{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":25,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":25,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"fb1763f2f70b","filters":{"venue":"Journal of Data Science"}},"results":[{"id":"W3215602957","doi":"10.6339/22-jds1047","title":"A Review on Graph Neural Network Methods in Financial Applications","year":2022,"lang":"en","type":"review","venue":"Journal of Data Science","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Computer science; Graph; Categorization; Artificial neural network; Financial modeling; Data mining; Data science; Finance; Artificial intelligence; Theoretical computer science; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.1986486505103352,"gpt":0.4830799741744901,"spread":0.2844313236641549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.008679627,0.0003693613,0.001622374,0.0007738631,0.0003662109,0.0001683249,0.01754633,0.00007852393,0.00001720684],"category_scores_gemma":[0.000818335,0.0002770015,0.0003575596,0.01228257,0.0003722827,0.002926539,0.003467009,0.001947128,0.000005432031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000192838,"about_ca_system_score_gemma":0.001434484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001098083,"about_ca_topic_score_gemma":0.000002019792,"domain_scores_codex":[0.9949133,0.0007972986,0.001611287,0.001010732,0.001032551,0.0006348083],"domain_scores_gemma":[0.9932342,0.001200383,0.002246106,0.002967555,0.0001117206,0.0002400809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[9.706417e-7,0.00003529955,3.55876e-7,0.001148327,0.000004318325,0.00003809642,0.000003137934,0.0002788379,8.907303e-8,0.002781851,0.004370948,0.9913378],"study_design_scores_gemma":[0.0000603741,0.000107142,0.000002681441,0.01173269,0.00007091598,0.0005201115,5.282834e-7,0.0007659727,4.351135e-8,0.002017345,0.9844719,0.0002502631],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.153501e-8,0.7810344,0.2173125,0.0001428599,0.0008427524,0.0005586838,0.00002019664,0.00001597319,0.0000726935],"genre_scores_gemma":[4.259521e-8,0.7644638,0.2341639,0.001017343,0.0002775799,0.00004983789,0.00001131376,0.00001198004,0.000004180936],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9910875,"threshold_uncertainty_score":0.9999682,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2514070870","doi":"10.6339/jds.201604_14(2).0002","title":"Comparing Pre-Post Change Across Groups: Guidelines for Choosing between Difference Scores, ANCOVA, and Residual Change Scores","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Analysis of covariance; Residual; Statistics; Significant difference; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.732100748033184,"gpt":0.5505718425854673,"spread":0.1815289054477167,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002966865,0.0002162913,0.0005489197,0.0001610113,0.0003989036,0.0003779499,0.001586564,0.00007019262,0.000002847548],"category_scores_gemma":[0.006347242,0.0001737242,0.00004289964,0.0004975356,0.000647907,0.004406527,0.001520932,0.0002991479,5.524422e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008516822,"about_ca_system_score_gemma":0.000196058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000459474,"about_ca_topic_score_gemma":0.0002020703,"domain_scores_codex":[0.9973553,0.00005243043,0.0008277284,0.0004925734,0.0007447835,0.0005272175],"domain_scores_gemma":[0.9959034,0.0006640108,0.0007688249,0.0007214326,0.001728602,0.0002137323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003279537,0.0005090248,0.4392118,0.001786777,0.0001711164,0.0002004943,0.01250116,0.000003955518,0.177164,0.02338207,0.005195928,0.3395457],"study_design_scores_gemma":[0.002799895,0.001544175,0.6957232,0.009362725,0.0003591907,0.001093963,0.003352721,0.005939356,0.09026293,0.1856637,0.002183412,0.001714715],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9079538,0.001229007,0.08835369,0.001356169,0.0001885948,0.0004030296,0.0004528069,0.00005559841,0.00000732839],"genre_scores_gemma":[0.6879482,0.0005213979,0.3101687,0.0002705036,0.001013134,0.00001618845,0.00003118515,0.00002069607,0.0000100154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.337831,"threshold_uncertainty_score":0.7598701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2564423956","doi":"10.6339/jds.201407_12(3).0001","title":"Factorial ANOVA with unbalanced data: A fresh look at the types of sums of squares","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Confusion; Factorial; Factorial analysis; Analysis of variance; Statistics; Type (biology); Econometrics; Mathematics; Factorial experiment; Explained sum of squares; Lack-of-fit sum of squares; Generalized least squares; Computer science; Arithmetic; Psychology; Non-linear least squares","retraction":null,"screen_n_in":null,"score":{"opus":0.7074570963113356,"gpt":0.5968141994031163,"spread":0.1106428969082193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007997203,0.00008831879,0.0005194033,0.00004790227,0.00007043596,0.00004492459,0.002866848,0.00004080647,0.0002216073],"category_scores_gemma":[0.1147987,0.00004559166,0.0000371144,0.0006063238,0.001471959,0.0006638664,0.001430363,0.0002194242,0.000001908252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002700373,"about_ca_system_score_gemma":0.0007903302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001093551,"about_ca_topic_score_gemma":0.00005547603,"domain_scores_codex":[0.9970808,0.0003009108,0.0009388548,0.0002832031,0.001221004,0.0001752097],"domain_scores_gemma":[0.9769497,0.01895624,0.001209696,0.002039701,0.0007513733,0.00009330993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004687378,0.002414256,0.03666034,0.001418672,0.001262873,0.0005066034,0.001682416,0.0001075556,0.5707844,0.1781355,0.1538323,0.04850769],"study_design_scores_gemma":[0.006842674,0.002210353,0.01025588,0.001979161,0.001185572,0.0004495072,0.001498645,0.001543183,0.378513,0.5848663,0.01001384,0.0006418028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5575567,0.0008891036,0.4217253,0.001905457,0.005918542,0.0005733939,0.009597329,0.00001854846,0.001815557],"genre_scores_gemma":[0.2052263,0.0000989788,0.7941126,0.00004431044,0.0004563261,3.222787e-7,0.00000754377,0.000009523447,0.00004416821],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4067309,"threshold_uncertainty_score":0.8926578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2181556329","doi":"10.6339/jds.2004.02(1).135","title":"The Poisson Inverse Gaussian Regression Model in