{"meta":{"query_hash":"f35200098bd0","filters":{"venue":"Statistical Analysis and Data Mining The ASA Data Science Journal"},"cohort_total":37,"direct_labels_cover":1,"predictions_cover":37,"exported":37,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/f35200098bd0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Statistical+Analysis+and+Data+Mining+The+ASA+Data+Science+Journal"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.18075572576648957,"score_gpt":0.4095357243360112,"score_spread":0.22877999856952164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512585278","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039459006,0.00013102213,0.98864555,0.0005501893,0.0002650826,0.00015713759,0.0062488336,0.000050446157,0.0000058195824],"genre_scores_gemma":[0.4717241,0.000078206096,0.5271198,0.000054176755,0.00030739678,0.000010394334,0.00069756375,0.0000063296234,0.0000020011119],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724835,0.00012429859,0.0005323223,0.00092400715,0.00086297543,0.0003080495],"domain_scores_gemma":[0.9954346,0.00044125193,0.00035277792,0.0031196414,0.00036547953,0.00028627086],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0058922996,0.000118291115,0.0002530214,0.0003065503,0.00082511466,0.00070520805,0.005997716,0.000044482615,0.0000059606004],"category_scores_gemma":[0.0010973244,0.00008165226,0.000021325319,0.0024475364,0.00069192145,0.0041032555,0.0039522615,0.00024836764,7.257976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022301062,0.00030445773,0.013808686,0.00008094403,0.001243338,0.0000079551055,0.0011659289,0.008027632,0.007350794,0.0054215775,0.010481947,0.95188373],"study_design_scores_gemma":[0.0001985856,0.00006657782,0.009380024,0.000011329474,0.0005668012,0.00006531797,0.00015163915,0.98687536,0.00006286104,0.0010912698,0.0014379731,0.00009224749],"about_ca_topic_score_codex":0.00051298976,"about_ca_topic_score_gemma":0.00039303928,"teacher_disagreement_score":0.97884774,"about_ca_system_score_codex":0.000100849385,"about_ca_system_score_gemma":0.0007429511,"threshold_uncertainty_score":0.9993803},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.12011645933756977,"score_gpt":0.3973333708886629,"score_spread":0.2772169115510931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525895928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019103043,0.00019171565,0.9654648,0.0024111455,0.0005009854,0.0001593842,0.0292683,0.000039581686,0.00005383015],"genre_scores_gemma":[0.020229038,0.0002494069,0.97430706,0.00017310957,0.0006208663,0.000013834052,0.0043697665,0.000012296934,0.000024625951],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99523616,0.00017079194,0.00077741063,0.001741008,0.0014469689,0.0006276463],"domain_scores_gemma":[0.99103487,0.0017240809,0.0010162082,0.005064225,0.0008421538,0.00031844582],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.019297792,0.0002778236,0.0005499746,0.00040394688,0.0022243334,0.007570941,0.015764963,0.00010010822,0.000015552168],"category_scores_gemma":[0.009649204,0.0001855086,0.00006985463,0.0011860963,0.0006971346,0.0024257817,0.02033588,0.00060548994,0.0000052639575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023008117,0.000117322474,0.005174021,0.000057074296,0.0017311022,0.00001213862,0.0011794847,0.00008570164,0.000049822378,0.015845276,0.10771348,0.8680116],"study_design_scores_gemma":[0.00015125066,0.000048666967,0.008948904,0.00010081334,0.0013448073,0.000028475608,0.00028783813,0.9661919,0.000008738364,0.011005937,0.011557314,0.00032537585],"about_ca_topic_score_codex":0.0001555048,"about_ca_topic_score_gemma":0.00013949502,"teacher_disagreement_score":0.9661062,"about_ca_system_score_codex":0.00014596934,"about_ca_system_score_gemma":0.0009227794,"threshold_uncertainty_score":0.99907464},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Recommender system; Matrix decomposition; Collaborative filtering; Matrix (chemical analysis); Factorization; Non-negative matrix