364543,0.000048914775],"category_scores_gemma":[0.0043559377,0.000036840374,0.00008338949,0.00047830938,0.000101983416,0.000196815,0.00001594634,0.00020586379,0.00001690203],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012329768,0.00015176916,0.76175326,0.000008758769,0.00010038589,0.0000043172777,0.0014996601,0.00063688157,0.0020606443,0.04939521,0.09973516,0.08453063],"study_design_scores_gemma":[0.00024357115,0.000120147895,0.9587475,0.000017863591,0.00005791975,0.0000022626368,0.0004897214,0.00028998076,0.00003791819,0.026467199,0.013452335,0.00007354662],"about_ca_topic_score_codex":0.0038046124,"about_ca_topic_score_gemma":0.00076045806,"teacher_disagreement_score":0.19699425,"about_ca_system_score_codex":0.0008488031,"about_ca_system_score_gemma":0.0003904279,"threshold_uncertainty_score":0.57514614},"labels":[],"label_agreement":null},{"id":"W1970517271","doi":"10.1080/01621459.2011.643743","title":"Partially Hidden Markov Model for Time-Varying Principal Stratification in HIV Prevention Trials","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Human immunodeficiency virus (HIV); Markov model; Markov chain; Principal (computer security); Mathematics; Econometrics; Statistics; Computer science; Medicine; Virology","score_opus":0.14586056066597575,"score_gpt":0.44569357495264006,"score_spread":0.2998330142866643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970517271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06945519,0.000009467631,0.9289343,0.00079821714,0.00007322386,0.00048790933,0.000061402345,0.000022367469,0.00015792705],"genre_scores_gemma":[0.5960547,0.000007781229,0.40328163,0.000046934056,0.00015711406,0.000031029773,0.000006573007,0.000014689575,0.00039956038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99738663,0.0006810182,0.0011162843,0.00009109694,0.00045360683,0.000271348],"domain_scores_gemma":[0.9925819,0.0037068937,0.0032485414,0.000137138,0.00025433747,0.000071160204],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005527363,0.00011514739,0.00054190867,0.00007530759,0.000059378326,0.000033117645,0.00017262746,0.000058201167,0.000021782764],"category_scores_gemma":[0.0168615,0.00008336475,0.00014758747,0.00016701374,0.000039661587,0.00034314638,0.00002897994,0.00022837371,0.0000033201823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029378773,0.003664772,0.075434014,0.00030180422,0.00095628324,0.0000038678477,0.0049125,0.002165211,0.073033385,0.4242457,0.061749563,0.35059506],"study_design_scores_gemma":[0.0010098547,0.00029156523,0.02105415,0.00014118152,0.00037654195,0.0000061976457,0.00011971817,0.109349124,0.0029540637,0.8643467,0.00009400911,0.00025691366],"about_ca_topic_score_codex":0.0000033502413,"about_ca_topic_score_gemma":0.0000076079505,"teacher_disagreement_score":0.52659947,"about_ca_system_score_codex":0.0007108729,"about_ca_system_score_gemma":0.00012699334,"threshold_uncertainty_score":0.9914199},"labels":[],"label_agreement":null},{"id":"W1971907399","doi":"10.1198/jasa.2010.tm09534","title":"Pseudo–Empirical Likelihood Inference for Multiple Frame Surveys","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Empirical likelihood; Inference; Point estimation; Statistics; Confidence interval; Likelihood function; Mathematics; Statistic; Population; Interval estimation; Confidence distribution; Econometrics; Statistical inference; Frame (networking); Expectation–maximization algorithm; Computer science; Estimation theory; Maximum likelihood; Artificial intelligence","score_opus":0.04316731173248054,"score_gpt":0.4051995834760186,"score_spread":0.362032271743538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971907399","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11582729,0.0000019171134,0.881128,0.0017726303,0.00067441375,0.00018364891,0.0002910986,0.000015852262,0.00010511817],"genre_scores_gemma":[0.46366966,0.0000029261394,0.5357721,0.00024422875,0.00025262783,0.0000071654154,0.0000016511295,0.000015382411,0.000034292498],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970659,0.00090011477,0.00079736195,0.00017061982,0.0006745204,0.0003914818],"domain_scores_gemma":[0.9653538,0.031686116,0.001761379,0.00023561255,0.0007698195,0.00019331394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003905278,0.0001718716,0.0006009497,0.00006127774,0.00015288683,0.00008812258,0.00040806507,0.0001031741,0.000085723],"category_scores_gemma":[0.107331134,0.00011124446,0.00019760965,0.0002963533,0.00019598046,0.00009670306,0.00006554146,0.0008205163,0.000008366274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023396073,0.00082737615,0.48219898,0.000086082226,0.00033073168,0.000008394241,0.00039260247,0.0000020585976,0.010846163,0.2514299,0.03509753,0.21854626],"study_design_scores_gemma":[0.0004708509,0.0003090854,0.30821025,0.000021509193,0.00012255141,0.000010066915,0.000042677388,0.0021859813,0.00033565142,0.6874866,0.00065804314,0.00014674965],"about_ca_topic_score_codex":0.00004268683,"about_ca_topic_score_gemma":0.00008728037,"teacher_disagreement_score":0.4360567,"about_ca_system_score_codex":0.00016981235,"about_ca_system_score_gemma":0.00021904323,"threshold_uncertainty_score":0.9001882},"labels":[],"label_agreement":null},{"id":"W1972508666","doi":"10.1198/016214508000000643","title":"A Directional Model for the Estimation of the Rotation Axes of the Ankle Joint","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Rotation (mathematics); Estimator; Mathematics; Orientation (vector space); Euler's rotation theorem; Ankle; Statistics; Geometry","score_opus":0.049892966512065366,"score_gpt":0.3106143710139499,"score_spread":0.2607214045018845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972508666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2675529,0.000013835908,0.7268497,0.0047207214,0.00023718017,0.00034309007,0.00018047277,0.000004475179,0.00009764207],"genre_scores_gemma":[0.9476567,0.000012346258,0.051782135,0.00017143483,0.000072865994,0.000011258427,0.0000011984007,0.000008079009,0.00028401078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9982116,0.00028339127,0.000646843,0.000071167924,0.0006714313,0.000115556555],"domain_scores_gemma":[0.9935693,0.0030066567,0.0027702416,0.00018842713,0.00044318876,0.000022200613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095526915,0.00008448548,0.0002719349,0.000028721068,0.00031112033,0.000012606266,0.00027137125,0.000037625843,0.000015064938],"category_scores_gemma":[0.007997284,0.00003453615,0.00026461083,0.00034452617,0.00019336933,0.00006546872,0.000056382127,0.00021056748,4.4104712e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005937762,0.002433543,0.084132634,0.00021610198,0.0016010446,0.0000012995549,0.004423656,0.22781174,0.013783517,0.48481864,0.15020727,0.029976787],"study_design_scores_gemma":[0.0004404272,0.00011907078,0.46975243,0.00004884944,0.0003021754,0.000016566597,0.00017526087,0.38298765,0.0014054864,0.14459847,0.000078188525,0.00007541166],"about_ca_topic_score_codex":0.000044086566,"about_ca_topic_score_gemma":0.000010306151,"teacher_disagreement_score":0.6801038,"about_ca_system_score_codex":0.00019201121,"about_ca_system_score_gemma":0.00013411546,"threshold_uncertainty_score":0.95740736},"labels":[],"label_agreement":null},{"id":"W1972826983","doi":"10.1080/01621459.2011.643732","title":"Modeling Waves of Extreme Temperature: The Changing Tails of Four Cities","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Climate Change and Health Impacts","field":"Environmental Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Heat wave; Series (stratigraphy); Extreme value theory; Sample (material); Environmental science; Statistics; Distribution (mathematics); Constant (computer programming); Climatology; Mathematics; Meteorology; Econometrics; Climate change; Atmospheric sciences; Geography; Geology; Physics; Thermodynamics; Computer science; Mathematical analysis","score_opus":0.05417574977560491,"score_gpt":0.30056701072777503,"score_spread":0.24639126095217012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972826983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950854,0.00007007153,0.0022517778,0.0021639902,0.00015839469,0.000064574146,0.000039070645,0.000001855966,0.00016483548],"genre_scores_gemma":[0.99799085,0.00009123587,0.0012960016,0.00038266293,0.00016397462,8.1351493e-7,6.9892275e-7,0.0000060424522,0.00006775173],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99865526,0.0001607633,0.0003682359,0.000040322517,0.00051688007,0.0002585662],"domain_scores_gemma":[0.99839646,0.00043521784,0.00096508826,0.0000852919,0.00004677824,0.0000711899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011753335,0.00006322717,0.00022171884,0.000030535157,0.00009781781,0.00001021443,0.00014847842,0.000022411128,0.00010932889],"category_scores_gemma":[0.0008368396,0.00003429587,0.00006634532,0.00023508808,0.00010527336,0.00014192704,0.00006578577,0.00016095307,0.0000035754383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002556856,0.00038354087,0.8505853,0.000111488385,0.00019096775,0.000002837912,0.02506057,0.0071788854,0.06832926,0.0017411209,0.016666286,0.029494101],"study_design_scores_gemma":[0.0005081349,0.00042077174,0.96253365,0.00019222638,0.00024119917,0.000030315085,0.009277,0.017840302,0.003321773,0.0051098173,0.0003117846,0.00021299964],"about_ca_topic_score_codex":0.0001678815,"about_ca_topic_score_gemma":0.000017299297,"teacher_disagreement_score":0.11194842,"about_ca_system_score_codex":0.00025737562,"about_ca_system_score_gemma":0.000015775353,"threshold_uncertainty_score":0.1398545},"labels":[],"label_agreement":null},{"id":"W1972949866","doi":"10.1080/01621459.2013.879531","title":"The Sparse MLE for Ultrahigh-Dimensional Feature Screening","year":2014,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Drug Abuse","keywords":"Computer science; Feature selection; Feature (linguistics); Context (archaeology); Estimator; Process (computing); Algorithm; Machine learning; Artificial intelligence; Mathematics; Statistics","score_opus":0.03508407808052878,"score_gpt":0.3527433810441259,"score_spread":0.3176593029635971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972949866","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016497618,0.00001580283,0.9753618,0.007178343,0.00045913403,0.00015220023,0.000101053534,0.000009891453,0.00022412915],"genre_scores_gemma":[0.19366123,0.0000076796805,0.80441666,0.0007306348,0.00051138166,0.0000071356376,0.0000017660259,0.000020559697,0.00064297067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979562,0.0005835413,0.00045589393,0.00010295482,0.0006306449,0.00027072016],"domain_scores_gemma":[0.971604,0.026177503,0.001483049,0.00015759216,0.00048344262,0.000094398885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026045965,0.00011497105,0.00035254055,0.00002313467,0.00034115004,0.00007589501,0.00027635857,0.000042554464,0.000014248576],"category_scores_gemma":[0.04244619,0.000058249443,0.00014758982,0.00015700844,0.00014896118,0.00004280763,0.000037480724,0.00035594858,0.000002796227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042875885,0.0001124845,0.004436353,0.00002260914,0.0002565435,0.0000016189099,0.00009615348,0.000055719032,0.00073237944,0.65012246,0.19036356,0.15337135],"study_design_scores_gemma":[0.000785729,0.000573247,0.078724876,0.00006621538,0.00027658528,0.0000187721,0.00010956111,0.011018039,0.00026224682,0.8868749,0.021114442,0.00017535659],"about_ca_topic_score_codex":0.000011449507,"about_ca_topic_score_gemma":0.000008175933,"teacher_disagreement_score":0.23675247,"about_ca_system_score_codex":0.0001329454,"about_ca_system_score_gemma":0.000056232217,"threshold_uncertainty_score":0.9656197},"labels":[],"label_agreement":null},{"id":"W1974366877","doi":"10.1198/016214504000000485","title":"A Conditionally Distribution-Free Multivariate Sign Test for One-Sided Alternatives","year":2004,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Orthant; Sign test; Mathematics; Test statistic; Null distribution; Likelihood-ratio test; Multivariate normal distribution; Conditional probability distribution; Conditional independence; Statistics; Intersection (aeronautics); Multivariate statistics; Statistical hypothesis testing; Applied mathematics","score_opus":0.041807474512575986,"score_gpt":0.3660138718190143,"score_spread":0.3242063973064383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974366877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013837313,0.0000031115048,0.9674883,0.008996978,0.00011593601,0.0003466361,0.009063177,0.000026212922,0.00012231896],"genre_scores_gemma":[0.88481796,0.000004219874,0.11425741,0.00039356743,0.00017971957,0.000046341753,0.00016707042,0.00001680994,0.000116881114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99793476,0.00013114006,0.00084603566,0.00014644246,0.0006970228,0.0002446131],"domain_scores_gemma":[0.98670924,0.00979268,0.0021687902,0.00020389486,0.0009917167,0.00013367244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007059174,0.00014292712,0.00037880556,0.00003913048,0.0002556238,0.00007019206,0.00036698626,0.000043986358,0.000054171625],"category_scores_gemma":[0.062624596,0.00010923456,0.0001739375,0.00030134304,0.00019111957,0.00012224598,0.000048142672,0.00023130391,0.0000143174975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060097824,0.0005844241,0.00048450055,0.000015061305,0.00014017758,0.000001251821,0.00006396286,0.00015966265,0.00068025454,0.97943467,0.0175264,0.00084955804],"study_design_scores_gemma":[0.0016056164,0.00020241937,0.16484982,0.00005569617,0.00018803323,0.000008177505,0.00006826047,0.0006338337,0.00047075225,0.8313189,0.00047107897,0.00012741938],"about_ca_topic_score_codex":0.00002634548,"about_ca_topic_score_gemma":0.000011087404,"teacher_disagreement_score":0.8709807,"about_ca_system_score_codex":0.00092155894,"about_ca_system_score_gemma":0.00021914547,"threshold_uncertainty_score":0.9452713},"labels":[],"label_agreement":null},{"id":"W1975754266","doi":"10.1198/016214504000002104","title":"Are Maintenance Practices for Railroad Tracks Effective?","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Covariate; Poisson distribution; Track (disk drive); Grinding; Computer science; Interval (graph theory); Statistics; Econometrics; Environmental science; Engineering; Mathematics; Mechanical engineering","score_opus":0.0057182700350403145,"score_gpt":0.25657613028866744,"score_spread":0.2508578602536271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975754266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32744113,0.000121039666,0.6682603,0.002547087,0.000751502,0.00022241702,0.000175866,0.00006479846,0.00041589464],"genre_scores_gemma":[0.97618526,0.000037018843,0.02296291,0.00014086327,0.00041915107,0.000008252492,0.0000012839033,0.00002135268,0.00022387956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99922585,0.00005035573,0.00026307328,0.00005620042,0.00022396978,0.00018052384],"domain_scores_gemma":[0.99734646,0.0011355509,0.0012413212,0.00007361,0.00015061686,0.0000524697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044471872,0.00008803678,0.00023482385,0.000035833855,0.000043060634,0.00003446888,0.00012688426,0.000030018155,0.0000033831286],"category_scores_gemma":[0.00350689,0.00006332744,0.000094015195,0.00012708263,0.000024941473,0.00012720129,0.0000071525933,0.00024205893,0.0000047304175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024004723,0.00017630382,0.020316,0.00013941608,0.00073754427,0.000009556462,0.00035931173,0.56892765,0.002865112,0.0022357944,0.10229953,0.30169374],"study_design_scores_gemma":[0.0009795725,0.00023694216,0.51314163,0.0000908454,0.00021937284,0.0000364204,0.00016539756,0.40676087,0.00034218916,0.001194088,0.07654884,0.00028386747],"about_ca_topic_score_codex":0.0000041455232,"about_ca_topic_score_gemma":0.000010730091,"teacher_disagreement_score":0.64874417,"about_ca_system_score_codex":0.0005003446,"about_ca_system_score_gemma":0.00001346449,"threshold_uncertainty_score":0.41983283},"labels":[],"label_agreement":null},{"id":"W1978834607","doi":"10.1198/016214501750332893","title":"Driving Fast in Reverse","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.0695026520084821,"score_gpt":0.358402241392434,"score_spread":0.2888995893839519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978834607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9876391,0.000038161168,0.0017113492,0.0054685846,0.0006974118,0.000055977933,0.000010074811,0.000006362089,0.004372956],"genre_scores_gemma":[0.9966998,0.000037863752,0.00069395144,0.0008491962,0.00016121604,0.0000023510715,3.9831144e-7,0.0000052901587,0.0015499071],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987229,0.00032465192,0.00037891674,0.00008878957,0.0002727458,0.00021200933],"domain_scores_gemma":[0.9985495,0.00046629907,0.0007698229,0.00008234965,0.00008025403,0.000051766066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053357176,0.000072855175,0.00025915654,0.00004115366,0.000055425662,0.000014333595,0.00016206833,0.00003467937,0.00041896256],"category_scores_gemma":[0.0005352228,0.00004391208,0.000080533944,0.00036247895,0.00008057514,0.0000416365,0.000029398157,0.0003404964,0.000060647686],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008772189,0.00019127119,0.9113855,4.795759e-7,0.00003647102,0.000053817505,0.00031957572,0.0000034112534,0.0000870343,0.00088643015,0.025576409,0.061371915],"study_design_scores_gemma":[0.0003117747,0.00017615122,0.9864893,0.000011648078,0.000029704868,0.000026394378,0.0005330797,0.0000036071494,0.0000012956874,0.0018361917,0.010523613,0.000057227116],"about_ca_topic_score_codex":0.00020178467,"about_ca_topic_score_gemma":0.00007310068,"teacher_disagreement_score":0.07510385,"about_ca_system_score_codex":0.00023688561,"about_ca_system_score_gemma":0.000009295177,"threshold_uncertainty_score":0.45873463},"labels":[],"label_agreement":null},{"id":"W1982733046","doi":"10.1198/016214506000000096","title":"Principal Components Analysis Based on Multivariate MM Estimators With Fast and Robust Bootstrap","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":144,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Principal component analysis; Mathematics; Asymptotic distribution; Robustness (evolution); Multivariate statistics; Consistency (knowledge bases); Eigenvalues and eigenvectors; Inference; M-estimator; Robust statistics; Statistics; Computer science; Artificial intelligence","score_opus":0.05271612320927879,"score_gpt":0.370291191177527,"score_spread":0.3175750679682482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982733046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13455847,0.0000020109158,0.86463386,0.0003793198,0.000039207673,0.000094321964,0.00013553389,0.0000098354985,0.0001474717],"genre_scores_gemma":[0.53321594,7.3661977e-7,0.46661302,0.00007657279,0.000034406337,0.0000016930192,0.0000030673766,0.000010861969,0.00004366952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9979911,0.00039398973,0.0005176798,0.00016036422,0.0007022537,0.00023462076],"domain_scores_gemma":[0.99439704,0.0036448077,0.0014916217,0.00014341409,0.00021543405,0.00010769632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006765859,0.00015938406,0.000571558,0.00011504361,0.00012421508,0.000046928388,0.00012015646,0.00003416638,0.000012481981],"category_scores_gemma":[0.0017671284,0.00009536959,0.00010507291,0.00040445727,0.00014291593,0.000063527914,0.000023201246,0.0002884629,7.4804547e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021560001,0.002086266,0.3396772,0.00011386176,0.0025259329,0.00013074148,0.00024752322,0.39796996,0.0011447943,0.22570553,0.00167731,0.026564844],"study_design_scores_gemma":[0.0009251164,0.00041148197,0.62262106,0.00004936026,0.0012348732,0.000006097732,0.00003687876,0.31116,0.00004381548,0.06329559,0.00003851326,0.00017722414],"about_ca_topic_score_codex":0.00010271408,"about_ca_topic_score_gemma":0.000029523571,"teacher_disagreement_score":0.3986575,"about_ca_system_score_codex":0.00025905287,"about_ca_system_score_gemma":0.00004308588,"threshold_uncertainty_score":0.3889059},"labels":[],"label_agreement":null},{"id":"W1988392272","doi":"10.1198/jasa.2011.tm09654","title":"An Outlier-Robust Fit for Generalized Additive Models With Applications to Disease Outbreak Detection","year":2011,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Outlier; Generalized linear model; Generalized additive model; Estimator; Poisson distribution; Statistics; Outbreak; Mathematics; Generalized estimating equation; Masking (illustration); Lasso (programming language); Econometrics; Computer science; Medicine","score_opus":0.12022757412902184,"score_gpt":0.39722495979144246,"score_spread":0.2769973856624206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988392272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006890329,0.0000032418675,0.99106216,0.00026844133,0.00006948778,0.0006237067,0.0009644195,0.00002049196,0.000097743934],"genre_scores_gemma":[0.2659879,0.000004148029,0.73331946,0.0002876715,0.0001345681,0.00013217454,0.0000045534634,0.00002752909,0.000102016005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833333,0.00028418505,0.0004953638,0.00019430292,0.00043551595,0.00025730932],"domain_scores_gemma":[0.996084,0.0015058271,0.0011585209,0.00022616936,0.00070117175,0.0003243644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000611325,0.0001512625,0.0004086588,0.00006606994,0.00017415863,0.000030824296,0.00019915352,0.000031771353,0.000016222557],"category_scores_gemma":[0.0020385257,0.0000986153,0.0001039157,0.00022406358,0.000080222264,0.00018980989,0.000024657706,0.00017714687,0.0000018003974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049652215,0.0015269861,0.0006909087,0.00008716649,0.0005457883,0.000010716753,0.0018373466,0.0087394975,0.00083587976,0.7418556,0.0030079863,0.23589686],"study_design_scores_gemma":[0.0007214039,0.0009902957,0.0076006576,0.000030219928,0.0006140584,0.0000053471504,0.0002766035,0.027614946,0.0002700423,0.96118677,0.00045974503,0.00022989282],"about_ca_topic_score_codex":0.000027977389,"about_ca_topic_score_gemma":0.000038357568,"teacher_disagreement_score":0.25909758,"about_ca_system_score_codex":0.00033528448,"about_ca_system_score_gemma":0.00008572285,"threshold_uncertainty_score":0.40214154},"labels":[],"label_agreement":null},{"id":"W1989499452","doi":"10.1198/016214505000001177","title":"Bent-Cable Regression Theory and Applications","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Bent molecular geometry; Mathematics; Piecewise linear function; Estimator; Linear regression; Asymptotic distribution; Multivariate normal distribution; Quadratic equation; Applied mathematics; Piecewise; Segmented regression; Linear model; Mathematical analysis; Statistics; Geometry; Multivariate statistics; Bayesian multivariate linear regression; Structural engineering; Engineering","score_opus":0.003180082169092338,"score_gpt":0.23173119123371047,"score_spread":0.22855110906461812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989499452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3550805,0.000099577854,0.63106674,0.0022605727,0.0002458953,0.0002794509,0.000100026016,0.00001778562,0.010849468],"genre_scores_gemma":[0.9871825,0.000029688188,0.010899599,0.00030571313,0.0001378478,0.0000043413297,0.000002847397,0.00000739402,0.0014301],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99913925,0.000118105454,0.00022386125,0.000074796466,0.0003218047,0.00012217966],"domain_scores_gemma":[0.9985197,0.0006440989,0.00069418753,0.00007233867,0.000026340338,0.000043292268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059314905,0.0000563192,0.00012584089,0.000015410824,0.00013330093,0.00002927034,0.00010029998,0.000015860336,0.000100138466],"category_scores_gemma":[0.00033772408,0.00003585113,0.000029331268,0.00015300418,0.00012673774,0.000057994093,0.00006390874,0.00011288639,0.000015858208],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096810094,0.0002043639,0.6364758,0.000009329914,0.000054496046,0.0000059145364,0.00012597514,0.001268929,0.0041470225,0.10931273,0.085148714,0.1631499],"study_design_scores_gemma":[0.00014822185,0.000046259403,0.82831484,0.000008792749,0.000046475732,0.000008739619,0.00007637828,0.00037921453,0.000059958,0.15540598,0.015443488,0.0000616509],"about_ca_topic_score_codex":0.00026015245,"about_ca_topic_score_gemma":0.000023497,"teacher_disagreement_score":0.632102,"about_ca_system_score_codex":0.00022331222,"about_ca_system_score_gemma":0.000009202226,"threshold_uncertainty_score":0.14619668},"labels":[],"label_agreement":null},{"id":"W1994102521","doi":"10.1080/01621459.2000.10473920","title":"Inference from Dual Frame Surveys","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Inference; Dual (grammatical number); Frame (networking); Computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.03189687030004611,"score_gpt":0.3681203927843366,"score_spread":0.3362235224842905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994102521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19479558,0.000008541795,0.80251426,0.0010429014,0.00023313392,0.00006998795,0.0003636968,0.000014544287,0.0009573454],"genre_scores_gemma":[0.5511652,0.000026630105,0.44795308,0.0003259013,0.00026018757,0.0000017272497,0.0000025708132,0.000014575576,0.0002500885],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964202,0.0017356492,0.000686193,0.00013249026,0.00076789845,0.0002575362],"domain_scores_gemma":[0.984184,0.014039023,0.001180777,0.00019475645,0.0002731581,0.00012827736],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018551924,0.00013856878,0.0005159377,0.000033775083,0.000097190336,0.00007537329,0.00027163327,0.000056667723,0.0016527275],"category_scores_gemma":[0.01745448,0.00008951999,0.000117070675,0.00029011708,0.00015380117,0.00009683595,0.000034252636,0.0004825275,0.000051407707],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001405264,0.00037785523,0.07821888,0.000014731672,0.00032817243,0.00003639927,0.00039854986,0.000007868507,0.0005503277,0.13111603,0.020299848,0.7685108],"study_design_scores_gemma":[0.00020027632,0.0001371996,0.3765628,0.000030509576,0.00009440362,0.000004942771,0.000032614214,0.00031259676,0.000063317515,0.6220018,0.00046122185,0.000098251156],"about_ca_topic_score_codex":0.00025912808,"about_ca_topic_score_gemma":0.000025510119,"teacher_disagreement_score":0.76841253,"about_ca_system_score_codex":0.00025175963,"about_ca_system_score_gemma":0.000108775515,"threshold_uncertainty_score":0.9992599},"labels":[],"label_agreement":null},{"id":"W1997098670","doi":"10.1198/016214507000000239","title":"Optimal Tests of Noncorrelation Between Multivariate Time Series","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Local asymptotic normality; Mathematics; Series (stratigraphy); Autoregressive model; Applied mathematics; Gaussian; Asymptotic distribution; Multivariate statistics; Diagonal; Covariance matrix; Gaussian process; Representation (politics); Statistics","score_opus":0.01641053598244449,"score_gpt":0.26185173439678344,"score_spread":0.24544119841433895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997098670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72911626,0.000030673345,0.26971853,0.00035424225,0.00016051863,0.00005086335,0.00015028586,0.000003885034,0.0004147569],"genre_scores_gemma":[0.9686225,0.000010787967,0.030961787,0.000031376258,0.00018060724,2.7352792e-7,0.0000036369788,0.0000087851195,0.00018024695],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99861175,0.000042411877,0.00096136983,0.000091095615,0.000123107,0.00017028186],"domain_scores_gemma":[0.996128,0.00069688115,0.0028626353,0.00009283891,0.00017017781,0.00004942364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019573986,0.00007560538,0.0004341333,0.00009680815,0.000066413435,0.000017057675,0.00013988062,0.000049437698,0.00002507935],"category_scores_gemma":[0.0027568366,0.00006558873,0.00011308959,0.00026893493,0.00006425255,0.00018478053,0.000030054569,0.00021547433,0.000028031825],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110026864,0.000060451428,0.9821836,0.0000065186496,0.000077108096,0.0000011081431,0.00035249506,0.0008334359,0.00023491528,0.009960215,0.00035418966,0.0058259843],"study_design_scores_gemma":[0.0002283029,0.00017857559,0.9825797,0.0000140730535,0.000025351557,0.000001292301,0.00003236679,0.0035318455,0.000086378794,0.012716684,0.0005328355,0.000072584065],"about_ca_topic_score_codex":0.00021032727,"about_ca_topic_score_gemma":0.000013250729,"teacher_disagreement_score":0.23950624,"about_ca_system_score_codex":0.00030238437,"about_ca_system_score_gemma":0.000034520872,"threshold_uncertainty_score":0.330039},"labels":[],"label_agreement":null},{"id":"W1997383317","doi":"10.1198/016214508000000382","title":"Covariate Bias Induced by Length-Biased Sampling of Failure Times","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Covariate; Statistics; Estimator; Mathematics; Econometrics; Regression analysis; Sampling (signal processing); Inference; Regression; Computer science","score_opus":0.14623556487301653,"score_gpt":0.3815102829129368,"score_spread":0.23527471803992028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997383317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54687893,0.000011910118,0.4510907,0.0011806102,0.00018534155,0.000110040215,0.00027352653,0.000011905899,0.00025704113],"genre_scores_gemma":[0.6871788,0.000014975739,0.3124964,0.00014238486,0.00007204323,0.0000012731754,0.0000017162447,0.000013710888,0.000078721176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737495,0.0006444748,0.000873891,0.00011200905,0.00076429767,0.00023036446],"domain_scores_gemma":[0.98701,0.009532068,0.0027042078,0.00015974301,0.00049184763,0.00010215237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012636229,0.0001368535,0.0006344572,0.000057289322,0.00011455159,0.000019560339,0.00025204095,0.00005993137,0.00017036517],"category_scores_gemma":[0.029542696,0.000091296955,0.00013598223,0.00032977067,0.00015056037,0.00006665677,0.000044947832,0.00040088582,0.0000048956717],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009018501,0.0020632634,0.07030787,0.00023303955,0.0020148433,0.000044124972,0.003457369,0.00007504028,0.10073579,0.5213243,0.23011948,0.06872307],"study_design_scores_gemma":[0.002206752,0.00177747,0.3414593,0.00027076327,0.00072616315,0.00008579457,0.00076666224,0.0019445971,0.008457794,0.6398403,0.0018407006,0.0006236692],"about_ca_topic_score_codex":0.00008108456,"about_ca_topic_score_gemma":0.0000028521413,"teacher_disagreement_score":0.27115142,"about_ca_system_score_codex":0.00021279778,"about_ca_system_score_gemma":0.00014543915,"threshold_uncertainty_score":0.97863185},"labels":[],"label_agreement":null},{"id":"W1998274033","doi":"10.1198/016214504000000764","title":"Inferences Under a Stochastic Ordering Constraint","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Mathematics; Estimator; Stochastic ordering; Nonparametric statistics; Homogeneity (statistics); Asymptotic distribution; Applied mathematics; Statistical inference; Simple (philosophy); Statistics; Sampling distribution; Empirical distribution function; Statistical hypothesis testing; Combinatorics","score_opus":0.04017065277072272,"score_gpt":0.36461456752232385,"score_spread":0.3244439147516011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998274033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053740215,0.000004848987,0.9396454,0.0058879824,0.00008135016,0.000090610556,0.00013269072,0.000017178898,0.00039968625],"genre_scores_gemma":[0.9545607,0.000002201669,0.044721592,0.00045822436,0.0001288457,0.000005083729,0.0000031358647,0.000007878945,0.00011235602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984984,0.00014625529,0.00056816946,0.0000845439,0.00052169553,0.00018098186],"domain_scores_gemma":[0.9955435,0.0026392469,0.0012445942,0.00010996113,0.00036226536,0.00010046405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047321126,0.000096934724,0.00026586893,0.000042116466,0.00012990578,0.000052209558,0.00018158717,0.000028463735,0.00022908112],"category_scores_gemma":[0.00623105,0.0000666741,0.00008241683,0.00027365846,0.00017172513,0.000083544954,0.000030750205,0.0002499173,0.00003246193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001715049,0.00015499284,0.00067103375,0.00000592356,0.00005251598,4.3337963e-7,0.000082903454,0.0009515716,0.00009784644,0.970834,0.009350684,0.017780952],"study_design_scores_gemma":[0.0008118155,0.00016734425,0.25039124,0.000058940648,0.0002883509,0.000049925067,0.000658178,0.014952787,0.00009212733,0.73100173,0.0012611541,0.00026642802],"about_ca_topic_score_codex":0.000011296861,"about_ca_topic_score_gemma":0.00001743465,"teacher_disagreement_score":0.9008205,"about_ca_system_score_codex":0.00042890015,"about_ca_system_score_gemma":0.00012594897,"threshold_uncertainty_score":0.74595994},"labels":[],"label_agreement":null},{"id":"W1998682508","doi":"10.1080/01621459.2000.10474272","title":"Integer-Valued, Minimax Robust Designs for Estimation and Extrapolation in Heteroscedastic, Approximately Linear Models","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Heteroscedasticity; Mathematics; Minimax; Extrapolation; Polynomial regression; Integer (computer science); Mathematical optimization; Variance (accounting); Regression; Linear regression; Simulated annealing; Minification; Regression analysis; Applied mathematics; Statistics; Computer science","score_opus":0.16231053548561797,"score_gpt":0.43708298046806854,"score_spread":0.27477244498245057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998682508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18272631,0.00003310243,0.81626683,0.00042061982,0.000113490474,0.00024191535,0.000046695513,0.000005839636,0.0001451665],"genre_scores_gemma":[0.5209032,0.0000118488115,0.47876775,0.00012740852,0.000046004476,0.000007105044,0.0000017084252,0.000010335735,0.00012461682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964612,0.0009065037,0.0010808898,0.00022862692,0.0010821453,0.00024060339],"domain_scores_gemma":[0.9934017,0.004643064,0.0013716543,0.00015373851,0.00032897896,0.00010084476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047331722,0.00014046658,0.00047471022,0.00017586708,0.000110332316,0.00016861604,0.0003093254,0.000058187492,0.00005741967],"category_scores_gemma":[0.0075470945,0.00009481218,0.00011116354,0.0005344274,0.00013840172,0.0005503477,0.000031403164,0.0002242605,0.0000073284577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022113076,0.0004691662,0.00941339,0.000018448713,0.00009179724,0.0000062850495,0.0018642645,0.33218512,0.008465904,0.0071948282,0.0027431368,0.63533634],"study_design_scores_gemma":[0.00060029014,0.00043989395,0.022080366,0.00002871306,0.000035591038,0.000012907828,0.00025960887,0.91867095,0.00041206967,0.05729602,0.00005293875,0.00011064161],"about_ca_topic_score_codex":0.00003764842,"about_ca_topic_score_gemma":0.000005739574,"teacher_disagreement_score":0.6352257,"about_ca_system_score_codex":0.0004000427,"about_ca_system_score_gemma":0.00007420917,"threshold_uncertainty_score":0.90351224},"labels":[],"label_agreement":null},{"id":"W1999676174","doi":"10.1198/jasa.2011.ap10446","title":"Bias-Corrected Hierarchical Bayesian Classification With a Selected Subset of High-Dimensional Features","year":2011,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Hyperparameter; Feature selection; Bayesian probability; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Bayesian hierarchical modeling; Machine learning; Bayesian inference; Model selection; Selection (genetic algorithm); Posterior probability; Data mining","score_opus":0.013292552738872391,"score_gpt":0.24270008467118778,"score_spread":0.2294075319323154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999676174","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9699016,0.000026300853,0.02900845,0.00061083876,0.00015526761,0.000099121025,0.00005435002,0.0000050631006,0.00013897005],"genre_scores_gemma":[0.99023604,0.000019081366,0.009211914,0.00017486542,0.000105110084,0.0000045924016,0.000049461367,0.00001307799,0.00018586646],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99854594,0.0003376536,0.00037286215,0.00014912606,0.00044702127,0.00014741489],"domain_scores_gemma":[0.99757487,0.00008907452,0.0014255507,0.00017931742,0.00065176893,0.000079450845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002939388,0.000106144966,0.00022858409,0.000066316235,0.000060794824,0.0000109321445,0.00019157333,0.00006821668,0.000023945635],"category_scores_gemma":[0.00081905205,0.00006678549,0.000066736575,0.00039942507,0.00013816833,0.0000069451908,0.000029367588,0.0002061438,8.485607e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032778757,0.00055659,0.15543216,0.000016499014,0.00042386833,0.0000035304329,0.00030029024,0.00007352152,0.7811547,0.0017043665,0.040300127,0.016756492],"study_design_scores_gemma":[0.0004974593,0.00069934776,0.94664776,0.000022337987,0.0000792414,0.000023358565,0.000086360626,0.00013838294,0.05101348,0.00041000464,0.00028721252,0.00009503766],"about_ca_topic_score_codex":0.00006584737,"about_ca_topic_score_gemma":0.000037841502,"teacher_disagreement_score":0.7912156,"about_ca_system_score_codex":0.00008356864,"about_ca_system_score_gemma":0.00024327636,"threshold_uncertainty_score":0.2723433},"labels":[],"label_agreement":null},{"id":"W1999985320","doi":"10.1198/jasa.2011.tm09650","title":"Fast Robust Model Selection in Large Datasets","year":2011,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Outlier; Covariate; Robust regression; Robustness (evolution); Selection (genetic algorithm); Computer science; Model selection; Robust statistics; Context (archaeology); Linear regression; Ordinary least squares; Feature selection; Regression; Statistic; Mathematics; Statistics; Artificial intelligence","score_opus":0.09881432076865368,"score_gpt":0.39598686108639736,"score_spread":0.29717254031774365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999985320","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022264875,0.0000036977754,0.976631,0.00013603772,0.00008020182,0.000088738365,0.00044038243,0.000008028127,0.00034703684],"genre_scores_gemma":[0.31811085,0.000009493231,0.6815645,0.00015661189,0.000046280653,0.0000026240893,0.0000030895212,0.000013818009,0.00009271374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99821764,0.0003723415,0.00058031856,0.000118805845,0.00043526743,0.00027559814],"domain_scores_gemma":[0.9973028,0.0011538428,0.0011960824,0.00009989982,0.00016335235,0.000084046726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012870778,0.00010915237,0.00037599972,0.00006855569,0.00006917283,0.0000144634705,0.00018528773,0.000039550767,0.000039527156],"category_scores_gemma":[0.005487601,0.000075463366,0.00006853222,0.0002726502,0.000050976283,0.00015297612,0.000050599265,0.00039789957,0.0000028711484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084608607,0.0021731553,0.047801908,0.000081971644,0.00030267492,0.000049201906,0.0023764456,0.0064501474,0.0012384827,0.8616538,0.028312735,0.048713386],"study_design_scores_gemma":[0.0006084786,0.00020255354,0.05012351,0.000038466038,0.00011798631,0.000014787793,0.00018319754,0.11810656,0.00011478441,0.8302403,0.00009593707,0.00015346141],"about_ca_topic_score_codex":0.00003060412,"about_ca_topic_score_gemma":0.0000788464,"teacher_disagreement_score":0.295846,"about_ca_system_score_codex":0.0003989439,"about_ca_system_score_gemma":0.000070851114,"threshold_uncertainty_score":0.6569567},"labels":[],"label_agreement":null},{"id":"W2001201042","doi":"10.1198/jasa.2001.s378","title":"Forecasting Non-Stationary Economic Time Series","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Series (stratigraphy); Econometrics; Time series; Economics; Mathematics; Computer