{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":37,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":37,"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":"f35200098bd0","filters":{"venue":"Statistical Analysis and Data Mining The ASA Data Science Journal"}},"results":[{"id":"W2015887370","doi":"10.1002/sam.11161","title":"A survey on unsupervised outlier detection in high‐dimensional numerical data","year":2012,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":856,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Outlier; Curse of dimensionality; Anomaly detection; Computer science; Linear subspace; Data mining; Euclidean distance; Clustering high-dimensional data; Task (project management); Machine learning; Artificial intelligence; Mathematics; Cluster analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.09488812902028622,"gpt":0.3590586097123034,"spread":0.2641704806920172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.009776866,0.0001470646,0.0002570498,0.0003698411,0.0008884257,0.0007597383,0.007069882,0.00003997956,0.00005465556],"category_scores_gemma":[0.00140131,0.00009415863,0.00001802546,0.003037613,0.0003791521,0.003507513,0.00565687,0.0003839279,0.00001736597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004101557,"about_ca_system_score_gemma":0.0001462005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008647855,"about_ca_topic_score_gemma":0.0003501672,"domain_scores_codex":[0.9970714,0.0002722957,0.0004629721,0.0009288625,0.0007991829,0.000465221],"domain_scores_gemma":[0.994402,0.0007537588,0.0001862617,0.004243769,0.00009630551,0.0003178945],"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":[0.00007280549,0.000668614,0.1139576,0.000004915212,0.0002709453,0.00001982562,0.0003006844,0.0001498803,0.0003986779,0.01178277,0.01364371,0.8587296],"study_design_scores_gemma":[0.00008789653,0.00003687949,0.444251,0.000004506081,0.00007415842,0.00002949123,0.00003298025,0.5544716,0.00001861326,0.0002257187,0.0006587137,0.0001085301],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02928215,0.00005216212,0.9673868,0.0006725916,0.0001221815,0.00007216251,0.002366836,0.00002582719,0.00001927896],"genre_scores_gemma":[0.8600723,0.00004010812,0.138541,0.0002386459,0.00009072051,0.000002271277,0.001003732,0.000004562342,0.000006724349],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8586211,"threshold_uncertainty_score":0.9983023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1979148915","doi":"10.1002/sam.11184","title":"Content‐boosted matrix factorization techniques for recommender systems","year":2013,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":51,"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":"Recommender system; Matrix decomposition; Collaborative filtering; Matrix (chemical analysis); Factorization; Non-negative matrix factorization","retraction":null,"screen_n_in":null,"score":{"opus":0.1579030355591327,"gpt":0.3788280581645315,"spread":0.2209250226053988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00554052,0.0001773419,0.0003756066,0.0003649504,0.001031028,0.00434433,0.006209823,0.00005018353,0.00002651685],"category_scores_gemma":[0.0008387912,0.0001029191,0.00003766544,0.001232241,0.0002670332,0.005229057,0.002621143,0.000193035,0.000003682569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004271385,"about_ca_system_score_gemma":0.000135367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006593422,"about_ca_topic_score_gemma":0.0000254484,"domain_scores_codex":[0.9972831,0.0001691363,0.0006805411,0.0008206846,0.0006102045,0.0004363547],"domain_scores_gemma":[0.9957095,0.0006758469,0.0004238017,0.002532316,0.0004118285,0.0002466706],"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":[0.00001821664,0.0001808306,0.01703539,0.00007765495,0.001086819,0.00001116752,0.0008454218,0.000008044177,0.002500208,0.1236737,0.2903306,0.5642319],"study_design_scores_gemma":[0.0002138866,0.000167719,0.01263752,0.00005867271,0.0003690819,0.0001379406,0.001184619,0.9636567,0.0001069699,0.003645425,0.01745487,0.0003665495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005172432,0.0001447734,0.9955451,0.002011835,0.0002821412,0.0003643144,0.0009807135,0.00007528699,0.00007853215],"genre_scores_gemma":[0.396437,0.0001866066,0.6022633,0.000193117,0.0001685129,0.00003066207,0.0006522405,0.000009166985,0.00005942655],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9636487,"threshold_uncertainty_score":0.9991671,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2407525010","doi":"10.1002/sam.11313","title":"Fast robust SUR with economical and actuarial applications","year":2016,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Outlier; Estimator; Computer science; Robust statistics; Covariance; Multivariate statistics; Robust regression; Generalization; Algorithm; Econometrics; Mathematics; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.224123729836376,"gpt":0.4341166368761696,"spread":0.2099929070397936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003554847,0.0001523502,0.000354941,0.0001228679,0.0008180257,0.0004731485,0.001582211,0.00002967956,0.0001158929],"category_scores_gemma":[0.00337227,0.0000679024,0.00001586022,0.0004254986,0.001661121,0.001343486,0.001409068,0.0001770425,0.000002451048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002227294,"about_ca_system_score_gemma":0.0001616113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002148719,"about_ca_topic_score_gemma":0.00009614649,"domain_scores_codex":[0.9979745,0.000104158,0.0004118211,0.000758369,0.0003893517,0.0003618457],"domain_scores_gemma":[0.9938824,0.003893918,0.0002153081,0.001533232,0.0001126844,0.0003624334],"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":[0.0001409513,0.00009895126,0.004970924,0.00001792073,0.0005113948,0.00002177535,0.0001788039,0.00002625088,0.0002569693,0.3571384,0.002399771,0.6342379],"study_design_scores_gemma":[0.001952247,0.0003417949,0.02379058,0.0001165338,0.004867909,0.000480725,0.001205288,0.5275833,0.00002999874,0.4328173,0.005908397,0.0009059496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00815704,0.00002533263,0.9858789,0.0009112672,0.0000257152,0.00009294398,0.004827163,0.000009628948,0.00007194082],"genre_scores_gemma":[0.08941454,0.0001278191,0.9101181,0.00005761226,0.0001369892,0.000004446124,0.00010124,0.000009187174,0.00003004448],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6333319,"threshold_uncertainty_score":0.6291675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1512585278","doi":"10.1002/sam.11261","title":"Prediction using hierarchical data: Applications for automated detection of cervical cancer","year":2015,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Occupational Cancer Research Centre","funders":"National Cancer Institute; National Institutes of Health","keywords":"Computer science; Papanicolaou stain; Cervical cancer; Artificial intelligence; Data mining; Pattern recognition (psychology); Machine learning; Cancer; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1807557257664896,"gpt":0.4095357243360112,"spread":0.2287799985695216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0058923,0.0001182911,0.0002530214,0.0003065503,0.0008251147,0.000705208,0.005997716,0.00004448261,0.0000059606],"category_scores_gemma":[0.001097324,0.00008165226,0.00002132532,0.002447536,0.0006919215,0.004103255,0.003952262,0.0002483676,7.257976e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001008494,"about_ca_system_score_gemma":0.0007429511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005129898,"about_ca_topic_score_gemma":0.0003930393,"domain_scores_codex":[0.9972484,0.0001242986,0.0005323223,0.0009240072,0.0008629754,0.0003080495],"domain_scores_gemma":[0.9954346,0.0004412519,0.0003527779,0.003119641,0.0003654795,0.0002862709],"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":[0.0002230106,0.0003044577,0.01380869,0.00008094403,0.001243338,0.000007955106,0.001165929,0.008027632,0.007350794,0.005421577,0.01048195,0.9518837],"study_design_scores_gemma":[0.0001985856,0.00006657782,0.009380024,0.00001132947,0.0005668012,0.00006531797,0.0001516391,0.9868754,0.00006286104,0.00109127,0.001437973,0.00009224749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003945901,0.0001310221,0.9886456,0.0005501893,0.0002650826,0.0001571376,0.006248834,0.00005044616,0.000005819582],"genre_scores_gemma":[0.4717241,0.0000782061,0.5271198,0.00005417675,0.0003073968,0.00001039433,0.0006975638,0.000006329623,0.000002001112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9788477,"threshold_uncertainty_score":0.9993803,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2953239640","doi":"10.1002/sam.11429","title":"Interactive volumetric segmentation for textile micro‐tomography data using wavelets and nonlocal means","year":2019,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Light Source (Canada)","funders":"Office of Science; National Aeronautics and Space Administration; U.S. Department of Energy","keywords":"Segmentation; Artificial intelligence; Voxel; Pattern recognition (psychology); Computer science; Wavelet; Discriminative