{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002491777,0.000072488474,0.9965475,0.000074157324,0.000011741015,0.000024523126,0.000023746086,0.00036437134,0.00038962954],"genre_scores_gemma":[0.167808,0.00031329333,0.82879657,0.00020645617,0.000082931976,0.00040219355,0.0002641975,0.0004516448,0.0016746874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803954,0.0008909802,0.00008777395,0.00028186035,0.00056213565,0.00013764288],"domain_scores_gemma":[0.9879622,0.008689043,0.00066406897,0.0016274952,0.0007541677,0.0003031007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005983412,0.001209664,0.0017450018,0.001376195,0.00091678917,0.0013288745,0.0030932452,0.0013280868,0.0043742033],"category_scores_gemma":[0.027380234,0.0009472236,0.0012386292,0.0014100879,0.0019752411,0.0020057056,0.002743863,0.0038329512,0.0011956333],"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":[0.00009851236,0.00007641284,0.001673721,0.000148991,0.00008235216,0.00011260115,0.00016343108,0.831586,0.0022569306,0.11672545,0.0014051037,0.045670625],"study_design_scores_gemma":[0.000008681932,0.000009047733,0.000058944028,0.00000812627,0.0000059732783,0.000011668808,0.0000055092746,0.98070025,0.000486436,0.018257951,0.00044193416,0.00000548599],"about_ca_topic_score_codex":0.009847834,"about_ca_topic_score_gemma":0.016135884,"teacher_disagreement_score":0.009847834,"about_ca_system_score_codex":0.002130493,"about_ca_system_score_gemma":0.004021254,"threshold_uncertainty_score":0.03164369},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012747062,0.00080305705,0.0037077565,0.78449184,0.09776777,0.00038721864,0.010306581,0.006104878,0.09515618],"genre_scores_gemma":[0.009714755,0.0009703371,0.0029492087,0.73339504,0.014983645,0.0006075951,0.0028024425,0.0017357154,0.2328413],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969111,0.00043274648,0.00033468896,0.0003464999,0.0015968488,0.00037809488],"domain_scores_gemma":[0.9792514,0.007043455,0.0009656939,0.0014817591,0.010018552,0.0012392254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038197576,0.0006468734,0.0005987672,0.0010293116,0.0016267202,0.0020977128,0.0026043358,0.010753941,0.37421292],"category_scores_gemma":[0.06645735,0.0004514393,0.001145927,0.00084602943,0.0013817402,0.003534729,0.002306267,0.006784301,0.21708417],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026636244,0.000006082719,0.000117013195,0.00003497847,0.0000017059627,0.000035521716,0.000028331211,0.000013257858,0.00005645355,0.00055302435,0.99544877,0.0036780986],"study_design_scores_gemma":[0.0000554008,0.000015047848,0.0006832512,0.00018730789,0.000006428386,0.0001625752,0.00018824679,0.00009500289,0.00046177418,0.0017366577,0.9963819,0.00002639922],"about_ca_topic_score_codex":0.01947837,"about_ca_topic_score_gemma":0.014832637,"teacher_disagreement_score":0.37421292,"about_ca_system_score_codex":0.0024767017,"about_ca_system_score_gemma":0.0029211934,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28223673,0.0006539737,0.7062446,0.0016345344,0.00008232035,0.00016786753,0.0005731026,0.0002128234,0.008194099],"genre_scores_gemma":[0.95503324,0.00051982043,0.0338724,0.00016946625,0.000052731622,0.0002921824,0.00042592807,0.00006484647,0.009569417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981482,0.0008742398,0.000108556036,0.0003629352,0.0002950527,0.00021105458],"domain_scores_gemma":[0.98947024,0.008148964,0.0012342673,0.0002604794,0.0006418995,0.00024409642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050262935,0.0008812052,0.0016327788,0.0011687941,0.0005447304,0.0021958535,0.0020648884,0.0020606047,0.0028353757],"category_scores_gemma":[0.02136509,0.0009460963,0.0017746717,0.001160743,0.0012980934,0.002446365,0.0015534009,0.0023553618,0.0004592175],"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":[0.000053255168,0.00009020285,0.007119615,0.000057038862,0.00008478332,0.0002112527,0.00033666665,0.90583897,0.0006144261,0.07988935,0.0006627896,0.005041555],"study_design_scores_gemma":[0.000007431673,0.0000069586313,0.00035927133,0.0000031731156,0.0000055710793,0.000011185463,0.000021394495,0.9910828,0.000029302044,0.008308175,0.00015908267,0.0000055856663],"about_ca_topic_score_codex":0.021471148,"about_ca_topic_score_gemma":0.008508105,"teacher_disagreement_score":0.021471148,"about_ca_system_score_codex":0.0020557598,"about_ca_system_score_gemma":0.0012869193,"threshold_uncertainty_score":0.042692363},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005817836,0.00016820256,0.99350137,0.00009335055,0.000016034066,0.000015667192,0.000018246039,0.00012181167,0.0002475409],"genre_scores_gemma":[0.25291377,0.0006188087,0.7419388,0.00019122071,0.00015697467,0.00028855985,0.0003568241,0.00028846107,0.0032466762],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958281,0.002577882,0.0001806747,0.00045247813,0.00078738807,0.00017345084],"domain_scores_gemma":[0.9835368,0.013856148,0.0008139948,0.0007266519,0.0007275215,0.00033883474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075284056,0.0010473252,0.0018154564,0.0017758438,0.00093168387,0.0018733855,0.0021291128,0.0016735013,0.0016106126],"category_scores_gemma":[0.019137494,0.0011627096,0.0013746533,0.001438423,0.0021465938,0.0025011017,0.0024867747,0.0023549935,0.00051747885],"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":[0.00021219724,0.00007808854,0.002161765,0.00020190618,0.00011415011,0.00024919023,0.00020310334,0.7189685,0.0024351596,0.18492825,0.001501717,0.088945925],"study_design_scores_gemma":[0.000011394698,0.000012668451,0.0001455985,0.00000696018,0.000007741669,0.000022697574,0.000005018396,0.967953,0.0003981953,0.030892348,0.00052970875,0.000014630162],"about_ca_topic_score_codex":0.0035847179,"about_ca_topic_score_gemma":0.0045853658,"teacher_disagreement_score":0.0075284056,"about_ca_system_score_codex":0.00139399,"about_ca_system_score_gemma":0.0017655669,"threshold_uncertainty_score":0.03981453},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.983461,0.00054282165,0.0072399527,0.0012230057,0.000055551074,0.00055454974,0.0009685909,0.00018692714,0.005767558],"genre_scores_gemma":[0.99423605,0.0002226937,0.002671467,0.00022434487,0.000017633456,0.0002675836,0.0005836785,0.0000099817435,0.0017665538],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9868285,0.008501436,0.0005105195,0.0011014311,0.0014815142,0.0015765119],"domain_scores_gemma":[0.9504305,0.03510757,0.008267048,0.002033168,0.0024823314,0.0016794518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020827092,0.00071001507,0.001491111,0.0008616253,0.0006776139,0.0019166918,0.002795186,0.0018102239,0.006775852],"category_scores_gemma":[0.05790612,0.0005062189,0.0009138981,0.001370067,0.000934629,0.0019313506,0.0015791579,0.0023448595,0.00062723766],"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":[0.010401402,0.006809248,0.3941201,0.00094606355,0.0016684034,0.0003064933,0.0009884624,0.3607536,0.0017592921,0.017236844,0.0055638645,0.19944628],"study_design_scores_gemma":[0.0039581293,0.03770065,0.47055623,0.00066258915,0.002068884,0.0001078454,0.008021311,0.4356529,0.011091149,0.017998466,0.011956331,0.00022546395],"about_ca_topic_score_codex":0.04891238,"about_ca_topic_score_gemma":0.03560379,"teacher_disagreement_score":0.04891238,"about_ca_system_score_codex":0.005989944,"about_ca_system_score_gemma":0.0071825683,"threshold_uncertainty_score":0.11014557},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015250492,0.0016909903,0.9749808,0.003724794,0.0002775512,0.0010521713,0.0012477454,0.0004468009,0.0013286184],"genre_scores_gemma":[0.46491092,0.0036178727,0.49913985,0.002694707,0.0008260096,0.016353315,0.0032253696,0.00018116372,0.009050808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93991774,0.051576756,0.0017894165,0.003847256,0.0019187334,0.000950138],"domain_scores_gemma":[0.75712365,0.22316049,0.009267196,0.0066887545,0.0026494884,0.0011104214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.105167,0.00213997,0.0049263122,0.002827275,0.0011164364,0.0027984043,0.0054367995,0.005025661,0.0096325055],"category_scores_gemma":[0.17990462,0.0020540827,0.0036887343,0.0027928716,0.003618574,0.0048959483,0.0031408106,0.0069873035,0.0014828693],"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":[0.002463348,0.0002138008,0.010922434,0.001587343,0.001743751,0.00068702333,0.0011076801,0.28075182,0.00070407835,0.63998556,0.005577519,0.054255717],"study_design_scores_gemma":[0.00088104064,0.00034864963,0.0014687694,0.00025846198,0.00043513716,0.000102837024,0.00005263413,0.61430997,0.0002874577,0.378986,0.002799868,0.000069159214],"about_ca_topic_score_codex":0.0071824086,"about_ca_topic_score_gemma":0.0061750757,"teacher_disagreement_score":0.105167,"about_ca_system_score_codex":0.003311856,"about_ca_system_score_gemma":0.0056977165,"threshold_uncertainty_score":0.5561829},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017935128,0.00009730435,0.99749243,0.0000797659,0.000017382568,0.000022305827,0.000026859072,0.00005614357,0.000414236],"genre_scores_gemma":[0.18710609,0.0006100407,0.80878687,0.00024990315,0.00021529832,0.0007165423,0.00045136968,0.00011449445,0.0017493109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9806136,0.01467819,0.0005663948,0.0016615043,0.0021910553,0.0002892741],"domain_scores_gemma":[0.90764594,0.07602982,0.0044732955,0.007939938,0.0034818498,0.00042911313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026282305,0.0010411955,0.0016255428,0.0025583399,0.00087020075,0.0025684554,0.0036042656,0.0017438991,0.004098814],"category_scores_gemma":[0.17317832,0.0011277599,0.0016957694,0.002765946,0.002712687,0.0058371737,0.003316964,0.0031907428,0.00085394515],"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":[0.00011790054,0.00005326097,0.0029705549,0.00019739599,0.00014975434,0.00020402008,0.0003657671,0.070716046,0.00044419878,0.83174103,0.0017714461,0.09126871],"study_design_scores_gemma":[0.00005232963,0.00006370711,0.0011975883,0.000077762255,0.00003735346,0.00017936005,0.000072591545,0.47311658,0.00058840134,0.5201866,0.004386427,0.000041410476],"about_ca_topic_score_codex":0.00217461,"about_ca_topic_score_gemma":0.0016107935,"teacher_disagreement_score":0.026282305,"about_ca_system_score_codex":0.0014828036,"about_ca_system_score_gemma":0.0017159245,"threshold_uncertainty_score":0.13899583},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00870204,0.00017532286,0.9897802,0.00013389422,0.00004197704,0.00002984742,0.00017393094,0.00011622421,0.00084647007],"genre_scores_gemma":[0.54588234,0.0018136177,0.43714607,0.0002873718,0.00021739856,0.0007010092,0.0017274593,0.00021088007,0.0120137865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99865675,0.00040597428,0.0000716076,0.0005129417,0.00025564554,0.000097203556],"domain_scores_gemma":[0.9979214,0.0008753921,0.00039861325,0.00040992958,0.00034206308,0.00005261725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002958879,0.000863568,0.0007467684,0.0010135126,0.00032425433,0.0010513343,0.0015146004,0.0010516249,0.003223912],"category_scores_gemma":[0.008491115,0.0006062343,0.0010214035,0.0013874281,0.00093537645,0.0010579772,0.0009179417,0.001458534,0.0017576546],"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":[0.00020990848,0.00010342836,0.012163783,0.00018127437,0.0001435279,0.00018405827,0.00033710455,0.6550602,0.011491308,0.13949043,0.0025253287,0.17810969],"study_design_scores_gemma":[0.000017918559,0.0001447477,0.0042013093,0.00003221492,0.000040386065,0.00021404344,0.000031712272,0.9629385,0.0009856789,0.026291205,0.0050470172,0.00005524418],"about_ca_topic_score_codex":0.0053420095,"about_ca_topic_score_gemma":0.0056658285,"teacher_disagreement_score":0.0053420095,"about_ca_system_score_codex":0.00052999856,"about_ca_system_score_gemma":0.0011447552,"threshold_uncertainty_score":0.015648246},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98228776,0.00006024352,0.015818333,0.0002200672,0.00000898169,0.000025431904,0.0003658236,0.000056210087,0.0011570578],"genre_scores_gemma":[0.9958332,0.00006776176,0.0024143038,0.00001916112,0.000008536616,0.000028817458,0.00048869476,0.000018128723,0.0011213897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969983,0.00013203664,0.000011193687,0.00006094838,0.000025380908,0.00007061153],"domain_scores_gemma":[0.99804497,0.0011403286,0.00036665087,0.00014886232,0.00016446724,0.00013469833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014919803,0.00044847184,0.00043444804,0.0009215644,0.0005599524,0.0012631322,0.0014984873,0.001206287,0.0016796077],"category_scores_gemma":[0.004396386,0.0004420181,0.0009337461,0.0011547743,0.00085293275,0.0009587589,0.0012488794,0.0011636086,0.00019908533],"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":[0.00015644767,0.00009533513,0.06083587,0.000014952083,0.000077968034,0.00013755688,0.0001843476,0.9290716,0.00064735586,0.0047435313,0.0005118965,0.0035232229],"study_design_scores_gemma":[0.00001055718,0.000019793599,0.008550024,0.0000027077137,0.000012465892,0.000012815907,0.000071018454,0.9893622,0.00010563097,0.0017040708,0.0001398861,0.000008905497],"about_ca_topic_score_codex":0.03577428,"about_ca_topic_score_gemma":0.024116782,"teacher_disagreement_score":0.03577428,"about_ca_system_score_codex":0.001315404,"about_ca_system_score_gemma":0.00057735416,"threshold_uncertainty_score":0.07113212},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029589448,0.00015214233,0.99628204,0.00017204539,0.000013481369,0.000020071882,0.000051705356,0.000098936056,0.00025068843],"genre_scores_gemma":[0.31704915,0.0009855228,0.6762179,0.0007412715,0.00028836128,0.0006031163,0.00087861763,0.00017433158,0.0030617134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99672526,0.0019370811,0.00012262125,0.00045026097,0.00060539966,0.0001594519],"domain_scores_gemma":[0.9753381,0.020134265,0.0012648164,0.0019153013,0.0010624115,0.00028505275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065265168,0.0010343046,0.0019465338,0.0015275665,0.0006950029,0.0011997769,0.0019212553,0.0013959078,0.002477596],"category_scores_gemma":[0.039575648,0.0008090432,0.0011806086,0.0016967697,0.0025952207,0.0029187473,0.002691321,0.0028141967,0.0006549016],"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":[0.00033095747,0.00016115925,0.0050130775,0.0006084509,0.00037724004,0.0005141394,0.00028134402,0.4327563,0.0059315995,0.37801656,0.0074499114,0.16855937],"study_design_scores_gemma":[0.000027567423,0.000053159194,0.0006416189,0.0000303139,0.000022361472,0.0001108993,0.000016283637,0.8799009,0.0008737188,0.11698988,0.0013031968,0.000030130966],"about_ca_topic_score_codex":0.0013869373,"about_ca_topic_score_gemma":0.0015324856,"teacher_disagreement_score":0.0065265168,"about_ca_system_score_codex":0.00059879146,"about_ca_system_score_gemma":0.0015080529,"threshold_uncertainty_score":0.034515917},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19795756,0.0002707475,0.7953365,0.00067235396,0.00014076506,0.00014639065,0.00043005295,0.00038957736,0.0046560424],"genre_scores_gemma":[0.8978931,0.000085262895,0.098243654,0.00016548012,0.00014543555,0.00022887098,0.00084597967,0.00006525591,0.0023269954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97757316,0.01427674,0.00078593916,0.0016899897,0.0048069255,0.00086735125],"domain_scores_gemma":[0.91590476,0.06700128,0.005227384,0.005251263,0.0046987473,0.0019165019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019088326,0.000667811,0.0022182865,0.003492935,0.0010382838,0.002000618,0.0031164996,0.0018420509,0.016615773],"category_scores_gemma":[0.09800181,0.00040478428,0.0010615921,0.0026991796,0.004140532,0.0031206538,0.0037608214,0.0025958885,0.0010187242],"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":[0.0028061192,0.00068309077,0.07528125,0.00048170143,0.0007653026,0.0013899169,0.00035194753,0.07431139,0.0070327306,0.5115958,0.006400599,0.31890023],"study_design_scores_gemma":[0.0005057791,0.0013227486,0.01891122,0.00013108618,0.00016571904,0.0011073258,0.00030787854,0.5875305,0.008399427,0.37695724,0.004462961,0.0001980784],"about_ca_topic_score_codex":0.00059924705,"about_ca_topic_score_gemma":0.000766353,"teacher_disagreement_score":0.019088326,"about_ca_system_score_codex":0.0009091565,"about_ca_system_score_gemma":0.0020126663,"threshold_uncertainty_score":0.10094994},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9873148,0.0022354014,0.001854201,0.0037284931,0.000092941584,0.000082731625,0.0005453148,0.000035413264,0.004110674],"genre_scores_gemma":[0.9986975,0.0002606223,0.0004266002,0.00017448996,0.00006253701,0.000018639119,0.000085838445,0.000002909191,0.00027081804],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99475753,0.0017899588,0.00044525927,0.0010903773,0.0012201525,0.00069673953],"domain_scores_gemma":[0.93479186,0.0336965,0.02494683,0.0033594046,0.0020041554,0.0012012817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008148472,0.00026688445,0.0007880473,0.00062472327,0.0003802621,0.0013150157,0.000953982,0.0017310039,0.004032359],"category_scores_gemma":[0.06317197,0.00016147958,0.0006941887,0.0009745047,0.0010298869,0.0014712042,0.00047982958,0.0008942151,0.0003589412],"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":[0.0017801102,0.0010701154,0.7619256,0.00044794296,0.00092488213,0.00019236853,0.0007828934,0.002847922,0.0016663207,0.0031535863,0.0024415865,0.22276671],"study_design_scores_gemma":[0.00014581897,0.0010842672,0.9892837,0.00008626446,0.00034980747,0.00012394604,0.0007929684,0.0028804939,0.00050227455,0.0018058008,0.0029329467,0.000011654291],"about_ca_topic_score_codex":0.005695102,"about_ca_topic_score_gemma":0.009201859,"teacher_disagreement_score":0.008148472,"about_ca_system_score_codex":0.0012767919,"about_ca_system_score_gemma":0.0010812676,"threshold_uncertainty_score":0.0430938},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078447625,0.0038032064,0.5592264,0.025053931,0.0058656707,0.0005484661,0.0036521174,0.007818668,0.31558403],"genre_scores_gemma":[0.670423,0.0052000005,0.13845006,0.008852444,0.0008796508,0.00065392733,0.0037904095,0.0041634412,0.16758706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9962607,0.001009333,0.0001791158,0.001087162,0.0009689541,0.0004946692],"domain_scores_gemma":[0.9887383,0.0031765406,0.00090772,0.0037344294,0.00300353,0.00043960786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043667876,0.0012105838,0.0010074102,0.0014756761,0.0024008902,0.0071937027,0.0017988519,0.0023719866,0.05118444],"category_scores_gemma":[0.038103115,0.00088666455,0.0012457703,0.0018992751,0.0024052283,0.010799865,0.0055611474,0.0033808805,0.036427803],"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":[0.00042530315,0.00018111515,0.015628537,0.00063956657,0.0002117467,0.0010946892,0.002812344,0.014652997,0.004086169,0.64034885,0.0907723,0.22914648],"study_design_scores_gemma":[0.00009717188,0.00015567492,0.002957733,0.0004574722,0.00015833817,0.00087545015,0.0031986304,0.037065443,0.0054648006,0.5463011,0.40310135,0.00016678545],"about_ca_topic_score_codex":0.0100556575,"about_ca_topic_score_gemma":0.0076260944,"teacher_disagreement_score":0.05118444,"about_ca_system_score_codex":0.0013677992,"about_ca_system_score_gemma":0.0035519504,"threshold_uncertainty_score":0.171229},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015712016,0.00023041818,0.99762386,0.00006569749,0.000020644537,0.000021833443,0.000033482556,0.00007710802,0.00035563819],"genre_scores_gemma":[0.08349953,0.0010518859,0.91323453,0.00013698895,0.0002643998,0.00038634992,0.00023237847,0.00016563527,0.0010282493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942543,0.0038282701,0.00021477383,0.00061971095,0.0008976245,0.00018531797],"domain_scores_gemma":[0.98427975,0.010549868,0.0015908466,0.0020542622,0.0013826161,0.00014268681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009147506,0.0014776996,0.0013942616,0.0023906184,0.00063484843,0.0017008155,0.0017562613,0.0014123745,0.0026908733],"category_scores_gemma":[0.044366915,0.00063932606,0.0018297395,0.003712782,0.0016267861,0.002577918,0.0021040235,0.0023650886,0.001299329],"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":[0.000117747644,0.000094197836,0.0027397338,0.00045294504,0.000468299,0.00019892638,0.00018863873,0.24291201,0.006279329,0.47168308,0.0042528827,0.2706122],"study_design_scores_gemma":[0.000024662877,0.00009016764,0.0013881273,0.00007391257,0.0000648672,0.00013647927,0.00003547081,0.738165,0.003090543,0.24982719,0.0070358375,0.00006770888],"about_ca_topic_score_codex":0.0013789363,"about_ca_topic_score_gemma":0.0010663276,"teacher_disagreement_score":0.009147506,"about_ca_system_score_codex":0.0005155364,"about_ca_system_score_gemma":0.0011232697,"threshold_uncertainty_score":0.048377216},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028713613,0.00007087948,0.9964612,0.00009900047,0.000012116525,0.000035310615,0.000026871663,0.00027205446,0.00015117986],"genre_scores_gemma":[0.10814015,0.00022184014,0.8889586,0.00020521515,0.000057243393,0.0003601817,0.00027875186,0.00042262484,0.0013554047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931397,0.004484363,0.0002649678,0.00082667003,0.0010757833,0.0002085313],"domain_scores_gemma":[0.97043353,0.022872144,0.0018423722,0.002099344,0.0023790838,0.00037348122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01547959,0.0016846034,0.0022760862,0.002295292,0.0009771009,0.0015955763,0.0031297691,0.0028836464,0.003374365],"category_scores_gemma":[0.08460176,0.001211007,0.002846084,0.0022626927,0.0020941563,0.0031240229,0.0034384504,0.0042829583,0.0011891922],"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":[0.00023251517,0.00022208327,0.009162456,0.00036517033,0.0004999187,0.0005429416,0.0008203828,0.66328734,0.004073418,0.13958749,0.0035436233,0.17766267],"study_design_scores_gemma":[0.000018274191,0.000050752544,0.00044514626,0.000025933137,0.000017249926,0.0000956487,0.00003337973,0.95897436,0.00045583645,0.03882158,0.0010315486,0.00003019544],"about_ca_topic_score_codex":0.004402568,"about_ca_topic_score_gemma":0.0045894063,"teacher_disagreement_score":0.01547959,"about_ca_system_score_codex":0.00090179,"about_ca_system_score_gemma":0.0017031514,"threshold_uncertainty_score":0.08186489},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029264654,0.0013013771,0.99106055,0.0003853498,0.00005892302,0.000014957779,0.00010997943,0.0002081678,0.0039341906],"genre_scores_gemma":[0.4280931,0.014985987,0.5208354,0.0009621483,0.0010266218,0.00036046584,0.0011398786,0.00066881237,0.031927623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979091,0.0009890753,0.000103861355,0.0003633549,0.00052554545,0.00010902788],"domain_scores_gemma":[0.99209917,0.0051618433,0.00068593887,0.00060858973,0.0012595832,0.00018487644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033448155,0.0012144066,0.0011694996,0.0020188256,0.0005070647,0.0014503408,0.0020061515,0.0016130566,0.0070031555],"category_scores_gemma":[0.016523201,0.00063839025,0.0014353982,0.0033112422,0.001536989,0.002133313,0.0017994171,0.0026647104,0.0021256488],"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":[0.000041129897,0.000058764013,0.002665023,0.00027714352,0.000096659736,0.00024357378,0.00018931592,0.35909376,0.0013306055,0.5489395,0.004577967,0.08248652],"study_design_scores_gemma":[0.000011647169,0.000036782552,0.0005759307,0.00004906008,0.000016522547,0.00013365985,0.00003514746,0.7418436,0.00033584755,0.24581914,0.011115773,0.000026925041],"about_ca_topic_score_codex":0.0061323815,"about_ca_topic_score_gemma":0.0033147612,"teacher_disagreement_score":0.0070031555,"about_ca_system_score_codex":0.001374044,"about_ca_system_score_gemma":0.0009217523,"threshold_uncertainty_score":0.023427904},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036105722,0.00026143252,0.96169525,0.00020718524,0.000057586723,0.00007143454,0.00016970823,0.00009893784,0.0013327337],"genre_scores_gemma":[0.6820809,0.0005088849,0.31135106,0.00029948086,0.00022237895,0.00056327885,0.0009453535,0.000050275838,0.003978326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9847179,0.010834779,0.0003620859,0.0023385184,0.0012074988,0.0005391808],"domain_scores_gemma":[0.9691451,0.020585816,0.0034874117,0.004187922,0.0020668479,0.00052682677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019163214,0.00090753764,0.0019627353,0.0023504705,0.0007378335,0.0021558017,0.0020504254,0.0017408867,0.0053047147],"category_scores_gemma":[0.07385922,0.0010717823,0.0013203796,0.0018412197,0.0022290684,0.002762639,0.0028931566,0.0018140975,0.00055821176],"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":[0.0013249582,0.00024858548,0.030512076,0.00037551182,0.0006893645,0.0002538648,0.0008042714,0.13554747,0.0019184884,0.62081933,0.0046043284,0.20290181],"study_design_scores_gemma":[0.00024422994,0.00028291222,0.0073315753,0.00015481953,0.0001747174,0.00016639833,0.00020834256,0.58756375,0.0016662154,0.39556053,0.0065849777,0.000061485305],"about_ca_topic_score_codex":0.005414067,"about_ca_topic_score_gemma":0.0034684138,"teacher_disagreement_score":0.019163214,"about_ca_system_score_codex":0.0014265453,"about_ca_system_score_gemma":0.0011269507,"threshold_uncertainty_score":0.10134596},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1807276,0.0005427323,0.815339,0.00084270525,0.000046108446,0.00008792338,0.00014840093,0.0003196342,0.0019459155],"genre_scores_gemma":[0.88413405,0.0003000354,0.11394954,0.00027074706,0.00015788997,0.00020122784,0.00045023902,0.00007885443,0.0004574651],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9660463,0.024796208,0.0015854082,0.0037514784,0.0028991585,0.00092139497],"domain_scores_gemma":[0.68118185,0.2934195,0.010418101,0.0088539785,0.0045063333,0.001620209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036374927,0.0009374419,0.002896252,0.0030946867,0.00081007153,0.0022905588,0.0020340532,0.0021134838,0.0014783252],"category_scores_gemma":[0.21190643,0.0009084468,0.001094632,0.0024212939,0.005391293,0.00460129,0.003731908,0.0024185013,0.0003122048],"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":[0.002186764,0.00052157365,0.07625025,0.00073592475,0.0014851607,0.0014881436,0.00075336953,0.30435604,0.0060942676,0.36508152,0.0023674816,0.23867947],"study_design_scores_gemma":[0.00023422323,0.0006655513,0.012146209,0.00006880616,0.00013397117,0.00036879492,0.00027390695,0.55630517,0.0038276191,0.4250929,0.00079524936,0.0000874962],"about_ca_topic_score_codex":0.0005141689,"about_ca_topic_score_gemma":0.0004116952,"teacher_disagreement_score":0.036374927,"about_ca_system_score_codex":0.00094833935,"about_ca_system_score_gemma":0.0020925894,"threshold_uncertainty_score":0.19237131},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051614814,0.0010606459,0.94378877,0.0014026053,0.00008297509,0.00021543664,0.00031202027,0.00027455037,0.0012482372],"genre_scores_gemma":[0.7122968,0.0014412086,0.27937275,0.0015355154,0.00038953943,0.00077603303,0.0008501234,0.0001778107,0.0031601435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95918643,0.031639695,0.0018884985,0.003463162,0.0029085951,0.000913615],"domain_scores_gemma":[0.6470135,0.30067307,0.021598311,0.02550073,0.004431264,0.0007830965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.091926254,0.0008049173,0.0018126399,0.0015376081,0.0010432056,0.0018839837,0.0028127118,0.002159067,0.0027861535],"category_scores_gemma":[0.34716612,0.00079297874,0.0018603358,0.0023184195,0.0033196125,0.0034197485,0.0028273345,0.0024057867,0.000476572],"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":[0.00125919,0.00018120235,0.2025598,0.0012566779,0.0019802419,0.0015580776,0.0043787393,0.11070688,0.0056520184,0.4742247,0.004929031,0.19131342],"study_design_scores_gemma":[0.0003260644,0.00038035307,0.05647702,0.00037668514,0.00070487097,0.0017457872,0.00052547327,0.39477804,0.006626685,0.53121966,0.006662767,0.00017654928],"about_ca_topic_score_codex":0.0042780805,"about_ca_topic_score_gemma":0.0033268316,"teacher_disagreement_score":0.9080737,"about_ca_system_score_codex":0.001635581,"about_ca_system_score_gemma":0.0016651581,"threshold_uncertainty_score":0.4861583},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12026788,0.00041169717,0.870218,0.0015808032,0.00009607827,0.00012360081,0.00064838334,0.00021946275,0.0064341705],"genre_scores_gemma":[0.7615336,0.00041425478,0.23434575,0.00093490834,0.00026626533,0.00023977195,0.0008083056,0.00006137099,0.0013957546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9677459,0.020373043,0.0019566524,0.0036681497,0.005116744,0.0011394564],"domain_scores_gemma":[0.8414466,0.13339366,0.008964418,0.011915785,0.0033451025,0.0009344226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023577526,0.0007860022,0.0019076695,0.0017973309,0.0010999747,0.0028059524,0.001577498,0.0018358522,0.0021263873],"category_scores_gemma":[0.16419722,0.0007828955,0.0011973936,0.0024977042,0.0028