science; Statistics; Geology","score_opus":0.012985963887903107,"score_gpt":0.22397314285613448,"score_spread":0.21098717896823138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001201042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95807046,0.00003546692,0.02668889,0.0030586629,0.0004481323,0.00009634985,0.00039213375,0.0000069933117,0.011202942],"genre_scores_gemma":[0.9918788,0.00005427992,0.0057564494,0.00021353253,0.00020832589,0.0000016203089,0.0000068985614,0.000012362787,0.0018677015],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99890435,0.000050259583,0.00068669853,0.00011130671,0.00007171182,0.00017568142],"domain_scores_gemma":[0.9971881,0.00040561595,0.0021668784,0.00010993239,0.00007156775,0.000057897745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010604928,0.00008297514,0.00034973442,0.00006886791,0.000103404374,0.000055061893,0.00017265767,0.000028824505,0.00034058525],"category_scores_gemma":[0.0008566986,0.00007271912,0.00011536033,0.00013931206,0.000056330635,0.00021638199,0.000037795908,0.00017119976,0.000059216727],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010819129,0.000053429212,0.9751389,0.000005807321,0.00011898752,0.0000060953967,0.000087308385,0.00022126059,0.000012766937,0.010774244,0.009103512,0.0043694847],"study_design_scores_gemma":[0.00027201892,0.00012618997,0.72838455,0.000009286792,0.000017776703,0.00002926157,0.00004317908,0.18147989,0.000002098074,0.07949547,0.010012145,0.00012813194],"about_ca_topic_score_codex":0.00010144916,"about_ca_topic_score_gemma":0.000016217065,"teacher_disagreement_score":0.24675435,"about_ca_system_score_codex":0.0006186758,"about_ca_system_score_gemma":0.000044391265,"threshold_uncertainty_score":0.37291694},"labels":[],"label_agreement":null},{"id":"W2004777611","doi":"10.1080/01621459.2011.646919","title":"Modeling Nonstationary Processes Through Dimension Expansion","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dimension (graph theory); Mathematics; Statistical physics; Applied mathematics; Econometrics; Pure mathematics; Physics","score_opus":0.06798158082999145,"score_gpt":0.38475115521467024,"score_spread":0.3167695743846788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004777611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2541452,0.000055351426,0.74438876,0.0006526106,0.00033183346,0.000082454746,0.000036487243,0.00001187211,0.0002954033],"genre_scores_gemma":[0.62780064,0.00003233654,0.3716712,0.00025398572,0.00019025849,0.000002269968,0.0000011276893,0.00001179697,0.00003638382],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997802,0.0004355042,0.0006155158,0.000089014786,0.00076822244,0.00028972368],"domain_scores_gemma":[0.9933874,0.0046740347,0.0010894897,0.00012437765,0.0006219058,0.000102771766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011532888,0.00012286448,0.00036341566,0.000036127673,0.00014369831,0.000027825483,0.00015969582,0.000039707662,0.0000473848],"category_scores_gemma":[0.021771735,0.000076257245,0.000075725875,0.0003325746,0.000073402116,0.00026118945,0.00005358972,0.00028932813,0.000008983446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074331,0.0024681692,0.11024893,0.00048209142,0.0006354428,0.000017515327,0.0076280795,0.0014987794,0.0056416295,0.7366018,0.043311693,0.09072251],"study_design_scores_gemma":[0.0006339428,0.00043328293,0.03864664,0.0002538785,0.00043756535,0.00006215056,0.0012786685,0.01844033,0.00084497576,0.9380858,0.00051325216,0.0003694936],"about_ca_topic_score_codex":0.000028733719,"about_ca_topic_score_gemma":0.0000021430608,"teacher_disagreement_score":0.3736554,"about_ca_system_score_codex":0.00027688092,"about_ca_system_score_gemma":0.00013193185,"threshold_uncertainty_score":0.9864683},"labels":[],"label_agreement":null},{"id":"W2005308861","doi":"10.1080/01621459.2014.946034","title":"Score Estimating Equations from Embedded Likelihood Functions Under Accelerated Failure Time Model","year":2014,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Medical Research Council; National Institutes of Health; Health Canada; University of Ottawa","keywords":"Estimating equations; Estimator; Accelerated failure time model; Covariate; Proportional hazards model; Independent and identically distributed random variables; Semiparametric model; Statistics; Mathematics; Event (particle physics); Semiparametric regression; Likelihood function; Econometrics; Computer science; Maximum likelihood; Random variable","score_opus":0.04563765243633032,"score_gpt":0.3451408181056067,"score_spread":0.29950316566927637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005308861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028202243,0.0000020534394,0.96899533,0.001873251,0.00021488432,0.000107868975,0.00028262773,0.000030910196,0.00029085288],"genre_scores_gemma":[0.32225114,6.021694e-7,0.6770416,0.0003158784,0.0002427698,0.0000041085295,0.000010778643,0.000020100179,0.00011304428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972904,0.0006973987,0.0007940771,0.00017339023,0.00074127957,0.00030348587],"domain_scores_gemma":[0.9869279,0.010210595,0.0018829292,0.00023842929,0.0005819878,0.00015811007],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011088141,0.00017771227,0.0005440075,0.000069573274,0.0002515173,0.00013043408,0.00028154685,0.00007271207,0.00022826367],"category_scores_gemma":[0.022285992,0.0001235188,0.00013686893,0.00038481475,0.00011027275,0.000151041,0.00006201318,0.0005011046,0.00004668702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020476642,0.0008998914,0.0056383433,0.00005461314,0.0010596777,0.0000064815126,0.0009828515,0.007553226,0.013689626,0.7475683,0.08013009,0.14221212],"study_design_scores_gemma":[0.00024446845,0.00008966265,0.007351783,0.00004656301,0.00022922471,0.000002207374,0.00007150979,0.3726707,0.0000408808,0.6191336,0.000012048902,0.00010734264],"about_ca_topic_score_codex":0.0000409309,"about_ca_topic_score_gemma":0.00001986069,"teacher_disagreement_score":0.3651175,"about_ca_system_score_codex":0.00035825625,"about_ca_system_score_gemma":0.00017836742,"threshold_uncertainty_score":0.9859497},"labels":[],"label_agreement":null},{"id":"W2005773605","doi":"10.1080/01621459.2013.779838","title":"Statistical Learning With Time Series Dependence: An Application to Scoring Sleep in Mice","year":2013,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Sleep and Wakefulness Research","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Institute on Aging","keywords":"Wakefulness; Sleep (system call); Computer science; Key (lock); Artificial intelligence; Machine learning; Eye movement; Psychology; Cognitive psychology; Neuroscience; Electroencephalography","score_opus":0.010472679760954893,"score_gpt":0.29028967242746345,"score_spread":0.27981699266650856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005773605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8827338,0.0000016085377,0.11515646,0.0015928892,0.000047611335,0.00024698366,0.000016781662,0.000013234538,0.00019058917],"genre_scores_gemma":[0.9919469,0.000004095058,0.0074525583,0.00028887062,0.00008404623,0.000025426109,0.0000015270824,0.000015935111,0.00018064059],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99744475,0.00066638686,0.00036689776,0.00020752002,0.000978643,0.00033580532],"domain_scores_gemma":[0.9975413,0.001399559,0.0005314628,0.00011467909,0.00023155987,0.00018141624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064903946,0.00010627755,0.00026053,0.00011702835,0.00015002121,0.00014688948,0.0003279764,0.000029069355,0.00007946396],"category_scores_gemma":[0.0046973475,0.00007177312,0.000024643636,0.00065064884,0.00011992458,0.00045041562,0.00006263629,0.00051757833,0.00013035264],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010752794,0.00056688156,0.44706535,0.00002792235,0.000056787612,0.000071059745,0.0012735439,0.011684991,0.30145618,0.0070424713,0.0011931331,0.22848637],"study_design_scores_gemma":[0.00057996355,0.0014269486,0.95964396,0.000044530334,0.0000358119,0.00006491534,0.00058268546,0.019020094,0.014492702,0.0035897484,0.00026061735,0.00025801087],"about_ca_topic_score_codex":0.000284143,"about_ca_topic_score_gemma":0.0000395361,"teacher_disagreement_score":0.5125786,"about_ca_system_score_codex":0.00041363318,"about_ca_system_score_gemma":0.00008013064,"threshold_uncertainty_score":0.56235033},"labels":[],"label_agreement":null},{"id":"W2011069117","doi":"10.1198/016214506000000267","title":"Algorithms for Constructing Combined Strata Variance Estimators","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Estimator; Variance (accounting); Jackknife resampling; Replicate; Computer science; Algorithm; Consistency (knowledge bases); Replication (statistics); Computation; Efficiency; Mathematics; Statistics; Artificial intelligence","score_opus":0.0797811815395222,"score_gpt":0.4244980670638094,"score_spread":0.3447168855242872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011069117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49928164,0.000026175705,0.4912906,0.0062166117,0.0018394659,0.00022978446,0.00016698176,0.00002054359,0.00092817144],"genre_scores_gemma":[0.74061394,0.0000051026714,0.2580405,0.00023233582,0.00054824416,0.000003092548,0.0000029106072,0.000008019499,0.00054587796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994566,0.00439409,0.00036208535,0.00007791834,0.00037882818,0.00022104986],"domain_scores_gemma":[0.9731146,0.025137363,0.0013103455,0.00006148243,0.0003240726,0.000052123716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013930494,0.00006198693,0.00025227424,0.00003496386,0.00034647668,0.00004493147,0.00019704198,0.000051986448,0.000018690953],"category_scores_gemma":[0.041247796,0.000047214085,0.00008583308,0.00025910765,0.00032924736,0.00009607006,0.000013870232,0.00019451404,0.0000018263177],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00509085,0.00036594327,0.64315647,0.000015815987,0.00039385966,0.00002286482,0.0018006059,0.0002504706,0.0018243948,0.23121078,0.05505269,0.060815264],"study_design_scores_gemma":[0.00089882937,0.00027172978,0.9101247,0.000019951032,0.00014093114,0.000009616708,0.0018081091,0.00032080436,0.00027177963,0.08014404,0.0058323513,0.00015710812],"about_ca_topic_score_codex":0.00060048694,"about_ca_topic_score_gemma":0.000133161,"teacher_disagreement_score":0.26696828,"about_ca_system_score_codex":0.00027709073,"about_ca_system_score_gemma":0.0003017381,"threshold_uncertainty_score":0.96682817},"labels":[],"label_agreement":null},{"id":"W2013385108","doi":"10.1198/jasa.2010.tm09757","title":"Estimability and Likelihood Inference for Generalized Linear Mixed Models Using Data Cloning","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":177,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Generalized linear mixed model; Estimator; Likelihood function; Binary data; Random effects model; Restricted maximum likelihood; Mathematics; Quasi-likelihood; Frequentist inference; Computer science; Markov chain Monte Carlo; Generalized linear model; Statistics; Poisson distribution; Bayesian probability; Bayesian inference; Binary number; Count data; Estimation theory","score_opus":0.11425867505733692,"score_gpt":0.43789684397732387,"score_spread":0.323638168919987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013385108","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20634434,0.0000052001615,0.7924123,0.00044074218,0.0002585527,0.0001303252,0.00038911635,0.0000073632114,0.000012108287],"genre_scores_gemma":[0.28868285,0.0000052418272,0.7110628,0.000076231205,0.0001524334,0.0000018318154,0.000003163435,0.000011400957,0.000004038407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981643,0.00035307958,0.0006289851,0.00019238671,0.00040619567,0.00025507042],"domain_scores_gemma":[0.98775226,0.009871079,0.0014235302,0.00034512652,0.000475589,0.00013241512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024602346,0.00013083784,0.0004918395,0.000037113674,0.0001553256,0.000073295334,0.00037945545,0.00005985384,0.000012263188],"category_scores_gemma":[0.04174762,0.00008836607,0.00006099053,0.00015383141,0.00018252149,0.00019486899,0.0001673457,0.00044544088,2.6794416e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046648103,0.0004993326,0.032550845,0.00021779616,0.00040265772,0.000007142893,0.00042133266,0.00011045142,0.018990243,0.73762584,0.002407801,0.2063001],"study_design_scores_gemma":[0.0003280684,0.000090474416,0.009567684,0.000022633063,0.00022189792,0.000009470713,0.000025671096,0.31877008,0.00011288621,0.6707269,0.000032730255,0.00009154668],"about_ca_topic_score_codex":0.00009889706,"about_ca_topic_score_gemma":0.000048155143,"teacher_disagreement_score":0.3186596,"about_ca_system_score_codex":0.000103162354,"about_ca_system_score_gemma":0.00018736845,"threshold_uncertainty_score":0.96632415},"labels":[],"label_agreement":null},{"id":"W2014115301","doi":"10.1198/016214507000000473","title":"How Useful Is Bagging in Forecasting Economic Time Series? A Case Study of U.S. Consumer Price Inflation","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Econometrics; Lasso (programming language); Inflation (cosmology); Bayesian probability; Mean squared error; Statistics; Consensus forecast; Bayesian inference; Time series; Regression; Probabilistic forecasting; Computer science; Mathematics","score_opus":0.07910127971310305,"score_gpt":0.34697885867041867,"score_spread":0.2678775789573156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014115301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907372,0.0000051895195,0.007702205,0.0011329758,0.00005413175,0.00020316147,0.000043029537,0.0000074557115,0.000114650036],"genre_scores_gemma":[0.98919225,0.000006336158,0.010469355,0.00005800305,0.00004888,0.0000048655756,5.0872774e-7,0.0000084164885,0.00021141527],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976753,0.00033582665,0.00095230964,0.0001607427,0.0007119071,0.0001639387],"domain_scores_gemma":[0.99338335,0.0023984758,0.0035255107,0.00021950874,0.00041614694,0.0000569844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020853004,0.00009601612,0.0004137661,0.0001924931,0.00016364886,0.0000815324,0.00030396934,0.000030940286,0.000030399837],"category_scores_gemma":[0.0049834205,0.000066690016,0.00008277436,0.0006405874,0.00011568359,0.0003320835,0.00008498799,0.00022771032,0.0000065202926],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001034682,0.00033215014,0.9592637,0.000003971083,0.00008405538,0.00017730809,0.004132865,0.0009910652,0.0002622517,0.00028197194,0.013909462,0.020457758],"study_design_scores_gemma":[0.002036513,0.00190586,0.86871296,0.000088004046,0.00018517626,0.004241445,0.012556009,0.08716061,0.0004906814,0.018083826,0.0040431307,0.0004958053],"about_ca_topic_score_codex":0.00039001016,"about_ca_topic_score_gemma":0.00012865537,"teacher_disagreement_score":0.09055073,"about_ca_system_score_codex":0.00039609903,"about_ca_system_score_gemma":0.00012683292,"threshold_uncertainty_score":0.59659797},"labels":[],"label_agreement":null},{"id":"W2016209757","doi":"10.1080/01621459.2013.859076","title":"Estimating the Lifetime Risk of Dementia in the Canadian Elderly Population Using Cross-Sectional Cohort Survival Data","year":2013,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Dementia; Population; Cohort; Estimation; Stratified sampling; Estimator; Cross-sectional study; Epidemiology; Cohort study; Medicine; Gerontology; Demography; Statistics; Environmental health; Economics; Mathematics; Disease","score_opus":0.07705459751595742,"score_gpt":0.4031104678716724,"score_spread":0.3260558703557149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016209757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8178567,0.000007707673,0.18072043,0.00044710893,0.0003107552,0.00022801578,0.0002956772,0.0000026868665,0.00013089365],"genre_scores_gemma":[0.7944309,0.0000020398434,0.20531514,0.00008399965,0.00014248033,0.0000025877112,0.000007774125,0.000008305432,0.0000067678175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963935,0.0014739459,0.0008727,0.00012621767,0.00089501485,0.00023861302],"domain_scores_gemma":[0.98852444,0.008429274,0.002228896,0.0003308658,0.00041587054,0.00007064372],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005614559,0.00010522266,0.00031356068,0.00005837191,0.00031213294,0.00017172098,0.00063127594,0.00004583801,0.00011297416],"category_scores_gemma":[0.029834237,0.00005490945,0.000062909814,0.0003286945,0.00015942835,0.0001626085,0.00007109417,0.0004834299,0.000002936083],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000087264625,0.00003535487,0.98844755,0.000007459889,0.00011779679,7.8509703e-7,0.00008799783,0.00040964386,0.000017732335,0.0068760524,0.0006436957,0.0033472362],"study_design_scores_gemma":[0.00011238383,0.000053645486,0.82147837,0.000017575305,0.00015172432,0.000006343994,0.000067779845,0.06916691,0.0000014105857,0.10888127,0.0000084803005,0.000054084856],"about_ca_topic_score_codex":0.12025145,"about_ca_topic_score_gemma":0.010862918,"teacher_disagreement_score":0.16696914,"about_ca_system_score_codex":0.00038013357,"about_ca_system_score_gemma":0.00021003956,"threshold_uncertainty_score":0.9783379},"labels":[],"label_agreement":null},{"id":"W2016979665","doi":"10.1080/01621459.2000.10474271","title":"Bayesian Regression Modeling with Interactions and Smooth Effects","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Bayesian linear regression; Bayesian probability; Interpretation (philosophy); Machine learning; Regression; Computation; Artificial intelligence; Bivariate analysis; Model selection; Regression analysis; Bayesian inference; Econometrics; Data mining; Algorithm; Mathematics; Statistics","score_opus":0.017252388416330745,"score_gpt":0.3433515887195779,"score_spread":0.3260992003032471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016979665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12152432,0.000009046663,0.8769919,0.00083806313,0.0000714718,0.00007524546,0.00001494011,0.000008778742,0.00046623644],"genre_scores_gemma":[0.56545484,0.000020677644,0.43421045,0.00013263877,0.00007376256,0.00000129208,3.1173565e-7,0.00001051728,0.00009548999],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857825,0.0004022622,0.00035182695,0.00010124053,0.0004001271,0.00016632218],"domain_scores_gemma":[0.9954682,0.0035624728,0.00061863224,0.00010586844,0.00014565073,0.000099201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046046101,0.00010920406,0.0003410864,0.00003968521,0.00012559343,0.000053138167,0.00010387298,0.000023745855,0.000090236914],"category_scores_gemma":[0.0026622375,0.000058371137,0.000046890626,0.00018291855,0.0000828465,0.0000998552,0.00001712445,0.00032624722,0.0000022164384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006089879,0.00029848123,0.010513041,0.000096325755,0.00026170665,0.00004445596,0.0006721581,0.00009502655,0.00052860193,0.10641091,0.003835933,0.87663436],"study_design_scores_gemma":[0.0008198523,0.0007630273,0.039537005,0.00055113895,0.00044145426,0.00010804359,0.00021715174,0.06736735,0.00012652742,0.88952273,0.0002958965,0.00024981835],"about_ca_topic_score_codex":0.000032047235,"about_ca_topic_score_gemma":0.0000110880155,"teacher_disagreement_score":0.87638456,"about_ca_system_score_codex":0.00015536854,"about_ca_system_score_gemma":0.000042999574,"threshold_uncertainty_score":0.31871393},"labels":[],"label_agreement":null},{"id":"W2019293164","doi":"10.1198/016214501750333054","title":"A Model-Calibration Approach to Using Complete Auxiliary Information From Survey Data","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":336,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Calibration; Mathematics; Population; Applied mathematics; Statistics; Function (biology); Linear model; Linear regression","score_opus":0.3089299026417691,"score_gpt":0.40148143882740894,"score_spread":0.09255153618563983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019293164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1515126,0.0000021868777,0.8468643,0.00027687213,0.00009050858,0.00012562843,0.0009861162,0.000028427487,0.0001133628],"genre_scores_gemma":[0.5034769,0.0000051353904,0.49580017,0.00039957417,0.00007737453,0.0000016065515,0.00021549119,0.000010973275,0.000012748945],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976723,0.00061955664,0.0007398689,0.00011197351,0.0006878681,0.0001684382],"domain_scores_gemma":[0.9953274,0.0021752787,0.0016493783,0.0003621212,0.0003976223,0.000088158464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028246206,0.0001130429,0.00034490306,0.00009679256,0.00012398152,0.00012099573,0.00046601516,0.000045376262,0.000008002173],"category_scores_gemma":[0.01071689,0.000084510946,0.000048599475,0.0004255622,0.000036577425,0.00067068235,0.00013372302,0.00022631895,0.000004276264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021036563,0.0016733039,0.48658213,0.000114448245,0.0012598366,0.0000052469923,0.0052321167,0.08409233,0.0023840687,0.016104195,0.31866652,0.081782155],"study_design_scores_gemma":[0.00017713083,0.000043879183,0.085709184,0.000026723132,0.0000793587,0.000006839372,0.00008444121,0.87082064,0.000017453469,0.042746373,0.00016999478,0.00011797904],"about_ca_topic_score_codex":0.00094075146,"about_ca_topic_score_gemma":0.00004882612,"teacher_disagreement_score":0.7867283,"about_ca_system_score_codex":0.00036031232,"about_ca_system_score_gemma":0.00012063363,"threshold_uncertainty_score":0.9976163},"labels":[],"label_agreement":null},{"id":"W2020483759","doi":"10.1198/016214507000001076","title":"Rank-Based Extensions of the Brock, Dechert, and Scheinkman Test","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Mathematics; Rank (graph theory); Statistic; Test statistic; Statistical hypothesis testing; Randomness; Monte Carlo method; Statistics; Series (stratigraphy); Null hypothesis; Asymptotic distribution; Applied mathematics; Margin (machine learning); Econometrics; Statistical physics; Computer science; Estimator","score_opus":0.013167351677924346,"score_gpt":0.22880885540478174,"score_spread":0.2156415037268574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020483759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8972429,0.00041580005,0.09667784,0.0037059,0.00032263188,0.00013619338,0.00023134988,0.000005581781,0.0012617839],"genre_scores_gemma":[0.99654824,0.000016915405,0.002730997,0.00026207548,0.000065299355,3.7903934e-7,5.3286124e-7,0.0000070204023,0.00036853866],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989314,0.000046990353,0.00068838993,0.00008402364,0.00011318231,0.00013598728],"domain_scores_gemma":[0.9963925,0.0009674861,0.0023027263,0.00014576953,0.00013993689,0.0000516076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008483477,0.00006717912,0.00037699073,0.00007182327,0.00010900432,0.000025037407,0.0001602901,0.000027179713,0.000047316134],"category_scores_gemma":[0.0022442995,0.00004384503,0.00015760616,0.0003825282,0.00009680531,0.00004470401,0.000039843217,0.00016186695,0.0000044816843],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003119599,0.00011580141,0.9750131,0.000010230481,0.00016967044,0.0000014224177,0.00007643132,0.00007782073,0.0005113291,0.015444348,0.003153326,0.0053953603],"study_design_scores_gemma":[0.00027847095,0.00009232855,0.9867739,0.000018410405,0.00005322116,0.0000041790063,0.000107521,0.0020143748,0.000070999515,0.006507841,0.004015067,0.00006366695],"about_ca_topic_score_codex":0.00043860247,"about_ca_topic_score_gemma":0.00014930747,"teacher_disagreement_score":0.099305324,"about_ca_system_score_codex":0.00016196867,"about_ca_system_score_gemma":0.000026914504,"threshold_uncertainty_score":0.26867983},"labels":[],"label_agreement":null},{"id":"W2021856897","doi":"10.1080/01621459.2000.10473894","title":"Functional Components of Variation in Handwriting","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Handwriting; Scripting language; Smoothing; Computer science; Replication (statistics); Variation (astronomy); Sample (material); Function (biology); Forcing (mathematics); Differential equation; Process (computing); Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics; Mathematical analysis","score_opus":0.012201554428516902,"score_gpt":0.2457886473898067,"score_spread":0.23358709296128982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021856897","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67489403,0.000010177463,0.3209411,0.003685971,0.00012518668,0.000060050614,0.000009768472,0.0000056482795,0.0002680655],"genre_scores_gemma":[0.98648375,0.000013331287,0.013141072,0.00020331143,0.00007307736,0.0000011577308,9.026224e-7,0.0000021727847,0.00008122829],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99899703,0.0001329247,0.00036186064,0.000065093,0.00034709886,0.00009597906],"domain_scores_gemma":[0.9986126,0.0004595698,0.00071114895,0.00008396291,0.000105130326,0.000027630223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000385281,0.00004134712,0.0001462574,0.00003549564,0.000047364585,0.000025633948,0.00021856108,0.00001335657,0.000026562093],"category_scores_gemma":[0.00013542884,0.000030156449,0.000045769924,0.00038899377,0.00002603478,0.00013651917,0.00002282197,0.00013618173,0.000004524808],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022193693,0.0011822016,0.16818841,0.000021664984,0.0001994178,0.000011886974,0.00084111374,0.034871362,0.032616384,0.14917637,0.017680615,0.59498864],"study_design_scores_gemma":[0.0002174785,0.00004700664,0.9645816,0.000016505817,0.000008436038,0.0000056806466,0.0000055738474,0.02611344,0.00007330286,0.008513518,0.00038120698,0.000036266523],"about_ca_topic_score_codex":0.00005875548,"about_ca_topic_score_gemma":0.0000047544268,"teacher_disagreement_score":0.79639316,"about_ca_system_score_codex":0.00012604176,"about_ca_system_score_gemma":0.000027745038,"threshold_uncertainty_score":0.122974426},"labels":[],"label_agreement":null},{"id":"W2025512415","doi":"10.1080/01621459.2013.787184","title":"Heteroscedasticity and Autocorrelation Robust Structural Change Detection","year":2013,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Heteroscedasticity; Autocorrelation; Series (stratigraphy); Monte Carlo method; Econometrics; Statistical hypothesis testing; Computer science; Sequential analysis; Mathematics; Statistics","score_opus":0.02244347246530303,"score_gpt":0.21415580678490803,"score_spread":0.191712334319605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025512415","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92735976,0.00008688211,0.07081964,0.001008637,0.00035071204,0.00014981945,0.000052803487,0.0000062496315,0.0001654793],"genre_scores_gemma":[0.9982336,0.000013338308,0.0013213031,0.00011852367,0.0001778359,0.000008207468,0.000001064067,0.000006350354,0.000119783515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99917567,0.00005248955,0.00048053756,0.00009190231,0.00007789666,0.00012152353],"domain_scores_gemma":[0.99790263,0.00014816527,0.0017257568,0.00007180622,0.000100423975,0.000051225135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029511578,0.00006842565,0.00029724094,0.00007218139,0.000109855915,0.00008986992,0.000073509626,0.000025808864,0.00017526693],"category_scores_gemma":[0.0004841074,0.000053128504,0.00007934875,0.00021287354,0.00004102529,0.0002516813,0.000028905955,0.0001372562,0.000028454737],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028170394,0.00003188485,0.94728446,0.000018460061,0.00025301243,8.0338424e-7,0.0003902099,0.00033635047,0.0001700426,0.017151352,0.0010039303,0.033331335],"study_design_scores_gemma":[0.00013276724,0.00009438296,0.9492941,0.000005302397,0.000021414193,0.0000061929095,0.000050964933,0.0381872,0.000004976247,0.011691811,0.00044682465,0.000064048945],"about_ca_topic_score_codex":0.0018443298,"about_ca_topic_score_gemma":0.00006514948,"teacher_disagreement_score":0.07087381,"about_ca_system_score_codex":0.0002514213,"about_ca_system_score_gemma":0.000004690512,"threshold_uncertainty_score":0.2788087},"labels":[],"label_agreement":null},{"id":"W2026428710","doi":"10.1198/016214506000001004","title":"Episodic Nonlinear Event Detection in the Canadian Exchange Rate","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Exchange rate; Liberian dollar; Econometrics; Us dollar; Economics; Event (particle physics); Financial economics; Monetary economics; Physics; Finance","score_opus":0.013133348872552303,"score_gpt":0.24801750815693602,"score_spread":0.23488415928438372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026428710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9360868,0.00007557246,0.05473959,0.0052572945,0.0006020801,0.00016496006,0.00019133306,0.000002718696,0.0028796836],"genre_scores_gemma":[0.9984297,0.000029285098,0.000547452,0.0007456616,0.00013936324,0.0000011859032,0.0000020757839,0.000005655912,0.00009962802],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99887115,0.0001405352,0.00058142823,0.00008481354,0.00009696469,0.00022511385],"domain_scores_gemma":[0.99802405,0.0005380902,0.001189327,0.000109828296,0.00006877877,0.00006991039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064840615,0.00006329856,0.00021867076,0.00014017739,0.000118339296,0.000048854952,0.00018843701,0.000037557933,0.000046936275],"category_scores_gemma":[0.0017253653,0.000045430956,0.00008108198,0.00037801653,0.00004076775,0.000062325256,0.000013014299,0.00032058032,0.000009845457],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074272044,0.00009883579,0.95458573,0.000008984794,0.00005283142,0.000013456855,0.0004996235,0.000028201235,0.000012555938,0.007466232,0.0009094734,0.036249787],"study_design_scores_gemma":[0.00016729982,0.000070267284,0.96000296,0.0000040963923,0.0000074148074,0.0000037722084,0.000068568486,0.014149972,0.0000032420667,0.016703013,0.008762725,0.000056646488],"about_ca_topic_score_codex":0.037476253,"about_ca_topic_score_gemma":0.23526199,"teacher_disagreement_score":0.19778574,"about_ca_system_score_codex":0.0012457144,"about_ca_system_score_gemma":0.00005297965,"threshold_uncertainty_score":0.9689333},"labels":[],"label_agreement":null},{"id":"W2027764114","doi":"10.1198/016214502760047069","title":"Efficient Estimation of Quadratic Finite Population Functions in the Presence of Auxiliary Information","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Mathematics; Population; Covariance; Quadratic equation; Applied mathematics; Correctness; Linear model; Variance (accounting); Mathematical optimization; Statistics; Algorithm","score_opus":0.0370660623633208,"score_gpt":0.3227786959343425,"score_spread":0.2857126335710217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027764114","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59398854,0.000007716496,0.40493193,0.00061199616,0.00010534714,0.0001752467,0.00004798564,0.000009860402,0.00012134587],"genre_scores_gemma":[0.97421443,0.00000494835,0.025684768,0.00004572996,0.000018395234,0.0000050672625,0.000006865932,0.000004310383,0.000015462738],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976603,0.000541033,0.0009539846,0.0000463917,0.0006956128,0.00010268599],"domain_scores_gemma":[0.99166864,0.0051509514,0.0026879336,0.00015776975,0.0003149657,0.00001972527],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021199253,0.000075436394,0.00026739461,0.00015063141,0.00006219118,0.00002095134,0.0001764516,0.00003561394,0.000019879926],"category_scores_gemma":[0.016032476,0.000047362893,0.000080148384,0.0005612082,0.000066187065,0.00015712646,0.000017021925,0.00019480706,0.0000028113543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036847574,0.0022740266,0.24193141,0.0006308251,0.0002885135,0.0000023983198,0.018706704,0.5115259,0.00035070174,0.050738387,0.029256396,0.14392626],"study_design_scores_gemma":[0.0002979961,0.00023431316,0.43127984,0.00015496157,0.00010564246,0.0000065506097,0.0006660962,0.53228456,0.00010370116,0.03475854,0.000022941058,0.000084856976],"about_ca_topic_score_codex":0.00016799146,"about_ca_topic_score_gemma":0.000012404022,"teacher_disagreement_score":0.3802259,"about_ca_system_score_codex":0.00017092393,"about_ca_system_score_gemma":0.000024182928,"threshold_uncertainty_score":0.9922559},"labels":[],"label_agreement":null},{"id":"W2029555586","doi":"10.1198/016214506000000195","title":"Estimation in Multiple-Frame Surveys","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Estimator; Frame (networking); Sampling (signal processing); Variance (accounting); Sampling frame; Statistics; Mathematics; Population; Maximum likelihood; M-estimator; Computer science; Econometrics","score_opus":0.03637944048334951,"score_gpt":0.34047377115739413,"score_spread":0.3040943306740446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029555586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44609222,0.0000047255107,0.55299085,0.00055286306,0.00011018734,0.00007417675,0.000024662057,0.000024026824,0.00012631527],"genre_scores_gemma":[0.87585145,0.0000027096369,0.123927146,0.000050199862,0.000060468392,0.0000027261965,0.0000045526713,0.000011111963,0.000089634595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976638,0.0009319886,0.0006662408,0.00007709691,0.0004950229,0.00016583744],"domain_scores_gemma":[0.9926225,0.005438537,0.0015764481,0.000115819465,0.00021664033,0.000030067375],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0039516534,0.00009004686,0.00030756052,0.00010478958,0.000059855138,0.00004044904,0.00015524005,0.000042074404,0.000011580361],"category_scores_gemma":[0.01442054,0.000064748034,0.000076297445,0.00036195086,0.0000568738,0.00010694275,0.000021195352,0.00026272677,0.00000514343],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006794787,0.00046715874,0.9052087,0.000030278625,0.00005819692,0.0000063016428,0.00016631583,0.0022945942,0.00060579664,0.015405479,0.025387194,0.050302032],"study_design_scores_gemma":[0.0002629557,0.000060582297,0.7566481,0.00003740126,0.000024512146,0.000006132951,0.000025793628,0.013191354,0.00031824288,0.22928551,0.000061155944,0.00007821687],"about_ca_topic_score_codex":0.00062767864,"about_ca_topic_score_gemma":0.00018859516,"teacher_disagreement_score":0.42975923,"about_ca_system_score_codex":0.0005018514,"about_ca_system_score_gemma":0.000053965756,"threshold_uncertainty_score":0.9938814},"labels":[],"label_agreement":null},{"id":"W2029653161","doi":"10.1198/016214504000000340","title":"Robust Analysis of Generalized Linear Mixed Models","year":2004,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Research Manitoba","funders":"","keywords":"Generalized linear mixed model; Outlier; Likelihood function; Mathematics; Estimator; Generalized linear model; M-estimator; Applied mathematics; Maximum likelihood; Restricted maximum likelihood; Monte Carlo method; Algorithm; Statistics","score_opus":0.10742562777369924,"score_gpt":0.40104898200332,"score_spread":0.29362335422962077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029653161","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109616436,0.000012485945,0.8893602,0.0005276671,0.00011214772,0.00007172296,0.00020134,0.0000069045277,0.000091107446],"genre_scores_gemma":[0.35519144,0.000022379203,0.6445659,0.0001026977,0.000051332718,0.0000013449518,0.0000024051835,0.000011523629,0.000051032766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976311,0.00040237795,0.000890609,0.00012206701,0.0007381859,0.00021567137],"domain_scores_gemma":[0.9941506,0.0025272325,0.0024825893,0.00019286608,0.0005421922,0.00010453904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011153859,0.00012612146,0.0008753982,0.00014562428,0.00006498527,0.0000130201515,0.0002239033,0.00004401411,0.000020455767],"category_scores_gemma":[0.0059836623,0.000082759056,0.00032753113,0.0008396449,0.00012052658,0.00010174498,0.000044526623,0.00025119868,7.3481596e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020659607,0.00038332152,0.00087080535,0.000024944185,0.00238194,0.000008919016,0.00036027638,0.31488317,0.0010501511,0.67206717,0.00072834577,0.007034392],"study_design_scores_gemma":[0.0006767398,0.00018434475,0.0067396886,0.000025134721,0.0025323175,0.000003246369,0.00010342063,0.062045787,0.00035063908,0.9271874,0.000031813786,0.000119462806],"about_ca_topic_score_codex":0.000067554574,"about_ca_topic_score_gemma":0.000027182412,"teacher_disagreement_score":0.25512028,"about_ca_system_score_codex":0.00039655843,"about_ca_system_score_gemma":0.00009833096,"threshold_uncertainty_score":0.71634346},"labels":[],"label_agreement":null},{"id":"W2031042604","doi":"10.1080/01621459.2000.10474291","title":"Statistics in Reliability","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo","funders":"","keywords":"Statistics; Reliability (semiconductor); Mathematics; Econometrics; Physics","score_opus":0.017834282569733427,"score_gpt":0.34765428146123367,"score_spread":0.32981999889150027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031042604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22388664,0.0000050955578,0.76945174,0.0036866304,0.00012352491,0.00021292725,0.0009749421,0.000020041452,0.0016384681],"genre_scores_gemma":[0.9136285,0.000018836847,0.08518251,0.0003796062,0.00006621839,0.0000070956485,0.000009862027,0.000011438895,0.00069588533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9980251,0.00033208693,0.00077053875,0.00010422278,0.00056952634,0.00019852884],"domain_scores_gemma":[0.9953957,0.0032072742,0.00085395685,0.000172778,0.0002821155,0.00008817278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008890019,0.000095112926,0.0003181504,0.00004034354,0.00007657933,0.00003068256,0.00020850725,0.0000332016,0.0008648052],"category_scores_gemma":[0.008600145,0.00006753,0.000067019515,0.00045776562,0.00013637109,0.00007284143,0.000016066502,0.0003132773,0.000052028947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012583968,0.00060262776,0.025465112,0.000022895441,0.000042707034,0.000007667694,0.0001434259,0.0002014047,0.000045733923,0.8211724,0.08720891,0.06496124],"study_design_scores_gemma":[0.0003774388,0.00007095395,0.49949694,0.000018347073,0.00005322603,0.000008328673,0.00004373098,0.0028204643,0.00001612776,0.49365327,0.0033503268,0.00009086868],"about_ca_topic_score_codex":0.00003864676,"about_ca_topic_score_gemma":0.000019318793,"teacher_disagreement_score":0.6897419,"about_ca_system_score_codex":0.00056516693,"about_ca_system_score_gemma":0.00009530322,"threshold_uncertainty_score":0.99975085},"labels":[],"label_agreement":null},{"id":"W2032234757","doi":"10.1198/jasa.2010.tm08551","title":"Weighted Generalized Estimating Functions for Longitudinal Response and Covariate Data That Are Missing at Random","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Missing data; Estimator; Statistics; Estimating equations; Econometrics; Mathematics; Random effects model; Generalized estimating equation; Computer science; Meta-analysis; Medicine","score_opus":0.10742718450881653,"score_gpt":0.40376227920922436,"score_spread":0.29633509470040786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032234757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15455438,0.000008321115,0.8412741,0.0027968497,0.00051201944,0.00015532767,0.0006748457,0.000010979832,0.000013170128],"genre_scores_gemma":[0.13060673,0.00000332493,0.86889327,0.00012306514,0.00023862574,0.000004715508,0.000008762033,0.000017381364,0.000104131104],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997834,0.00073676795,0.00055509707,0.00019756559,0.0004384855,0.00023805053],"domain_scores_gemma":[0.9762046,0.020913452,0.0021282355,0.00030472325,0.00031720195,0.00013182744],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032643066,0.00013960987,0.0005305505,0.000054609252,0.00037271716,0.000118937576,0.0002706059,0.000055341337,0.00005607789],"category_scores_gemma":[0.047789305,0.00009153788,0.000075470576,0.00015392192,0.00016997932,0.00012997609,0.00014334584,0.0003649281,0.0000014728447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025674772,0.00090285967,0.31268454,0.00040062732,0.0020473711,0.00008662557,0.0008717208,0.000017982626,0.050846625,0.15865436,0.12189971,0.3259128],"study_design_scores_gemma":[0.0034740495,0.0002743621,0.31785038,0.00012583144,0.0009579451,0.00013743076,0.00013260967,0.08624647,0.00023970462,0.5890059,0.0012653647,0.00028995768],"about_ca_topic_score_codex":0.000026064778,"about_ca_topic_score_gemma":0.000037868038,"teacher_disagreement_score":0.43035153,"about_ca_system_score_codex":0.0001611026,"about_ca_system_score_gemma":0.00009607624,"threshold_uncertainty_score":0.96023154},"labels":[],"label_agreement":null},{"id":"W2032301741","doi":"10.1198/jasa.2003.s307","title":"Multivariate Dispersion, Central Regions and Depth: the Lift Zonoid Approach. Karl Mosler","year":2003,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lift (data mining); Multivariate statistics; Dispersion (optics); Geology; Mathematics; Geodesy; Statistics; Geography; Environmental science; Computer science; Physics; Optics; Data