the Analysis of Clustered Counts Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Guelph; Western University","funders":"","keywords":"Poisson regression; Statistics; Mathematics; Covariate; Poisson distribution; Negative binomial distribution; Count data; Inverse Gaussian distribution; Regression analysis; Generalized linear model; Regression; Distribution (mathematics); Population","retraction":null,"screen_n_in":null,"score":{"opus":0.1427107502866689,"gpt":0.3991228810900525,"spread":0.2564121308033835,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.006640339,0.00005603813,0.0001554227,0.0001655429,0.0001394535,0.0002101164,0.008004703,0.00002205919,0.000003629827],"category_scores_gemma":[0.0004351679,0.00002636804,0.00003460708,0.002247252,0.0002050204,0.002039676,0.001495778,0.000180017,8.720458e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001895516,"about_ca_system_score_gemma":0.0005522894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007537174,"about_ca_topic_score_gemma":0.00006124757,"domain_scores_codex":[0.998357,0.0001900772,0.0003165695,0.0002591974,0.0007285899,0.0001485385],"domain_scores_gemma":[0.9967541,0.0001686711,0.0003147315,0.002551438,0.0001576228,0.00005341327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005588788,0.0004171719,0.0009515773,0.00003194669,0.000273274,0.0003326146,0.005883321,0.003402537,0.01612442,0.1048271,0.07292892,0.7947712],"study_design_scores_gemma":[0.00008878438,0.000008989372,0.0009495883,0.00003196793,0.00005123628,0.00003472892,0.00007699144,0.9932007,0.0001499178,0.003519751,0.001847563,0.00003979444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001734458,0.0003405519,0.9936621,0.003240077,0.0001769532,0.00002688701,0.00003711614,0.000001657866,0.0007802075],"genre_scores_gemma":[0.2698298,0.0006132637,0.7287197,0.0006596601,0.00005225772,2.553277e-7,0.00001258889,0.000003071701,0.0001093541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9897981,"threshold_uncertainty_score":0.9973625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2182961570","doi":"10.6339/jds.2004.02(1).142","title":"A Two-Stage Bayesian Model for Predicting Winners in Major League Baseball","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Korea Science and Engineering Foundation","keywords":"League; Markov chain Monte Carlo; Bayesian probability; Bayesian inference; Computer science; Econometrics; Field (mathematics); Markov chain; Inference; Artificial intelligence; Operations research; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09328473143994379,"gpt":0.3027483287623079,"spread":0.2094635973223641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003090281,0.00007657336,0.0002569642,0.0003067024,0.0001109623,0.0001507452,0.0008867721,0.00002582091,0.0001069996],"category_scores_gemma":[0.0003865006,0.00007738193,0.00005456427,0.0005636302,0.000113646,0.002063097,0.0001816244,0.0001596936,0.000003730931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008306821,"about_ca_system_score_gemma":0.0003504555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005506722,"about_ca_topic_score_gemma":0.0001832306,"domain_scores_codex":[0.9985933,0.000003058674,0.0007177817,0.0003144714,0.0000995576,0.0002718539],"domain_scores_gemma":[0.9987273,0.00003644381,0.0005494088,0.0004612438,0.0001164433,0.0001091109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009410277,0.0003772441,0.5565434,0.0001383105,0.00006313914,0.0001785436,0.001409378,0.3024364,0.001117902,0.1307053,0.003551424,0.003384825],"study_design_scores_gemma":[0.0005843013,0.000027319,0.003203453,0.00003651033,0.000004513225,0.00002058319,0.0001586805,0.9902189,0.00008116342,0.001094788,0.004471166,0.00009862907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4706391,0.001603278,0.5171114,0.002117533,0.0009229393,0.0001785624,0.001420795,0.000008174851,0.005998178],"genre_scores_gemma":[0.9789901,0.0001870621,0.0197134,0.0002622072,0.0001211224,9.334387e-7,0.00001474107,0.000007786875,0.0007026966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6877825,"threshold_uncertainty_score":0.3155544,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3138069980","doi":"10.6339/jds.201207_10(3).0006","title":"A Data Mining Approach to Comparing American and Canadian Grade 10 Students’ PISA Science Test Performance","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Test (biology); Academic achievement; Mathematics education; Achievement test; Psychology; Political science; Standardized test","retraction":null,"screen_n_in":null,"score":{"opus":0.1098757292940929,"gpt":0.3657505192465182,"spread":0.2558747899524254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004324073,0.0001194834,0.0002479314,0.0005661916,0.0007169619,0.001708918,0.01360755,0.00001246183,0.00000158472],"category_scores_gemma":[0.001720924,0.0001038905,0.00001256683,0.004309228,0.001097888,0.005762088,0.005574811,0.0002825989,0.000005799383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001210666,"about_ca_system_score_gemma":0.003398544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006905925,"about_ca_topic_score_gemma":0.001122176,"domain_scores_codex":[0.9968207,0.0000318846,0.0003520878,0.0007855649,0.001448606,0.0005611897],"domain_scores_gemma":[0.9964073,0.0001028206,0.0002727047,0.001984949,0.0004081513,0.0008240441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006256724,0.0006922846,0.8462794,0.00005394688,0.00003425064,0.0002329053,0.003046144,0.002528361,0.006256429,0.0009613115,0.005582249,0.1343264],"study_design_scores_gemma":[0.0001984357,0.0001612949,0.1744384,0.000113229,0.00001547629,0.0006936764,0.0008877355,0.8144599,0.0001365018,0.00000920536,0.008658362,0.000227815],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720128,0.0001083208,0.02204034,0.004433875,0.0002779155,0.00005616598,0.00005105435,0.0000194266,0.001000153],"genre_scores_gemma":[0.7565812,0.00003571608,0.2428893,0.0003521005,0.0000796419,1.420572e-7,0.00000521869,0.000003538297,0.00005312094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8119315,"threshold_uncertainty_score":0.9993274,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2181591901","doi":"10.6339/jds.2008.06(3).508","title":"Evaluating Aortic Stenosis Using the Archimedean Copula Methodology","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Copula (linguistics); Stenosis; China; Statistics; Econometrics; Actuarial science; Mathematics; Medicine; Cardiology; Internal