198494,0.0047762967,0.0029880917,0.003233325,0.00034343734],"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":[0.0006484237,0.00020643635,0.028980006,0.0005846815,0.00058677566,0.0017509477,0.00090594613,0.108371876,0.005045522,0.7178092,0.0029241578,0.13218616],"study_design_scores_gemma":[0.000119556535,0.00009502652,0.006594899,0.00009632654,0.000104544924,0.0004985134,0.00020299699,0.19164602,0.0025295652,0.79474914,0.003309915,0.00005353879],"about_ca_topic_score_codex":0.0043571,"about_ca_topic_score_gemma":0.0038618224,"teacher_disagreement_score":0.023577526,"about_ca_system_score_codex":0.0017661687,"about_ca_system_score_gemma":0.003368509,"threshold_uncertainty_score":0.12469137},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002675582,0.00008129968,0.9969163,0.00003235195,0.0000074357977,0.000057755045,0.000014605563,0.00003308957,0.00018151893],"genre_scores_gemma":[0.0892787,0.00019901842,0.9090187,0.0000746497,0.00002445298,0.0009401533,0.000067313995,0.000039593862,0.00035746905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9631375,0.031649783,0.0007631992,0.0017684373,0.0023626084,0.00031845353],"domain_scores_gemma":[0.943679,0.04625941,0.0040164758,0.003505831,0.0022195254,0.0003197243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040264744,0.0013346628,0.0025735118,0.00121308,0.00038540628,0.001305493,0.0020543917,0.0015111163,0.0020927219],"category_scores_gemma":[0.06730449,0.001082026,0.0013861365,0.0010635641,0.0026580011,0.0018099146,0.0019552007,0.0023425082,0.00035508486],"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":[0.0010177591,0.00032783885,0.0010934889,0.00068342505,0.00028630564,0.00009716333,0.00033317835,0.57086,0.008316382,0.32687804,0.0005253867,0.08958105],"study_design_scores_gemma":[0.0002256614,0.00090044196,0.00049904897,0.00010996694,0.00005780152,0.000038044353,0.000031119733,0.8131369,0.0049995175,0.17798917,0.001956476,0.000055927812],"about_ca_topic_score_codex":0.00029083746,"about_ca_topic_score_gemma":0.0002592319,"teacher_disagreement_score":0.040264744,"about_ca_system_score_codex":0.0010557581,"about_ca_system_score_gemma":0.001584357,"threshold_uncertainty_score":0.21294284},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08864982,0.0004187295,0.9082873,0.0003738256,0.00008248529,0.00014301276,0.00029706984,0.0010243658,0.0007233755],"genre_scores_gemma":[0.7364685,0.00017588281,0.2595555,0.00030504403,0.00017344688,0.00022097497,0.0013157383,0.00013680391,0.0016481704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682945,0.00124829,0.0001857363,0.00052384206,0.0009067171,0.00030595475],"domain_scores_gemma":[0.98890847,0.005717727,0.0008266508,0.0012466761,0.0030206977,0.00027979133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007242858,0.00094578444,0.001528973,0.0022444713,0.00088785193,0.0010667075,0.0020179574,0.001504642,0.001386359],"category_scores_gemma":[0.017495496,0.00039668978,0.0012300308,0.0015718356,0.0007840116,0.0012051607,0.0012962562,0.0017422887,0.0004727244],"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":[0.00063083466,0.00025471134,0.022155164,0.00016015998,0.00028782507,0.00016580992,0.00025223917,0.4447838,0.0076675694,0.009590085,0.007256823,0.506795],"study_design_scores_gemma":[0.000020253827,0.000026366415,0.0013682154,0.000010222164,0.00001988132,0.000014484272,0.000008545191,0.99344444,0.0009774545,0.0037601893,0.00033710856,0.000012877431],"about_ca_topic_score_codex":0.014529432,"about_ca_topic_score_gemma":0.011286233,"teacher_disagreement_score":0.014529432,"about_ca_system_score_codex":0.0012025704,"about_ca_system_score_gemma":0.0023215164,"threshold_uncertainty_score":0.03830433},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025811347,0.00035402036,0.9955059,0.0002660379,0.00003082469,0.00008868358,0.00022229848,0.00080068794,0.00015036592],"genre_scores_gemma":[0.06749653,0.00056058203,0.9273865,0.00033733173,0.00018160771,0.0010558777,0.0017828315,0.0004885657,0.00071019545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9798647,0.015838226,0.00079706457,0.001608636,0.0015603594,0.00033100593],"domain_scores_gemma":[0.92331034,0.06478028,0.0025474392,0.0064198766,0.0024687368,0.0004733955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037371036,0.0030045472,0.0041664895,0.0032152187,0.0016144064,0.0024677988,0.004096329,0.0025072491,0.0034537665],"category_scores_gemma":[0.10045173,0.0018538313,0.0038169606,0.004135635,0.0014468404,0.003215761,0.0041002817,0.0048472607,0.0018603117],"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":[0.0004950341,0.00016767977,0.004779074,0.00085148885,0.0012377105,0.0007815826,0.00024643558,0.7057642,0.0023951633,0.0504166,0.011330228,0.22153474],"study_design_scores_gemma":[0.00012818589,0.000071693496,0.0007518289,0.0000487636,0.00008693308,0.00012883446,0.000045578552,0.9190647,0.0010363347,0.07591706,0.0026779023,0.000042120315],"about_ca_topic_score_codex":0.0059781815,"about_ca_topic_score_gemma":0.009091998,"teacher_disagreement_score":0.037371036,"about_ca_system_score_codex":0.0011735092,"about_ca_system_score_gemma":0.0037647288,"threshold_uncertainty_score":0.19763929},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52515435,0.020393362,0.42413023,0.0112382695,0.0034540023,0.00016911318,0.0029356403,0.0011677799,0.011357274],"genre_scores_gemma":[0.92587763,0.0065827775,0.05844453,0.00035837686,0.0011586554,0.00006736043,0.0031775301,0.00006644347,0.004266726],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995919,0.00015551291,0.000029221796,0.000054902383,0.00013183415,0.00003668049],"domain_scores_gemma":[0.9978422,0.0012132553,0.0003168998,0.00015190915,0.00041443465,0.000061311795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022837492,0.0006048575,0.00067708874,0.0010870592,0.0002170569,0.0007033692,0.0005326251,0.0007403222,0.0012861014],"category_scores_gemma":[0.01231257,0.00022016361,0.0005157239,0.0012022903,0.00024988115,0.0016648726,0.0006214023,0.0010854846,0.0004751314],"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":[0.00050354266,0.00025169522,0.047069725,0.00049563,0.00034118936,0.00038750097,0.00020765391,0.3682766,0.0032570616,0.052896783,0.067112096,0.45920047],"study_design_scores_gemma":[0.000025418803,0.000053546944,0.010480864,0.000055035627,0.000058167247,0.00005760203,0.000060464758,0.95572364,0.0023632848,0.022855366,0.008247499,0.000019174006],"about_ca_topic_score_codex":0.0047772033,"about_ca_topic_score_gemma":0.0050106244,"teacher_disagreement_score":0.0047772033,"about_ca_system_score_codex":0.00051392266,"about_ca_system_score_gemma":0.0004419591,"threshold_uncertainty_score":0.012077808},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01410038,0.00021868898,0.98481226,0.00017193618,0.000026976877,0.000020345939,0.00009419951,0.00010606378,0.00044918628],"genre_scores_gemma":[0.64623165,0.0014933698,0.347251,0.00033793622,0.0003298911,0.00039548744,0.0010086199,0.00009203338,0.0028599754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989925,0.00047494282,0.000052392872,0.00024272145,0.0001655829,0.00007190293],"domain_scores_gemma":[0.99702567,0.001981391,0.00047860394,0.0002704248,0.00018296005,0.000060927414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00208863,0.0008120411,0.0008116304,0.00083280413,0.0004197595,0.000932138,0.0009414918,0.00069881586,0.00091280637],"category_scores_gemma":[0.0045337295,0.00044910132,0.0010118898,0.0009828358,0.0010605671,0.0017710667,0.0013379157,0.0018478049,0.00017582971],"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":[0.00006957308,0.00005922417,0.0046178806,0.00008379032,0.00014005593,0.00011774146,0.00019851647,0.854511,0.002271632,0.101331644,0.0012541242,0.035344746],"study_design_scores_gemma":[0.0000042666697,0.000014719344,0.00037865728,0.000005314435,0.0000079512965,0.00001417941,0.000008785132,0.9791916,0.00016390317,0.019580675,0.0006215065,0.000008466775],"about_ca_topic_score_codex":0.0038278424,"about_ca_topic_score_gemma":0.0035875072,"teacher_disagreement_score":0.0038278424,"about_ca_system_score_codex":0.0006040452,"about_ca_system_score_gemma":0.0008105252,"threshold_uncertainty_score":0.011045873},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038152393,0.00019888603,0.99525154,0.00013529441,0.000014379885,0.000045878347,0.00010795894,0.000091436414,0.00033944362],"genre_scores_gemma":[0.16378845,0.0019855772,0.8238494,0.00022658653,0.00024129581,0.0012918093,0.0020223383,0.00026717316,0.006327346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949189,0.0032537198,0.0002766052,0.0005441887,0.0008086846,0.00019792869],"domain_scores_gemma":[0.96806127,0.024854654,0.0019940163,0.0019076237,0.0028656102,0.000316812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013568051,0.001451178,0.002289881,0.0016112914,0.00044437675,0.0018937242,0.0026948892,0.001810977,0.0045023873],"category_scores_gemma":[0.05292371,0.00085737073,0.0019664753,0.0025511237,0.001519297,0.003534141,0.0035119338,0.004066465,0.0013474053],"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":[0.000108971195,0.00007718443,0.0042326823,0.00028498413,0.00018455942,0.00026614944,0.00041643358,0.34808335,0.0011098081,0.5312783,0.0036554148,0.11030226],"study_design_scores_gemma":[0.000056286797,0.000046896363,0.0011191245,0.00004648453,0.000050019753,0.00011207201,0.000026624664,0.82017505,0.0003570674,0.17504509,0.0029271496,0.00003808468],"about_ca_topic_score_codex":0.0045018406,"about_ca_topic_score_gemma":0.003986526,"teacher_disagreement_score":0.013568051,"about_ca_system_score_codex":0.0012893364,"about_ca_system_score_gemma":0.002496615,"threshold_uncertainty_score":0.07175559},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048713037,0.00006014436,0.9945803,0.00012798265,0.000011126129,0.000018949302,0.00003114974,0.00016574208,0.00013327903],"genre_scores_gemma":[0.20386833,0.00045012808,0.7929554,0.00033235707,0.00014418748,0.0003154295,0.00027103839,0.00014122346,0.001521828],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987483,0.0007202723,0.00006273343,0.00017344297,0.00024046254,0.000054691765],"domain_scores_gemma":[0.9919126,0.006207478,0.0006819476,0.0005822008,0.00042293835,0.00019278521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004710987,0.0006112541,0.00075931376,0.0006959039,0.00028696266,0.0005162201,0.0013177752,0.00087535096,0.0010511291],"category_scores_gemma":[0.013786122,0.00040412304,0.00113805,0.00095276843,0.0008171682,0.00072664855,0.0012584014,0.0020287856,0.00029112902],"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":[0.00013057918,0.00019607699,0.0069699506,0.00014678948,0.0002605136,0.0003117935,0.00015420155,0.74420524,0.011283768,0.059770424,0.0019158409,0.17465475],"study_design_scores_gemma":[0.0000069201337,0.000044426444,0.0004945722,0.000004108741,0.0000072705475,0.000029811972,0.000003425293,0.983914,0.0005799547,0.014393922,0.0005105369,0.000011051194],"about_ca_topic_score_codex":0.0047464655,"about_ca_topic_score_gemma":0.005745475,"teacher_disagreement_score":0.0047464655,"about_ca_system_score_codex":0.00066062156,"about_ca_system_score_gemma":0.0014067495,"threshold_uncertainty_score":0.024914384},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087534986,0.00004411805,0.9979261,0.00003414977,0.000020607884,0.00023140444,0.00005653956,0.00050703005,0.00030472124],"genre_scores_gemma":[0.009634135,0.000054234737,0.9883652,0.000031057516,0.000031501953,0.00094738725,0.00025755604,0.000138732,0.00054019823],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98901117,0.005703539,0.0010737992,0.0014576836,0.0022253734,0.000528412],"domain_scores_gemma":[0.97125006,0.01815551,0.0016748669,0.003997967,0.004454673,0.00046687422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016871857,0.0019409338,0.0022931723,0.0046500904,0.001600414,0.002616149,0.004399672,0.0019306992,0.015770648],"category_scores_gemma":[0.074103706,0.0018632608,0.0025420163,0.004755518,0.0009657987,0.002510711,0.0047931876,0.0030973444,0.006765091],"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":[0.0003804794,0.00028371354,0.0046060015,0.00035247774,0.0003272526,0.000118853335,0.0005147405,0.100745894,0.0023974336,0.070486695,0.0076947217,0.81209177],"study_design_scores_gemma":[0.00054678076,0.0002555509,0.0022606486,0.0001637151,0.00021188874,0.000277534,0.00027971517,0.69210505,0.0050059594,0.28194827,0.016824074,0.000120874225],"about_ca_topic_score_codex":0.003509852,"about_ca_topic_score_gemma":0.003960327,"teacher_disagreement_score":0.016871857,"about_ca_system_score_codex":0.0018440448,"about_ca_system_score_gemma":0.0049928734,"threshold_uncertainty_score":0.089227974},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013160467,0.00010578489,0.99794465,0.000219692,0.00001840074,0.000055860048,0.000051103183,0.00007001671,0.00021840371],"genre_scores_gemma":[0.051795613,0.0003036678,0.9455339,0.00030240344,0.00008926677,0.0011472027,0.00031404404,0.000104442675,0.00040960708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.882992,0.103394195,0.0032735667,0.0048875185,0.0048182462,0.0006344749],"domain_scores_gemma":[0.56050026,0.39341488,0.01121588,0.02868749,0.0055080624,0.0006735229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09822444,0.0020877079,0.0037113624,0.0044264654,0.002241716,0.0046475753,0.006336994,0.0040026857,0.0035245756],"category_scores_gemma":[0.40062046,0.00202444,0.0052115973,0.0054955985,0.008031869,0.008153896,0.009625861,0.008515417,0.00083331333],"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":[0.00013580926,0.000080192825,0.0046505188,0.0004650015,0.00045105608,0.00031387212,0.0009292871,0.050482098,0.00047567475,0.8571988,0.0015816438,0.083236024],"study_design_scores_gemma":[0.00008967384,0.00006739783,0.00057699706,0.00016645937,0.00010906236,0.00021835626,0.0000985644,0.2293388,0.00090994354,0.764832,0.0035368132,0.00005598058],"about_ca_topic_score_codex":0.0032242064,"about_ca_topic_score_gemma":0.0025152876,"teacher_disagreement_score":0.09822444,"about_ca_system_score_codex":0.0025789973,"about_ca_system_score_gemma":0.0041216584,"threshold_uncertainty_score":0.5194667},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8528714,0.002095028,0.13899727,0.0029193785,0.00013519572,0.00006619201,0.0003891721,0.00053503545,0.001991167],"genre_scores_gemma":[0.9668394,0.0004494751,0.031781398,0.00017808453,0.000068242065,0.000026348203,0.0003189929,0.000017982933,0.00032011408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855417,0.0009809933,0.00006296156,0.00012823936,0.00018722423,0.00008641905],"domain_scores_gemma":[0.9822833,0.01515658,0.00065908604,0.000972836,0.0007486197,0.00017959857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063147624,0.0008772581,0.0013652699,0.0011690836,0.00081597955,0.0012379928,0.00084830995,0.0015464954,0.0006544515],"category_scores_gemma":[0.023763794,0.00028994904,0.0005344982,0.0026796027,0.0005843769,0.0022905641,0.0007077702,0.0017899736,0.00020196164],"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":[0.0010016816,0.0006332709,0.06576928,0.00017365346,0.00029335215,0.00030915404,0.00037174454,0.6476197,0.0013445026,0.0062947758,0.0037179133,0.27247095],"study_design_scores_gemma":[0.0000366263,0.00017890736,0.011447403,0.000031464522,0.000065518434,0.00007590587,0.00024157988,0.9757957,0.0009865642,0.010204145,0.0009020482,0.000034287797],"about_ca_topic_score_codex":0.011463505,"about_ca_topic_score_gemma":0.011468986,"teacher_disagreement_score":0.011463505,"about_ca_system_score_codex":0.00049368216,"about_ca_system_score_gemma":0.0006393026,"threshold_uncertainty_score":0.033396065},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72923803,0.005139922,0.24842693,0.0029465617,0.00013117422,0.0005445489,0.008419613,0.00058891904,0.004564351],"genre_scores_gemma":[0.9061743,0.0027371044,0.0836054,0.00020263462,0.00004550172,0.00015963022,0.0053112702,0.00003310469,0.0017309503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99832326,0.0006888843,0.00010926959,0.0002550348,0.00044433112,0.00017911385],"domain_scores_gemma":[0.9884614,0.007168756,0.0010069842,0.0011436836,0.0019727,0.0002465267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009206256,0.0006259248,0.00055064494,0.0022636596,0.0010457808,0.0011626098,0.00163103,0.00070001563,0.0010181299],"category_scores_gemma":[0.04098914,0.00035015322,0.0009624266,0.0028855435,0.00082607777,0.00073532335,0.0010531247,0.0009591523,0.0001398989],"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":[0.0002973997,0.00014197319,0.54799527,0.00034325756,0.0011850446,0.00040842383,0.0008143536,0.27128202,0.00046846838,0.037756737,0.0059037227,0.13340332],"study_design_scores_gemma":[0.00012076267,0.000115246614,0.26627448,0.00023010984,0.0005021469,0.00031607444,0.00095723924,0.69369084,0.000841109,0.026193025,0.010630725,0.00012822918],"about_ca_topic_score_codex":0.9368196,"about_ca_topic_score_gemma":0.9176738,"teacher_disagreement_score":0.06318039,"about_ca_system_score_codex":0.008152253,"about_ca_system_score_gemma":0.016332442,"threshold_uncertainty_score":0.12710488},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023398109,0.0006095719,0.9735449,0.000503394,0.00004984563,0.000038988663,0.000122125,0.0002556345,0.0014773703],"genre_scores_gemma":[0.685663,0.0011411145,0.30572513,0.00033669267,0.0002125879,0.00031006933,0.00036426168,0.00018309365,0.006064084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9908647,0.0064731366,0.00022349418,0.001022081,0.0010245242,0.00039201186],"domain_scores_gemma":[0.9694101,0.024326704,0.0026914538,0.0018809689,0.0011516656,0.00053902995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014752652,0.0012415164,0.0024106519,0.0019895572,0.00078648725,0.0022459882,0.002392002,0.0022973577,0.0055286908],"category_scores_gemma":[0.04265577,0.0010092696,0.0021608954,0.0026544868,0.002963842,0.0028631778,0.0027923312,0.0039164713,0.0007563243],"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":[0.0003724966,0.0001460987,0.007452515,0.00021107888,0.0005245029,0.0003408091,0.0004139431,0.4335341,0.0015618899,0.49193457,0.0018643907,0.061643686],"study_design_scores_gemma":[0.000056126635,0.00009602836,0.0019722935,0.000054747146,0.00013271769,0.00006397319,0.00003962659,0.6494,0.00026094008,0.345551,0.0023186887,0.000053853677],"about_ca_topic_score_codex":0.008406886,"about_ca_topic_score_gemma":0.006991939,"teacher_disagreement_score":0.014752652,"about_ca_system_score_codex":0.0010699389,"about_ca_system_score_gemma":0.0012919682,"threshold_uncertainty_score":0.07802045},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002438103,0.00016217255,0.99640155,0.00020502896,0.000022100048,0.000027923572,0.000050540788,0.00006647403,0.0006261593],"genre_scores_gemma":[0.36542287,0.0014629713,0.6290347,0.0005271063,0.00029064785,0.00067038176,0.0005577832,0.000083301595,0.0019502228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99128366,0.0067695696,0.00018808187,0.00072037464,0.0008584831,0.00017979738],"domain_scores_gemma":[0.9876165,0.008151803,0.000924327,0.0023469883,0.00083849765,0.00012193898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012892667,0.0010847589,0.0016266389,0.002002771,0.00066811184,0.0015915548,0.0026001686,0.0021262688,0.0026350352],"category_scores_gemma":[0.054783773,0.0008371506,0.0014247416,0.0032566553,0.0020548953,0.0039666947,0.002983389,0.0026486772,0.00050257164],"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":[0.00010298909,0.00014967115,0.0037070313,0.0004092876,0.00038503576,0.00017495961,0.00050552696,0.35809898,0.00096352125,0.50110143,0.0021708915,0.1322307],"study_design_scores_gemma":[0.000060840463,0.00014700307,0.0012252212,0.00009724541,0.0000841247,0.0001910559,0.00008702428,0.59653074,0.0016544447,0.39377618,0.0060762702,0.00006979712],"about_ca_topic_score_codex":0.0013272959,"about_ca_topic_score_gemma":0.0011944853,"teacher_disagreement_score":0.012892667,"about_ca_system_score_codex":0.001079104,"about_ca_system_score_gemma":0.0023185087,"threshold_uncertainty_score":0.06818372},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057984788,0.0007572601,0.93428355,0.0007666824,0.00012132985,0.00014661982,0.0003560299,0.0003196674,0.00526401],"genre_scores_gemma":[0.74703556,0.0010094485,0.24496907,0.0005122862,0.0006381849,0.00055393984,0.000854161,0.00018466431,0.004242654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98031807,0.011158892,0.0009803935,0.0024236378,0.004579037,0.00054001465],"domain_scores_gemma":[0.8586226,0.1153449,0.00943661,0.010252315,0.0052524544,0.0010911465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026610024,0.0011604698,0.00196101,0.0046729916,0.00091220636,0.002169086,0.0030714134,0.001740382,0.0051372834],"category_scores_gemma":[0.13901389,0.000486023,0.0017715117,0.0026471636,0.004062157,0.007264652,0.002587807,0.0032046684,0.00078065495],"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":[0.00049883017,0.00019838045,0.017928295,0.00028673996,0.00047683303,0.00041435362,0.00040302178,0.12437208,0.0016909811,0.7014058,0.0031993706,0.14912525],"study_design_scores_gemma":[0.00016924017,0.0005873286,0.007664096,0.00007855709,0.00013175423,0.00044200104,0.00012261338,0.511937,0.0018510553,0.4717482,0.0050704214,0.00019763174],"about_ca_topic_score_codex":0.0011257393,"about_ca_topic_score_gemma":0.0009107001,"teacher_disagreement_score":0.026610024,"about_ca_system_score_codex":0.0013389151,"about_ca_system_score_gemma":0.0019520685,"threshold_uncertainty_score":0.14072901},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9668297,0.00015387221,0.029994333,0.00010512806,0.000018486084,0.00006639835,0.0008336678,0.00017965517,0.0018188735],"genre_scores_gemma":[0.9973526,0.000022972446,0.0021060968,0.0000043302025,0.0000050495055,0.000019548519,0.00024627475,0.000014762386,0.00022842495],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993339,0.00018739849,0.00006361596,0.00021212928,0.00014499371,0.000057953665],"domain_scores_gemma":[0.9967822,0.001993467,0.00030532174,0.0003349209,0.0004659487,0.00011822378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001470742,0.00040093678,0.0003441182,0.0022486805,0.0002470147,0.0008584936,0.00025734823,0.00033629348,0.0024451052],"category_scores_gemma":[0.009284692,0.00017994923,0.00043116254,0.001632712,0.0006925955,0.00060217356,0.00047349854,0.00030673837,0.00025537235],"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":[0.00077843183,0.00022069452,0.5869604,0.00049807806,0.000982489,0.0010104012,0.002331836,0.08395581,0.06109018,0.014273083,0.0017059174,0.24619277],"study_design_scores_gemma":[0.000008571787,0.00009478385,0.8571032,0.000019478184,0.000053830765,0.00033006677,0.0002459824,0.13358113,0.0020272485,0.0057423096,0.00074460334,0.000048755195],"about_ca_topic_score_codex":0.0043381127,"about_ca_topic_score_gemma":0.002179689,"teacher_disagreement_score":0.0043381127,"about_ca_system_score_codex":0.0005088955,"about_ca_system_score_gemma":0.0003376197,"threshold_uncertainty_score":0.008625746},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14056462,0.0003052,0.85542876,0.00028344375,0.00005026374,0.00010416121,0.00028568096,0.0005336348,0.0024442887],"genre_scores_gemma":[0.898532,0.00012035925,0.10005267,0.00006565892,0.0000476122,0.00011549662,0.00032060774,0.000060815793,0.00068479456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99260193,0.0037272777,0.0003417742,0.0011956922,0.0018051935,0.0003281994],"domain_scores_gemma":[0.9596754,0.02908601,0.004448801,0.0041895527,0.0022549895,0.00034531788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00982831,0.0005643938,0.0010963468,0.0014853857,0.00054107606,0.0010147033,0.0014486023,0.0010592252,0.0018171723],"category_scores_gemma":[0.058835845,0.00032559907,0.0009684764,0.0015652864,0.001341809,0.0014720956,0.0013876251,0.0014821212,0.00039860976],"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":[0.00083996763,0.0006939997,0.046048064,0.00045740054,0.0011886032,0.0013846724,0.00067616184,0.29411617,0.020063,0.23760846,0.004105516,0.39281788],"study_design_scores_gemma":[0.000077705794,0.0003400468,0.01919232,0.00002731752,0.00009715838,0.00039805556,0.00010619391,0.87270147,0.0077909413,0.09797746,0.001211653,0.00007961608],"about_ca_topic_score_codex":0.0014329705,"about_ca_topic_score_gemma":0.0015886908,"teacher_disagreement_score":0.00982831,"about_ca_system_score_codex":0.0005438239,"about_ca_system_score_gemma":0.0013707797,"threshold_uncertainty_score":0.051977694},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97505105,0.0006541476,0.010568599,0.0004812956,0.00006806939,0.00003873446,0.005147768,0.00035971397,0.00763064],"genre_scores_gemma":[0.9935282,0.00023792847,0.0027028185,0.000027038885,0.000025523112,0.0000071530535,0.0024940707,0.0000138901805,0.0009634302],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995521,0.00004153485,0.0000138306905,0.000084405416,0.00022631686,0.00008183531],"domain_scores_gemma":[0.99896634,0.00028098148,0.00016121613,0.000074220436,0.0003994992,0.00011766904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007867755,0.00033981344,0.00037157262,0.0024187532,0.0009612157,0.001052576,0.0006504234,0.00033870712,0.0008240069],"category_scores_gemma":[0.0046685273,0.00015832492,0.00021985275,0.0034956448,0.00035392412,0.0003034521,0.00062283635,0.00057819724,0.00016606602],"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":[0.0010048249,0.0001631891,0.64180136,0.00020330877,0.00028442638,0.0010182126,0.001157986,0.09578159,0.010401459,0.011237729,0.02069864,0.2162473],"study_design_scores_gemma":[0.00004094933,0.000029228682,0.7351835,0.000027461316,0.000050518775,0.00013908645,0.00044110557,0.25320885,0.002660542,0.00158717,0.006558848,0.00007271686],"about_ca_topic_score_codex":0.84990877,"about_ca_topic_score_gemma":0.86511755,"teacher_disagreement_score":0.15009123,"about_ca_system_score_codex":0.0031515004,"about_ca_system_score_gemma":0.0045011886,"threshold_uncertainty_score":0.30195028},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058583408,0.000036309637,0.9937317,0.000037883692,0.0000043388636,0.0000113373735,0.00002277538,0.000043001928,0.00025431425],"genre_scores_gemma":[0.36619753,0.00039436814,0.62914026,0.0001296633,0.000066028835,0.00030624509,0.0005801122,0.00008253613,0.0031031978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969085,0.0021148622,0.00008599806,0.0003791054,0.00040944747,0.000102065635],"domain_scores_gemma":[0.9811034,0.014830034,0.0013214317,0.0018586712,0.00074907695,0.00013735238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009560149,0.0006062626,0.0010801026,0.0010250644,0.0003106028,0.0011161434,0.0019740334,0.00075657666,0.0013918305],"category_scores_gemma":[0.04053445,0.0005307609,0.0006566516,0.0012903658,0.0013714189,0.0025145318,0.00209341,0.0014737066,0.00033391514],"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":[0.00009832901,0.00007602815,0.005222668,0.00021058062,0.00011864408,0.00012030025,0.00028126323,0.5139615,0.0023551155,0.34380117,0.0013883491,0.13236608],"study_design_scores_gemma":[0.000014440232,0.000032041913,0.0009907444,0.000014190472,0.000010745396,0.000048389506,0.000022841894,0.9016089,0.0010433773,0.095256366,0.0009398706,0.000018010105],"about_ca_topic_score_codex":0.000964919,"about_ca_topic_score_gemma":0.0013013727,"teacher_disagreement_score":0.009560149,"about_ca_system_score_codex":0.0006683003,"about_ca_system_score_gemma":0.0011013624,"threshold_uncertainty_score":0.05055952},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017782042,0.00023147732,0.9810954,0.00012417021,0.000019632571,0.000057166173,0.000048859107,0.000048515976,0.000592765],"genre_scores_gemma":[0.4900936,0.0005673457,0.5062121,0.00009683534,0.00011003376,0.00048553105,0.00032430628,0.000034128763,0.0020761304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882359,0.008641567,0.00029356062,0.0014574211,0.0011139823,0.00025750807],"domain_scores_gemma":[0.97145116,0.020812128,0.002850061,0.0026219462,0.0020409145,0.00022375368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017561749,0.00075740844,0.0013373296,0.0015175223,0.0005325094,0.001163965,0.0017607321,0.0011669775,0.0032785283],"category_scores_gemma":[0.06119928,0.00073948485,0.0008964826,0.0017908349,0.0010579928,0.0023241618,0.0019096533,0.0010961466,0.00039678637],"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":[0.00033858398,0.00021023076,0.037660386,0.0005598596,0.0004000896,0.00027069647,0.000868856,0.28688258,0.0027385822,0.3352289,0.0033042715,0.331537],"study_design_scores_gemma":[0.000080289086,0.0002468283,0.009764986,0.00015292615,0.00008054693,0.00022617969,0.00017444856,0.80352986,0.0015894034,0.17729618,0.0068150936,0.000043382],"about_ca_topic_score_codex":0.004394149,"about_ca_topic_score_gemma":0.003685266,"teacher_disagreement_score":0.017561749,"about_ca_system_score_codex":0.0012