mining","score_opus":0.03287875679416995,"score_gpt":0.32827403949704836,"score_spread":0.2953952827028784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032301741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015108196,0.000029384735,0.9813469,0.0020737092,0.00023041446,0.00015185667,0.00005478893,0.000009002253,0.000995762],"genre_scores_gemma":[0.4774053,0.000039323815,0.52193415,0.00034981838,0.00011116921,0.000003652229,7.844944e-7,0.000015623114,0.00014016054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997318,0.0011972415,0.0005153038,0.00013945388,0.00051172136,0.00031825242],"domain_scores_gemma":[0.9926101,0.005678814,0.0011653793,0.00018631131,0.0002096537,0.00014972757],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012567827,0.00014432766,0.0003869115,0.00003207164,0.00024585784,0.000082618804,0.0002138083,0.000046356054,0.000030394307],"category_scores_gemma":[0.018434567,0.00007417951,0.00010752927,0.00025778988,0.00025646287,0.00007718916,0.00004435462,0.00044737718,0.0000025337715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055949182,0.00021218378,0.019429496,0.00001898665,0.00017153774,0.0000048962434,0.0006313539,0.0000062763975,0.0001823104,0.9531737,0.011510911,0.014602384],"study_design_scores_gemma":[0.00051164115,0.00016032107,0.25823697,0.000037751346,0.00032136997,0.000055795437,0.00068972365,0.001960213,0.00006138637,0.73597896,0.0018112004,0.00017469311],"about_ca_topic_score_codex":0.00005167153,"about_ca_topic_score_gemma":0.000009257558,"teacher_disagreement_score":0.4622971,"about_ca_system_score_codex":0.00020374976,"about_ca_system_score_gemma":0.000084075975,"threshold_uncertainty_score":0.9898336},"labels":[],"label_agreement":null},{"id":"W2032594307","doi":"10.1198/016214505000000042","title":"A Unified Nonparametric Approach for Unbalanced Factorial Designs","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mathematics; Estimator; Nonparametric statistics; Rank (graph theory); Statistical hypothesis testing; Statistics; Asymptotic distribution; Covariance; Null hypothesis; Factorial; Monte Carlo method; Combinatorics","score_opus":0.015470364516804018,"score_gpt":0.2763856955835969,"score_spread":0.2609153310667929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032594307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1725934,0.000035071233,0.82640886,0.0002410293,0.00026253622,0.00013877107,0.000066048575,0.0000022209213,0.00025205483],"genre_scores_gemma":[0.72414994,0.0000063913767,0.27449143,0.00018438017,0.00089025055,0.000004025966,0.000011005877,0.000008031792,0.00025454396],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99910647,0.00012224079,0.00027259154,0.0001033324,0.0002299698,0.00016541846],"domain_scores_gemma":[0.9987717,0.00020018665,0.0006695737,0.00010588038,0.00019287317,0.000059742226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032261034,0.00008295302,0.00018528872,0.000027047916,0.000061223196,0.000018957564,0.00019517411,0.000052603697,0.0000043979053],"category_scores_gemma":[0.0012720104,0.00005801547,0.000105756815,0.00013654283,0.000056010846,0.0000032523074,0.000023543085,0.00011073728,0.0000010903988],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006552049,0.0026469924,0.0986525,0.00009595113,0.0026073034,8.945705e-7,0.0008748378,0.062654085,0.25015274,0.047638193,0.27634096,0.25178352],"study_design_scores_gemma":[0.00527273,0.0053656576,0.89676845,0.00001741765,0.00057861436,0.000032244378,0.00029006798,0.0022493135,0.019532297,0.015441405,0.053767204,0.0006846201],"about_ca_topic_score_codex":0.000004511637,"about_ca_topic_score_gemma":0.0000016193884,"teacher_disagreement_score":0.7981159,"about_ca_system_score_codex":0.000093257884,"about_ca_system_score_gemma":0.00010213802,"threshold_uncertainty_score":0.23658022},"labels":[],"label_agreement":null},{"id":"W2035260443","doi":"10.1198/016214501753208546","title":"Multiple Test Procedures for Identifying the Maximum Safe Dose","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pairwise comparison; Monotonic function; Computer science; Multiple comparisons problem; Monte Carlo method; Mathematics; Sequence (biology); Statistics; Reliability engineering; Algorithm; Engineering","score_opus":0.3033497489109927,"score_gpt":0.5236922743536984,"score_spread":0.22034252544270566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035260443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04314935,0.000032042804,0.9436031,0.010384095,0.0012228811,0.0008586997,0.00035921787,0.000029604596,0.0003609946],"genre_scores_gemma":[0.35689342,0.000057603927,0.640642,0.0009481191,0.0009537799,0.000029285913,9.3315083e-7,0.000037895934,0.00043694777],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99628913,0.000925969,0.0013267052,0.00017485487,0.0009084924,0.00037485597],"domain_scores_gemma":[0.8025315,0.19303608,0.0033949013,0.00028173623,0.00063104625,0.00012473649],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00560262,0.00017090852,0.00068061176,0.000047994337,0.00028340594,0.000115713854,0.00055748574,0.0000697563,0.00006274501],"category_scores_gemma":[0.55463207,0.000091484384,0.00030342935,0.0003958629,0.00024292087,0.000089540816,0.00009016028,0.00048515934,0.000010602837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036874935,0.002928751,0.26102087,0.0005014798,0.0019472691,0.00006763757,0.001284437,0.000101015394,0.0054562786,0.1295376,0.3448339,0.24863327],"study_design_scores_gemma":[0.0011085897,0.000351645,0.094919555,0.000079997866,0.00039666012,0.00003070639,0.0002574559,0.00071775255,0.00014321013,0.89955616,0.0022980247,0.0001402321],"about_ca_topic_score_codex":0.000018961942,"about_ca_topic_score_gemma":0.000029862435,"teacher_disagreement_score":0.7700186,"about_ca_system_score_codex":0.00037032712,"about_ca_system_score_gemma":0.00015260495,"threshold_uncertainty_score":0.44911945},"labels":[],"label_agreement":null},{"id":"W2038334661","doi":"10.1198/jasa.2004.s333","title":"Generalized Poisson Models and Their Applications in Insurance and Finance","year":2004,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Poisson distribution; Mathematics; Econometrics; Actuarial science; Economics; Statistics","score_opus":0.013354479071121523,"score_gpt":0.2273078944532751,"score_spread":0.21395341538215357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038334661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91598713,0.00075315376,0.081145614,0.0015337662,0.00006610922,0.00012436896,0.00011895598,0.0000027015049,0.0002681784],"genre_scores_gemma":[0.9943133,0.0018092304,0.0034888962,0.00028928742,0.000042595824,0.000007963826,0.0000010559518,0.0000065595254,0.000041139123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992481,0.00002256941,0.00042921555,0.00011499851,0.000048340207,0.00013677964],"domain_scores_gemma":[0.99882615,0.00009338567,0.0009372494,0.000081441336,0.000039978724,0.000021785341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043195987,0.00007627413,0.00031625133,0.00007434707,0.000070983064,0.000029811796,0.00009917474,0.000025162273,9.0723466e-7],"category_scores_gemma":[0.0001508138,0.000059870115,0.00003826552,0.00024182007,0.00006520824,0.00015459377,0.000030323508,0.0001441668,0.0000018487227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003310439,0.000082679166,0.19566609,0.000008505746,0.000028100914,0.000001302607,0.0005895915,0.0021823992,0.00001546091,0.7898815,0.00010629318,0.011404937],"study_design_scores_gemma":[0.00041013997,0.000041861775,0.5832833,0.000010063722,0.0000029744772,0.0000014542235,0.000050749462,0.0006902761,0.000009178888,0.41417378,0.0012654281,0.000060771534],"about_ca_topic_score_codex":0.00039726775,"about_ca_topic_score_gemma":0.0000624864,"teacher_disagreement_score":0.38761723,"about_ca_system_score_codex":0.00022709767,"about_ca_system_score_gemma":0.000016153146,"threshold_uncertainty_score":0.24414325},"labels":[],"label_agreement":null},{"id":"W2038840372","doi":"10.1080/01621459.2011.641430","title":"Topological Analysis of Variance and the Maxillary Complex","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Alberta","funders":"","keywords":"Topological data analysis; Persistent homology; Variance (accounting); Curse of dimensionality; Nonlinear system; Computer science; Topology (electrical circuits); High dimensional; Computational topology; Landmark; Theoretical computer science; Data mining; Algorithm; Mathematics; Artificial intelligence","score_opus":0.01454430915466728,"score_gpt":0.27369769421795276,"score_spread":0.2591533850632855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038840372","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13843887,0.00021630793,0.84849244,0.012286087,0.00015465352,0.00005304812,0.00006458082,0.0000067822584,0.00028720335],"genre_scores_gemma":[0.9782181,0.00008364019,0.020785931,0.00080958515,0.000053419422,6.075258e-7,0.0000014906748,0.00000121701,0.00004603433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9982504,0.00056020013,0.00042050955,0.00008271069,0.0005056033,0.00018053257],"domain_scores_gemma":[0.9956924,0.0025214078,0.0013597147,0.00019646563,0.00015356144,0.00007648175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017243889,0.00006768057,0.0004986554,0.00012699075,0.00009376897,0.00004355521,0.00055813004,0.000023924065,0.00004252774],"category_scores_gemma":[0.002717056,0.00002970314,0.00019592521,0.0022818192,0.0003370132,0.00015964507,0.00020883328,0.00016091827,0.0000017812403],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009620039,0.00024152105,0.3569882,0.000003566925,0.0026189876,0.0000055902688,0.00036244254,0.00020925993,0.00010334153,0.5934141,0.0032316647,0.042725127],"study_design_scores_gemma":[0.0002110564,0.00006647788,0.98182267,0.0000012523366,0.00079035404,0.00001291727,0.000058150694,0.007332034,0.0000068201334,0.008671606,0.000979948,0.000046701134],"about_ca_topic_score_codex":0.00011572644,"about_ca_topic_score_gemma":0.0000040662485,"teacher_disagreement_score":0.8397792,"about_ca_system_score_codex":0.00006860789,"about_ca_system_score_gemma":0.000018082446,"threshold_uncertainty_score":0.3252766},"labels":[],"label_agreement":null},{"id":"W2039943102","doi":"10.1198/016214507000000950","title":"Robust Linear Model Selection Based on Least Angle Regression","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Scalability; Computer science; Robust regression; Multivariate statistics; Model selection; Data set; Set (abstract data type); Linear regression; Regression; Sequence (biology); Selection (genetic algorithm); Data mining; Algorithm; Artificial intelligence; Mathematics; Machine learning; Statistics","score_opus":0.0874089107963037,"score_gpt":0.41240264168897717,"score_spread":0.32499373089267347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039943102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016040357,0.0000026973005,0.9823714,0.00074272405,0.0001645994,0.00010103603,0.000050527065,0.000017647075,0.00050903583],"genre_scores_gemma":[0.32525674,0.0000029046714,0.67387587,0.0003984197,0.00017145163,0.000001089409,0.0000012634307,0.000019782872,0.00027247478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781233,0.0003091579,0.0006031317,0.00014219155,0.0008396671,0.00029351708],"domain_scores_gemma":[0.9936343,0.0040784557,0.0015986577,0.00013508595,0.00041774398,0.0001357831],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002072934,0.00014482893,0.00039217927,0.00008940565,0.00015574115,0.000019872552,0.00015468974,0.000060007565,0.000018987335],"category_scores_gemma":[0.009640983,0.00009016808,0.00012766891,0.0003168064,0.00007396083,0.00008178865,0.00002311098,0.0004930008,0.0000032434602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004435741,0.0026347444,0.0120129725,0.0001401694,0.0003318269,0.00006408501,0.00054247526,0.343775,0.008668971,0.32385346,0.04602375,0.2575168],"study_design_scores_gemma":[0.0006396901,0.00059151155,0.00723449,0.00010573951,0.00013947923,0.000009429212,0.00007221465,0.7349264,0.00078948116,0.25509706,0.00021967648,0.00017484088],"about_ca_topic_score_codex":0.0000069723355,"about_ca_topic_score_gemma":0.000009539774,"teacher_disagreement_score":0.3911514,"about_ca_system_score_codex":0.00064592104,"about_ca_system_score_gemma":0.00009419822,"threshold_uncertainty_score":0.9987012},"labels":[],"label_agreement":null},{"id":"W2041121499","doi":"10.1198/016214508000000517","title":"Combining Registration and Fitting for Functional Models","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Computer science; Econometrics; Mathematics; Artificial intelligence","score_opus":0.03196521524814722,"score_gpt":0.25255041528521477,"score_spread":0.22058520003706755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041121499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01969114,0.000008612787,0.9773465,0.0025281555,0.00019551338,0.000049772134,0.000010765582,0.000007416973,0.00016213334],"genre_scores_gemma":[0.82983786,0.000021832084,0.16929516,0.00040412447,0.00014030446,0.0000019378906,0.0000035483074,0.0000034514871,0.00029179367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992286,0.000057700323,0.00022517647,0.0000762269,0.00031621786,0.00009606931],"domain_scores_gemma":[0.9984734,0.00050237594,0.0007783519,0.00007256844,0.00014238505,0.000030887033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005283893,0.000044065546,0.00011585931,0.000031520794,0.00017311641,0.00006998187,0.00017273909,0.000009868454,6.6258e-7],"category_scores_gemma":[0.000505104,0.0000320143,0.000035880043,0.00012846844,0.000039256305,0.00048228295,0.000055095436,0.0000822599,4.651433e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011791155,0.00021398732,0.034073614,0.000027932067,0.00030229535,0.000016574948,0.0009712116,0.0030738984,0.00045533536,0.63931966,0.12614226,0.1952853],"study_design_scores_gemma":[0.00088852167,0.00037180036,0.2530319,0.000022904049,0.00005528922,0.0000554229,0.00010548986,0.64985627,0.000048504935,0.09336506,0.0020486568,0.00015021108],"about_ca_topic_score_codex":0.000009125267,"about_ca_topic_score_gemma":0.0000010894827,"teacher_disagreement_score":0.8101467,"about_ca_system_score_codex":0.00008002228,"about_ca_system_score_gemma":0.000037407506,"threshold_uncertainty_score":0.1331489},"labels":[],"label_agreement":null},{"id":"W2042209726","doi":"10.1198/jasa.2009.tm09124","title":"Linear Mixed-Effects Modeling by Parameter Cascading","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Nuisance parameter; Smoothing; Mathematical optimization; Computation; Computer science; Maximization; Basis (linear algebra); Estimation theory; Simple (philosophy); Algorithm; Mathematics; Applied mathematics; Statistics","score_opus":0.027516457221477747,"score_gpt":0.35625885605182983,"score_spread":0.32874239883035206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042209726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.387458,0.0000049751056,0.6113397,0.00045805034,0.0005189534,0.00006482247,0.000042192452,0.000008661576,0.000104682134],"genre_scores_gemma":[0.5788221,0.000004621334,0.42071596,0.0002115761,0.00016921465,0.0000020670207,5.982799e-7,0.00001389478,0.000059968912],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980053,0.00042987295,0.00057429983,0.00011825396,0.00060431164,0.0002679817],"domain_scores_gemma":[0.9873518,0.010902139,0.0011436582,0.00016228277,0.0003047664,0.00013538434],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013954748,0.00013125114,0.00044566242,0.00004063911,0.00010978776,0.000051371153,0.00024810058,0.00006341131,0.000037589627],"category_scores_gemma":[0.04543989,0.000083897045,0.00012392082,0.00019434742,0.00009063632,0.00007121157,0.000048745074,0.00078912673,0.000007395236],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032213464,0.0010943814,0.03773286,0.00022259745,0.00094894855,0.000056015324,0.00092736684,0.00020885121,0.07239408,0.44818336,0.1287431,0.3091663],"study_design_scores_gemma":[0.0006117022,0.0004403043,0.009541211,0.000082264676,0.00038164036,0.00004257676,0.00010960115,0.15689643,0.002724776,0.82817733,0.00067127676,0.00032088667],"about_ca_topic_score_codex":0.000039980736,"about_ca_topic_score_gemma":0.0000058984892,"teacher_disagreement_score":0.37999398,"about_ca_system_score_codex":0.00014870276,"about_ca_system_score_gemma":0.00004924563,"threshold_uncertainty_score":0.96260077},"labels":[],"label_agreement":null},{"id":"W2044203736","doi":"10.1198/016214502753479275","title":"Bayesian Spatial Prediction of Random Space-Time Fields With Application to Mapping PM<sub>2.5</sub>Exposure","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Wishart distribution; Covariance; Bayes' theorem; Gaussian; Mathematics; Bayesian probability; Algorithm; Computer science; Statistics; Data mining; Multivariate statistics","score_opus":0.008820254793653347,"score_gpt":0.23413501402603645,"score_spread":0.22531475923238312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044203736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37340835,0.0000048642323,0.61760056,0.008380352,0.00005840638,0.00021286779,0.0000489037,0.00000775385,0.00027792837],"genre_scores_gemma":[0.9932502,0.000019022043,0.005560881,0.00097445055,0.00012828963,0.0000045006705,0.000002172395,0.000008100857,0.00005242018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982845,0.00025915916,0.00046175887,0.00010954482,0.00068322115,0.0002017722],"domain_scores_gemma":[0.9980824,0.00039194414,0.0011946536,0.000121861995,0.00005480349,0.00015434338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006239931,0.000089249086,0.00028333586,0.000039021554,0.00011123579,0.00001614659,0.00013467869,0.000047173093,0.00012383111],"category_scores_gemma":[0.0005316533,0.000062215186,0.000053619424,0.00034393428,0.000089626454,0.0001179437,0.00003328684,0.00021765078,0.000045853798],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013585764,0.0007284423,0.41000947,0.00008409055,0.00025835284,0.000007397691,0.005189528,0.022801366,0.05329486,0.00021237008,0.09738673,0.40866882],"study_design_scores_gemma":[0.001156847,0.0013045704,0.9664747,0.00005575275,0.00008784531,0.0000127431595,0.0001412758,0.026378496,0.0015619264,0.00086347334,0.0018353027,0.0001270317],"about_ca_topic_score_codex":0.00024721387,"about_ca_topic_score_gemma":0.00006791099,"teacher_disagreement_score":0.6198418,"about_ca_system_score_codex":0.0004838827,"about_ca_system_score_gemma":0.000020194339,"threshold_uncertainty_score":0.25370616},"labels":[],"label_agreement":null},{"id":"W2051705420","doi":"10.1198/016214504000001510","title":"Diagnostic Checking in ARMA Models With Uncorrelated Errors","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":164,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Uncorrelated; Mathematics; Statistics; Computer science; Econometrics; Algorithm","score_opus":0.05216969875186943,"score_gpt":0.37768564462795484,"score_spread":0.3255159458760854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051705420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70973754,0.000026540938,0.28420746,0.004458516,0.00028295565,0.00011497092,0.000013555321,0.000008988154,0.0011494571],"genre_scores_gemma":[0.9191469,0.000006315526,0.08013215,0.00033812848,0.00012467442,0.0000021386006,3.2143424e-7,0.000012249741,0.00023710633],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99513143,0.0013424018,0.0010128586,0.0001798609,0.00204629,0.0002871665],"domain_scores_gemma":[0.9723785,0.023848442,0.0029023103,0.00020936056,0.00055443513,0.000106943065],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074696783,0.00012450543,0.00047836214,0.00023189653,0.000088691835,0.000101722675,0.000545487,0.000040334166,0.000056195433],"category_scores_gemma":[0.07091636,0.0000693646,0.00009709035,0.0015016163,0.00012065643,0.00032674486,0.000073092175,0.0005344518,0.000015821064],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035650574,0.00017087207,0.5532215,0.000002076184,0.00009526348,0.00003553665,0.0009384145,0.1245857,0.00006765495,0.0014758202,0.0064804666,0.31257018],"study_design_scores_gemma":[0.0006872618,0.00024851377,0.854075,0.00007644927,0.00008016487,0.00005653321,0.00038750883,0.103181325,0.000038039565,0.040256195,0.00076451927,0.00014846271],"about_ca_topic_score_codex":0.00009275733,"about_ca_topic_score_gemma":0.00014825609,"teacher_disagreement_score":0.3124217,"about_ca_system_score_codex":0.0008084731,"about_ca_system_score_gemma":0.00016871144,"threshold_uncertainty_score":0.9369097},"labels":[],"label_agreement":null},{"id":"W2056592727","doi":"10.1198/016214508000000751","title":"Functional Additive Models","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":245,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Functional principal component analysis; Functional data analysis; Additive model; Mathematics; Linear form; Linear model; Principal component regression; Regression analysis; Principal component analysis; Regression; Proper linear model; Generalized additive model; Linear regression; Covariance; Computer science; Bayesian multivariate linear regression; Econometrics; Statistics","score_opus":0.08664755365517686,"score_gpt":0.3459915902536139,"score_spread":0.2593440365984371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056592727","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07092641,0.000007985524,0.9255672,0.001004627,0.00033841035,0.00006662629,0.00017360851,0.000010896545,0.0019042145],"genre_scores_gemma":[0.68490994,0.000032119224,0.31365767,0.00047273067,0.00029742322,0.0000029682435,0.0000015321125,0.00001350699,0.00061210454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980832,0.00040319166,0.00048307053,0.00008775392,0.00075869414,0.00018413042],"domain_scores_gemma":[0.9920375,0.005951316,0.0013028121,0.00010381581,0.0005126277,0.00009193591],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006552323,0.000095712865,0.0003479905,0.00004024492,0.00014620162,0.000014650086,0.00015109952,0.000030829804,0.00018130304],"category_scores_gemma":[0.011659164,0.000060266488,0.00011803738,0.00022220457,0.00017684096,0.00009031836,0.000036225676,0.00032491086,0.000012649597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021302658,0.00030910404,0.007537719,0.000010279024,0.00027629582,0.000032581713,0.00037101694,0.0000985596,0.0002367935,0.69580376,0.26836327,0.026747571],"study_design_scores_gemma":[0.00029972065,0.00020804684,0.16834015,0.000018899345,0.00009065469,0.00007585658,0.0000862137,0.0022105603,0.00010721211,0.82794905,0.0005130687,0.00010058478],"about_ca_topic_score_codex":0.000017122315,"about_ca_topic_score_gemma":0.0000017700654,"teacher_disagreement_score":0.6139835,"about_ca_system_score_codex":0.0003135162,"about_ca_system_score_gemma":0.00013615697,"threshold_uncertainty_score":0.9966661},"labels":[],"label_agreement":null},{"id":"W2060831937","doi":"10.1198/jasa.2010.tm09032","title":"Testing the Order of a Finite Mixture","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Homogeneity (statistics); Mathematics; Null hypothesis; Likelihood-ratio test; Applied mathematics; Statistical hypothesis testing; Limiting; Null (SQL); Statistics; Statistical power; Null distribution; Alternative hypothesis; Ratio test; Test statistic; Computer science; Data mining","score_opus":0.011810188231399895,"score_gpt":0.2762009980932988,"score_spread":0.2643908098618989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060831937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018301576,0.000009503836,0.97530645,0.005518217,0.0004151578,0.00004519005,0.00000841821,0.0000053920708,0.00039010946],"genre_scores_gemma":[0.4062132,0.0000017844242,0.59304243,0.0005629336,0.00012237045,5.605962e-7,8.866288e-8,0.0000035205026,0.000053101812],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986546,0.00033452074,0.00033844815,0.00007801775,0.00045128184,0.00014313824],"domain_scores_gemma":[0.9943594,0.0033446376,0.0014863004,0.00022513875,0.00053672056,0.000047850335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014741325,0.00006869127,0.00021190236,0.000030471356,0.0000923019,0.000055239438,0.00066152075,0.000030688276,0.0000054476186],"category_scores_gemma":[0.008184294,0.000033869004,0.000071845716,0.00058514514,0.00009338275,0.00010383017,0.00009001162,0.00051976193,0.0000013937448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003264049,0.00016919055,0.02370782,0.000013792325,0.00017133029,0.00001005463,0.0011809797,0.00012578313,0.038382392,0.19100903,0.0119119175,0.73328507],"study_design_scores_gemma":[0.0005427203,0.0004603151,0.5975176,0.00005292873,0.00015615411,0.00009837337,0.000053692052,0.062072806,0.0015658233,0.33250666,0.004726647,0.0002462367],"about_ca_topic_score_codex":0.000030182222,"about_ca_topic_score_gemma":0.000006818644,"teacher_disagreement_score":0.73303884,"about_ca_system_score_codex":0.00003915568,"about_ca_system_score_gemma":0.00013124368,"threshold_uncertainty_score":0.9797956},"labels":[],"label_agreement":null},{"id":"W2061337431","doi":"10.1080/01621459.2000.10474281","title":"Jackknife Variance Estimation under Imputation for Estimators Using Poststratification Information","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Statistics Canada","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Imputation (statistics); Mathematics; Weighting; Econometrics; Missing data","score_opus":0.03967785128842156,"score_gpt":0.3694318726392187,"score_spread":0.3297540213507971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061337431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1995094,0.000003120371,0.79912263,0.0007901847,0.00014594711,0.00025423555,0.00007430896,0.00004163563,0.000058536483],"genre_scores_gemma":[0.5180125,0.000004159617,0.481631,0.0001924664,0.00007081398,0.000008675926,0.000024776555,0.000012794531,0.00004279703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798304,0.00025320158,0.00092146633,0.000095241914,0.00055500347,0.00019203631],"domain_scores_gemma":[0.9946814,0.0020666162,0.002356651,0.00015396776,0.00067909324,0.00006225061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017209615,0.0001351117,0.000304561,0.00010542021,0.00021428481,0.00013249014,0.00017405408,0.00006763786,0.000040943018],"category_scores_gemma":[0.0049481844,0.00010587519,0.00011627231,0.00036278486,0.00006184535,0.0007034547,0.000009324329,0.00017834659,0.000009303857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010783989,0.00058551267,0.008501122,0.00028548954,0.0005369393,0.0000012723382,0.0019784493,0.13248333,0.0018790896,0.16083245,0.027499191,0.66433877],"study_design_scores_gemma":[0.000647723,0.00027063987,0.05774311,0.00010527419,0.00026998596,0.00003504593,0.00016659556,0.38463825,0.000796358,0.55472475,0.00035373427,0.00024851414],"about_ca_topic_score_codex":0.000055764798,"about_ca_topic_score_gemma":0.0000030558022,"teacher_disagreement_score":0.6640902,"about_ca_system_score_codex":0.00062594813,"about_ca_system_score_gemma":0.00015900348,"threshold_uncertainty_score":0.5923796},"labels":[],"label_agreement":null},{"id":"W2064228679","doi":"10.1198/016214506000000258","title":"Statistical Inference for the Difference Between the Best Treatment Mean and a Control Mean","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Confidence interval; Mathematics; Mean difference; Inference; Upper and lower bounds; Homogeneous; Statistics; Coverage probability; Mathematical optimization; Computer science; Artificial intelligence","score_opus":0.05773673034347347,"score_gpt":0.39316321320818587,"score_spread":0.3354264828647124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064228679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10133026,0.000033578,0.89427483,0.0032259068,0.00006164232,0.0004945815,0.00051308324,0.000020223333,0.00004591216],"genre_scores_gemma":[0.96438414,0.00004938514,0.034940045,0.00017216246,0.0002621995,0.00004145877,0.000003723052,0.000018519067,0.0001283855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979892,0.00040089202,0.0006347722,0.00013989312,0.00053776725,0.0002974745],"domain_scores_gemma":[0.9702163,0.027678683,0.0014839988,0.0002246558,0.00032873813,0.000067668094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000917814,0.00019182307,0.00051662175,0.000032644326,0.0002983831,0.00010157742,0.0003155944,0.000044915094,0.0000081213],"category_scores_gemma":[0.0044859233,0.00008410919,0.00010242619,0.00014573027,0.00039088135,0.0000703354,0.000044894823,0.000298022,0.0000014446287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044599458,0.00066065794,0.2969039,0.000053153315,0.001093021,0.000009815174,0.0011447537,0.00006256021,0.0014333805,0.47840223,0.0060578757,0.21373264],"study_design_scores_gemma":[0.00084950594,0.0011750729,0.31325775,0.000042948715,0.0009970736,0.0000102774175,0.00035195198,0.0012222099,0.00037150737,0.6809965,0.0005496959,0.00017552497],"about_ca_topic_score_codex":0.0003216727,"about_ca_topic_score_gemma":0.00026224807,"teacher_disagreement_score":0.86305386,"about_ca_system_score_codex":0.0005038359,"about_ca_system_score_gemma":0.00009486824,"threshold_uncertainty_score":0.53703934},"labels":[],"label_agreement":null},{"id":"W2066180388","doi":"10.1080/01621459.2013.794730","title":"Parameter Estimation of Partial Differential Equation Models","year":2013,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Western University","funders":"National Institute of Environmental Health Sciences; National Science Foundation; National Institutes of Health; National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; King Abdullah University of Science and Technology","keywords":"Mathematics; Applied mathematics; Estimation; First-order partial differential equation; Partial differential equation; Statistics; Mathematical analysis; Economics","score_opus":0.06108375704515718,"score_gpt":0.32261127117850397,"score_spread":0.2615275141333468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066180388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2108398,0.0000047005974,0.7880636,0.00064592704,0.00029474281,0.00008942653,0.000013867241,0.0000042157867,0.000043756398],"genre_scores_gemma":[0.962307,0.0000026798305,0.037431438,0.000052232044,0.00008495503,0.000003363564,0.0000011957101,0.00000582461,0.00011134615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969063,0.0003964867,0.00094497687,0.00010652425,0.0014930288,0.00015269943],"domain_scores_gemma":[0.9924885,0.004324283,0.0022386396,0.00018281772,0.0006924714,0.00007329366],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013926118,0.00008500471,0.00036263544,0.00009567607,0.000054604196,0.0000943979,0.0003463025,0.00003765002,0.00012855075],"category_scores_gemma":[0.016002845,0.000047660345,0.00013200117,0.00036225226,0.00010023118,0.0003226295,0.00004268756,0.00016616142,0.000026785574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013946096,0.00030563478,0.008104642,0.000012667303,0.00019927118,0.0000014733015,0.0005669209,0.7188547,0.0020678756,0.04600148,0.022985278,0.20076056],"study_design_scores_gemma":[0.00016735759,0.00012220153,0.06876677,0.000010828904,0.000049775925,0.000002159851,0.00004489699,0.7329224,0.0001805226,0.19766317,0.00001652642,0.00005340981],"about_ca_topic_score_codex":0.000052817708,"about_ca_topic_score_gemma":5.7975575e-7,"teacher_disagreement_score":0.75146717,"about_ca_system_score_codex":0.0001753891,"about_ca_system_score_gemma":0.000072545234,"threshold_uncertainty_score":0.9922858},"labels":[],"label_agreement":null},{"id":"W2066654086","doi":"10.1198/016214507000000842","title":"Spatial-Temporal Modeling of Forest Gaps Generated by Colonization From Below- and Above-Ground Bark Beetle Species","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Forest Insect Ecology and Management","field":"Environmental Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Bark beetle; Colonization; Bark (sound); Ecology; Biology","score_opus":0.008081318668538779,"score_gpt":0.2108066064178957,"score_spread":0.2027252877493569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066654086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95103115,0.000025276926,0.04819153,0.00027456437,0.00011177855,0.000072994866,0.000070119626,0.0000032992552,0.00021929211],"genre_scores_gemma":[0.99616724,0.00012328912,0.0032246325,0.00018799532,0.00004497777,0.0000012472323,0.000018736428,0.000006170141,0.00022570587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990126,0.00013010995,0.00032199864,0.0000891948,0.00032720465,0.000118918506],"domain_scores_gemma":[0.9989477,0.0001834952,0.0007197902,0.000062653846,0.000041297688,0.00004509119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023381089,0.000070535556,0.00020163528,0.0000192048,0.00013536101,0.000011830341,0.00010724808,0.000031699183,0.00015886532],"category_scores_gemma":[0.00030737222,0.000053790838,0.000032054817,0.00015611088,0.00019625753,0.000102194455,0.000065145236,0.00010916285,0.0000059662525],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009377434,0.00012216094,0.962852,0.0000035508974,0.00008121937,0.000006063755,0.00028513017,0.01628586,0.003549306,0.00017129122,0.016000409,0.00054922147],"study_design_scores_gemma":[0.00027990146,0.00017715337,0.9476065,0.0000054985385,0.000049926115,0.0000036770816,0.00005718779,0.04925734,0.000097754295,0.00196833,0.00043368866,0.00006302429],"about_ca_topic_score_codex":0.0033447023,"about_ca_topic_score_gemma":0.0011011907,"teacher_disagreement_score":0.0451361,"about_ca_system_score_codex":0.00028473648,"about_ca_system_score_gemma":0.000018515047,"threshold_uncertainty_score":0.50562114},"labels":[],"label_agreement":null},{"id":"W2067485854","doi":"10.1080/01621459.2000.10474278","title":"Nonparametric Density Estimation from Biased Data with Unknown Biasing Function","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Census and Population Estimation","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Estimator; Kernel density estimation; Mathematics; Statistics; Nonparametric statistics; Sampling bias; Multivariate kernel density estimation; Omitted-variable bias; Sampling (signal processing); Density estimation; Kernel (algebra); Population; Variable kernel density estimation; Sample size determination; Econometrics; Kernel method; Computer science; Artificial intelligence; Combinatorics","score_opus":0.04411850906276157,"score_gpt":0.3281121396387715,"score_spread":0.28399363057600996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067485854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6418675,0.000007328606,0.35695595,0.00067397667,0.00012484928,0.00009238974,0.000099624354,0.000018708048,0.00015966127],"genre_scores_gemma":[0.89044976,0.0000082576325,0.10896357,0.00017859541,0.000184857,6.247812e-7,0.000089008114,0.00001622363,0.00010907011],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979079,0.00044656688,0.0005734621,0.00015322842,0.0007605243,0.00015836375],"domain_scores_gemma":[0.9953783,0.0021779388,0.0017617381,0.0003397523,0.00027139834,0.00007084114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010589552,0.00012134916,0.0003170801,0.000086438864,0.00016941296,0.00008065805,0.00023634569,0.000037532107,0.00016125533],"category_scores_gemma":[0.0034361375,0.00008052853,0.000053822598,0.0006017802,0.00006940965,0.00032708212,0.000029463916,0.00025205454,0.000020874448],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010144485,0.0005071898,0.1661256,0.000028540151,0.0004966577,0.000012810407,0.00035016472,0.0068709753,0.0002266673,0.0058930335,0.019962143,0.7985118],"study_design_scores_gemma":[0.0007224243,0.00020677704,0.8635051,0.000079520134,0.0005835858,0.00001764365,0.000034664543,0.0931725,0.00003569191,0.04046173,0.0010217321,0.00015859939],"about_ca_topic_score_codex":0.00021078912,"about_ca_topic_score_gemma":0.000072190174,"teacher_disagreement_score":0.7983532,"about_ca_system_score_codex":0.0003725329,"about_ca_system_score_gemma":0.00007183798,"threshold_uncertainty_score":0.41136256},"labels":[],"label_agreement":null},{"id":"W2068225596","doi":"10.1198/016214503000000305","title":"The Intrinsic Distribution and Selection Bias of Long-Period Cometary Orbits","year":2003,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Field-Flow Fractionation Techniques","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Selection (genetic algorithm); Period (music); Distribution (mathematics); Celestial sphere; Physics; Statistical physics; Mathematics; Mechanism (biology); Statistics; Astrophysics; Computer science; Mathematical analysis; Quantum mechanics; Artificial intelligence","score_opus":0.0065471297986992635,"score_gpt":0.23190183358056454,"score_spread":0.22535470378186528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068225596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71831787,0.00014890358,0.2795544,0.0010992041,0.00041596,0.00013582983,0.00005288197,0.000041817235,0.00023314598],"genre_scores_gemma":[0.99761456,0.0001892507,0.0020762521,0.0000308999,0.000042744527,0.0000021015767,0.0000025803665,0.0000074853265,0.00003413028],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99897903,0.00019797057,0.00036134568,0.000044109518,0.0003143665,0.000103159626],"domain_scores_gemma":[0.99833447,0.00077588385,0.00055951736,0.000050278013,0.00024825404,0.00003160547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000659462,0.00006676819,0.00016787347,0.000037829748,0.00009931048,0.000032717646,0.000070456175,0.00003371705,0.000009892236],"category_scores_gemma":[0.002348641,0.000043398803,0.000045999503,0.00030908003,0.00006515117,0.00010417986,0.000008772219,0.00025799448,0.0000010241725],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023204423,0.00028041576,0.5005456,0.00011961788,0.0012172065,0.000009552766,0.00044810848,0.0042661047,0.009461762,0.04554646,0.08226208,0.35561106],"study_design_scores_gemma":[0.0002727652,0.0002260827,0.9772736,0.00002569013,0.0001090213,0.00006990589,0.0001127677,0.0033110203,0.008605553,0.004744546,0.0051317755,0.0001172776],"about_ca_topic_score_codex":0.000016061913,"about_ca_topic_score_gemma":0.000016416847,"teacher_disagreement_score":0.476728,"about_ca_system_score_codex":0.00033822173,"about_ca_system_score_gemma":0.000032542543,"threshold_uncertainty_score":0.28117123},"labels":[],"label_agreement":null},{"id":"W2074124346","doi":"10.1080/01621459.2014.922777","title":"Functional and Structural Methods With Mixed Measurement Error and Misclassification in Covariates","year":2014,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute","keywords":"Covariate; Inference; Observational error; Computer science; Econometrics; Statistics; Data mining; Machine learning; Mathematics; Artificial intelligence","score_opus":0.09363819307541298,"score_gpt":0.4062871231973908,"score_spread":0.3126489301219778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074124346","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08166893,0.00001680777,0.91689146,0.0012050179,0.00008100448,0.00008276765,0.00001220605,0.0000040632162,0.00003777194],"genre_scores_gemma":[0.4436207,0.0000043219966,0.5562577,0.000060822247,0.000032489606,0.000002205254,4.2254356e-7,0.0000063095167,0.000015017081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979839,0.00089440454,0.0003900399,0.00012023456,0.00047049913,0.0001409573],"domain_scores_gemma":[0.99518955,0.0034894594,0.00089003576,0.00007657511,0.00028057778,0.00007382307],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024765015,0.00009916059,0.00033687966,0.000046004912,0.00007529178,0.000029726065,0.000055946308,0.000027343693,0.0000057058264],"category_scores_gemma":[0.008894694,0.00005842116,0.00002331585,0.00012502457,0.00012446959,0.00007655216,0.000023032673,0.00021706823,1.601565e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007585834,0.00014143196,0.03717495,0.0000954873,0.00027381175,0.0000030951287,0.0005295379,0.00027605597,0.0068955356,0.5974861,0.0010622502,0.35530317],"study_design_scores_gemma":[0.00056062784,0.00020981632,0.48634523,0.000033409313,0.00010188924,0.000015976964,0.00012239326,0.012373577,0.00011365712,0.49993992,0.00010075636,0.00008273162],"about_ca_topic_score_codex":0.0000181416,"about_ca_topic_score_gemma":0.00003178983,"teacher_disagreement_score":0.4491703,"about_ca_system_score_codex":0.00022836075,"about_ca_system_score_gemma":0.000039602764,"threshold_uncertainty_score":0.9994538},"labels":[],"label_agreement":null},{"id":"W2076374456","doi":"10.1080/01621459.2000.10474289","title":"Internet Traffic Data","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Network Traffic and Congestion Control","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Internet traffic; The Internet; World Wide