factorization","score_opus":0.15790303555913265,"score_gpt":0.37882805816453147,"score_spread":0.2209250226053988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979148915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005172432,0.00014477337,0.99554515,0.0020118353,0.00028214118,0.00036431444,0.0009807135,0.00007528699,0.000078532146],"genre_scores_gemma":[0.396437,0.00018660662,0.6022633,0.00019311704,0.00016851291,0.00003066207,0.0006522405,0.000009166985,0.00005942655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972831,0.00016913628,0.0006805411,0.0008206846,0.0006102045,0.00043635472],"domain_scores_gemma":[0.99570954,0.0006758469,0.00042380168,0.0025323161,0.00041182846,0.0002466706],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00554052,0.00017734188,0.00037560656,0.00036495042,0.001031028,0.0043443297,0.006209823,0.000050183527,0.000026516851],"category_scores_gemma":[0.0008387912,0.00010291905,0.000037665435,0.0012322407,0.0002670332,0.005229057,0.0026211427,0.00019303503,0.0000036825693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018216642,0.00018083057,0.01703539,0.00007765495,0.0010868193,0.000011167517,0.0008454218,0.000008044177,0.0025002079,0.12367374,0.29033062,0.5642319],"study_design_scores_gemma":[0.00021388658,0.00016771897,0.012637521,0.000058672715,0.00036908188,0.00013794057,0.0011846195,0.9636567,0.000106969885,0.0036454254,0.017454874,0.00036654953],"about_ca_topic_score_codex":0.00065934216,"about_ca_topic_score_gemma":0.000025448402,"teacher_disagreement_score":0.9636487,"about_ca_system_score_codex":0.000042713855,"about_ca_system_score_gemma":0.00013536704,"threshold_uncertainty_score":0.9991671},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Citation; Library science; Computer science; Information retrieval","score_opus":0.05194367942912519,"score_gpt":0.3425082124392971,"score_spread":0.2905645330101719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982925244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031127121,0.00007358086,0.8936186,0.033913244,0.0020734635,0.00036358432,0.019555772,0.000052294643,0.019222358],"genre_scores_gemma":[0.11767175,0.00023460544,0.8744082,0.00096787827,0.005273317,0.0000058989767,0.0009789165,0.0000145799595,0.00044489102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756324,0.00007368195,0.00041193637,0.00072823453,0.0008906614,0.0003322436],"domain_scores_gemma":[0.993993,0.0011104584,0.0002689922,0.0042750156,0.00013522788,0.00021729506],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005474205,0.00013378695,0.00022902768,0.0001772536,0.0013119549,0.0013741861,0.011377611,0.000028048551,0.0006736707],"category_scores_gemma":[0.0022249413,0.00006687651,0.00003080604,0.0018908336,0.0014840986,0.001392966,0.0038303395,0.00044139966,0.000043240205],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008257555,0.00013667594,0.00081776635,0.0000025454185,0.00016957345,0.000011271338,0.00038282957,0.000008594852,0.0005312032,0.08287826,0.119661614,0.7953914],"study_design_scores_gemma":[0.00020387035,0.00016852387,0.02143108,0.000025179943,0.00062496425,0.000122025325,0.0016691576,0.62074,0.00008011592,0.0016561202,0.35296363,0.00031533086],"about_ca_topic_score_codex":0.00009097179,"about_ca_topic_score_gemma":0.0001366399,"teacher_disagreement_score":0.7950761,"about_ca_system_score_codex":0.000007496026,"about_ca_system_score_gemma":0.00022332849,"threshold_uncertainty_score":0.9999882},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09488812902028622,"score_gpt":0.35905860971230336,"score_spread":0.26417048069201715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015887370","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02928215,0.00005216212,0.9673868,0.0006725916,0.0001221815,0.00007216251,0.0023668362,0.000025827194,0.000019278965],"genre_scores_gemma":[0.8600723,0.00004010812,0.13854095,0.00023864592,0.00009072051,0.0000022712773,0.0010037324,0.0000045623424,0.000006724349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707144,0.0002722957,0.00046297206,0.00092886254,0.0007991829,0.00046522103],"domain_scores_gemma":[0.994402,0.0007537588,0.00018626168,0.0042437688,0.000096305506,0.00031789448],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.009776866,0.0001470646,0.0002570498,0.00036984106,0.00088842574,0.0007597383,0.0070698815,0.00003997956,0.000054655557],"category_scores_gemma":[0.0014013097,0.00009415863,0.000018025463,0.0030376134,0.00037915207,0.0035075126,0.0056568696,0.00038392792,0.000017365968],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