718502,"about_ca_system_score_gemma":0.00085923745,"threshold_uncertainty_score":0.092876494},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007468359,0.0003418473,0.99832445,0.000079321006,0.000025585885,0.000026810736,0.000051357874,0.00015086528,0.0002528533],"genre_scores_gemma":[0.12441332,0.002821834,0.86773515,0.00028589374,0.0003503588,0.0009951292,0.0009042463,0.00033586397,0.0021581964],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9797513,0.014800688,0.0006302373,0.0020078383,0.002436062,0.00037388393],"domain_scores_gemma":[0.9721452,0.022678476,0.0018761625,0.0015895522,0.001535917,0.0001747403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017142635,0.0026082215,0.0036125756,0.0032301333,0.00075327925,0.0027700064,0.003332834,0.0020641417,0.0027974145],"category_scores_gemma":[0.05977127,0.0011557561,0.0043068146,0.0028843337,0.002184624,0.0018769534,0.0032363955,0.0033469447,0.0008617891],"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":[0.00017247788,0.00006742213,0.0013145843,0.00079377746,0.0013211764,0.00028945634,0.00024670953,0.5667938,0.0021648114,0.27112052,0.003016948,0.15269832],"study_design_scores_gemma":[0.000026457777,0.00007606048,0.00045874808,0.00006400264,0.00010927075,0.00008909077,0.000024145624,0.87678033,0.00084359664,0.117872,0.003602699,0.00005358949],"about_ca_topic_score_codex":0.0031870718,"about_ca_topic_score_gemma":0.002197272,"teacher_disagreement_score":0.017142635,"about_ca_system_score_codex":0.0015950516,"about_ca_system_score_gemma":0.0025549326,"threshold_uncertainty_score":0.090660036},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001704237,0.39841238,0.44041198,0.065365456,0.02317509,0.00028642997,0.003848486,0.0036247442,0.063171215],"genre_scores_gemma":[0.13815182,0.32649654,0.360424,0.039439376,0.081030324,0.0029190066,0.007161337,0.003449974,0.040927652],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98212034,0.009257295,0.0017672827,0.0013430169,0.0050691627,0.00044293827],"domain_scores_gemma":[0.9277218,0.050037406,0.0048489105,0.0083868755,0.007777633,0.0012272693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026177607,0.0025748622,0.002229271,0.008905448,0.0013926685,0.006695372,0.0015943106,0.005004627,0.01491357],"category_scores_gemma":[0.09840858,0.0014022539,0.0016644107,0.0093054045,0.0076803938,0.009070723,0.0040867887,0.013597421,0.0138208],"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":[0.00006881897,0.00004225339,0.0014021375,0.001352663,0.00021983501,0.00016703835,0.00076307444,0.0025850395,0.00034638078,0.4086049,0.41945615,0.16499178],"study_design_scores_gemma":[0.000037011647,0.00006833312,0.0017776869,0.0012319915,0.000085320906,0.00059689325,0.0001860909,0.0025113514,0.00034795445,0.6103523,0.38274068,0.000064423504],"about_ca_topic_score_codex":0.0031708134,"about_ca_topic_score_gemma":0.0019832982,"teacher_disagreement_score":0.026177607,"about_ca_system_score_codex":0.0028723779,"about_ca_system_score_gemma":0.0036944132,"threshold_uncertainty_score":0.13844204},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008218063,0.00031987502,0.9981046,0.00014553264,0.00002585376,0.000086453896,0.00017195016,0.00010689374,0.00021700727],"genre_scores_gemma":[0.028263353,0.0018746449,0.9632667,0.00024190365,0.000119381424,0.002156477,0.0012893392,0.00016916367,0.0026190828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97749215,0.01895285,0.00074611127,0.001319516,0.0011960382,0.0002933725],"domain_scores_gemma":[0.9502816,0.03991207,0.0029245617,0.0047208294,0.001989639,0.00017114823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040624384,0.00236529,0.0027579935,0.0036011776,0.0006038961,0.0014612797,0.00507222,0.0027949854,0.007542885],"category_scores_gemma":[0.11640006,0.0014994879,0.0034116535,0.0048778774,0.0015922224,0.0046702866,0.0024995795,0.00475986,0.003080302],"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":[0.00009603959,0.00008407582,0.0038244394,0.0007063301,0.0011191652,0.00030651793,0.00050654815,0.09852992,0.0006833775,0.70219463,0.008989864,0.18295915],"study_design_scores_gemma":[0.00008936339,0.00011151957,0.0019023845,0.0003374257,0.0003435887,0.00034152466,0.00012392677,0.351539,0.0006373004,0.62716556,0.017301844,0.000106631334],"about_ca_topic_score_codex":0.005295298,"about_ca_topic_score_gemma":0.0073041054,"teacher_disagreement_score":0.040624384,"about_ca_system_score_codex":0.0015893711,"about_ca_system_score_gemma":0.0028675827,"threshold_uncertainty_score":0.21484482},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007777365,0.25454083,0.6848222,0.03542151,0.0023346364,0.000055051612,0.0006537251,0.00038047796,0.014014159],"genre_scores_gemma":[0.4163351,0.24433158,0.28890544,0.00822964,0.014125582,0.0005460044,0.001153976,0.001229467,0.025143115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976286,0.0014614144,0.00012078559,0.00027745776,0.0003802136,0.00013151062],"domain_scores_gemma":[0.98679346,0.0105431145,0.00081328815,0.0004280446,0.0010157003,0.00040631744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075469376,0.0014610766,0.0019361078,0.0037922626,0.0016274444,0.003333618,0.00161,0.002137917,0.0063044094],"category_scores_gemma":[0.024355225,0.001439842,0.0013919843,0.005570958,0.005402453,0.008622678,0.00385907,0.005383763,0.0013341276],"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":[0.00012257387,0.000038314127,0.0024612506,0.00037037092,0.0002036977,0.00023291355,0.0008543235,0.015870769,0.00021842238,0.77804303,0.088433534,0.113150835],"study_design_scores_gemma":[0.000021096232,0.000019391753,0.0011854212,0.00018586412,0.000066541936,0.000105562576,0.00017751202,0.011572568,0.00011198607,0.957413,0.029081544,0.000059438324],"about_ca_topic_score_codex":0.012065869,"about_ca_topic_score_gemma":0.010594569,"teacher_disagreement_score":0.012065869,"about_ca_system_score_codex":0.0030317844,"about_ca_system_score_gemma":0.0016362049,"threshold_uncertainty_score":0.039912462},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088068267,0.00003637328,0.998637,0.000026254615,0.000013905132,0.000030001132,0.0000376566,0.000050659684,0.00028741505],"genre_scores_gemma":[0.04831343,0.0002039603,0.94855887,0.00011572082,0.00014952997,0.0010475903,0.0002949021,0.000081093676,0.0012347981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9851083,0.009445812,0.000560748,0.0016640387,0.0027996036,0.00042149148],"domain_scores_gemma":[0.98215175,0.011112616,0.0013337893,0.0027792512,0.0023043042,0.0003183285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01817694,0.001225819,0.0020230783,0.0023956571,0.0007958403,0.0017171542,0.0027284694,0.001265211,0.0037138031],"category_scores_gemma":[0.045303863,0.0006410185,0.0016518617,0.0027762703,0.002511565,0.0028062593,0.002589486,0.0021843496,0.00074170023],"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":[0.00015668478,0.00011550006,0.0018098981,0.00032741233,0.0002001416,0.00020305408,0.00030814335,0.10464806,0.0046837945,0.68250215,0.0031027168,0.20194241],"study_design_scores_gemma":[0.000060849827,0.00028397597,0.0012094268,0.00004419124,0.00005239578,0.00013671706,0.000051731993,0.45889965,0.0011561824,0.52911896,0.008918606,0.00006726988],"about_ca_topic_score_codex":0.0009473528,"about_ca_topic_score_gemma":0.0011398075,"teacher_disagreement_score":0.01817694,"about_ca_system_score_codex":0.0010718687,"about_ca_system_score_gemma":0.0025255291,"threshold_uncertainty_score":0.09613001},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009773902,0.00019795245,0.99745446,0.00013896848,0.000052597497,0.0003302842,0.00009181559,0.00024211097,0.00051444216],"genre_scores_gemma":[0.027925199,0.00029049517,0.96694285,0.00021821834,0.00016699896,0.0035915282,0.00017094177,0.00015132215,0.0005424822],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9275471,0.05751756,0.0023627882,0.0042676395,0.007731239,0.00057366857],"domain_scores_gemma":[0.699251,0.26770368,0.008731855,0.016710395,0.006816498,0.00078655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.080833904,0.002904903,0.003074035,0.0057383943,0.0013224656,0.001748996,0.004691251,0.0036789898,0.011749162],"category_scores_gemma":[0.27145353,0.0010632499,0.0036571436,0.0035871218,0.0040783994,0.0036368319,0.0034637973,0.0069004456,0.0025742878],"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":[0.0015570375,0.000331619,0.004319659,0.0017641494,0.0018688156,0.0005413926,0.0006078551,0.0516669,0.0065861717,0.3457648,0.008399207,0.5765924],"study_design_scores_gemma":[0.0007527591,0.0032772226,0.003988174,0.0005497071,0.0005775018,0.0008617693,0.00022704802,0.2531806,0.015933715,0.69621533,0.02414039,0.00029577533],"about_ca_topic_score_codex":0.0005657624,"about_ca_topic_score_gemma":0.00053079054,"teacher_disagreement_score":0.080833904,"about_ca_system_score_codex":0.0012473892,"about_ca_system_score_gemma":0.0024883423,"threshold_uncertainty_score":0.42749566},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013344434,0.03671266,0.93212235,0.00632028,0.0015113576,0.0000719544,0.00032864313,0.00038243821,0.009205863],"genre_scores_gemma":[0.4444693,0.09996717,0.39859,0.0042672954,0.014832394,0.0009397275,0.0014669436,0.0007642926,0.034702856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99543506,0.0028754198,0.00023319696,0.00038162377,0.0008695239,0.00020508007],"domain_scores_gemma":[0.94054216,0.050472364,0.0030591823,0.0018654933,0.00296853,0.0010922439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013399006,0.0019187342,0.0038905682,0.0059367674,0.0014508187,0.004318697,0.0037748253,0.005816214,0.006224698],"category_scores_gemma":[0.065843835,0.0021899221,0.0029300791,0.010253948,0.0055197943,0.0068085766,0.0035853395,0.0075247125,0.0013893876],"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":[0.000017123913,0.000031481854,0.0005887514,0.00010253001,0.000052519095,0.00009919805,0.0002128795,0.029826412,0.00008541259,0.95312095,0.0035197483,0.012342965],"study_design_scores_gemma":[0.00001550488,0.000008009258,0.00016141718,0.00003982558,0.000021078957,0.00007509761,0.000049398204,0.10351593,0.000028497481,0.89213985,0.0039206804,0.000024690775],"about_ca_topic_score_codex":0.0069335937,"about_ca_topic_score_gemma":0.0052518365,"teacher_disagreement_score":0.013399006,"about_ca_system_score_codex":0.002784985,"about_ca_system_score_gemma":0.0030395081,"threshold_uncertainty_score":0.07086158},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5123687,0.0019734984,0.4686118,0.0030448444,0.00011341665,0.00007407931,0.0016202668,0.0004288725,0.011764431],"genre_scores_gemma":[0.9466381,0.00058836833,0.050386563,0.00009211321,0.00012275971,0.000089408095,0.0011225641,0.00009539797,0.00086464995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767524,0.0011265061,0.00011400784,0.00037402113,0.00059472997,0.00011540059],"domain_scores_gemma":[0.9843456,0.009922092,0.0024092328,0.001730412,0.001139881,0.00045274943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034399063,0.00037124968,0.0005939048,0.004091278,0.0009982641,0.0026626075,0.0006122531,0.000491481,0.0025239247],"category_scores_gemma":[0.02652614,0.00021511364,0.0005361951,0.0034498707,0.003468702,0.0025801864,0.002548401,0.0011609863,0.00026856732],"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":[0.00039787093,0.000080824866,0.04427773,0.00023554813,0.00019188554,0.00032815227,0.0011293815,0.06285038,0.005241539,0.6672089,0.007582287,0.21047547],"study_design_scores_gemma":[0.000040495845,0.00016148473,0.039697453,0.00009742764,0.00005960849,0.00062448817,0.00093120866,0.20923384,0.0022947132,0.7335328,0.013234355,0.00009211632],"about_ca_topic_score_codex":0.0012114507,"about_ca_topic_score_gemma":0.0012795987,"teacher_disagreement_score":0.004091278,"about_ca_system_score_codex":0.00094914477,"about_ca_system_score_gemma":0.0009933175,"threshold_uncertainty_score":0.018192172},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003342554,0.00011266798,0.9956542,0.00008904309,0.000018282753,0.000023722178,0.000056154167,0.0005142174,0.00018906881],"genre_scores_gemma":[0.283258,0.0005377516,0.7112054,0.00021515961,0.00021712277,0.0003985975,0.0013384949,0.0005527377,0.0022768425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960879,0.002439282,0.00017184774,0.0005180351,0.00060869387,0.00017426952],"domain_scores_gemma":[0.9893602,0.007581705,0.0008442458,0.00089018035,0.0011735692,0.0001501519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005495818,0.0018406021,0.0024200387,0.0015874706,0.0005498354,0.0014660995,0.0018802502,0.0010107466,0.00231458],"category_scores_gemma":[0.02272347,0.00096347986,0.0017330468,0.0016769856,0.00080491573,0.0016423333,0.0015861093,0.00278012,0.0017887418],"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":[0.00018228301,0.00007290941,0.0017911289,0.00011284011,0.00032896933,0.00017355358,0.000046937042,0.87815654,0.002312583,0.01659136,0.002301743,0.09792909],"study_design_scores_gemma":[0.0000124033,0.000024445579,0.000110312445,0.0000051284424,0.0000129466725,0.000012831289,0.0000045399183,0.9937543,0.0005467861,0.0051439926,0.00036206297,0.000010322361],"about_ca_topic_score_codex":0.003432387,"about_ca_topic_score_gemma":0.0029415805,"teacher_disagreement_score":0.005495818,"about_ca_system_score_codex":0.0005007538,"about_ca_system_score_gemma":0.0015908547,"threshold_uncertainty_score":0.029065013},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035812678,0.000047925765,0.995876,0.00007856029,0.000008684289,0.00002367044,0.000013553037,0.00015303999,0.00021735525],"genre_scores_gemma":[0.1457812,0.00012958699,0.8518436,0.00008089387,0.00006967571,0.00025910736,0.00023358359,0.0004292598,0.0011732451],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99115705,0.0054293307,0.00039391953,0.0012048226,0.0015467941,0.00026816825],"domain_scores_gemma":[0.98776776,0.0078163855,0.00087431987,0.0024154792,0.0009806197,0.0001453731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012619506,0.0014069136,0.0023501932,0.0034540256,0.0012663974,0.002796142,0.0021892148,0.002249192,0.0027082285],"category_scores_gemma":[0.037393615,0.0013446439,0.0027034765,0.0035690218,0.003924495,0.003792241,0.0043365373,0.003144837,0.0009813444],"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":[0.00021248705,0.00009952075,0.0026017658,0.00019290476,0.00027748317,0.0001698311,0.00038897272,0.537628,0.006513679,0.20369822,0.0014243914,0.2467928],"study_design_scores_gemma":[0.000014896148,0.000047391262,0.00045539826,0.000013776435,0.000017445383,0.000052975014,0.000032454114,0.8886695,0.0021112529,0.10688958,0.0016686189,0.00002665436],"about_ca_topic_score_codex":0.0034334753,"about_ca_topic_score_gemma":0.003075054,"teacher_disagreement_score":0.012619506,"about_ca_system_score_codex":0.0015845689,"about_ca_system_score_gemma":0.0017415864,"threshold_uncertainty_score":0.06673914},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001074754,0.00006985549,0.99814725,0.00006765585,0.000015731872,0.00006647369,0.000048605874,0.00027791457,0.00023186023],"genre_scores_gemma":[0.04274893,0.00017665212,0.9538771,0.00011160675,0.000045257908,0.00090337696,0.00024446906,0.00034265342,0.001549977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97465193,0.020488376,0.00059530337,0.0026897541,0.0012941168,0.00028046433],"domain_scores_gemma":[0.9664809,0.02737028,0.0010726423,0.0034912731,0.0013450548,0.00023992342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024035666,0.002479264,0.0031630835,0.00207027,0.0011837386,0.0021472464,0.0050221337,0.0025126499,0.009599628],"category_scores_gemma":[0.056100708,0.0016853156,0.0049132253,0.0031120426,0.0017685621,0.0034738865,0.004242546,0.005333695,0.0021415134],"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":[0.00036441901,0.00020533652,0.0033388596,0.0006605031,0.0018618961,0.00033220183,0.0010038564,0.4808486,0.002507256,0.29178706,0.0049501276,0.21214],"study_design_scores_gemma":[0.00004892222,0.000095229545,0.00045487095,0.000047599267,0.00016846703,0.000073392715,0.000042320407,0.8688589,0.0006964887,0.124536514,0.004918049,0.00005927984],"about_ca_topic_score_codex":0.005272936,"about_ca_topic_score_gemma":0.0073842597,"teacher_disagreement_score":0.024035666,"about_ca_system_score_codex":0.0014949868,"about_ca_system_score_gemma":0.0020116847,"threshold_uncertainty_score":0.12711424},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017774383,0.00011331429,0.9812692,0.0001566712,0.000010542675,0.000014883571,0.0000615614,0.00018031834,0.0004191196],"genre_scores_gemma":[0.572128,0.0006185699,0.42340836,0.00013789997,0.00010611524,0.00018682651,0.00060565164,0.0001428412,0.0026657875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999526,0.0002339,0.000018358784,0.00009851921,0.00008341767,0.00003985626],"domain_scores_gemma":[0.9975121,0.0019117045,0.00020702522,0.0001220181,0.00020335506,0.00004380699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00228866,0.0004962826,0.00061936356,0.00068548747,0.00036972392,0.0006135596,0.0009004204,0.00074426614,0.0012324055],"category_scores_gemma":[0.0069093783,0.00038515433,0.0007159536,0.00096542557,0.0006211394,0.0008733906,0.00079398596,0.00090536755,0.00023192645],"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":[0.000054941436,0.000040412564,0.003920843,0.000034139495,0.00004871173,0.00006432696,0.000096032534,0.9043329,0.0012266992,0.028342634,0.00063093804,0.061207432],"study_design_scores_gemma":[0.0000034072166,0.0000074003733,0.00061705674,0.000003780826,0.0000036450288,0.000015107289,0.000007755451,0.9907203,0.0002232899,0.008166518,0.00022518115,0.000006559094],"about_ca_topic_score_codex":0.014381207,"about_ca_topic_score_gemma":0.01087316,"teacher_disagreement_score":0.014381207,"about_ca_system_score_codex":0.0006866127,"about_ca_system_score_gemma":0.000816547,"threshold_uncertainty_score":0.02859497},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19870417,0.00081734644,0.79571664,0.0013281275,0.000115077935,0.00009807811,0.00032367185,0.0010447816,0.0018521573],"genre_scores_gemma":[0.9020801,0.00026260677,0.096243225,0.00022077901,0.000081329825,0.0001043121,0.0004356364,0.00005296302,0.00051912107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9765622,0.015673744,0.0014085417,0.0023186975,0.0032680111,0.0007687829],"domain_scores_gemma":[0.54864717,0.41819647,0.020216607,0.007083022,0.004362009,0.0014947555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039720885,0.0011186918,0.0022259504,0.0050580185,0.0010583431,0.002683533,0.003520709,0.003556174,0.002257536],"category_scores_gemma":[0.3245221,0.0008595904,0.0013458187,0.0037824395,0.003807823,0.0034704814,0.0030560466,0.0021134678,0.0003223163],"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":[0.0012414663,0.00032711166,0.108073875,0.0005431147,0.0006736645,0.0034394225,0.0008453744,0.5256938,0.001828227,0.21923293,0.0034847844,0.13461621],"study_design_scores_gemma":[0.00010033698,0.00012051684,0.002662059,0.00004533973,0.00004845353,0.0003482415,0.00008412645,0.86766475,0.0009468113,0.12750417,0.00042833659,0.000046836107],"about_ca_topic_score_codex":0.0025033273,"about_ca_topic_score_gemma":0.001593381,"teacher_disagreement_score":0.039720885,"about_ca_system_score_codex":0.0012398202,"about_ca_system_score_gemma":0.002620981,"threshold_uncertainty_score":0.21006662},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019497761,0.0008840131,0.99053043,0.00063539983,0.00017729893,0.00008387038,0.00060105487,0.0003013326,0.0048368024],"genre_scores_gemma":[0.31092972,0.007115954,0.6165521,0.0032084307,0.0017560172,0.002861775,0.0040408527,0.0009907447,0.05254438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990306,0.0052859294,0.00045935265,0.0017711286,0.0016622219,0.0005153693],"domain_scores_gemma":[0.98644817,0.009113066,0.001177651,0.0014912509,0.0015836699,0.0001861888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01327588,0.0037317732,0.0031983503,0.0031359387,0.0011248909,0.0040342533,0.0064143515,0.0034072853,0.016996747],"category_scores_gemma":[0.027706029,0.0013386525,0.0050756643,0.004178252,0.0023362725,0.004249128,0.003654879,0.0042516245,0.0063379514],"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":[0.00008987176,0.0001236707,0.0025371325,0.00049921643,0.0006417124,0.00022652444,0.00031542103,0.109566584,0.00076313666,0.7987814,0.009776592,0.0766788],"study_design_scores_gemma":[0.000039388968,0.00010687465,0.0007793369,0.00013138211,0.0002982054,0.00028106853,0.0000863209,0.3081863,0.00042750553,0.6657653,0.023817152,0.00008118678],"about_ca_topic_score_codex":0.005267684,"about_ca_topic_score_gemma":0.005731977,"teacher_disagreement_score":0.016996747,"about_ca_system_score_codex":0.001987324,"about_ca_system_score_gemma":0.0021750336,"threshold_uncertainty_score":0.0702104},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06706121,0.00021164308,0.9300915,0.0003261044,0.000051251194,0.000086346336,0.00014556869,0.0004940382,0.0015322692],"genre_scores_gemma":[0.625376,0.00029946346,0.37024924,0.0003707951,0.00014008977,0.000335686,0.0009006215,0.0003504037,0.0019777578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9867792,0.006000963,0.0008658983,0.0030067177,0.0027066704,0.0006406503],"domain_scores_gemma":[0.87678,0.100900404,0.0049987193,0.010310262,0.0054073944,0.0016033083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020787984,0.0009897273,0.0019812945,0.0032365248,0.0015469807,0.0035623026,0.0028352137,0.002370253,0.0036140948],"category_scores_gemma":[0.13130626,0.0012191051,0.0020489253,0.0016099166,0.0045180894,0.0073690545,0.0038576901,0.002689255,0.0010605529],"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":[0.0018137442,0.00037685034,0.07559329,0.0006113642,0.0007629498,0.0010268424,0.0017776813,0.16601437,0.026686348,0.45455533,0.0036021415,0.26717898],"study_design_scores_gemma":[0.00008394635,0.00022470349,0.007945648,0.00011985054,0.00013372028,0.0005006013,0.00020787165,0.53120816,0.014782538,0.4411854,0.0034492556,0.00015833584],"about_ca_topic_score_codex":0.0018289264,"about_ca_topic_score_gemma":0.0014216771,"teacher_disagreement_score":0.020787984,"about_ca_system_score_codex":0.0016053161,"about_ca_system_score_gemma":0.0021129227,"threshold_uncertainty_score":0.10993868},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051923147,0.00007573276,0.9940655,0.00004306596,0.000015657966,0.000057817,0.000039408744,0.00013251214,0.000377879],"genre_scores_gemma":[0.22342029,0.00029742133,0.77141964,0.00018475908,0.00008173496,0.0009329277,0.0007218525,0.00017833193,0.0027630285],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9408494,0.045235034,0.0017372827,0.004522121,0.006344643,0.0013114029],"domain_scores_gemma":[0.90719116,0.06325155,0.008595945,0.013653773,0.0068172836,0.0004903218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049011104,0.00086630945,0.001995456,0.0018886098,0.0008891781,0.0016570361,0.00416797,0.0014251365,0.0024404502],"category_scores_gemma":[0.18384638,0.0013171704,0.0017932284,0.0035103457,0.0024974346,0.003049783,0.0027358008,0.002809508,0.0009762397],"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":[0.00044892414,0.00031274388,0.030118732,0.00055130944,0.001060487,0.00043823718,0.001012641,0.24161673,0.0017630532,0.34109622,0.008095066,0.37348592],"study_design_scores_gemma":[0.00008690591,0.0002196522,0.006647104,0.00017839317,0.0001278181,0.00022824321,0.00014825266,0.84660715,0.003619474,0.13631573,0.005720227,0.00010092632],"about_ca_topic_score_codex":0.0050458806,"about_ca_topic_score_gemma":0.005663782,"teacher_disagreement_score":0.049011104,"about_ca_system_score_codex":0.0012587539,"about_ca_system_score_gemma":0.002699887,"threshold_uncertainty_score":0.25919855},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013091587,0.0004045433,0.9834042,0.0006368412,0.000116274256,0.0003730271,0.0002603954,0.00036991885,0.0013431538],"genre_scores_gemma":[0.22593348,0.0005798918,0.76844335,0.0006782516,0.00026324336,0.0021083304,0.0007820521,0.00027720907,0.00093417114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90005845,0.066975,0.00395654,0.013307443,0.014249726,0.0014528332],"domain_scores_gemma":[0.39678493,0.55674833,0.011079254,0.025794014,0.008570823,0.0010227489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1392924,0.0021134987,0.0056612366,0.0070399228,0.0024647743,0.004131882,0.005152315,0.0045916643,0.008828734],"category_scores_gemma":[0.44965813,0.0012156032,0.0043775523,0.0052644094,0.008329328,0.00596095,0.0037724054,0.010086358,0.0011641202],"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":[0.003154678,0.0010246605,0.018738125,0.0016273782,0.0029671967,0.00046324264,0.001339054,0.10736642,0.0056712744,0.4770005,0.008848201,0.37179935],"study_design_scores_gemma":[0.00078239053,0.0015917552,0.01282524,0.0006774701,0.0010192252,0.0005262868,0.00049514667,0.4681198,0.014205931,0.49190417,0.007618716,0.0002338352],"about_ca_topic_score_codex":0.002467597,"about_ca_topic_score_gemma":0.0017716282,"teacher_disagreement_score":0.1392924,"about_ca_system_score_codex":0.0032371583,"about_ca_system_score_gemma":0.0047480087,"threshold_uncertainty_score":0.73665744},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057763373,0.00015231436,0.9932595,0.000098798955,0.000010351746,0.000024117564,0.00006614129,0.00014148843,0.00047096738],"genre_scores_gemma":[0.56477225,0.0012589007,0.42908964,0.00015900767,0.000100936,0.00047720366,0.0009414754,0.0002497673,0.0029508586],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982589,0.00080302544,0.00011018758,0.0003698942,0.0003650093,0.00009307865],"domain_scores_gemma":[0.9930581,0.005335149,0.0005710562,0.0003864188,0.0005480514,0.00010111928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030147415,0.0010920771,0.0014713829,0.0012165768,0.00050148106,0.0013910844,0.0020718302,0.0017227492,0.0015334067],"category_scores_gemma":[0.016919529,0.00092775305,0.0016180545,0.0011810361,0.0010113693,0.0021865645,0.0018860006,0.0022807992,0.0004009257],"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":[0.00002847309,0.000032584936,0.0018211955,0.00010524717,0.00006477761,0.0000681028,0.0000733282,0.940668,0.0008767658,0.02654181,0.0006890663,0.02903068],"study_design_scores_gemma":[0.0000038801395,0.0000055422806,0.00017178948,0.000008919977,0.0000065599397,0.000013580538,0.0000064415917,0.98772323,0.0002449352,0.011358913,0.00044681263,0.000009424285],"about_ca_topic_score_codex":0.0074901213,"about_ca_topic_score_gemma":0.004173963,"teacher_disagreement_score":0.0074901213,"about_ca_system_score_codex":0.0009401499,"about_ca_system_score_gemma":0.0016290158,"threshold_uncertainty_score":0.015943706},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9743372,0.00007385777,0.02483137,0.00008237842,0.0000044286985,0.000008847406,0.00017365809,0.000041612762,0.00044664205],"genre_scores_gemma":[0.996711,0.000037667935,0.0027707636,0.000006542885,0.0000021742817,0.000011140941,0.000103681065,0.0000048434413,0.0003521507],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998042,0.00006364584,0.0000111692825,0.000057940255,0.000019361098,0.000043773947],"domain_scores_gemma":[0.9988219,0.0007237041,0.00024765154,0.00005683288,0.00008085203,0.00006896015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092378637,0.00027433696,0.00027685385,0.00046093093,0.00028814757,0.0004969328,0.0006967072,0.0005184895,0.0006867599],"category_scores_gemma":[0.0020489283,0.00038199028,0.00060194405,0.00034010445,0.00042392054,0.00052957714,0.0004427839,0.0004254281,0.00006500765],"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":[0.00003381112,0.000030710835,0.027241645,0.000009228393,0.00003595902,0.000051011168,0.00005433928,0.9664226,0.00072048436,0.0030699794,0.000062716696,0.0022674606],"study_design_scores_gemma":[0.000001946824,0.0000074194386,0.0026076895,0.0000012672505,0.000006407599,0.000007665513,0.000013883218,0.9967476,0.000066148415,0.0004973709,0.00004006144,0.0000025678924],"about_ca_topic_score_codex":0.045886073,"about_ca_topic_score_gemma":0.038598534,"teacher_disagreement_score":0.045886073,"about_ca_system_score_codex":0.00088660035,"about_ca_system_score_gemma":0.00064753,"threshold_uncertainty_score":0.09123796},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019902272,0.00025438616,0.9791043,0.00012748581,0.0000210813,0.000037747177,0.00008711148,0.00015797216,0.00030763826],"genre_scores_gemma":[0.6185609,0.0005783334,0.3778331,0.00023272165,0.00014428375,0.00032245263,0.0008047294,0.00011212659,0.0014112474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9904385,0.006598006,0.00036553934,0.00071807625,0.0016043205,0.00027551217],"domain_scores_gemma":[0.9362805,0.048810888,0.0036356817,0.0067680962,0.0042531905,0.00025163393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018392041,0.00045745895,0.0014837402,0.0020888757,0.0004986205,0.0014636117,0.