model","retraction":null,"screen_n_in":null,"score":{"opus":0.06895868629883593,"gpt":0.3872516588172325,"spread":0.3182929725183966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005901194,0.0001621374,0.0003064405,0.0006894172,0.0006931135,0.001972711,0.006486909,0.00003215317,0.00006467013],"category_scores_gemma":[0.001773864,0.0001090365,0.00002528695,0.002549871,0.0007122667,0.007059445,0.00631059,0.0002491715,0.000002930471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003654813,"about_ca_system_score_gemma":0.0002153755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001131002,"about_ca_topic_score_gemma":0.00003334611,"domain_scores_codex":[0.9969032,0.0001526823,0.0005108278,0.001196992,0.0008503985,0.0003858738],"domain_scores_gemma":[0.9951995,0.001160397,0.0003596878,0.002791111,0.0002058532,0.0002834522],"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":[0.00003690007,0.0001164275,0.01022817,0.00003157742,0.0004968679,0.00001733552,0.0006776615,0.00001380095,0.009388524,0.0004773606,0.009146909,0.9693685],"study_design_scores_gemma":[0.0002655131,0.00008523164,0.004993571,0.00002645837,0.0004203767,0.00009249272,0.0008235009,0.9923142,0.0003188684,0.0002610548,0.0002400181,0.0001586704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009753337,0.00009878901,0.9861996,0.000281491,0.000144109,0.0002062614,0.003283603,0.00001940078,0.00001341612],"genre_scores_gemma":[0.05466449,0.0001179968,0.9432513,0.0003445725,0.00005938672,0.000001758693,0.001546851,0.000006162089,0.000007538991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9923005,"threshold_uncertainty_score":0.9990633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4240834168","doi":"10.1002/sam.10016","title":"Discovering and Exploiting Statistical Properties for Query Optimization in Relational Databases: A Survey","year":2009,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":10,"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":"Computer science; Query optimization; Relational database; Data mining; Relational database management system; Cardinality (data modeling); Relational model; Sargable; View; Information retrieval; Key (lock); Exploratory data analysis; Database; Database design; Web search query; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.1529843466621269,"gpt":0.3608533658037779,"spread":0.207869019141651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006329778,0.000150293,0.0003031076,0.0002648642,0.0009041677,0.0008220832,0.00147667,0.00001828518,0.000007248269],"category_scores_gemma":[0.005800716,0.0000956272,0.00001209744,0.001077004,0.0004987154,0.007572072,0.001789776,0.0001875258,3.657593e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002832601,"about_ca_system_score_gemma":0.0002481088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000401347,"about_ca_topic_score_gemma":0.0007196285,"domain_scores_codex":[0.9974509,0.0001828339,0.000571625,0.0008597904,0.0005532171,0.0003815713],"domain_scores_gemma":[0.9969312,0.00123314,0.0002222029,0.001305204,0.0001279588,0.0001802891],"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":[0.0003167095,0.0002900929,0.1241214,0.00009263062,0.000340203,0.0001116689,0.002421726,0.02917971,0.000407717,0.6242599,0.002797446,0.2156608],"study_design_scores_gemma":[0.000190562,0.00004633636,0.07783312,0.00005415072,0.00006917073,0.00005542895,0.0006678676,0.9202632,0.000002839223,0.0004064924,0.0002591096,0.0001517522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008458452,0.0001979009,0.983438,0.0004386345,0.00005946014,0.0001130979,0.007276137,0.00001120704,0.00000710293],"genre_scores_gemma":[0.2108646,0.0001487996,0.7863024,0.00008775213,0.0000524308,0.00000276807,0.002533975,0.000003802006,0.000003484836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8910835,"threshold_uncertainty_score":0.7927367,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964276935","doi":"10.1002/sam.11410","title":"Pruning variable selection ensembles","year":2019,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Sorting; Selection (genetic algorithm); Ensemble learning; Lasso (programming language); Context (archaeology); Stability (learning theory); Pruning; Artificial intelligence; Feature selection; Machine learning; Process (computing); Boosting (machine learning); Variable (mathematics); Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04718228723840193,"gpt":0.3264302161271736,"spread":0.2792479288887716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004800423,0.0001044468,0.0001949467,0.0002650905,0.0009809582,0.001926045,0.004284411,0.00002682645,0.0002029051],"category_scores_gemma":[0.0007627705,0.00006286784,0.00001640288,0.002156484,0.0002040318,0.004781599,0.002977573,0.000240382,0.00003650157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001685783,"about_ca_system_score_gemma":0.0002351292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009872089,"about_ca_topic_score_gemma":0.00002520906,"domain_scores_codex":[0.9978335,0.0001107583,0.0002959508,0.0007242448,0.0006877414,0.0003477368],"domain_scores_gemma":[0.9974572,0.0004298421,0.000177338,0.001614915,0.0001397215,0.0001809738],"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":[0.00007677697,0.0002815764,0.09560838,0.00004860533,0.001045452,0.00005106231,0.001805094,0.001516874,0.02445184,0.1156135,0.0805766,0.6789242],"study_design_scores_gemma":[0.0001236157,0.00004654391,0.01278443,0.00002723725,0.0001931208,0.0001057625,0.0003629666,0.9802229,0.00006369477,0.00251341,0.003426161,0.000130175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02657344,0.00005099702,0.9719622,0.0005662876,0.0001797072,0.00004677657,0.0002602225,0.00002007398,0.0003403278],"genre_scores_gemma":[0.312186,0.00008819917,0.6870064,0.0002696796,0.00007859768,7.399319e-7,0.0002973986,0.000003636901,0.00006929717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.978706,"threshold_uncertainty_score":0.99911,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2509008132","doi":"10.1002/sam.11320","title":"Biased penalty calls in the National Hockey League","year":2016,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Université Laval","funders":"","keywords":"League; Situational ethics; Computer science; Penalty method; Data science; Psychology; Operations research; Applied psychology; Engineering; Mathematics; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1957237084336176,"gpt":0.3529167201555753,"spread":0.1571930117219577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01280906,0.0001129367,0.0002850461,0.0003952619,0.0006188874,0.0007132936,0.003323554,0.00002659949,0.0006177472],"category_scores_gemma":[0.002168101,0.00005364574,0.00003427541,0.001366632,0.0006640725,0.001477593,0.0007453213,0.0002000835,0.00004305627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004153927,"about_ca_system_score_gemma":0.0001315475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003794249,"about_ca_topic_score_gemma":0.0004891661,"domain_scores_codex":[0.9980087,0.00003478982,0.0006670356,0.00060384,0.0003369523,0.0003487315],"domain_scores_gemma":[0.9977409,0.0005903874,0.0003495614,0.001115863,0.00007885246,0.0001244299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003970622,0.0001691443,0.7857487,0.000007677208,0.0003494839,0.00004350071,0.000741919,0.0001534392,0.00002744022,0.14108,0.04723911,0.0244],"study_design_scores_gemma":[0.000322323,0.00003614432,0.7201192,0.00001850962,0.0001072064,0.00005222442,0.0003506418,0.2466481,0.000001129602,0.008794663,0.02335743,0.0001924262],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5063933,0.001165145,0.4180079,0.02972369,0.0005209909,0.0002591184,0.03996103,0.0000158254,0.003952926],"genre_scores_gemma":[0.9939524,0.0006578529,0.004192131,0.0007028564,0.0001640832,0.000001230027,0.0002625526,0.000004273846,0.00006264547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4875591,"threshold_uncertainty_score":0.6878306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3195567601","doi":"10.1002/sam.11543","title":"Parallel coordinate order for<scp>high‐dimensional</scp>data","year":2021,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Huawei Technologies (Canada); Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Parallel coordinates; Computer science; Visualization; Coordinate descent; Data mining; Dimension (graph theory); Data visualization; Data structure; Theoretical computer science; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1347123595111435,"gpt":0.3734952579050034,"spread":0.2387828983938599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008981525,0.0002530801,0.0006252759,0.00007098843,0.002202709,0.001508936,0.005208759,0.00007100662,0.0005189924],"category_scores_gemma":[0.02075888,0.0000923381,0.00006860676,0.003092227,0.001005522,0.001424574,0.004825609,0.0003527838,0.00001103318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001621962,"about_ca_system_score_gemma":0.0001617792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002388038,"about_ca_topic_score_gemma":0.0008884701,"domain_scores_codex":[0.9954311,0.0004718402,0.000723294,0.001635414,0.001023357,0.0007149424],"domain_scores_gemma":[0.9891897,0.007562738,0.0003271495,0.001782677,0.000618469,0.0005192871],"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":[0.00009905051,0.0005670072,0.01817366,0.0000256834,0.00264143,0.0003384849,0.0001594424,0.0003502852,0.0108433,0.03205505,0.1299014,0.8048452],"study_design_scores_gemma":[0.0004342113,0.0001950581,0.183729,0.00003164138,0.004056766,0.0002472892,0.00230917,0.7490188,0.00006350553,0.0123742,0.04719809,0.0003423215],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.184631,0.00114717,0.7387969,0.008207059,0.0004431681,0.0002333741,0.06628105,0.00003962998,0.0002206321],"genre_scores_gemma":[0.1934006,0.0005573209,0.7772787,0.001274923,0.0006078321,0.000003832513,0.0265487,0.000004265388,0.000323863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8045028,"threshold_uncertainty_score":0.9995276,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394687825","doi":"10.1002/sam.11679","title":"Data‐driven stochastic model for quantifying the interplay between amyloid‐beta and calcium levels in Alzheimer's disease","year":2024,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Prince Edward Island; Wilfrid Laurier University; University of Manitoba","funders":"Janssen Alzheimer Immunotherapy Research And Development; Johnson and Johnson Pharmaceutical Research and Development; National Institute on Aging; Agencia Estatal de Investigación; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Eisai Canada; H. Lundbeck A/S; Servier; Eisai; Shared Hierarchical Academic Research Computing Network; Ministerio de Ciencia, Innovación y Universidades; Northern California Institute for Research and Education; IXICO; Takeda Pharmaceutical Company; Alzheimer's Association; Fujirebio US; DoD Alzheimer's Disease Neuroimaging Initiative; Natural Sciences and Engineering Research Council of Canada; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Roche; AbbVie Canada; University of Southern California; Novartis Pharmaceuticals Corporation; Chesapeake Research Consortium; U.S. Department of Defense; Eli Lilly and Company; Alliance de recherche numérique du Canada; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation; Merck; GE Healthcare; Basque Center for Applied Mathematics; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics","keywords":"Disease; BETA (programming language); Amyloid (mycology); Amyloid beta; Alzheimer's disease; Neuroscience; Computer science; Biology; Medicine; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.3030961333940841,"gpt":0.4876074570137182,"spread":0.1845113236196341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004112665,0.000196531,0.0003972652,0.0003431812,0.0007929211,0.001125762,0.002310713,0.00002740605,0.00003293809],"category_scores_gemma":[0.001452874,0.00009873835,0.00004104547,0.0009446062,0.001193543,0.00163386,0.003266434,0.0003890875,0.000004153449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003239545,"about_ca_system_score_gemma":0.0008881197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001103428,"about_ca_topic_score_gemma":0.000171694,"domain_scores_codex":[0.9970093,0.0001108496,0.0004589347,0.001031068,0.0008426069,0.0005472386],"domain_scores_gemma":[0.9952319,0.001607254,0.00009353108,0.002232437,0.0000904199,0.000744412],"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":[0.002026551,0.001060632,0.3721925,0.0004448089,0.08522366,0.00205131,0.003227854,0.002216603,0.000117212,0.008621981,0.02955639,0.4932605],"study_design_scores_gemma":[0.0003423674,0.00005407702,0.09359394,0.0001301243,0.01085649,0.00003696411,0.0003805311,0.8939207,5.319931e-7,0.0005058232,0.0000683413,0.0001101098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06017478,0.01089993,0.820339,0.00472406,0.000077738,0.0004925054,0.1032652,0.00001826852,0.00000851301],"genre_scores_gemma":[0.977869,0.0002031112,0.01575573,0.00008761445,0.0001449634,0.000007001783,0.005915532,0.00001343052,0.000003604025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9176942,"threshold_uncertainty_score":0.9999112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176140770","doi":"10.1002/sam.11643","title":"Stratified learning: A general‐purpose statistical method for improved learning under covariate shift","year":2023,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"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":"Science and Technology Facilities Council; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Computer science; Inference; Weighting; Causal inference; Machine learning; Artificial intelligence; Set (abstract data type); Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2786726334383422,"gpt":0.4905551637432045,"spread":0.2118825303048623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02213152,0.0003318416,0.0008050175,0.0004152286,0.00220436,0.001713228,0.002965855,0.00009035291,0.0003677084],"category_scores_gemma":[0.04486051,0.0002121134,0.00006888103,0.002307548,0.001036939,0.0008288365,0.002348899,0.0009167304,0.00001237819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004038325,"about_ca_system_score_gemma":0.0004720445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001640625,"about_ca_topic_score_gemma":0.00010289,"domain_scores_codex":[0.9947536,0.0009434107,0.001051799,0.001342412,0.0009208344,0.0009879726],"domain_scores_gemma":[0.9794387,0.0175153,0.0004992298,0.001686662,0.0002903579,0.0005697394],"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":[0.000191291,0.0001244292,0.001167465,0.00006960313,0.0009798575,0.00004715715,0.000690819,0.0003857536,0.001396394,0.765137,0.009624267,0.220186],"study_design_scores_gemma":[0.0003690655,0.0002000164,0.009489488,0.00001861124,0.001463939,0.00003209943,0.001029504,0.7648632,0.00001019478,0.2208623,0.001390731,0.0002708333],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003111491,0.00002470829,0.9888822,0.001180293,0.0001594498,0.0002297563,0.006257812,0.00006822777,0.000086],"genre_scores_gemma":[0.02899464,0.0001074162,0.9683282,0.0001606044,0.000214638,0.00001235537,0.001990616,0.0000294815,0.0001620057],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7644774,"threshold_uncertainty_score":0.9993231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2053843934","doi":"10.1002/sam.11149","title":"Nearest‐neighbors medians clustering","year":2012,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Mathematics; Median; Uniqueness; Partition (number theory); Univariate; Cluster analysis; Nonparametric statistics; Fixed point; Sample (material); Algorithm; Combinatorics; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.09250896968680458,"gpt":0.3798075243016192,"spread":0.2872985546148146,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01184459,0.0001617286,0.000296383,0.0002863445,0.001206839,0.001731673,0.008362317,0.00003515855,0.00006132048],"category_scores_gemma":[0.001594255,0.00009386941,0.00003217832,0.001976387,0.0007154941,0.005710634,0.006604244,0.0003470323,0.000008551951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002223222,"about_ca_system_score_gemma":0.0002013872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007782133,"about_ca_topic_score_gemma":0.00007183079,"domain_scores_codex":[0.9970434,0.0002338799,0.0004156269,0.0007159078,0.000873646,0.0007175424],"domain_scores_gemma":[0.9951534,0.0006943943,0.0001965129,0.003222027,0.0000889213,0.0006447067],"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":[0.000009830228,0.00008470987,0.01440297,0.000008755048,0.000312848,0.00004579725,0.002128275,0.00002253049,0.000154051,0.06781822,0.01004868,0.9049633],"study_design_scores_gemma":[0.0001193207,0.00003080672,0.03669122,0.00001434092,0.0004469667,0.0002843082,0.0002441824,0.9550499,0.000008263499,0.003293554,0.003590835,0.0002262802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001212685,0.0003342546,0.9957324,0.001566219,0.0003604833,0.00003998605,0.0004718592,0.00001860758,0.00026349],"genre_scores_gemma":[0.1924204,0.0001635013,0.806664,0.0003749835,0.0002620952,6.616156e-7,0.00009556146,0.000004721275,0.00001404551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9550274,"threshold_uncertainty_score":0.9993047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3169835580","doi":"10.1002/sam.11530","title":"Penalized composite likelihood for colored graphical Gaussian models","year":2021,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphical model; Computer science; Gaussian; Algorithm; Matrix (chemical analysis); Estimator; Selection (genetic algorithm); Model selection; Colored; Pattern recognition (psychology); Data mining; Mathematical