007280549,0.000668614,0.11395758,0.0000049152122,0.00027094525,0.000019825624,0.00030068436,0.00014988027,0.00039867795,0.011782773,0.013643708,0.8587296],"study_design_scores_gemma":[0.00008789653,0.00003687949,0.44425097,0.000004506081,0.00007415842,0.000029491232,0.00003298025,0.55447155,0.00001861326,0.0002257187,0.0006587137,0.00010853015],"about_ca_topic_score_codex":0.00086478546,"about_ca_topic_score_gemma":0.00035016725,"teacher_disagreement_score":0.85862106,"about_ca_system_score_codex":0.00004101557,"about_ca_system_score_gemma":0.00014620055,"threshold_uncertainty_score":0.99830234},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09250896968680458,"score_gpt":0.3798075243016192,"score_spread":0.28729855461481457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053843934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012126851,0.00033425455,0.9957324,0.0015662195,0.00036048327,0.00003998605,0.00047185915,0.000018607578,0.00026349],"genre_scores_gemma":[0.19242038,0.00016350135,0.80666405,0.00037498353,0.00026209521,6.616156e-7,0.00009556146,0.0000047212748,0.0000140455095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970434,0.00023387992,0.00041562694,0.0007159078,0.000873646,0.0007175424],"domain_scores_gemma":[0.9951534,0.0006943943,0.00019651286,0.003222027,0.000088921304,0.0006447067],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.011844589,0.0001617286,0.00029638296,0.00028634447,0.0012068391,0.0017316729,0.0083623165,0.00003515855,0.00006132048],"category_scores_gemma":[0.0015942551,0.00009386941,0.000032178323,0.0019763869,0.0007154941,0.0057106344,0.006604244,0.00034703227,0.000008551951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009830228,0.00008470987,0.014402969,0.000008755048,0.00031284802,0.00004579725,0.0021282749,0.000022530487,0.00015405103,0.067818224,0.010048677,0.9049633],"study_design_scores_gemma":[0.00011932075,0.000030806717,0.036691222,0.000014340919,0.00044696673,0.00028430822,0.0002441824,0.95504993,0.000008263499,0.0032935538,0.003590835,0.00022628023],"about_ca_topic_score_codex":0.00007782133,"about_ca_topic_score_gemma":0.00007183079,"teacher_disagreement_score":0.9550274,"about_ca_system_score_codex":0.000022232216,"about_ca_system_score_gemma":0.00020138721,"threshold_uncertainty_score":0.99930465},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.2031330746131957,"score_gpt":0.39143483193317025,"score_spread":0.18830175731997453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153591306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7857816,0.00056304934,0.19623394,0.0013011487,0.0001937435,0.0001251774,0.015196454,0.000028368107,0.00057650654],"genre_scores_gemma":[0.8851881,0.00014301823,0.1122102,0.00013382403,0.00014698763,0.0000010897819,0.0021414647,0.0000012486336,0.000034043194],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99599636,0.00049578835,0.00083446165,0.00091860467,0.0012541567,0.0005006137],"domain_scores_gemma":[0.9950889,0.0024078162,0.00046177953,0.0010376384,0.00038354954,0.00062035565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0118307425,0.00020462711,0.00082789635,0.00027570289,0.0008003993,0.0006617218,0.003886363,0.00005639242,0.00051396375],"category_scores_gemma":[0.0068366625,0.00007042385,0.00011952167,0.007838533,0.0014619349,0.00088200875,0.0019256333,0.0002601352,0.0000031121906],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022475708,0.0006184598,0.30352703,0.0000138513615,0.011444566,0.000082176724,0.0009825069,0.0008183892,0.006256006,0.031840324,0.006646593,0.63754535],"study_design_scores_gemma":[0.00013097355,0.00017934517,0.53536874,0.000009769049,0.0162437,0.000028846316,0.0026314056,0.43775004,0.000017156362,0.0020121182,0.0053440738,0.000283829],"about_ca_topic_score_codex":0.0011497467,"about_ca_topic_score_gemma":0.0014583026,"teacher_disagreement_score":0.6372615,"about_ca_system_score_codex":0.000028705566,"about_ca_system_score_gemma":0.00010907187,"threshold_uncertainty_score":0.8184618},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.224123729836376,"score_gpt":0.43411663687616964,"score_spread":0.20999290703979365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407525010","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