medicine; Business; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.8478728438504952,"gpt":0.6353580343979097,"spread":0.2125148094525855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01583181,0.00007505135,0.0002552419,0.0000680932,0.0002694102,0.0001213412,0.001413536,0.00002106633,0.0001244786],"category_scores_gemma":[0.06214725,0.00004364635,0.00003734853,0.0005804625,0.0006242409,0.0004578724,0.0006532015,0.0002819175,0.000001583095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004020914,"about_ca_system_score_gemma":0.0007895619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008651919,"about_ca_topic_score_gemma":0.000001797654,"domain_scores_codex":[0.9972565,0.000933705,0.0005566085,0.0002171634,0.0007884051,0.0002476097],"domain_scores_gemma":[0.9914322,0.006620479,0.0004963205,0.000764721,0.0005719274,0.0001143576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003319631,0.0001784943,0.001964483,0.0000840271,0.00007553044,0.000109988,0.001642302,0.00008167928,0.3790466,0.193218,0.000533426,0.4230323],"study_design_scores_gemma":[0.000442262,0.0002963663,0.005407384,0.0003121872,0.0003702934,0.001016626,0.002695564,0.1753732,0.01944175,0.7942369,0.0001735191,0.000233909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2971866,0.00007152477,0.7017448,0.0004467312,0.000327531,0.00003935173,0.0000177699,0.00000295785,0.0001627156],"genre_scores_gemma":[0.08308332,0.00001750591,0.9166182,0.0001597144,0.0001053048,2.509364e-7,4.349512e-7,0.000004985994,0.00001033246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6010189,"threshold_uncertainty_score":0.9457527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2189164006","doi":"10.6339/jds.2004.02(2).144","title":"Wavelet Analysis of Tide-affected Low Streamflows Series","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Series (stratigraphy); Streamflow; Wavelet; Environmental science; Quantile; Flow (mathematics); Noise (video); Frequency domain; Wavelet transform; Geology; Mathematics; Statistics; Computer science; Geography; Mathematical analysis; Drainage basin","retraction":null,"screen_n_in":null,"score":{"opus":0.04068391126091666,"gpt":0.3338900321005291,"spread":0.2932061208396125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003361136,0.00009132154,0.0003766235,0.0005706875,0.0001292408,0.0003130076,0.003586734,0.00002632541,0.00002916149],"category_scores_gemma":[0.001226327,0.00007195819,0.0001127138,0.006106427,0.0003350182,0.007973767,0.0009420873,0.0001579283,0.000002544556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003110023,"about_ca_system_score_gemma":0.0008881874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001525909,"about_ca_topic_score_gemma":0.0000179733,"domain_scores_codex":[0.9977916,0.0001918676,0.0004915312,0.000335744,0.0009571777,0.000232068],"domain_scores_gemma":[0.9969163,0.0001857844,0.0004531297,0.001340937,0.0009694245,0.0001344038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000397565,0.0003965229,0.001483463,0.00004736683,0.0006112453,0.001095338,0.0009813667,0.001718312,0.8042411,0.007310686,0.001712982,0.1803618],"study_design_scores_gemma":[0.001076034,0.00047684,0.07205319,0.0002344304,0.0008708742,0.001189099,0.000249233,0.2334723,0.6856671,0.001582954,0.002621515,0.000506452],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1713868,0.0002687049,0.8268139,0.0005225147,0.000425194,0.00002678433,0.00004773253,0.00001128765,0.0004971006],"genre_scores_gemma":[0.3395992,0.0001298458,0.6599969,0.0001308507,0.00004395191,1.293953e-7,0.000008598392,0.000003209907,0.00008736557],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.231754,"threshold_uncertainty_score":0.6665103,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2185363721","doi":"10.6339/jds.2010.08(1).585","title":"A Bayesian Estimator of the Intracluster Correlation Coefficient from Correlated Binary Responses","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Water Quality and Resources Studies","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Mathematics; Estimator; Statistics; Beta-binomial distribution; Negative binomial distribution; Poisson distribution","retraction":null,"screen_n_in":null,"score":{"opus":0.05897463788431407,"gpt":0.2840856813768295,"spread":0.2251110434925154,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001293521,0.00007119749,0.0001434055,0.00003909075,0.000310807,0.00004701109,0.001181771,0.00003134359,0.0002346862],"category_scores_gemma":[0.0008117645,0.00004141702,0.00004078079,0.0007065236,0.001428744,0.0007823008,0.001465086,0.000181962,0.0000182453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007502238,"about_ca_system_score_gemma":0.0001307135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007403023,"about_ca_topic_score_gemma":0.00002554998,"domain_scores_codex":[0.9982587,0.0001607188,0.0003978736,0.0002100162,0.0008216094,0.0001511134],"domain_scores_gemma":[0.9987224,0.0002173837,0.0003904857,0.0005382271,0.00005974883,0.00007176922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005959272,0.00119758,0.4711885,0.0000345871,0.0001116821,0.0002695934,0.01627379,0.1037144,0.3713824,0.0001888777,0.02267021,0.01237238],"study_design_scores_gemma":[0.0008952338,0.0002215596,0.7749177,0.0003714504,0.000131253,0.0002980026,0.00292131,0.1833692,0.02481415,0.0004597426,0.01133833,0.0002620385],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885507,0.0001972616,0.008221807,0.001935321,0.0005704027,0.00005614392,0.00007147002,0.000003686725,0.000393234],"genre_scores_gemma":[0.9958688,0.00002583644,0.003733797,0.0001364878,0.00003112259,1.77489e-7,0.000003679987,0.000003026046,0.0001970729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3465683,"threshold_uncertainty_score":0.5264268,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2185241920","doi":"10.6339/jds.201101_09(1).0005","title":"Estimating Transmissibility of Seasonal Influenza Virus by Surveillance Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada","keywords":"Transmissibility (structural dynamics); Outbreak; Estimation; Transmission (telecommunications); Flu season; Seasonal influenza; Virus; Vaccination; Influenza A virus; Virology; Statistics; Biology; Computer science; Medicine; Mathematics; Coronavirus disease 2019 (COVID-19); Disease; Engineering; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.2321728817170107,"gpt":0.4759016103250826,"spread":0.2437287286080719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006580694,0.0001098485,0.0004226906,0.00009846438,0.000165928,0.00006264912,0.002205427,0.00003139592,0.00009393124],"category_scores_gemma":[0.01202163,0.00008261368,0.00004139932,0.0008931615,0.001202214,0.002294322,0.00135834,0.0003927136,0.000003969507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007930442,"about_ca_system_score_gemma":0.002594978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003997041,"about_ca_topic_score_gemma":0.00001624939,"domain_scores_codex":[0.996529,0.0001016975,0.0007106377,0.00044801,0.001868695,0.0003419226],"domain_scores_gemma":[0.9956803,0.0003487134,0.0003964177,0.001934367,0.001360733,0.0002794827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0005415491,0.0007070996,0.219478,0.0005746724,0.0002040258,0.0002942247,0.000459185,0.000105558,0.685939,0.00003674521,0.02312602,0.06853398],"study_design_scores_gemma":[0.008539447,0.001199046,0.6130591,0.002059504,0.000304762,0.00193875,0.0009568197,0.1382414,0.1443495,0.0003511925,0.08822603,0.0007744214],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9766737,0.00922522,0.008379192,0.001513591,0.0002713839,0.0001710576,0.003205441,0.00001222192,0.0005482211],"genre_scores_gemma":[0.8546209,0.00054552,0.1437077,0.0007272205,0.0002546216,6.068832e-7,0.00009236294,0.00001396245,0.00003709118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5415894,"threshold_uncertainty_score":0.9963005,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2190667587","doi":"10.6339/jds.2003.01(2).131","title":"Analysis of Unbalanced Microarray Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Microarray analysis techniques; China; Data science; Microarray databases; Library science; Data analysis; Data mining; Computer science; Statistics; Political science; Mathematics; Biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.06929950204773849,"gpt":0.3692050382421703,"spread":0.2999055361944318,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007697123,0.00003915673,0.0001172237,0.0001133444,0.00003708763,0.00002697405,0.001807787,0.00002374832,0.0000299597],"category_scores_gemma":[0.0003418654,0.00003143483,0.00003203641,0.0009511275,0.0001705375,0.0000445537,0.0006426651,0.00004400253,5.381578e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006355207,"about_ca_system_score_gemma":0.0005758295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001681202,"about_ca_topic_score_gemma":0.000008907719,"domain_scores_codex":[0.9991241,0.00002735226,0.0002364811,0.0002639579,0.0002661177,0.00008195655],"domain_scores_gemma":[0.9977617,0.000006508385,0.0002849042,0.001552304,0.0003350336,0.00005953806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001074889,0.00002962798,0.003065082,0.000002265711,0.00006434225,0.000001389255,0.000009616234,0.00004051481,0.9890066,0.00001020381,0.004068903,0.003690704],"study_design_scores_gemma":[0.000244956,0.00004722432,0.03026665,0.00001615716,0.0002196599,0.00002564854,0.0002274451,0.001329423,0.8843977,0.000007971822,0.08314189,0.00007526024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9524938,0.002871392,0.04204399,0.0008689092,0.0004376131,0.00003563118,0.0005520707,0.000001656097,0.0006949537],"genre_scores_gemma":[0.9922895,0.0006030778,0.006496013,0.0001086106,0.00006910665,1.015907e-7,0.0003422801,0.000002000958,0.00008928684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1046089,"threshold_uncertainty_score":0.3359348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3053629049","doi":"10.6339/jds.202007_18(3).0018","title":"Data Visualization and Descriptive Analysis for Understanding Epidemiological Characteristics of COVID-19: A Case Study of a Dataset from January 22, 2020 to March 29, 2020","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Case fatality rate; Epidemiology; Coronavirus disease 2019 (COVID-19); Coronavirus; Incubation period; Medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Nonparametric statistics; Disease; Internal medicine; Pathology; Statistics; Psychology; Incubation; Infectious disease (medical specialty); Outbreak","retraction":null,"screen_n_in":null,"score":{"opus":0.6960204092600549,"gpt":0.5511004728700827,"spread":0.1449199363899722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01144667,0.0001721722,0.001213833,0.0002101476,0.000267307,0.00005679892,0.001644897,0.00005833986,0.00004391964],"category_scores_gemma":[0.1409302,0.0001231554,0.00006226088,0.001821445,0.0005378365,0.0008630788,0.003857885,0.0001835224,2.410041e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002216817,"about_ca_system_score_gemma":0.0004898361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004113865,"about_ca_topic_score_gemma":0.000803528,"domain_scores_codex":[0.9961742,0.0006655864,0.001520616,0.0007665899,0.0006068689,0.0002661126],"domain_scores_gemma":[0.9831129,0.01320773,0.001463971,0.001408038,0.0004304791,0.0003768335],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.002447822,0.00685594,0.6735767,0.001405592,0.006356285,0.008175047,0.01652803,0.0006081801,0.008603422,0.01054078,0.2625439,0.002358317],"study_design_scores_gemma":[0.009661905,0.00910592,0.1841908,0.0008614925,0.01855595,0.002460132,0.346473,0.2945874,0.0002420644,0.1214136,0.01025192,0.002195869],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4141982,0.0001431572,0.5497556,0.00113912,0.00005749861,0.0003419453,0.03435899,0.000004121116,0.000001418391],"genre_scores_gemma":[0.9430358,0.0002662963,0.05467123,0.0005284995,0.00008160291,0.000003933843,0.00140521,0.000006032816,0.000001330198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5288377,"threshold_uncertainty_score":0.8663061,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3047907238","doi":"10.6339/jds.202007_18(3).0015","title":"COVID-19 Fatality: A Cross-Sectional Study using Adaptive Lasso Penalized Sliced Inverse Regression","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Case fatality rate; Lasso (programming language); Coronavirus disease 2019 (COVID-19); Outbreak; Feature selection; Regression; Pandemic; Regression analysis; Population; Statistics; Medicine; Computer science; Disease; Mathematics; Infectious disease (medical specialty); Virology; Artificial intelligence; Environmental health; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.723200934496076,"gpt":0.58094962354606,"spread":0.1422513109500161,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01172496,0.0001765539,0.0005421838,0.0001640376,0.000818791,0.0002135026,0.001572083,0.00006237454,0.000214574],"category_scores_gemma":[0.09476079,0.0001169835,0.0001088176,0.00109184,0.0008968957,0.001899472,0.00243331,0.000415446,0.000006140687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007819641,"about_ca_system_score_gemma":0.00251352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001651937,"about_ca_topic_score_gemma":0.0001855808,"domain_scores_codex":[0.995985,0.0005573085,0.00100583,0.0006044346,0.00149573,0.0003516584],"domain_scores_gemma":[0.9934072,0.003213124,0.001158713,0.0008723917,0.000877201,0.0004713965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000654063,0.001706798,0.9625285,0.000136241,0.0002857315,0.001282761,0.002245721,0.0005061773,0.0175616,0.003774499,0.008964414,0.0003534595],"study_design_scores_gemma":[0.01163772,0.001634568,0.7973773,0.0005506745,0.0006044402,0.002394201,0.0163217,0.03541623,0.001297232,0.11614,0.01520053,0.001425404],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.978149,0.0001088809,0.0199916,0.0008857669,0.0004089137,0.0002138937,0.0001219564,0.00002466432,0.00009530933],"genre_scores_gemma":[0.9355711,0.00004805982,0.06258841,0.001475216,0.0002265767,0.000002088151,0.000005269304,0.000009858567,0.00007340601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1651512,"threshold_uncertainty_score":0.9128644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394949264","doi":"10.6339/24-jds1122","title":"BIE: Binary Image Encoding for the Classification of Tabular Data","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Encoding (memory); Pattern recognition (psychology); Convolutional neural network; Contextual image classification; Benchmark (surveying); Image (mathematics); Deep learning; Feature (linguistics); Field (mathematics); Binary image; Image processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1344438530442302,"gpt":0.4013867433579452,"spread":0.266942890313715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.007706206,0.00007802618,0.0001307884,0.0002435514,0.0002811387,0.000501885,0.01324826,0.00002207764,0.000006115273],"category_scores_gemma":[0.002050845,0.00004887885,0.00003290367,0.001312964,0.0004870626,0.01066193,0.003003365,0.000280369,0.000003550487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004360569,"about_ca_system_score_gemma":0.0007115863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006074778,"about_ca_topic_score_gemma":8.614966e-7,"domain_scores_codex":[0.9981767,0.0000522311,0.0004134818,0.0004133142,0.0007507002,0.0001935754],"domain_scores_gemma":[0.9963021,0.0008389234,0.0003698044,0.002187422,0.0002416877,0.00006004443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003547081,0.0001030375,0.0004391841,0.0002005431,0.00008028596,0.00007782885,0.001254583,0.006732252,0.5858502,0.1089871,0.02208731,0.2741522],"study_design_scores_gemma":[0.00009036637,0.00005399955,0.001305681,0.00009931105,0.00002631104,0.00005923465,0.000139076,0.9828343,0.0005814522,0.000547315,0.01420075,0.00006218494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001656687,0.0008709146,0.9914201,0.004463262,0.001316331,0.00009583672,0.00004900914,0.00001859298,0.0001092014],"genre_scores_gemma":[0.653806,0.000132484,0.3456773,0.00004345236,0.0003018965,7.771951e-7,0.000009957498,0.000006466732,0.00002163403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9761021,"threshold_uncertainty_score":0.9920905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210580103","doi":"10.6339/22-jds1034","title":"Computational Challenges of t and Related Copulas","year":2022,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Copula (linguistics); Skew; Quantile; Computer science; Marginal distribution; Applied mathematics; Mathematics; Econometrics; Random variable; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.12877524547984,"gpt":0.2953975106835824,"spread":0.1666222652037424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002544924,0.00003204922,0.0001534876,0.0001967236,0.000145513,0.000015215,0.0005331874,0.00001004632,0.00004802323],"category_scores_gemma":[0.0002191208,0.00003455838,0.00001787997,0.0002449276,0.0001726208,0.0007661697,0.0003280916,0.0001240265,0.00000166804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002972912,"about_ca_system_score_gemma":0.000083091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001611766,"about_ca_topic_score_gemma":0.000001020969,"domain_scores_codex":[0.99921,0.000008585505,0.0004578898,0.000145881,0.00009876237,0.00007887351],"domain_scores_gemma":[0.9992206,0.00004110707,0.0004800413,0.0001681381,0.00005406223,0.00003607471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004751949,0.0002021044,0.0373231,0.00003556937,0.00002652405,0.00001153327,0.002458383,0.02752479,0.000109481,0.9067809,0.0004568081,0.02502327],"study_design_scores_gemma":[0.0006950299,0.0003488051,0.1176431,0.00002305156,0.00000691378,0.0001549879,0.0006325201,0.6107587,0.00001275421,0.2607127,0.008862898,0.0001485746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9832312,0.0101037,0.003542325,0.001120282,0.0003264497,0.00003812524,0.0002494908,0.000002388149,0.001385976],"genre_scores_gemma":[0.995,0.0004865871,0.004469322,0.00001684644,0.00001372294,1.662869e-7,0.000002640838,0.000002052288,0.000008654887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6460682,"threshold_uncertainty_score":0.140925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392752805","doi":"10.6339/24-jds1121","title":"Testing Perceptual Accuracy in a U.S. General Population Survey Using Stacked Bar Charts","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Bar chart; Visualization; Perception; Computer science; Bar (unit); Data visualization; Information visualization; Pie chart; Population; Key (lock); Data science; Survey data collection; Human–computer interaction; Data