Web","score_opus":0.01525988860597554,"score_gpt":0.25276474259739656,"score_spread":0.23750485399142102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076374456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16793019,0.000091843714,0.8124763,0.017532898,0.00083098,0.00009944759,0.000041568474,0.00004951392,0.0009472679],"genre_scores_gemma":[0.98286015,0.000032620464,0.014671299,0.0010858364,0.00023501935,5.258542e-7,0.0000018571225,0.000004174502,0.0011085062],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986981,0.00024931275,0.00032318747,0.000121570134,0.0004512133,0.00015660553],"domain_scores_gemma":[0.9983351,0.0005665905,0.0006022499,0.00032779993,0.000099244186,0.000069005924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064670655,0.00006599202,0.00019340075,0.000023536462,0.00004736784,0.000102721846,0.0013578258,0.00001762791,0.00009302057],"category_scores_gemma":[0.00033949455,0.000043235515,0.000051327293,0.00025848878,0.00004631225,0.00026074937,0.000082172526,0.00021729669,0.000048432285],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020297499,0.000042951942,0.00074715225,5.891181e-7,0.000049267073,0.0000053151293,0.000057713598,0.0007837647,0.0000032287649,0.0025854306,0.061728198,0.9339761],"study_design_scores_gemma":[0.00080583745,0.0003504759,0.0886904,0.000031894084,0.000108931075,0.00007666407,0.000029295701,0.8245991,0.00000585508,0.0021818166,0.08291865,0.00020108865],"about_ca_topic_score_codex":0.000009597771,"about_ca_topic_score_gemma":0.0000068328814,"teacher_disagreement_score":0.933775,"about_ca_system_score_codex":0.00012761382,"about_ca_system_score_gemma":0.00008175381,"threshold_uncertainty_score":0.25232008},"labels":[],"label_agreement":null},{"id":"W2078249808","doi":"10.1198/jasa.2009.0119","title":"Screening Experiments for Developing Dynamic Treatment Regimes","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute on Drug Abuse; National Institute of Mental Health","keywords":"Fractional factorial design; Factorial experiment; Computer science; Treatment effect; Factorial; Design of experiments; Machine learning; Mathematical optimization; Medicine; Mathematics; Statistics","score_opus":0.12215089528701961,"score_gpt":0.4961811498570252,"score_spread":0.3740302545700056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078249808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0854026,0.000079555546,0.9088184,0.0048430883,0.00033591833,0.00021035702,0.000030004247,0.0000088662355,0.00027117663],"genre_scores_gemma":[0.4697489,0.000010299538,0.5288751,0.0005568006,0.000070484915,0.000003582939,9.1906946e-7,0.0000069470084,0.0007269392],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968966,0.0006134523,0.0008200403,0.00018487837,0.0012326782,0.00025231327],"domain_scores_gemma":[0.99333286,0.0037740455,0.0022424236,0.00018664713,0.0003792248,0.00008479656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024445856,0.00013349406,0.00047962726,0.00011884604,0.0001823996,0.00016692522,0.00044735213,0.000031431133,0.000016342687],"category_scores_gemma":[0.007091734,0.000077243625,0.00022083275,0.00045362022,0.00006502683,0.00020847787,0.00003100138,0.00010125562,0.000006849025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076765683,0.00029061353,0.007806007,0.0000014464308,0.00023910661,0.000009385299,0.0010130709,0.00036500333,0.031109106,0.008203857,0.011304109,0.93889064],"study_design_scores_gemma":[0.0041844686,0.007686215,0.68916756,0.00011842602,0.0003035532,0.00007473346,0.004877194,0.025070392,0.04167277,0.20911805,0.016944487,0.0007821683],"about_ca_topic_score_codex":0.000011216345,"about_ca_topic_score_gemma":0.000001073442,"teacher_disagreement_score":0.93810844,"about_ca_system_score_codex":0.0011924217,"about_ca_system_score_gemma":0.00012437782,"threshold_uncertainty_score":0.84899807},"labels":[],"label_agreement":null},{"id":"W2081508613","doi":"10.1080/01621459.2014.881742","title":"Spatially Varying Coefficient Model for Neuroimaging Data With Jump Discontinuities","year":2014,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Point processes and geometric inequalities","field":"Mathematics","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of General Medical Sciences; National Institute of Mental Health","keywords":"Classification of discontinuities; Monte Carlo method; Piecewise; Covariance; Principal component analysis; Consistency (knowledge bases); Asymptotic distribution; Covariance function; Data set","score_opus":0.05504662327902528,"score_gpt":0.3368350070499039,"score_spread":0.2817883837708786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081508613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03756083,0.000008870359,0.9602065,0.0015901377,0.00010906293,0.000102269965,0.00023020024,0.000009921957,0.00018218663],"genre_scores_gemma":[0.89217454,0.000006826906,0.10681968,0.00036362707,0.00018931198,0.0000026375037,0.0000076901415,0.000018680032,0.00041697812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985044,0.00013107377,0.0004587222,0.000119629054,0.0005648969,0.00022130225],"domain_scores_gemma":[0.99405235,0.003612945,0.0016565584,0.00023487455,0.00039459733,0.000048654783],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014963688,0.00010235469,0.00035635693,0.000071004986,0.00012990243,0.00009648058,0.00040165574,0.000014804937,0.0000035320593],"category_scores_gemma":[0.009965795,0.000060697064,0.000054402506,0.00021528933,0.00007100755,0.00018523286,0.0001002312,0.00016442941,5.2305273e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020869547,0.0015837548,0.028659875,0.0013416104,0.00161625,0.00001389668,0.009759257,0.064297125,0.0006380177,0.6192546,0.09134087,0.17940778],"study_design_scores_gemma":[0.0006447002,0.00032839493,0.0015226918,0.00009452154,0.0003005667,0.000011132348,0.00024378409,0.8713925,0.0000434346,0.12461881,0.00064260024,0.00015686877],"about_ca_topic_score_codex":0.000027094115,"about_ca_topic_score_gemma":0.000021417218,"teacher_disagreement_score":0.8546137,"about_ca_system_score_codex":0.00012477492,"about_ca_system_score_gemma":0.00011034502,"threshold_uncertainty_score":0.9983737},"labels":[],"label_agreement":null},{"id":"W2082880140","doi":"10.1198/016214506000000320","title":"Optimizing the Expected Overlap of Survey Samples via the Northwest Corner Rule","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Selection (genetic algorithm); Sampling (signal processing); Variance (accounting); Computer science; Mathematical optimization; Hypergeometric distribution; Statistics; Simple random sample; Mathematics; Focus (optics); Algorithm; Population; Artificial intelligence","score_opus":0.017352205864050636,"score_gpt":0.27735369714539715,"score_spread":0.26000149128134653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082880140","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86025625,0.00007556767,0.13289508,0.00490458,0.00054283644,0.00020453203,0.00035768774,0.000020679647,0.00074274774],"genre_scores_gemma":[0.9959405,0.000028726576,0.0034893572,0.00015374285,0.00017212851,0.0000015776435,0.000027742199,0.00000707929,0.0001791351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975562,0.0009878969,0.00046383476,0.000069123555,0.0007529826,0.00016997084],"domain_scores_gemma":[0.99455976,0.003052864,0.0017314445,0.000096905664,0.00052551844,0.000033488333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018361276,0.00007150464,0.00020230148,0.000031142685,0.00046707512,0.00006317292,0.00027995266,0.000032016007,0.000028436549],"category_scores_gemma":[0.0016658694,0.000037171452,0.00008799776,0.0005104077,0.00031172502,0.00009976251,0.000009321026,0.00019511988,0.0000016099232],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007016947,0.00007370656,0.97227925,0.0000019879155,0.00006864543,9.701737e-7,0.0031686202,0.014334583,0.00009419972,0.0032435015,0.0051465733,0.0015177798],"study_design_scores_gemma":[0.00013981375,0.00003309615,0.99586797,0.000009470335,0.00006439568,7.1037425e-7,0.0015226698,0.00037328203,0.000020883677,0.0009935509,0.00092268764,0.000051485848],"about_ca_topic_score_codex":0.024276001,"about_ca_topic_score_gemma":0.010899983,"teacher_disagreement_score":0.13568424,"about_ca_system_score_codex":0.00017802302,"about_ca_system_score_gemma":0.00015591884,"threshold_uncertainty_score":0.9822214},"labels":[],"label_agreement":null},{"id":"W2083645524","doi":"10.1198/016214506000000951","title":"A Multiresolution Hazard Model for Multicenter Survival Studies","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"National Cancer Institute","keywords":"Hazard ratio; Hazard; Statistics; Econometrics; Proportional hazards model; Survival analysis; Computer science; Mathematics; Confidence interval; Biology","score_opus":0.4978380573074715,"score_gpt":0.5919939326207032,"score_spread":0.09415587531323172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083645524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039857753,0.000020377194,0.95676607,0.0015187116,0.0012223588,0.00035660865,0.00018458805,0.000017393848,0.00005612755],"genre_scores_gemma":[0.24791813,0.000022902563,0.75098294,0.00032489156,0.00047446744,0.0000063356074,4.6602835e-7,0.000023577733,0.00024629533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961888,0.00077579264,0.0015486734,0.00017147548,0.0009074823,0.00040774996],"domain_scores_gemma":[0.8876317,0.10753283,0.0033022906,0.00020196171,0.0011893535,0.00014186713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0115856165,0.00016671914,0.0008980509,0.00006798379,0.0001445033,0.000029874536,0.00028501212,0.000075710705,0.00000737586],"category_scores_gemma":[0.32812747,0.00010730278,0.0003187008,0.00022072866,0.00023998298,0.00007646204,0.00008007635,0.00037787075,0.0000031890843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0128513,0.003409185,0.06653983,0.0006751554,0.0061793765,0.000048260994,0.00402989,0.001386808,0.0051583075,0.5045889,0.1606153,0.2345177],"study_design_scores_gemma":[0.0022511727,0.00041782676,0.026913272,0.00009537982,0.0006948285,0.0000037437237,0.0005136082,0.0508806,0.00029067212,0.9174685,0.0002590283,0.00021136737],"about_ca_topic_score_codex":0.000005338986,"about_ca_topic_score_gemma":0.000034252247,"teacher_disagreement_score":0.4128796,"about_ca_system_score_codex":0.00081385823,"about_ca_system_score_gemma":0.00008339913,"threshold_uncertainty_score":0.677532},"labels":[],"label_agreement":null},{"id":"W2084192089","doi":"10.1198/016214504000001006","title":"Exact and Approximate Inferences for Nonlinear Mixed-Effects Models With Missing Covariates","year":2004,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Covariate; Missing data; Categorical variable; Convergence (economics); Monte Carlo method; Mathematics; Expectation–maximization algorithm; Applied mathematics; Computer science; Statistics; Maximum likelihood","score_opus":0.029116050359756826,"score_gpt":0.3410638414224675,"score_spread":0.31194779106271064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084192089","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031880673,0.000015243659,0.96665835,0.0010030676,0.00008872727,0.00018832264,0.00009502451,0.000009864778,0.000060742677],"genre_scores_gemma":[0.2196015,0.00001281455,0.7801798,0.000105028346,0.000074192896,0.000005292906,0.0000011187796,0.000012409444,0.000007841416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986444,0.00021481031,0.00040546816,0.00012177879,0.00039052937,0.00022302638],"domain_scores_gemma":[0.9917759,0.0065503367,0.0011823669,0.00009126752,0.00029964303,0.00010050164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008070571,0.00013437212,0.00046568035,0.000042651976,0.00013429498,0.000095609365,0.00012858139,0.000037571397,0.0000027416745],"category_scores_gemma":[0.006646279,0.000076349315,0.000056701487,0.00016181036,0.00015137081,0.00012754278,0.000027384636,0.00020314359,3.2660603e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024704405,0.00020002008,0.003197485,0.00019669288,0.00021388443,0.000008483473,0.00035419702,0.00010523546,0.0002879703,0.9438401,0.0003077837,0.051041115],"study_design_scores_gemma":[0.0007664919,0.0006277824,0.010686914,0.00015959714,0.00024316854,0.000020947311,0.00009643341,0.009694534,0.00033817597,0.9772302,0.000016124139,0.00011962349],"about_ca_topic_score_codex":0.00003244167,"about_ca_topic_score_gemma":0.0000072761186,"teacher_disagreement_score":0.18772082,"about_ca_system_score_codex":0.00017266674,"about_ca_system_score_gemma":0.00012112236,"threshold_uncertainty_score":0.7956697},"labels":[],"label_agreement":null},{"id":"W2086696611","doi":"10.1198/016214506000000889","title":"Transition Models for Multivariate Longitudinal Binary Data","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Multivariate statistics; Categorical variable; Binary data; Statistics; Econometrics; Mathematics; Marginal model; Logistic regression; Binary number; Regression analysis","score_opus":0.12608300461563685,"score_gpt":0.42921773164859145,"score_spread":0.30313472703295463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086696611","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008250056,0.000007817951,0.9891678,0.0014140067,0.0002700819,0.00017069781,0.00061868766,0.000010435635,0.00009039442],"genre_scores_gemma":[0.3264894,0.000004896603,0.67311025,0.00014102562,0.00021134672,0.0000014423674,0.000008123975,0.000012666275,0.000020857347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980456,0.00026642624,0.0007013412,0.00015950769,0.00054468727,0.00028241272],"domain_scores_gemma":[0.98982143,0.008007413,0.0014034112,0.00026221504,0.00040248898,0.000103059276],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036512571,0.00011781351,0.00041007076,0.000059612135,0.00012346194,0.000039250506,0.00040206136,0.000046623492,0.0000149862935],"category_scores_gemma":[0.009017159,0.00007844811,0.000098135875,0.00022567248,0.000080890975,0.00020710357,0.000058892685,0.00026085408,0.0000014191164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015725576,0.00078832253,0.0029535457,0.00013415595,0.00055331626,0.000039834016,0.0006388858,0.0001063085,0.0024481772,0.7664169,0.031494804,0.19285315],"study_design_scores_gemma":[0.00058329414,0.0003380537,0.043052465,0.000052498763,0.0003156355,0.000017761953,0.00016373515,0.04022099,0.000096840835,0.9148951,0.00013395061,0.00012968396],"about_ca_topic_score_codex":0.000041141317,"about_ca_topic_score_gemma":0.000013909514,"teacher_disagreement_score":0.31823933,"about_ca_system_score_codex":0.00026122932,"about_ca_system_score_gemma":0.000081252045,"threshold_uncertainty_score":0.9993303},"labels":[],"label_agreement":null},{"id":"W2088311091","doi":"10.1198/jasa.2009.0004","title":"Robust Estimation of Mean Functions and Treatment Effects for Recurrent Events Under Event-Dependent Censoring and Termination: Application to Skeletal Complications in Cancer Metastatic to Bone","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Censoring (clinical trials); Inverse probability; Statistics; Event (particle physics); Breast cancer; Marginal structural model; Event data; Marginal distribution; Clinical trial; Mathematics; Econometrics; Medicine; Cancer; Confidence interval; Covariate; Internal medicine; Random variable","score_opus":0.20039376046594784,"score_gpt":0.5090273976216245,"score_spread":0.3086336371556767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088311091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23168957,0.000019751536,0.7627064,0.00419447,0.00013233814,0.0010412821,0.00020294983,0.0000061062246,0.000007139991],"genre_scores_gemma":[0.6583256,0.000021415535,0.34133172,0.0001318981,0.00005171992,0.00009938244,0.000002413314,0.000009447962,0.000026377165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977371,0.00048794856,0.00096941064,0.0002054488,0.0004157451,0.00018434011],"domain_scores_gemma":[0.9861829,0.01198871,0.0012555973,0.00014887525,0.00027680089,0.00014709504],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001427146,0.00014321081,0.0006033218,0.00014343228,0.000087441105,0.000022421871,0.00009360017,0.000033618348,0.000002761444],"category_scores_gemma":[0.013856045,0.000108134285,0.000076672186,0.0003338821,0.000041151638,0.00006785733,0.000028600876,0.00012459142,8.273431e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004954331,0.0012244978,0.003878563,0.00013142878,0.00024473848,0.0000011715586,0.0005931503,0.008076759,0.0024850578,0.030321505,0.00042929812,0.9521184],"study_design_scores_gemma":[0.0019993922,0.0028969126,0.63688344,0.0002833135,0.00072259316,0.000009342619,0.00021660744,0.014533304,0.00044162344,0.34176156,0.000039933926,0.00021201598],"about_ca_topic_score_codex":0.00003701082,"about_ca_topic_score_gemma":0.00008415188,"teacher_disagreement_score":0.9519064,"about_ca_system_score_codex":0.00077338755,"about_ca_system_score_gemma":0.00005742775,"threshold_uncertainty_score":0.9944507},"labels":[],"label_agreement":null},{"id":"W2108486794","doi":"10.1080/01621459.2012.720899","title":"A Multiresolution Method for Parameter Estimation of Diffusion Processes","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Stochastic processes and financial applications","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences","keywords":"Inference; Gibbs sampling; Extrapolation; Stochastic differential equation; Computer science; Parametric statistics; Bayesian inference; Bayesian probability; Frequentist inference; Applied mathematics; Algorithm; Diffusion; Mathematics; Econometrics; Statistics; Artificial intelligence","score_opus":0.022775276672395227,"score_gpt":0.2959182035990222,"score_spread":0.273142926926627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108486794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021079643,0.00019795338,0.9774605,0.0006339363,0.00017716156,0.00016169665,0.00023478398,0.0000038143278,0.000050493552],"genre_scores_gemma":[0.7233088,0.000015572557,0.27641946,0.000089535664,0.00011337325,0.000017461776,0.0000041349394,0.000007222675,0.000024457488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990325,0.000016276454,0.0006231851,0.00007653388,0.0000874266,0.00016405269],"domain_scores_gemma":[0.99576724,0.0011519416,0.0027293758,0.00008233716,0.0002225233,0.00004659341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082075456,0.00006736291,0.00032389228,0.00006731836,0.000077365214,0.000013947746,0.00012604178,0.00003492508,0.000005850804],"category_scores_gemma":[0.0073919604,0.000053811622,0.00009136568,0.00031664822,0.00004022369,0.0001453746,0.000021187543,0.00008699127,0.000005159398],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021427781,0.0007178779,0.058936458,0.00019046859,0.0001573541,8.438095e-8,0.0010094059,0.0006610508,0.0004043204,0.86179495,0.0017835883,0.07413016],"study_design_scores_gemma":[0.00073323253,0.0003363726,0.3947897,0.00004445168,0.00012280705,0.000006496509,0.000112496506,0.051910575,0.0004081914,0.5484104,0.002936746,0.00018853745],"about_ca_topic_score_codex":0.000077230055,"about_ca_topic_score_gemma":0.0000027794736,"teacher_disagreement_score":0.70222914,"about_ca_system_score_codex":0.00019135678,"about_ca_system_score_gemma":0.000037996862,"threshold_uncertainty_score":0.8849401},"labels":[],"label_agreement":null},{"id":"W2115621436","doi":"10.1198/jasa.2010.tm09414","title":"Composite Likelihood Bayesian Information Criteria for Model Selection in High-Dimensional Data","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Bayesian information criterion; Information Criteria; Model selection; Marginal likelihood; Sample size determination; Bayes' theorem; Bayes factor; Consistency (knowledge bases); Selection (genetic algorithm); Computer science; Mathematics; Statistics; Quasi-maximum likelihood; Likelihood principle; Bayesian probability; Maximum likelihood; Likelihood function; Machine learning; Artificial intelligence","score_opus":0.03807718683195343,"score_gpt":0.37731518636530154,"score_spread":0.3392379995333481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115621436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15409234,8.335415e-7,0.8435527,0.0012692229,0.00030148437,0.00015783774,0.00057178433,0.000008121272,0.00004565733],"genre_scores_gemma":[0.4341778,0.0000010716884,0.56544036,0.00024624343,0.00009845074,0.0000035145843,0.00001598723,0.0000069977555,0.00000959109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982237,0.00022644039,0.00073848164,0.00010657839,0.00047935577,0.0002254069],"domain_scores_gemma":[0.99489695,0.0030564812,0.001335872,0.00016548406,0.00046121413,0.00008401897],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019776826,0.00010923627,0.00035640755,0.0000892302,0.00009390223,0.00007260472,0.00032494488,0.000059477657,0.00003130627],"category_scores_gemma":[0.0130310515,0.00007804945,0.00005002781,0.00022757464,0.000060151793,0.00035440194,0.000080527476,0.00045671748,0.0000022690888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014966755,0.0011303216,0.0378847,0.00020911914,0.00036109885,0.0000039785177,0.00074144185,0.0009410636,0.037914373,0.5962843,0.10148194,0.22155102],"study_design_scores_gemma":[0.00054760993,0.00014522055,0.06298761,0.000025016454,0.000085064945,0.000008955782,0.000018795527,0.45025077,0.000146898,0.48556396,0.000118294454,0.000101803154],"about_ca_topic_score_codex":0.00006958789,"about_ca_topic_score_gemma":0.00007614283,"teacher_disagreement_score":0.4493097,"about_ca_system_score_codex":0.00018647555,"about_ca_system_score_gemma":0.00015904453,"threshold_uncertainty_score":0.9952826},"labels":[],"label_agreement":null},{"id":"W2134201249","doi":"10.1198/016214505000001023","title":"Bayesian Sample Size Determination for Case-Control Studies","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Sample size determination; Bayesian probability; Statistics; Monte Carlo method; Range (aeronautics); Computer science; Sample (material); Confidence interval; Interval estimation; Interval (graph theory); Mathematics; Engineering","score_opus":0.03259294827984577,"score_gpt":0.38508688999481944,"score_spread":0.35249394171497367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134201249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009254574,0.00002010795,0.98824227,0.0014241871,0.0002766091,0.00022007292,0.000493223,0.000011550655,0.000057395802],"genre_scores_gemma":[0.39547995,0.000003505175,0.6040395,0.00015075106,0.00025537345,0.000009257428,4.52283e-7,0.000011482061,0.000049743347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796724,0.00049927086,0.00073775544,0.00011727602,0.000429323,0.00024913813],"domain_scores_gemma":[0.9344256,0.06291485,0.001824512,0.000114793525,0.000666113,0.000054164622],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015536166,0.00013241926,0.0005434634,0.000043196276,0.00018038903,0.000050730217,0.00013981735,0.000040099134,0.00002648856],"category_scores_gemma":[0.08316276,0.00008606378,0.0001583499,0.00018938498,0.00012246777,0.000080962825,0.000019936148,0.00017985304,8.724157e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047713355,0.0005234289,0.034052152,0.00022502536,0.0007874885,0.00019229834,0.0004185885,0.000024875997,0.00093214825,0.5969101,0.04491593,0.32054082],"study_design_scores_gemma":[0.00064216164,0.0002934479,0.022329556,0.00003161967,0.0004572919,0.00012356791,0.00018650907,0.0034429482,0.00009735535,0.97212446,0.00015544589,0.00011561984],"about_ca_topic_score_codex":0.00007001962,"about_ca_topic_score_gemma":0.000063911364,"teacher_disagreement_score":0.38622537,"about_ca_system_score_codex":0.0004429095,"about_ca_system_score_gemma":0.000061550745,"threshold_uncertainty_score":0.9245601},"labels":[],"label_agreement":null},{"id":"W2136185920","doi":"10.1080/01621459.2012.699792","title":"Robust Estimation of Multivariate Location and Scatter in the Presence of Missing Data","year":2012,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate statistics; Missing data; Statistics; Estimation; Multivariate analysis; Mathematics; Computer science; Econometrics; Economics","score_opus":0.1512631494871567,"score_gpt":0.44076512519392796,"score_spread":0.2895019757067713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136185920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045206252,0.000029656196,0.9536319,0.0008856793,0.000059608166,0.000102776066,0.00005536158,0.0000012832433,0.00002752314],"genre_scores_gemma":[0.5747974,0.0000059137383,0.42511863,0.000042130057,0.000025790554,6.7729314e-7,0.0000015762513,0.0000037660122,0.000004108831],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99817216,0.00065799075,0.00055685785,0.000069175665,0.0004126848,0.00013115241],"domain_scores_gemma":[0.9910077,0.0069007105,0.0016722209,0.00020581289,0.00017842799,0.00003511462],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027876925,0.000065664135,0.00028612677,0.000037055303,0.000036558526,0.000011391248,0.00022812097,0.00002320738,0.000003010493],"category_scores_gemma":[0.017852806,0.000037703117,0.00002128992,0.00020452305,0.00012626089,0.0002421288,0.00006451708,0.00017053937,1.526968e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042811097,0.0015467751,0.04783208,0.0006550181,0.00027844787,0.000003996923,0.008800602,0.007294233,0.004663897,0.39654803,0.0033764362,0.5285724],"study_design_scores_gemma":[0.00055172143,0.00014957332,0.41499695,0.00026969516,0.00028792126,0.00002070378,0.0006425184,0.20477474,0.0003425227,0.377805,0.000036620764,0.00012203294],"about_ca_topic_score_codex":0.000051209656,"about_ca_topic_score_gemma":0.0000047076032,"teacher_disagreement_score":0.52959114,"about_ca_system_score_codex":0.00006833118,"about_ca_system_score_gemma":0.000034821293,"threshold_uncertainty_score":0.9904202},"labels":[],"label_agreement":null},{"id":"W2146675947","doi":"10.1198/jasa.2009.0011","title":"Estimating Response-Maximized Decision Rules With Applications to Breastfeeding","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Breastfeeding; Estimation; Breastfeeding promotion; Probit; Probit model; Medicine; Decision rule; Set (abstract data type); Observational study; Duration (music); Term (time); Randomized controlled trial; Econometrics; Mathematics; Statistics; Computer science; Pediatrics; Economics","score_opus":0.009983025576045983,"score_gpt":0.3125343999993475,"score_spread":0.30255137442330154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146675947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76552165,0.0000037857453,0.22044323,0.013505156,0.00005442636,0.00024478429,0.0000243287,0.000018907207,0.00018376549],"genre_scores_gemma":[0.76820236,9.816519e-7,0.23072718,0.00075067155,0.00025556877,0.0000042324286,0.0000014901979,0.000010381668,0.000047134075],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981332,0.00018932164,0.0004093175,0.00014300749,0.00090085407,0.00022431664],"domain_scores_gemma":[0.99614835,0.0020039203,0.000989686,0.00017463173,0.0004704199,0.0002129975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008364515,0.00012373034,0.0004847111,0.000099487406,0.00013798662,0.000049979124,0.00015810296,0.000028641281,0.000011084931],"category_scores_gemma":[0.0035626392,0.00007666336,0.00010439394,0.00050356385,0.000057034045,0.00010705249,0.00003579575,0.0003397596,0.000021915548],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014826884,0.007956382,0.2249037,0.0000389965,0.0005629017,0.00006943567,0.00045647915,0.0015872964,0.020763962,0.0077746767,0.009398392,0.7116609],"study_design_scores_gemma":[0.00082668074,0.0012927124,0.9836217,0.00011993873,0.00021531782,0.00006595552,0.000033525284,0.00126346,0.00019992216,0.012063317,0.00020461195,0.00009283018],"about_ca_topic_score_codex":0.000014092185,"about_ca_topic_score_gemma":0.000002252804,"teacher_disagreement_score":0.758718,"about_ca_system_score_codex":0.000671533,"about_ca_system_score_gemma":0.00012657861,"threshold_uncertainty_score":0.42650694},"labels":[],"label_agreement":null},{"id":"W2148129708","doi":"10.1198/016214502388618889","title":"Marginal Methods for Incomplete Longitudinal Data Arising in Clusters","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Missing data; Generalized estimating equation; Statistics; Cluster analysis; Marginal model; Multivariate statistics; Mathematics; Estimating equations; Econometrics; Logistic regression; Random effects model; Computer science; Regression analysis; Data mining; Estimator","score_opus":0.183358493295378,"score_gpt":0.4736633770486534,"score_spread":0.2903048837532754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148129708","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002856915,0.000024495013,0.9939937,0.0023268068,0.000275367,0.0001536748,0.0001920529,0.0000062860386,0.0001707274],"genre_scores_gemma":[0.049185343,0.000015206528,0.95035964,0.00020806496,0.00016453544,0.0000033573533,0.0000026966145,0.00001556853,0.000045601562],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997285,0.0010195626,0.0007941283,0.0001848262,0.00041096477,0.00030552325],"domain_scores_gemma":[0.98269093,0.015140213,0.0015702293,0.00030094013,0.00021067694,0.00008702599],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035826815,0.00013092419,0.0005681217,0.0000907458,0.000096669646,0.000068316185,0.00055052387,0.00004132466,0.000074640106],"category_scores_gemma":[0.02813574,0.000090870424,0.0000867897,0.0003428366,0.000120825665,0.00014711353,0.00014016205,0.00038132456,0.0000024602143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026392727,0.00040650452,0.040344417,0.00010428905,0.0002496991,0.0000196775,0.0003403036,0.000010300756,0.00033071364,0.1355887,0.035387546,0.7869539],"study_design_scores_gemma":[0.00087084854,0.00033125043,0.10768843,0.000111101544,0.00026467838,0.000041037278,0.00014206914,0.08405408,0.0000286142,0.8044664,0.0017916071,0.00020986957],"about_ca_topic_score_codex":0.00003919414,"about_ca_topic_score_gemma":0.000019680108,"teacher_disagreement_score":0.78674406,"about_ca_system_score_codex":0.00040759813,"about_ca_system_score_gemma":0.00004154856,"threshold_uncertainty_score":0.9800507},"labels":[],"label_agreement":null},{"id":"W2160929550","doi":"10.1198/016214504000002069","title":"Limited- and Full-Information Estimation and Goodness-of-Fit Testing in 2<i><sup>n</sup></i>Contingency Tables","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":264,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of British Columbia","funders":"","keywords":"Statistics; Goodness of fit; Mathematics; Contingency table; Pooling; Estimator; Multivariate statistics; Statistical hypothesis testing; Parametric statistics; Econometrics; Computer science","score_opus":0.18925620646060193,"score_gpt":0.455272008541823,"score_spread":0.26601580208122105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160929550","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7400749,0.000046792342,0.25733325,0.001742432,0.0001255926,0.0002822471,0.00013008871,0.00001534439,0.0002494024],"genre_scores_gemma":[0.43591473,0.000031297765,0.56382704,0.000110823625,0.00009627156,0.0000026812768,6.860593e-7,0.000008343659,0.000008114723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966992,0.0007270435,0.0016442464,0.00011708806,0.00058384374,0.0002285612],"domain_scores_gemma":[0.9574437,0.038724612,0.0031898618,0.00013024035,0.00041319468,0.00009835237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004302433,0.00014399819,0.0006834382,0.00012984939,0.00007577704,0.00006635112,0.00015135706,0.00007718996,0.000017201444],"category_scores_gemma":[0.20584695,0.00010620793,0.000058141082,0.00044786773,0.00017858087,0.0003914639,0.00008014996,0.00037513245,0.0000019839981],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033601726,0.00029436903,0.098242074,0.000233497,0.00015765698,0.000003330413,0.0012419322,0.0013842821,0.0004036869,0.031457495,0.0016001179,0.86464554],"study_design_scores_gemma":[0.0018851834,0.00068899523,0.22560965,0.0004305108,0.00039832623,0.00004387724,0.00066453,0.18382122,0.00016204857,0.58582175,0.00018640855,0.000287548],"about_ca_topic_score_codex":0.000041429656,"about_ca_topic_score_gemma":0.000010193943,"teacher_disagreement_score":0.864358,"about_ca_system_score_codex":0.00022283528,"about_ca_system_score_gemma":0.000071820345,"threshold_uncertainty_score":0.8008425},"labels":[],"label_agreement":null},{"id":"W2161630302","doi":"10.1198/016214502753479347","title":"Length-Biased Sampling With Right Censoring","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":217,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Censoring (clinical trials); Estimator; Mathematics; Truncation (statistics); Survival function; Statistics; Econometrics; Nonparametric statistics; Conditional probability distribution; Asymptotic distribution; Applied mathematics","score_opus":0.07582687449166572,"score_gpt":0.351289446542451,"score_spread":0.2754625720507853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161630302","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16380996,0.000017248183,0.83249116,0.001354315,0.00023059148,0.000102902355,0.00006256396,0.000019385621,0.0019118796],"genre_scores_gemma":[0.49324912,0.000014468545,0.50612974,0.00020272554,0.00016613911,0.0000015596686,2.605726e-7,0.000015457685,0.00022054733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807656,0.00035951968,0.0005126322,0.000107697,0.00068616046,0.00025740537],"domain_scores_gemma":[0.9914002,0.0065813754,0.0014470769,0.00014899825,0.00031502682,0.000107343214],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007677748,0.00012225128,0.00041522898,0.000045868303,0.0001291625,0.00005380591,0.0002014295,0.000030287343,0.00043456486],"category_scores_gemma":[0.011047289,0.00006960505,0.00008017856,0.0002757588,0.00010875731,0.00006874488,0.000027269001,0.00038721637,0.0000114253135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003979756,0.0010992906,0.061559957,0.00012260316,0.00085177174,0.00013447167,0.0015556219,0.00014564268,0.0022121738,0.6017892,0.041584127,0.2885472],"study_design_scores_gemma":[0.00262864,0.002136026,0.22932759,0.0005038832,0.0011272432,0.00024434854,0.0007285275,0.014604848,0.0013832905,0.73845494,0.00797899,0.0008816821],"about_ca_topic_score_codex":0.000015135048,"about_ca_topic_score_gemma":0.0000033429146,"teacher_disagreement_score":0.32943916,"about_ca_system_score_codex":0.00030449114,"about_ca_system_score_gemma":0.000025571073,"threshold_uncertainty_score":0.9972831},"labels":[],"label_agreement":null},{"id":"W2162340617","doi":"10.1198/jasa.2009.tm08393","title":"Learn From Thy Neighbor: Parallel-Chain and Regional Adaptive MCMC","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Markov chain Monte Carlo; Chain (unit); Computer science; Mathematics; Artificial intelligence; Bayesian probability; Physics","score_opus":0.03818152078787884,"score_gpt":0.33171437632028944,"score_spread":0.2935328555324106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162340617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4615188,0.00021947436,0.5196953,0.015721314,0.00032500355,0.00022913728,0.00013575892,0.00002575143,0.002129487],"genre_scores_gemma":[0.71790427,0.00012103369,0.27912864,0.0017723177,0.00040796876,0.0000013994253,0.0000023888772,0.000015027409,0.0006469241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981598,0.00058075436,0.00042847704,0.00011826882,0.000527737,0.00018495809],"domain_scores_gemma":[0.99529564,0.0028883452,0.0013822548,0.00012443922,0.00020233386,0.00010698311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097221904,0.00012100788,0.00041856623,0.00004079277,0.000090316644,0.000037748534,0.00014451072,0.000047518446,0.00001330773],"category_scores_gemma":[0.0029606328,0.00007983703,0.00011828785,0.00013033915,0.00008225912,0.00007202941,0.000030577427,0.00034684205,1.5438384e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017794559,0.00068300386,0.020295708,0.000018085866,0.00092924957,0.00007478034,0.002830081,0.00008208895,0.002599998,0.44247752,0.16253662,0.3656934],"study_design_scores_gemma":[0.0015304686,0.0013135892,0.21562915,0.00010013636,0.00041694695,0.000038589635,0.0012791376,0.004032787,0.00006738515,0.7686715,0.006575422,0.0003448614],"about_ca_topic_score_codex":0.000060590763,"about_ca_topic_score_gemma":0.000021219523,"teacher_disagreement_score":0.36534855,"about_ca_system_score_codex":0.0002478432,"about_ca_system_score_gemma":0.000054763164,"threshold_uncertainty_score":0.35443678},"labels":[],"label_agreement":null},{"id":"W2204774351","doi":"10.1080/01621459.2015.1108848","title":"Exact Post-Selection Inference for Sequential Regression Procedures","year":2016,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":352,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Inference; Lasso (programming language); Mathematics; Regression; Model selection; Algorithm; Regularization (linguistics); Computer science; Regression analysis; Statistics; Artificial intelligence","score_opus":0.042453381628087546,"score_gpt":0.4014923890323961,"score_spread":0.35903900740430855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204774351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11046892,0.0000052731643,0.8855568,0.0032374607,0.0003042068,0.00017602067,0.00015690677,0.000014471469,0.00007990083],"genre_scores_gemma":[0.7468515,0.000021391805,0.25232717,0.0001988057,0.00027344143,0.000009415042,7.453452e-7,0.00001547464,0.0003020498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816203,0.00038952666,0.0005562366,0.00012518904,0.00052642316,0.00024057603],"domain_scores_gemma":[0.98745215,0.009615554,0.0018407023,0.00010021682,0.0009008011,0.00009059634],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010531041,0.00012273622,0.0003611492,0.000055083994,0.00012277573,0.00004013132,0.00019397821,0.00004966846,0.00008081631],"category_scores_gemma":[0.06485523,0.00005739568,0.00012468197,0.00017350705,0.000103502956,0.00010962326,0.000034657736,0.00016409092,0.000003943218],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013903731,0.00044348443,0.044004668,0.00016858715,0.00035605967,0.000004569664,0.00029518217,0.000004028444,0.09993327,0.42784014,0.052058835,0.3735008],"study_design_scores_gemma":[0.0009398409,0.0013097152,0.12763149,0.00033807833,0.00024517762,0.000023260985,0.000074777745,0.00039550033,0.005019916,0.8628704,0.00093365327,0.00021821122],"about_ca_topic_score_codex":0.00001692925,"about_ca_topic_score_gemma":0.000014895129,"teacher_disagreement_score":0.6363826,"about_ca_system_score_codex":0.00040688287,"about_ca_system_score_gemma":0.00023119553,"threshold_uncertainty_score":0.9430219},"labels":[],"label_agreement":null},{"id":"W2289998504","doi":"10.1080/01621459.2017.1319840","title":"Oracle Estimation of a Change Point in High-Dimensional Quantile Regression","year":2017,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"European Research Council; Economic and Social Research Council","keywords":"Quantile regression; Quantile; Oracle; Estimator; Covariate; Mathematics; Econometrics; Function (biology); Statistics; Quantile function; Regression analysis; Regression; Applied mathematics; Computer science; Probability distribution","score_opus":0.10148184220728133,"score_gpt":0.4207269148726762,"score_spread":0.31924507266539487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289998504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8264,0.000011727958,0.17002167,0.0028132033,0.00036879646,0.00015872852,0.00010622846,0.000005203123,0.0001144803],"genre_scores_gemma":[0.7202686,0.000006783753,0.2795679,0.00006372368,0.000059279977,0.0000026167459,8.0793e-7,0.0000073765455,0.000022935423],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99807173,0.00039125193,0.00065337407,0.00009478034,0.00062431913,0.00016456103],"domain_scores_gemma":[0.9931327,0.0027636054,0.0035207507,0.00023894118,0.0002837862,0.00006022503],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015602682,0.0000971476,0.00048118015,0.00006564483,0.000118906966,0.000036394926,0.00026810364,0.000042026793,0.000052139232],"category_scores_gemma":[0.026821703,0.00006022574,0.00007477292,0.00011007728,0.00014929315,0.00015923937,0.00008661272,0.00025813025,0.0000031437467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074149884,0.0010586282,0.13063481,0.00016481831,0.00016970964,0.000044946653,0.0009021702,0.000122037054,0.00224418,0.42746708,0.008067049,0.42838308],"study_design_scores_gemma":[0.00043079877,0.00022936602,0.63750273,0.00022868231,0.000054576114,0.000005532967,0.000040890965,0.012887015,0.00040665845,0.3481298,0.000011661667,0.00007228972],"about_ca_topic_score_codex":0.00035489842,"about_ca_topic_score_gemma":0.000027289172,"teacher_disagreement_score":0.50686795,"about_ca_system_score_codex":0.00021650603,"about_ca_system_score_gemma":0.0000627633,"threshold_uncertainty_score":0.9813758},"labels":[],"label_agreement":null},{"id":"W2314015194","doi":"10.1080/01621459.2016.1158716","title":"Model