optimization; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06367776533288279,"gpt":0.3649556518565307,"spread":0.301277886523648,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001964942,0.0001092077,0.0001973777,0.00009950859,0.0007434927,0.0005158958,0.001643045,0.0000459428,0.00004115042],"category_scores_gemma":[0.000624014,0.00007060238,0.00004628078,0.0007148282,0.0004759799,0.00007418676,0.001303279,0.0001194119,6.560103e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007522248,"about_ca_system_score_gemma":0.0003793631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001161534,"about_ca_topic_score_gemma":0.00007602433,"domain_scores_codex":[0.9981711,0.000109958,0.0003113746,0.0007367361,0.0003815829,0.0002892788],"domain_scores_gemma":[0.9977821,0.00008789184,0.0001461074,0.001515532,0.0002216809,0.0002467615],"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":[0.0008597083,0.0004881133,0.01132203,0.00004132041,0.002015536,0.00004563378,0.0003733308,0.0003257089,0.7349174,0.01363903,0.1268516,0.1091206],"study_design_scores_gemma":[0.002321249,0.00034602,0.05394613,0.00005357324,0.003186392,0.0003661148,0.002900268,0.8605168,0.00813494,0.01031574,0.05717285,0.0007399248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05422908,0.000621793,0.9394533,0.002199545,0.0001103737,0.00007962598,0.003190862,0.000004123151,0.0001112705],"genre_scores_gemma":[0.8755152,0.0008003095,0.1160073,0.0004825113,0.0001754562,0.000005511453,0.006958985,0.000007702447,0.00004702156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8601911,"threshold_uncertainty_score":0.571842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790407909","doi":"10.1002/sam.11373","title":"Building cancer prognosis systems with survival function clusters","year":2018,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneous; Cluster analysis; Computer science; Cancer; Lung cancer; Cluster (spacecraft); Population; Medicine; Covariate; Demographics; Survival analysis; Data mining; Oncology; Internal medicine; Artificial intelligence; Mathematics; Machine learning; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.08062547735272997,"gpt":0.3739859447699232,"spread":0.2933604674171932,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008269235,0.0001642203,0.0003091211,0.0002658682,0.001456301,0.00268805,0.005208912,0.00003038902,0.00002123647],"category_scores_gemma":[0.0004043923,0.00008654899,0.00002061155,0.002398032,0.001038313,0.003308035,0.002692216,0.0002435328,0.000001948893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000314817,"about_ca_system_score_gemma":0.0003193684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003732977,"about_ca_topic_score_gemma":0.0002410658,"domain_scores_codex":[0.9969363,0.0002537567,0.0003668352,0.00100099,0.0009641102,0.0004779789],"domain_scores_gemma":[0.9966519,0.0003803561,0.0002694268,0.002115502,0.0002784301,0.0003043922],"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":[0.0001092349,0.00008961862,0.02095285,0.00002590356,0.001209779,0.00004732599,0.0007872939,0.000136281,0.0003431351,0.1153117,0.009287972,0.8516989],"study_design_scores_gemma":[0.0001599877,0.0001490614,0.01471946,0.00004622477,0.0007983599,0.00009477927,0.0001967547,0.9808452,0.000008775661,0.001224424,0.001565898,0.0001911274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003622751,0.0001898434,0.9941517,0.000922389,0.0004934278,0.00007640523,0.0004406933,0.000019996,0.00008275997],"genre_scores_gemma":[0.2672927,0.00007852427,0.7320957,0.0001500746,0.0003221767,0.000002686794,0.00004061478,0.000005178605,0.00001232275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9807088,"threshold_uncertainty_score":0.9998437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153591306","doi":"10.1002/sam.11270","title":"Principal axes analysis of symbolic histogram variables","year":2015,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Histogram; Mathematics; Principal component analysis; Estimator; Symbolic data analysis; Quantile; Pattern recognition (psychology); Histogram matching; Statistics; Artificial intelligence; Computer science; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.2031330746131957,"gpt":0.3914348319331702,"spread":0.1883017573199745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01183074,0.0002046271,0.0008278964,0.0002757029,0.0008003993,0.0006617218,0.003886363,0.00005639242,0.0005139638],"category_scores_gemma":[0.006836663,0.00007042385,0.0001195217,0.007838533,0.001461935,0.0008820088,0.001925633,0.0002601352,0.000003112191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002870557,"about_ca_system_score_gemma":0.0001090719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001149747,"about_ca_topic_score_gemma":0.001458303,"domain_scores_codex":[0.9959964,0.0004957884,0.0008344617,0.0009186047,0.001254157,0.0005006137],"domain_scores_gemma":[0.9950889,0.002407816,0.0004617795,0.001037638,0.0003835495,0.0006203557],"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":[0.0002247571,0.0006184598,0.303527,0.00001385136,0.01144457,0.00008217672,0.0009825069,0.0008183892,0.006256006,0.03184032,0.006646593,0.6375453],"study_design_scores_gemma":[0.0001309736,0.0001793452,0.5353687,0.000009769049,0.0162437,0.00002884632,0.002631406,0.43775,0.00001715636,0.002012118,0.005344074,0.000283829],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7857816,0.0005630493,0.1962339,0.001301149,0.0001937435,0.0001251774,0.01519645,0.00002836811,0.0005765065],"genre_scores_gemma":[0.8851881,0.0001430182,0.1122102,0.000133824,0.0001469876,0.000001089782,0.002141465,0.000001248634,0.00003404319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6372615,"threshold_uncertainty_score":0.8184618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2998595054","doi":"10.1002/sam.11445","title":"A new method for performance analysis in nonlinear dimensionality reduction","year":2020,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Skewness; Benchmark (surveying); Computer science; Curse of dimensionality; Intrinsic dimension; Measure (data warehouse); Dimension (graph theory); Rank (graph theory); Pattern recognition (psychology); Data mining; Artificial intelligence; Algorithm; Mathematics; Statistics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1089186232522482,"gpt":0.3994450036008474,"spread":0.2905263803485991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005194842,0.0001148949,0.0003198177,0.00035286,0.0006500185,0.0007680664,0.003332847,0.00002759964,0.00005291782],"category_scores_gemma":[0.001223661,0.00007216479,0.00004842279,0.004759633,0.0001603156,0.002994985,0.001979911,0.0002167102,0.000003711378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001690136,"about_ca_system_score_gemma":0.0002756977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001518734,"about_ca_topic_score_gemma":0.00005586079,"domain_scores_codex":[0.9975908,0.0001351091,0.0004541929,0.0008856757,0.0006331574,0.0003010396],"domain_scores_gemma":[0.9976345,0.0004333996,0.0002079163,0.001261069,0.0001291883,0.0003339719],"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":[0.0001685399,0.0001188828,0.01576226,0.00002584118,0.001186853,0.00001817492,0.001598516,0.003537527,0.001860172,0.002643875,0.02243944,0.9506399],"study_design_scores_gemma":[0.0001825329,0.0000503597,0.02187084,0.000009070171,0.0008228146,0.00001704176,0.0002769988,0.975345,0.00005943992,0.0004557256,0.0008029923,0.0001071972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01414781,0.00004599744,0.9794678,0.005462824,0.00006611114,0.00006454471,0.0007226888,0.00001067006,0.00001154679],"genre_scores_gemma":[0.08515183,0.00009541013,0.9136503,0.0003167532,0.000113444,0.000001216784,0.0006616816,0.000002438891,0.000006879631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9718075,"threshold_uncertainty_score":0.7406483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2793406240","doi":"10.1002/sam.11371","title":"Informative priors in Bayesian inference and computation","year":2018,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":3,"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; National Science Foundation","keywords":"Prior probability; Inference; Computer science; Bayesian inference; Prior information; Bayesian probability; Machine learning; Artificial intelligence; Computation; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.05260797491513945,"gpt":0.3710747324231752,"spread":0.3184667575080358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003731672,0.0001379974,0.0002420517,0.0004245253,0.0008492647,0.00229678,0.004185725,0.00002817705,0.00002226403],"category_scores_gemma":[0.001331405,0.00008528012,0.00001023814,0.00266481,0.001415993,0.006119389,0.003930528,0.0002542386,0.0000049148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001983854,"about_ca_system_score_gemma":0.0003658171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001147933,"about_ca_topic_score_gemma":0.0003247864,"domain_scores_codex":[0.9978222,0.00008662239,0.0004724899,0.0006526428,0.0005861868,0.0003799151],"domain_scores_gemma":[0.9976391,0.0004764739,0.0002565113,0.00120222,0.0001862024,0.0002394506],"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":[0.00002604153,0.00007893035,0.09578594,0.00002764852,0.0001580438,0.00004867022,0.007995263,0.00004176671,0.00004298741,0.08829005,0.00146281,0.8060418],"study_design_scores_gemma":[0.000120436,0.00007440014,0.2100294,0.00002702807,0.000063143,0.00006488358,0.0006361881,0.7813615,0.000004389785,0.007394114,0.0001032393,0.0001212194],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01818597,0.00004302358,0.9802215,0.001028949,0.00006391743,0.00004906713,0.0002028739,0.00001092827,0.0001938049],"genre_scores_gemma":[0.7202212,0.00008431196,0.2794354,0.0001644213,0.00003379684,4.971325e-7,0.00005672787,0.000001668038,0.00000206666],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8059206,"threshold_uncertainty_score":0.9987389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3208584122","doi":"10.1002/sam.11555","title":"A