002009336,0.0014590626,0.0011234552],"category_scores_gemma":[0.12853749,0.0005143586,0.00072552654,0.0024214666,0.0016967093,0.0019168404,0.0023885553,0.0014337964,0.00034217714],"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":[0.000389356,0.00016904282,0.038245674,0.000611908,0.0005818325,0.00061204715,0.00070342276,0.3676429,0.004870242,0.27560204,0.004903413,0.3056682],"study_design_scores_gemma":[0.000049290884,0.000041913696,0.006235012,0.000097308504,0.000060251972,0.00020438903,0.00006101565,0.8444279,0.0017501995,0.14452451,0.0025060868,0.00004210267],"about_ca_topic_score_codex":0.0035772144,"about_ca_topic_score_gemma":0.0023781045,"teacher_disagreement_score":0.018392041,"about_ca_system_score_codex":0.0010809844,"about_ca_system_score_gemma":0.0010358301,"threshold_uncertainty_score":0.09726757},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97640675,0.0004992836,0.021067642,0.00014843083,0.000021203166,0.000012068819,0.00018535268,0.000085161744,0.0015740935],"genre_scores_gemma":[0.99818593,0.00012118303,0.0012483143,0.000023496392,0.000024447134,0.0000063895427,0.00021651495,0.000017843739,0.00015588757],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986696,0.0005726582,0.00007824903,0.00035214232,0.00023944225,0.000087935805],"domain_scores_gemma":[0.9827527,0.009674006,0.003315223,0.0026587804,0.0011331667,0.00046607433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004514014,0.00013029818,0.0003256009,0.0011879881,0.00032958318,0.0007702209,0.00042344333,0.00028551088,0.0010840942],"category_scores_gemma":[0.028662253,0.00015120173,0.0002465991,0.000792992,0.0015146602,0.0009683864,0.00045548932,0.00036787702,0.00015871141],"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":[0.00037751198,0.000044234774,0.8868146,0.00012926747,0.00024966119,0.00023078153,0.00088983757,0.008480786,0.021046707,0.03862157,0.0008498051,0.04226524],"study_design_scores_gemma":[0.000027162396,0.00016369138,0.9262944,0.00003197684,0.00006890964,0.0009360203,0.00027402482,0.03430029,0.006706976,0.02931215,0.001836295,0.000048055004],"about_ca_topic_score_codex":0.001366129,"about_ca_topic_score_gemma":0.0008535067,"teacher_disagreement_score":0.004514014,"about_ca_system_score_codex":0.0007985405,"about_ca_system_score_gemma":0.0003311157,"threshold_uncertainty_score":0.023872674},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016642489,0.0006078042,0.9962876,0.0006425768,0.00005776477,0.000047961068,0.00005891582,0.000052734948,0.00058036996],"genre_scores_gemma":[0.15591674,0.002700851,0.83424234,0.0011213335,0.00067369867,0.0012347833,0.0005835455,0.00017665792,0.0033500309],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95410323,0.037204295,0.0015060484,0.003630958,0.0030111335,0.0005444326],"domain_scores_gemma":[0.87115145,0.10043375,0.008851881,0.014144484,0.004650613,0.00076782476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05734548,0.0025436154,0.002340658,0.003961333,0.0013434694,0.0025662638,0.005435781,0.0038117152,0.0042687734],"category_scores_gemma":[0.16774367,0.0011529553,0.0038221045,0.004090169,0.0052306275,0.005950759,0.0050327815,0.0049837544,0.00087057764],"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":[0.000061805236,0.00008385958,0.0055244947,0.0006387667,0.0005845938,0.00015967661,0.00052937923,0.058740634,0.0003541474,0.8186374,0.002681083,0.11200429],"study_design_scores_gemma":[0.0000491339,0.000114701514,0.0014941819,0.00032227856,0.00019734226,0.00022350169,0.000098844575,0.21117675,0.000435119,0.7791218,0.00671326,0.000053190848],"about_ca_topic_score_codex":0.0025853862,"about_ca_topic_score_gemma":0.0031588825,"teacher_disagreement_score":0.05734548,"about_ca_system_score_codex":0.0018444186,"about_ca_system_score_gemma":0.0043709623,"threshold_uncertainty_score":0.30327553},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029048707,0.0009569307,0.011624767,0.0007614651,0.0005516716,0.00086672837,0.9076254,0.004629674,0.04393466],"genre_scores_gemma":[0.050142493,0.00087645656,0.0071156947,0.00028491087,0.00016620813,0.0007185915,0.9328138,0.0002576861,0.00762415],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9975013,0.00022262661,0.00032864008,0.00035146496,0.0014197124,0.00017624286],"domain_scores_gemma":[0.9941842,0.0007141797,0.00053490535,0.001282535,0.0029386175,0.00034563514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001124999,0.0010686752,0.00096659776,0.0075461087,0.0007418228,0.0016744742,0.0012993749,0.0011995953,0.015261244],"category_scores_gemma":[0.009196822,0.0003167623,0.0005108453,0.010061151,0.00025928477,0.0017469716,0.00096568686,0.0014847047,0.021555344],"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":[0.0006068969,0.0010868649,0.038303852,0.0011575145,0.00020907684,0.0004065074,0.00022632675,0.015511441,0.0057890797,0.022620011,0.72984916,0.18423332],"study_design_scores_gemma":[0.00012779578,0.0002189722,0.06456906,0.00025976848,0.00010104495,0.0009965145,0.0003037124,0.025845714,0.006538113,0.014341531,0.88653445,0.00016325964],"about_ca_topic_score_codex":0.007045238,"about_ca_topic_score_gemma":0.00445344,"teacher_disagreement_score":0.015261244,"about_ca_system_score_codex":0.0009690541,"about_ca_system_score_gemma":0.00088986,"threshold_uncertainty_score":0.05105388},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026308443,0.00021575805,0.9687167,0.00030870712,0.00006852478,0.001842899,0.00015828264,0.0002624875,0.0021182396],"genre_scores_gemma":[0.27607104,0.00025478672,0.71497375,0.00030114577,0.000057474568,0.007635595,0.00014240674,0.000028379673,0.00053549634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9508997,0.041740447,0.0011797621,0.0028499442,0.0027344073,0.0005956769],"domain_scores_gemma":[0.7451471,0.22999544,0.011822133,0.009062736,0.0030654965,0.0009071898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.066361904,0.0016926562,0.002140796,0.0021746755,0.00085419137,0.0018542655,0.0017687441,0.0027874878,0.005788237],"category_scores_gemma":[0.18838482,0.001000381,0.0017837655,0.0013288524,0.0033195615,0.003306196,0.0021011012,0.0020667256,0.00039931948],"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":[0.004611243,0.002384952,0.008024557,0.0022508355,0.000737252,0.00024968197,0.0006086573,0.2797318,0.01379547,0.50040233,0.0020277938,0.18517534],"study_design_scores_gemma":[0.002165507,0.0061256485,0.0031653394,0.00029840006,0.0003910087,0.000113433445,0.00014162814,0.585479,0.013586529,0.38267988,0.0056932657,0.0001603621],"about_ca_topic_score_codex":0.0005901159,"about_ca_topic_score_gemma":0.0005716869,"teacher_disagreement_score":0.066361904,"about_ca_system_score_codex":0.00223815,"about_ca_system_score_gemma":0.003252451,"threshold_uncertainty_score":0.35095948},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042269077,0.00028275326,0.9558039,0.0005434635,0.000029517138,0.000043357024,0.0002223544,0.00017573616,0.0006299437],"genre_scores_gemma":[0.81859046,0.0007802016,0.1738235,0.0004120142,0.00016138419,0.0004251858,0.0008713715,0.00013920375,0.0047966433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997821,0.00092203857,0.000087576824,0.00054406736,0.0004013253,0.00022403187],"domain_scores_gemma":[0.9867464,0.009529729,0.001468575,0.0012656044,0.0007587872,0.00023091558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069501773,0.0010529245,0.0014387688,0.0020932308,0.00045042118,0.0011605301,0.003841084,0.0023789057,0.0022156169],"category_scores_gemma":[0.025263576,0.0007142883,0.0016556641,0.001791924,0.002803796,0.0031071438,0.0021047606,0.0035325899,0.0004384207],"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":[0.00012806493,0.0000611271,0.00875982,0.00013798043,0.00016448506,0.00045895594,0.00031038048,0.5993909,0.004523423,0.35958874,0.0014813907,0.024994712],"study_design_scores_gemma":[0.000014696051,0.00002666947,0.0014449382,0.000008692778,0.000021389684,0.00005294134,0.000015314958,0.9441724,0.00029274196,0.053488906,0.0004430704,0.000018250938],"about_ca_topic_score_codex":0.0075779622,"about_ca_topic_score_gemma":0.004370336,"teacher_disagreement_score":0.0075779622,"about_ca_system_score_codex":0.001328801,"about_ca_system_score_gemma":0.0010451772,"threshold_uncertainty_score":0.036756516},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015603823,0.000097754164,0.98276055,0.0001459745,0.00001705654,0.00017983414,0.000060195027,0.00011440877,0.0010203554],"genre_scores_gemma":[0.16972026,0.00015530927,0.82644,0.0002360801,0.000053926913,0.0013937112,0.00032897294,0.00011692499,0.0015549053],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9657081,0.025263567,0.0011689184,0.0041467003,0.0029097889,0.0008028551],"domain_scores_gemma":[0.9457967,0.04287566,0.0030995582,0.0047884677,0.002748341,0.00069123966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029659975,0.0010273008,0.0032791577,0.0016152759,0.00094626524,0.0016382111,0.003165356,0.0018503307,0.0030269455],"category_scores_gemma":[0.084360726,0.0012885617,0.0014643046,0.0020891537,0.0025126056,0.003123993,0.0036908379,0.002435399,0.0007594096],"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":[0.0010270679,0.00041355542,0.01180578,0.00031779686,0.00040681646,0.00027404792,0.0006389375,0.57259065,0.0030276363,0.17220978,0.0036250544,0.23366295],"study_design_scores_gemma":[0.00030185803,0.00040810555,0.0016893975,0.00008309199,0.00006792774,0.00014753564,0.0001198713,0.9009958,0.0036632041,0.08890354,0.0035755814,0.00004409537],"about_ca_topic_score_codex":0.0023769476,"about_ca_topic_score_gemma":0.0019082413,"teacher_disagreement_score":0.029659975,"about_ca_system_score_codex":0.0012013087,"about_ca_system_score_gemma":0.0024234925,"threshold_uncertainty_score":0.1568588},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006085749,0.00058843597,0.99109894,0.0007917452,0.000056931818,0.00025457953,0.00035811224,0.0001654591,0.0006000707],"genre_scores_gemma":[0.36409172,0.0016794548,0.6214047,0.0012029189,0.000566565,0.0051155607,0.0021609135,0.00025079353,0.0035273777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96086377,0.031495854,0.0010585958,0.0032673257,0.0025882155,0.00072618213],"domain_scores_gemma":[0.8874401,0.086368605,0.009498255,0.012920083,0.002678125,0.0010948883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08468123,0.0011238385,0.0026714695,0.0030352368,0.00071660447,0.0023555357,0.0046505434,0.002955644,0.0058293696],"category_scores_gemma":[0.14981379,0.0009909837,0.0035281596,0.003511148,0.0019894568,0.0036597562,0.0034228538,0.0046798987,0.0010525921],"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":[0.0007479602,0.00013306575,0.010427842,0.00054037076,0.0010062534,0.00059897354,0.0009822781,0.251013,0.0011427382,0.6452222,0.00524366,0.08294176],"study_design_scores_gemma":[0.00034642394,0.0003344122,0.0030907246,0.00016356498,0.0002575777,0.00035821742,0.00009156466,0.5276065,0.00044696205,0.45807692,0.009140379,0.000086686974],"about_ca_topic_score_codex":0.0020187073,"about_ca_topic_score_gemma":0.0010885347,"teacher_disagreement_score":0.08468123,"about_ca_system_score_codex":0.001441463,"about_ca_system_score_gemma":0.001992524,"threshold_uncertainty_score":0.44784248},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015809457,0.00022384964,0.99759716,0.00015576338,0.000010485265,0.000038364225,0.000038286737,0.000067263216,0.00028794416],"genre_scores_gemma":[0.084944345,0.0009211875,0.9113951,0.00032742028,0.00009977929,0.0006600958,0.00032146485,0.00012430495,0.0012063255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9816024,0.015171742,0.00053508906,0.0011090508,0.0014157554,0.00016590283],"domain_scores_gemma":[0.9021262,0.089621305,0.0025697818,0.0037564128,0.001588384,0.0003378159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029090043,0.0013488272,0.0019023773,0.002398202,0.0010233686,0.0017808812,0.0028025988,0.0021306744,0.0038679282],"category_scores_gemma":[0.16124186,0.0011990805,0.0018965084,0.002333671,0.0031241088,0.0055253934,0.0029968072,0.0034931109,0.00070392987],"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":[0.00014014654,0.00008511958,0.0036624058,0.0005457088,0.00035802234,0.00023581053,0.0006015686,0.3367783,0.00050041324,0.5114626,0.0020857332,0.14354402],"study_design_scores_gemma":[0.000049955815,0.000039528408,0.00053389854,0.000082907136,0.00004587042,0.00012497623,0.00006170709,0.51787657,0.0004204145,0.47816542,0.0025637907,0.000035029778],"about_ca_topic_score_codex":0.0034709496,"about_ca_topic_score_gemma":0.0055419593,"teacher_disagreement_score":0.029090043,"about_ca_system_score_codex":0.0015139701,"about_ca_system_score_gemma":0.0022865932,"threshold_uncertainty_score":0.15384471},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060189273,0.0004050172,0.991757,0.00042328716,0.000044596847,0.00008271027,0.00047729356,0.00029510373,0.00049604726],"genre_scores_gemma":[0.3427921,0.0026033665,0.63601035,0.00072296744,0.00046620672,0.002563741,0.0039344467,0.00035224034,0.01055456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9921137,0.0051696366,0.00035778116,0.001308759,0.0006920823,0.00035801256],"domain_scores_gemma":[0.94749635,0.044405375,0.0031290194,0.002764583,0.0016441682,0.00056039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020548305,0.001310657,0.0022065917,0.0032301578,0.000863665,0.0019162958,0.003971334,0.002395615,0.007893],"category_scores_gemma":[0.06888361,0.0009382908,0.0023747233,0.003347191,0.0022500877,0.004821258,0.0028650123,0.0054467404,0.0015921298],"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":[0.00023839241,0.00010420514,0.00601355,0.00029891357,0.00024536593,0.000278935,0.0005779783,0.13449176,0.000459087,0.8040856,0.003568397,0.049637888],"study_design_scores_gemma":[0.000047243397,0.000043435746,0.0007962123,0.000055438304,0.00005472856,0.000103764985,0.000052966534,0.4455507,0.00012954861,0.55002695,0.0031051603,0.00003380596],"about_ca_topic_score_codex":0.0064290804,"about_ca_topic_score_gemma":0.005242431,"teacher_disagreement_score":0.020548305,"about_ca_system_score_codex":0.0016731515,"about_ca_system_score_gemma":0.0016205034,"threshold_uncertainty_score":0.10867107},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00810591,0.0003866695,0.9905138,0.00032855512,0.000024477402,0.00011464021,0.000049527353,0.00017050304,0.0003059236],"genre_scores_gemma":[0.292551,0.0014970638,0.69879365,0.0005447176,0.00020624281,0.0013960518,0.00037031382,0.00028909298,0.004351875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98330843,0.013901706,0.00035088015,0.0010966547,0.00091185485,0.0004305258],"domain_scores_gemma":[0.89426327,0.09432841,0.004351554,0.004683667,0.0018308944,0.00054209726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047826797,0.001237388,0.0032139916,0.001302555,0.00050375,0.0018645223,0.003956619,0.002896851,0.0019600163],"category_scores_gemma":[0.11341165,0.0010109267,0.003786605,0.0010670177,0.0023761322,0.0019077375,0.0025022833,0.00451923,0.0003517525],"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":[0.00093664543,0.00032582323,0.0089895455,0.00045787188,0.0013776557,0.00026349584,0.00056077086,0.60244966,0.0028053673,0.17568189,0.0019060391,0.20424536],"study_design_scores_gemma":[0.00014731595,0.00024238705,0.0025096035,0.00007754363,0.0001716377,0.00005122726,0.000037847396,0.9072612,0.0013295333,0.086313285,0.001785211,0.00007319487],"about_ca_topic_score_codex":0.005320309,"about_ca_topic_score_gemma":0.003989949,"teacher_disagreement_score":0.047826797,"about_ca_system_score_codex":0.0017920339,"about_ca_system_score_gemma":0.0035310576,"threshold_uncertainty_score":0.2529353},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007913023,0.0001885228,0.99863005,0.000051920313,0.000019502899,0.00000794793,0.000018547395,0.00007281598,0.00021938754],"genre_scores_gemma":[0.06054321,0.00071278313,0.9368689,0.00008387648,0.00011140487,0.00009585061,0.00012607752,0.00015408748,0.0013038451],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876034,0.0005440514,0.0000525832,0.00020425698,0.00037033067,0.000068437155],"domain_scores_gemma":[0.9973417,0.0016707649,0.00027184546,0.00035987337,0.00026505633,0.000090844835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027566142,0.0008604722,0.0011496433,0.0017034676,0.00056510704,0.0012470845,0.0014690155,0.0018552691,0.0024847076],"category_scores_gemma":[0.011597013,0.00075543043,0.001979989,0.0014066248,0.0007219363,0.0019408838,0.0014938022,0.0029814127,0.00090689963],"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":[0.0001326712,0.00008959124,0.0012860963,0.0003238416,0.00022273764,0.0004052797,0.00034712366,0.46783605,0.024719127,0.22548991,0.0044769123,0.27467063],"study_design_scores_gemma":[0.000008395337,0.00001384664,0.00017162057,0.00001563247,0.000014096277,0.00008959203,0.000007954126,0.9760675,0.0011435858,0.019322522,0.0031251868,0.000020109159],"about_ca_topic_score_codex":0.00250146,"about_ca_topic_score_gemma":0.0016152845,"teacher_disagreement_score":0.0027566142,"about_ca_system_score_codex":0.0006227253,"about_ca_system_score_gemma":0.0008958405,"threshold_uncertainty_score":0.014578521},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018759778,0.00031652083,0.9968971,0.00019414963,0.000018026569,0.000054365693,0.000095177646,0.00009433102,0.00045433096],"genre_scores_gemma":[0.14284112,0.0010205711,0.85136634,0.0004566713,0.0003189028,0.0012041517,0.0012557833,0.0002832855,0.0012532491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9789001,0.014949634,0.00081877754,0.0012998994,0.0037137314,0.00031780847],"domain_scores_gemma":[0.90559196,0.08055966,0.00295736,0.0045421817,0.0053399815,0.0010088256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031355683,0.0016065952,0.003062175,0.0035813744,0.0013573284,0.0029387705,0.004217566,0.0024697443,0.0032031776],"category_scores_gemma":[0.1263952,0.0010917245,0.0016982737,0.0046407864,0.0037156367,0.0034598375,0.0044752387,0.004596564,0.0010600439],"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":[0.0004093991,0.000121137644,0.004178811,0.0007620972,0.0004913004,0.00037415398,0.0003668547,0.33211887,0.0016331717,0.5435207,0.0073421765,0.10868129],"study_design_scores_gemma":[0.00006690242,0.000060720122,0.00072759925,0.00007909389,0.000041063195,0.00010894116,0.000037060236,0.6338873,0.00056852144,0.3622573,0.0021197398,0.000045848818],"about_ca_topic_score_codex":0.0022943942,"about_ca_topic_score_gemma":0.002354262,"teacher_disagreement_score":0.031355683,"about_ca_system_score_codex":0.0019962548,"about_ca_system_score_gemma":0.004311205,"threshold_uncertainty_score":0.16582668},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075366534,0.00075250585,0.99711007,0.00030009143,0.00008333024,0.00032595874,0.000054896904,0.00009129172,0.00052814686],"genre_scores_gemma":[0.037026323,0.001426236,0.9552381,0.0005314436,0.00033354913,0.004479273,0.000321908,0.00012422334,0.00051893725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8515161,0.124622285,0.004984791,0.006512339,0.011707944,0.00065657665],"domain_scores_gemma":[0.69415873,0.2709385,0.010167172,0.016124787,0.0078187,0.0007920573],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15820593,0.0018780929,0.004754013,0.0058672577,0.001733297,0.0026425563,0.0060189324,0.0046769143,0.0047242083],"category_scores_gemma":[0.47934696,0.0017293617,0.0024854064,0.0043456713,0.0047185705,0.0049673356,0.0044244276,0.0061844145,0.0011029153],"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":[0.0005764482,0.00020146946,0.0067258473,0.0019651784,0.00079878565,0.00038784015,0.0009099753,0.03497207,0.0013610745,0.69422716,0.009190385,0.24868383],"study_design_scores_gemma":[0.0004431287,0.00026702287,0.0017317379,0.00074934924,0.0002860331,0.00045998607,0.00009823082,0.15425064,0.0016021716,0.8236286,0.016390279,0.00009275753],"about_ca_topic_score_codex":0.0019916971,"about_ca_topic_score_gemma":0.0013816173,"teacher_disagreement_score":0.8417941,"about_ca_system_score_codex":0.0023317703,"about_ca_system_score_gemma":0.003859308,"threshold_uncertainty_score":0.8366829},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010027083,0.00010000724,0.98955697,0.000063949476,0.0000070169244,0.00001091539,0.00003747261,0.000093157185,0.000103402665],"genre_scores_gemma":[0.3199988,0.00035361125,0.6783551,0.000055798257,0.000048429287,0.000126774,0.00038837522,0.00011307625,0.00055990176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967483,0.0020447087,0.00018285893,0.00042507728,0.00046845045,0.00013057848],"domain_scores_gemma":[0.9793732,0.015361337,0.0016999698,0.0022288365,0.0010925586,0.00024398955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010426379,0.0008258432,0.0014786208,0.0014281791,0.00045899142,0.0011224844,0.0018386374,0.0012189855,0.0009280643],"category_scores_gemma":[0.037748005,0.0006670118,0.0012444841,0.001743851,0.0015864334,0.0021236087,0.0022534966,0.0014289676,0.00030389623],"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":[0.00045675298,0.00007071047,0.00874841,0.0003147056,0.00027146423,0.00037812904,0.00031407355,0.7472755,0.0063692164,0.10459713,0.0014536415,0.12975028],"study_design_scores_gemma":[0.000026650272,0.00004523388,0.0012479908,0.0000272362,0.000019700854,0.00013617879,0.000029171724,0.9458008,0.0024628122,0.04941217,0.00076034694,0.000031757125],"about_ca_topic_score_codex":0.0015258234,"about_ca_topic_score_gemma":0.0011311414,"teacher_disagreement_score":0.010426379,"about_ca_system_score_codex":0.0004926233,"about_ca_system_score_gemma":0.001283404,"threshold_uncertainty_score":0.055140615},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0389254,0.0009386589,0.9569041,0.00081477896,0.00006735113,0.00033837912,0.00020730855,0.0004241761,0.0013799662],"genre_scores_gemma":[0.5108871,0.0009153019,0.48136058,0.00072909467,0.00015473792,0.0014621197,0.0007306699,0.00023821581,0.0035222522],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97430915,0.02120624,0.0006900269,0.001998874,0.0010298269,0.000765828],"domain_scores_gemma":[0.80695343,0.18176739,0.004308843,0.0032343722,0.002966804,0.00076914334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037530053,0.0019484013,0.005104216,0.002264195,0.0010288772,0.0029526297,0.0027869444,0.0038321265,0.0035779083],"category_scores_gemma":[0.14994247,0.0016998936,0.0027305968,0.0019271022,0.0027740744,0.0024474813,0.0029866858,0.00484877,0.00052029284],"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":[0.00024059854,0.00015697804,0.0044126147,0.00015733983,0.0002658268,0.000116318006,0.0002253067,0.9243326,0.00028573663,0.041073043,0.0005936777,0.028139915],"study_design_scores_gemma":[0.00005550729,0.00005940559,0.00048326625,0.00003689337,0.000031228865,0.000015359452,0.00002895142,0.9660503,0.00021801316,0.032592528,0.00040588182,0.000022706357],"about_ca_topic_score_codex":0.010765629,"about_ca_topic_score_gemma":0.005308334,"teacher_disagreement_score":0.037530053,"about_ca_system_score_codex":0.0026987714,"about_ca_system_score_gemma":0.0033058817,"threshold_uncertainty_score":0.19848025},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006348634,0.00018948648,0.99875236,0.00010733477,0.000019693585,0.000048461254,0.00004652427,0.00006633439,0.00013492408],"genre_scores_gemma":[0.040862765,0.0010611964,0.9533871,0.00027178664,0.00019883728,0.0015375223,0.00042671151,0.00016866268,0.0020853577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97923684,0.016282918,0.0007768657,0.0017949163,0.00160537,0.00030314008],"domain_scores_gemma":[0.9063527,0.07860484,0.0042455913,0.00783869,0.0024571645,0.0005010639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04498631,0.0016684906,0.0027160444,0.0036955713,0.0010514305,0.0021105262,0.0058076535,0.0026799773,0.005981787],"category_scores_gemma":[0.12472366,0.0018042866,0.0031938553,0.0039269337,0.0034224356,0.0046963547,0.0051091877,0.0053336876,0.001278481],"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":[0.00012084503,0.000068319714,0.002840002,0.00053675694,0.0005614923,0.00028043264,0.00062869577,0.08518861,0.00044088298,0.8128488,0.0028639915,0.09362117],"study_design_scores_gemma":[0.00005893998,0.000055839562,0.00065777363,0.00009590078,0.00008204127,0.0001415768,0.00007371426,0.37517115,0.00034099992,0.6171041,0.006176219,0.000041671487],"about_ca_topic_score_codex":0.004298702,"about_ca_topic_score_gemma":0.004839766,"teacher_disagreement_score":0.04498631,"about_ca_system_score_codex":0.0017449113,"about_ca_system_score_gemma":0.0034657693,"threshold_uncertainty_score":0.23791319},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027454127,0.0004172602,0.97028357,0.00031357506,0.00003329022,0.00014184653,0.00027794827,0.00027587367,0.0008025044],"genre_scores_gemma":[0.5305017,0.00049923686,0.4648521,0.0003240494,0.00019563442,0.0016086465,0.0010810385,0.00015652023,0.0007810808],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9465315,0.04391118,0.0022084685,0.0033042703,0.0035064404,0.0005382072],"domain_scores_gemma":[0.539906,0.42359042,0.011817561,0.020067995,0.0036710817,0.00094694603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.057322685,0.0010390616,0.0026348687,0.0029055676,0.0007342936,0.0020491818,0.00282756,0.0016024108,0.0049698697],"category_scores_gemma":[0.31802797,0.0007879133,0.0018400353,0.0029361006,0.0039743227,0.004642046,0.0025097402,0.0028041308,0.0007126195],"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":[0.0020789753,0.00041737763,0.049026717,0.0014697242,0.0015282466,0.0015220897,0.0016857221,0.15323515,0.0031753446,0.36590928,0.0074499263,0.41250154],"study_design_scores_gemma":[0.00018546398,0.00060026295,0.011774905,0.00021462925,0.00017194067,0.000613562,0.00019400421,0.5460886,0.0023452104,0.43538246,0.002317892,0.00011105899],"about_ca_topic_score_codex":0.0006517352,"about_ca_topic_score_gemma":0.0006317502,"teacher_disagreement_score":0.057322685,"about_ca_system_score_codex":0.0007293094,"about_ca_system_score_gemma":0.001397995,"threshold_uncertainty_score":0.30315495},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040469147,0.0006720859,0.95647347,0.00036328443,0.00005319028,0.00009242173,0.00012857112,0.00017880558,0.0015689811],"genre_scores_gemma":[0.63648844,0.001377278,0.35681146,0.00069902005,0.00037849598,0.00057378644,0.00068628404,0.00011193144,0.0028733173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9775318,0.017443836,0.00078999193,0.0013456792,0.002216403,0.0006722559],"domain_scores_gemma":[0.9032418,0.07600733,0.006515914,0.01160309,0.0021271226,0.0005046949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032738406,0.000558042,0.0012572579,0.0015347265,0.0007505797,0.0011570988,0.0017594845,0.0015253824,0.0020827053],"category_scores_gemma":[0.14306606,0.00048668133,0.0010670644,0.0018859439,0.0022279774,0.0023374844,0.0031788235,0.0014562946,0.00039150397],"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":[0.00092568836,0.00016743974,0.07399915,0.0005436641,0.0004387965,0.0023479995,0.001813314,0.13592793,0.0028682766,0.53464013,0.0030898314,0.24323773],"study_design_scores_gemma":[0.00017031145,0.00017740457,0.010533737,0.0002013273,0.00015302026,0.001070414,0.0001832197,0.51528466,0.0023272433,0.46566784,0.004152031,0.0000787674],"about_ca_topic_score_codex":0.0019316071,"about_ca_topic_score_gemma":0.0022452562,"teacher_disagreement_score":0.032738406,"about_ca_system_score_codex":0.00090895727,"about_ca_system_score_gemma":0.0010490143,"threshold_uncertainty_score":0.17313927},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016550843,0.0002776636,0.9796666,0.00024104124,0.000059142014,0.000082423125,0.00007877916,0.00068039366,0.002363029],"genre_scores_gemma":[0.32954606,0.00024854235,0.6646644,0.00025118302,0.00009181853,0.0002640177,0.0003570412,0.00042256832,0.0041544572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868315,0.00064436573,0.000044324235,0.0003053403,0.00024327768,0.00007966054],"domain_scores_gemma":[0.99456906,0.003167807,0.00027798594,0.0011633473,0.0006442563,0.00017748716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003695254,0.00062672375,0.0011259768,0.00083999924,0.0008075682,0.0010833524,0.002686438,0.0012280863,0.004461195],"category_scores_gemma":[0.016321339,0.0006238932,0.0007064096,0.0010394161,0.001223316,0.00192794,0.0018171639,0.00198809,0.0009446613],"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":[0.00024540344,0.0001014904,0.0026264421,0.00007625726,0.0001209672,0.00007677865,0.00015161619,0.7839401,0.00074569986,0.075815015,0.0032136324,0.1328866],"study_design_scores_gemma":[0.000011688395,0.000006338014,0.00008639668,0.0000034131237,0.0000052112264,0.000008888085,0.00000531772,0.98532724,0.00020064224,0.013906203,0.0004331837,0.0000055554533],"about_ca_topic_score_codex":0.0134863695,"about_ca_topic_score_gemma":0.019555222,"teacher_disagreement_score":0.0134863695,"about_ca_system_score_codex":0.0012606472,"about_ca_