Comparison and Assessment for Single Particle Tracking in Biological Fluids","year":2016,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Fractional Differential Equations Solutions","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistical physics; Brownian motion; Inference; Particle (ecology); Tracking (education); Bayesian inference; Langevin equation; Fractional Brownian motion; Computer science; Bayesian probability; Model selection; Econometrics; Mathematics; Physics; Statistics; Artificial intelligence; Ecology; Biology","score_opus":0.15760534852212243,"score_gpt":0.42388175418422624,"score_spread":0.2662764056621038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2314015194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49622917,0.000004753151,0.50119823,0.0023756267,0.000048220423,0.00007398106,0.0000367064,0.000004004991,0.000029303315],"genre_scores_gemma":[0.90991473,0.0000075740386,0.08993194,0.000049843828,0.00004288294,0.0000070272044,7.0685337e-7,0.0000057186185,0.00003954334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989026,0.00017810278,0.00044576137,0.00007428552,0.00025537537,0.0001438441],"domain_scores_gemma":[0.9953437,0.0037031816,0.0006748039,0.000058098525,0.00017742555,0.000042821317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006104642,0.000060961054,0.00023696627,0.00003423742,0.000073792675,0.000024581272,0.000074210686,0.000028169856,0.000008017106],"category_scores_gemma":[0.004874228,0.000033937253,0.000057683872,0.00010629343,0.00007588016,0.000101746904,0.000022782782,0.00011458198,7.005647e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023191559,0.0015801963,0.30759266,0.000016769625,0.00017176084,0.0000013336673,0.00032420672,0.00047866316,0.17133772,0.4499058,0.0041124546,0.0642465],"study_design_scores_gemma":[0.0010046615,0.00039543648,0.44842324,0.000056589437,0.000093718736,0.0000053944036,0.00015789464,0.09335637,0.0008464809,0.45543936,0.000108291424,0.00011256607],"about_ca_topic_score_codex":0.000006862662,"about_ca_topic_score_gemma":0.00002444486,"teacher_disagreement_score":0.4136856,"about_ca_system_score_codex":0.0006040089,"about_ca_system_score_gemma":0.00005659079,"threshold_uncertainty_score":0.58352584},"labels":[],"label_agreement":null},{"id":"W2323491979","doi":"10.1080/01621459.2016.1159211","title":"A Method of Constructing Space-Filling Orthogonal Designs","year":2016,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Orthogonality; Generality; Orthogonal array; Simplicity; Space (punctuation); Class (philosophy); Latin hypercube sampling; Hypercube; Computer science; Mathematics; Theoretical computer science; Algebra over a field; Algorithm; Mathematical optimization; Pure mathematics; Discrete mathematics; Artificial intelligence; Geometry; Statistics; Monte Carlo method","score_opus":0.016654755919725307,"score_gpt":0.30833159826350426,"score_spread":0.29167684234377894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2323491979","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002366284,0.0000064958904,0.99578756,0.0014300754,0.0002158545,0.00005847329,0.0000216356,0.000010977265,0.00010262294],"genre_scores_gemma":[0.12979493,0.000011215467,0.86998206,0.000087784,0.00006173633,5.578267e-7,1.1821533e-7,0.000006572692,0.00005503908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981411,0.00048408378,0.00049430644,0.00012724582,0.0005719864,0.00018128655],"domain_scores_gemma":[0.9933082,0.0031370984,0.0026517373,0.00013956928,0.0006922672,0.000071167255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010085503,0.00008873381,0.00031117143,0.00008280561,0.00006855962,0.00002706643,0.00037025387,0.000024057803,0.00001170915],"category_scores_gemma":[0.00384838,0.000051069837,0.00009800128,0.0004532335,0.000108139386,0.00029919334,0.00008950976,0.00014811585,0.0000022832653],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007409163,0.00012388949,0.03745749,0.000008759988,0.0002715142,0.000013253935,0.0005518725,0.0044288817,0.029391153,0.10450731,0.0003981787,0.8227736],"study_design_scores_gemma":[0.009571582,0.0027262343,0.30659327,0.000902054,0.0006178827,0.001163655,0.0027170277,0.34507263,0.09046023,0.23584352,0.0024593212,0.0018726004],"about_ca_topic_score_codex":0.000005335886,"about_ca_topic_score_gemma":0.0000011958196,"teacher_disagreement_score":0.820901,"about_ca_system_score_codex":0.00037634897,"about_ca_system_score_gemma":0.00016241243,"threshold_uncertainty_score":0.46071482},"labels":[],"label_agreement":null},{"id":"W2486722287","doi":"10.1080/01621459.2016.1141687","title":"Nonparametric Estimation of the Leverage Effect: A Trade-Off Between Robustness and Efficiency","year":2016,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Econometrics; Estimator; Nonparametric statistics; Economics; Volatility (finance); Implied volatility; Volatility smile; Mathematics; Statistics","score_opus":0.010984284709677019,"score_gpt":0.22597055041475161,"score_spread":0.2149862657050746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2486722287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558772,0.00012521888,0.040670943,0.0024529519,0.00023011852,0.0001145422,0.00013988127,0.0000028415716,0.0003863405],"genre_scores_gemma":[0.9989435,0.00006905919,0.0007837461,0.00006553513,0.00005979177,0.0000015800316,3.961061e-7,0.0000065242634,0.000069887246],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99894136,0.000115732866,0.0005737197,0.00009821464,0.0001301547,0.00014081008],"domain_scores_gemma":[0.9965203,0.0012109055,0.0020881877,0.00010916328,0.000035738976,0.000035720423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009940221,0.00008403129,0.00039322174,0.00008680997,0.000087682936,0.000031208572,0.00018549566,0.000035449837,0.000013478245],"category_scores_gemma":[0.0029698096,0.000043561475,0.00009693065,0.0004054653,0.00016271239,0.00014463656,0.000035393743,0.000117745054,0.000002404979],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005974587,0.000092201066,0.8549224,0.00003578021,0.00011652875,7.939822e-7,0.00013249325,0.00050592335,0.00009351776,0.05619302,0.0015351122,0.08631246],"study_design_scores_gemma":[0.00037395942,0.00026801773,0.9826412,0.000037156537,0.000034869856,0.0000018658914,0.000009937706,0.0014427758,0.00009735909,0.01479901,0.00022698076,0.00006682235],"about_ca_topic_score_codex":0.000036885383,"about_ca_topic_score_gemma":0.0000014176444,"teacher_disagreement_score":0.12771882,"about_ca_system_score_codex":0.00021363384,"about_ca_system_score_gemma":0.00003113999,"threshold_uncertainty_score":0.3555354},"labels":[],"label_agreement":null},{"id":"W2561265960","doi":"10.1080/01621459.2017.1407775","title":"Censoring Unbiased Regression Trees and Ensembles","year":2018,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute","keywords":"Censoring (clinical trials); Random forest; Regression; Statistics; Inference; Mathematics; Computer science; Mean squared error; Regression analysis; Artificial intelligence; Machine learning","score_opus":0.0496418759659346,"score_gpt":0.3841708336032706,"score_spread":0.334528957637336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561265960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74642813,0.000017634075,0.2512377,0.001336101,0.00030995772,0.000068967376,0.000038441744,0.000012206776,0.0005508906],"genre_scores_gemma":[0.78453195,0.000021712018,0.21488872,0.00016350148,0.0002711727,7.133771e-7,2.1115444e-7,0.000009703759,0.000112333815],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984579,0.00042795297,0.00041092344,0.0000922183,0.00043558504,0.00017540203],"domain_scores_gemma":[0.993997,0.0043030404,0.0011717628,0.00010816775,0.00033026963,0.00008980055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009004751,0.00009457217,0.00033031622,0.000040301587,0.00013064481,0.000042523516,0.00012561992,0.00003036382,0.00004493368],"category_scores_gemma":[0.018569658,0.000053868032,0.00005083859,0.00017047922,0.00021726107,0.000050544702,0.00004753014,0.00019840081,0.0000034404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057092216,0.00032594553,0.15479465,0.00006943064,0.00033794952,0.000026647835,0.0013770176,0.0000017192251,0.014057023,0.384489,0.049024597,0.3949251],"study_design_scores_gemma":[0.000468601,0.00068326446,0.41423965,0.00017248718,0.0001775114,0.000027337732,0.00029110615,0.0012754656,0.0015182678,0.58008754,0.0009052742,0.00015349535],"about_ca_topic_score_codex":0.000023761853,"about_ca_topic_score_gemma":0.000011493503,"teacher_disagreement_score":0.3947716,"about_ca_system_score_codex":0.00013762651,"about_ca_system_score_gemma":0.000038475853,"threshold_uncertainty_score":0.98969734},"labels":[],"label_agreement":null},{"id":"W2573013575","doi":"10.1080/01621459.2017.1281813","title":"Equivalence of Regression Curves","year":2017,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Estimator; Nominal level; Sample size determination; Equivalence (formal languages); Covariate; Null hypothesis; Statistics; Applied mathematics; Parametric statistics; Inference; Statistical hypothesis testing; Confidence interval; Discrete mathematics; Computer science; Artificial intelligence","score_opus":0.11135897940056116,"score_gpt":0.4853311378153559,"score_spread":0.37397215841479475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573013575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03604284,0.00006959038,0.95954335,0.0029892323,0.00032174637,0.00010010843,0.00011653448,0.0000052296045,0.00081138534],"genre_scores_gemma":[0.55878323,0.00023023773,0.44036987,0.00016260744,0.00009609654,0.0000012143707,3.3192788e-7,0.00001129489,0.0003450871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982656,0.0003065022,0.00054421404,0.00008226376,0.00064379553,0.00015759538],"domain_scores_gemma":[0.9913286,0.0032331971,0.004657214,0.00030594587,0.00040465035,0.00007037655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012780305,0.000087339824,0.00046585628,0.000022947444,0.00016880748,0.000022076554,0.0004259851,0.000025305975,0.000024339764],"category_scores_gemma":[0.03956427,0.000050205916,0.0001129876,0.000056197518,0.00023730082,0.00013549623,0.0000997114,0.00023490633,0.0000010471585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004981226,0.00063184503,0.041634794,0.0006942033,0.00041423365,0.000034913297,0.00035282588,0.000027285783,0.0093731405,0.61071193,0.06479809,0.27082863],"study_design_scores_gemma":[0.00032418827,0.00025585582,0.09996983,0.00072848314,0.00019201811,0.000009423178,0.000048831633,0.00040919715,0.0010641166,0.89660215,0.00029364918,0.0001022272],"about_ca_topic_score_codex":0.000018059885,"about_ca_topic_score_gemma":0.0000029480834,"teacher_disagreement_score":0.5227404,"about_ca_system_score_codex":0.0001248735,"about_ca_system_score_gemma":0.00005801058,"threshold_uncertainty_score":0.9685259},"labels":[],"label_agreement":null},{"id":"W2669206880","doi":"10.1080/01621459.2018.1505626","title":"MCMC for Imbalanced Categorical Data","year":2018,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Computer science; Markov chain Monte Carlo; Bayesian probability; Approximate Bayesian computation; Computational complexity theory; Computation; Sample size determination; Sample (material); Bayesian inference; Logarithm; Machine learning; Data mining; Algorithm; Artificial intelligence; Mathematics; Statistics","score_opus":0.03988550071863376,"score_gpt":0.3559444286280251,"score_spread":0.31605892790939133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2669206880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046786113,0.000043773056,0.9901397,0.0065884967,0.0020924723,0.00019947495,0.0003308585,0.000016422217,0.000120933575],"genre_scores_gemma":[0.041989848,0.000046745987,0.9557546,0.00081476156,0.0011782659,0.000005989661,0.000020650574,0.000015813253,0.00017336858],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973801,0.00057078263,0.00067085074,0.00036700827,0.0007104604,0.00030081708],"domain_scores_gemma":[0.9934195,0.0015432396,0.0032497204,0.0010166899,0.0006470789,0.00012376689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025642894,0.0001827402,0.00065218436,0.0000628395,0.00011022261,0.00021593942,0.003181599,0.000116369745,0.0000038753155],"category_scores_gemma":[0.0037485175,0.000119502154,0.00018656136,0.00021799732,0.00009684758,0.00017028359,0.0015918124,0.0006836356,0.0000035987673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017948801,0.00031803866,0.0031354483,0.00010561083,0.0008172795,0.000014718891,0.0004263587,0.00007693718,0.00027320578,0.12617615,0.5332782,0.33519858],"study_design_scores_gemma":[0.00048080657,0.00037593336,0.024920631,0.00006267231,0.00028794014,0.000029516843,0.0000080657865,0.10376327,0.00007183424,0.8581315,0.011532544,0.00033523812],"about_ca_topic_score_codex":0.00003314348,"about_ca_topic_score_gemma":0.000004604166,"teacher_disagreement_score":0.7319554,"about_ca_system_score_codex":0.00049089355,"about_ca_system_score_gemma":0.00048088678,"threshold_uncertainty_score":0.59122556},"labels":[],"label_agreement":null},{"id":"W2749533234","doi":"10.1080/01621459.2018.1520117","title":"Forecasting Multiple Time Series With One-Sided Dynamic Principal Components","year":2018,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Series (stratigraphy); Mathematics; Principal component analysis; Applied mathematics; Dynamic factor; Monte Carlo method; Ergodic theory; Factor analysis; Time series; Mean squared error; Statistics; Algorithm; Mathematical analysis","score_opus":0.08378136906995488,"score_gpt":0.35944966637924264,"score_spread":0.27566829730928777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749533234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8506751,0.000008066797,0.14396852,0.0035603207,0.00031751473,0.00042770628,0.0005630149,0.000045958164,0.00043379466],"genre_scores_gemma":[0.81569964,0.000004723385,0.18317889,0.00011817769,0.00020865357,0.000012914786,0.000020321046,0.000026752707,0.0007299257],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99504477,0.00053230306,0.001328674,0.00036008566,0.002407763,0.00032639017],"domain_scores_gemma":[0.9857806,0.004143809,0.007694401,0.0005607863,0.001681405,0.00013900171],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003213247,0.00024283385,0.00082717394,0.00016846719,0.00029167565,0.0003489251,0.0012763187,0.00011011672,0.00006899895],"category_scores_gemma":[0.01659068,0.00014588983,0.00022441268,0.0005536174,0.00040703593,0.00014922275,0.00072353584,0.0008472566,0.00004217774],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038986271,0.002645244,0.60344195,0.00016745427,0.0032614276,0.000111122055,0.0030345838,0.014541849,0.0075315535,0.00336875,0.17989491,0.17810257],"study_design_scores_gemma":[0.0007787166,0.0012806783,0.5867017,0.0007641458,0.0004783841,0.00013770655,0.00020953378,0.22616029,0.0004173069,0.17888428,0.0034951316,0.000692126],"about_ca_topic_score_codex":0.00009871306,"about_ca_topic_score_gemma":0.000076384684,"teacher_disagreement_score":0.21161844,"about_ca_system_score_codex":0.00077344064,"about_ca_system_score_gemma":0.00026433103,"threshold_uncertainty_score":0.991693},"labels":[],"label_agreement":null},{"id":"W2801477319","doi":"10.1080/01621459.2018.1469991","title":"Capture-Recapture Methods for Data on the Activation of Applications on Mobile Phones","year":2018,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Census and Population Estimation","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Mark and recapture; Identification (biology); Context (archaeology); Automatic identification and data capture; Estimator; Mobile device; Data mining; Parametric statistics; Real-time computing; Variance (accounting); Mobile broadband; Statistics; Telecommunications; World Wide Web; Geography","score_opus":0.07360517283819713,"score_gpt":0.4430409186927909,"score_spread":0.36943574585459377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801477319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026929641,0.000005781093,0.9673139,0.0042344765,0.00021127873,0.0005752723,0.0002702788,0.000009728082,0.00044965558],"genre_scores_gemma":[0.80713564,0.000004869698,0.19160926,0.0005712716,0.00047020928,0.000027937356,0.000036189984,0.000018526984,0.00012612493],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842036,0.00048739612,0.00049472187,0.0001097734,0.00037585627,0.00011189059],"domain_scores_gemma":[0.98985434,0.0069294036,0.002282859,0.00038831058,0.0005139518,0.00003116748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021068694,0.00009258756,0.0002463404,0.00004875768,0.0001696251,0.00002210383,0.0003545719,0.000037603088,0.000028083052],"category_scores_gemma":[0.005970355,0.000051003586,0.000079270525,0.00025160227,0.0000975088,0.00007552524,0.000036378948,0.00018230127,0.0000037921748],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075835147,0.0009844428,0.0034804146,0.00009369987,0.0005552383,1.8185737e-7,0.0021546541,0.00047563572,0.0067094304,0.39164338,0.18550989,0.40763468],"study_design_scores_gemma":[0.0016547815,0.0022324598,0.109016426,0.00031935493,0.0009833132,0.000010480518,0.001439192,0.063554175,0.012259602,0.723608,0.08439948,0.00052274787],"about_ca_topic_score_codex":0.000024141738,"about_ca_topic_score_gemma":0.0000067951296,"teacher_disagreement_score":0.78020597,"about_ca_system_score_codex":0.00018076881,"about_ca_system_score_gemma":0.000047900725,"threshold_uncertainty_score":0.7147504},"labels":[],"label_agreement":null},{"id":"W2884166570","doi":"10.1080/01621459.2018.1505624","title":"Quantile-Regression Inference With Adaptive Control of Size","year":2018,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Quantile; Covariate; Estimator; Quantile regression; Variance (accounting); Sample size determination; Inference; Monte Carlo method; Asymptotic distribution","score_opus":0.03533491766544427,"score_gpt":0.3729662933818459,"score_spread":0.3376313757164016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884166570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15694457,0.0000056488398,0.8417711,0.00047393286,0.00013961192,0.00010200294,0.000109090885,0.000006117189,0.000447911],"genre_scores_gemma":[0.74084216,0.0000037815125,0.25886917,0.00012520657,0.00010393893,0.0000013413108,1.228369e-7,0.000008593972,0.000045663568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99777186,0.00059417845,0.0005990284,0.00010115615,0.0007362036,0.00019759891],"domain_scores_gemma":[0.9808943,0.014975048,0.0027684364,0.00015676275,0.0011181288,0.000087318986],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009905763,0.00012397607,0.0005674919,0.000035717003,0.0000771811,0.000019207946,0.00022874039,0.000037376158,0.00010769075],"category_scores_gemma":[0.028602108,0.00006336499,0.0000764343,0.00028343548,0.0004342775,0.00006326597,0.000032877353,0.00026629155,0.0000039167303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003513079,0.0007392806,0.14898781,0.00007345746,0.00082014455,0.000018354383,0.0010320023,0.000013846241,0.006680686,0.749168,0.008807991,0.08014538],"study_design_scores_gemma":[0.001757037,0.005402198,0.49589184,0.0004406825,0.00054298906,0.000020014151,0.00045810672,0.0044760136,0.0024009368,0.4881772,0.00017583942,0.00025713342],"about_ca_topic_score_codex":0.000044883272,"about_ca_topic_score_gemma":0.000012553153,"teacher_disagreement_score":0.5838976,"about_ca_system_score_codex":0.00014993486,"about_ca_system_score_gemma":0.000147775,"threshold_uncertainty_score":0.9795804},"labels":[],"label_agreement":null},{"id":"W2896398456","doi":"10.1080/01621459.2018.1543124","title":"Adaptive Huber Regression","year":2018,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":305,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Regression; Statistics; Mathematics; Econometrics","score_opus":0.0743662802260562,"score_gpt":0.43997008739893506,"score_spread":0.3656038071728789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896398456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021836093,0.000008950914,0.97526807,0.00091096404,0.00037395058,0.00007707992,0.000049929113,0.000010472995,0.0014644769],"genre_scores_gemma":[0.36717597,0.000008304701,0.6314394,0.00032388596,0.0004122458,0.0000013594215,3.006683e-7,0.000014579136,0.0006239661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809253,0.00049425196,0.00048116903,0.00010586753,0.0006089123,0.00021727222],"domain_scores_gemma":[0.9939537,0.003525955,0.0016851582,0.0001463896,0.00058936543,0.000099432626],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009780569,0.00010811084,0.00037760267,0.000037307607,0.00013382318,0.00002056839,0.00018797583,0.000035454068,0.00006715975],"category_scores_gemma":[0.011205593,0.00006048599,0.00009954921,0.00021425477,0.00022469662,0.000092105336,0.0000561499,0.00028961705,0.000011404946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081358565,0.00037782473,0.0038939076,0.00002093933,0.00034346536,0.000024381508,0.00078681664,0.000012384231,0.0017009818,0.63310724,0.14301938,0.21589908],"study_design_scores_gemma":[0.00031787073,0.0006429921,0.013452404,0.00006539885,0.00013688112,0.00001611942,0.00015406328,0.001322006,0.0004406523,0.98083144,0.0025062095,0.00011392915],"about_ca_topic_score_codex":0.000008752677,"about_ca_topic_score_gemma":0.0000052078794,"teacher_disagreement_score":0.34772423,"about_ca_system_score_codex":0.00031179714,"about_ca_system_score_gemma":0.00006123624,"threshold_uncertainty_score":0.9971234},"labels":[],"label_agreement":null},{"id":"W2917498738","doi":"10.1080/01621459.2023.2183130","title":"Hypotheses Testing from Complex Survey Data Using Bootstrap Weights: A Unified Approach","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Stroke Foundation; National Science Foundation","keywords":"Type I and type II errors; Statistics; Categorical variable; Wald test; Statistical hypothesis testing; Computer science; Likelihood-ratio test; Goodness of fit; Mathematics; Nominal level; Econometrics; Data mining; Confidence interval","score_opus":0.5140034967384134,"score_gpt":0.45464535895251196,"score_spread":0.05935813778590143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917498738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10694906,0.000005221381,0.88956803,0.00019339923,0.00018596298,0.00011678407,0.0026447787,0.000034843943,0.00030191385],"genre_scores_gemma":[0.23217797,0.000005683988,0.767425,0.00009735593,0.00019881512,9.335467e-7,0.000050097242,0.000023077184,0.000021073214],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9962088,0.0016174407,0.00079040555,0.000227264,0.00082825526,0.0003278199],"domain_scores_gemma":[0.9651784,0.031924635,0.0019545981,0.00042270936,0.00040271835,0.000116980926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00311677,0.00016260071,0.0006200397,0.000085250205,0.0001832234,0.000117299365,0.0007359084,0.000048986574,0.000040596737],"category_scores_gemma":[0.06274059,0.00010765549,0.00006440989,0.0009844878,0.00017363804,0.00013136545,0.0002331059,0.00038552345,0.000008396526],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005063513,0.0010104724,0.6640185,0.00016516798,0.0016758782,0.000093814306,0.0008256162,0.000086210646,0.007973016,0.10560033,0.072272465,0.14577214],"study_design_scores_gemma":[0.00021087435,0.000065043656,0.5832049,0.000047045516,0.00016714286,0.000007649231,0.00017360445,0.062873915,0.000017255765,0.35304657,0.00005555004,0.00013041736],"about_ca_topic_score_codex":0.0009156512,"about_ca_topic_score_gemma":0.000028941236,"teacher_disagreement_score":0.24744624,"about_ca_system_score_codex":0.00024120853,"about_ca_system_score_gemma":0.00017171765,"threshold_uncertainty_score":0.94515437},"labels":[],"label_agreement":null},{"id":"W2949372305","doi":"10.1080/01621459.2019.1632078","title":"Model-Free Forward Screening Via Cumulative Divergence","year":2019,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institute on Drug Abuse; National Natural Science Foundation of China","keywords":"Divergence (linguistics); Mathematics; Statistics","score_opus":0.05327451455521445,"score_gpt":0.3651657928124792,"score_spread":0.3118912782572647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949372305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1097529,0.0000052872665,0.8882849,0.00073991995,0.00022938076,0.00011929771,0.000106589076,0.000010045693,0.0007516517],"genre_scores_gemma":[0.49219584,0.000004880638,0.5071394,0.0002337449,0.00006574232,0.0000013003686,5.0954714e-7,0.000012164598,0.00034642173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997641,0.00040187413,0.00063183333,0.00013423811,0.0009225932,0.00026842798],"domain_scores_gemma":[0.99214363,0.0051462203,0.0018757796,0.0002620408,0.0004608719,0.00011148008],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012588371,0.00013534985,0.0004952992,0.000048924034,0.00008850397,0.000035541554,0.00044951047,0.000041977095,0.000146017],"category_scores_gemma":[0.014837934,0.00008835458,0.00014853722,0.00026848167,0.00008998817,0.000115074385,0.0001559966,0.00039556902,0.000017874836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000557646,0.00039276376,0.18801153,0.00009446032,0.0007484119,0.000014650758,0.0010926188,0.0035613289,0.0031949854,0.6600427,0.036233824,0.10605506],"study_design_scores_gemma":[0.00039490865,0.00025552517,0.08277652,0.00004922675,0.00013665296,0.0000058845662,0.00008941212,0.13675722,0.00010018194,0.7791967,0.00009936632,0.00013843495],"about_ca_topic_score_codex":0.00003523006,"about_ca_topic_score_gemma":0.000004549442,"teacher_disagreement_score":0.38244292,"about_ca_system_score_codex":0.00027433882,"about_ca_system_score_gemma":0.00006850464,"threshold_uncertainty_score":0.9934605},"labels":[],"label_agreement":null},{"id":"W2952007299","doi":"10.1080/01621459.2021.1981913","title":"Saddlepoint Approximations for Spatial Panel Data Models","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Collegio Carlo Alberto; McGill University; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Estimator; Edgeworth series; Resampling; Mathematics; Applied mathematics; Gaussian; Econometrics; Monte Carlo method; Panel data; Dimension (graph theory); Cumulant; Series (stratigraphy); Covariate; Statistics","score_opus":0.10876502113985205,"score_gpt":0.280812262977202,"score_spread":0.17204724183734998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952007299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077156345,0.00011442833,0.98089856,0.0045694485,0.00033958413,0.00007386297,0.0056543914,0.0000044682365,0.00062961533],"genre_scores_gemma":[0.94957083,0.00012057078,0.04822118,0.00070101547,0.00041487883,0.0000048259635,0.00036213628,0.000014605954,0.000589952],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878484,0.00006359433,0.00070514844,0.00017441496,0.000115827665,0.00015616561],"domain_scores_gemma":[0.9969705,0.000554166,0.0018728393,0.0003452959,0.00019902477,0.00005819291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008386905,0.00007433165,0.00041193122,0.00005827945,0.00010793517,0.000082431456,0.00038304698,0.000029360932,0.00010432837],"category_scores_gemma":[0.0031787474,0.00006213429,0.00013489362,0.0002745705,0.000037642516,0.00020896964,0.00011271681,0.00014076816,0.00001978581],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027100384,0.0010818088,0.14890106,0.000089887944,0.002798432,0.000021415493,0.0008575226,0.0072801406,0.00028178407,0.6199427,0.12533636,0.09313785],"study_design_scores_gemma":[0.00087418687,0.00014335457,0.11789036,0.00001960556,0.00028200707,0.000018123335,0.00025444658,0.42180318,0.000062141895,0.41854957,0.03982842,0.00027460145],"about_ca_topic_score_codex":0.0005382806,"about_ca_topic_score_gemma":0.00016770598,"teacher_disagreement_score":0.9418552,"about_ca_system_score_codex":0.00019610359,"about_ca_system_score_gemma":0.000073669624,"threshold_uncertainty_score":0.38054872},"labels":[],"label_agreement":null},{"id":"W2952818057","doi":"10.1080/01621459.2019.1629939","title":"Estimating Optimal Dynamic Treatment Regimes With Survival Outcomes","year":2019,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Biostatistics; Epidemiology; Rheumatoid arthritis; Cohort; Medicine; Demography; Gerontology; Family medicine; Sociology; Internal medicine","score_opus":0.00713358345031154,"score_gpt":0.2992374305077353,"score_spread":0.29210384705742376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952818057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9895068,0.00006211965,0.005953654,0.003819853,0.00016141307,0.00015767395,0.00002096085,0.0000090099065,0.00030855773],"genre_scores_gemma":[0.96649206,0.00013186221,0.03205911,0.00010170755,0.00004285885,0.0000022351264,0.000003284279,0.0000137663465,0.0011531003],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985947,0.0001525203,0.00027882977,0.000085249514,0.0006783284,0.00021035277],"domain_scores_gemma":[0.9982284,0.0006791141,0.0006712396,0.00012345049,0.00019820896,0.000099615536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003202683,0.00009975999,0.00048063378,0.000050448085,0.00006221536,0.000037279206,0.00007961859,0.000017034132,0.00006160569],"category_scores_gemma":[0.00061393576,0.00004976867,0.0001053338,0.00013568772,0.0000826006,0.00007615162,0.00001588856,0.0001825361,0.00002199582],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068776676,0.00021881216,0.9612932,0.000010818151,0.00074549526,0.000034601268,0.0002474238,0.00034345916,0.0004309511,0.00044800586,0.0003835207,0.035155915],"study_design_scores_gemma":[0.0025676945,0.003159818,0.98675025,0.00011065721,0.000053216318,0.000099462115,0.00043448617,0.005722993,0.000060141392,0.00028292634,0.0006683126,0.00009003578],"about_ca_topic_score_codex":0.00007001017,"about_ca_topic_score_gemma":0.000012858639,"teacher_disagreement_score":0.03506588,"about_ca_system_score_codex":0.0005364355,"about_ca_system_score_gemma":0.0001751038,"threshold_uncertainty_score":0.20295075},"labels":[],"label_agreement":null},{"id":"W2963426032","doi":"10.1080/01621459.2018.1527700","title":"FarmTest: Factor-Adjusted Robust Multiple Testing With Approximate False Discovery Control","year":2018,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences","keywords":"False discovery rate; Multiple comparisons problem; Estimator; Computer science; Robust statistics; Covariance; Normality; Inference; Statistical hypothesis testing; Mathematics; Statistics; Data mining; Econometrics; Artificial intelligence","score_opus":0.2885035623946631,"score_gpt":0.44852181038620226,"score_spread":0.16001824799153913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963426032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16372335,0.000004993369,0.83393496,0.0008422009,0.0004787159,0.00033724846,0.00046011707,0.000037334117,0.00018107714],"genre_scores_gemma":[0.5211197,0.0000019978063,0.4779426,0.00029777296,0.0005240399,0.0000049064693,4.5486172e-7,0.00003102289,0.0000775369],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948978,0.0017351699,0.001415823,0.00025921958,0.0012102431,0.00048178685],"domain_scores_gemma":[0.89652896,0.09751185,0.0042958762,0.00031908945,0.0011577352,0.00018646341],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030725303,0.00026148435,0.0011066847,0.00007398003,0.00021447049,0.00015683234,0.000451622,0.00008911125,0.000046486402],"category_scores_gemma":[0.30191973,0.00015093367,0.0001705546,0.0006256381,0.00057705736,0.00021024467,0.000083042854,0.0006541316,0.000011260383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004531723,0.0017542888,0.8556944,0.00021636712,0.002337326,0.00010327835,0.0005952912,0.0003159852,0.005432007,0.03922273,0.011641115,0.07815549],"study_design_scores_gemma":[0.00629412,0.0034132185,0.54534626,0.0004202878,0.001363642,0.000082657025,0.00038873797,0.015443841,0.0009033973,0.42544082,0.00022008066,0.00068295613],"about_ca_topic_score_codex":0.00005367878,"about_ca_topic_score_gemma":0.000029168996,"teacher_disagreement_score":0.3862181,"about_ca_system_score_codex":0.00049913616,"about_ca_system_score_gemma":0.00018030823,"threshold_uncertainty_score":0.7039605},"labels":[],"label_agreement":null},{"id":"W2980548856","doi":"10.1080/01621459.2019.1677241","title":"Doubly Robust Inference With Nonprobability Survey Samples","year":2019,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":154,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Nonprobability sampling; Robustness (evolution); Statistics; Sample (material); Survey sampling; Population; Inference; Computer science; Variance (accounting); Statistical inference; Sampling (signal processing); Econometrics; Mathematics; Artificial intelligence","score_opus":0.060624572119190485,"score_gpt":0.3571311995777698,"score_spread":0.2965066274585793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980548856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27909988,0.000002535395,0.71965384,0.00044476436,0.00016060217,0.00014816568,0.00018564136,0.000009353686,0.0002952463],"genre_scores_gemma":[0.5573253,0.0000028632107,0.44241577,0.00011207573,0.00004598188,0.0000016923885,0.0000018488466,0.000011158617,0.00008327447],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997013,0.0011123812,0.0006177557,0.00016619767,0.0008171374,0.00027357793],"domain_scores_gemma":[0.98031044,0.016738484,0.0018298884,0.00026477734,0.0007447523,0.00011164902],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026152302,0.00015189989,0.00060252665,0.000040613337,0.00007228447,0.00007417497,0.00032838242,0.000043754222,0.00018023314],"category_scores_gemma":[0.021721998,0.00008496528,0.00008022584,0.00040750345,0.00016963633,0.000110534165,0.00005859608,0.00042481796,0.00001646599],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031485787,0.00017811917,0.8885725,0.000040670813,0.0001309878,0.0000033209806,0.00008710725,0.000038878155,0.00010341219,0.09642671,0.0023943994,0.011709052],"study_design_scores_gemma":[0.00032138874,0.00040088344,0.76553494,0.000047989946,0.00007124459,0.000007309991,0.00003872969,0.00030121405,0.00003879488,0.23304851,0.000073413576,0.00011555698],"about_ca_topic_score_codex":0.00026741758,"about_ca_topic_score_gemma":0.00015190884,"teacher_disagreement_score":0.27822545,"about_ca_system_score_codex":0.00035851263,"about_ca_system_score_gemma":0.00021280932,"threshold_uncertainty_score":0.98651844},"labels":[],"label_agreement":null},{"id":"W3008477519","doi":"10.1080/01621459.2021.1987250","title":"Model-Assisted Estimation Through Random Forests in Finite Population Sampling","year":2021,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Variance (accounting); Statistics; Random forest; Estimation; Point estimation; Computer science; Random effects model; Population; Sampling (signal processing); Simple random sample; Small area estimation; Calibration; Sampling design; Sample (material); Econometrics; Random variable; Confidence interval; Mathematics; Machine learning; Engineering","score_opus":0.0405564620954532,"score_gpt":0.3468353973952853,"score_spread":0.3062789352998321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008477519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031724077,0.00006207192,0.9655226,0.0017882726,0.0006349235,0.00017667685,0.000025660722,0.000015795653,0.000049928014],"genre_scores_gemma":[0.46863583,0.000028789887,0.53103113,0.00020316854,0.000060709117,0.000004255898,0.000012902417,0.000008505063,0.00001469242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659777,0.0010108593,0.001006652,0.00028942758,0.0008373059,0.00025801203],"domain_scores_gemma":[0.9942785,0.0016339293,0.0032741923,0.00036837166,0.00037943636,0.00006557548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017730356,0.00020482719,0.0007554308,0.00012387891,0.00009041172,0.0003134173,0.00064111396,0.00014666714,0.0000022726924],"category_scores_gemma":[0.003574891,0.0001566992,0.000244966,0.00047526814,0.000033034306,0.0003906409,0.00037510289,0.00096631795,6.037349e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012232657,0.00020956242,0.016345678,0.00008037684,0.00018246366,0.000023265191,0.0015364612,0.7238056,0.00010155814,0.01900444,0.00045069167,0.23813757],"study_design_scores_gemma":[0.00037312883,0.00002481078,0.15208063,0.00015975587,0.000053958873,0.000006668457,0.000007348732,0.6276478,0.000010282367,0.21951577,0.0000039589454,0.00011585352],"about_ca_topic_score_codex":0.00025650096,"about_ca_topic_score_gemma":0.00014176042,"teacher_disagreement_score":0.43691173,"about_ca_system_score_codex":0.0009807729,"about_ca_system_score_gemma":0.0003249598,"threshold_uncertainty_score":0.6390008},"labels":[],"label_agreement":null},{"id":"W3009292765","doi":"10.1080/01621459.2020.1730852","title":"Toward Optimal Fingerprinting in Detection and Attribution of Changes in Climate Extremes","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Climate variability and models","field":"Environmental Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"University of Connecticut; National Science Foundation","keywords":"Attribution; Independence (probability theory); Econometrics; Computer science; Climate model; Scale (ratio); Extreme value theory; Statistics; Climate change; Data mining; Mathematics; Psychology; Ecology; Geography; Social psychology","score_opus":0.02410547962109939,"score_gpt":0.25525035019212583,"score_spread":0.23114487057102645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009292765","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842298,0.000004607509,0.013081254,0.0025672426,0.000026749236,0.000051794144,0.000014142786,0.000001827651,0.000022559827],"genre_scores_gemma":[0.99763024,0.000055753637,0.0021750864,0.000117130854,0.00001720654,8.549257e-7,3.7526223e-7,0.0000024864107,8.8913464e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991836,0.00014776264,0.00027145652,0.00007484741,0.0002068942,0.00011542119],"domain_scores_gemma":[0.99912363,0.00026464448,0.0005375626,0.000028652039,0.000013647398,0.00003183759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071502494,0.000043529915,0.00017146647,0.000021641106,0.000021169419,0.000008879539,0.00005892455,0.000020330423,0.000026354708],"category_scores_gemma":[0.0009487767,0.000034054727,0.000021770184,0.00022302273,0.00006172506,0.000078594225,0.00007569915,0.00014155303,0.0000010992079],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001247524,0.000054915094,0.9301311,0.000018733934,0.000006577211,0.0000021019282,0.0012009259,0.0039854078,0.040958792,0.00007941418,0.000011192709,0.023426091],"study_design_scores_gemma":[0.00021327876,0.00013939473,0.9707199,0.000018527957,0.000012570564,0.0000018442269,0.00023615024,0.026896015,0.0013336024,0.0003528335,0.000036187117,0.000039729664],"about_ca_topic_score_codex":0.00021693253,"about_ca_topic_score_gemma":0.00021723239,"teacher_disagreement_score":0.04058877,"about_ca_system_score_codex":0.00029366618,"about_ca_system_score_gemma":0.000006086122,"threshold_uncertainty_score":0.13887115},"labels":[],"label_agreement":null},{"id":"W3010371357","doi":"10.1080/01621459.2020.1737079","title":"Targeted Inference Involving High-Dimensional Data Using Nuisance Penalized Regression","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute on Drug Abuse; National Human Genome Research Institute; National Institute of Mental Health; National Institutes of Health; National Science Foundation","keywords":"Nuisance parameter; Estimator; Inference; Statistic; Econometrics; Statistics; Nuisance; Mathematics; Computer science; Coherence (philosophical gambling strategy); Statistical inference; Regression; Regression analysis; Artificial