00815704,0.000025332633,0.98587894,0.00091126724,0.000025715199,0.000092943985,0.0048271627,0.000009628948,0.00007194082],"genre_scores_gemma":[0.08941454,0.0001278191,0.9101181,0.00005761226,0.00013698921,0.0000044461235,0.00010123998,0.000009187174,0.00003004448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797446,0.00010415796,0.00041182112,0.00075836905,0.00038935168,0.0003618457],"domain_scores_gemma":[0.9938824,0.003893918,0.00021530807,0.0015332319,0.000112684414,0.00036243343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003554847,0.00015235016,0.00035494103,0.00012286787,0.0008180257,0.00047314848,0.0015822112,0.000029679559,0.00011589287],"category_scores_gemma":[0.0033722704,0.0000679024,0.00001586022,0.0004254986,0.0016611207,0.0013434864,0.0014090679,0.00017704253,0.0000024510475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001409513,0.000098951255,0.0049709235,0.000017920725,0.0005113948,0.00002177535,0.00017880392,0.000026250884,0.00025696927,0.35713843,0.0023997712,0.6342379],"study_design_scores_gemma":[0.0019522472,0.0003417949,0.023790583,0.00011653381,0.004867909,0.000480725,0.0012052882,0.5275833,0.00002999874,0.43281728,0.0059083975,0.00090594956],"about_ca_topic_score_codex":0.000021487185,"about_ca_topic_score_gemma":0.00009614649,"teacher_disagreement_score":0.6333319,"about_ca_system_score_codex":0.00002227294,"about_ca_system_score_gemma":0.0001616113,"threshold_uncertainty_score":0.6291675},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1957237084336176,"score_gpt":0.35291672015557535,"score_spread":0.15719301172195774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509008132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5063933,0.0011651448,0.41800794,0.029723693,0.0005209909,0.00025911845,0.03996103,0.000015825404,0.003952926],"genre_scores_gemma":[0.9939524,0.00065785286,0.0041921306,0.0007028564,0.00016408323,0.0000012300272,0.0002625526,0.000004273846,0.00006264547],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99800867,0.000034789817,0.0006670356,0.00060384005,0.00033695233,0.00034873147],"domain_scores_gemma":[0.9977409,0.00059038744,0.00034956142,0.0011158627,0.00007885246,0.00012442989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0128090605,0.00011293671,0.00028504612,0.00039526194,0.0006188874,0.00071329356,0.0033235543,0.000026599495,0.0006177472],"category_scores_gemma":[0.0021681015,0.00005364574,0.000034275414,0.001366632,0.0006640725,0.0014775933,0.0007453213,0.00020008352,0.00004305627],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003970622,0.00016914433,0.78574866,0.0000076772085,0.00034948395,0.000043500706,0.00074191904,0.00015343918,0.000027440221,0.14107996,0.047239106,0.024399996],"study_design_scores_gemma":[0.000322323,0.000036144316,0.7201192,0.000018509621,0.00010720645,0.000052224423,0.00035064179,0.24664813,0.0000011296015,0.008794663,0.023357429,0.00019242617],"about_ca_topic_score_codex":0.00037942486,"about_ca_topic_score_gemma":0.0004891661,"teacher_disagreement_score":0.48755905,"about_ca_system_score_codex":0.00004153927,"about_ca_system_score_gemma":0.00013154747,"threshold_uncertainty_score":0.6878306},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","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","score_opus":0.08062547735272997,"score_gpt":0.3739859447699232,"score_spread":0.29336046741719324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790407909","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036227505,0.00018984335,0.9941517,0.000922389,0.0004934278,0.00007640523,0.00044069334,0.000019996003,0.00008275997],"genre_scores_gemma":[0.26729268,0.000078524274,0.7320957,0.00015007456,0.00032217673,0.0000026867936,0.00004061478,0.000005178605,0.000012322748],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969363,0.0002537567,0.0003668352,0.0010009896,0.0009641102,0.00047797887],"domain_scores_gemma":[0.9966519,0.00038035613,0.00026942685,0.0021155023,0.00027843015,0.00030439222],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0082692355,0.00016422027,0.0003091211,0.00026586818,0.0014563008,0.0026880496,0.0052089123,0.000030389025,0.000021236474],"category_scores_gemma":[0.0004043923,0.000086548986,0.000020611553,0.0023980315,0.0010383128,0.0033080