mining; Psychology; Statistics; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.2466232187591786,"gpt":0.4300851825046271,"spread":0.1834619637454485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004490261,0.00008177588,0.000136549,0.0004861497,0.0001240516,0.001102157,0.002368154,0.00002063948,0.00001283286],"category_scores_gemma":[0.002348063,0.00006750062,0.00001805819,0.002536709,0.0001114972,0.01113635,0.0007321038,0.0001590032,0.000008169129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001076201,"about_ca_system_score_gemma":0.0006612935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002407559,"about_ca_topic_score_gemma":0.00003842876,"domain_scores_codex":[0.9981562,0.0001030859,0.0004745974,0.0003295503,0.0007115194,0.0002250164],"domain_scores_gemma":[0.9987277,0.0002138615,0.0001941992,0.0005038559,0.0002452486,0.0001151441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002661255,0.0005108597,0.4794505,0.0001782744,0.00004919318,0.0008733842,0.005223976,0.01749722,0.1022181,0.04809641,0.007204383,0.3386711],"study_design_scores_gemma":[0.00007382543,0.00002375205,0.1493928,0.0001001033,0.000003236001,0.00009645964,0.00002317405,0.8497407,0.00004139396,0.0001193615,0.0003058281,0.00007937441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6868399,0.0001172735,0.3120004,0.0001857429,0.0006845215,0.00004855884,0.00006931691,0.00002500774,0.00002934005],"genre_scores_gemma":[0.924145,0.00001766072,0.07556961,0.000106257,0.0001199243,6.949025e-8,0.00002803828,0.000004461363,0.000009007565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8322434,"threshold_uncertainty_score":0.9999348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2188439980","doi":"10.6339/jds.201404_12(2).0008","title":"SENSITIVITY ANALYSIS OF BAYES FACTOR FOR CATEGORICAL DATA WITH EMPHASIS ON SPARSE MULTINOMIAL DATA","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Government of Newfoundland and Labrador","funders":"","keywords":"Categorical variable; Multinomial distribution; Contingency table; Bayes factor; Prior probability; Dirichlet distribution; Computer science; Bayes' theorem; Bayesian probability; Sensitivity (control systems); Context (archaeology); Econometrics; Statistics; Consistency (knowledge bases); Factor analysis; Data mining; Mathematics; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2991029132364069,"gpt":0.4089341009435077,"spread":0.1098311877071008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003439849,0.0001198776,0.0005418054,0.00007034904,0.0002066458,0.0001406638,0.002501789,0.00004033492,0.0001522587],"category_scores_gemma":[0.005224105,0.00004243374,0.00007595112,0.002108755,0.0003965276,0.001333108,0.000993519,0.0001392246,9.408042e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001973114,"about_ca_system_score_gemma":0.0001311951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001094898,"about_ca_topic_score_gemma":0.001052833,"domain_scores_codex":[0.9975293,0.0002631644,0.0004894179,0.0007221811,0.0007513015,0.0002445813],"domain_scores_gemma":[0.995061,0.002778528,0.0004562415,0.0009969957,0.0005105012,0.0001967437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000486863,0.0008458038,0.01509571,0.000013753,0.0009269539,0.0002106918,0.00006567787,0.0003254951,0.2993062,0.0005223328,0.001147078,0.6810535],"study_design_scores_gemma":[0.0006302563,0.001017291,0.6311952,0.0000463446,0.00314434,0.0001338284,0.0008636329,0.335306,0.01178788,0.0001216365,0.01527988,0.0004737338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9264234,0.00007049247,0.04888042,0.001221954,0.0001447486,0.00008689805,0.0231298,0.000005622992,0.00003666569],"genre_scores_gemma":[0.9328405,0.00004644249,0.06588476,0.0000937814,0.0001716327,1.646416e-7,0.0009511833,7.02193e-7,0.00001084146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6805797,"threshold_uncertainty_score":0.6254119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400245371","doi":"10.6339/24-jds1143","title":"Physician Effects in Critical Care: A Causal Inference Approach Through Propensity Weighting with Parametric and Super Learning Methods","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Propensity score matching; Weighting; Causal inference; Covariate; Confounding; Inverse probability weighting; Estimator; Parametric statistics; Intensive care unit; Computer science; Medicine; Statistics; Intensive care medicine; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3299550711103181,"gpt":0.5379351258148638,"spread":0.2079800547045457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003244107,0.0001624719,0.0003797658,0.0003242841,0.0001472083,0.0003264702,0.0007325846,0.00004944994,0.000001432361],"category_scores_gemma":[0.008248367,0.0001062239,0.00002001586,0.00178249,0.000857624,0.004808632,0.000526991,0.0009037742,6.741744e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215689,"about_ca_system_score_gemma":0.0003896698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001801169,"about_ca_topic_score_gemma":0.000004689755,"domain_scores_codex":[0.9980167,0.0002532307,0.0003632564,0.0004379753,0.0005882335,0.0003406258],"domain_scores_gemma":[0.9963394,0.002762388,0.0001336952,0.0003903232,0.0002742821,0.00009984375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001301272,0.0005623878,0.01658872,0.004712914,0.00007646345,0.001046746,0.01569311,0.0002091062,0.06137669,0.6286972,0.0001356386,0.2707709],"study_design_scores_gemma":[0.001795865,0.005685781,0.01145032,0.01078512,0.0007080071,0.003157263,0.01122919,0.1545424,0.1006476,0.6957391,0.001777597,0.00248173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1592505,0.0007925133,0.8388926,0.00008422919,0.00007045051,0.0001889949,0.000003262585,0.00005709082,0.0006603087],"genre_scores_gemma":[0.5136003,0.00002849429,0.4863088,0.00001903706,0.0000304724,0.000002371085,6.427164e-7,0.000008102314,0.000001805588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3543497,"threshold_uncertainty_score":0.9874662,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4398770290","doi":"10.6339/24-jds1131","title":"Evaluating Perceptual Judgements on 3D Printed Bar Charts","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Bar (unit); Bar chart; Perception; Computer science; Engineering drawing; Psychology; Statistics; Mathematics; Engineering; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.1546686567399368,"gpt":0.3983999130363163,"spread":0.2437312562963795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001852501,0.00006903847,0.0001029239,0.0002497934,0.00007712385,0.000189543,0.0007630649,0.00001446765,0.0001466251],"category_scores_gemma":[0.0001867838,0.00005215048,0.00003356529,0.0004174773,0.00006696502,0.001035515,0.000112844,0.0002034894,0.00009687713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006568603,"about_ca_system_score_gemma":0.00008980424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001111081,"about_ca_topic_score_gemma":3.532473e-7,"domain_scores_codex":[0.9987356,0.00001264181,0.0002518274,0.0001655377,0.0006721501,0.0001622269],"domain_scores_gemma":[0.9994685,0.00003295796,0.00003263184,0.0002965647,0.00008665791,0.00008266592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008822029,0.00005653867,0.0001371049,0.00009565298,0.0001473993,0.0000922566,0.001503834,0.4561051,0.1304389,0.0001296964,0.007199176,0.4040855],"study_design_scores_gemma":[0.00005653439,0.00004952357,0.0001850298,0.0001873003,0.00003283641,0.0000183867,0.00008623123,0.997947,0.0004310592,0.00001865065,0.000925866,0.00006152874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.923427,0.0005484865,0.07301013,0.0002295564,0.001162048,0.0000415303,0.00003129485,0.00008151535,0.001468457],"genre_scores_gemma":[0.9920022,0.00007216065,0.007644075,0.00003677481,0.000177263,2.269932e-7,0.000003044305,0.000007734611,0.0000564955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5418419,"threshold_uncertainty_score":0.2126635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3135587851","doi":"10.6339/jds.201807_16(3).0002","title":"Minimum