intelligence","score_opus":0.16649957485134262,"score_gpt":0.4235532931007584,"score_spread":0.2570537182494158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010371357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27973524,0.000062512736,0.71546626,0.003724014,0.0003854544,0.00013926222,0.000425147,0.000022171089,0.000039915005],"genre_scores_gemma":[0.50207525,0.000013164003,0.49691674,0.00074389996,0.0002158314,5.7288986e-7,0.000006327506,0.000014654925,0.000013559391],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99675745,0.0009061289,0.0008203273,0.00022653956,0.0010228993,0.00026664874],"domain_scores_gemma":[0.98971,0.0066748085,0.0025931506,0.00031135516,0.0005065933,0.00020413716],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012267934,0.00016860983,0.0006250545,0.000035957095,0.00015669935,0.00006633112,0.0006527773,0.000050154427,0.00018326283],"category_scores_gemma":[0.06519603,0.00010543463,0.00007380166,0.00042322036,0.00014588676,0.00019171934,0.00034105853,0.0005300032,0.0000065192057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028476196,0.0012383517,0.09736938,0.0005085505,0.0016205515,0.00023572374,0.0023385428,0.0014419673,0.12632161,0.46545663,0.20217004,0.09845101],"study_design_scores_gemma":[0.0019822277,0.00073668896,0.09253471,0.0006105391,0.0007781693,0.00003458395,0.00029492175,0.37226626,0.0014964589,0.5279285,0.00068268756,0.00065431197],"about_ca_topic_score_codex":0.000100094585,"about_ca_topic_score_gemma":0.0000032686255,"teacher_disagreement_score":0.37082428,"about_ca_system_score_codex":0.00025905948,"about_ca_system_score_gemma":0.00023944535,"threshold_uncertainty_score":0.9426782},"labels":[],"label_agreement":null},{"id":"W3015403274","doi":"10.1080/01621459.2020.1753521","title":"Doubly Robust Estimation of Optimal Dosing Strategies","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; HEC Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Context (archaeology); Computer science; Dosing; Regression; Mathematical optimization; Extension (predicate logic); Estimation; Robust regression; Ordinary least squares; Focus (optics); Mathematics; Regression analysis; Machine learning; Statistics; Medicine","score_opus":0.07009081916655979,"score_gpt":0.3687500853026862,"score_spread":0.2986592661361264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015403274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.116725065,0.0000067320984,0.88043386,0.0022248852,0.000100158046,0.000052008803,0.000057918176,0.000008802239,0.00039057343],"genre_scores_gemma":[0.53878313,0.0000024408723,0.4609998,0.00012340979,0.00007190958,5.255765e-7,5.975163e-7,0.0000071170066,0.000011095474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980855,0.0003521629,0.0006991106,0.0000892161,0.00061554904,0.00015846276],"domain_scores_gemma":[0.99427813,0.0030560382,0.002136295,0.0000880657,0.0003441281,0.00009736761],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00071283354,0.00010204037,0.00045250097,0.00003895941,0.000057576886,0.00005485549,0.00020378288,0.000033195392,0.00007370301],"category_scores_gemma":[0.012082337,0.00006829491,0.000103862854,0.00036299558,0.00012757158,0.00012934812,0.000041917032,0.00027794577,0.000002509775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007694174,0.00041588285,0.0074937097,0.00026754348,0.0005487116,0.000019802354,0.0028043012,0.03315729,0.0047708503,0.72096205,0.026874369,0.2019161],"study_design_scores_gemma":[0.0016603755,0.0023912643,0.17235598,0.0002546188,0.00092260283,0.00003052548,0.0023167161,0.24962199,0.0023768707,0.567299,0.000277259,0.0004927753],"about_ca_topic_score_codex":0.000021146416,"about_ca_topic_score_gemma":9.76853e-7,"teacher_disagreement_score":0.42205805,"about_ca_system_score_codex":0.00013897012,"about_ca_system_score_gemma":0.00011752268,"threshold_uncertainty_score":0.9962393},"labels":[],"label_agreement":null},{"id":"W3021941172","doi":"10.1080/01621459.2020.1764365","title":"Spectral Inference under Complex Temporal Dynamics","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Statistical inference; Range (aeronautics); Computer science; Frequency domain; Nonlinear system; Spectral density; White noise; Statistical hypothesis testing; Mathematics; Algorithm; Mathematical optimization; Applied mathematics; Statistics; Artificial intelligence; Physics","score_opus":0.027531239290293157,"score_gpt":0.30928871737059793,"score_spread":0.28175747808030477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021941172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019903304,0.0000021700496,0.9298785,0.049772054,0.00007473805,0.000050772196,0.000014323605,0.000038743336,0.00026543275],"genre_scores_gemma":[0.8736153,0.0000035763564,0.12068193,0.0055713244,0.00007553823,5.160157e-7,0.0000023919704,0.000004774949,0.000044597917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99851966,0.000308823,0.0003705752,0.00010230076,0.0005536698,0.00014498715],"domain_scores_gemma":[0.9979258,0.00048145928,0.0011554561,0.00012117344,0.00021372159,0.00010238459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003910491,0.00008028595,0.00022688894,0.000034335495,0.00006404792,0.00015160655,0.00060816435,0.000023639792,0.000014888588],"category_scores_gemma":[0.00083912455,0.00005767335,0.00008055319,0.00042429983,0.000064807165,0.0002633211,0.00010925825,0.00031532245,0.000009655519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006157634,0.00016993702,0.06942963,0.000009328453,0.00015431286,0.000015074314,0.0016513655,0.001581805,0.0010386084,0.8469356,0.051509388,0.027443431],"study_design_scores_gemma":[0.00036521128,0.0005728532,0.663945,0.000012479626,0.00003496358,0.000012925707,0.0001918807,0.27256933,0.00021016077,0.059412215,0.0024570965,0.00021587202],"about_ca_topic_score_codex":0.00010387876,"about_ca_topic_score_gemma":0.00009038031,"teacher_disagreement_score":0.853712,"about_ca_system_score_codex":0.00042209562,"about_ca_system_score_gemma":0.00017232113,"threshold_uncertainty_score":0.23518509},"labels":[],"label_agreement":null},{"id":"W3023436065","doi":"10.1080/01621459.2023.2229486","title":"Frequency Detection and Change Point Estimation for Time Series of Complex Oscillation","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Series (stratigraphy); Change detection; Gaussian; Frequency domain; Algorithm; Time domain; Order of integration (calculus); Time series; Range (aeronautics); Point estimation; Computer science; Statistics; Artificial intelligence; Mathematical analysis","score_opus":0.03343209563960971,"score_gpt":0.25051244131670164,"score_spread":0.21708034567709195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023436065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7923858,0.00011758429,0.1996475,0.0056235795,0.00040143286,0.00044414803,0.001009909,0.000025440288,0.0003445669],"genre_scores_gemma":[0.99434537,0.00003321707,0.0052751065,0.000037961985,0.00010090497,0.0000060566867,0.000011395727,0.00000793644,0.00018208193],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991263,0.000038525264,0.0005740475,0.000081899816,0.000077405944,0.000101777296],"domain_scores_gemma":[0.997469,0.0002519042,0.0020422067,0.00006996547,0.00013903393,0.000027880385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007359761,0.000058555208,0.00035126248,0.00013933318,0.00008922282,0.000029050601,0.000059579506,0.000022332631,0.000040086572],"category_scores_gemma":[0.0008558931,0.000050455532,0.00009378128,0.00038685743,0.00004374233,0.00018309637,0.000019788986,0.000049815906,0.000013152441],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005902843,0.00027394804,0.53237593,0.00052370125,0.0020739068,0.0000038547337,0.005554608,0.002441978,0.015850576,0.27679104,0.013362527,0.15015763],"study_design_scores_gemma":[0.00024088769,0.00025713225,0.8479399,0.000013382134,0.00004506748,0.000003864982,0.00011106829,0.07361992,0.000036996018,0.076779984,0.00087329076,0.000078506],"about_ca_topic_score_codex":0.00034163124,"about_ca_topic_score_gemma":0.000039083097,"teacher_disagreement_score":0.31556395,"about_ca_system_score_codex":0.00016345097,"about_ca_system_score_gemma":0.000008084248,"threshold_uncertainty_score":0.20575169},"labels":[],"label_agreement":null},{"id":"W3027257009","doi":"10.1080/01621459.2020.1769636","title":"Smoothing Spline Semiparametric Density Models","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Probity Medical Research","funders":"Division of Mathematical Sciences; National Science Foundation","keywords":"Statistics; Mathematics; Econometrics; Smoothing; Spline (mechanical); Engineering","score_opus":0.08470072460900817,"score_gpt":0.3579781567261543,"score_spread":0.2732774321171461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027257009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13130791,0.000011457567,0.8635807,0.0044758576,0.00014572841,0.00007341224,0.000047823447,0.000014582138,0.00034253523],"genre_scores_gemma":[0.6093834,0.000011104842,0.3890619,0.0013193265,0.00018150185,6.5195843e-7,3.9570796e-7,0.00001144665,0.000030279863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977797,0.00048191738,0.0006445803,0.00012231627,0.0007526183,0.00021886601],"domain_scores_gemma":[0.9910528,0.0065393886,0.0016964264,0.00011842793,0.00040740694,0.00018556217],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010999726,0.00011801591,0.00051480805,0.00004263708,0.000088229004,0.00005057072,0.00026933555,0.00003993199,0.000043955548],"category_scores_gemma":[0.039921395,0.00007732183,0.00012747927,0.0005818986,0.00008224481,0.00009042652,0.000078735306,0.0005027148,0.000008012357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047458571,0.00043028544,0.03506234,0.00013345602,0.00055325415,0.000060083792,0.001554253,0.0007352245,0.002029283,0.77666926,0.06795593,0.11434205],"study_design_scores_gemma":[0.00040369504,0.00038399253,0.034626216,0.000037787442,0.0002680396,0.000014500643,0.00015531927,0.05528916,0.00030767845,0.9080682,0.00027091018,0.00017454],"about_ca_topic_score_codex":0.000025837382,"about_ca_topic_score_gemma":0.0000015976495,"teacher_disagreement_score":0.47807547,"about_ca_system_score_codex":0.00026033598,"about_ca_system_score_gemma":0.00008354642,"threshold_uncertainty_score":0.96816576},"labels":[],"label_agreement":null},{"id":"W3040900896","doi":"10.1080/01621459.2020.1787840","title":"Semiparametric Estimation of the Distribution of Episodically Consumed Foods Measured With Error","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"National Cancer Institute; Australian Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Nonparametric statistics; Estimation; Econometrics; Statistics; Parametric statistics; Computer science; Mathematics; Economics","score_opus":0.01874912685464795,"score_gpt":0.28348442103542615,"score_spread":0.2647352941807782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040900896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9252996,0.00011018223,0.045484204,0.028130919,0.000098529505,0.00035101638,0.00040365238,0.0000062884087,0.00011561281],"genre_scores_gemma":[0.99522305,0.000018048488,0.004262651,0.0004136746,0.00005414646,0.000002688513,0.000010557625,0.0000056648314,0.000009552626],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982297,0.0001708512,0.0004980536,0.000068203364,0.000926201,0.000107035055],"domain_scores_gemma":[0.9967239,0.0007252486,0.0017301645,0.00007813719,0.0006620452,0.00008053908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036500368,0.0000746568,0.00042573956,0.00002197409,0.000061499915,0.000005998809,0.00009991755,0.000027885555,0.000009818998],"category_scores_gemma":[0.0077656386,0.00003838967,0.00012992822,0.0006682638,0.0002223978,0.000032419328,0.000029697994,0.00021151442,7.58449e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006262228,0.0014125414,0.9004787,0.00045401775,0.0021025715,0.000012561141,0.0003997776,0.0019708,0.006687966,0.0055735763,0.050826713,0.02381853],"study_design_scores_gemma":[0.0012862501,0.0011749447,0.9929545,0.00012295666,0.0005304677,0.0000141252485,0.000140603,0.0018334239,0.0008097469,0.00073838327,0.0003446133,0.000049998962],"about_ca_topic_score_codex":0.00004840312,"about_ca_topic_score_gemma":0.000003465765,"teacher_disagreement_score":0.092475764,"about_ca_system_score_codex":0.00023325214,"about_ca_system_score_gemma":0.00014905183,"threshold_uncertainty_score":0.9296756},"labels":[],"label_agreement":null},{"id":"W3042683922","doi":"10.1080/01621459.2022.2096619","title":"Hypothesis Tests for Structured Rank Correlation Matrices","year":2022,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Rank (graph theory); Dimension (graph theory); Sample size determination; Mathematics; Statistical hypothesis testing; Partial correlation; Matrix (chemical analysis); Sample (material); Statistics; Covariance matrix; Design matrix; Correlation; Computer science; Algorithm; Linear model; Combinatorics","score_opus":0.009740699280160262,"score_gpt":0.24569690350529003,"score_spread":0.23595620422512975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042683922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81867266,0.000032471064,0.17467256,0.0035845756,0.0012438549,0.00042764284,0.0006537879,0.000016343358,0.00069607765],"genre_scores_gemma":[0.97274214,0.000006876803,0.026428549,0.0004373041,0.00007510685,0.000009319277,0.000004221191,0.000009434686,0.00028705818],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987089,0.00017429695,0.0002941512,0.000086711705,0.00058545655,0.00015047833],"domain_scores_gemma":[0.9969924,0.0015810477,0.0012736925,0.00007296057,0.00003571245,0.000044167926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006236731,0.00006416083,0.00016686646,0.000028316661,0.00028915203,0.000024204792,0.00019036415,0.000011684859,0.00031734],"category_scores_gemma":[0.0020109853,0.00004821988,0.000072123075,0.00026969903,0.000064636035,0.000059211376,0.00008532867,0.00015844338,0.0000062654944],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044918753,0.00020694116,0.465884,0.00001356695,0.00020065057,0.000008450784,0.00095126726,0.043575764,0.0039111404,0.0027691536,0.24078007,0.2412498],"study_design_scores_gemma":[0.00042487826,0.0002655413,0.95144165,0.000003077051,0.000115803516,0.00001476394,0.00030605134,0.008420671,0.000028108001,0.025699683,0.013179384,0.000100364865],"about_ca_topic_score_codex":0.00009953681,"about_ca_topic_score_gemma":0.000017557333,"teacher_disagreement_score":0.48555768,"about_ca_system_score_codex":0.0007513131,"about_ca_system_score_gemma":0.000025197072,"threshold_uncertainty_score":0.34746504},"labels":[],"label_agreement":null},{"id":"W3042834892","doi":"10.1080/01621459.2021.1999819","title":"A Likelihood-Based Approach for Multivariate Categorical Response Regression in High Dimensions","year":2021,"lang":"en","type":"preprint","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Genetics","funders":"National Science Foundation","keywords":"Categorical variable; Interpretability; Bivariate analysis; Multivariate statistics; Estimator; Statistics; Mathematics; Marginal model; Computer science; Regression; Regression analysis; Econometrics; Machine learning","score_opus":0.05687323109752065,"score_gpt":0.38662235740586276,"score_spread":0.32974912630834213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042834892","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16163823,0.000025340907,0.83535856,0.0016647789,0.0005161877,0.00042199064,0.00034440626,0.000012540184,0.000017980863],"genre_scores_gemma":[0.43988508,0.000008639132,0.55970526,0.00017904272,0.00011136489,0.000035094596,0.000017246346,0.00002753856,0.000030723935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99345624,0.003446799,0.0013460678,0.00036713498,0.00094322814,0.00044053857],"domain_scores_gemma":[0.97099435,0.024013026,0.0035349068,0.00039632994,0.00088180543,0.00017960487],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004562767,0.00031440723,0.0013259872,0.00017109848,0.0001169449,0.000110663386,0.00043739408,0.00024501065,0.000021410335],"category_scores_gemma":[0.07785749,0.00020298628,0.00034582813,0.00041121448,0.00012766174,0.00004135673,0.0002869523,0.0014624691,6.966761e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06170025,0.028177397,0.097033605,0.0053771576,0.0054285284,0.0010160793,0.008455932,0.022871908,0.031656533,0.44025302,0.11002849,0.18800111],"study_design_scores_gemma":[0.0027129923,0.000834862,0.18588069,0.00078825897,0.0008402116,0.00001645852,0.0005192957,0.106428325,0.00045744382,0.7007738,0.00010261739,0.0006450438],"about_ca_topic_score_codex":0.00023914721,"about_ca_topic_score_gemma":0.000012836202,"teacher_disagreement_score":0.27824685,"about_ca_system_score_codex":0.0013818465,"about_ca_system_score_gemma":0.00090235536,"threshold_uncertainty_score":0.9299101},"labels":[],"label_agreement":null},{"id":"W3107982686","doi":"10.1080/01621459.2020.1846975","title":"The Statistical Analysis of Multivariate Failure Time Data: A Marginal Modeling Approach.","year":2020,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multivariate statistics; Statistics; Marginal model; Multivariate analysis; Econometrics; Computer science; Mathematics; Regression analysis","score_opus":0.06808856179599139,"score_gpt":0.3688075242345694,"score_spread":0.30071896243857804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107982686","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036279787,0.000015965925,0.991863,0.0029434995,0.000057944424,0.00012568204,0.0012326364,0.000010228213,0.00012305375],"genre_scores_gemma":[0.2865867,0.000011776289,0.7130259,0.00018379338,0.00013077485,0.0000020624698,0.000021506497,0.000016576994,0.000020900343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607533,0.0011905275,0.0011137881,0.00023742505,0.0010729254,0.000309986],"domain_scores_gemma":[0.985642,0.011182808,0.00213436,0.0003870829,0.0004689431,0.00018477962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022753463,0.0001746184,0.0009224327,0.00006672787,0.00017796102,0.00009418836,0.00085007027,0.000052210915,0.000048623424],"category_scores_gemma":[0.030477446,0.00009683285,0.00021734771,0.0009907323,0.00023488689,0.00011540547,0.00022615003,0.000532808,0.0000043940577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010233574,0.00056210504,0.006141171,0.00012781122,0.009082226,0.00002494218,0.000978652,0.0016356059,0.0017922925,0.91293454,0.022123618,0.04357367],"study_design_scores_gemma":[0.00032944424,0.00019303775,0.009709877,0.00001859706,0.00354426,0.0000043255022,0.00028387667,0.8757849,0.0000094856305,0.10972075,0.0002577352,0.0001437566],"about_ca_topic_score_codex":0.00005978171,"about_ca_topic_score_gemma":0.000008381882,"teacher_disagreement_score":0.87414926,"about_ca_system_score_codex":0.00017890602,"about_ca_system_score_gemma":0.00015315435,"threshold_uncertainty_score":0.97768927},"labels":[],"label_agreement":null},{"id":"W3137656297","doi":"10.1080/01621459.2021.1904957","title":"Count Time Series: A Methodological Review","year":2021,"lang":"en","type":"review","venue":"Journal of the American Statistical Association","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Series (stratigraphy); Econometrics; Statistics; Mathematics; Computer science; Geology","score_opus":0.1278720754217726,"score_gpt":0.37032433502677814,"score_spread":0.24245225960500555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137656297","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032824782,0.97832394,0.019235035,0.0007974723,0.00042470376,0.0002127957,0.0006265498,0.000006437412,0.0003697817],"genre_scores_gemma":[0.0000021035282,0.98497075,0.013451446,0.00050997763,0.00029341993,0.000008197171,0.000022284612,0.000025660056,0.0007161645],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962744,0.0007749061,0.0022234356,0.00026009858,0.00019903103,0.00026813906],"domain_scores_gemma":[0.9896016,0.0019693791,0.007824087,0.00027679873,0.00024228606,0.000085826025],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00493571,0.0002447832,0.0040596644,0.00008663364,0.00009277142,0.00006204004,0.00042355873,0.00014412594,0.00028512286],"category_scores_gemma":[0.017647682,0.00017288822,0.0009965032,0.00060699123,0.00007800906,0.00010901422,0.00010587326,0.0008124568,0.00017201727],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017285012,0.00016821941,0.00042014205,0.007175907,0.0008384906,0.000029733343,0.000050497638,0.0000056130434,1.0129744e-7,0.034377918,0.06499716,0.89191896],"study_design_scores_gemma":[0.00005762936,0.000096642725,0.00022190985,0.0068528717,0.0004623988,0.00003734935,0.000003973621,0.000048953294,2.3540391e-8,0.006465508,0.98556006,0.00019269655],"about_ca_topic_score_codex":0.000033105116,"about_ca_topic_score_gemma":0.0000019403813,"teacher_disagreement_score":0.92056286,"about_ca_system_score_codex":0.0010761652,"about_ca_system_score_gemma":0.00027008104,"threshold_uncertainty_score":0.9906271},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3152330735","doi":"10.1080/01621459.2021.1909597","title":"Balancing Inferential Integrity and Disclosure Risk Via Model Targeted Masking and Multiple Imputation","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; University of Alberta","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Imputation (statistics); Inference; Risk model; Econometrics; Statistics; Missing data; Mathematics; Artificial intelligence; Machine learning","score_opus":0.010340287801239361,"score_gpt":0.2628697703301932,"score_spread":0.25252948252895385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152330735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2865448,0.00002997298,0.7076175,0.0055917874,0.00011136437,0.000028982813,0.00004985452,0.000021280292,0.0000044641924],"genre_scores_gemma":[0.6465213,0.000069421396,0.35330832,0.000065883716,0.000025963613,3.7994357e-7,0.0000026108728,0.00000347182,0.0000026539549],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986365,0.00030622748,0.0003236533,0.00017117242,0.00039597682,0.00016646518],"domain_scores_gemma":[0.997146,0.0010052514,0.0010348448,0.0005211033,0.00024604972,0.000046716705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000701657,0.000088815905,0.00022886576,0.000049117963,0.00014341933,0.00016426106,0.0013190289,0.00004852525,0.0000011005599],"category_scores_gemma":[0.049805943,0.000065713524,0.000037588758,0.00028131923,0.00008050392,0.0003875174,0.0049765552,0.00060087355,3.9806167e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005573973,0.00014389375,0.69201356,0.000033549077,0.00030076387,0.000031857686,0.00057691545,0.0027183096,0.0067658927,0.0030327963,0.014879158,0.27944756],"study_design_scores_gemma":[0.00018573194,0.00003296715,0.17562671,0.000014988728,0.000029767301,0.000016686145,0.0000357979,0.65763164,0.00041541716,0.16594334,0.000008364828,0.000058561443],"about_ca_topic_score_codex":0.00007533052,"about_ca_topic_score_gemma":0.00003297166,"teacher_disagreement_score":0.65491337,"about_ca_system_score_codex":0.0002146437,"about_ca_system_score_gemma":0.00009755035,"threshold_uncertainty_score":0.95819795},"labels":[],"label_agreement":null},{"id":"W3164525758","doi":"10.1080/01621459.2021.1933496","title":"A Dynamic Interaction Semiparametric Function-on-Scalar Model","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Bivariate analysis; Test statistic; Asymptotic distribution; Estimator; Mathematics; Covariate; Covariance; Statistic; Statistics; Econometrics; Statistical hypothesis testing","score_opus":0.037986541834068924,"score_gpt":0.3746728065920733,"score_spread":0.3366862647580044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164525758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09134919,0.000010841767,0.9058711,0.0013762623,0.00048309422,0.00005647176,0.000090671165,0.000011647856,0.0007507111],"genre_scores_gemma":[0.75214744,0.000019633688,0.24652259,0.0008315859,0.000069545145,0.0000026391997,0.0000015249631,0.000015832049,0.00038921443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997766,0.00057454733,0.00059173553,0.00014034742,0.00072262983,0.00020471452],"domain_scores_gemma":[0.9902997,0.0074335337,0.0013840037,0.00018443097,0.0006007272,0.00009761406],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00086846907,0.00012292337,0.00040707673,0.00008674648,0.00009887863,0.00005881245,0.0001487498,0.00004703447,0.000096375734],"category_scores_gemma":[0.025491582,0.000084143605,0.00015624177,0.00060768495,0.000059615137,0.00007311573,0.000034428347,0.00052917394,0.000016345504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010576112,0.0020301468,0.018302545,0.00012440878,0.0013883148,0.000081993196,0.000393513,0.008021795,0.004417026,0.6593004,0.073004335,0.2318779],"study_design_scores_gemma":[0.0005340594,0.00048206394,0.06674842,0.00008588854,0.00042076103,0.00004229127,0.00019060381,0.16068318,0.00019715197,0.7700439,0.00038525226,0.00018643489],"about_ca_topic_score_codex":0.000005275845,"about_ca_topic_score_gemma":0.000003993927,"teacher_disagreement_score":0.66079825,"about_ca_system_score_codex":0.00062177033,"about_ca_system_score_gemma":0.00015448015,"threshold_uncertainty_score":0.9827171},"labels":[],"label_agreement":null},{"id":"W3185747415","doi":"10.1080/01621459.2021.1996377","title":"Accelerating Bayesian Structure Learning in Sparse Gaussian Graphical Models","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Graphical model; Hyperparameter; Bottleneck; Algorithm; Computer science; Gaussian; Bayesian probability; Wishart distribution; Scalability; Graph; Laplace's method; Mathematics; Mathematical optimization; Artificial intelligence; Machine learning; Theoretical computer science","score_opus":0.014799831060358051,"score_gpt":0.27521854319626987,"score_spread":0.26041871213591183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185747415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029418651,0.0000360513,0.9649935,0.004958922,0.00023508811,0.000040707626,0.0000061682786,0.000011712705,0.000299252],"genre_scores_gemma":[0.59792346,0.000015749074,0.40144262,0.00047591387,0.00008325237,4.864991e-7,6.732962e-7,0.0000060977145,0.00005175734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972741,0.0011097491,0.0005286683,0.00019623594,0.0006036682,0.00028754945],"domain_scores_gemma":[0.9978233,0.00065113785,0.0009911228,0.0001888679,0.00023361934,0.00011194236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092541205,0.00012122345,0.00038683624,0.0000901149,0.00012248612,0.0001824132,0.000442098,0.000061160405,0.000011740345],"category_scores_gemma":[0.0013324923,0.00008659665,0.00011796034,0.0008409793,0.00004470219,0.00035618062,0.00013121055,0.00088295393,5.8270723e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004746036,0.00021506772,0.050312307,0.000020966623,0.00017395061,0.00033523387,0.0021773642,0.009960018,0.006806941,0.5906273,0.0017889544,0.33753443],"study_design_scores_gemma":[0.0005670617,0.00015296706,0.13325104,0.00007503299,0.000044035256,0.00014334865,0.00011321136,0.29233342,0.00063808315,0.5722239,0.00021013898,0.0002477623],"about_ca_topic_score_codex":0.000025605712,"about_ca_topic_score_gemma":0.000043073884,"teacher_disagreement_score":0.5685048,"about_ca_system_score_codex":0.00025673513,"about_ca_system_score_gemma":0.00023862654,"threshold_uncertainty_score":0.38360447},"labels":[],"label_agreement":null},{"id":"W3204441930","doi":"10.1080/01621459.2023.2216909","title":"An Automated Approach to Causal Inference in Discrete Settings","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; Office of Naval Research; University of Pennsylvania; York University; National Institutes of Health; National Science Foundation; Yale University; Carnegie Corporation of New York","keywords":"Causal inference; Computer science; Inference; Range (aeronautics); Algorithm; Causal model; Mathematical optimization; Mathematics; Artificial intelligence; Econometrics; Statistics","score_opus":0.055280762557961514,"score_gpt":0.44274617951837264,"score_spread":0.38746541696041115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204441930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6105485,0.0000011263064,0.38654736,0.001743182,0.000101334874,0.0002675848,0.00008411939,0.0003581121,0.00034868286],"genre_scores_gemma":[0.8750437,0.000004263555,0.12452716,0.00026449934,0.000054434688,0.000010707857,0.00000510313,0.000019146093,0.00007101691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99800235,0.0003877178,0.00057644845,0.00013492837,0.00059837935,0.00030016835],"domain_scores_gemma":[0.99611634,0.0023077058,0.0010510221,0.00018840104,0.00022237063,0.00011417412],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014412228,0.00012215176,0.0003943974,0.0001710378,0.000056804023,0.00004945776,0.0003366345,0.000044243152,0.0000053879107],"category_scores_gemma":[0.012434778,0.00008593606,0.00005074092,0.0010696794,0.00006145709,0.00019666179,0.000075515185,0.0003683943,0.000010581613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006222545,0.0017874946,0.28144467,0.00025039449,0.00046281065,0.000136457,0.010617008,0.0120061375,0.0391029,0.44006005,0.17564507,0.03786475],"study_design_scores_gemma":[0.00047163127,0.0008515734,0.47370815,0.00017004726,0.0000938455,0.000013743128,0.0013208893,0.06992278,0.0010005613,0.4517317,0.00029255432,0.00042249067],"about_ca_topic_score_codex":0.000057617395,"about_ca_topic_score_gemma":0.000018014762,"teacher_disagreement_score":0.26449516,"about_ca_system_score_codex":0.0005731118,"about_ca_system_score_gemma":0.000083064406,"threshold_uncertainty_score":0.9958839},"labels":[],"label_agreement":null},{"id":"W3206135247","doi":"10.1080/01621459.2021.1990766","title":"Evaluating Association Between Two Event Times with Observations Subject to Informative Censoring","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Statistical Sciences Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Censoring (clinical trials); Estimator; Copula (linguistics); Joint probability distribution; Bivariate analysis; Statistics; Marginal distribution; Inference; Econometrics; Event (particle physics); Conditional probability distribution; Mathematics; Marginal model; Computer science; Regression analysis; Artificial intelligence; Random variable","score_opus":0.11800942121791665,"score_gpt":0.4454183548606759,"score_spread":0.32740893364275925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206135247","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5372628,0.0000045710194,0.4589541,0.0028149772,0.0001619265,0.00016130903,0.00016783351,0.000015075484,0.0004574223],"genre_scores_gemma":[0.42854738,0.0000037415393,0.570426,0.00038764987,0.00020918071,0.0000069023595,0.0000047200906,0.000015925587,0.00039851925],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963447,0.0009998407,0.00086693524,0.00013454666,0.0013355082,0.00031851113],"domain_scores_gemma":[0.9826711,0.0128024295,0.0025275785,0.00017110136,0.0016842845,0.00014354962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027298091,0.00014989258,0.00055584346,0.00006400661,0.00019482842,0.0001052392,0.00019396278,0.000038692182,0.00006708684],"category_scores_gemma":[0.052973818,0.00010177301,0.00010605088,0.00073732407,0.000034551053,0.00016192964,0.00008132804,0.0004363616,0.000011613758],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020220653,0.00030008177,0.7926528,0.000079163096,0.0016178325,0.00001843449,0.003453863,0.0011737789,0.0017298092,0.10257161,0.010608863,0.08559156],"study_design_scores_gemma":[0.0007271981,0.000613537,0.8762589,0.0001983126,0.00060517684,0.000009865676,0.0007548632,0.0017261299,0.001222654,0.117355436,0.00029673698,0.00023117366],"about_ca_topic_score_codex":0.00004216779,"about_ca_topic_score_gemma":0.000025256584,"teacher_disagreement_score":0.11147187,"about_ca_system_score_codex":0.0014079062,"about_ca_system_score_gemma":0.00032952472,"threshold_uncertainty_score":0.9550034},"labels":[],"label_agreement":null},{"id":"W3215045347","doi":"10.1080/01621459.2024.2412363","title":"Robust Permutation Tests in Linear Instrumental Variables Regression","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"International Development and Aid","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"York University","keywords":"Heteroscedasticity; Resampling; Instrumental variable; Mathematics; Permutation (music); Conditional independence; Statistics; Linear regression; Orthogonality; Regression; Applied mathematics","score_opus":0.017323025769957683,"score_gpt":0.32598215876943903,"score_spread":0.30865913299948133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215045347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.960706,0.000069529306,0.0059403176,0.022689488,0.0029563669,0.00015354843,0.000042929874,0.000027219412,0.0074146017],"genre_scores_gemma":[0.9936521,0.00005528999,0.004640834,0.00013096043,0.00033880075,0.0000013434213,0.000004139998,0.0000056834765,0.0011708352],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99851996,0.0002662161,0.00030267955,0.000073439645,0.00069727754,0.00014044647],"domain_scores_gemma":[0.9987396,0.0006788953,0.00036996655,0.00002738765,0.00014391483,0.000040261024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00110384,0.000055705783,0.00012693855,0.00009985658,0.00012326172,0.00009113034,0.00014120179,0.000030394576,0.00008416791],"category_scores_gemma":[0.0017057344,0.000037288668,0.00004996069,0.00040901755,0.000078498604,0.0002402258,0.000021788554,0.00021997698,0.00001589924],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001796622,0.0002896608,0.57369196,0.000035815283,0.00022997854,0.00010370924,0.013454905,0.0009446207,0.0015631906,0.27287555,0.045726873,0.09090405],"study_design_scores_gemma":[0.0003875547,0.00012851032,0.9339192,0.00045078507,0.0000560696,0.000010480924,0.0027043747,0.005103233,0.0001138285,0.037898205,0.019038944,0.00018882619],"about_ca_topic_score_codex":0.0003470096,"about_ca_topic_score_gemma":0.00025953568,"teacher_disagreement_score":0.3602272,"about_ca_system_score_codex":0.001115,"about_ca_system_score_gemma":0.0003039458,"threshold_uncertainty_score":0.2915686},"labels":[],"label_agreement":null},{"id":"W4200343539","doi":"10.1080/01621459.2021.2011298","title":"Tukey’s Depth for Object Data","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences North","funders":"National Institute of Mental Health; National Institutes of Health; National Science Foundation","keywords":"Mathematics; Outlier; Metric (unit); Euclidean geometry; Metric space; Euclidean space; Data point; Algorithm; Artificial intelligence; Pattern recognition (psychology); Combinatorics; Computer science; Statistics; Geometry; Discrete mathematics","score_opus":0.1582213422149579,"score_gpt":0.475872776300752,"score_spread":0.3176514340857941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200343539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032643583,0.000031342082,0.99341136,0.0018642409,0.00034278832,0.00010473142,0.00068835047,0.000008071641,0.0002847323],"genre_scores_gemma":[0.061307497,0.000028499691,0.9373787,0.00047462858,0.0002721758,0.0000031980046,0.000014197492,0.000020570193,0.0005005196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981421,0.00041462656,0.0005518862,0.00016350587,0.00049580185,0.0002320398],"domain_scores_gemma":[0.98827416,0.009387567,0.0013173324,0.0003588646,0.00057061284,0.000091478236],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013613249,0.000101006604,0.0004509213,0.000022687866,0.00010311515,0.00004096631,0.00035269547,0.000031631596,0.00002245066],"category_scores_gemma":[0.045558583,0.000067896595,0.00010588832,0.00019253916,0.000065198576,0.00011673583,0.00013347127,0.00023997971,0.0000017182952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034199454,0.0005792387,0.004453995,0.00012478209,0.0007365305,0.000053192238,0.00026049,0.000081982624,0.0022346433,0.53227997,0.16888252,0.28997064],"study_design_scores_gemma":[0.0005796609,0.00017978076,0.009774181,0.000039291852,0.00037960836,0.00003560853,0.00019040791,0.0039788596,0.00040796518,0.9757234,0.008572535,0.00013873035],"about_ca_topic_score_codex":0.00000771315,"about_ca_topic_score_gemma":0.00003448085,"teacher_disagreement_score":0.4434434,"about_ca_system_score_codex":0.00024353313,"about_ca_system_score_gemma":0.00021287236,"threshold_uncertainty_score":0.9624811},"labels":[],"label_agreement":null},{"id":"W4220750582","doi":"10.1080/01621459.2022.2050243","title":"Sparse Reduced Rank Huber Regression in High Dimensions","year":2022,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Coordinate descent; Mathematics; Rate of convergence; Bounded function; Applied mathematics; Rank (graph theory); Moment (physics); Noise (video); Consistency (knowledge bases); Gaussian; Gaussian noise; Mathematical optimization; Algorithm; Computer science; Combinatorics; Mathematical analysis; Artificial intelligence; Discrete mathematics","score_opus":0.008938009588913798,"score_gpt":0.24666802707774935,"score_spread":0.23773001748883554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220750582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99502456,0.00004762757,0.0031421264,0.0009033614,0.00052600144,0.000067911984,0.000024551733,0.000041369865,0.00022251077],"genre_scores_gemma":[0.99538743,0.00003655528,0.0042449185,0.0001800496,0.00006746909,0.0000023164932,0.0000021187038,0.000014728894,0.00006443125],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9987766,0.00026662694,0.00031877198,0.00006339698,0.0004217863,0.00015279422],"domain_scores_gemma":[0.9990567,0.00032277819,0.0004043227,0.000114035654,0.00006412036,0.00003805012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036342745,0.00007832988,0.00024148794,0.00008919982,0.00009206087,0.000014693331,0.00015424716,0.000017286236,0.00004053011],"category_scores_gemma":[0.00031987965,0.000057473488,0.00006051734,0.0003244413,0.000027381968,0.00004834475,0.000067285946,0.00045100768,0.0000019090694],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005297475,0.00054284965,0.049055655,0.000015274049,0.00044006977,0.0002948224,0.0013296816,0.14495073,0.14310093,0.0050508115,0.6070946,0.047594868],"study_design_scores_gemma":[0.0020183607,0.0007723842,0.8740019,0.0002482442,0.00027540978,0.00017436572,0.00091854227,0.05027522,0.0145812435,0.04016351,0.015873399,0.00069736957],"about_ca_topic_score_codex":0.00006668201,"about_ca_topic_score_gemma":0.0000056285467,"teacher_disagreement_score":0.8249463,"about_ca_system_score_codex":0.00060418714,"about_ca_system_score_gemma":0.000028351127,"threshold_uncertainty_score":0.23437008},"labels":[],"label_agreement":null},{"id":"W4226071104","doi":"10.1080/01621459.2024.2402567","title":"Neyman-Pearson Multi-Class Classification via Cost-Sensitive Learning","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Oracle; Computer science; Class (philosophy); Consistency (knowledge bases); Binary number; Binary classification; Machine learning; Word error rate; Artificial intelligence; Algorithm; Mathematics; Support vector machine; Programming