family of mixture models for biclustering","year":2021,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Biclustering; Cluster analysis; Diagonal; Covariance matrix; Latent variable; Covariance; Block matrix; Mathematics; Algorithm; Computer science; Matrix (chemical analysis); Pattern recognition (psychology); Data mining; Artificial intelligence; Statistics; Correlation clustering; CURE data clustering algorithm; Eigenvalues and eigenvectors","retraction":null,"screen_n_in":null,"score":{"opus":0.1142151275950539,"gpt":0.3767657191606953,"spread":0.2625505915656414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.006653762,0.0001269927,0.0003590082,0.0001929486,0.000618835,0.0009568013,0.00547405,0.00003314498,0.000008519472],"category_scores_gemma":[0.001249851,0.00007816812,0.00004956126,0.001780611,0.0004230502,0.002624126,0.004622164,0.0001873238,2.935781e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001121289,"about_ca_system_score_gemma":0.0004365212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002982348,"about_ca_topic_score_gemma":0.00002976777,"domain_scores_codex":[0.9975916,0.000150902,0.0004580822,0.0008276047,0.0006102296,0.0003616547],"domain_scores_gemma":[0.9956999,0.0007625223,0.0002264261,0.002782238,0.0003103498,0.0002185246],"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":[0.0000282757,0.0001056487,0.0003746914,0.00004197839,0.0005754113,0.00006649732,0.001013906,0.0003743828,0.004583463,0.2328127,0.007316781,0.7527063],"study_design_scores_gemma":[0.0001447443,0.00003061146,0.001192101,0.00002111172,0.0003680204,0.0001036319,0.0001570494,0.9597816,0.00007799447,0.03746482,0.0005448508,0.0001134426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001196728,0.0005243613,0.9953398,0.0009812521,0.0001290902,0.00004896777,0.001669555,0.000007435819,0.0001028868],"genre_scores_gemma":[0.06981896,0.0002086,0.9294482,0.0002757948,0.00006674488,0.000001020293,0.0001599512,0.000004032351,0.00001673279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9594073,"threshold_uncertainty_score":0.9999068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1525895928","doi":"10.1002/sam.11394","title":"Standardizing interestingness measures for association rules","year":2018,"lang":"en","type":"preprint","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; McMaster University; Thompson Rivers University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Lift (data mining); Computer science; Raw data; Association rule learning; Standardization; Association (psychology); Data mining; Value (mathematics); Machine learning; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1201164593375698,"gpt":0.3973333708886629,"spread":0.2772169115510931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01929779,0.0002778236,0.0005499746,0.0004039469,0.002224333,0.007570941,0.01576496,0.0001001082,0.00001555217],"category_scores_gemma":[0.009649204,0.0001855086,0.00006985463,0.001186096,0.0006971346,0.002425782,0.02033588,0.0006054899,0.000005263958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001459693,"about_ca_system_score_gemma":0.0009227794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001555048,"about_ca_topic_score_gemma":0.000139495,"domain_scores_codex":[0.9952362,0.0001707919,0.0007774106,0.001741008,0.001446969,0.0006276463],"domain_scores_gemma":[0.9910349,0.001724081,0.001016208,0.005064225,0.0008421538,0.0003184458],"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":[0.00002300812,0.0001173225,0.005174021,0.0000570743,0.001731102,0.00001213862,0.001179485,0.00008570164,0.00004982238,0.01584528,0.1077135,0.8680116],"study_design_scores_gemma":[0.0001512507,0.00004866697,0.008948904,0.0001008133,0.001344807,0.00002847561,0.0002878381,0.9661919,0.000008738364,0.01100594,0.01155731,0.0003253758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001910304,0.0001917156,0.9654648,0.002411145,0.0005009854,0.0001593842,0.0292683,0.00003958169,0.00005383015],"genre_scores_gemma":[0.02022904,0.0002494069,0.9743071,0.0001731096,0.0006208663,0.00001383405,0.004369766,0.00001229693,0.00002462595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9661062,"threshold_uncertainty_score":0.9990746,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4244236454","doi":"10.1002/sam.11386","title":"Issue Information","year":2019,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Transportation Systems and Logistics","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web; Library science","retraction":null,"screen_n_in":null,"score":{"opus":0.04854510382062079,"gpt":0.3262234257958047,"spread":0.2776783219751839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002762828,0.0002172758,0.0004685319,0.0004236654,0.0004450563,0.001564224,0.003378693,0.00009011688,0.001485418],"category_scores_gemma":[0.0003619498,0.000136451,0.00003111105,0.001117657,0.0004104448,0.002660539,0.0005372377,0.0005142207,0.001185022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003145794,"about_ca_system_score_gemma":0.0002357862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001285389,"about_ca_topic_score_gemma":0.00007463417,"domain_scores_codex":[0.9976445,0.00004136755,0.0007516591,0.0003841106,0.0008286202,0.0003496908],"domain_scores_gemma":[0.9970503,0.0002888144,0.0002609981,0.002044495,0.0001537838,0.0002016012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005483467,0.000006620901,0.0003411956,0.0001005828,0.0005355849,0.000004876382,0.0003478975,0.006673734,0.00000539641,0.0003442851,0.9620035,0.02963085],"study_design_scores_gemma":[0.00009982035,0.00001639193,0.004506537,0.00004697273,0.0008820985,0.00002655064,0.0007425482,0.3660646,6.984091e-7,0.00001638408,0.6273673,0.0002300797],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001939625,0.0006601235,0.9379987,0.0001377278,0.002784402,0.0001020052,0.05309363,0.00001918584,0.005010272],"genre_scores_gemma":[0.3835256,0.01818909,0.266245,0.001080714,0.004788039,0.00001300783,0.315743,0.0001360515,0.01027947],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6717536,"threshold_uncertainty_score":0.9995927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4231764799","doi":"10.1002/sam.11387","title":"Issue Information","year":2019,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.07162451266438453,"gpt":0.3683286561938265,"spread":0.296704143529442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004119816,0.0001968899,0.0003530644,0.000520993,0.0005979338,0.001837216,0.003099645,0.00008266781,0.04040167],"category_scores_gemma":[0.0005704757,0.0001294031,0.00002889063,0.0009026439,0.0004042732,0.003911602,0.001092211,0.0005290415,0.02121925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006559319,"about_ca_system_score_gemma":0.0002254406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009407612,"about_ca_topic_score_gemma":0.00002966986,"domain_scores_codex":[0.997686,0.00007561005,0.0005684084,0.0003797703,0.0009719082,0.0003182471],"domain_scores_gemma":[0.9972966,0.0001914361,0.0002088785,0.001972525,0.0001426694,0.0001878668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002747596,0.00000370663,0.0000302931,0.00002394694,0.000167485,5.385216e-7,0.0002447423,0.002654356,0.00001178591,0.00000830256,0.9549817,0.04187043],"study_design_scores_gemma":[0.00006819697,0.00001193943,0.002454549,0.00002198957,0.0004994433,0.000011963,0.0004538442,0.5135813,4.199234e-7,0.00001160851,0.4827425,0.000142217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0009747503,0.0004071927,0.9526601,0.0004204595,0.006845149,0.0001803465,0.0254738,0.00003762413,0.01300057],"genre_scores_gemma":[0.08468768,0.03207391,0.2914493,0.003603202,0.01937249,0.00002470186,0.516661,0.0002211992,0.0519065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6612108,"threshold_uncertainty_score":0.999199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4231631488","doi":"10.1002/sam.10048","title":"Application of model selection technique in chemogenomic data analysis","year":2009,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; York University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Dependency (UML); Model selection; Bayesian network; Selection (genetic algorithm); Data set; Construct (python library); Set (abstract data type); Bayesian information criterion; Bayesian