system_score_gemma":0.0017973258,"threshold_uncertainty_score":0.026815712},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007172036,0.000059370217,0.9982451,0.00009884694,0.00003385217,0.000036361922,0.0000758818,0.00038192736,0.00035138035],"genre_scores_gemma":[0.080869265,0.0003276525,0.9124417,0.00045837383,0.0003521083,0.000959888,0.0008106775,0.0010025898,0.0027778193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9791869,0.01261712,0.0011191716,0.002290953,0.00406973,0.0007160738],"domain_scores_gemma":[0.9260235,0.055517647,0.003325996,0.009829244,0.0046638576,0.00063981186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029381802,0.0021119649,0.0027032157,0.0020392681,0.0009603094,0.0022547022,0.0048053428,0.0016321586,0.017024716],"category_scores_gemma":[0.12693486,0.0012506567,0.0030331914,0.0025373877,0.0025120762,0.003911166,0.004185508,0.0060863425,0.0034412455],"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":[0.0004749958,0.00029681475,0.005128433,0.000577897,0.0006106837,0.00044966186,0.00035092366,0.2218428,0.002985153,0.4269715,0.012250887,0.32806045],"study_design_scores_gemma":[0.00013451811,0.00013382496,0.000849243,0.00008488814,0.000073772,0.00009422508,0.000032415766,0.7091082,0.003140116,0.28069383,0.005608506,0.0000464875],"about_ca_topic_score_codex":0.0038128274,"about_ca_topic_score_gemma":0.0052254545,"teacher_disagreement_score":0.029381802,"about_ca_system_score_codex":0.0015397796,"about_ca_system_score_gemma":0.005398488,"threshold_uncertainty_score":0.15538764},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022390332,0.00021828669,0.9764323,0.00025517988,0.00001878273,0.000026513071,0.00008031842,0.00014949807,0.0004287716],"genre_scores_gemma":[0.76857424,0.0005202982,0.22728059,0.00030751817,0.0001223231,0.00017043724,0.0004979733,0.000121980614,0.0024046921],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997177,0.0015580116,0.00012780166,0.00059088465,0.000366201,0.00018003545],"domain_scores_gemma":[0.97620004,0.018661499,0.0018935745,0.0019069923,0.0008918999,0.0004460031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009184737,0.0007032932,0.0016192603,0.0006843047,0.00036555898,0.0013111901,0.002302143,0.0018815276,0.0021412729],"category_scores_gemma":[0.046147373,0.0006250315,0.0008124762,0.00085705385,0.0021276837,0.0023462623,0.0018533072,0.0029219324,0.00034577184],"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":[0.00044881002,0.000170482,0.019730223,0.00038065968,0.00018344377,0.00051819504,0.00035045313,0.5883072,0.0052961223,0.29105982,0.00255759,0.09099698],"study_design_scores_gemma":[0.000021924767,0.000056535686,0.002274949,0.000022923532,0.000016810702,0.00006420436,0.000027263522,0.94429696,0.0009338803,0.051704217,0.0005555434,0.000024781544],"about_ca_topic_score_codex":0.0018873861,"about_ca_topic_score_gemma":0.0012870592,"teacher_disagreement_score":0.009184737,"about_ca_system_score_codex":0.00082816277,"about_ca_system_score_gemma":0.0007740544,"threshold_uncertainty_score":0.04857409},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19970496,0.0012866666,0.79186434,0.0015639628,0.00010314705,0.00016090696,0.00076479,0.0005501683,0.004001044],"genre_scores_gemma":[0.8579373,0.0009947832,0.13629317,0.00031933433,0.00009610602,0.0005232158,0.0014269582,0.0002733939,0.0021356598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998823,0.00062571326,0.00007852555,0.00016756958,0.00021982644,0.00008547711],"domain_scores_gemma":[0.98349726,0.013708196,0.00090833305,0.00055816123,0.0010703544,0.00025769256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007456337,0.0007989294,0.0010939211,0.0014583652,0.0007957819,0.001356343,0.0019317734,0.0020250336,0.002558733],"category_scores_gemma":[0.02512438,0.0003370569,0.001735502,0.00072614005,0.00067971495,0.0016973289,0.001283218,0.0014351507,0.00035874997],"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":[0.00009565012,0.000059914793,0.0031206994,0.00012751773,0.000066853165,0.000102912876,0.00011867066,0.95888054,0.001070263,0.02732278,0.0006723331,0.008361876],"study_design_scores_gemma":[0.0000055542164,0.000021972046,0.0003215552,0.000012241793,0.000009486169,0.000019506331,0.000019813793,0.9913043,0.00021228888,0.0078096725,0.00025278132,0.000010755553],"about_ca_topic_score_codex":0.01135136,"about_ca_topic_score_gemma":0.0056922757,"teacher_disagreement_score":0.01135136,"about_ca_system_score_codex":0.001440449,"about_ca_system_score_gemma":0.0023037472,"threshold_uncertainty_score":0.0394333},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011275676,0.000036496796,0.9977277,0.00002056376,0.00003614346,0.00015815053,0.000044005446,0.00014402093,0.00070544926],"genre_scores_gemma":[0.01325802,0.000077326484,0.9846223,0.000053179734,0.000041770243,0.001053791,0.00008527754,0.00007489867,0.00073338917],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9867007,0.009381565,0.0005214593,0.001118324,0.0019743498,0.00030361227],"domain_scores_gemma":[0.9829606,0.010804525,0.0011697259,0.0026939383,0.0021197116,0.0002516064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012324526,0.0015871215,0.0015094567,0.0025100806,0.0010383214,0.0011614818,0.001401569,0.0010454028,0.009480459],"category_scores_gemma":[0.035405934,0.0010077553,0.0016870559,0.0019619854,0.0017665522,0.0015812169,0.00231432,0.0023446165,0.0022758837],"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":[0.00084370916,0.0002789668,0.0011729286,0.0006550782,0.00026058493,0.00016012015,0.00051719544,0.051208895,0.013645807,0.26980788,0.0044567133,0.6569922],"study_design_scores_gemma":[0.0013141122,0.0037721666,0.0018046701,0.00042357665,0.00036323705,0.00090545596,0.00030346148,0.3914929,0.035624847,0.46859276,0.09503158,0.00037124983],"about_ca_topic_score_codex":0.0004895411,"about_ca_topic_score_gemma":0.000581005,"teacher_disagreement_score":0.012324526,"about_ca_system_score_codex":0.0005442114,"about_ca_system_score_gemma":0.0022225883,"threshold_uncertainty_score":0.06517911},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01634218,0.0007471007,0.98095644,0.00050063845,0.000042410906,0.000061688675,0.000109945,0.0001826423,0.0010570041],"genre_scores_gemma":[0.68074834,0.0019101234,0.31277025,0.0005630073,0.0008319839,0.00040164604,0.0008600258,0.00023358391,0.0016810264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985586,0.010588969,0.0006105864,0.0012960718,0.0015916063,0.00032673916],"domain_scores_gemma":[0.776668,0.19422925,0.0074440683,0.018059913,0.0031024627,0.0004962657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02947496,0.0012727403,0.0021328724,0.0026339542,0.0005618165,0.0029274598,0.0029797931,0.0019523769,0.001440218],"category_scores_gemma":[0.18248965,0.00083048537,0.0015240466,0.0023143818,0.0027287588,0.0050353776,0.003959386,0.003311862,0.0003264507],"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":[0.00041230867,0.00031231914,0.04944673,0.000644037,0.0018686583,0.0009683269,0.00048393168,0.4052657,0.0054685664,0.2939193,0.002991743,0.23821844],"study_design_scores_gemma":[0.00007005899,0.00015228406,0.008272465,0.00012063757,0.00013820763,0.0003627062,0.00007484637,0.8270341,0.0017891349,0.15973216,0.0021622032,0.00009117628],"about_ca_topic_score_codex":0.0018899235,"about_ca_topic_score_gemma":0.0017892043,"teacher_disagreement_score":0.02947496,"about_ca_system_score_codex":0.0005134088,"about_ca_system_score_gemma":0.0009318303,"threshold_uncertainty_score":0.15588033},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030662913,0.0003673116,0.99551624,0.00009550375,0.00002580546,0.00001011839,0.000046707115,0.00015899003,0.00071292114],"genre_scores_gemma":[0.3281512,0.0020705392,0.6639069,0.0004629314,0.0005537632,0.00025805936,0.0009167427,0.00023699386,0.0034429007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967794,0.0015697107,0.00013377794,0.00042352246,0.0009319965,0.00016164871],"domain_scores_gemma":[0.9936805,0.0037832065,0.00056076347,0.00095135334,0.0008897958,0.00013436314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048129717,0.0007676299,0.0012712852,0.0016116834,0.0006255902,0.0012682811,0.0013737613,0.0010879522,0.0016572926],"category_scores_gemma":[0.016887588,0.00039499998,0.00096310175,0.0018036737,0.00089294306,0.002180852,0.0015230748,0.00213296,0.00063731696],"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":[0.0000662221,0.000043081433,0.0032079527,0.00012952779,0.00017134495,0.000106846834,0.00016632427,0.49664715,0.0016900242,0.28303975,0.0040644817,0.21066718],"study_design_scores_gemma":[0.00000929176,0.000027923425,0.0006282679,0.000038749804,0.000025126614,0.000077117365,0.000019579007,0.8402878,0.0009353048,0.1532879,0.0046422733,0.000020738484],"about_ca_topic_score_codex":0.0015800474,"about_ca_topic_score_gemma":0.0021222015,"teacher_disagreement_score":0.0048129717,"about_ca_system_score_codex":0.00057294837,"about_ca_system_score_gemma":0.00095688226,"threshold_uncertainty_score":0.025453746},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05855275,0.001325828,0.93059576,0.0008129166,0.000104996114,0.0003070598,0.00051594153,0.0007345624,0.007050148],"genre_scores_gemma":[0.7401424,0.0017798006,0.24832746,0.0005757512,0.0003533593,0.0013971641,0.0021006665,0.0008281027,0.0044953376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96240777,0.018774046,0.0021114822,0.008125625,0.0073371455,0.0012439338],"domain_scores_gemma":[0.77880657,0.17165817,0.015003282,0.020403726,0.012232929,0.0018953553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049752127,0.0013970035,0.0031142193,0.005407005,0.00092629174,0.004285432,0.0040445607,0.0031486587,0.0070860847],"category_scores_gemma":[0.28411603,0.0009096161,0.0027073491,0.0022006638,0.0050225793,0.007497495,0.004872878,0.0058026724,0.0021173481],"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":[0.0012591914,0.0003294023,0.034403242,0.0010811274,0.00063581386,0.0007052243,0.0027924422,0.13263759,0.0055055553,0.5367841,0.0031787632,0.28068754],"study_design_scores_gemma":[0.00018068407,0.0013644337,0.026740124,0.0004984177,0.00021718678,0.0011220819,0.00076208217,0.37495738,0.0040030777,0.5705809,0.019329183,0.0002443942],"about_ca_topic_score_codex":0.0012854885,"about_ca_topic_score_gemma":0.0003610405,"teacher_disagreement_score":0.049752127,"about_ca_system_score_codex":0.0019770965,"about_ca_system_score_gemma":0.0014320647,"threshold_uncertainty_score":0.26311755},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048830616,0.00033588486,0.99172795,0.0005415546,0.00005823232,0.00009642535,0.0005207965,0.000813906,0.0010222191],"genre_scores_gemma":[0.18567505,0.0006409171,0.8060017,0.00062489306,0.0002750914,0.00086538953,0.0027720935,0.0005595987,0.0025852742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419254,0.0031172105,0.00024522652,0.000919105,0.0012814882,0.00024438582],"domain_scores_gemma":[0.9623518,0.02795421,0.0018728429,0.005565414,0.001770016,0.00048571805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0096137505,0.0010920266,0.0015605645,0.002855642,0.0014632626,0.0022729186,0.0034349049,0.0019922147,0.005973953],"category_scores_gemma":[0.071771875,0.0013112413,0.0013667308,0.0041060005,0.0025330046,0.0033273136,0.0027568594,0.0052496474,0.0015987394],"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":[0.0003579856,0.00011795748,0.006069031,0.0004484323,0.00022396505,0.00021442183,0.0005211295,0.39214036,0.0020484533,0.46560892,0.015585002,0.11666427],"study_design_scores_gemma":[0.000027856195,0.000009321043,0.0004708826,0.000034611832,0.000011117041,0.00003617823,0.0000231241,0.77145725,0.00061382196,0.22444978,0.00285073,0.00001533081],"about_ca_topic_score_codex":0.009907124,"about_ca_topic_score_gemma":0.012961196,"teacher_disagreement_score":0.009907124,"about_ca_system_score_codex":0.0030228128,"about_ca_system_score_gemma":0.003412998,"threshold_uncertainty_score":0.050843},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035460327,0.00031623896,0.96336955,0.00014609616,0.000044911503,0.000027380403,0.00008228748,0.000109481414,0.00044357908],"genre_scores_gemma":[0.5610137,0.0008372421,0.43527177,0.0000646324,0.00012558747,0.00011530798,0.00055781077,0.00005879316,0.0019551993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914956,0.0002479046,0.00005804352,0.00021425402,0.0002611768,0.00006906215],"domain_scores_gemma":[0.997922,0.0012831949,0.0002615392,0.00024650822,0.0002349662,0.000051788982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021754247,0.0008455084,0.0010566022,0.00096302055,0.00027933528,0.0010718129,0.0008580928,0.0009162522,0.0010055625],"category_scores_gemma":[0.008323312,0.0004022572,0.0009319023,0.0016410968,0.0007774386,0.0015027641,0.0009835019,0.001628479,0.0002385035],"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":[0.000074696996,0.000047959096,0.0027743445,0.000073684176,0.00008611439,0.000075511656,0.000052880532,0.8741098,0.0023361654,0.01891416,0.0005578901,0.10089685],"study_design_scores_gemma":[0.0000030879278,0.000013497062,0.0004272038,0.0000042741603,0.00000782099,0.000014700803,0.0000047684666,0.9932821,0.0005574985,0.005364188,0.00031262529,0.000008141729],"about_ca_topic_score_codex":0.0038450342,"about_ca_topic_score_gemma":0.002912584,"teacher_disagreement_score":0.0038450342,"about_ca_system_score_codex":0.0005580271,"about_ca_system_score_gemma":0.00088161364,"threshold_uncertainty_score":0.011504889},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060018403,0.0010146151,0.9894853,0.00023846056,0.00014609896,0.00045783445,0.0015634549,0.00043894592,0.0006534231],"genre_scores_gemma":[0.1501077,0.00197585,0.8247539,0.00086872216,0.00043877366,0.0048819534,0.009661844,0.00029451944,0.0070167505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9766732,0.013238863,0.0011989345,0.006320192,0.002059113,0.00050960405],"domain_scores_gemma":[0.90830094,0.06143597,0.010363909,0.016101835,0.003367624,0.00042962047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.055819154,0.0025778764,0.003366,0.0045606573,0.0017175261,0.002801609,0.008981871,0.0050187325,0.0046775513],"category_scores_gemma":[0.10764933,0.0020205816,0.00554372,0.0071076592,0.003221662,0.0050151385,0.0036132722,0.0054951087,0.002353562],"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":[0.00058841944,0.00047814968,0.060722332,0.0029781777,0.005398979,0.0012044912,0.00221193,0.37863126,0.004293108,0.31446472,0.011957941,0.21707052],"study_design_scores_gemma":[0.00017170206,0.0008027141,0.024542773,0.00053514115,0.00091188157,0.00079775165,0.0006360961,0.7297986,0.0037692552,0.20614475,0.03146608,0.00042321382],"about_ca_topic_score_codex":0.012324701,"about_ca_topic_score_gemma":0.008881197,"teacher_disagreement_score":0.055819154,"about_ca_system_score_codex":0.002626384,"about_ca_system_score_gemma":0.0017932542,"threshold_uncertainty_score":0.29520345},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034010918,0.00010723654,0.99536633,0.00019095061,0.000031375384,0.00003849754,0.000050307222,0.00032340473,0.00049083174],"genre_scores_gemma":[0.24985352,0.00029364642,0.74557877,0.0005163854,0.0002413004,0.00060163654,0.0004010864,0.00060806295,0.0019055866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9767224,0.01738022,0.0007503623,0.0025003362,0.0020825167,0.0005640979],"domain_scores_gemma":[0.858583,0.11495126,0.004931503,0.016868845,0.004046988,0.0006185137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04494173,0.0011402762,0.0018364621,0.0012990377,0.00070079055,0.0016739586,0.0040088724,0.0018573604,0.004113366],"category_scores_gemma":[0.21153565,0.00096344674,0.0015720879,0.0018007845,0.0029960065,0.0043053078,0.004657503,0.0051767086,0.00088030467],"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":[0.00052457344,0.0002322728,0.01312337,0.00028349276,0.00042472928,0.00028071474,0.0004468154,0.19735274,0.005163883,0.56533587,0.004799329,0.21203223],"study_design_scores_gemma":[0.0001528571,0.000075653516,0.0015916673,0.000058655573,0.00005933482,0.00009411983,0.00003455307,0.69167507,0.0030429866,0.30088246,0.0022905366,0.000042082516],"about_ca_topic_score_codex":0.0026168122,"about_ca_topic_score_gemma":0.0024724996,"teacher_disagreement_score":0.04494173,"about_ca_system_score_codex":0.0013617423,"about_ca_system_score_gemma":0.002233339,"threshold_uncertainty_score":0.23767745},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037916964,0.00052739674,0.9940686,0.00025422996,0.000059135014,0.000036033343,0.00018046699,0.0003902736,0.0006921857],"genre_scores_gemma":[0.43116942,0.0030624827,0.54853654,0.0008869138,0.00089419895,0.00048596106,0.0018563803,0.00072582526,0.012382358],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99567974,0.0019954767,0.00016678343,0.0011325568,0.0007531691,0.00027229515],"domain_scores_gemma":[0.98659724,0.0076275696,0.0013269779,0.0028900397,0.0013060725,0.0002520354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008272365,0.0015229152,0.0023541967,0.0020496715,0.00074851426,0.0014472392,0.0031374684,0.002036054,0.0032956332],"category_scores_gemma":[0.029740093,0.00081107765,0.0016699543,0.0026608114,0.0019888405,0.002950013,0.0020395156,0.003495502,0.0015038084],"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":[0.00021257481,0.00008380375,0.006866552,0.0004719965,0.000551339,0.00029736056,0.0002006118,0.5473922,0.00433487,0.271176,0.01016977,0.15824285],"study_design_scores_gemma":[0.000016935212,0.000033827113,0.0010286184,0.000033026055,0.00003748075,0.00005569611,0.000014956848,0.9090032,0.0012081795,0.08543884,0.00309084,0.000038431397],"about_ca_topic_score_codex":0.0033547939,"about_ca_topic_score_gemma":0.0032224106,"teacher_disagreement_score":0.008272365,"about_ca_system_score_codex":0.0012230054,"about_ca_system_score_gemma":0.0014797858,"threshold_uncertainty_score":0.043748975},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008452565,0.00010246281,0.99848264,0.00008021119,0.00002223982,0.00014770919,0.000032653214,0.00007052051,0.00021641084],"genre_scores_gemma":[0.030700905,0.00045542783,0.9661479,0.00014433706,0.00016218582,0.0018473893,0.00017621128,0.0000765428,0.00028909164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9371778,0.050455432,0.0025007578,0.0026194998,0.006791479,0.00045504846],"domain_scores_gemma":[0.8929196,0.085682325,0.004270361,0.009983753,0.006358099,0.0007858313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.078073926,0.0017957439,0.003713791,0.0078077363,0.001369268,0.0035578387,0.004104731,0.0023429797,0.004140011],"category_scores_gemma":[0.16851321,0.0015520325,0.0025854106,0.005483031,0.0037221347,0.005558698,0.0060769,0.004467129,0.0012068029],"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":[0.00016184774,0.00030616098,0.0054999273,0.0011580351,0.00071687024,0.0004877547,0.001453807,0.044778615,0.001934794,0.5387155,0.0060670543,0.3987196],"study_design_scores_gemma":[0.00012993847,0.00025690722,0.0022651628,0.00042302243,0.00014641791,0.00022439733,0.00030173088,0.304254,0.0012566264,0.68004483,0.0105855055,0.0001114336],"about_ca_topic_score_codex":0.0011665762,"about_ca_topic_score_gemma":0.0011365894,"teacher_disagreement_score":0.078073926,"about_ca_system_score_codex":0.0013095083,"about_ca_system_score_gemma":0.0032102726,"threshold_uncertainty_score":0.41289932},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057263034,0.00013067872,0.99317074,0.0001155271,0.000021126914,0.000044431275,0.000040271098,0.0003274765,0.0004234229],"genre_scores_gemma":[0.3916484,0.00043126201,0.60133094,0.00051953294,0.00014060571,0.0004605279,0.000599319,0.00035034298,0.004518997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626356,0.001841479,0.00017217467,0.00050003367,0.0009713477,0.00025129222],"domain_scores_gemma":[0.9784151,0.016791197,0.0008795008,0.0015254179,0.0018838976,0.0005048218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008057383,0.0014233752,0.002378954,0.0021635601,0.0008759279,0.0014664046,0.002543244,0.0017791104,0.0030751547],"category_scores_gemma":[0.031632844,0.000734825,0.001803836,0.0017441298,0.001971131,0.0024704144,0.003451348,0.0021950179,0.00070298795],"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":[0.00048394583,0.00021882824,0.0066501168,0.0005004187,0.00029300427,0.00079102145,0.00034156418,0.5074804,0.010025269,0.14999646,0.00534953,0.31786934],"study_design_scores_gemma":[0.000024333298,0.000056033954,0.0003508931,0.000017203183,0.00001933068,0.00010961649,0.000010768651,0.96205026,0.0016916918,0.034907907,0.00073485705,0.000027047015],"about_ca_topic_score_codex":0.0047442988,"about_ca_topic_score_gemma":0.0030632785,"teacher_disagreement_score":0.008057383,"about_ca_system_score_codex":0.0012000228,"about_ca_system_score_gemma":0.0031908627,"threshold_uncertainty_score":0.042612016},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016301436,0.00029093298,0.99669844,0.00024876723,0.000029542529,0.000018996936,0.00009475778,0.00011825986,0.0008699838],"genre_scores_gemma":[0.29403958,0.003660156,0.6809595,0.0010684248,0.00046303158,0.0010719285,0.0019966515,0.00092981587,0.015810916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99630773,0.0023981526,0.00017266771,0.0003890615,0.0005680971,0.00016437446],"domain_scores_gemma":[0.9674123,0.027410636,0.0013005816,0.0018387262,0.0017231214,0.000314689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013565557,0.0013591645,0.0020943116,0.0023328275,0.00061289215,0.0020882732,0.0035683725,0.0020964365,0.006818844],"category_scores_gemma":[0.05845126,0.0013484027,0.0026294095,0.002368159,0.0022111086,0.0043253326,0.002868705,0.0047136648,0.0015595967],"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":[0.000038662383,0.00003147819,0.0016349824,0.0001838801,0.0001314825,0.00019534568,0.0002734041,0.35658935,0.00039889375,0.6141306,0.004293527,0.022098338],"study_design_scores_gemma":[0.000010857115,0.000011148874,0.0002012953,0.000036953446,0.000014802913,0.000031496802,0.000020717225,0.7855418,0.00011349089,0.21191956,0.0020843267,0.00001350565],"about_ca_topic_score_codex":0.0056021577,"about_ca_topic_score_gemma":0.0048537515,"teacher_disagreement_score":0.013565557,"about_ca_system_score_codex":0.0017225337,"about_ca_system_score_gemma":0.0015877004,"threshold_uncertainty_score":0.071742356},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03235297,0.00037168004,0.96436965,0.00077001407,0.000042606072,0.00025739166,0.0006686816,0.00024205225,0.0009248985],"genre_scores_gemma":[0.43368828,0.00066113874,0.5587296,0.00050069025,0.00014346754,0.0016520014,0.0020142249,0.00019728988,0.0024133443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9793691,0.016500292,0.0006988945,0.0019574682,0.00095722894,0.0005170654],"domain_scores_gemma":[0.94137263,0.049073257,0.004333338,0.0038166675,0.0010331394,0.00037097317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033581134,0.001163024,0.0026475552,0.0021205915,0.0004878657,0.0017962353,0.0019863255,0.0021412626,0.0037384185],"category_scores_gemma":[0.11932681,0.0010085593,0.002589974,0.0023226994,0.0014486802,0.002082715,0.0025411195,0.0030784912,0.00064110657],"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":[0.00068892003,0.00024134728,0.02087926,0.00039249714,0.0009108486,0.00015945442,0.0003264292,0.6889674,0.0009465634,0.12398225,0.0035831342,0.15892184],"study_design_scores_gemma":[0.00019212274,0.00023502088,0.00417049,0.00016162705,0.00018685928,0.00007719297,0.000056857116,0.8111618,0.00073282945,0.17915285,0.0038080905,0.0000642954],"about_ca_topic_score_codex":0.0053697536,"about_ca_topic_score_gemma":0.004080017,"teacher_disagreement_score":0.033581134,"about_ca_system_score_codex":0.0015979124,"about_ca_system_score_gemma":0.003117423,"threshold_uncertainty_score":0.17759615},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015483183,0.00023191421,0.99369377,0.00025888212,0.00011558221,0.0002308865,0.00043511207,0.0030618587,0.00042363012],"genre_scores_gemma":[0.100779906,0.00034509224,0.8888529,0.00075168983,0.0003252898,0.003623207,0.0014507888,0.0023078567,0.0015632205],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96542346,0.025613608,0.001428755,0.0028534268,0.0040485696,0.00063213066],"domain_scores_gemma":[0.8377946,0.13662225,0.006541457,0.0124960905,0.005472779,0.0010728893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03847216,0.002140363,0.0036645874,0.0032478587,0.001194417,0.0024130577,0.006142058,0.0028993727,0.017109614],"category_scores_gemma":[0.2538438,0.0011293531,0.003155578,0.004007626,0.00354902,0.0027791907,0.003909463,0.0054837354,0.0034560994],"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":[0.0028199805,0.00042698908,0.014223351,0.002246978,0.0040044915,0.0019104659,0.00074533944,0.14171347,0.0067530377,0.13674313,0.0614846,0.62692815],"study_design_scores_gemma":[0.00094555836,0.0007073515,0.0036853156,0.00028780755,0.0005268223,0.00083599763,0.0001169805,0.7518342,0.006452346,0.21401319,0.020392314,0.00020215017],"about_ca_topic_score_codex":0.0026616747,"about_ca_topic_score_gemma":0.0028103443,"teacher_disagreement_score":0.03847216,"about_ca_system_score_codex":0.0014932454,"about_ca_system_score_gemma":0.0067313113,"threshold_uncertainty_score":0.20346266},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026864535,0.000083310704,0.99632794,0.00020380228,0.00002652409,0.00005486577,0.0001008151,0.00006402321,0.00045227713],"genre_scores_gemma":[0.3332241,0.00058815366,0.66013604,0.0007089384,0.00042131392,0.0013175047,0.0008799592,0.00013582545,0.0025881266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9539194,0.035359196,0.0013129248,0.003554276,0.005180284,0.0006738003],"domain_scores_gemma":[0.81988513,0.1490728,0.009512129,0.016539434,0.004349695,0.0006407982],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052416135,0.0013097485,0.0029685292,0.0029304803,0.00096904545,0.0025021145,0.0058797533,0.0022365141,0.0056180917],"category_scores_gemma":[0.21499816,0.0011202168,0.002855327,0.0023754644,0.004123888,0.0042394972,0.0039197113,0.0040010475,0.00063520577],"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":[0.00012706083,0.00014656445,0.0042755976,0.0003165128,0.00040683922,0.00031352823,0.00026006575,0.12118249,0.0006304672,0.82389003,0.002234903,0.046215996],"study_design_scores_gemma":[0.00006823135,0.000063116975,0.0012773258,0.00008055712,0.0000694194,0.00007730851,0.00003563828,0.5070355,0.0005782461,0.4885443,0.002139626,0.000030705014],"about_ca_topic_score_codex":0.0037045255,"about_ca_topic_score_gemma":0.002771025,"teacher_disagreement_score":0.94758385,"about_ca_system_score_codex":0.0020474927,"about_ca_system_score_gemma":0.0024875258,"threshold_uncertainty_score":0.2772063},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017321077,0.00011486072,0.9978284,0.00003423747,0.00001069211,0.0000202794,0.0000277591,0.00014508709,0.00008654182],"genre_scores_gemma":[0.12078237,0.00048720787,0.8766103,0.00015936443,0.00013213097,0.00043993516,0.00050935615,0.00016398268,0.00071543624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98941714,0.00854723,0.00023859585,0.0008248858,0.0007129817,0.00025911885],"domain_scores_gemma":[0.96490973,0.030230349,0.0014386979,0.0020040877,0.001165292,0.00025173393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016956028,0.0013129889,0.0025424808,0.002529003,0.0009431474,0.0015502268,0.0030343756,0.0018804416,0.0018594462],"category_scores_gemma":[0.048588775,0.0013610427,0.0022060962,0.0026994941,0.0017578622,0.0023263276,0.0021748885,0.002456781,0.00066941686],"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":[0.00011651807,0.000092839095,0.0031408786,0.00020324388,0.0002472024,0.00016534771,0.00017450697,0.7961857,0.0007027861,0.092528105,0.001636795,0.10480609],"study_design_scores_gemma":[0.000019135246,0.000015495707,0.00017974059,0.000021501617,0.000014336751,0.00002938811,0.000008023656,0.93944436,0.0001767691,0.05956169,0.0005156768,0.000013745926],"about_ca_topic_score_codex":0.008248773,"about_ca_topic_score_gemma":0.009514002,"teacher_disagreement_score":0.016956028,"about_ca_system_score_codex":0.0008884489,"about_ca_system_score_gemma":0.0018524517,"threshold_uncertainty_score":0.08967316},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029887963,0.00023303798,0.9683539,0.00017975384,0.000035699108,0.000042101874,0.00025411852,0.00047811412,0.0005353493],"genre_scores_gemma":[0.39357308,0.00020728188,0.604388,0.00011755481,0.000100057325,0.00017145443,0.00082214974,0.00022027522,0.0004001364],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935713,0.0039312164,0.00031422358,0.0014263969,0.00042108158,0.0003357736],"domain_scores_gemma":[0.96527773,0.025203938,0.0024749017,0.004647704,0.0017633094,0.0006323262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016784405,0.00090845587,0.0015850525,0.0040574023,0.0009007663,0.002332366,0.0014790603,0.0013913892,0.0027727226],"