Profile Hellinger Distance Estimation for A Two-Sample Location-Shifted Model","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Hellinger distance; Nonparametric statistics; Parametric statistics; Robustness (evolution); Mathematics; Asymptotic distribution; Parametric model; Statistics; Semiparametric regression; Sample size determination; Consistency (knowledge bases); Estimation theory; Applied mathematics; Semiparametric model; Estimator","retraction":null,"screen_n_in":null,"score":{"opus":0.2435364681247042,"gpt":0.4655376581424227,"spread":0.2220011900177184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002011104,0.00007416882,0.0001832401,0.00005812961,0.0001450147,0.0001281328,0.0006955267,0.00002048239,0.00003593604],"category_scores_gemma":[0.02278411,0.00005878542,0.00002488422,0.0005022013,0.0002114424,0.0009751854,0.0001211499,0.0001014075,0.000002190312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004310677,"about_ca_system_score_gemma":0.0008099211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000179453,"about_ca_topic_score_gemma":0.000003887304,"domain_scores_codex":[0.9986331,0.00003596408,0.0004513132,0.0002254743,0.0004684451,0.0001857134],"domain_scores_gemma":[0.9961177,0.001792334,0.00035918,0.0004948264,0.00112853,0.0001074276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008750558,0.000415829,0.00008809698,0.0003337372,0.00002502762,0.00001085403,0.0006151959,0.003379785,0.01486656,0.8967551,0.00558013,0.07784216],"study_design_scores_gemma":[0.0001814309,0.00003112304,0.00002555212,0.00008025086,0.00001978907,0.00001051877,0.00004473115,0.6520442,0.002906324,0.3444875,0.0001130788,0.0000555567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004180179,0.0000711746,0.994684,0.0003346869,0.0001483439,0.0001051634,0.0003616832,0.000006228179,0.0001084936],"genre_scores_gemma":[0.08543681,0.000009065781,0.9143575,0.00006460801,0.00005876124,0.000003794165,0.00001659906,0.000005943924,0.00004684585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6486644,"threshold_uncertainty_score":0.9854474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3157762174","doi":"10.6339/21-jds993","title":"Testing for COVID-19: Some Statistical Issues","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Coronavirus disease 2019 (COVID-19); Coronavirus; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Test (biology); Computer science; Statistical hypothesis testing; Statistical analysis; Statistics; Virology; Medicine; Mathematics; Outbreak; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.2762481615787679,"gpt":0.4780197762690521,"spread":0.2017716146902842,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00177704,0.00005431661,0.000164047,0.0001151627,0.0001939152,0.00008955463,0.0003262788,0.00001833438,0.0000280967],"category_scores_gemma":[0.05919012,0.00004272769,0.00002104257,0.0005150358,0.0002712198,0.0008601853,0.0001469908,0.0001501826,0.000005294452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007570266,"about_ca_system_score_gemma":0.002008409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001148654,"about_ca_topic_score_gemma":0.000002305679,"domain_scores_codex":[0.9988235,0.00001928143,0.000306357,0.0002008638,0.0004666183,0.0001834312],"domain_scores_gemma":[0.9979582,0.0008144599,0.0001840356,0.000301068,0.0005236166,0.0002186468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004384068,0.00009071966,0.004816713,0.00008566799,0.0000130033,0.0005050303,0.00009698358,0.000004327163,0.9626306,0.001256431,0.005441057,0.02501568],"study_design_scores_gemma":[0.005706171,0.002212524,0.01779018,0.0006905152,0.0003481931,0.02924143,0.001911423,0.04889923,0.5755649,0.009894229,0.3072731,0.0004681021],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7139465,0.001786996,0.2662633,0.0144022,0.001766915,0.0003237295,0.0002923372,0.0000884937,0.001129569],"genre_scores_gemma":[0.433285,0.000009509319,0.5568482,0.00892177,0.0008574066,9.675399e-7,0.000009089345,0.0000101999,0.00005780367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3870656,"threshold_uncertainty_score":0.9487347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127126615","doi":"10.6339/21-jds997","title":"A Vine Copula Model for Climate Trend Analysis using Canadian Temperature Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Western University; Actua; University of Waterloo","funders":"","keywords":"Copula (linguistics); Vine copula; Multivariate statistics; Econometrics; Computer science; Climate change; Climate model; Data mining; Mathematics; Machine learning; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.2421264965514139,"gpt":0.3988594280744594,"spread":0.1567329315230455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001549856,0.0001118721,0.0002710157,0.00006695727,0.0006614571,0.000504613,0.002586828,0.00005394841,0.00009985681],"category_scores_gemma":[0.0007083743,0.00003652014,0.00009039604,0.00255367,0.0001915556,0.0026449,0.0007191066,0.0001813247,0.000001717794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008830171,"about_ca_system_score_gemma":0.0003937783,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0025849,"about_ca_topic_score_gemma":0.1792681,"domain_scores_codex":[0.9979364,0.00004202181,0.0003633362,0.0004659039,0.0006473073,0.0005450504],"domain_scores_gemma":[0.9982401,0.00009729605,0.0001622306,0.0003379933,0.0006374868,0.0005249235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002480493,0.00005891094,0.001640916,0.00001052679,0.00009077259,0.00006075107,0.00008045411,0.0006944499,0.980514,0.00007999948,0.002374334,0.01437007],"study_design_scores_gemma":[0.0003280524,0.0001890447,0.03190944,0.00008429203,0.0006538999,0.0003198465,0.001659535,0.9442412,0.0052969,0.00009140564,0.014784,0.0004423472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908478,0.0002920107,0.00004896954,0.003388429,0.00008786546,0.00007798778,0.005213985,0.000004599645,0.00003835001],"genre_scores_gemma":[0.9924967,0.0002081719,0.005444326,0.0002136709,0.0002383556,5.04516e-7,0.001298085,6.168258e-7,0.00009953432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9752171,"threshold_uncertainty_score":0.8357081,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415273830","doi":"10.6339/25-jds1200","title":"Q-learning