language","score_opus":0.020154951574805853,"score_gpt":0.31093661223476,"score_spread":0.29078166065995414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226071104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024072914,0.00002795655,0.9892517,0.007231723,0.00053874945,0.0001511148,0.000029605202,0.00014818324,0.00021368175],"genre_scores_gemma":[0.8980001,0.000064915825,0.10082045,0.00044812492,0.00015947939,0.000008878721,0.000009266878,0.000017257405,0.00047150513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760556,0.00061350095,0.00054607366,0.00024361105,0.0007394743,0.00025176228],"domain_scores_gemma":[0.99680305,0.0011378903,0.0012427171,0.0002730358,0.00045167608,0.000091614944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010816357,0.00013489231,0.00027537314,0.00015818898,0.00015331777,0.0003284083,0.0006173185,0.00005359784,0.0000057241505],"category_scores_gemma":[0.0018048609,0.00009966737,0.000118707336,0.0008102391,0.00010419916,0.00058763736,0.00011169492,0.00069228077,0.00006090787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050540286,0.00024519154,0.006132131,0.000038411566,0.00029100638,0.000057909416,0.0011651759,0.00025918602,0.05809845,0.101615466,0.040918175,0.79112834],"study_design_scores_gemma":[0.00028252852,0.00028088223,0.28838798,0.00010926335,0.00008561785,0.00008209271,0.00018765697,0.6729854,0.003779053,0.004441396,0.029104514,0.00027364574],"about_ca_topic_score_codex":0.000026233178,"about_ca_topic_score_gemma":0.0000040938585,"teacher_disagreement_score":0.8955928,"about_ca_system_score_codex":0.001081012,"about_ca_system_score_gemma":0.00016865684,"threshold_uncertainty_score":0.40643173},"labels":[],"label_agreement":null},{"id":"W4233304560","doi":"10.1080/01621459.2000.10474343","title":"Likelihood","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Statistics","score_opus":0.023939375856940337,"score_gpt":0.3492266467615187,"score_spread":0.3252872709045784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233304560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65827525,0.000026111182,0.32549927,0.0050308583,0.0005235221,0.00016949933,0.000151161,0.000029874956,0.010294452],"genre_scores_gemma":[0.57951504,0.00003763733,0.4182207,0.0008420973,0.0003117181,0.0000019542097,4.7132846e-7,0.000017733817,0.0010526093],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981966,0.00043451414,0.0005039133,0.00007641937,0.0005719209,0.00021664934],"domain_scores_gemma":[0.9947745,0.003896451,0.00089115684,0.0001300965,0.00020891085,0.00009887847],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010020748,0.000087857654,0.00033840968,0.000025717014,0.00007499932,0.00003499716,0.00022095712,0.000027782704,0.0009299946],"category_scores_gemma":[0.00869853,0.000053203596,0.00010465253,0.0002342662,0.000086563254,0.000047123398,0.000018689523,0.00029121086,0.000037753653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016471517,0.00030957712,0.01845473,0.000018340295,0.00019353307,0.000014777679,0.0002318534,0.000006100877,0.00034227842,0.13498954,0.073927544,0.771347],"study_design_scores_gemma":[0.00029903423,0.00029718282,0.15506072,0.000032134227,0.00014063201,0.00002176731,0.00005928924,0.00034411324,0.00011123278,0.8388102,0.0047134175,0.000110235436],"about_ca_topic_score_codex":0.000021817561,"about_ca_topic_score_gemma":0.0000032487503,"teacher_disagreement_score":0.7712368,"about_ca_system_score_codex":0.00021593276,"about_ca_system_score_gemma":0.00006829009,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W4238912906","doi":"10.1198/016214507000000707","title":"Comment","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mathematics","score_opus":0.009353454888913783,"score_gpt":0.30791781412790636,"score_spread":0.2985643592389926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238912906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75022817,0.00003290787,0.21266793,0.031912573,0.0011927393,0.00021659586,0.00022020529,0.000040477997,0.0034883919],"genre_scores_gemma":[0.9837855,0.0000036148099,0.013008367,0.0028015552,0.00025729745,3.3520206e-7,0.0000013981743,0.000020612813,0.00012131478],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9977768,0.0002979157,0.000570759,0.00006562076,0.0010093974,0.00027949066],"domain_scores_gemma":[0.9950613,0.0017521249,0.002584901,0.00012004055,0.000361403,0.00012022571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003458053,0.00008402864,0.00027349766,0.000074481315,0.00009155387,0.000032558328,0.00024316234,0.000021135096,0.000052087988],"category_scores_gemma":[0.00371169,0.00005416552,0.000113721624,0.0004341405,0.00010108875,0.00008078632,0.00004246968,0.00033894408,0.00015798463],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054001354,0.00045468955,0.39688846,0.000005024804,0.0003940828,0.000037733946,0.00037046018,0.00005523817,0.00568811,0.017493775,0.5427887,0.035283715],"study_design_scores_gemma":[0.00046421643,0.0002471924,0.94922554,0.000013659589,0.00012147893,0.000023995703,0.00025941155,0.00009789821,0.00060246314,0.004783704,0.044066884,0.0000935776],"about_ca_topic_score_codex":0.000049481718,"about_ca_topic_score_gemma":0.000021254651,"teacher_disagreement_score":0.55233705,"about_ca_system_score_codex":0.0016542401,"about_ca_system_score_gemma":0.00006137492,"threshold_uncertainty_score":0.44435078},"labels":[],"label_agreement":null},{"id":"W4246704690","doi":"10.1198/016214506000000690","title":"Comment","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics","score_opus":0.0059446759291786,"score_gpt":0.26829845960969545,"score_spread":0.26235378368051687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246704690","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86723757,0.000055143097,0.059262536,0.06595351,0.0010641563,0.00026845306,0.00057537796,0.000056977893,0.005526264],"genre_scores_gemma":[0.9894425,0.0000023203797,0.008543679,0.0014061187,0.00032706786,9.931837e-7,0.0000034556067,0.000020781134,0.00025306773],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9978921,0.00043339768,0.0005051621,0.00006575647,0.0008896054,0.00021397394],"domain_scores_gemma":[0.9961759,0.00088618096,0.002466388,0.00011307336,0.00030280324,0.000055660596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00102699,0.0000846185,0.00027610903,0.00005414535,0.00009098896,0.0000466053,0.00021730403,0.00001791666,0.000053344378],"category_scores_gemma":[0.0013484891,0.00005449451,0.00011588219,0.0003512432,0.00009485312,0.000081411024,0.000036146164,0.00025936635,0.0001617534],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009792353,0.00026079538,0.19979325,0.0000022588151,0.000103327424,0.000008473553,0.00003602781,0.00020328273,0.0022882265,0.016849615,0.777414,0.0029428035],"study_design_scores_gemma":[0.0004784415,0.00017029185,0.93123543,0.000012143134,0.00013293156,0.000017037313,0.00006459487,0.00033872918,0.0003089318,0.017742353,0.049403746,0.000095397045],"about_ca_topic_score_codex":0.00023951106,"about_ca_topic_score_gemma":0.000025658988,"teacher_disagreement_score":0.73144215,"about_ca_system_score_codex":0.0013392146,"about_ca_system_score_gemma":0.0000630765,"threshold_uncertainty_score":0.35019997},"labels":[],"label_agreement":null},{"id":"W4250194478","doi":"10.1080/01621459.2016.1240080","title":"Comment","year":2016,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Pharmacogenetics and Drug Metabolism","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Mathematics","score_opus":0.058158899861969975,"score_gpt":0.43457833319639233,"score_spread":0.37641943333442235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250194478","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8382328,0.00021643103,0.020445483,0.13470875,0.0039270516,0.00018403168,0.0003338545,0.00001821482,0.0019333848],"genre_scores_gemma":[0.9867638,0.00032291326,0.0011236606,0.01083975,0.0004287409,0.0000021726773,4.7207502e-7,0.000009360084,0.00050914055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982231,0.00075398386,0.0003896058,0.00007378592,0.00033233812,0.0002271386],"domain_scores_gemma":[0.99690104,0.0015720342,0.0010895967,0.00008264332,0.00020578569,0.00014891158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012538276,0.00008614049,0.00023981486,0.00003877699,0.00009972396,0.000010645609,0.00025450697,0.000042940923,0.00035782304],"category_scores_gemma":[0.0010652303,0.00004331532,0.00010866953,0.00014026907,0.00013116328,0.00004825098,0.00005565312,0.00031001744,0.000055573215],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046947724,0.00041581,0.15250131,0.0000061059804,0.0005981445,0.000018564808,0.00019651424,0.000040380324,0.09172417,0.010879302,0.3251309,0.41801932],"study_design_scores_gemma":[0.0015871227,0.00015536399,0.14483073,0.000011632385,0.000312558,0.000017166685,0.0000344964,0.00012404937,0.0143831745,0.008045811,0.8303736,0.00012432614],"about_ca_topic_score_codex":0.0000052319024,"about_ca_topic_score_gemma":0.0000011729376,"teacher_disagreement_score":0.50524265,"about_ca_system_score_codex":0.00027035867,"about_ca_system_score_gemma":0.00006940029,"threshold_uncertainty_score":0.39179114},"labels":[],"label_agreement":null},{"id":"W4250271509","doi":"10.1198/jasa.2009.0103","title":"Order Selection in Finite Mixture Models With a Nonsmooth Penalty","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Akaike information criterion; Bayesian information criterion; Mathematics; Information Criteria; Mixing (physics); Mixture model; Scad; Model selection; Maximization; Bayesian probability; Expectation–maximization algorithm; Penalty method; Applied mathematics; Selection (genetic algorithm); Mathematical optimization; Absolute deviation; Statistics; Computer science; Maximum likelihood; Artificial intelligence","score_opus":0.007316331187808707,"score_gpt":0.25892188898643553,"score_spread":0.2516055577986268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250271509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063628894,0.000017162905,0.9876482,0.0054538203,0.000061823914,0.00007088217,0.000003921729,0.00000984555,0.00037149087],"genre_scores_gemma":[0.45933685,0.000011698373,0.5394054,0.001112397,0.00005146861,7.533857e-7,2.191824e-7,0.0000035798953,0.00007761125],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842256,0.0004026199,0.00032163702,0.00013452345,0.00050394767,0.00021470235],"domain_scores_gemma":[0.99822867,0.0004442845,0.00085177046,0.00010766529,0.0002983102,0.00006927654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008240052,0.00010126534,0.0002797084,0.00009348903,0.000065465705,0.00008182316,0.00034153348,0.000036549296,0.0000030446122],"category_scores_gemma":[0.0004486999,0.000060069207,0.000051954125,0.0009405711,0.000027141654,0.00034332395,0.000023259541,0.00040921473,0.0000010822143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005029418,0.00078270334,0.015254035,0.0000140214925,0.00018325602,0.00007529279,0.002134491,0.024377855,0.0014936646,0.34476697,0.012967977,0.5974468],"study_design_scores_gemma":[0.000929564,0.0011235795,0.1927182,0.00007177554,0.000057884503,0.00008397724,0.00002150471,0.37114176,0.00012953555,0.4331303,0.0003425321,0.00024938877],"about_ca_topic_score_codex":0.000033686087,"about_ca_topic_score_gemma":0.000031049458,"teacher_disagreement_score":0.5971974,"about_ca_system_score_codex":0.00029979652,"about_ca_system_score_gemma":0.00017511258,"threshold_uncertainty_score":0.24495511},"labels":[],"label_agreement":null},{"id":"W4253164021","doi":"10.1198/016214505000000691","title":"Rejoinder","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics","score_opus":0.2224096634831433,"score_gpt":0.47857288979036566,"score_spread":0.2561632263072223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253164021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65215784,0.000080612714,0.3108186,0.029641207,0.0012636026,0.00007238794,0.000023853652,0.0000132428595,0.0059286444],"genre_scores_gemma":[0.8923314,0.000010384606,0.10487566,0.001252179,0.00043779708,3.160873e-7,9.467879e-8,0.000004304201,0.0010878155],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99634826,0.00088284456,0.0007714445,0.0001051017,0.0017163244,0.00017602603],"domain_scores_gemma":[0.9596091,0.036451634,0.003086058,0.0001992118,0.0005740754,0.0000799349],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008251292,0.000060823066,0.00031252857,0.0001467007,0.00009787393,0.000106619205,0.00055450917,0.000022934766,0.00016352179],"category_scores_gemma":[0.26105127,0.000031056938,0.00012953817,0.0012756009,0.000071591865,0.00013972621,0.000066337896,0.0002619401,0.000051903757],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034281336,0.000047785587,0.30494168,4.1581438e-7,0.00003811775,0.000002201624,0.00009758853,0.00024496266,0.00018207265,0.0015929819,0.14562348,0.5471944],"study_design_scores_gemma":[0.00017272843,0.000097205964,0.9236294,0.00000430492,0.000021011845,0.000018687077,0.0002249694,0.00081326487,0.000047184945,0.036981236,0.037938405,0.00005156942],"about_ca_topic_score_codex":0.000011834767,"about_ca_topic_score_gemma":0.000004029623,"teacher_disagreement_score":0.61868775,"about_ca_system_score_codex":0.00027102776,"about_ca_system_score_gemma":0.0000633029,"threshold_uncertainty_score":0.7451732},"labels":[],"label_agreement":null},{"id":"W4253389928","doi":"10.2307/2669463","title":"Bayesian Regression Modeling with Interactions and Smooth Effects","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Bayesian linear regression; Interpretation (philosophy); Bayesian probability; Computation; Machine learning; Regression; Artificial intelligence; Bivariate analysis; Model selection; Regression analysis; Gaussian process; Bayesian inference; Algorithm; Gaussian; Mathematics; Statistics","score_opus":0.004437693998908057,"score_gpt":0.24336192438036883,"score_spread":0.23892423038146077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253389928","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08657524,0.000018294611,0.91019195,0.002769935,0.000071729744,0.000038856226,0.0000019979504,0.000009853411,0.00032214884],"genre_scores_gemma":[0.93125504,0.00003441272,0.06826221,0.0002901222,0.000048356353,7.245624e-7,1.7463469e-7,0.0000042898337,0.00010466925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909365,0.000120281875,0.00021223439,0.00010451453,0.00033149988,0.0001377914],"domain_scores_gemma":[0.9989003,0.00032158053,0.000473025,0.00011273637,0.00011530768,0.00007703203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019001648,0.00007834307,0.0001801167,0.000039205086,0.00012711954,0.00013406183,0.00024425553,0.000014342278,0.000012491291],"category_scores_gemma":[0.00017594559,0.000042368203,0.000030711726,0.00026746248,0.0000391609,0.00032534776,0.00003148191,0.00022019554,0.0000026922266],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001577664,0.00017691513,0.015285047,0.000043323394,0.00012826188,0.000044875436,0.0010123651,0.0020070854,0.00035788387,0.019740103,0.0019353904,0.959111],"study_design_scores_gemma":[0.0008918386,0.0010342567,0.14319444,0.00051484513,0.0001327865,0.0002445631,0.00012864752,0.8030062,0.00021051863,0.04941647,0.00089564495,0.00032983458],"about_ca_topic_score_codex":0.000027072701,"about_ca_topic_score_gemma":0.000007786934,"teacher_disagreement_score":0.9587811,"about_ca_system_score_codex":0.00010922708,"about_ca_system_score_gemma":0.00006583137,"threshold_uncertainty_score":0.17277253},"labels":[],"label_agreement":null},{"id":"W4295631026","doi":"10.1080/01621459.2022.2097086","title":"Comments on “Measuring Housing Vitality from Multi-Source Big Data and Machine Learning”","year":2022,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Vitality; Big data; Computer science; Psychology; Data science; Statistics; Econometrics; Mathematics; Data mining; Philosophy","score_opus":0.08603744249388633,"score_gpt":0.3284766530567009,"score_spread":0.24243921056281453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295631026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93629056,0.000046727157,0.05650628,0.006296939,0.00024782057,0.00008674953,0.00041750094,0.000014564546,0.000092832044],"genre_scores_gemma":[0.9983495,0.000021386924,0.00060514966,0.0006310679,0.0001786382,0.0000010794315,0.000029781308,0.000006244672,0.0001771531],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964956,0.0020679,0.00029222766,0.00013625668,0.0008637199,0.00014430106],"domain_scores_gemma":[0.9970745,0.0016125801,0.000981771,0.00015962278,0.00009390832,0.0000776298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025327858,0.00006231158,0.00020960254,0.000047142454,0.0012032688,0.00008405397,0.00036524283,0.0000151598715,0.000068807174],"category_scores_gemma":[0.004351007,0.000051702646,0.000048650083,0.0002694719,0.00014776678,0.000071875635,0.00017381085,0.00046106934,0.0000018082637],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009790339,0.00038407271,0.79707706,0.0000035984108,0.00024547265,0.0000034039376,0.004602894,0.0026796437,0.00013028963,0.00014167599,0.0011289276,0.19350505],"study_design_scores_gemma":[0.0010161931,0.00030391148,0.87742764,0.000031399144,0.00045039217,9.5229444e-7,0.013968529,0.053313397,0.00001854127,0.0016104357,0.05158915,0.00026945083],"about_ca_topic_score_codex":0.017215155,"about_ca_topic_score_gemma":0.003380706,"teacher_disagreement_score":0.19323559,"about_ca_system_score_codex":0.00075253705,"about_ca_system_score_gemma":0.00011126988,"threshold_uncertainty_score":0.9893293},"labels":[],"label_agreement":null},{"id":"W4361205542","doi":"10.1080/01621459.2023.2195976","title":"Feature Screening with Conditional Rank Utility for Big-Data Classification","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Categorical variable; Cru; Estimator; Feature (linguistics); Computer science; Outlier; Rank (graph theory); Data mining; Constructive; Artificial intelligence; Statistics; Mathematics; Machine learning","score_opus":0.2304884306171918,"score_gpt":0.42377583046024586,"score_spread":0.19328739984305407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361205542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009823595,0.0000038932358,0.97970784,0.008093997,0.00025346366,0.00019450995,0.0018121495,0.000023534636,0.00008699831],"genre_scores_gemma":[0.41124904,0.000009523772,0.58736795,0.00030167704,0.00060220633,0.000012429731,0.00014070424,0.000023015766,0.0002934612],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9981394,0.0003773391,0.00038146542,0.00016800656,0.0007057192,0.00022809375],"domain_scores_gemma":[0.98737466,0.010308386,0.0013946715,0.0002752557,0.0005630475,0.00008396435],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002232626,0.00011003937,0.0003631227,0.00006062666,0.00016870299,0.00005464591,0.0003620544,0.000045500692,0.00001314801],"category_scores_gemma":[0.022075627,0.0000670974,0.00006915527,0.00047525586,0.00014861155,0.00008886629,0.00006543544,0.00029825568,0.00000401456],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009225874,0.00022136752,0.042506192,0.00011254472,0.0005800296,0.000009592752,0.00015938221,0.000021246573,0.0005975679,0.21464829,0.47430113,0.26592007],"study_design_scores_gemma":[0.0006587173,0.00025675748,0.58552074,0.000052059626,0.0002475597,0.000010784248,0.0002414231,0.018511761,0.000031831543,0.38863537,0.005710291,0.00012269778],"about_ca_topic_score_codex":0.0000072185626,"about_ca_topic_score_gemma":0.000008476321,"teacher_disagreement_score":0.5430145,"about_ca_system_score_codex":0.00012755542,"about_ca_system_score_gemma":0.00013084794,"threshold_uncertainty_score":0.9861618},"labels":[],"label_agreement":null},{"id":"W4386134063","doi":"10.1080/01621459.2023.2250098","title":"Spectral Clustering, Bayesian Spanning Forest, and Forest Process","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Eisai; National Institute on Aging; Alzheimer's Association","keywords":"Cluster analysis; Bayesian probability; Environmental science; Forestry; Mathematics; Statistics; Geography","score_opus":0.011162884816843674,"score_gpt":0.2962793568059756,"score_spread":0.2851164719891319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386134063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07732817,0.000011575019,0.9188895,0.0033305609,0.00021852215,0.00005711364,0.0000048278043,0.000025041621,0.00013467677],"genre_scores_gemma":[0.7851144,0.000017273935,0.21424825,0.00030446684,0.00015896586,0.0000015732847,4.537801e-7,0.000008214076,0.00014637358],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99867064,0.00019643636,0.0003057711,0.00013270898,0.00043639351,0.00025802603],"domain_scores_gemma":[0.99830014,0.0005885115,0.00075847487,0.00012846653,0.00012045744,0.00010395417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009628969,0.000092357914,0.00024798,0.00008391087,0.00011958868,0.00013278714,0.00037584864,0.000027342994,0.0000016523501],"category_scores_gemma":[0.00093608804,0.000062582156,0.000063357686,0.0005194022,0.00005751153,0.00022449536,0.0001107821,0.0002424948,0.0000024900028],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010717441,0.00012286747,0.54834664,0.000091132075,0.00028578183,0.0001564964,0.0035733923,0.003421571,0.0006104187,0.12860398,0.015634041,0.2990465],"study_design_scores_gemma":[0.0002267268,0.00018608569,0.58796895,0.00003447762,0.000030004014,0.000050324856,0.00004966079,0.26718402,0.000021424923,0.14396974,0.00016873084,0.00010989533],"about_ca_topic_score_codex":0.000021162496,"about_ca_topic_score_gemma":0.000028790239,"teacher_disagreement_score":0.70778626,"about_ca_system_score_codex":0.00011937737,"about_ca_system_score_gemma":0.00007246349,"threshold_uncertainty_score":0.25520262},"labels":[],"label_agreement":null},{"id":"W4386475977","doi":"10.1080/01621459.2023.2235059","title":"Poisson-FOCuS: An Efficient Online Method for Detecting Count Bursts with Application to Gamma Ray Burst Detection","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Gamma-ray bursts and supernovae","field":"Physics and Astronomy","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Institut sur la Nutrition et les Aliments Fonctionnels","keywords":"Poisson distribution; Focus (optics); Sliding window protocol; Fermi Gamma-ray Space Telescope; Computer science; Grid; Window (computing); Photon; Energy (signal processing); Algorithm; Detector; Gamma-ray burst; Real-time computing; Physics; Optics; Mathematics; Telecommunications; Astrophysics; Statistics","score_opus":0.009220726744286882,"score_gpt":0.2962169181157131,"score_spread":0.28699619137142623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386475977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47428676,0.0000012979119,0.52437097,0.0009318671,0.000078169105,0.00018731598,0.00012337082,0.000012714208,0.000007523612],"genre_scores_gemma":[0.951239,6.312713e-7,0.047955498,0.00009719826,0.00056362856,0.000028621267,0.000021146892,0.000026539272,0.000067718895],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99842846,0.00016742048,0.00041225256,0.00018921314,0.0005005542,0.00030211871],"domain_scores_gemma":[0.9976568,0.0007001453,0.0008738655,0.0001537507,0.00047978328,0.0001356216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010704326,0.00013975725,0.00032071315,0.00010541494,0.00022162897,0.00007035642,0.00018486731,0.000026081108,0.0000067184396],"category_scores_gemma":[0.00023010833,0.00009440888,0.00010282497,0.0006313956,0.00003331357,0.00007481259,0.000027113387,0.00021942229,0.0000073911947],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062450045,0.00045272429,0.1144407,0.000017865716,0.00037864907,0.0000023511072,0.0012819453,0.045237496,0.022634435,0.0008159535,0.0007178145,0.81339556],"study_design_scores_gemma":[0.0013186513,0.0015919742,0.87159705,0.000055653425,0.00034241326,0.0000066694342,0.0030810523,0.11235384,0.0036467155,0.0021438561,0.0034904059,0.00037173554],"about_ca_topic_score_codex":0.00053907227,"about_ca_topic_score_gemma":0.00007896242,"teacher_disagreement_score":0.8130238,"about_ca_system_score_codex":0.00034601876,"about_ca_system_score_gemma":0.000072963965,"threshold_uncertainty_score":0.38498825},"labels":[],"label_agreement":null},{"id":"W4387060245","doi":"10.1080/01621459.2023.2241701","title":"Inference in High-Dimensional Multivariate Response Regression with Hidden Variables","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Stroke Foundation","keywords":"Estimator; Mathematics; Multivariate statistics; Statistics; Multivariate normal distribution; Inference; Confidence interval; Applied mathematics; Computer science; Artificial intelligence","score_opus":0.04014729081793959,"score_gpt":0.3773256889766591,"score_spread":0.3371783981587195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387060245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86790645,0.0000032239616,0.12919907,0.0023863204,0.00021165119,0.00012345194,0.0001022574,0.00002363625,0.00004395107],"genre_scores_gemma":[0.744055,0.000005602936,0.25554836,0.00012669779,0.000056650504,0.0000037379334,0.0000017265378,0.000014952047,0.00018731569],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99658203,0.0015191814,0.00061435293,0.00014780866,0.0008450393,0.0002915571],"domain_scores_gemma":[0.97191226,0.02614189,0.0013640018,0.00016842934,0.00031768787,0.00009574222],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031459483,0.00014163538,0.00048979267,0.00014697341,0.00008966257,0.000039089595,0.00022774946,0.000051351253,0.000058609796],"category_scores_gemma":[0.051826034,0.00007773498,0.000050143786,0.0008640362,0.000121070814,0.00008241927,0.000087213724,0.00043433078,0.000009851733],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014032936,0.0011479096,0.26443067,0.00013427895,0.00059767807,0.0005697822,0.001847494,0.0016827483,0.023464238,0.5629615,0.031228188,0.09790252],"study_design_scores_gemma":[0.000864805,0.0004332786,0.6440336,0.0002532712,0.00006716869,0.000008856651,0.00011026103,0.00904148,0.00018273052,0.3448122,0.00005112449,0.00014117929],"about_ca_topic_score_codex":0.0001531697,"about_ca_topic_score_gemma":0.000022585173,"teacher_disagreement_score":0.37960297,"about_ca_system_score_codex":0.00036196882,"about_ca_system_score_gemma":0.00027222678,"threshold_uncertainty_score":0.95616084},"labels":[],"label_agreement":null},{"id":"W4387311761","doi":"10.1080/01621459.2023.2263202","title":"Copula Modeling of Serially Correlated Multivariate Data with Hidden Structures","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Computer science; Multivariate statistics; Hidden Markov model; Inference; Section (typography); Algorithm; Theoretical computer science; Econometrics; Data mining; Mathematics; Artificial intelligence; Machine learning","score_opus":0.02901518291234277,"score_gpt":0.3159927258049126,"score_spread":0.2869775428925698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387311761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030158337,0.000008686422,0.96806824,0.0012645975,0.00030541382,0.00006395401,0.00007253201,0.000018272383,0.000039948358],"genre_scores_gemma":[0.5444258,0.000009609165,0.45538002,0.00008243674,0.000056220848,3.1316918e-7,0.000004856598,0.0000064703977,0.000034304714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982216,0.00041868407,0.0004344982,0.00015340639,0.00059271575,0.00017911293],"domain_scores_gemma":[0.99736446,0.00057124044,0.0013194769,0.0003854435,0.00029579742,0.00006355683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011982303,0.000091485366,0.00033519504,0.00007054922,0.00006892316,0.000058752794,0.0009930877,0.000033668803,0.0000029323028],"category_scores_gemma":[0.0011086568,0.000054083637,0.000042995936,0.00062708766,0.000045007306,0.00024664126,0.00025723787,0.0002428372,0.0000016102027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012971214,0.00039856473,0.020010697,0.000112463254,0.0024418207,0.00019556869,0.004919397,0.05738173,0.018479815,0.32216507,0.030711487,0.54188627],"study_design_scores_gemma":[0.0004044937,0.000158552,0.0272799,0.00003412926,0.000077468525,0.000016382042,0.000031650015,0.91995037,0.00005178812,0.051862344,0.000041336098,0.00009157001],"about_ca_topic_score_codex":0.00013346804,"about_ca_topic_score_gemma":0.000008521875,"teacher_disagreement_score":0.8625687,"about_ca_system_score_codex":0.00009216281,"about_ca_system_score_gemma":0.00016786484,"threshold_uncertainty_score":0.22054666},"labels":[],"label_agreement":null},{"id":"W4388752511","doi":"10.1080/01621459.2023.2284980","title":"Bootstrap Inference in the Presence of Bias","year":2023,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Core Research for Evolutional Science and Technology; Natural Sciences and Engineering Research Council of Canada; Universitat de les Illes Balears; Universidade Federal do Rio Grande do Sul; Danmarks Grundforskningsfond; University of Oxford; Singapore Management University; York University; Aarhus Universitet; International Association for Applied Econometrics; University of Pittsburgh; National Research Foundation; Queen Mary University of London","keywords":"Inference; Econometrics; Statistics; Mathematics; Computer science; Artificial intelligence","score_opus":0.1636894013790908,"score_gpt":0.44276080036904814,"score_spread":0.27907139898995736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388752511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81266755,0.000011824274,0.18146206,0.0042646388,0.00031893523,0.00022499479,0.00015083673,0.00001431819,0.0008848669],"genre_scores_gemma":[0.9636686,0.0000320589,0.0360106,0.000150963,0.000057501846,0.000003530656,5.605964e-7,0.00000668814,0.000069526206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99710584,0.0011116408,0.0006733571,0.000079133984,0.0008233278,0.0002067065],"domain_scores_gemma":[0.9628835,0.035199333,0.0014602742,0.00017367252,0.00024383774,0.00003938814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034140323,0.000085186766,0.000364478,0.000077747995,0.00004618365,0.000027908254,0.00043324247,0.000029646058,0.000029339977],"category_scores_gemma":[0.08269988,0.00004455015,0.00008389399,0.0008790696,0.00016937016,0.00005218184,0.0000537112,0.00035532287,0.000006213578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013539365,0.00036608233,0.22918397,0.00010387742,0.00013136362,0.000035764842,0.00272717,0.00014725585,0.0010734333,0.6741281,0.028320983,0.06364661],"study_design_scores_gemma":[0.00015455093,0.0001823676,0.5214156,0.00006108877,0.000042647393,0.0000032235985,0.0005416982,0.0016513919,0.00009143272,0.4756531,0.00014745093,0.000055440036],"about_ca_topic_score_codex":0.00007560913,"about_ca_topic_score_gemma":0.000018737592,"teacher_disagreement_score":0.29223162,"about_ca_system_score_codex":0.00009437642,"about_ca_system_score_gemma":0.00009646613,"threshold_uncertainty_score":0.92502695},"labels":[],"label_agreement":null},{"id":"W4393221521","doi":"10.1080/01621459.2024.2335587","title":"Automatic Regenerative Simulation via Non-Reversible Simulated Tempering","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Probabilistic logic; Algorithm; Metric (unit); Mathematical optimization; Variance (accounting); Bounded function; Set (abstract data type); Mathematics; Artificial intelligence","score_opus":0.027965387621884726,"score_gpt":0.37520948006736343,"score_spread":0.3472440924454787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393221521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4611863,0.000039456565,0.53696173,0.0007056551,0.0006287851,0.00015099479,0.000023309796,0.00003755811,0.00026622653],"genre_scores_gemma":[0.941597,0.000007918645,0.057267983,0.00011306409,0.00026239597,0.0000013191025,0.0000015047231,0.000024244395,0.0007246043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808645,0.0004485813,0.0005867402,0.00012228884,0.00055992213,0.00019604225],"domain_scores_gemma":[0.994156,0.0044592503,0.0008748882,0.00014103734,0.00029218406,0.000076615484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014938622,0.00013357839,0.00040001734,0.0001033516,0.000107234126,0.00009424909,0.00015321428,0.00004968281,0.000035267465],"category_scores_gemma":[0.0038439748,0.00008806406,0.00017887975,0.00046533512,0.000049253016,0.00015105952,0.000044579476,0.00033527237,8.276581e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053204305,0.0010000766,0.015024657,0.0015885666,0.005381219,0.0003715295,0.014977134,0.12362099,0.07063765,0.039941844,0.117917515,0.60900676],"study_design_scores_gemma":[0.00028970555,0.00020779151,0.0024956416,0.00020969598,0.0003169327,0.000013308722,0.00021419702,0.97930884,0.0009572898,0.014672479,0.0011489912,0.00016511073],"about_ca_topic_score_codex":0.00002248359,"about_ca_topic_score_gemma":0.0000064184123,"teacher_disagreement_score":0.85568786,"about_ca_system_score_codex":0.00079405715,"about_ca_system_score_gemma":0.00010086597,"threshold_uncertainty_score":0.46018746},"labels":[],"label_agreement":null},{"id":"W4394840601","doi":"10.1080/01621459.2024.2343459","title":"Introduction to Environmental Data Science","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Environmental science","score_opus":0.00881834497256143,"score_gpt":0.28544221004177694,"score_spread":0.2766238650692155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394840601","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02016577,0.000029360433,0.9416473,0.036660884,0.0012197654,0.0000498199,0.00014689931,0.000018834022,0.00006134938],"genre_scores_gemma":[0.9081995,0.000019149187,0.090031475,0.0006328991,0.00089410576,6.209334e-7,0.000007753326,0.000005649843,0.00020884804],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9981329,0.00011331915,0.00028374183,0.00025382888,0.0010452374,0.00017096005],"domain_scores_gemma":[0.9986478,0.00026818967,0.00035504886,0.000572964,0.000057455323,0.000098526914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001938174,0.00005994152,0.00014439346,0.00014904846,0.00010511638,0.00038727067,0.001901348,0.000008373675,0.000020363705],"category_scores_gemma":[0.0016776582,0.000039202965,0.000034895198,0.001198716,0.000119585005,0.0012871857,0.000642278,0.00018238195,0.00010785207],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019663807,0.00013699246,0.006570642,0.000007074074,0.00021444008,0.000028497705,0.00044965214,0.00038318237,0.021272931,0.03538629,0.5301369,0.40539375],"study_design_scores_gemma":[0.00021921958,0.00058094074,0.46088836,0.000050536903,0.00032749993,0.00018148955,0.00021646715,0.23305202,0.0016978295,0.00801398,0.29436207,0.00040960262],"about_ca_topic_score_codex":0.000017845894,"about_ca_topic_score_gemma":0.000002984911,"teacher_disagreement_score":0.88803375,"about_ca_system_score_codex":0.00073871017,"about_ca_system_score_gemma":0.00016696459,"threshold_uncertainty_score":0.373446},"labels":[],"label_agreement":null},{"id":"W4396860058","doi":"10.1080/01621459.2024.2353948","title":"Generalized Data Thinning Using Sufficient Statistics","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; W. M. Keck Foundation; National Institutes of Health; National Science Foundation","keywords":"Generalization; Random variable; Mathematics; Thinning; Inference; Sum of normally distributed random variables; Set (abstract data type); Variables; Sample (material); Exponential function; Statistics; Variable (mathematics); Function (biology); Exponential family; Applied mathematics; Computer science; Marginal distribution; Artificial intelligence; Mathematical analysis","score_opus":0.14891054081528926,"score_gpt":0.44730948182901004,"score_spread":0.2983989410137208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396860058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060128383,0.000084656254,0.9367835,0.00068171433,0.000948253,0.00008521189,0.0011606555,0.000023198209,0.000104450366],"genre_scores_gemma":[0.123139516,0.000029181281,0.87605447,0.0002378792,0.00035582166,7.6262063e-7,0.000008330636,0.000028185399,0.00014584576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971169,0.0006646211,0.0008083351,0.0001966008,0.00092894916,0.00028459396],"domain_scores_gemma":[0.99027663,0.007867134,0.0010664536,0.00034901692,0.00033160913,0.00010917505],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025773149,0.00014591674,0.00046235466,0.000078893405,0.0001253478,0.00019388914,0.00053877203,0.000039524006,0.000113563176],"category_scores_gemma":[0.020016974,0.00009232076,0.00007449397,0.00044136986,0.00013875432,0.00012394977,0.00020343397,0.0004891546,0.000008188504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006879647,0.00016325201,0.002895618,0.00011908347,0.0004183818,0.000082399885,0.00045111883,0.00012642077,0.0014016535,0.8486188,0.09989749,0.045757003],"study_design_scores_gemma":[0.0003262037,0.00025196487,0.010614686,0.0002661361,0.0008459438,0.00008751143,0.00024532323,0.3574569,0.000109298024,0.6252235,0.004282659,0.00028984912],"about_ca_topic_score_codex":0.0000734427,"about_ca_topic_score_gemma":0.000005501627,"teacher_disagreement_score":0.35733047,"about_ca_system_score_codex":0.00048702213,"about_ca_system_score_gemma":0.00028166454,"threshold_uncertainty_score":0.98823786},"labels":[],"label_agreement":null},{"id":"W4401569379","doi":"10.1080/01621459.2024.2388908","title":"Parallel Sampling of Decomposable Graphs Using Markov Chains on Junction Trees","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Graphical model; Markov chain Monte Carlo; Computer science; Approximate inference; Markov chain; Inference; Theoretical computer science; Graph partition; Algorithm; Mathematics; Graph; Bayesian probability; Artificial intelligence; Machine learning","score_opus":0.0304337309115025,"score_gpt":0.31434852024946586,"score_spread":0.2839147893379634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401569379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09170571,0.00004536145,0.90654135,0.001025399,0.0005260567,0.000031830117,0.000008703411,0.000016649114,0.00009893666],"genre_scores_gemma":[0.86055684,0.000032119686,0.13913393,0.00014919302,0.00007293501,5.022296e-7,4.8690686e-7,0.000005819781,0.000048189642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986549,0.0001838088,0.0003934481,0.00012234086,0.0004867688,0.00015871509],"domain_scores_gemma":[0.9983117,0.00071073376,0.0006283506,0.00012877413,0.00016668055,0.0000537664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007089284,0.000084840365,0.00023154817,0.000113586604,0.000079233265,0.00011299386,0.0002997134,0.00002761199,0.000004251112],"category_scores_gemma":[0.00033979426,0.000058088564,0.000116827556,0.00047661213,0.000046597397,0.00017689902,0.000043219083,0.00025418188,0.0000027814845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020927991,0.0004026435,0.013392106,0.00008295297,0.0005968984,0.00002614973,0.001058716,0.06402916,0.013040199,0.5271576,0.0064691147,0.3735352],"study_design_scores_gemma":[0.0001993312,0.00046054524,0.04441149,0.00025527575,0.00009078032,0.00002829555,0.000059677575,0.8814008,0.0003098119,0.072409816,0.00022010083,0.00015405909],"about_ca_topic_score_codex":0.00007083508,"about_ca_topic_score_gemma":0.000005714375,"teacher_disagreement_score":0.81737167,"about_ca_system_score_codex":0.00025545523,"about_ca_system_score_gemma":0.00012420087,"threshold_uncertainty_score":0.23687829},"labels":[],"label_agreement":null},{"id":"W4405183266","doi":"10.1080/01621459.2024.2436686","title":"Deconvolution Density Estimation with Penalized MLE","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Deconvolution; Estimation; Statistics; Mathematics; Econometrics; Density estimation; Maximum likelihood; Applied mathematics; Estimator; Economics","score_opus":0.005328146860555236,"score_gpt":0.23147859690342615,"score_spread":0.2261504500428709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405183266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60666627,0.0001390309,0.38482252,0.0064768,0.000584463,0.00009531358,0.00005849063,0.000065814755,0.001091318],"genre_scores_gemma":[0.976032,0.000021260274,0.022988155,0.00066387036,0.00007005211,1.2854284e-7,0.0000071203563,0.0000021444284,0.00021526897],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99913454,0.00014130273,0.00018377729,0.000066648754,0.0003685015,0.00010520812],"domain_scores_gemma":[0.9990363,0.00043511964,0.00033432824,0.00005065579,0.00010089303,0.00004271247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054344296,0.000054625085,0.0001309169,0.000053585154,0.00008183759,0.00007785482,0.000090954854,0.000015409534,0.00020395516],"category_scores_gemma":[0.00035898527,0.000030414285,0.000045665143,0.00022721665,0.00007003841,0.00018180176,0.00000433745,0.00017242033,0.000035299672],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025621857,0.000024328701,0.25246468,0.000024743542,0.00015061276,0.000029915398,0.0002186096,0.0011200189,0.00008305419,0.00068954594,0.101217054,0.6437212],"study_design_scores_gemma":[0.00020040383,0.0003527671,0.6485824,0.0000892369,0.00013773644,0.0001036755,0.00010704611,0.33076793,0.0002846298,0.011301958,0.007963616,0.00010858617],"about_ca_topic_score_codex":0.00090348173,"about_ca_topic_score_gemma":0.000027542144,"teacher_disagreement_score":0.6436126,"about_ca_system_score_codex":0.00007510363,"about_ca_system_score_gemma":0.00008812305,"threshold_uncertainty_score":0.22331661},"labels":[],"label_agreement":null},{"id":"W4405638481","doi":"10.1080/01621459.2024.2443275","title":"A Bias-Accuracy-Privacy Trilemma for Statistical Estimation","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Trilemma; Estimation; Econometrics; Computer science; Statistics; Mathematics; Economics","score_opus":0.03496055933458475,"score_gpt":0.3349503274301001,"score_spread":0.29998976809551536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405638481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004415441,0.00005557276,0.9275081,0.06630172,0.0009786944,0.000192668,0.00035806256,0.00014735362,0.000042347656],"genre_scores_gemma":[0.28602877,0.000033485016,0.71337306,0.0003368298,0.00014971434,0.000011944776,0.000011093865,0.00001533163,0.00003979557],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99754214,0.00028183678,0.00072016957,0.0002715949,0.00083358714,0.0003506768],"domain_scores_gemma":[0.9869796,0.009963177,0.0011573238,0.0014964301,0.0003067971,0.00009664318],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.0017736497,0.00015665546,0.00037681486,0.00016695121,0.00013994773,0.0004736745,0.0073993662,0.00006365779,0.00001414302],"category_scores_gemma":[0.22196072,0.00010841382,0.00014171508,0.00078947685,0.00013402298,0.00068482757,0.0050845547,0.000460028,0.00002377378],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037065656,0.000060121478,0.0005498008,0.00003949081,0.00012951884,0.00001974758,0.00006988024,0.00004786883,0.00020663433,0.056927923,0.61320865,0.3287033],"study_design_scores_gemma":[0.00023129098,0.00028024797,0.009977418,0.00006763503,0.00007241028,0.000039965867,0.000020203364,0.4762196,0.00023153402,0.5014035,0.011321106,0.00013509208],"about_ca_topic_score_codex":0.000024690056,"about_ca_topic_score_gemma":0.000002332617,"teacher_disagreement_score":0.6018875,"about_ca_system_score_codex":0.00080267305,"about_ca_system_score_gemma":0.0003386037,"threshold_uncertainty_score":0.99797106},"labels":[],"label_agreement":null},{"id":"W4405638577","doi":"10.1080/01621459.2024.2441657","title":"Estimation