category_scores_gemma":[0.072872594,0.00062901026,0.0015353105,0.002940062,0.0019614021,0.002817496,0.003723146,0.0024373517,0.0007072948],"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":[0.0009242575,0.00031089905,0.120038174,0.0006031809,0.00067786704,0.00050134474,0.0014193319,0.19183975,0.011387887,0.08274552,0.007409487,0.5821423],"study_design_scores_gemma":[0.00008346502,0.0001406434,0.027218772,0.00015910546,0.00013262444,0.00032496944,0.000322111,0.74146545,0.007307491,0.21827787,0.0044416487,0.00012583962],"about_ca_topic_score_codex":0.0032128862,"about_ca_topic_score_gemma":0.002329095,"teacher_disagreement_score":0.016784405,"about_ca_system_score_codex":0.0006021236,"about_ca_system_score_gemma":0.0016098015,"threshold_uncertainty_score":0.08876544},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001859401,0.00007230788,0.99777764,0.00007135378,0.000007778041,0.000019661404,0.000015688465,0.000065425986,0.00011072516],"genre_scores_gemma":[0.20115453,0.00056624005,0.7955261,0.00034162716,0.00012265213,0.0004405714,0.00031101605,0.00019298318,0.0013441732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98409456,0.012163039,0.0004707012,0.0016668809,0.0012812685,0.0003235392],"domain_scores_gemma":[0.90635055,0.08083415,0.003715606,0.0060497224,0.0024885566,0.0005614194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02602974,0.0015492854,0.0027997885,0.0017409903,0.0008198375,0.0019693635,0.0044088783,0.0026349262,0.0019898687],"category_scores_gemma":[0.115550354,0.0010194086,0.0021747684,0.001937494,0.0031099692,0.0038602252,0.0042109126,0.004289057,0.0006657804],"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":[0.00034880632,0.00015354961,0.005907638,0.0005213624,0.0005416138,0.00072946324,0.0005520592,0.593183,0.0042678732,0.27857435,0.002061575,0.11315881],"study_design_scores_gemma":[0.000022370923,0.00005146865,0.0004048352,0.000029094603,0.000026705482,0.0000611438,0.000019987752,0.93317866,0.0007582633,0.064845435,0.0005806011,0.00002147033],"about_ca_topic_score_codex":0.0025478993,"about_ca_topic_score_gemma":0.0025724715,"teacher_disagreement_score":0.02602974,"about_ca_system_score_codex":0.0011409911,"about_ca_system_score_gemma":0.002402812,"threshold_uncertainty_score":0.13766003},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006080068,0.00022207125,0.9918419,0.00036416328,0.000029583218,0.000074346746,0.00020203645,0.00016048533,0.0010253993],"genre_scores_gemma":[0.48963895,0.0009006814,0.49972698,0.00057744986,0.00022653527,0.00090950157,0.0011092854,0.00022139779,0.0066892537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994665,0.0032024917,0.00025179074,0.0008022501,0.00078927027,0.00028921026],"domain_scores_gemma":[0.98097587,0.0143373,0.0018487857,0.0017272979,0.00090440904,0.00020628195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011675671,0.0009908038,0.0025540167,0.0009807878,0.00031748397,0.0017331782,0.002232881,0.0018872558,0.0058452315],"category_scores_gemma":[0.065288864,0.0007540909,0.0012427103,0.0008649762,0.0011468503,0.0020859118,0.0016646675,0.0029642885,0.001016583],"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":[0.00038468896,0.00013439743,0.0027501986,0.00023072513,0.00025194473,0.000106259235,0.00011100014,0.6658082,0.0016728719,0.21165091,0.0037475394,0.113151304],"study_design_scores_gemma":[0.000054929857,0.00006869776,0.00058227876,0.000043526295,0.000045708923,0.000031762447,0.000013017181,0.9180871,0.0008838907,0.078601584,0.0015634695,0.000024004676],"about_ca_topic_score_codex":0.002355939,"about_ca_topic_score_gemma":0.0015536464,"teacher_disagreement_score":0.011675671,"about_ca_system_score_codex":0.001157096,"about_ca_system_score_gemma":0.0020506997,"threshold_uncertainty_score":0.06174761},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034455038,0.000050612984,0.9960347,0.00005184942,0.0000073909346,0.0000055448527,0.00002454857,0.00005816348,0.00032176342],"genre_scores_gemma":[0.53685856,0.000833596,0.45772153,0.0003014036,0.00022549513,0.00023774437,0.0005449247,0.00021780186,0.0030589171],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979321,0.00071525876,0.000105915606,0.000471949,0.00063118286,0.00014358724],"domain_scores_gemma":[0.9748258,0.020028226,0.0020729657,0.0014022029,0.0014356591,0.00023524495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006246256,0.0007394348,0.0009375611,0.0017847881,0.0005399457,0.0017388891,0.0019096468,0.0012247826,0.002358637],"category_scores_gemma":[0.04818661,0.00064679695,0.0009722271,0.0012596576,0.0025677336,0.0033699467,0.0025466706,0.0021311438,0.00044575622],"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":[0.000060315044,0.000026595664,0.0018623035,0.00009126741,0.00008129856,0.00016347849,0.00016484193,0.5609321,0.0023272003,0.38557646,0.00074867223,0.04796546],"study_design_scores_gemma":[0.000005592615,0.000009691274,0.0002338115,0.00001109035,0.00000523959,0.00003638464,0.000010487263,0.9035145,0.000597526,0.09516018,0.00040544133,0.000010070961],"about_ca_topic_score_codex":0.0030968585,"about_ca_topic_score_gemma":0.001580742,"teacher_disagreement_score":0.006246256,"about_ca_system_score_codex":0.0009324619,"about_ca_system_score_gemma":0.001169131,"threshold_uncertainty_score":0.03303373},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023925038,0.00011720539,0.97556305,0.000039125156,0.000011583388,0.000019266776,0.00002655609,0.00008000561,0.00021816246],"genre_scores_gemma":[0.5550113,0.0004602422,0.4427961,0.0000544105,0.00009799841,0.00014813995,0.00025960372,0.00007771626,0.0010945966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924374,0.00027192998,0.000036460897,0.00020167764,0.00019787514,0.000048421884],"domain_scores_gemma":[0.9941584,0.0046764915,0.00050128886,0.00027897788,0.000304244,0.00008064524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019778165,0.0005596221,0.0006245185,0.0013269868,0.00021911338,0.0005679698,0.000935491,0.00084638014,0.0010743641],"category_scores_gemma":[0.016367013,0.00024166766,0.00050466775,0.00131123,0.00078135566,0.0010022837,0.0007799281,0.0008915077,0.00029260467],"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":[0.0004350764,0.0001701005,0.013548954,0.00039208855,0.00018026418,0.0005187864,0.0003508075,0.44038418,0.044351928,0.048427198,0.0010466538,0.450194],"study_design_scores_gemma":[0.0000055611354,0.00004719384,0.0019824246,0.0000069952785,0.000008871427,0.000093801485,0.000013441075,0.98852915,0.0022961597,0.0066714827,0.0003318294,0.000013109169],"about_ca_topic_score_codex":0.00091343455,"about_ca_topic_score_gemma":0.00063561514,"teacher_disagreement_score":0.0019778165,"about_ca_system_score_codex":0.00025397568,"about_ca_system_score_gemma":0.00029608182,"threshold_uncertainty_score":0.01045984},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038758286,0.00019664121,0.9944417,0.000120102835,0.000021793003,0.00002455624,0.00011790975,0.00019350194,0.0010079601],"genre_scores_gemma":[0.5600117,0.0019972438,0.42060083,0.00025592354,0.00023918209,0.0005859571,0.0013011331,0.00040569794,0.014602317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997349,0.0014795851,0.00011862643,0.00031999612,0.00055175123,0.0001809496],"domain_scores_gemma":[0.9912009,0.0055709016,0.0006974011,0.0011902584,0.0011594811,0.00018102402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062472215,0.0008783027,0.0016182192,0.0018312548,0.00053754734,0.0018408534,0.0025249657,0.0018604322,0.004964407],"category_scores_gemma":[0.023017129,0.000652048,0.0017613382,0.0026547885,0.0013201747,0.0021436778,0.0016863332,0.0022587616,0.0012594309],"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":[0.0000790666,0.000049923496,0.0020480554,0.00019306144,0.00009060943,0.00017938537,0.00020232743,0.4792332,0.001120847,0.46255895,0.0031211535,0.0511235],"study_design_scores_gemma":[0.000007645553,0.000012967908,0.0002618437,0.000021482478,0.000013365412,0.00006418746,0.000017921417,0.9121034,0.00019084776,0.08531334,0.0019757615,0.000017163395],"about_ca_topic_score_codex":0.0034768493,"about_ca_topic_score_gemma":0.0028392274,"teacher_disagreement_score":0.0062472215,"about_ca_system_score_codex":0.0008101148,"about_ca_system_score_gemma":0.0013018474,"threshold_uncertainty_score":0.033038855},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02357842,0.0001048437,0.9754464,0.0001118377,0.000011081217,0.000033634027,0.00029382,0.00012731503,0.0002925425],"genre_scores_gemma":[0.65463555,0.0003432073,0.34006923,0.0001628181,0.00008037239,0.0004096977,0.0020988728,0.0001084406,0.002091772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965429,0.0022321604,0.00017561587,0.00053062255,0.00040807543,0.00011071846],"domain_scores_gemma":[0.9525631,0.037691146,0.0026913458,0.0055120024,0.0013157956,0.00022666225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007948083,0.00060634664,0.0012604772,0.0010082825,0.00025204706,0.0011165487,0.002215911,0.0011268294,0.0015190069],"category_scores_gemma":[0.05709583,0.0004031209,0.0010054001,0.0011212747,0.00092811114,0.0011621515,0.001784682,0.0015125464,0.00031701516],"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":[0.00048638738,0.0002501571,0.042578667,0.0005764071,0.0006388441,0.00045109823,0.0006680216,0.5096643,0.005761384,0.15612625,0.0037690578,0.2790294],"study_design_scores_gemma":[0.00003564509,0.00007932773,0.008382723,0.000052053725,0.000053570173,0.0001704354,0.000060607512,0.9231168,0.0016276466,0.064945325,0.0014277746,0.00004809498],"about_ca_topic_score_codex":0.0015494388,"about_ca_topic_score_gemma":0.0013636013,"teacher_disagreement_score":0.007948083,"about_ca_system_score_codex":0.0004475882,"about_ca_system_score_gemma":0.00093167997,"threshold_uncertainty_score":0.04203397},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043192565,0.00021835041,0.9514177,0.00036720364,0.000083314146,0.00045185347,0.0010564039,0.00077076355,0.002441813],"genre_scores_gemma":[0.63295525,0.0002331146,0.3593862,0.000357174,0.00024679874,0.0028086423,0.0025008386,0.0002487956,0.0012630776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9496846,0.03739772,0.00176341,0.0055477843,0.004689471,0.0009170744],"domain_scores_gemma":[0.5718101,0.39268625,0.011189937,0.016877191,0.006194595,0.0012419076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036255058,0.0015003013,0.0019455807,0.0034372073,0.0010985731,0.002686015,0.0029974265,0.0017631097,0.010659091],"category_scores_gemma":[0.28474808,0.00079321116,0.002085877,0.0033536146,0.004717167,0.0052316026,0.0026927975,0.0034781282,0.001621468],"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":[0.0015691967,0.0005215565,0.03428053,0.001288741,0.00212784,0.0012974987,0.0008047292,0.25012037,0.0052883825,0.42885938,0.011883161,0.2619586],"study_design_scores_gemma":[0.0003832286,0.00077559956,0.008135666,0.00014826396,0.00013479184,0.0003367517,0.00024713125,0.70763934,0.003255035,0.2762029,0.0026413612,0.00009993474],"about_ca_topic_score_codex":0.0007257713,"about_ca_topic_score_gemma":0.0006283871,"teacher_disagreement_score":0.036255058,"about_ca_system_score_codex":0.0010445621,"about_ca_system_score_gemma":0.0025959625,"threshold_uncertainty_score":0.19173741},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035439825,0.000036567995,0.9992299,0.0001183378,0.000008865371,0.000016117416,0.00003773829,0.00009518372,0.000102809245],"genre_scores_gemma":[0.042184107,0.00026082763,0.9536992,0.00028028176,0.00020910914,0.00056093716,0.0004523083,0.00026855626,0.0020847425],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99186796,0.0059848153,0.00026194213,0.00080686394,0.0009178558,0.00016058522],"domain_scores_gemma":[0.97751665,0.017589418,0.0012111028,0.0019363976,0.0014251327,0.0003213294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013053186,0.0012900352,0.0017370741,0.0022357386,0.00067735044,0.0017222983,0.004518973,0.0018610106,0.006891759],"category_scores_gemma":[0.05107844,0.0009588768,0.0019301535,0.002642893,0.0013894096,0.0019776726,0.0030826046,0.0042948727,0.0026680809],"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":[0.00016569771,0.00023822067,0.005996803,0.00054380525,0.00043143024,0.0003148531,0.00038109982,0.3471399,0.0034299803,0.34569278,0.010340308,0.28532517],"study_design_scores_gemma":[0.000030795803,0.0000400922,0.0005743904,0.00003403139,0.000022832739,0.000098927354,0.000020435831,0.87579626,0.00042044307,0.1194763,0.0034499401,0.00003545924],"about_ca_topic_score_codex":0.0030048771,"about_ca_topic_score_gemma":0.0031438174,"teacher_disagreement_score":0.013053186,"about_ca_system_score_codex":0.0009657301,"about_ca_system_score_gemma":0.0021178923,"threshold_uncertainty_score":0.06903273},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042183995,0.0034114872,0.98801416,0.0023457075,0.0002753326,0.00013039919,0.00061726384,0.00020787673,0.0007793315],"genre_scores_gemma":[0.32972968,0.013892901,0.64256215,0.0017545255,0.0024659666,0.0021021704,0.0024112742,0.00029537955,0.004785891],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9779668,0.018016022,0.00062075397,0.0015010275,0.0015944068,0.0003009357],"domain_scores_gemma":[0.8977566,0.0897814,0.0051879575,0.004866042,0.0017025687,0.0007054583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04090419,0.0020372372,0.0032120799,0.0032627396,0.0009543648,0.0023063286,0.004069009,0.0021365576,0.0045908988],"category_scores_gemma":[0.1107931,0.0010526116,0.0028830597,0.0032226574,0.0041142744,0.0035849086,0.003096395,0.005562437,0.0009709775],"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":[0.0005172849,0.00026947394,0.015231136,0.0016934748,0.002779751,0.00046746415,0.001107416,0.093751624,0.0008961759,0.6752725,0.01824513,0.18976854],"study_design_scores_gemma":[0.00007279643,0.00021757031,0.0031961163,0.00025056227,0.00033048223,0.00023273271,0.00011385924,0.25316963,0.00035107994,0.73414564,0.007844568,0.000075007236],"about_ca_topic_score_codex":0.0064631375,"about_ca_topic_score_gemma":0.004771532,"teacher_disagreement_score":0.04090419,"about_ca_system_score_codex":0.0014403571,"about_ca_system_score_gemma":0.0030031393,"threshold_uncertainty_score":0.21632463},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006853325,0.99758303,0.00068785733,0.00069952157,0.00020147365,0.0000068107424,0.000034335433,0.0000059602226,0.00071258686],"genre_scores_gemma":[0.0007988178,0.9978694,0.0006032781,0.00019639233,0.00030878,0.000012986344,0.000040976807,0.0000044538715,0.00016498573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873596,0.00036934816,0.00021578268,0.00023754619,0.00039091235,0.00005054198],"domain_scores_gemma":[0.9918555,0.0061132084,0.00054634095,0.00020233249,0.0011365417,0.00014607568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038726323,0.0011928946,0.002110679,0.0061796717,0.0004913398,0.0022809955,0.0020132381,0.0018988864,0.0043480676],"category_scores_gemma":[0.010055074,0.0006966667,0.0011215182,0.011125789,0.0013095795,0.0040031914,0.0011459095,0.002313206,0.0023346462],"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":[0.00006587509,0.00009258073,0.00075381354,0.032597035,0.0001849249,0.00013562194,0.00018319975,0.00079681585,0.0002771536,0.038786177,0.034258276,0.89186835],"study_design_scores_gemma":[0.000017794073,0.00007926104,0.0027562878,0.031851463,0.00026785803,0.0008595122,0.00021409504,0.00050394813,0.00022224794,0.023188332,0.9399799,0.0000592684],"about_ca_topic_score_codex":0.0027101457,"about_ca_topic_score_gemma":0.0027325165,"teacher_disagreement_score":0.0061796717,"about_ca_system_score_codex":0.0014385607,"about_ca_system_score_gemma":0.0037163869,"threshold_uncertainty_score":0.020480692},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03080327,0.00083912513,0.96194583,0.0036050214,0.00007491512,0.00027087715,0.00019923557,0.00039872984,0.0018631528],"genre_scores_gemma":[0.6469623,0.00038764314,0.34999722,0.0008631593,0.00016317528,0.00050572853,0.00023622287,0.0001167266,0.00076781964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8068689,0.16072425,0.006786201,0.009137033,0.0145561,0.0019275075],"domain_scores_gemma":[0.5385876,0.31067705,0.028975274,0.110174604,0.009765767,0.0018195516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14746787,0.0012796303,0.002119868,0.0020857193,0.0019436548,0.006164325,0.004833904,0.0031548655,0.0014906299],"category_scores_gemma":[0.3638474,0.0012622266,0.001960911,0.003171493,0.005389826,0.010065973,0.011950739,0.005003737,0.00048147276],"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":[0.0025499067,0.00036600884,0.04722594,0.0013541599,0.0019095184,0.0007878522,0.009016158,0.10814062,0.011320117,0.35939837,0.0048420276,0.45308942],"study_design_scores_gemma":[0.00030932468,0.0006485192,0.007039525,0.0005087272,0.0006395075,0.0010051485,0.00095466804,0.3962874,0.020373274,0.5614627,0.010592276,0.00017895017],"about_ca_topic_score_codex":0.0012424925,"about_ca_topic_score_gemma":0.0009991775,"teacher_disagreement_score":0.14746787,"about_ca_system_score_codex":0.0025827975,"about_ca_system_score_gemma":0.0070136185,"threshold_uncertainty_score":0.77989393},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055651847,0.0008380613,0.9339203,0.0020520454,0.00013589028,0.00015333819,0.0022654778,0.00055816007,0.0044248793],"genre_scores_gemma":[0.8791119,0.0012258661,0.0957265,0.0009223684,0.00035908844,0.00092604425,0.0029999258,0.0001660488,0.018562255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963085,0.001844967,0.0001386687,0.0008854013,0.00037947585,0.0004429327],"domain_scores_gemma":[0.99207073,0.0050224126,0.0011322019,0.0006115468,0.00079191633,0.00037111592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058926716,0.0014031823,0.002547646,0.0017036921,0.00048182925,0.0021079548,0.003347263,0.002308993,0.006808589],"category_scores_gemma":[0.011715459,0.0008197192,0.0020378064,0.0019494346,0.0018167926,0.002630674,0.0023073733,0.0026379018,0.0011168666],"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":[0.00050320686,0.00022516998,0.020259095,0.00032423253,0.00048672373,0.0011210789,0.00048190614,0.5862785,0.0019460771,0.33169845,0.006155482,0.05052008],"study_design_scores_gemma":[0.000077961886,0.00013122843,0.0030647602,0.000032377127,0.000102965554,0.00021644519,0.000056997134,0.9217609,0.00020278573,0.07115607,0.0031311559,0.000066454835],"about_ca_topic_score_codex":0.00703622,"about_ca_topic_score_gemma":0.0038046476,"teacher_disagreement_score":0.00703622,"about_ca_system_score_codex":0.0013123557,"about_ca_system_score_gemma":0.0015068142,"threshold_uncertainty_score":0.031163812},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013392212,0.00022815597,0.9841875,0.00021910702,0.000019380055,0.000027761866,0.000061017217,0.001086793,0.0007781257],"genre_scores_gemma":[0.27274346,0.000485886,0.722713,0.00026749214,0.00007059981,0.00017673627,0.0005468228,0.00043574275,0.002560205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999014,0.000409358,0.00003677733,0.00015276758,0.00029596497,0.00009104943],"domain_scores_gemma":[0.9932922,0.0054110065,0.00033692998,0.00043627975,0.000373167,0.00015055313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028202583,0.0008564032,0.00143996,0.0011920155,0.00060747983,0.0011278866,0.002037058,0.0016836599,0.003082952],"category_scores_gemma":[0.016164068,0.00081310386,0.0010824301,0.0014664842,0.00090060756,0.0022276847,0.0018374134,0.0022480204,0.001082789],"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":[0.00007513751,0.000059334005,0.0009907442,0.0000969522,0.0000386314,0.000045413504,0.00009619202,0.8708163,0.001188057,0.036898363,0.0024885463,0.08720644],"study_design_scores_gemma":[0.000008610335,0.0000057201237,0.00005226704,0.0000046487207,0.0000032099167,0.000008596394,0.000004012407,0.9867512,0.00024358285,0.012714552,0.00020055755,0.0000029415737],"about_ca_topic_score_codex":0.012712889,"about_ca_topic_score_gemma":0.019635374,"teacher_disagreement_score":0.012712889,"about_ca_system_score_codex":0.0014868242,"about_ca_system_score_gemma":0.0026634575,"threshold_uncertainty_score":0.025277793},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006484584,0.000033931232,0.9979824,0.00019728132,0.000008567613,0.000034518987,0.00008233985,0.0004450461,0.00056749734],"genre_scores_gemma":[0.044442233,0.00009614568,0.9537438,0.0001838978,0.000041597046,0.00032816987,0.00024241036,0.00025726066,0.0006645243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9879423,0.0073100924,0.0006942617,0.0014696427,0.002228075,0.00035560658],"domain_scores_gemma":[0.9152931,0.07075437,0.002733841,0.008286801,0.002442729,0.0004892428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016873945,0.0014539169,0.0019297989,0.0029608926,0.0014740918,0.0042523374,0.0041760425,0.0021182438,0.013357877],"category_scores_gemma":[0.106971115,0.0015413528,0.002841545,0.0028183574,0.0035998554,0.0047620195,0.0059450017,0.0070385626,0.0023328208],"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":[0.00016114654,0.00014767429,0.0025089493,0.00057694764,0.00020519133,0.00020652515,0.0005926789,0.22044118,0.0015891313,0.6171547,0.0052888566,0.15112704],"study_design_scores_gemma":[0.00006433691,0.000022441774,0.00019654528,0.00007367075,0.000025452333,0.000058409674,0.000044853838,0.37644395,0.0011749621,0.61769634,0.004177173,0.0000218117],"about_ca_topic_score_codex":0.003443992,"about_ca_topic_score_gemma":0.0054437835,"teacher_disagreement_score":0.016873945,"about_ca_system_score_codex":0.0025908982,"about_ca_system_score_gemma":0.006180087,"threshold_uncertainty_score":0.089239},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29329357,0.0012610691,0.7016689,0.0007558766,0.0001544211,0.00026446782,0.00088621327,0.00028378316,0.001431669],"genre_scores_gemma":[0.8453929,0.00051567936,0.14994109,0.00025033185,0.00017839111,0.0005120385,0.0022148339,0.00009786453,0.0008968132],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9622275,0.026951341,0.0024215241,0.0048575397,0.002639333,0.0009027793],"domain_scores_gemma":[0.5315288,0.43304652,0.017207246,0.01337417,0.0029839838,0.0018593523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09361559,0.0009114541,0.0023614326,0.003663007,0.0008253916,0.0028012746,0.0025405842,0.0029678885,0.0032487293],"category_scores_gemma":[0.27336553,0.00072909356,0.0022819203,0.0042830477,0.0032065092,0.0036016975,0.0033264016,0.0036564472,0.00039549958],"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":[0.0031015545,0.0009173901,0.56080765,0.0011127316,0.0034270529,0.0019771256,0.0014765507,0.16167471,0.0037513962,0.08089782,0.0019441062,0.17891198],"study_design_scores_gemma":[0.00028696694,0.0015498172,0.1642337,0.00041709267,0.0012428915,0.0015398483,0.00083396054,0.5872587,0.0058609317,0.23148938,0.0050271815,0.00025954295],"about_ca_topic_score_codex":0.00145463,"about_ca_topic_score_gemma":0.0015387308,"teacher_disagreement_score":0.09361559,"about_ca_system_score_codex":0.001037303,"about_ca_system_score_gemma":0.0022701619,"threshold_uncertainty_score":0.4950925},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005979411,0.0002673115,0.9897898,0.00027181432,0.00008347002,0.00013070383,0.00020577094,0.0004521768,0.002819577],"genre_scores_gemma":[0.38457102,0.0009784352,0.6057913,0.00049679965,0.00045242233,0.0014623179,0.0012987007,0.00059935765,0.0043495796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95820034,0.03328233,0.0011618623,0.002283944,0.004331883,0.00073958223],"domain_scores_gemma":[0.8298489,0.14829434,0.006720416,0.009683511,0.0048019923,0.0006508549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032240205,0.0013985117,0.0023704648,0.003029976,0.0009278512,0.002582218,0.0034384062,0.0018925222,0.008009789],"category_scores_gemma":[0.23073721,0.00073812,0.0020869859,0.00398356,0.0039282735,0.0042807953,0.0035287347,0.0038368334,0.0017407193],"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":[0.0003715476,0.00017108371,0.005452718,0.00038766855,0.00048350234,0.0005020284,0.0002840426,0.122365676,0.00079425913,0.66433513,0.003941293,0.20091115],"study_design_scores_gemma":[0.00013579037,0.0002593276,0.0016115604,0.00008616244,0.000072329996,0.00016663504,0.00008619672,0.33710712,0.0012659661,0.6539491,0.005173769,0.00008590236],"about_ca_topic_score_codex":0.001464209,"about_ca_topic_score_gemma":0.00087072165,"teacher_disagreement_score":0.032240205,"about_ca_system_score_codex":0.0011729437,"about_ca_system_score_gemma":0.003541684,"threshold_uncertainty_score":0.17050451},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030896836,0.00012346053,0.99603206,0.00006982862,0.000025755162,0.000039664246,0.00015312571,0.00018794916,0.0002783885],"genre_scores_gemma":[0.092744395,0.00030091632,0.9047332,0.00017973487,0.00013371622,0.00048397665,0.00050030067,0.0002167297,0.00070710486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99274,0.002887776,0.00074496254,0.0015201787,0.0018126855,0.00029439136],"domain_scores_gemma":[0.9692044,0.0188564,0.00267252,0.0058428734,0.002571567,0.0008522676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01077202,0.0012487848,0.0015304929,0.003517542,0.0010927322,0.003083226,0.0023431603,0.0014040124,0.0033642855],"category_scores_gemma":[0.055102117,0.0007735117,0.002542603,0.0035497537,0.003835319,0.0070689376,0.005985463,0.00335316,0.0010075936],"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":[0.0007313244,0.00010813559,0.010014794,0.0009713732,0.00032810887,0.00038862263,0.0016665723,0.091900386,0.0142348055,0.43870187,0.004841557,0.4361124],"study_design_scores_gemma":[0.00009084147,0.000570824,0.004071846,0.00012290124,0.000063592655,0.0007095793,0.00037689676,0.39546192,0.010963305,0.558277,0.029138386,0.00015295015],"about_ca_topic_score_codex":0.0014294051,"about_ca_topic_score_gemma":0.0014047761,"teacher_disagreement_score":0.01077202,"about_ca_system_score_codex":0.0013701578,"about_ca_system_score_gemma":0.0021246031,"threshold_uncertainty_score":0.05696857},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041969703,0.0001318819,0.994773,0.00019737626,0.000021590155,0.000020355767,0.00007216333,0.0001845379,0.0004021661],"genre_scores_gemma":[0.20221908,0.0008862674,0.79064816,0.00041602718,0.0002732258,0.00021632324,0.0006752073,0.00021038312,0.0044552935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986523,0.0006253483,0.000041339226,0.00022703272,0.00035847924,0.000095585856],"domain_scores_gemma":[0.99687755,0.0015960521,0.00036702372,0.0006049138,0.00044104925,0.00011355073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028915284,0.0011949479,0.0016354751,0.00093442196,0.00048960315,0.0011670814,0.0018782733,0.0015152105,0.001757577],"category_scores_gemma":[0.008335621,0.0005697091,0.00083671673,0.0015527708,0.0015096866,0.0018824885,0.0015338273,0.0023329342,0.0009865462],"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":[0.00011258619,0.00009068114,0.001235635,0.00020509482,0.0001147726,0.00017685321,0.00010838869,0.81892043,0.008358469,0.08765677,0.005746415,0.07727397],"study_design_scores_gemma":[0.000006138159,0.000014214298,0.00010073369,0.0000043961295,0.0000043599425,0.000014158207,0.000004930404,0.99043626,0.0007927078,0.007956572,0.0006572518,0.000008409324],"about_ca_topic_score_codex":0.002790648,"about_ca_topic_score_gemma":0.0033403866,"teacher_disagreement_score":0.0028915284,"about_ca_system_score_codex":0.00060502504,"about_ca_system_score_gemma":0.0013518616,"threshold_uncertainty_score":0.015292048},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070398916,0.0003201049,0.9901545,0.00052960234,0.00004556119,0.000116428935,0.00010028487,0.00033669305,0.0013567599],"genre_scores_gemma":[0.47801694,0.0006859212,0.5134404,0.0010386335,0.0004186789,0.000691941,0.00089429424,0.00026418464,0.0045490977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934069,0.002860995,0.0003001972,0.0012016296,0.0018138997,0.00041634275],"domain_scores_gemma":[0.9771674,0.016574735,0.001822177,0.0020784636,0.0018049878,0.00055225356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012424615,0.0013777404,0.0029686026,0.0030320897,0.0009573632,0.0029552926,0.0041387114,0.0024115853,0.0036930724],"category_scores_gemma":[0.03254646,0.00077270274,0.0014040298,0.00273849,0.002051174,0.0037809683,0.0037768378,0.0047082184,0.0012005521],"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":[0.00041353892,0.00039080894,0.0045199785,0.00032908155,0.00021112479,0.00017950425,0.0002534291,0.4584613,0.0014798216,0.109498926,0.013881653,0.41038084],"study_design_scores_gemma":[0.000019203193,0.000039521543,0.0003680679,0.000023836827,0.000015468551,0.00005712009,0.000020932743,0.9523182,0.00065619394,0.045495793,0.00097182713,0.000013882366],"about_ca_topic_score_codex":0.0022823254,"about_ca_topic_score_gemma":0.0018506382,"teacher_disagreement_score":0.012424615,"about_ca_system_score_codex":0.0023943195,"about