probability; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04998375380142114,"gpt":0.3711030331056732,"spread":0.321119279304252,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003160074,0.00008825453,0.0001941107,0.0003413763,0.0002034785,0.0001159588,0.002686789,0.00004381318,0.000009733284],"category_scores_gemma":[0.000389165,0.00006205279,0.00002219586,0.002041051,0.0002293609,0.00009190332,0.0009764574,0.0001166998,3.050274e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001487426,"about_ca_system_score_gemma":0.0002022108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005699668,"about_ca_topic_score_gemma":0.0001828307,"domain_scores_codex":[0.9983661,0.00006184894,0.0003715202,0.0007285735,0.0003013888,0.0001706112],"domain_scores_gemma":[0.9971499,0.0000250876,0.0002455386,0.002402206,0.00008936419,0.0000878814],"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":[0.0001051006,0.0001667824,0.03295345,0.000006167884,0.0004759506,9.067872e-7,0.0000731061,0.005304689,0.8409288,0.0006281099,0.003024012,0.1163329],"study_design_scores_gemma":[0.00009782268,0.00003435621,0.07728657,0.00000340856,0.0007935162,0.000008586549,0.0001184972,0.9186658,0.002197942,0.0002941002,0.0004101389,0.0000893083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04005169,0.000114921,0.9582765,0.0002857827,0.000008282562,0.00006949441,0.001157023,0.000002232892,0.00003414971],"genre_scores_gemma":[0.8999087,0.0002955307,0.09507871,0.00006750048,0.00003794195,0.000002011336,0.004599843,0.000002507324,0.000007241304],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9133611,"threshold_uncertainty_score":0.4992768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4239375881","doi":"10.1002/sam.11423","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.08550868619541674,"gpt":0.3686068909417464,"spread":0.2830982047463297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002903897,0.0001948199,0.0003466452,0.0003779659,0.00069559,0.001870182,0.003068505,0.00007039502,0.03379505],"category_scores_gemma":[0.0008327688,0.0001305705,0.00002845804,0.001091779,0.0004457706,0.003432041,0.001176577,0.0005686318,0.01176779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365627,"about_ca_system_score_gemma":0.0002064556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000713483,"about_ca_topic_score_gemma":0.00002633635,"domain_scores_codex":[0.9977275,0.00007698203,0.0005762596,0.000385075,0.0009466413,0.0002875694],"domain_scores_gemma":[0.9978197,0.0001555477,0.0001927827,0.00143486,0.0001203038,0.000276845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003064058,0.00000296138,0.00001370904,0.00002076768,0.0001680288,0.000001235604,0.0003552857,0.001089754,0.00001327562,0.000007894195,0.951629,0.04669497],"study_design_scores_gemma":[0.00005593878,0.00001197093,0.001340749,0.00001512985,0.0005728778,0.00001075287,0.000476873,0.5013105,5.014188e-7,0.0000138965,0.4960632,0.0001275373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0003483468,0.0003356236,0.961793,0.001102543,0.003347484,0.0001288262,0.02464771,0.00004459183,0.008251859],"genre_scores_gemma":[0.05777293,0.03127204,0.3930459,0.005940717,0.02361654,0.00002447565,0.4761647,0.0001928834,0.01196974],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5687471,"threshold_uncertainty_score":0.999166,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210695710","doi":"10.1002/sam.11427","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.08550868619541674,"gpt":0.3686068909417464,"spread":0.2830982047463297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002903897,0.0001948199,0.0003466452,0.0003779659,0.00069559,0.001870182,0.003068505,0.00007039502,0.03379505],"category_scores_gemma":[0.0008327688,0.0001305705,0.00002845804,0.001091779,0.0004457706,0.003432041,0.001176577,0.0005686318,0.01176779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365627,"about_ca_system_score_gemma":0.0002064556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000713483,"about_ca_topic_score_gemma":0.00002633635,"domain_scores_codex":[0.9977275,0.00007698203,0.0005762596,0.000385075,0.0009466413,0.0002875694],"domain_scores_gemma":[0.9978197,0.0001555477,0.0001927827,0.00143486,0.0001203038,0.000276845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003064058,0.00000296138,0.00001370904,0.00002076768,0.0001680288,0.000001235604,0.0003552857,0.001089754,0.00001327562,0.000007894195,0.951629,0.04669497],"study_design_scores_gemma":[0.00005593878,0.00001197093,0.001340749,0.00001512985,0.0005728778,0.00001075287,0.000476873,0.5013105,5.014188e-7,0.0000138965,0.4960632,0.0001275373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0003483468,0.0003356236,0.961793,0.001102543,0.003347484,0.0001288262,0.02464771,0.00004459183,0.008251859],"genre_scores_gemma":[0.05777293,0.03127204,0.3930459,0.005940717,0.02361654,0.00002447565,0.4761647,0.0001928834,0.01196974],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5687471,"threshold_uncertainty_score":0.999166,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206662956","doi":"10.1002/sam.11466","title":"Issue Information","year":2021,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.07724045282164911,"gpt":0.3726486626682964,"spread":0.2954082098466473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003824405,0.0001900015,0.0003505646,0.0004356199,0.0007597795,0.002299066,0.002610616,0.00007897646,0.05425288],"category_scores_gemma":[0.0008384298,0.0001297037,0.0000309643,0.001146606,0.0004356836,0.003398759,0.001221357,0.0005339399,0.005597943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006378987,"about_ca_system_score_gemma":0.0002838371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009215492,"about_ca_topic_score_gemma":0.00005776683,"domain_scores_codex":[0.9976568,0.00009502706,0.0005800453,0.0003913939,0.0009691076,0.0003076094],"domain_scores_gemma":[0.9973861,0.0001779652,0.0001825041,0.001846162,0.0001914575,0.0002157986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001733122,0.000004640057,0.00001759694,0.00002070248,0.0001954233,0.000001974795,0.0002697796,0.001306839,0.0000162731,0.000007785901,0.9447384,0.0534188],"study_design_scores_gemma":[0.00006561381,0.000008788436,0.00222839,0.00003016775,0.0007125619,0.0000259337,0.0008728289,0.4657682,9.87719e-7,0.00001286957,0.5301157,0.0001579321],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0009498989,0.0008471753,0.9591712,0.0005487679,0.005025131,0.0001160989,0.02330065,0.00003590683,0.01000512],"genre_scores_gemma":[0.03013856,0.03949951,0.3476554,0.002714434,0.01614763,0.00002049979,0.5394098,0.0001438764,0.02427031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6115159,"threshold_uncertainty_score":0.9987366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4236215018","doi":"10.1002/sam.11360","title":"Issue Information","year":2018,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.07753281751408107,"gpt":0.3766135914705343,"spread":0.2990807739564532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004635337,0.0001965586,0.0003203154,0.0005173777,0.000883456,0.001950717,0.003208255,0.00008216043,0.05649981],"category_scores_gemma":[0.0007409742,0.0001286768,0.00002637339,0.0009864349,0.0007607398,0.003784603,0.001149342,0.0004404324,0.01557525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006262758,"about_ca_system_score_gemma":0.000201332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009360851,"about_ca_topic_score_gemma":0.00005326123,"domain_scores_codex":[0.9976816,0.00007872543,0.0005798048,0.0003812776,0.0009517169,0.0003269061],"domain_scores_gemma":[0.9973494,0.0001523806,0.0002072328,0.001874884,0.0001941811,0.0002219381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002788105,0.000003638989,0.00001633992,0.00001483992,0.0001567548,6.01102e-7,0.0002887113,0.0003739985,0.000009104084,0.000005413903,0.9611536,0.03797421],"study_design_scores_gemma":[0.00006017499,0.00001616971,0.002011712,0.00002179505,0.0005986734,0.00001535431,0.0004228699,0.4475783,7.026019e-7,0.00002151576,0.5491084,0.000144214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001201034,0.0003013072,0.9564448,0.0003891815,0.005450423,0.0001382562,0.02361378,0.00004305546,0.01241817],"genre_scores_gemma":[0.04737784,0.02559553,0.4506448,0.003207855,0.03482186,0.00002586494,0.4084181,0.0001980355,0.02971014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5058,"threshold_uncertainty_score":0.9990854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4255653278","doi":"10.1002/sam.11385","title":"Issue Information","year":2019,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07162451266438453,"gpt":0.3683286561938265,"spread":0.296704143529442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004119816,0.0001968899,0.0003530644,0.000520993,0.0005979338,0.001837216,0.003099645,0.00008266781,0.04040167],"category_scores_gemma":[0.0005704757,0.0001294031,0.00002889063,0.0009026439,0.0004042732,0.003911602,0.001092211,0.0005290415,0.02121925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006559319,"about_ca_system_score_gemma":0.0002254406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009407612,"about_ca_topic_score_gemma":0.00002966986,"domain_scores_codex":[0.997686,0.00007561005,0.0005684084,0.0003797703,0.0009719082,0.0003182471],"domain_scores_gemma":[0.9972966,0.0001914361,0.0002088785,0.001972525,0.0001426694,0.0001878668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002747596,0.00000370663,0.0000302931,0.00002394694,0.000167485,5.385216e-7,0.0002447423,0.002654356,0.00001178591,0.00000830256,0.9549817,0.04187043],"study_design_scores_gemma":[0.00006819697,0.00001193943,0.002454549,0.00002198957,0.0004994433,0.000011963,0.0004538442,0.5135813,4.199234e-7,0.00001160851,0.4827425,0.000142217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0009747503,0.0004071927,0.9526601,0.0004204595,0.006845149,0.0001803465,0.0254738,0.00003762413,0.01300057],"genre_scores_gemma":[0.08468768,0.03207391,0.2914493,0.003603202,0.01937249,0.00002470186,0.516661,0.0002211992,0.0519065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6612108,"threshold_uncertainty_score":0.999199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4214902008","doi":"10.1002/sam.11469","title":"Issue