and Inference for Nonparametric Expected Shortfall Regression over RKHS","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Inference; Econometrics; Nonparametric statistics; Statistics; Nonparametric regression; Regression; Mathematics; Statistical inference; Expected shortfall; Computer science; Economics; Artificial intelligence; Risk management","score_opus":0.040626783703733925,"score_gpt":0.42015741260273526,"score_spread":0.37953062889900135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405638577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15063703,0.000074907955,0.847945,0.0006466989,0.0003298583,0.00015589036,0.000099878285,0.000019973466,0.00009078947],"genre_scores_gemma":[0.6267909,0.00003337955,0.37288097,0.00008016732,0.000099452904,0.000006885747,0.0000017097065,0.000012917032,0.000093623974],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838024,0.00025974406,0.0005403922,0.00014113754,0.00049312186,0.00018536265],"domain_scores_gemma":[0.9828565,0.015968157,0.0007287966,0.00010568877,0.00025337358,0.00008747893],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010355812,0.00012342338,0.0003726483,0.000118283,0.00008584936,0.00013192993,0.00012745828,0.00005002093,0.00003350715],"category_scores_gemma":[0.035130877,0.00007340773,0.00008699029,0.000460383,0.000092564944,0.00011336897,0.00004123664,0.00027674343,0.0000019261167],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015752333,0.0001299508,0.007989236,0.00020002165,0.00020510024,0.000009425019,0.00039732046,0.000020526266,0.0008827173,0.3550537,0.021540305,0.61341417],"study_design_scores_gemma":[0.0003074721,0.0004763361,0.087383986,0.00029573217,0.00029890746,0.000015699878,0.00007900507,0.13086472,0.0001959683,0.77936757,0.0005494719,0.00016510046],"about_ca_topic_score_codex":0.000015487101,"about_ca_topic_score_gemma":0.0000027612007,"teacher_disagreement_score":0.61324906,"about_ca_system_score_codex":0.00027022546,"about_ca_system_score_gemma":0.0000949363,"threshold_uncertainty_score":0.97299665},"labels":[],"label_agreement":null},{"id":"W4406100263","doi":"10.1080/01621459.2024.2448857","title":"Inferences in Multinomial Dynamic Mixed Logit Models","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixed logit; Econometrics; Multinomial logistic regression; Multinomial distribution; Statistics; Multinomial probit; Logistic regression; Mathematics","score_opus":0.0429779171084795,"score_gpt":0.24796878532931507,"score_spread":0.20499086822083556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406100263","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94157183,0.00007493953,0.053829934,0.0018651065,0.0004079229,0.00006802134,0.00006451099,0.0000026159723,0.002115123],"genre_scores_gemma":[0.99694425,0.00008859123,0.0023122455,0.0002733793,0.0000218517,0.0000024426795,0.0000025620936,0.0000039,0.0003507693],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990374,0.000059439404,0.00063326716,0.00009821113,0.000047174683,0.00012452285],"domain_scores_gemma":[0.99839985,0.00028408208,0.0012019343,0.000074380594,0.000017444445,0.000022309561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007314443,0.00006268793,0.00029917076,0.00010994656,0.0000392165,0.000028505052,0.00015344204,0.00003305476,0.000040488183],"category_scores_gemma":[0.00054636324,0.0000550548,0.00006953182,0.00015625062,0.000055582976,0.00014855436,0.00003741177,0.00016743675,0.000029181907],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028724136,0.000085888634,0.9357709,0.000004103121,0.000057722867,6.3002693e-7,0.00010942025,0.006490079,0.000019595294,0.048868205,0.0009975034,0.007567189],"study_design_scores_gemma":[0.0003395609,0.000034989414,0.83327144,0.000009301687,0.000008522227,4.036916e-7,0.00009148145,0.03608636,0.0000059120853,0.12993257,0.0001689465,0.000050524268],"about_ca_topic_score_codex":0.00021621246,"about_ca_topic_score_gemma":0.00008884921,"teacher_disagreement_score":0.10249951,"about_ca_system_score_codex":0.0009949681,"about_ca_system_score_gemma":0.000030540155,"threshold_uncertainty_score":0.2601807},"labels":[],"label_agreement":null},{"id":"W4406112031","doi":"10.1080/01621459.2024.2443246","title":"Robust Inference for Federated Meta-Learning","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences North","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Stroke Foundation; U.S. National Library of Medicine; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Inference; Computer science; Machine learning; Generalizability theory; Matching (statistics); Data mining; Statistical inference; Model selection; Artificial intelligence; Parametric statistics; Selection (genetic algorithm); Statistics; Mathematics","score_opus":0.10699018924991914,"score_gpt":0.4092920222758023,"score_spread":0.30230183302588315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406112031","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008146489,0.000019618044,0.9883529,0.0022644291,0.00024988136,0.00014401466,0.00005569068,0.000013404609,0.0007535919],"genre_scores_gemma":[0.40143102,0.000014680159,0.5964952,0.00056886714,0.000083568746,0.000015229964,0.0000014231576,0.000012549323,0.0013774744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806255,0.00061284204,0.000629985,0.00011032763,0.0003685602,0.00021574965],"domain_scores_gemma":[0.97932553,0.018328538,0.0014500134,0.00009114012,0.0007466121,0.000058178655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001403161,0.000120469864,0.00062719436,0.000060941962,0.00019496729,0.00008820716,0.00019914968,0.00004168551,0.00006737635],"category_scores_gemma":[0.075066395,0.000072728166,0.0002040987,0.00035607722,0.00008328389,0.000051147083,0.000046013156,0.0003781235,0.0000018189284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002603722,0.0002454272,0.0111769885,0.00010306145,0.0028408426,0.0000033634785,0.0001457108,0.0003228858,0.00075148995,0.8822001,0.04030611,0.061643604],"study_design_scores_gemma":[0.0006057549,0.00042865454,0.040286902,0.00006720357,0.0027368562,0.0000031434183,0.00020268178,0.011898531,0.0003750843,0.9399938,0.0032290134,0.00017237615],"about_ca_topic_score_codex":0.000021884349,"about_ca_topic_score_gemma":0.000006977703,"teacher_disagreement_score":0.39328453,"about_ca_system_score_codex":0.00026289572,"about_ca_system_score_gemma":0.00016176484,"threshold_uncertainty_score":0.9327247},"labels":[],"label_agreement":null},{"id":"W4407903965","doi":"10.1080/01621459.2025.2468011","title":"Class-Specific Joint Feature Screening in Ultrahigh-Dimensional Mixture Regression","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Key Research and Development Program of China","keywords":"Feature (linguistics); Class (philosophy); Regression; Joint (building); Artificial intelligence; Pattern recognition (psychology); Computer science; Statistics; Mathematics; Engineering","score_opus":0.011068565266198049,"score_gpt":0.28065491987849067,"score_spread":0.26958635461229263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407903965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007263701,0.00019345914,0.9704194,0.021074768,0.0006146323,0.0000759144,0.000009354789,0.0000112853795,0.00033749777],"genre_scores_gemma":[0.23136975,0.0000450915,0.765837,0.0019098378,0.00013760025,0.0000016036239,0.0000013348266,0.00000690653,0.00069088815],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978052,0.0006870312,0.00045293692,0.00019258757,0.00061894656,0.0002432961],"domain_scores_gemma":[0.99761605,0.00083913136,0.0010018479,0.00022999808,0.00024090517,0.0000720495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013227223,0.00013165516,0.0003984827,0.00016607638,0.00011381806,0.00009977778,0.00049289584,0.00007933523,0.0000048945158],"category_scores_gemma":[0.0008020011,0.00008009526,0.0001364434,0.0008333107,0.00005752523,0.00019241807,0.00012294122,0.0007615979,0.000001568344],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019166563,0.0002477097,0.016703706,0.00001968143,0.00015813397,0.00008512614,0.00039247796,0.00040636203,0.010297746,0.2089557,0.29014102,0.47240067],"study_design_scores_gemma":[0.0012963847,0.00020718106,0.81555337,0.00057540624,0.000057458907,0.00005771376,0.000050658826,0.020105299,0.0017878262,0.14452614,0.0154737355,0.00030884566],"about_ca_topic_score_codex":0.000014218967,"about_ca_topic_score_gemma":0.0000057931993,"teacher_disagreement_score":0.79884964,"about_ca_system_score_codex":0.0003040243,"about_ca_system_score_gemma":0.00013341982,"threshold_uncertainty_score":0.3308806},"labels":[],"label_agreement":null},{"id":"W4408398943","doi":"10.1080/01621459.2025.2476221","title":"An Economical Approach to Design Posterior Analyses","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.10904751526756334,"score_gpt":0.30698393245458944,"score_spread":0.1979364171870261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408398943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5851357,0.00004515774,0.4111132,0.0013955877,0.00023426536,0.00011555681,0.000067620465,0.0000044754584,0.0018884006],"genre_scores_gemma":[0.96446794,0.000015452159,0.033745427,0.0013787155,0.000073265786,0.0000044958547,0.0000034586315,0.000007753978,0.0003034935],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988845,0.00011280083,0.0006546941,0.00015267674,0.000047891663,0.00014744823],"domain_scores_gemma":[0.9984658,0.0002161845,0.0010662521,0.0001506414,0.000025526737,0.00007561117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009983071,0.00008267929,0.0003797735,0.0001263354,0.0000727314,0.00006796862,0.00024655234,0.00003219499,0.000051130082],"category_scores_gemma":[0.00045145213,0.00007176962,0.00009759854,0.0001745095,0.000044869408,0.00015870578,0.000035261226,0.00012622902,0.0000798041],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021402513,0.0005999128,0.8864085,0.000011563489,0.00052771036,8.499057e-7,0.0004045338,0.024458751,0.0010585462,0.05644775,0.016178565,0.013689297],"study_design_scores_gemma":[0.00026849797,0.00018167254,0.9752313,0.000005233873,0.00004073162,0.0000021303595,0.00012812273,0.0075464947,0.000119809774,0.015438429,0.0009385457,0.000099048666],"about_ca_topic_score_codex":0.00005510311,"about_ca_topic_score_gemma":0.0000020258676,"teacher_disagreement_score":0.3793322,"about_ca_system_score_codex":0.00088685745,"about_ca_system_score_gemma":0.000031482028,"threshold_uncertainty_score":0.29266798},"labels":[],"label_agreement":null},{"id":"W4408404791","doi":"10.1080/01621459.2025.2474266","title":"Positive and Unlabeled Data: Model, Estimation, Inference, and Classification","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Inference; Estimation; Artificial intelligence; Computer science; Statistics; Econometrics; Mathematics; Pattern recognition (psychology); Machine learning; Data mining; Economics","score_opus":0.01785442230205226,"score_gpt":0.33019765773690907,"score_spread":0.3123432354348568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408404791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018674945,0.000037165148,0.9675252,0.013318936,0.00007583479,0.000056519315,0.00004353088,0.000011611396,0.00025630122],"genre_scores_gemma":[0.89765096,0.00007987376,0.101634,0.0004609972,0.000016899712,0.00000113307,0.000016861393,0.0000023282546,0.00013694022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989254,0.00025175526,0.00030068672,0.00016184544,0.0002671469,0.00009319229],"domain_scores_gemma":[0.9975491,0.0010568666,0.00083961425,0.00027972832,0.00023119964,0.000043464344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081040704,0.00006695437,0.00016844658,0.000080749014,0.00014095643,0.00017813254,0.0004096506,0.000024764116,5.623769e-7],"category_scores_gemma":[0.003408154,0.000047819467,0.000012506943,0.00034228642,0.00007957174,0.00046616947,0.00020817736,0.0002056412,0.0000011660387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003530562,0.000081984115,0.067730986,0.000017630266,0.00010029812,8.2074854e-7,0.0002643789,0.00075878977,0.00069631846,0.4565068,0.009321543,0.46448514],"study_design_scores_gemma":[0.00011854225,0.000027380705,0.4039524,0.000014846393,0.000030096215,0.0000021729559,0.000016119919,0.580351,0.0000063984166,0.015221317,0.00022709339,0.000032613432],"about_ca_topic_score_codex":0.000028176572,"about_ca_topic_score_gemma":0.000006722823,"teacher_disagreement_score":0.878976,"about_ca_system_score_codex":0.000116213705,"about_ca_system_score_gemma":0.00013832381,"threshold_uncertainty_score":0.40801248},"labels":[],"label_agreement":null},{"id":"W4408563401","doi":"10.1080/01621459.2025.2479220","title":"Prediction of Cognitive Function via Brain Region Volumes with Applications to Alzheimer’s Disease Based on Space-Factor-Guided Functional Principal Component Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Principal component analysis; Cognition; Disease; Component (thermodynamics); Functional principal component analysis; Factor (programming language); Computer science; Neuroscience; Artificial intelligence; Pattern recognition (psychology); Psychology; Medicine; Physics; Pathology","score_opus":0.04080527294020982,"score_gpt":0.29549040380517044,"score_spread":0.25468513086496064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408563401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12778291,0.000010294675,0.8522112,0.018545937,0.0002612322,0.0005364345,0.00045224704,0.000026421016,0.00017332558],"genre_scores_gemma":[0.9953272,0.0000028615743,0.0004975749,0.0038182687,0.000106839674,0.00005790445,0.000016738471,0.000011283131,0.00016133366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973181,0.0005701949,0.00050514925,0.00032729923,0.0010862809,0.00019298942],"domain_scores_gemma":[0.9870828,0.010617429,0.0013029783,0.00019801411,0.00067194103,0.00012685423],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003949767,0.00017097461,0.0004164452,0.00045210923,0.00028827967,0.00003491786,0.00014420885,0.000032579137,0.000019470808],"category_scores_gemma":[0.009741755,0.00012543629,0.00018511205,0.0020191746,0.00019923454,0.00011624646,0.000048603593,0.00026033755,0.0000051285565],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011194346,0.0021654652,0.8315373,0.000049868522,0.003921724,0.00001224007,0.00019368708,0.08331489,0.0085048815,0.009940101,0.033495937,0.015669528],"study_design_scores_gemma":[0.0006644387,0.00073807884,0.9801863,0.00006172975,0.0019138138,0.000001958638,0.00006153919,0.013844696,0.00091106957,0.0008481116,0.000661572,0.00010671312],"about_ca_topic_score_codex":0.000040996263,"about_ca_topic_score_gemma":0.000024104045,"teacher_disagreement_score":0.8675443,"about_ca_system_score_codex":0.0005580528,"about_ca_system_score_gemma":0.00023497645,"threshold_uncertainty_score":0.9985996},"labels":[],"label_agreement":null},{"id":"W4409003881","doi":"10.1080/01621459.2025.2485342","title":"Network-Based Neighborhood Regression","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistics; Regression; Regression analysis; Mathematics; Computer science; Econometrics","score_opus":0.00802707070942985,"score_gpt":0.3196529010892763,"score_spread":0.3116258303798464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409003881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105681494,0.00024315571,0.73847556,0.13261369,0.0019459726,0.0004096698,0.000049949205,0.000062523,0.020517986],"genre_scores_gemma":[0.9954455,0.000016445616,0.0009931547,0.0022184956,0.00030150422,0.0000018652279,0.0000018467715,0.0000033352349,0.0010178854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976752,0.0010355641,0.00037874663,0.00008491471,0.0006219714,0.0002036488],"domain_scores_gemma":[0.99649996,0.0018719694,0.0010287579,0.00011845834,0.00041362582,0.00006725048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002026587,0.00006507162,0.00024674818,0.00006550376,0.00051791116,0.00006934138,0.00026868054,0.000042150128,0.00011314345],"category_scores_gemma":[0.0044290074,0.000043954315,0.00014030255,0.0008621228,0.0002095926,0.00006589327,0.000018278635,0.00024550242,0.000006461633],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020559435,0.00038092138,0.59569615,0.00001812646,0.00031666478,0.00000455948,0.0013186686,0.005823424,0.000069320005,0.1055803,0.14443153,0.14615472],"study_design_scores_gemma":[0.0009337846,0.00022013894,0.778607,0.00027117744,0.00076339603,3.3884803e-7,0.0025429872,0.008793844,0.00005219155,0.14886655,0.058679152,0.00026945205],"about_ca_topic_score_codex":0.0008745702,"about_ca_topic_score_gemma":0.00088017405,"teacher_disagreement_score":0.88976395,"about_ca_system_score_codex":0.00077243464,"about_ca_system_score_gemma":0.0006713969,"threshold_uncertainty_score":0.5302255},"labels":[],"label_agreement":null},{"id":"W4409421020","doi":"10.1080/01621459.2024.2421998","title":"Discussion of “Data Fission: Splitting a Single Data Point”","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Office of Naval Research; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Fission; Nuclear data; Point (geometry); Statistical physics; Mathematics; Nuclear physics; Physics; Geometry; Neutron","score_opus":0.12246539850569539,"score_gpt":0.43834009369890636,"score_spread":0.315874695193211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409421020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008314454,0.000024661234,0.98085994,0.008305136,0.00035281506,0.00011337782,0.0008529389,0.000009397117,0.0011672833],"genre_scores_gemma":[0.20148697,0.000013796256,0.7975727,0.00027563918,0.00013002208,6.1432655e-7,0.000016414006,0.000011193788,0.0004926704],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753267,0.0006222426,0.00088861934,0.00018209704,0.00059380656,0.0001805627],"domain_scores_gemma":[0.988745,0.007907862,0.0021840509,0.00079430547,0.0003023816,0.00006641927],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026571217,0.00010395349,0.0005027912,0.0000591614,0.000085745254,0.00003794076,0.0010978067,0.000038406135,0.000061841514],"category_scores_gemma":[0.057985466,0.000052988413,0.000055384055,0.0004099557,0.00012943345,0.00018147191,0.00073236553,0.00030625443,0.0000014903184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002550306,0.0007862846,0.01934781,0.00019595571,0.00038315612,0.000009379025,0.00025155485,0.000002779442,0.004100269,0.11898479,0.1766354,0.6790476],"study_design_scores_gemma":[0.00070382655,0.0003803838,0.072144695,0.00078593066,0.0006700078,0.000011120973,0.00083983457,0.014764965,0.0004876175,0.9049214,0.0040887794,0.00020145265],"about_ca_topic_score_codex":0.00003567815,"about_ca_topic_score_gemma":0.0000063173875,"teacher_disagreement_score":0.7859366,"about_ca_system_score_codex":0.00017701526,"about_ca_system_score_gemma":0.0001553756,"threshold_uncertainty_score":0.9499495},"labels":[],"label_agreement":null},{"id":"W4409421713","doi":"10.1080/01621459.2025.2450191","title":"Our Mission in Action: Past, Present, and Future","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Agriculture and Farm Safety","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"U.S. Food and Drug Administration","keywords":"Action (physics); Aeronautics; Computer science; Engineering; Physics","score_opus":0.012289304247817073,"score_gpt":0.2799263761562873,"score_spread":0.2676370719084702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409421713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88210607,0.00009517031,0.00012242292,0.11662251,0.00039793013,0.000091009846,0.000025213743,0.000006354281,0.0005333073],"genre_scores_gemma":[0.996927,0.00013735233,0.00022564815,0.0005835431,0.0014821138,6.36698e-7,0.0000026919722,3.1756332e-7,0.0006406615],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99925524,0.00016053302,0.00021265169,0.00006903136,0.0001976958,0.00010485281],"domain_scores_gemma":[0.99923974,0.00022996371,0.00039438042,0.000017578746,0.0000802222,0.000038125218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002466482,0.000056463334,0.00015620147,0.000009724164,0.000081242666,0.000026386375,0.00009709677,0.000036266436,0.000008399695],"category_scores_gemma":[0.000042735606,0.000016385464,0.000045689423,0.00034939917,0.000015326708,0.000061569044,0.000032016134,0.00019072255,9.694525e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015813169,0.00013675827,0.33818823,0.0000059743666,0.0000503605,0.000005023251,0.000072961775,0.0000078751,0.01188041,0.0013566278,0.079553865,0.5685838],"study_design_scores_gemma":[0.000098399185,0.00007366606,0.9190829,0.000011042709,0.00001880484,0.000003820037,0.00077832147,0.000019469804,0.000035796205,0.001266538,0.07857546,0.00003580365],"about_ca_topic_score_codex":0.000061486055,"about_ca_topic_score_gemma":0.000042270043,"teacher_disagreement_score":0.58089465,"about_ca_system_score_codex":0.00010916052,"about_ca_system_score_gemma":0.000009617599,"threshold_uncertainty_score":0.08286052},"labels":[],"label_agreement":null},{"id":"W4411235583","doi":"10.1080/01621459.2025.2516209","title":"Mutually Exciting Point Processes with Latency","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Diffusion and Search Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; National Research University Higher School of Economics","keywords":"Point process; Computer science; Psychology; Mathematics; Statistics","score_opus":0.002765217856993608,"score_gpt":0.2563814529591524,"score_spread":0.25361623510215875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411235583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9233712,0.00003863668,0.072020926,0.0026946345,0.000091024805,0.00006496093,0.000022350972,0.0000032648197,0.0016930213],"genre_scores_gemma":[0.99352705,0.000089497444,0.00414725,0.00090416404,0.00006428129,0.0000011849402,0.0000049029163,0.000005493127,0.0012561859],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99929637,0.000092381895,0.00019193024,0.00007102613,0.00022916748,0.000119153294],"domain_scores_gemma":[0.99894077,0.00013977362,0.00043802487,0.000072955256,0.0003721398,0.00003631366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027662705,0.000056141995,0.000123112,0.000027448252,0.00006274631,0.000029784502,0.00013862696,0.000021884769,0.0000054242223],"category_scores_gemma":[0.002588098,0.000033674798,0.000036623984,0.00019246184,0.00006282509,0.0000040584237,0.000045975,0.0001143141,8.411394e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024776396,0.0011143369,0.63806516,0.00030350836,0.0015804424,0.000050110473,0.00058663497,0.0008435761,0.17492878,0.013242078,0.07554224,0.09126546],"study_design_scores_gemma":[0.002684722,0.0028538092,0.9545651,0.00036861878,0.0003203298,0.0000891867,0.001849739,0.0012724454,0.009506689,0.008999302,0.01701123,0.00047882614],"about_ca_topic_score_codex":0.000010962399,"about_ca_topic_score_gemma":0.000046196255,"teacher_disagreement_score":0.31649992,"about_ca_system_score_codex":0.00006717506,"about_ca_system_score_gemma":0.00033016587,"threshold_uncertainty_score":0.3098382},"labels":[],"label_agreement":null},{"id":"W4411984812","doi":"10.1080/01621459.2025.2520460","title":"Checking the Cox Proportional Hazards Model with Interval-Censored Data","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health; University of Waterloo","keywords":"Proportional hazards model; Statistics; Mathematics; Interval (graph theory); Econometrics; Combinatorics","score_opus":0.06215604467419755,"score_gpt":0.40088076934795197,"score_spread":0.3387247246737544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411984812","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022708913,0.000010530542,0.968119,0.0077986973,0.00015512801,0.00014058239,0.00024599262,0.00000999862,0.0008111339],"genre_scores_gemma":[0.47597975,0.0000109892635,0.52238536,0.0008794967,0.00009750048,0.000004455243,0.0000047051294,0.000012768523,0.0006250074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99785787,0.00043373735,0.00060655107,0.00014508973,0.00075353606,0.00020322508],"domain_scores_gemma":[0.9936466,0.0039247493,0.0014824322,0.0003835374,0.0005109492,0.000051713134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019830777,0.00011879306,0.00038206446,0.00003984466,0.00016402513,0.0000794241,0.0006485703,0.00003055495,0.000028752325],"category_scores_gemma":[0.01642953,0.000055791854,0.00006225047,0.00031717625,0.00024359064,0.000089353656,0.00018537282,0.00044710722,0.0000016883774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045238397,0.00034264385,0.01826696,0.000064225074,0.0007063666,0.000010418306,0.0002830331,0.00029925854,0.00026460917,0.8082551,0.0987471,0.0723079],"study_design_scores_gemma":[0.00058143144,0.00022560872,0.08485686,0.00021593078,0.0005797598,0.000021621032,0.00029932588,0.17813432,0.000091108064,0.7338954,0.00093780435,0.00016081225],"about_ca_topic_score_codex":0.000025501431,"about_ca_topic_score_gemma":0.000016071612,"teacher_disagreement_score":0.45327082,"about_ca_system_score_codex":0.00028916606,"about_ca_system_score_gemma":0.00038493008,"threshold_uncertainty_score":0.9918555},"labels":[],"label_agreement":null},{"id":"W4411984890","doi":"10.1080/01621459.2025.2519814","title":"Adaptive Selection for False Discovery Rate Control Leveraging Symmetry","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Key Research and Development Program of China; Alberta Machine Intelligence Institute","keywords":"False discovery rate; Selection (genetic algorithm); Computer science; Econometrics; Mathematics; Statistics; Artificial intelligence; Biology","score_opus":0.15565189437174692,"score_gpt":0.48701101146231585,"score_spread":0.3313591170905689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411984890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01748965,0.000012860627,0.9776371,0.0029696955,0.0010532244,0.00039882193,0.00024429892,0.0000166158,0.00017773062],"genre_scores_gemma":[0.5642977,0.0000097526745,0.4334573,0.0012139558,0.00036295978,0.000017191369,4.919721e-7,0.00001879214,0.00062186626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957985,0.002036537,0.0012010975,0.00018528705,0.00047764133,0.000300917],"domain_scores_gemma":[0.8849746,0.11167389,0.0025080296,0.00013779938,0.0006365936,0.000069100126],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006111571,0.00016104792,0.00088459364,0.00010636694,0.00017081214,0.00009908145,0.0002655375,0.00007535367,0.000012027891],"category_scores_gemma":[0.2274964,0.00010951173,0.00030753043,0.0005113466,0.00013624945,0.00013995162,0.00004424691,0.0004752165,0.000001972121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033019609,0.00054846663,0.02958671,0.0001237481,0.002077578,0.000004188356,0.00009583317,0.00016072132,0.0016216732,0.841501,0.06281285,0.05816526],"study_design_scores_gemma":[0.0017174557,0.0003741364,0.034791317,0.00010824745,0.0007555957,0.000002543397,0.00012861706,0.004094847,0.00039395076,0.95716244,0.0003478826,0.00012294811],"about_ca_topic_score_codex":0.000021469185,"about_ca_topic_score_gemma":0.000006111938,"teacher_disagreement_score":0.54680806,"about_ca_system_score_codex":0.0009367063,"about_ca_system_score_gemma":0.00022366224,"threshold_uncertainty_score":0.7790107},"labels":[],"label_agreement":null},{"id":"W4413751953","doi":"10.1080/01621459.2025.2552416","title":"Exponential Families in Theory and Practice","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Intergenerational Family Dynamics and Caregiving","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exponential family; Mathematics; Exponential function; Psychology; Econometrics; Applied mathematics; Mathematical economics; Mathematical analysis","score_opus":0.004956614711957774,"score_gpt":0.3301378846631963,"score_spread":0.3251812699512385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413751953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91900283,0.00012705312,0.04317036,0.018915063,0.001073373,0.0001060948,0.000016498247,0.000005324347,0.017583381],"genre_scores_gemma":[0.99632066,0.00020093219,0.0015189665,0.0011176309,0.000098978904,0.0000010159138,3.6077114e-7,0.0000019959402,0.0007394707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9981342,0.0011925646,0.00020987986,0.00004808732,0.00031560057,0.00009967847],"domain_scores_gemma":[0.99575377,0.0035761737,0.00040855003,0.000031783286,0.000207666,0.000022032355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029278912,0.000035479672,0.000114083006,0.00006172002,0.00014678457,0.00005733684,0.00009718365,0.000020725165,0.000006684409],"category_scores_gemma":[0.013317843,0.000026684393,0.000032166226,0.00022934042,0.0001299486,0.000121117424,0.000027271872,0.00014005488,5.789038e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015134712,0.000048289367,0.025280291,0.0000024625374,0.00005615177,0.0000032135213,0.0027288338,0.00005099795,0.00044358094,0.95297444,0.0029533042,0.015307073],"study_design_scores_gemma":[0.0005644421,0.00012209952,0.738734,0.00009946711,0.00015867708,0.000004775113,0.053770144,0.0006855229,0.00003148593,0.17270038,0.032970402,0.00015858325],"about_ca_topic_score_codex":0.0005372978,"about_ca_topic_score_gemma":0.000572965,"teacher_disagreement_score":0.7802741,"about_ca_system_score_codex":0.00038480794,"about_ca_system_score_gemma":0.00017580292,"threshold_uncertainty_score":0.9949934},"labels":[],"label_agreement":null},{"id":"W4414472698","doi":"10.1080/01621459.2025.2555054","title":"Nonparametric Density Estimation of a Long-Term Trend from Repeated Semicontinuous Data","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Estimation; Density estimation; Kernel density estimation; Estimation theory","score_opus":0.04390328920868996,"score_gpt":0.3873810067977987,"score_spread":0.3434777175891087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414472698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47609043,0.000018157265,0.5228603,0.00026445423,0.00018022145,0.00007172282,0.0003893554,0.000007005727,0.0001183535],"genre_scores_gemma":[0.7271741,0.000015998448,0.27256334,0.000092230664,0.000042327112,8.1374316e-7,0.000019840087,0.0000071681093,0.00008414977],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975645,0.0006085208,0.0009288976,0.00017196406,0.00055483525,0.0001712796],"domain_scores_gemma":[0.9862219,0.010399202,0.0025264067,0.00045825948,0.00033319768,0.000061038874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013085754,0.00012226927,0.0006370525,0.00012570636,0.00006262552,0.00004183117,0.00050338387,0.000055704157,0.000039802373],"category_scores_gemma":[0.04415464,0.00008515125,0.00008476064,0.0007373243,0.00012921597,0.00009234518,0.00017228755,0.00031488878,0.0000018695029],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046592962,0.0007342868,0.3901141,0.00012065042,0.0010281119,0.000030085384,0.00024076439,0.0000548784,0.0021898835,0.028899265,0.020916704,0.55520535],"study_design_scores_gemma":[0.0004738235,0.00013604555,0.8180822,0.0001736261,0.0006474209,0.000005532987,0.00003932912,0.01229512,0.00083440257,0.16719757,0.000013328253,0.00010160686],"about_ca_topic_score_codex":0.00018376492,"about_ca_topic_score_gemma":0.00003976798,"teacher_disagreement_score":0.5551037,"about_ca_system_score_codex":0.00027406326,"about_ca_system_score_gemma":0.00013165767,"threshold_uncertainty_score":0.9638969},"labels":[],"label_agreement":null},{"id":"W4415749113","doi":"10.1080/01621459.2025.2579953","title":"A Factor-Copula Latent-Vine Time Series Model for Extreme Flood Insurance Losses","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Agricultural risk and resilience","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Series (stratigraphy); Time series; Flood myth; Risk model","score_opus":0.012849342866584776,"score_gpt":0.2419172452533936,"score_spread":0.2290679023868088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415749113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906702,0.00006607464,0.0022816085,0.006290536,0.00013967966,0.00014085938,0.0003334086,0.000012425164,0.00006523347],"genre_scores_gemma":[0.9937738,0.00008892957,0.0020728544,0.00028165692,0.00013418536,0.0000039299516,0.000007636825,7.384591e-7,0.0036362386],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99891424,0.00011754933,0.00033966036,0.00011307199,0.00031200578,0.0002034924],"domain_scores_gemma":[0.9980611,0.0008572431,0.0006897009,0.000032313576,0.00030619954,0.000053405696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022670062,0.00010486584,0.000279591,0.000009788095,0.0002066942,0.000056551457,0.00026313294,0.000040635696,0.000020219892],"category_scores_gemma":[0.0012209268,0.00003091419,0.0001418666,0.00033183154,0.00008263883,0.00014573656,0.000042832045,0.00013356419,0.000004505083],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092535786,0.0004129285,0.49358338,0.00003163127,0.00027602856,0.000004588992,0.00023167323,0.001654974,0.3124745,0.0022565632,0.040194757,0.14795363],"study_design_scores_gemma":[0.00015065647,0.00021853065,0.9912135,0.00003409179,0.00004365039,0.0000048644483,0.00007019555,0.0026058469,0.0005836004,0.004052472,0.00092580233,0.000096793134],"about_ca_topic_score_codex":0.000040715684,"about_ca_topic_score_gemma":0.00007040615,"teacher_disagreement_score":0.49763012,"about_ca_system_score_codex":0.00014456088,"about_ca_system_score_gemma":0.00002791319,"threshold_uncertainty_score":0.15897456},"labels":[],"label_agreement":null},{"id":"W4415932740","doi":"10.1080/01621459.2025.2582874","title":"Functional Partial Least-Squares: Adaptive Estimation and Inference","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec-Société et Culture","keywords":"Inference; Estimation; Pattern recognition (psychology); Estimation theory; Statistical inference","score_opus":0.045247960679467895,"score_gpt":0.37563260457567066,"score_spread":0.33038464389620276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415932740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05637433,0.000014453006,0.9413667,0.0014463195,0.00027940903,0.00008283993,0.000048429785,0.000008897917,0.00037861837],"genre_scores_gemma":[0.78017265,0.000008001054,0.21928698,0.0002746742,0.000070719965,0.0000037750794,8.0248003e-7,0.000005168,0.00017723946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983659,0.0004271081,0.00049496157,0.000107508466,0.00044613515,0.0001583913],"domain_scores_gemma":[0.9906925,0.007814095,0.0009564329,0.00009468035,0.00037775718,0.00006451583],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00084627036,0.00010219766,0.00032690918,0.00006317157,0.0001238289,0.000052782903,0.000110824614,0.000037847665,0.00004767234],"category_scores_gemma":[0.023929827,0.000068621535,0.000058601247,0.0002678882,0.00016730578,0.00008242504,0.000054099553,0.0002936882,0.0000035445375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002213366,0.000115581875,0.014049518,0.000026586016,0.0001547736,0.0000023460054,0.00011893429,0.000084052226,0.0001661228,0.81192493,0.010430389,0.16270545],"study_design_scores_gemma":[0.00035617384,0.00024029714,0.25181833,0.00008578607,0.00018579757,0.0000050000467,0.00015826328,0.021950884,0.00016942086,0.7247819,0.00015922723,0.00008896365],"about_ca_topic_score_codex":0.000028138606,"about_ca_topic_score_gemma":0.000005122728,"teacher_disagreement_score":0.72379833,"about_ca_system_score_codex":0.00024241713,"about_ca_system_score_gemma":0.00015659796,"threshold_uncertainty_score":0.98429203},"labels":[],"label_agreement":null},{"id":"W4416510269","doi":"10.1080/01621459.2025.2587316","title":"Bias Control for M-Quantile-Based Small Area Estimators","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Italy: Economic History and Contemporary Issues","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; Outlier; Linearization; Small area estimation; Sample (material); Estimation; Sample size determination; Extremum estimator","score_opus":0.03409381177812841,"score_gpt":0.2468777618032915,"score_spread":0.2127839500251631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416510269","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26369175,0.00038444408,0.7215049,0.007896362,0.0014957775,0.00031867277,0.00078334543,0.000016769352,0.0039079683],"genre_scores_gemma":[0.9925572,0.000005677991,0.0041760704,0.0016451029,0.00007897723,0.000009964543,0.0000047384715,0.00001016898,0.0015120477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987633,0.00006302993,0.0008122462,0.00014072761,0.0000433815,0.0001772968],"domain_scores_gemma":[0.99621767,0.0012132745,0.002265111,0.00014220025,0.00011315453,0.00004862138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011232576,0.00010269057,0.0005548502,0.0001434139,0.000121011515,0.000052234747,0.00023618921,0.00004157492,0.000039075796],"category_scores_gemma":[0.0026291516,0.00009002089,0.00023036129,0.00017023484,0.000075547,0.00008667085,0.000011563786,0.00014874963,0.000020928086],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052654475,0.0002498482,0.6176794,0.00004491325,0.0005711529,0.000004088963,0.0001712113,0.001157073,0.000033833683,0.3237489,0.05141701,0.0043960433],"study_design_scores_gemma":[0.006628806,0.001015746,0.403116,0.00014914965,0.000325973,0.0000041790618,0.00032187035,0.07271645,0.00020989974,0.21023259,0.304613,0.00066634937],"about_ca_topic_score_codex":0.000057112953,"about_ca_topic_score_gemma":0.000012309288,"teacher_disagreement_score":0.7288655,"about_ca_system_score_codex":0.0005416495,"about_ca_system_score_gemma":0.000115149174,"threshold_uncertainty_score":0.36709455},"labels":[],"label_agreement":null},{"id":"W4417200172","doi":"10.1080/01621459.2025.2596297","title":"The Impact of Job Stability on Monetary Poverty in Italy: Causal Small Area Estimation","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Italy: Economic History and Contemporary Issues","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Centro de Investigación en Computación; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; University of Bristol; University of California Berkeley","keywords":"Estimation; Poverty; Stability (learning theory); Job loss; Small area estimation","score_opus":0.021101315884674367,"score_gpt":0.2519832799679205,"score_spread":0.23088196408324616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417200172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904872,0.0001672803,0.0032027187,0.0014850318,0.00027681582,0.00011162432,0.00020536836,0.0000031059913,0.004060851],"genre_scores_gemma":[0.99918413,0.000033604316,0.0003127842,0.00014450663,0.000024411176,0.0000023403202,0.0000029408106,0.0000052000805,0.00029009322],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986427,0.0001298113,0.00089610106,0.00012109,0.00006049107,0.00014982164],"domain_scores_gemma":[0.99678147,0.0011092115,0.0018221498,0.00018681321,0.000067818815,0.00003253796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013840635,0.00009486353,0.00044427798,0.00010936271,0.0000865094,0.000030382856,0.00022135093,0.000036746456,0.00003414982],"category_scores_gemma":[0.0022887068,0.00006506054,0.00018074975,0.00023977151,0.00009284458,0.00012268922,0.000025643241,0.00023962861,0.000009714235],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004100656,0.0002014155,0.9627658,0.000010549498,0.00026264653,0.0000021335468,0.00049752125,0.0027133117,0.000027277998,0.022392021,0.0056385607,0.005078684],"study_design_scores_gemma":[0.00033811203,0.00024135153,0.9390787,0.000021126956,0.0000133637695,6.0198624e-7,0.00011286617,0.0090784915,0.000022982935,0.05063515,0.0003865538,0.0000706984],"about_ca_topic_score_codex":0.0011528467,"about_ca_topic_score_gemma":0.00014846308,"teacher_disagreement_score":0.02824313,"about_ca_system_score_codex":0.0013188843,"about_ca_system_score_gemma":0.000105549145,"threshold_uncertainty_score":0.34488365},"labels":[],"label_agreement":null}]}