with Compound Outcome and Mixed Misclassification and Measurement Error in Covariates","year":2025,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Covariate; Outcome (game theory); Observational error; Univariate; Estimation; Scope (computer science); Psychological intervention; Binary number","retraction":null,"screen_n_in":null,"score":{"opus":0.3429165163248257,"gpt":0.4523712167509067,"spread":0.109454700426081,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004205763,0.00004947178,0.0001509383,0.0001185261,0.00008341265,0.0000979049,0.0002749129,0.00001325621,0.00000337484],"category_scores_gemma":[0.005180477,0.00003201017,0.00000380748,0.0002608956,0.0003023527,0.000369446,0.0001157159,0.0001461494,1.437024e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003551324,"about_ca_system_score_gemma":0.0001394617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007566806,"about_ca_topic_score_gemma":0.00001802327,"domain_scores_codex":[0.9990674,0.0000739658,0.0002877006,0.0001360121,0.0003420768,0.0000928552],"domain_scores_gemma":[0.998902,0.0005163729,0.000184249,0.0001552047,0.0001921578,0.00004999914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001977143,0.0003068514,0.3800214,0.0004058738,0.00005135308,0.00003543764,0.0009346197,0.00001626452,0.03943006,0.4420591,0.0004736264,0.1360677],"study_design_scores_gemma":[0.001267631,0.0003320506,0.8919119,0.0007003055,0.00007798708,0.00008088678,0.001359696,0.02096362,0.0007370124,0.08175113,0.0006556527,0.0001621567],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5915924,0.0001332698,0.406407,0.00118496,0.00009435283,0.00009637255,0.000006584245,0.000004421834,0.0004806427],"genre_scores_gemma":[0.6784601,0.00001319981,0.3214937,0.00001999727,0.00000435552,3.044641e-7,1.731463e-7,0.000001169545,0.000006982011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5118905,"threshold_uncertainty_score":0.6201889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404422782","doi":"10.6339/24-jds1134","title":"Rethinking Attention Weights as Bidirectional Coefficients","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Ministry of Education, India; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Statistics; Mathematics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.08340618000620546,"gpt":0.3567068886842551,"spread":0.2733007086780496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004344075,0.0001001261,0.0001245841,0.0006228109,0.0003994261,0.001324823,0.004584617,0.00003591792,0.00003646395],"category_scores_gemma":[0.0005199928,0.0000787032,0.00005763208,0.002487366,0.0003721486,0.01127643,0.0009043847,0.0003098761,0.0002833696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001593997,"about_ca_system_score_gemma":0.0009407223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002296984,"about_ca_topic_score_gemma":0.000004929327,"domain_scores_codex":[0.9971682,0.00005583456,0.0004644907,0.0004930762,0.001498963,0.0003194142],"domain_scores_gemma":[0.998238,0.0001784307,0.0001930212,0.0007664149,0.000457187,0.0001669503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001984576,0.00025901,0.0006059245,0.00005146863,0.00004895112,0.0008319016,0.00331196,0.0005635715,0.1122908,0.6261635,0.006912866,0.2489402],"study_design_scores_gemma":[0.0001590607,0.0004804842,0.00184963,0.000878113,0.00003601585,0.003012277,0.0002879039,0.6947091,0.05573184,0.153194,0.08916653,0.0004949837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1279299,0.0007594249,0.8607247,0.002570993,0.005599337,0.00008168304,0.00000728474,0.00009932803,0.002227363],"genre_scores_gemma":[0.9493563,0.00009945274,0.04975957,0.0001745,0.0003268053,5.693646e-7,0.000002134343,0.000006503788,0.0002741364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8214264,"threshold_uncertainty_score":0.9997119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3136368678","doi":"10.6339/jds.201407_12(3).0007","title":"Copulas Applications in Estimating Value-at-Risk (VaR): Iranian Crude Oil Prices","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Economics; Econometrics; Crude oil; Normality; Risk management; Petroleum; Value at risk; Profit (economics); Multivariate statistics; Financial economics; Finance; Statistics; Microeconomics; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07526248261515965,"gpt":0.3051591706552883,"spread":0.2298966880401286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002844356,0.00008224422,0.0002717491,0.0002496789,0.0003015383,0.0001440799,0.0010794,0.00003873107,0.00003596988],"category_scores_gemma":[0.001383902,0.00008580221,0.00004507829,0.0009456638,0.0001528362,0.001775418,0.000394245,0.0002422709,0.00003348834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603773,"about_ca_system_score_gemma":0.0002351635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001780653,"about_ca_topic_score_gemma":0.0001141776,"domain_scores_codex":[0.9984019,0.00001331524,0.0008437813,0.0003725388,0.0001279304,0.0002405333],"domain_scores_gemma":[0.9983097,0.0001001735,0.0007922198,0.0005944596,0.0001076379,0.00009577288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003093468,0.0005216552,0.8327982,0.0001290374,0.00002763205,0.00004616056,0.002716323,0.0209036,0.001627355,0.07522748,0.0004209502,0.06555066],"study_design_scores_gemma":[0.0007928425,0.00006226862,0.1819003,0.0001660096,0.00001926362,0.00007092435,0.0003668892,0.7504246,0.0004463614,0.02965833,0.03570789,0.0003843362],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8797281,0.002683465,0.1151869,0.0003124041,0.0003292573,0.00004127573,0.0002321073,0.000006054381,0.001480432],"genre_scores_gemma":[0.8350365,0.0006104063,0.1640917,0.0000575311,0.0001324759,0.000001579771,0.00001099689,0.000006923327,0.0000518883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.729521,"threshold_uncertainty_score":0.3498912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}