Information","year":2021,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Citation; Information retrieval; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07724045282164911,"gpt":0.3726486626682964,"spread":0.2954082098466473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003824405,0.0001900015,0.0003505646,0.0004356199,0.0007597795,0.002299066,0.002610616,0.00007897646,0.05425288],"category_scores_gemma":[0.0008384298,0.0001297037,0.0000309643,0.001146606,0.0004356836,0.003398759,0.001221357,0.0005339399,0.005597943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006378987,"about_ca_system_score_gemma":0.0002838371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009215492,"about_ca_topic_score_gemma":0.00005776683,"domain_scores_codex":[0.9976568,0.00009502706,0.0005800453,0.0003913939,0.0009691076,0.0003076094],"domain_scores_gemma":[0.9973861,0.0001779652,0.0001825041,0.001846162,0.0001914575,0.0002157986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001733122,0.000004640057,0.00001759694,0.00002070248,0.0001954233,0.000001974795,0.0002697796,0.001306839,0.0000162731,0.000007785901,0.9447384,0.0534188],"study_design_scores_gemma":[0.00006561381,0.000008788436,0.00222839,0.00003016775,0.0007125619,0.0000259337,0.0008728289,0.4657682,9.87719e-7,0.00001286957,0.5301157,0.0001579321],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0009498989,0.0008471753,0.9591712,0.0005487679,0.005025131,0.0001160989,0.02330065,0.00003590683,0.01000512],"genre_scores_gemma":[0.03013856,0.03949951,0.3476554,0.002714434,0.01614763,0.00002049979,0.5394098,0.0001438764,0.02427031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6115159,"threshold_uncertainty_score":0.9987366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213289775","doi":"10.1002/sam.11425","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.08550868619541674,"gpt":0.3686068909417464,"spread":0.2830982047463297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002903897,0.0001948199,0.0003466452,0.0003779659,0.00069559,0.001870182,0.003068505,0.00007039502,0.03379505],"category_scores_gemma":[0.0008327688,0.0001305705,0.00002845804,0.001091779,0.0004457706,0.003432041,0.001176577,0.0005686318,0.01176779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365627,"about_ca_system_score_gemma":0.0002064556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000713483,"about_ca_topic_score_gemma":0.00002633635,"domain_scores_codex":[0.9977275,0.00007698203,0.0005762596,0.000385075,0.0009466413,0.0002875694],"domain_scores_gemma":[0.9978197,0.0001555477,0.0001927827,0.00143486,0.0001203038,0.000276845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003064058,0.00000296138,0.00001370904,0.00002076768,0.0001680288,0.000001235604,0.0003552857,0.001089754,0.00001327562,0.000007894195,0.951629,0.04669497],"study_design_scores_gemma":[0.00005593878,0.00001197093,0.001340749,0.00001512985,0.0005728778,0.00001075287,0.000476873,0.5013105,5.014188e-7,0.0000138965,0.4960632,0.0001275373],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0003483468,0.0003356236,0.961793,0.001102543,0.003347484,0.0001288262,0.02464771,0.00004459183,0.008251859],"genre_scores_gemma":[0.05777293,0.03127204,0.3930459,0.005940717,0.02361654,0.00002447565,0.4761647,0.0001928834,0.01196974],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5687471,"threshold_uncertainty_score":0.999166,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4244973481","doi":"10.1002/sam.11358","title":"Issue Information","year":2018,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07753281751408107,"gpt":0.3766135914705343,"spread":0.2990807739564532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004635337,0.0001965586,0.0003203154,0.0005173777,0.000883456,0.001950717,0.003208255,0.00008216043,0.05649981],"category_scores_gemma":[0.0007409742,0.0001286768,0.00002637339,0.0009864349,0.0007607398,0.003784603,0.001149342,0.0004404324,0.01557525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006262758,"about_ca_system_score_gemma":0.000201332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009360851,"about_ca_topic_score_gemma":0.00005326123,"domain_scores_codex":[0.9976816,0.00007872543,0.0005798048,0.0003812776,0.0009517169,0.0003269061],"domain_scores_gemma":[0.9973494,0.0001523806,0.0002072328,0.001874884,0.0001941811,0.0002219381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002788105,0.000003638989,0.00001633992,0.00001483992,0.0001567548,6.01102e-7,0.0002887113,0.0003739985,0.000009104084,0.000005413903,0.9611536,0.03797421],"study_design_scores_gemma":[0.00006017499,0.00001616971,0.002011712,0.00002179505,0.0005986734,0.00001535431,0.0004228699,0.4475783,7.026019e-7,0.00002151576,0.5491084,0.000144214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001201034,0.0003013072,0.9564448,0.0003891815,0.005450423,0.0001382562,0.02361378,0.00004305546,0.01241817],"genre_scores_gemma":[0.04737784,0.02559553,0.4506448,0.003207855,0.03482186,0.00002586494,0.4084181,0.0001980355,0.02971014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5058,"threshold_uncertainty_score":0.9990854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245052885","doi":"10.1002/sam.11384","title":"Issue Information","year":2019,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.07162451266438453,"gpt":0.3683286561938265,"spread":0.296704143529442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004119816,0.0001968899,0.0003530644,0.000520993,0.0005979338,0.001837216,0.003099645,0.00008266781,0.04040167],"category_scores_gemma":[0.0005704757,0.0001294031,0.00002889063,0.0009026439,0.0004042732,0.003911602,0.001092211,0.0005290415,0.02121925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006559319,"about_ca_system_score_gemma":0.0002254406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009407612,"about_ca_topic_score_gemma":0.00002966986,"domain_scores_codex":[0.997686,0.00007561005,0.0005684084,0.0003797703,0.0009719082,0.0003182471],"domain_scores_gemma":[0.9972966,0.0001914361,0.0002088785,0.001972525,0.0001426694,0.0001878668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002747596,0.00000370663,0.0000302931,0.00002394694,0.000167485,5.385216e-7,0.0002447423,0.002654356,0.00001178591,0.00000830256,0.9549817,0.04187043],"study_design_scores_gemma":[0.00006819697,0.00001193943,0.002454549,0.00002198957,0.0004994433,0.000011963,0.0004538442,0.5135813,4.199234e-7,0.00001160851,0.4827425,0.000142217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0009747503,0.0004071927,0.9526601,0.0004204595,0.006845149,0.0001803465,0.0254738,0.00003762413,0.01300057],"genre_scores_gemma":[0.08468768,0.03207391,0.2914493,0.003603202,0.01937249,0.00002470186,0.516661,0.0002211992,0.0519065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6612108,"threshold_uncertainty_score":0.999199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4254812759","doi":"10.1002/sam.11467","title":"Issue Information","year":2021,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07724045282164911,"gpt":0.3726486626682964,"spread":0.2954082098466473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003824405,0.0001900015,0.0003505646,0.0004356199,0.0007597795,0.002299066,0.002610616,0.00007897646,0.05425288],"category_scores_gemma":[0.0008384298,0.0001297037,0.0000309643,0.001146606,0.0004356836,0.003398759,0.001221357,0.0005339399,0.005597943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006378987,"about_ca_system_score_gemma":0.0002838371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009215492,"about_ca_topic_score_gemma":0.00005776683,"domain_scores_codex":[0.9976568,0.00009502706,0.0005800453,0.0003913939,0.0009691076,0.0003076094],"domain_scores_gemma":[0.9973861,0.0001779652,0.0001825041,0.001846162,0.0001914575,0.0002157986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001733122,0.000004640057,0.00001759694,0.00002070248,0.0001954233,0.000001974795,0.0002697796,0.001306839,0.0000162731,0.000007785901,0.9447384,0.0534188],"study_design_scores_gemma":[0.00006561381,0.000008788436,0.00222839,0.00003016775,0.0007125619,0.0000259337,0.0008728289,0.4657682,9.87719e-7,0.00001286957,0.5301157,0.0001579321],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0009498989,0.0008471753,0.9591712,0.0005487679,0.005025131,0.0001160989,0.02330065,0.00003590683,0.01000512],"genre_scores_gemma":[0.03013856,0.03949951,0.3476554,0.002714434,0.01614763,0.00002049979,0.5394098,0.0001438764,0.02427031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6115159,"threshold_uncertainty_score":0.9987366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245325236","doi":"10.1002/sam.11362","title":"Issue