_ca_system_score_gemma":0.002812676,"threshold_uncertainty_score":0.06570846},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038263462,0.00115082,0.91264474,0.0021171323,0.000613624,0.00025746066,0.00988508,0.008547545,0.06095725],"genre_scores_gemma":[0.16860217,0.0020458722,0.5470852,0.0022148476,0.0016566239,0.0013764269,0.035460223,0.007801407,0.23375726],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972652,0.001061944,0.00012427662,0.0007953074,0.0005824204,0.00017088525],"domain_scores_gemma":[0.9947885,0.002512838,0.00016725618,0.0017497676,0.00065097644,0.0001307142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032358202,0.0011895394,0.0014680002,0.0025205945,0.0010473132,0.0043124147,0.0023893374,0.002085328,0.12928396],"category_scores_gemma":[0.026611926,0.00094695383,0.0015244719,0.0023053677,0.00096199126,0.004110363,0.0023691356,0.0030217983,0.079484746],"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":[0.0003218553,0.0001629614,0.0034878321,0.0003904984,0.00023226738,0.000348413,0.0001861667,0.028269073,0.0012908094,0.35038126,0.22194484,0.39298394],"study_design_scores_gemma":[0.00014780434,0.000059177495,0.0013225634,0.00014642577,0.000095941396,0.0010760294,0.000107975626,0.1727977,0.0033198039,0.62196606,0.1989032,0.000057366313],"about_ca_topic_score_codex":0.0022989835,"about_ca_topic_score_gemma":0.002860632,"teacher_disagreement_score":0.12928396,"about_ca_system_score_codex":0.0010316845,"about_ca_system_score_gemma":0.0020669883,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004225937,0.00034935444,0.00021989214,0.9649589,0.028817056,0.000024825998,0.0002915146,0.000075064534,0.0048407447],"genre_scores_gemma":[0.0015852831,0.00010537993,0.00018059605,0.9827907,0.011755453,0.00004047988,0.000057152512,0.00003639472,0.0034485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9708928,0.005893332,0.0030312168,0.0063472865,0.011083143,0.0027523004],"domain_scores_gemma":[0.7919509,0.12755996,0.011400655,0.013331244,0.04779006,0.007967153],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03107339,0.0009668603,0.0018913643,0.0019457531,0.005302906,0.006603402,0.0071643963,0.060906086,0.039461907],"category_scores_gemma":[0.28296226,0.0013560667,0.003260577,0.0029806786,0.007897329,0.0058781197,0.0039023869,0.051817887,0.034168873],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057278037,0.000009456994,0.0006961615,0.00004737091,0.000024048893,0.00011244997,0.00014240856,0.00003840269,0.00007904452,0.0034747252,0.99333537,0.0019833113],"study_design_scores_gemma":[0.00021905114,0.000052433432,0.005290133,0.0006542096,0.00009825804,0.00050902076,0.00075559353,0.00034663704,0.000601027,0.014250222,0.9770815,0.00014198876],"about_ca_topic_score_codex":0.028358495,"about_ca_topic_score_gemma":0.021408781,"teacher_disagreement_score":0.9605381,"about_ca_system_score_codex":0.006851454,"about_ca_system_score_gemma":0.01009316,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004130436,0.0003573245,0.00021653756,0.9664491,0.027387217,0.000023877072,0.00027473285,0.00007162674,0.0048065223],"genre_scores_gemma":[0.0015917934,0.000107897504,0.0001824317,0.98282295,0.011699559,0.00004014171,0.000054240925,0.000035063986,0.0034659659],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9710125,0.005868879,0.0030214048,0.0063934354,0.010994882,0.0027089342],"domain_scores_gemma":[0.7918401,0.12764755,0.011848863,0.013513431,0.046955656,0.008194398],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.031701386,0.0009756214,0.0018902267,0.0019139899,0.005397702,0.0066581247,0.0070649427,0.0628118,0.038385306],"category_scores_gemma":[0.27992103,0.0013531962,0.0032379527,0.0029126948,0.007959935,0.00602558,0.003933512,0.051774256,0.033369325],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006238042,0.000009971144,0.0007270477,0.00004936265,0.000025396148,0.00012039208,0.00015332966,0.000040133044,0.00008491103,0.0037796656,0.9928906,0.0020568627],"study_design_scores_gemma":[0.00021804312,0.00005288962,0.0051162792,0.0006414645,0.00009716773,0.00049122673,0.0007327572,0.00033086166,0.0005910144,0.014309829,0.97728044,0.00013799577],"about_ca_topic_score_codex":0.027505754,"about_ca_topic_score_gemma":0.021043038,"teacher_disagreement_score":0.96161467,"about_ca_system_score_codex":0.006857686,"about_ca_system_score_gemma":0.009988676,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037484986,0.00052796956,0.00030796134,0.9546807,0.038061447,0.00002839418,0.00045624163,0.000083486106,0.0054789395],"genre_scores_gemma":[0.0015933074,0.00016095124,0.00020127083,0.97874796,0.015690662,0.000058252164,0.000070141396,0.00003579552,0.0034415717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9710065,0.006579783,0.0032906272,0.0060127503,0.010607616,0.0025026945],"domain_scores_gemma":[0.77782565,0.14421473,0.011966448,0.01363043,0.0445993,0.0077634226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035985626,0.0008135441,0.0016198724,0.0017254369,0.0037627032,0.005283907,0.005546402,0.044064414,0.03460726],"category_scores_gemma":[0.28745422,0.001158312,0.002839766,0.0026887755,0.0064791623,0.0044306763,0.0029784164,0.04221438,0.026575463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005063057,0.000008566655,0.0009034272,0.00006953649,0.000026439502,0.00010506727,0.00014258125,0.000037682825,0.000056444682,0.0046094647,0.9909376,0.0030525262],"study_design_scores_gemma":[0.00015517157,0.000034836226,0.00508059,0.0007175307,0.00007291573,0.00040611922,0.00045698258,0.00023648478,0.00032708616,0.010073878,0.98233175,0.000106688654],"about_ca_topic_score_codex":0.019752149,"about_ca_topic_score_gemma":0.014812766,"teacher_disagreement_score":0.044064414,"about_ca_system_score_codex":0.0050410666,"about_ca_system_score_gemma":0.009407575,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006957764,0.0000918628,0.99248135,0.000069056325,0.000013825813,0.00001633597,0.000014271209,0.00010018166,0.00025528567],"genre_scores_gemma":[0.25652036,0.0002555421,0.7390406,0.00012245502,0.00007019163,0.00021403554,0.00024530615,0.00020079491,0.003330767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971347,0.001711606,0.00010188017,0.0003071853,0.00062290364,0.00012181059],"domain_scores_gemma":[0.99230427,0.00612169,0.0004416964,0.0003677183,0.00055703096,0.0002076012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005150482,0.00080020825,0.0011396892,0.0011385336,0.00073127233,0.0013750808,0.0019383951,0.0011234987,0.002033127],"category_scores_gemma":[0.0123765785,0.0007492008,0.00097238924,0.00093493675,0.0015301016,0.0014552057,0.0019104067,0.0015677484,0.0004239795],"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":[0.00020603748,0.0000793791,0.0019541543,0.00015608469,0.000092916554,0.00023973291,0.00018319883,0.7584578,0.0035161215,0.13464803,0.0014907098,0.09897592],"study_design_scores_gemma":[0.000007274925,0.000012266378,0.00013117619,0.00000530701,0.0000036122217,0.000018548368,0.0000046661708,0.986148,0.00052808196,0.0126685845,0.00046290265,0.000009499617],"about_ca_topic_score_codex":0.0045041703,"about_ca_topic_score_gemma":0.0047421088,"teacher_disagreement_score":0.005150482,"about_ca_system_score_codex":0.0011807014,"about_ca_system_score_gemma":0.0015554567,"threshold_uncertainty_score":0.027238667},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001974156,0.0013422872,0.0067188963,0.56359446,0.38185227,0.00023876585,0.00063232455,0.002060274,0.0415865],"genre_scores_gemma":[0.011105602,0.00076180894,0.00545468,0.5016799,0.09454842,0.00027923018,0.0006017296,0.0011650769,0.38440356],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99597836,0.00063202926,0.00026611495,0.00067348045,0.0020177062,0.00043233723],"domain_scores_gemma":[0.9730006,0.0056336764,0.00061946723,0.0032606758,0.013920312,0.0035652893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043559186,0.0007120479,0.001057624,0.0010756114,0.002616307,0.0035839586,0.0027824277,0.015134844,0.0963522],"category_scores_gemma":[0.04637268,0.00041155607,0.0011267826,0.0004431477,0.0014510329,0.002968477,0.0029623162,0.014076632,0.08134783],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042272426,0.000022361608,0.00015140169,0.000020635833,0.0000043580753,0.000092699374,0.000046242112,0.000017918997,0.00024909247,0.001028735,0.9882359,0.010088384],"study_design_scores_gemma":[0.00002976948,0.000026601188,0.0004039102,0.0000662539,0.000013983912,0.00018117517,0.00016527776,0.00013644254,0.00024647693,0.0042693145,0.9944402,0.000020669426],"about_ca_topic_score_codex":0.0044112545,"about_ca_topic_score_gemma":0.009068148,"teacher_disagreement_score":0.0963522,"about_ca_system_score_codex":0.0012324296,"about_ca_system_score_gemma":0.0023324303,"threshold_uncertainty_score":0},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024038984,0.00061162474,0.973004,0.0004980698,0.00004735371,0.00003639305,0.00011665683,0.0002754795,0.0013713959],"genre_scores_gemma":[0.6943721,0.0011687094,0.2978749,0.00032151694,0.0001806536,0.00026827672,0.000351829,0.00017586713,0.005286122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922185,0.005429234,0.00018841084,0.0009056926,0.00090068555,0.00035742568],"domain_scores_gemma":[0.9732387,0.02128756,0.0022855233,0.0016031436,0.001104187,0.0004808706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013894877,0.0011894222,0.0024039734,0.0020058423,0.0007767629,0.0021967806,0.002361837,0.0023067773,0.0050297095],"category_scores_gemma":[0.040012967,0.0009846325,0.0020892057,0.0027497578,0.0030015863,0.0028621969,0.002655789,0.0038766407,0.00072355283],"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":[0.00032504808,0.00013104505,0.007626617,0.00019489731,0.00046839166,0.00028518162,0.00038813002,0.46500272,0.0014416984,0.45807433,0.0018807185,0.064181134],"study_design_scores_gemma":[0.000051686708,0.00007969737,0.001982197,0.000051603474,0.00011106156,0.000054085547,0.000037622933,0.6771451,0.00024179627,0.3180881,0.0021052398,0.00005171338],"about_ca_topic_score_codex":0.010409061,"about_ca_topic_score_gemma":0.008852177,"teacher_disagreement_score":0.013894877,"about_ca_system_score_codex":0.0011471474,"about_ca_system_score_gemma":0.0013879131,"threshold_uncertainty_score":0.073484},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006757549,0.00053842517,0.00087176356,0.93120444,0.06411506,0.000037180504,0.0004049892,0.00011393098,0.0020385755],"genre_scores_gemma":[0.0022021339,0.0003239614,0.0007415518,0.9640434,0.027197612,0.00007004519,0.00014418509,0.000053984553,0.005223134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863777,0.0028646193,0.001650046,0.0021151386,0.00545587,0.0015365487],"domain_scores_gemma":[0.90739685,0.04562183,0.0050487933,0.0021859377,0.034193907,0.005552661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018109309,0.001469091,0.0013443058,0.0015776916,0.006158713,0.0058231005,0.0032822045,0.038944166,0.0097443545],"category_scores_gemma":[0.11938705,0.0011271884,0.0022851806,0.0020193935,0.0040794825,0.0047015417,0.0044697546,0.03400037,0.008913148],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002625237,0.000010041889,0.0005373099,0.000050255345,0.0000130176095,0.00011611535,0.00017594233,0.000073264186,0.00020386615,0.0010554113,0.994871,0.0028674803],"study_design_scores_gemma":[0.000055474557,0.000051834566,0.005479418,0.0005557933,0.00005255322,0.00022612937,0.0013755215,0.0005975708,0.0006617103,0.0032384808,0.98757076,0.00013474695],"about_ca_topic_score_codex":0.03220882,"about_ca_topic_score_gemma":0.035447076,"teacher_disagreement_score":0.038944166,"about_ca_system_score_codex":0.0036290819,"about_ca_system_score_gemma":0.009542119,"threshold_uncertainty_score":0.095772326},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004152792,0.00022477382,0.9946202,0.0001834813,0.000020988351,0.00008194428,0.00008085162,0.000340387,0.00029452675],"genre_scores_gemma":[0.42359933,0.00064078195,0.5703853,0.00061105716,0.0002780595,0.0009879642,0.0010339724,0.00029831287,0.002165287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891726,0.0070750127,0.0003896205,0.0010196766,0.001968352,0.00037479942],"domain_scores_gemma":[0.954641,0.033274822,0.0025993208,0.0052595506,0.0034687489,0.00075641595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0179844,0.001833758,0.002366393,0.0031119166,0.0010391873,0.0019054626,0.0028041974,0.0018575585,0.0023317346],"category_scores_gemma":[0.07181957,0.0005866541,0.0015871003,0.003713198,0.0031291842,0.0036091565,0.003500084,0.0032979916,0.0008264092],"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":[0.00059519854,0.00035914683,0.01204921,0.0006889066,0.0003227544,0.00055789243,0.00035084412,0.34150726,0.0046030744,0.30957437,0.009432741,0.31995854],"study_design_scores_gemma":[0.000031897656,0.00010173325,0.00088870217,0.000026597258,0.000024918918,0.00007454827,0.000027669514,0.87948143,0.001449541,0.11680107,0.0010561674,0.000035776633],"about_ca_topic_score_codex":0.002057207,"about_ca_topic_score_gemma":0.0019647419,"teacher_disagreement_score":0.0179844,"about_ca_system_score_codex":0.0013333706,"about_ca_system_score_gemma":0.0031643494,"threshold_uncertainty_score":0.09511179},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053962916,0.00042688547,0.9927578,0.00018943072,0.00002479625,0.000027854698,0.000097196586,0.00019828859,0.0008813713],"genre_scores_gemma":[0.3074315,0.0019888994,0.6838614,0.00033627686,0.00024765794,0.00030299934,0.0010783048,0.00033243265,0.004420596],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99752194,0.0010808461,0.00008172932,0.00059065287,0.0005301336,0.00019473911],"domain_scores_gemma":[0.99535096,0.0025168364,0.0006033179,0.00060602534,0.0006870708,0.00023579293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004411137,0.001113794,0.0017570073,0.0032516073,0.001557324,0.0018575179,0.0027297866,0.0022961511,0.0030164046],"category_scores_gemma":[0.015871407,0.0008877753,0.0014625131,0.0042835176,0.0023235704,0.0048706452,0.0020843083,0.0021422072,0.0011564107],"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":[0.0000934932,0.0000746887,0.0020498948,0.00018312596,0.00009662884,0.000106934094,0.00023030677,0.5451425,0.0011844175,0.36007693,0.00483158,0.08592948],"study_design_scores_gemma":[0.000006646876,0.000008916092,0.00028187866,0.000017481585,0.000011089929,0.000059765607,0.000018141083,0.8429911,0.0002523919,0.15513977,0.0011954872,0.0000173113],"about_ca_topic_score_codex":0.011031779,"about_ca_topic_score_gemma":0.013081542,"teacher_disagreement_score":0.011031779,"about_ca_system_score_codex":0.0022171345,"about_ca_system_score_gemma":0.002040432,"threshold_uncertainty_score":0.023328543},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064461534,0.00018053107,0.9887638,0.00009475335,0.00005697943,0.000064542386,0.00023306422,0.003481298,0.00067894673],"genre_scores_gemma":[0.13909203,0.00025313464,0.85522187,0.0001645483,0.00020334974,0.0003647043,0.0008017173,0.0009462618,0.0029522937],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907506,0.00024725476,0.00004429581,0.00016187136,0.00041078212,0.000060685783],"domain_scores_gemma":[0.99662846,0.0018312165,0.00034123633,0.0004125744,0.0006021619,0.00018434056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019249088,0.0010065578,0.00092890026,0.0020849542,0.00051952817,0.0009237697,0.0029463195,0.0009132348,0.0042250548],"category_scores_gemma":[0.011361623,0.0005819727,0.00058811164,0.0014806152,0.00061143585,0.0017357938,0.0018538674,0.001022966,0.0013606683],"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":[0.0006253555,0.00029039383,0.010538156,0.00029142338,0.00021161769,0.00029951907,0.00038157686,0.17275806,0.014180172,0.027598992,0.024316743,0.748508],"study_design_scores_gemma":[0.00004043152,0.000038496233,0.0007474189,0.00000822633,0.000010527939,0.00011942211,0.000020860056,0.98508936,0.0023296422,0.008122581,0.0034473364,0.000025687712],"about_ca_topic_score_codex":0.0060746423,"about_ca_topic_score_gemma":0.007094386,"teacher_disagreement_score":0.0060746423,"about_ca_system_score_codex":0.0006417282,"about_ca_system_score_gemma":0.0017798168,"threshold_uncertainty_score":0.014134169},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019665407,0.00017292319,0.97952867,0.00018289917,0.000017671146,0.000040177347,0.000067653724,0.00010812921,0.00021653938],"genre_scores_gemma":[0.5842343,0.00064828945,0.411881,0.0003199116,0.0002613591,0.0005548814,0.00057866884,0.00011910662,0.0014025313],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9561418,0.035126634,0.0011550171,0.0044447654,0.0024828943,0.00064900296],"domain_scores_gemma":[0.6902513,0.27979308,0.011521166,0.014009637,0.0037092522,0.0007157182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059804857,0.0015949362,0.0029524025,0.0017555802,0.0009507603,0.0020053487,0.003709564,0.001967607,0.0021143388],"category_scores_gemma":[0.22676231,0.0013201601,0.0024033138,0.0021974978,0.0048575327,0.004583601,0.0035720635,0.0046498324,0.00034788367],"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":[0.00082927855,0.00036513005,0.015772676,0.0008212548,0.0011375732,0.0005770925,0.0009244277,0.4654235,0.0030052487,0.40038875,0.0011792845,0.109575786],"study_design_scores_gemma":[0.0000634598,0.000083418396,0.001666423,0.00003893329,0.000059496313,0.00006550864,0.000047841244,0.84948575,0.001267138,0.14684452,0.00033695868,0.000040589908],"about_ca_topic_score_codex":0.0034939474,"about_ca_topic_score_gemma":0.0018405697,"teacher_disagreement_score":0.059804857,"about_ca_system_score_codex":0.0013658408,"about_ca_system_score_gemma":0.0015414973,"threshold_uncertainty_score":0.3162821},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038225476,0.00009793096,0.99555546,0.00007641221,0.000011705178,0.000012562962,0.00006563197,0.000112015405,0.00024570982],"genre_scores_gemma":[0.35178214,0.0013483061,0.6400602,0.0002957287,0.00018183741,0.00042588488,0.0010730403,0.00054180593,0.0042910995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997474,0.0012531659,0.0001132433,0.00062340155,0.0003491211,0.00018707292],"domain_scores_gemma":[0.98525095,0.011059685,0.0013441043,0.0013548549,0.0007684964,0.0002219285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005953783,0.0012888175,0.001905625,0.0018145216,0.0006309989,0.0018990962,0.0036263622,0.0014132741,0.0029701316],"category_scores_gemma":[0.025608681,0.0012737141,0.0020689326,0.0022814546,0.0017004983,0.0032532315,0.0024754438,0.0032423309,0.0010353783],"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":[0.00009135102,0.00008989359,0.0032902933,0.00021944662,0.00030717862,0.00037692685,0.0004813638,0.6469708,0.004411206,0.28227922,0.0024817518,0.0590006],"study_design_scores_gemma":[0.0000051049283,0.000011800949,0.00036780187,0.000014761122,0.000017696428,0.00004596846,0.000012317546,0.9488578,0.00046289514,0.049506452,0.0006804763,0.000016876245],"about_ca_topic_score_codex":0.004824437,"about_ca_topic_score_gemma":0.0047681686,"teacher_disagreement_score":0.005953783,"about_ca_system_score_codex":0.0010101661,"about_ca_system_score_gemma":0.0014551509,"threshold_uncertainty_score":0.031487048},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034165815,0.0002894032,0.9948967,0.00028257893,0.0000482202,0.000028208902,0.000037274083,0.00008292062,0.00091807474],"genre_scores_gemma":[0.32896125,0.0016914024,0.66408736,0.0009878743,0.0006518811,0.00061217597,0.00034858508,0.00024073561,0.0024188142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9754641,0.017920144,0.00088325696,0.0017372095,0.0033456655,0.0006495636],"domain_scores_gemma":[0.8798571,0.0994008,0.0055340235,0.01072868,0.0040163794,0.000462965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.035913453,0.001110916,0.0026235948,0.0023974536,0.00094440265,0.0026360971,0.0032959275,0.003103542,0.0024482918],"category_scores_gemma":[0.21543394,0.0009840885,0.0015541827,0.0031766982,0.0037019341,0.004497539,0.004101222,0.0041638236,0.0008954539],"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":[0.00008719555,0.000059949718,0.0041698543,0.00029771164,0.00032646593,0.00066033774,0.00033322826,0.103769064,0.0010660681,0.82856405,0.002407256,0.05825888],"study_design_scores_gemma":[0.000027620594,0.00003620255,0.0004856144,0.00008656467,0.00005058049,0.00012664065,0.00004558572,0.31732047,0.0010572299,0.67726934,0.0034686783,0.000025402902],"about_ca_topic_score_codex":0.0020461155,"about_ca_topic_score_gemma":0.0010472279,"teacher_disagreement_score":0.96408653,"about_ca_system_score_codex":0.0010902315,"about_ca_system_score_gemma":0.0017971284,"threshold_uncertainty_score":0.18993074},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011519127,0.000030470761,0.98599017,0.00005156597,0.000011923239,0.000033320364,0.000033094533,0.0009961975,0.0013340997],"genre_scores_gemma":[0.47231188,0.00008695561,0.5244273,0.000108606444,0.000029617395,0.00029391356,0.00018704798,0.00067496137,0.0018796818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987814,0.0004732502,0.000057880316,0.0002218041,0.00036366069,0.00010212796],"domain_scores_gemma":[0.99497366,0.0033648126,0.00037031295,0.00081614236,0.00032162733,0.00015342292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022154367,0.00057933806,0.0006977219,0.0006240342,0.0005836947,0.0009686379,0.002110451,0.0008645954,0.0032774033],"category_scores_gemma":[0.011256395,0.00056776387,0.0008154635,0.0004717116,0.0012467187,0.0011853814,0.0017900672,0.0015533476,0.00075270014],"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":[0.00007335502,0.000033191078,0.0008678085,0.00004983778,0.000030388357,0.000065040156,0.00008224167,0.8989815,0.004148264,0.07110701,0.00063130347,0.023930088],"study_design_scores_gemma":[0.00000586441,0.0000069441307,0.000029076253,0.0000027433011,0.0000019149247,0.0000071276513,0.0000023459017,0.9903106,0.00065283896,0.008694709,0.0002821218,0.00000374611],"about_ca_topic_score_codex":0.002778197,"about_ca_topic_score_gemma":0.0032985539,"teacher_disagreement_score":0.0032774033,"about_ca_system_score_codex":0.0010587515,"about_ca_system_score_gemma":0.0014481988,"threshold_uncertainty_score":0.011716425},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088233844,0.14521992,0.31385297,0.054415338,0.03512943,0.0005665733,0.020426147,0.008604869,0.42090246],"genre_scores_gemma":[0.011362998,0.15585536,0.24684168,0.049523205,0.028671104,0.0008263316,0.019329885,0.0053702733,0.4822192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973743,0.00060052605,0.0002466562,0.0004111417,0.0012793384,0.00008796844],"domain_scores_gemma":[0.99156886,0.0054167043,0.00020698254,0.0007393314,0.0017422108,0.00032598438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002911471,0.0010151027,0.0011214317,0.0032952325,0.0009863931,0.0039481213,0.0016563572,0.0019933528,0.09508019],"category_scores_gemma":[0.008922572,0.0008683504,0.0011601583,0.0049626576,0.001237296,0.004878736,0.002195229,0.0053670187,0.0582607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013926755,0.000028260227,0.00021577434,0.00045200108,0.000023793387,0.00012498748,0.00011205772,0.00070877356,0.00038083078,0.041489575,0.7627738,0.1936763],"study_design_scores_gemma":[0.000002184986,0.0000059815743,0.00012455104,0.00011720243,0.0000020804432,0.00012372849,0.000019720484,0.00015230302,0.000051528536,0.020758215,0.97863483,0.000007703497],"about_ca_topic_score_codex":0.0014827726,"about_ca_topic_score_gemma":0.0023088404,"teacher_disagreement_score":0.09508019,"about_ca_system_score_codex":0.0011723556,"about_ca_system_score_gemma":0.0018073063,"threshold_uncertainty_score":0.31807494},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004524931,0.00012410725,0.9942577,0.00014776606,0.000025647885,0.000060753515,0.00008955425,0.00019020261,0.00057928666],"genre_scores_gemma":[0.12198168,0.0005914775,0.87286055,0.0005610575,0.00020185283,0.0010368573,0.00076830725,0.00042102655,0.0015771522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9884199,0.006543054,0.00093216903,0.0015824084,0.0020247032,0.00049782265],"domain_scores_gemma":[0.9501343,0.03130663,0.0037093032,0.0103970375,0.0036213598,0.0008314215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03227434,0.001470133,0.0022739614,0.0039487365,0.0013500648,0.0019536512,0.0026357598,0.0020608804,0.0033000186],"category_scores_gemma":[0.07529718,0.0013264163,0.003691199,0.0028599848,0.0042902343,0.0055600316,0.0050699012,0.0048604077,0.0009958252],"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":[0.00025497196,0.00011183232,0.004567456,0.0003784895,0.00022957074,0.0006574851,0.0006108158,0.084835015,0.006931154,0.7986179,0.003999785,0.09880559],"study_design_scores_gemma":[0.00007700156,0.00012558831,0.0010942193,0.00015848667,0.000046315086,0.0004079591,0.000094627954,0.3552561,0.0053378106,0.6317098,0.0056267544,0.00006532084],"about_ca_topic_score_codex":0.0010206788,"about_ca_topic_score_gemma":0.0010441969,"teacher_disagreement_score":0.03227434,"about_ca_system_score_codex":0.0011600815,"about_ca_system_score_gemma":0.0036132194,"threshold_uncertainty_score":0.17068505},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030463861,0.00012443824,0.9671891,0.0001557072,0.000027290547,0.0000916873,0.00014583435,0.0007658383,0.001036232],"genre_scores_gemma":[0.52503824,0.00027528757,0.46951082,0.00021916078,0.000082553706,0.00048037086,0.0010895625,0.00056187296,0.0027421995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985514,0.00064032315,0.000051784053,0.0003468429,0.00027446533,0.00013512716],"domain_scores_gemma":[0.9920282,0.005884975,0.00044468048,0.0009730859,0.00037196313,0.00029717688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003490627,0.0007479834,0.0014470835,0.0011623934,0.0010190522,0.0014974396,0.0029672834,0.0011894419,0.003734611],"category_scores_gemma":[0.014841384,0.0010901261,0.0014915152,0.0011471966,0.0018996638,0.0025024049,0.0021496315,0.0027333263,0.0007377867],"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":[0.00030407708,0.00011195625,0.003571775,0.00010380698,0.000104804094,0.00023179673,0.00023327098,0.82107294,0.0024457306,0.12866297,0.0015996208,0.04155734],"study_design_scores_gemma":[0.000024111936,0.000009228706,0.00010536574,0.000006121842,0.0000066347616,0.000016501332,0.000010128773,0.9611473,0.00038773735,0.0379839,0.0002971239,0.0000057645343],"about_ca_topic_score_codex":0.011061061,"about_ca_topic_score_gemma":0.020153115,"teacher_disagreement_score":0.011061061,"about_ca_system_score_codex":0.0015568341,"about_ca_system_score_gemma":0.002217242,"threshold_uncertainty_score":0.021993399},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015417549,0.00010537927,0.997498,0.00009400717,0.000015989533,0.000019660694,0.000048008485,0.00038577837,0.0002914041],"genre_scores_gemma":[0.112453945,0.0003144864,0.8829441,0.00024716603,0.00009585784,0.00024446845,0.0007647619,0.0005757573,0.0023594038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967159,0.0018805946,0.00016301448,0.0004368433,0.00066212675,0.00014145882],"domain_scores_gemma":[0.98676443,0.009251277,0.0007782849,0.0013967573,0.0016458498,0.00016338275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062760226,0.0014346882,0.0014629985,0.0017714755,0.0005777235,0.0019782137,0.0023236754,0.0021125658,0.002998818],"category_scores_gemma":[0.034536958,0.0010625543,0.0012223894,0.0014445006,0.0017844415,0.0029031234,0.0029183214,0.0029464317,0.0014342504],"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":[0.00033563445,0.00008553199,0.001700383,0.00036230858,0.00024046606,0.00013846798,0.00016884874,0.7824039,0.0062292707,0.0720256,0.005951235,0.13035838],"study_design_scores_gemma":[0.00001374232,0.000013445338,0.0001619662,0.000016578648,0.000008392664,0.000028786095,0.0000062080526,0.9816201,0.0014668608,0.015442711,0.0012021211,0.000019144483],"about_ca_topic_score_codex":0.0030758947,"about_ca_topic_score_gemma":0.002873976,"teacher_disagreement_score":0.0062760226,"about_ca_system_score_codex":0.0010079459,"about_ca_system_score_gemma":0.0018113065,"threshold_uncertainty_score":0.033191204},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036273012,0.0009958018,0.9757682,0.0067053065,0.00022441946,0.00008757412,0.00060600485,0.00020482694,0.011780543],"genre_scores_gemma":[0.47741103,0.007607346,0.48343807,0.008304049,0.0039015412,0.0016215228,0.0016286464,0.0006860569,0.015401792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97805595,0.008254109,0.0012375301,0.0037464474,0.007143016,0.0015629801],"domain_scores_gemma":[0.87837684,0.09388186,0.0043187025,0.013619506,0.008581429,0.0012215906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02155207,0.001994073,0.0025157975,0.0027988222,0.0024168498,0.0070081446,0.0034933067,0.0043904018,0.006481756],"category_scores_gemma":[0.11822009,0.0013208846,0.003347608,0.0053042565,0.008805289,0.01674589,0.010797959,