Information","year":2018,"lang":"en","type":"paratext","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07753281751408107,"gpt":0.3766135914705343,"spread":0.2990807739564532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004635337,0.0001965586,0.0003203154,0.0005173777,0.000883456,0.001950717,0.003208255,0.00008216043,0.05649981],"category_scores_gemma":[0.0007409742,0.0001286768,0.00002637339,0.0009864349,0.0007607398,0.003784603,0.001149342,0.0004404324,0.01557525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006262758,"about_ca_system_score_gemma":0.000201332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009360851,"about_ca_topic_score_gemma":0.00005326123,"domain_scores_codex":[0.9976816,0.00007872543,0.0005798048,0.0003812776,0.0009517169,0.0003269061],"domain_scores_gemma":[0.9973494,0.0001523806,0.0002072328,0.001874884,0.0001941811,0.0002219381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002788105,0.000003638989,0.00001633992,0.00001483992,0.0001567548,6.01102e-7,0.0002887113,0.0003739985,0.000009104084,0.000005413903,0.9611536,0.03797421],"study_design_scores_gemma":[0.00006017499,0.00001616971,0.002011712,0.00002179505,0.0005986734,0.00001535431,0.0004228699,0.4475783,7.026019e-7,0.00002151576,0.5491084,0.000144214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001201034,0.0003013072,0.9564448,0.0003891815,0.005450423,0.0001382562,0.02361378,0.00004305546,0.01241817],"genre_scores_gemma":[0.04737784,0.02559553,0.4506448,0.003207855,0.03482186,0.00002586494,0.4084181,0.0001980355,0.02971014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5058,"threshold_uncertainty_score":0.9990854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413289142","doi":"10.1002/sam.70038","title":"Distributionally Conservative Stochastic Dominance via Subsampling","year":2025,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Stochastic dominance; Dominance (genetics); Econometrics; Statistics; Mathematics; Computer science; Economics; Mathematical optimization; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.145829436943856,"gpt":0.4572373035182113,"spread":0.3114078665743553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01736355,0.0001512789,0.0003926928,0.0005202839,0.002013274,0.002249669,0.005821222,0.00003478034,0.0001649384],"category_scores_gemma":[0.02247795,0.00008494105,0.00003943054,0.005674806,0.001725524,0.002434438,0.002680823,0.0002763011,0.00001335423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003474141,"about_ca_system_score_gemma":0.0006652102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001159584,"about_ca_topic_score_gemma":0.0001837377,"domain_scores_codex":[0.9958047,0.0002226315,0.0009113569,0.0009977409,0.001678766,0.0003848192],"domain_scores_gemma":[0.9915197,0.004557347,0.0005067691,0.002463957,0.0007308873,0.0002212926],"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":[0.0003212217,0.0002269856,0.2092731,0.000005665837,0.00105713,0.00006819575,0.000859529,0.01563165,0.0001840186,0.09215683,0.09351248,0.5867032],"study_design_scores_gemma":[0.000166436,0.00001904174,0.1804858,0.0000163622,0.0005259099,0.00003495087,0.0007997002,0.7958007,0.000002978642,0.01922077,0.002805837,0.0001214594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01507279,0.0002048321,0.9773217,0.002281529,0.0002164593,0.00006689362,0.004690397,0.000006877519,0.0001384785],"genre_scores_gemma":[0.8798397,0.0002777864,0.1178821,0.0003575567,0.00008748416,0.000001650186,0.001416273,0.000003608664,0.0001338577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8647669,"threshold_uncertainty_score":0.9995577,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982925244","doi":"10.1002/sam.10094","title":"Special issue on the best papers of SDM'10","year":2010,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Citation; Library science; Computer science; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.05194367942912519,"gpt":0.3425082124392971,"spread":0.2905645330101719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005474205,0.0001337869,0.0002290277,0.0001772536,0.001311955,0.001374186,0.01137761,0.00002804855,0.0006736707],"category_scores_gemma":[0.002224941,0.00006687651,0.00003080604,0.001890834,0.001484099,0.001392966,0.00383034,0.0004413997,0.0000432402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007496026,"about_ca_system_score_gemma":0.0002233285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009097179,"about_ca_topic_score_gemma":0.0001366399,"domain_scores_codex":[0.9975632,0.00007368195,0.0004119364,0.0007282345,0.0008906614,0.0003322436],"domain_scores_gemma":[0.993993,0.001110458,0.0002689922,0.004275016,0.0001352279,0.0002172951],"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":[0.000008257555,0.0001366759,0.0008177664,0.000002545419,0.0001695735,0.00001127134,0.0003828296,0.000008594852,0.0005312032,0.08287826,0.1196616,0.7953914],"study_design_scores_gemma":[0.0002038704,0.0001685239,0.02143108,0.00002517994,0.0006249642,0.0001220253,0.001669158,0.62074,0.00008011592,0.00165612,0.3529636,0.0003153309],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03112712,0.00007358086,0.8936186,0.03391324,0.002073464,0.0003635843,0.01955577,0.00005229464,0.01922236],"genre_scores_gemma":[0.1176718,0.0002346054,0.8744082,0.0009678783,0.005273317,0.000005898977,0.0009789165,0.00001457996,0.000444891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7950761,"threshold_uncertainty_score":0.9999882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392370559","doi":"10.1002/sam.11668","title":"Marginal clustered multistate models for longitudinal progressive processes with informative cluster size","year":2024,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Resampling; Inference; Cluster (spacecraft); Computer science; Statistics; Data mining; Process (computing); Econometrics; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0727690246232361,"gpt":0.3869419909109413,"spread":0.3141729662877052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003280338,0.0002378324,0.0004842296,0.0002732124,0.0007209239,0.001612597,0.00171375,0.00002891526,0.00008944123],"category_scores_gemma":[0.003837726,0.0001228253,0.0000401392,0.001780531,0.001488914,0.004390135,0.00147107,0.0003098514,0.000005458335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005052706,"about_ca_system_score_gemma":0.001440833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002828231,"about_ca_topic_score_gemma":0.0001877488,"domain_scores_codex":[0.9969112,0.00006540007,0.0005586228,0.0009151821,0.001013289,0.0005362567],"domain_scores_gemma":[0.9953728,0.001804358,0.000254318,0.001556381,0.000568408,0.0004437245],"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":[0.0210323,0.001724426,0.1534782,0.009048446,0.02694679,0.005723739,0.0153457,0.004352067,0.0001339128,0.01051753,0.2616387,0.4900582],"study_design_scores_gemma":[0.0009457997,0.0003189579,0.02971832,0.0004432148,0.003332809,0.0008974829,0.001357932,0.960219,0.000003911301,0.0005750611,0.001939795,0.000247765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01675037,0.0009966784,0.9366047,0.001828014,0.00008803126,0.0005074354,0.04306358,0.00004811343,0.0001130199],"genre_scores_gemma":[0.7059674,0.0002734244,0.2866215,0.000294791,0.0001967836,0.00002097995,0.006535986,0.00001952364,0.00006965266],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9558669,"threshold_uncertainty_score":0.9994238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413868413","doi":"10.1002/sam.70042","title":"Recursive Random Binning to Detect and Display Pairwise Dependence","year":2025,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Pairwise comparison; Computer science; Mathematics; Statistics; Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04648949380676017,"gpt":0.3791487152178348,"spread":0.3326592214110746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.006286339,0.0001562796,0.0003141178,0.0006007738,0.001330847,0.002994045,0.006235382,0.00002644106,0.00002117973],"category_scores_gemma":[0.005090086,0.00009822986,0.0000228803,0.004117287,0.000591613,0.002804536,0.007018029,0.0002267843,0.000005062603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002292559,"about_ca_system_score_gemma":0.0003050928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007219324,"about_ca_topic_score_gemma":0.0001467381,"domain_scores_codex":[0.9972861,0.0001693844,0.0004524258,0.0009880076,0.0007067956,0.0003973324],"domain_scores_gemma":[0.9959993,0.0009755557,0.0001712947,0.002310162,0.0001747141,0.0003689787],"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":[0.0001031376,0.00007526356,0.01954475,0.00003213299,0.0008339642,0.0001240731,0.001460666,0.0002748267,0.0003991823,0.1377721,0.04600803,0.7933719],"study_design_scores_gemma":[0.0004174699,0.00005636703,0.01936039,0.00007451593,0.0006364189,0.00006855779,0.0006055891,0.9699109,0.00002919036,0.00407003,0.004545508,0.0002251002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002954721,0.0001932804,0.9932385,0.00242174,0.000119085,0.00006803388,0.0009124978,0.00001665704,0.0000754581],"genre_scores_gemma":[0.3099573,0.0006661629,0.6868311,0.001981526,0.00007216722,0.000002160567,0.0003957788,0.000006105528,0.00008779773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.969636,"threshold_uncertainty_score":0.9999693,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"}]}