0.014559805,0.0025970382],"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":[0.00005831194,0.000037207486,0.000679393,0.00016434446,0.00004782705,0.000121792196,0.00021580493,0.012825724,0.0009437135,0.96597475,0.003960014,0.014971041],"study_design_scores_gemma":[0.00002760214,0.000048374797,0.00027289218,0.00009459275,0.000032874806,0.00029216308,0.00004276865,0.08870091,0.0014843805,0.90123004,0.007738455,0.000034941993],"about_ca_topic_score_codex":0.0011756624,"about_ca_topic_score_gemma":0.0006619094,"teacher_disagreement_score":0.02155207,"about_ca_system_score_codex":0.004713378,"about_ca_system_score_gemma":0.0034536973,"threshold_uncertainty_score":0.11397958},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070336964,0.00015646096,0.99217904,0.00013992017,0.000016044703,0.00003455409,0.00007138794,0.00016608328,0.00020272321],"genre_scores_gemma":[0.4700249,0.0010757752,0.5225946,0.00035265693,0.00024761536,0.0007312286,0.0012485206,0.00028507775,0.003439629],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99559647,0.0030173124,0.00020781891,0.0005196308,0.00047147754,0.00018721914],"domain_scores_gemma":[0.95794815,0.035663944,0.0018282044,0.0024356933,0.0017135338,0.00041052277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01365516,0.0011928736,0.0017082626,0.0011607005,0.00046866457,0.0013072006,0.0022876475,0.0014291969,0.0025377255],"category_scores_gemma":[0.05645491,0.0007196602,0.0014934202,0.0010134899,0.0022018787,0.0022417584,0.0025483232,0.0036402026,0.0005502399],"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":[0.00026474782,0.00016879445,0.006144818,0.00034712738,0.00021948993,0.0002409407,0.00014824318,0.7968543,0.0021749781,0.12930003,0.0020328397,0.06210365],"study_design_scores_gemma":[0.000014285808,0.000026990469,0.00036581454,0.00001636034,0.000009005024,0.000020227077,0.000011444472,0.974447,0.00035371073,0.024457784,0.00026842317,0.000009020168],"about_ca_topic_score_codex":0.0034727396,"about_ca_topic_score_gemma":0.0027047177,"teacher_disagreement_score":0.01365516,"about_ca_system_score_codex":0.0009590928,"about_ca_system_score_gemma":0.0018523514,"threshold_uncertainty_score":0.07221621},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023498474,0.0006841623,0.97222024,0.00064075046,0.00006876028,0.00014459508,0.00042477035,0.0002873692,0.0020308038],"genre_scores_gemma":[0.5926726,0.0018806115,0.3964406,0.0007458067,0.00034106695,0.0008499954,0.0018310879,0.00018422972,0.0050542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9806491,0.0151727935,0.00060372625,0.0017900841,0.0014315237,0.00035283854],"domain_scores_gemma":[0.9125854,0.078669764,0.003947473,0.0028944854,0.0014505499,0.00045224823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025550082,0.001341862,0.0025185032,0.0033859515,0.0010563054,0.0034180863,0.0043756007,0.0020382274,0.006951069],"category_scores_gemma":[0.14225677,0.0014171212,0.0024859526,0.0032799714,0.0017590743,0.0062147947,0.0034806577,0.0031131937,0.0009287242],"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":[0.00026620776,0.00016991925,0.014506266,0.0005465229,0.000548964,0.0009285531,0.0006326954,0.37239859,0.00043568618,0.51439476,0.0027007738,0.09247108],"study_design_scores_gemma":[0.000047976442,0.00004191833,0.0010777748,0.00010197571,0.000077182885,0.00016857649,0.000120915654,0.6066932,0.00021507086,0.3891984,0.002209965,0.00004711459],"about_ca_topic_score_codex":0.008950585,"about_ca_topic_score_gemma":0.0074967067,"teacher_disagreement_score":0.025550082,"about_ca_system_score_codex":0.0021186774,"about_ca_system_score_gemma":0.0013782885,"threshold_uncertainty_score":0.13512337},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047932616,0.00021485321,0.9937589,0.0003289325,0.00001859973,0.0000709531,0.00019330271,0.00043108244,0.00019009161],"genre_scores_gemma":[0.41190743,0.0002801079,0.5838015,0.0007294056,0.0001492805,0.0007249659,0.0015173728,0.0001930139,0.00069689465],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97736025,0.015524289,0.0011271021,0.0035601477,0.0019335266,0.0004946362],"domain_scores_gemma":[0.9157371,0.06435251,0.0051114713,0.010603084,0.0034317153,0.0007641256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04856168,0.0021815856,0.003831608,0.0034895672,0.0013222565,0.004081267,0.006177206,0.0026768846,0.0016072079],"category_scores_gemma":[0.11613461,0.0017328259,0.0039489446,0.0032271545,0.00313896,0.003910473,0.005181283,0.005386358,0.0004775804],"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":[0.00028293367,0.00017805069,0.007071309,0.0003320615,0.0013783006,0.00022576207,0.00019431103,0.87033075,0.0006480105,0.052446123,0.0012244396,0.06568787],"study_design_scores_gemma":[0.00003506493,0.000040488485,0.00030416506,0.000035300945,0.00008205439,0.000022682198,0.000020829584,0.91200906,0.0005126612,0.086535804,0.00038730094,0.00001465044],"about_ca_topic_score_codex":0.0056691635,"about_ca_topic_score_gemma":0.0056732805,"teacher_disagreement_score":0.04856168,"about_ca_system_score_codex":0.0033621327,"about_ca_system_score_gemma":0.004039403,"threshold_uncertainty_score":0.25682175},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042175725,0.00010917351,0.99525523,0.000046674253,0.0000056581266,0.000013560811,0.00002038732,0.0002179562,0.000113823095],"genre_scores_gemma":[0.19870383,0.00030862706,0.7984916,0.00017615169,0.000045675177,0.00022244122,0.00033362684,0.00022970875,0.0014883267],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99615896,0.0024436286,0.00013315899,0.0005308724,0.00056648155,0.00016691336],"domain_scores_gemma":[0.9864318,0.010480061,0.00083481014,0.0012543894,0.00075661513,0.00024234451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065458384,0.0010603984,0.0020546478,0.0017500268,0.0007543227,0.0012852014,0.0026315136,0.0016761539,0.0018348747],"category_scores_gemma":[0.020997072,0.00087572966,0.0020125313,0.0015208342,0.0016485355,0.0022377393,0.0026185166,0.0020423701,0.0007770305],"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":[0.00069528155,0.00029325197,0.009528858,0.00049740047,0.00042575478,0.0004599834,0.0004930578,0.45690924,0.021368284,0.14677577,0.0039764456,0.3585766],"study_design_scores_gemma":[0.000018524079,0.000030227087,0.00075965567,0.000014969446,0.000024988236,0.000080805985,0.000014058014,0.95871603,0.002319535,0.037212573,0.00077562395,0.00003299841],"about_ca_topic_score_codex":0.002699218,"about_ca_topic_score_gemma":0.0030010783,"teacher_disagreement_score":0.0065458384,"about_ca_system_score_codex":0.00081219635,"about_ca_system_score_gemma":0.0012413097,"threshold_uncertainty_score":0.03461814},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013832198,0.00005475093,0.99658066,0.0003429804,0.000031712498,0.0003416136,0.000043989334,0.000068781526,0.001152315],"genre_scores_gemma":[0.076072015,0.00020705548,0.91938525,0.00044593314,0.0001121933,0.0029898062,0.00010692418,0.00012911487,0.0005517176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9001949,0.08233904,0.0026571641,0.0026617802,0.011446712,0.0007004852],"domain_scores_gemma":[0.75708526,0.20026514,0.00880176,0.020365806,0.012296044,0.0011859722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08230868,0.0014751835,0.0018747823,0.004153868,0.0011078882,0.0037573178,0.0026049686,0.0026664382,0.011127259],"category_scores_gemma":[0.293447,0.0019012124,0.0017356813,0.0026629888,0.0036767705,0.0044208057,0.0043194965,0.005180106,0.0017036338],"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":[0.00078000233,0.0003527852,0.0038766495,0.0006947859,0.0004980808,0.00025906813,0.0007107832,0.12428205,0.0026077207,0.71080977,0.0035039634,0.1516244],"study_design_scores_gemma":[0.00065485673,0.00086213293,0.001706854,0.0003073427,0.00020351645,0.00033615044,0.00017399155,0.3366048,0.0031215497,0.6374634,0.018437069,0.00012831521],"about_ca_topic_score_codex":0.00082429126,"about_ca_topic_score_gemma":0.0011910276,"teacher_disagreement_score":0.08230868,"about_ca_system_score_codex":0.0021854162,"about_ca_system_score_gemma":0.006140839,"threshold_uncertainty_score":0.4352951},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052032247,0.0004135951,0.9920682,0.001011369,0.00008470585,0.00007554261,0.00022392147,0.0001265411,0.0007929742],"genre_scores_gemma":[0.42376405,0.0018865968,0.5627898,0.001838044,0.0013931497,0.0012810591,0.002358149,0.00022583395,0.004463294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98828655,0.0065158983,0.000450584,0.0025503668,0.0017286788,0.00046787303],"domain_scores_gemma":[0.95617706,0.03082053,0.0032039722,0.007033489,0.0021939636,0.0005710026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021893352,0.0017568307,0.0027942252,0.002146411,0.0013337675,0.0038796545,0.005490818,0.003817958,0.002851109],"category_scores_gemma":[0.069132686,0.001445139,0.0017376604,0.0033447456,0.005011727,0.007461074,0.0049016364,0.008376365,0.0009965237],"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":[0.00026454995,0.00027689716,0.012934068,0.00049869256,0.00023407223,0.0004669869,0.00063012575,0.17711823,0.0017697208,0.6182149,0.007664214,0.17992756],"study_design_scores_gemma":[0.000024301951,0.000046125184,0.0010163758,0.00008308711,0.000036001242,0.0001769036,0.000076614706,0.5899429,0.0006407641,0.404535,0.0033825636,0.0000394134],"about_ca_topic_score_codex":0.0035421434,"about_ca_topic_score_gemma":0.0031780757,"teacher_disagreement_score":0.021893352,"about_ca_system_score_codex":0.0020197066,"about_ca_system_score_gemma":0.0029225436,"threshold_uncertainty_score":0.115784526},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16285655,0.0017398677,0.8316269,0.0003938282,0.00007127595,0.0001386947,0.00047481357,0.0018873526,0.0008108323],"genre_scores_gemma":[0.7015566,0.0011966438,0.2949003,0.00006637125,0.00010836942,0.00018906868,0.0007597106,0.00023978329,0.0009830785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996332,0.00010095025,0.000021583415,0.00010267718,0.00009697012,0.000044553977],"domain_scores_gemma":[0.9989064,0.0004943113,0.00013348892,0.000110958405,0.00029928389,0.00005560959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010535612,0.0011594258,0.0008223057,0.0024648164,0.00042681387,0.000918488,0.00055113353,0.000644506,0.000789182],"category_scores_gemma":[0.004984717,0.00026964597,0.0013360197,0.0019858945,0.00055227807,0.00061313057,0.0006526709,0.0009632013,0.00028900377],"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":[0.0003563517,0.0002011725,0.026574787,0.0002134897,0.0003805673,0.00045077584,0.000371694,0.4676157,0.025171619,0.0061226287,0.003488662,0.46905255],"study_design_scores_gemma":[0.0000069908942,0.000045975496,0.010595164,0.000013705597,0.00003443307,0.00012479712,0.000034006476,0.9810736,0.0024581468,0.0049241628,0.0006551142,0.000033865465],"about_ca_topic_score_codex":0.011826883,"about_ca_topic_score_gemma":0.008975646,"teacher_disagreement_score":0.011826883,"about_ca_system_score_codex":0.00041847522,"about_ca_system_score_gemma":0.0011077985,"threshold_uncertainty_score":0.023516059},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024242824,0.00031409948,0.9736458,0.00018673672,0.00002330709,0.00003819205,0.0001712387,0.0002907972,0.0010871029],"genre_scores_gemma":[0.7811645,0.0007350116,0.20860523,0.00020186971,0.00013082403,0.000312695,0.0010879325,0.00029974722,0.007462067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868506,0.00064161065,0.00003459377,0.00037065623,0.000189999,0.000078060926],"domain_scores_gemma":[0.99659795,0.00214213,0.00040908638,0.0003324493,0.0004369068,0.000081482955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024562038,0.00057007524,0.0010188891,0.0012569735,0.0004191204,0.0007280532,0.0018424954,0.00077734975,0.0020265682],"category_scores_gemma":[0.010452866,0.00036421124,0.0008993714,0.0011624636,0.0007206124,0.0013909036,0.001216063,0.0011058316,0.00064111507],"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":[0.000101439255,0.000053515425,0.008176019,0.000120169614,0.00015621097,0.00012251858,0.0001240153,0.8444377,0.0022429037,0.06333358,0.002934047,0.07819792],"study_design_scores_gemma":[0.0000036563538,0.000008923989,0.00047081697,0.0000040274044,0.000008134015,0.000018719593,0.000008504463,0.9897322,0.00021620208,0.0090339845,0.0004903243,0.0000045118477],"about_ca_topic_score_codex":0.0055229496,"about_ca_topic_score_gemma":0.0046529537,"teacher_disagreement_score":0.0055229496,"about_ca_system_score_codex":0.00080536224,"about_ca_system_score_gemma":0.00069085514,"threshold_uncertainty_score":0.012989819},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023219557,0.00081405434,0.01012428,0.94964486,0.034516186,0.00004575142,0.00031228588,0.00020779943,0.0041025276],"genre_scores_gemma":[0.0059927427,0.0005478612,0.0075596557,0.94219404,0.035838895,0.00032716407,0.00012233427,0.0004079291,0.007009283],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8807068,0.06282265,0.009833495,0.013665886,0.02949833,0.0034728886],"domain_scores_gemma":[0.72330207,0.20988846,0.0073322277,0.010247608,0.04453615,0.0046933903],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13440531,0.0027298722,0.0028755397,0.0023148058,0.012083991,0.009222754,0.010910629,0.0469462,0.01343647],"category_scores_gemma":[0.32634214,0.0023836633,0.0064242817,0.0023060301,0.022416417,0.019718464,0.008614209,0.08315059,0.009947218],"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":[0.000066546905,0.000010873371,0.00021328787,0.00016296678,0.00003558054,0.0001357391,0.0017154686,0.00021624476,0.00024296527,0.10105003,0.89220643,0.0039437944],"study_design_scores_gemma":[0.00007522892,0.000046010333,0.0006278665,0.0008613657,0.0000623534,0.00030961353,0.0014118395,0.0013880449,0.0009207887,0.09384367,0.9002737,0.00017958712],"about_ca_topic_score_codex":0.020657271,"about_ca_topic_score_gemma":0.017375112,"teacher_disagreement_score":0.8655947,"about_ca_system_score_codex":0.008626494,"about_ca_system_score_gemma":0.014886637,"threshold_uncertainty_score":0.71081173},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011155056,0.01978284,0.001976735,0.95177835,0.018484402,0.000015863696,0.00012624761,0.00013396697,0.0065860166],"genre_scores_gemma":[0.19644044,0.082118735,0.03354993,0.6078535,0.042430643,0.00039114026,0.0010165047,0.0007718638,0.035427213],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.965033,0.01888335,0.0011620868,0.0025357848,0.006439267,0.0059464946],"domain_scores_gemma":[0.8749307,0.027782606,0.0036247002,0.0050513167,0.022630852,0.065979764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06580107,0.0012220156,0.00134292,0.0020639363,0.010580926,0.028303757,0.0024051378,0.013955402,0.011140252],"category_scores_gemma":[0.055236552,0.000638215,0.0011036335,0.0025918002,0.019650271,0.017647108,0.011267619,0.022550365,0.0064407657],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011667863,0.0001305351,0.0027260147,0.00053476635,0.000048139304,0.00019298703,0.008790173,0.00028609953,0.0003870783,0.10231832,0.7788516,0.10561771],"study_design_scores_gemma":[0.000018679402,0.00007864599,0.002283918,0.0014464819,0.000027620325,0.00023952589,0.01769557,0.0004732122,0.00021856488,0.06178391,0.91563326,0.00010055197],"about_ca_topic_score_codex":0.014009211,"about_ca_topic_score_gemma":0.014793634,"teacher_disagreement_score":0.06580107,"about_ca_system_score_codex":0.012144285,"about_ca_system_score_gemma":0.06231029,"threshold_uncertainty_score":0.3479935},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038052876,0.00025382123,0.95994765,0.0002822368,0.00004944629,0.000056205743,0.00009240162,0.00018277612,0.0010826086],"genre_scores_gemma":[0.8882907,0.0007350186,0.101488166,0.00020576993,0.00027637053,0.00032013503,0.00032919782,0.00012391686,0.008230692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982705,0.00054760906,0.00010718194,0.0004477341,0.0004346256,0.0001922569],"domain_scores_gemma":[0.97890043,0.015174595,0.002889074,0.0011496908,0.0014101764,0.0004760723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004472977,0.00094978884,0.0009394219,0.00145221,0.0004789006,0.0018086359,0.0022018314,0.0016280488,0.0033852682],"category_scores_gemma":[0.027938155,0.00070476084,0.0013187759,0.0014604944,0.0022692734,0.004141704,0.0026294685,0.0030173166,0.00058635784],"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":[0.00017352082,0.00007753739,0.0070850393,0.00016148304,0.000112055575,0.0004237658,0.00045054045,0.4530182,0.0045798863,0.5012278,0.0008470924,0.031843055],"study_design_scores_gemma":[0.000012052948,0.000044174125,0.0008539614,0.00001344415,0.000017167818,0.00010191545,0.00003826202,0.91976243,0.0004951098,0.07807755,0.00055150274,0.000032542306],"about_ca_topic_score_codex":0.0020817837,"about_ca_topic_score_gemma":0.0011733487,"teacher_disagreement_score":0.004472977,"about_ca_system_score_codex":0.0011198502,"about_ca_system_score_gemma":0.0009413971,"threshold_uncertainty_score":0.023655593},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035176747,0.00015501097,0.9627946,0.0004925295,0.000059270573,0.00010648598,0.00035956642,0.000363369,0.00049228803],"genre_scores_gemma":[0.6842206,0.00039311964,0.31141192,0.0005638965,0.00023475318,0.00062357145,0.0016770775,0.00019050167,0.00068457297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9435468,0.038332466,0.002759186,0.006048926,0.008099851,0.0012127035],"domain_scores_gemma":[0.5665165,0.38868284,0.0135461,0.024270426,0.0055571534,0.0014269996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11622987,0.0012631358,0.0027004378,0.0029035292,0.0016171163,0.0029683444,0.0075876107,0.0033452369,0.0037542346],"category_scores_gemma":[0.37763432,0.0011478994,0.002945153,0.0028515959,0.0048038494,0.0062753805,0.0053203874,0.0047933036,0.0005551864],"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":[0.0014808327,0.0003264724,0.09843399,0.00086130295,0.0011831949,0.0023273272,0.0014437934,0.53554654,0.0023416851,0.26898998,0.0033765559,0.08368833],"study_design_scores_gemma":[0.00020918476,0.0002548444,0.0042903037,0.00011453987,0.00010184782,0.00067625655,0.00019929656,0.76083046,0.0020475166,0.22922578,0.0019767361,0.000073082345],"about_ca_topic_score_codex":0.0053968113,"about_ca_topic_score_gemma":0.002209054,"teacher_disagreement_score":0.11622987,"about_ca_system_score_codex":0.0015145527,"about_ca_system_score_gemma":0.0059750117,"threshold_uncertainty_score":0.61468965},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00418719,0.00012609008,0.99491066,0.00012958863,0.00003204465,0.000068529866,0.000027751354,0.00024276099,0.00027539136],"genre_scores_gemma":[0.49165985,0.00042687453,0.50454235,0.00060757546,0.00034695686,0.0008922533,0.0002494058,0.00024337856,0.0010313414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9735649,0.019555215,0.0010547083,0.0022333413,0.0031336313,0.00045816452],"domain_scores_gemma":[0.91616374,0.067845605,0.0042126,0.006890411,0.0041281795,0.00075935357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036282018,0.0014295486,0.0019677447,0.0015750913,0.00073752797,0.0015489904,0.0029997162,0.001424935,0.0016991543],"category_scores_gemma":[0.09984595,0.0005651477,0.0013242061,0.0017566987,0.0034946084,0.001984672,0.0030118779,0.0028450477,0.00062916166],"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":[0.0019689454,0.00038699593,0.013084341,0.0006363688,0.00087933487,0.0011375947,0.00080365303,0.3150131,0.029115673,0.23355901,0.0058028693,0.39761207],"study_design_scores_gemma":[0.00028657264,0.00038357606,0.0012401196,0.000039084105,0.00008595441,0.0002866235,0.0000443531,0.90093386,0.006863008,0.088143215,0.0016398814,0.000053759457],"about_ca_topic_score_codex":0.00077431224,"about_ca_topic_score_gemma":0.0005550883,"teacher_disagreement_score":0.036282018,"about_ca_system_score_codex":0.0009009238,"about_ca_system_score_gemma":0.0031551998,"threshold_uncertainty_score":0.19187993},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00157076,0.73839194,0.09783423,0.047261883,0.0058763917,0.00006570368,0.00054278993,0.0009541339,0.107502244],"genre_scores_gemma":[0.1243416,0.5814209,0.118757136,0.015132874,0.016772108,0.00092430844,0.00089917006,0.001281838,0.14047006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956689,0.0021296376,0.0003509995,0.00055592967,0.0011304198,0.00016415065],"domain_scores_gemma":[0.98052466,0.015867472,0.00045488885,0.0012641925,0.0015226011,0.00036620468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010567337,0.0014766234,0.0022589455,0.0033583846,0.0013503213,0.005011252,0.0019440546,0.003142401,0.024184441],"category_scores_gemma":[0.022304235,0.0015759268,0.0009732076,0.0038901765,0.007988992,0.010777987,0.0026947125,0.0056669493,0.00990235],"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":[0.00003506323,0.000042958072,0.0002728461,0.0005775772,0.000035499525,0.00007916163,0.00078417006,0.0014472008,0.00009045622,0.6090199,0.28105956,0.10655566],"study_design_scores_gemma":[0.000013236855,0.000022354616,0.00031729726,0.00059756683,0.000008331319,0.0001315274,0.00028972546,0.0017035623,0.00006708454,0.63102496,0.36580282,0.000021582671],"about_ca_topic_score_codex":0.0035549607,"about_ca_topic_score_gemma":0.0026291383,"teacher_disagreement_score":0.024184441,"about_ca_system_score_codex":0.0031260338,"about_ca_system_score_gemma":0.0022811345,"threshold_uncertainty_score":0.08090502},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04690983,0.00028713784,0.9516167,0.00019400094,0.000026512473,0.00007025686,0.0003077873,0.00018375067,0.0004040257],"genre_scores_gemma":[0.72715914,0.00062881294,0.26697543,0.000182548,0.00012601909,0.00056042144,0.0018961336,0.00010321223,0.0023682544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99579924,0.0024511167,0.00023112031,0.0007602509,0.0005460477,0.00021219636],"domain_scores_gemma":[0.9330692,0.055698264,0.003650099,0.005030838,0.0022243536,0.000327084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015610678,0.0006352312,0.0019721359,0.0019465402,0.00059326406,0.0014316632,0.0032797423,0.0017746219,0.0016493165],"category_scores_gemma":[0.07049043,0.0006100089,0.0017141748,0.0028372286,0.0025727456,0.0026012051,0.0016576248,0.0026295297,0.00030552948],"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":[0.00039610636,0.00026425178,0.05094464,0.0005080049,0.0006234528,0.00084217207,0.0008702883,0.5975342,0.0029948293,0.20922917,0.0022727847,0.13352007],"study_design_scores_gemma":[0.000019543259,0.00009693626,0.006439292,0.000048947062,0.000032526543,0.00014014056,0.000082458435,0.9197229,0.00061067246,0.07176588,0.0009969677,0.00004364762],"about_ca_topic_score_codex":0.008545995,"about_ca_topic_score_gemma":0.0047804187,"teacher_disagreement_score":0.015610678,"about_ca_system_score_codex":0.0010933392,"about_ca_system_score_gemma":0.0010115751,"threshold_uncertainty_score":0.082558155},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024288852,0.00023342615,0.971386,0.00042110172,0.000041205978,0.00004317834,0.0004613429,0.00020266493,0.0029222881],"genre_scores_gemma":[0.860517,0.0008990369,0.12453127,0.00022298428,0.000098444456,0.00032138996,0.0010058054,0.0001718607,0.012232294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990212,0.0003941457,0.00003981087,0.00027286317,0.00014225449,0.00012982296],"domain_scores_gemma":[0.99766695,0.0014252127,0.00033629985,0.00020656134,0.00026984158,0.000095157906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026581504,0.00079364213,0.0009507698,0.0010733012,0.0004514059,0.001849416,0.0021947299,0.0013249625,0.003935211],"category_scores_gemma":[0.008323112,0.0004698674,0.0011671932,0.0013457303,0.001158899,0.0019449262,0.0013886912,0.002513519,0.0006643191],"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":[0.000053392654,0.00006009174,0.0038954625,0.000063687694,0.00009841263,0.00022202027,0.00021395428,0.65682554,0.0008551563,0.3141355,0.0027114847,0.020865291],"study_design_scores_gemma":[0.000004397381,0.000013633401,0.000591756,0.000010148058,0.0000113385995,0.000043505228,0.000022801165,0.96109825,0.000082300256,0.03719385,0.00091516017,0.000012898984],"about_ca_topic_score_codex":0.008226491,"about_ca_topic_score_gemma":0.006595846,"teacher_disagreement_score":0.008226491,"about_ca_system_score_codex":0.001166449,"about_ca_system_score_gemma":0.0010938835,"threshold_uncertainty_score":0.016357183},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003918188,0.000091977985,0.99557364,0.00012814591,0.000010066074,0.000015174725,0.000014042386,0.00005102116,0.00019769209],"genre_scores_gemma":[0.25687423,0.00051363936,0.74017525,0.0002269459,0.00012407971,0.00031737593,0.00015440835,0.000108778455,0.0015053441],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969031,0.0022000335,0.00007672317,0.00035514173,0.00038872936,0.0000761648],"domain_scores_gemma":[0.98474115,0.012888886,0.0008480728,0.0007070469,0.00070520374,0.00010978112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077726776,0.0011441802,0.00093817944,0.0008267798,0.00043326503,0.0006301173,0.0016039258,0.0013014965,0.0014183059],"category_scores_gemma":[0.037629902,0.0005497178,0.0007533335,0.0012965687,0.002090562,0.0014697158,0.0017415681,0.0016488746,0.0002861057],"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":[0.00011504006,0.00009631962,0.005901471,0.00027546217,0.00021124567,0.00021695322,0.00015968274,0.699866,0.00420773,0.14253704,0.0016747052,0.14473832],"study_design_scores_gemma":[0.000010910272,0.000032496537,0.00033761156,0.000008523484,0.000009190139,0.00003312455,0.0000073073115,0.9693833,0.0006239739,0.029073127,0.00047087137,0.0000095080895],"about_ca_topic_score_codex":0.0029872155,"about_ca_topic_score_gemma":0.0024162177,"teacher_disagreement_score":0.0077726776,"about_ca_system_score_codex":0.0005105459,"about_ca_system_score_gemma":0.0012704295,"threshold_uncertainty_score":0.041106403},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010459304,0.00050030864,0.9875915,0.00013497731,0.000038101625,0.000059637496,0.0000906588,0.0002679155,0.00085765996],"genre_scores_gemma":[0.64658886,0.0006567575,0.34862167,0.0003828426,0.00029193232,0.00056228595,0.0007006126,0.0003810011,0.0018140714],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9868132,0.008965843,0.0005731736,0.00139552,0.0019730332,0.00027928292],"domain_scores_gemma":[0.90341425,0.07335985,0.0062483745,0.011273684,0.005284981,0.00041888613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025617605,0.0009217142,0.0011694295,0.0018644452,0.0004976931,0.0015975472,0.0030615316,0.0015338813,0.0038699463],"category_scores_gemma":[0.15639108,0.00059928675,0.0010345619,0.0024041198,0.001870392,0.0026784686,0.0030390962,0.0019014938,0.000770364],"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":[0.0005653243,0.00017372628,0.033273388,0.000765629,0.0009020415,0.00027849418,0.00069248315,0.31289884,0.0051460415,0.25709775,0.005555435,0.38265085],"study_design_scores_gemma":[0.000112400005,0.0002449165,0.012056185,0.00016625384,0.0001648913,0.00016324325,0.00011172884,0.870547,0.0057923766,0.104581326,0.005986437,0.00007326504],"about_ca_topic_score_codex":0.00098301,"about_ca_topic_score_gemma":0.00068070483,"teacher_disagreement_score":0.025617605,"about_ca_system_score_codex":0.0007647021,"about_ca_system_score_gemma":0.0010158176,"threshold_uncertainty_score":0.13548046},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86739576,0.0021423292,0.121155255,0.0025357523,0.00007549004,0.00021968593,0.0015453291,0.00018128834,0.00474908],"genre_scores_gemma":[0.98885286,0.0003462438,0.009644612,0.00009445034,0.000044383472,0.00008276029,0.00053244934,0.000011216261,0.00039088196],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969843,0.0021384172,0.000090678484,0.0004001239,0.00017512673,0.0002113435],"domain_scores_gemma":[0.9761295,0.018797815,0.0026537704,0.0016196388,0.00058165623,0.000217514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010380313,0.0003722127,0.0007254826,0.0015016097,0.000694326,0.0010808762,0.0012451576,0.0006612593,0.0026132877],"category_scores_gemma":[0.03643732,0.00029586346,0.0011892426,0.0021428852,0.001305187,0.00063414813,0.0017312166,0.0010123921,0.00016003533],"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":[0.00037035882,0.00015406423,0.8128144,0.0002936514,0.0008222273,0.00049927447,0.00097081077,0.08600236,0.00028979644,0.03765967,0.0029991972,0.057124216],"study_design_scores_gemma":[0.00016302297,0.00022015374,0.44164056,0.00027542596,0.00085160404,0.00025391052,0.001534606,0.49050903,0.0007556718,0.05861896,0.0051082917,0.000068770096],"about_ca_topic_score_codex":0.05740833,"about_ca_topic_score_gemma":0.03722554,"teacher_disagreement_score":0.05740833,"about_ca_system_score_codex":0.0010955058,"about_ca_system_score_gemma":0.0021379336,"threshold_uncertainty_score":0.11414838},"labels":[],"label_agreement":null}]}