347,0.0026922163,0.00024353276,0.0000019488932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010923487,0.000089618625,0.020952849,0.000025903557,0.0012097794,0.000047325993,0.0007872939,0.00013628101,0.00034313512,0.115311675,0.009287972,0.85169894],"study_design_scores_gemma":[0.00015998771,0.00014906142,0.014719465,0.000046224766,0.0007983599,0.00009477927,0.00019675471,0.98084515,0.000008775661,0.0012244236,0.0015658978,0.00019112737],"about_ca_topic_score_codex":0.0003732977,"about_ca_topic_score_gemma":0.00024106582,"teacher_disagreement_score":0.98070884,"about_ca_system_score_codex":0.000031481704,"about_ca_system_score_gemma":0.00031936844,"threshold_uncertainty_score":0.99984366},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.052607974915139445,"score_gpt":0.37107473242317524,"score_spread":0.31846675750803577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793406240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018185973,0.000043023578,0.98022145,0.0010289487,0.00006391743,0.00004906713,0.00020287387,0.000010928268,0.00019380491],"genre_scores_gemma":[0.72022116,0.000084311956,0.27943537,0.00016442135,0.000033796838,4.9713253e-7,0.000056727866,0.0000016680376,0.0000020666605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782217,0.000086622385,0.00047248992,0.0006526428,0.0005861868,0.00037991512],"domain_scores_gemma":[0.9976391,0.00047647388,0.0002565113,0.0012022203,0.00018620242,0.00023945062],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0037316724,0.00013799744,0.0002420517,0.0004245253,0.0008492647,0.00229678,0.004185725,0.000028177046,0.000022264032],"category_scores_gemma":[0.0013314049,0.000085280124,0.000010238142,0.0026648103,0.001415993,0.006119389,0.003930528,0.00025423858,0.0000049148],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026041533,0.00007893035,0.09578594,0.000027648519,0.00015804377,0.000048670223,0.007995263,0.000041766714,0.00004298741,0.08829005,0.00146281,0.80604184],"study_design_scores_gemma":[0.00012043601,0.00007440014,0.21002942,0.000027028065,0.000063143,0.000064883585,0.0006361881,0.7813615,0.000004389785,0.0073941136,0.00010323928,0.00012121939],"about_ca_topic_score_codex":0.000114793336,"about_ca_topic_score_gemma":0.00032478638,"teacher_disagreement_score":0.8059206,"about_ca_system_score_codex":0.000019838537,"about_ca_system_score_gemma":0.00036581708,"threshold_uncertainty_score":0.99873894},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06895868629883593,"score_gpt":0.3872516588172325,"score_spread":0.31829297251839656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953239640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009753337,0.00009878901,0.9861996,0.00028149103,0.00014410896,0.00020626141,0.0032836027,0.000019400775,0.000013416119],"genre_scores_gemma":[0.05466449,0.00011799677,0.94325125,0.00034457247,0.000059386715,0.0000017586926,0.0015468514,0.0000061620885,0.000007538991],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690324,0.0001526823,0.00051082775,0.0011969921,0.0008503985,0.00038587378],"domain_scores_gemma":[0.9951995,0.0011603974,0.00035968778,0.0027911114,0.00020585315,0.00028345216],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005901194,0.00016213735,0.00030644052,0.00068941724,0.0006931135,0.0019727114,0.006486909,0.000032153166,0.00006467013],"category_scores_gemma":[0.0017738638,0.00010903647,0.00002528695,0.0025498709,0.00071226666,0.0070594447,0.0063105896,0.00024917145,0.0000029304713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003690007,0.000116427495,0.010228169,0.000031577423,0.00049686787,0.00001733552,0.0006776615,0.000013800947,0.009388524,0.0004773606,0.009146909,0.96936846],"study_design_scores_gemma":[0.00026551314,0.000085231644,0.004993571,0.000026458369,0.00042037666,0.000092492715,0.0008235009,0.9923142,0.0003188684,0.00026105478,0.0002400181,0.0001586704],"about_ca_topic_score_codex":0.00011310022,"about_ca_topic_score_gemma":0.00003334611,"teacher_disagreement_score":0.99230045,"about_ca_system_score_codex":0.00003654813,"about_ca_system_score_gemma":0.00021537552,"threshold_uncertainty_score":0.9990633},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04718228723840193,"score_gpt":0.3264302161271736,"score_spread":0.27924792888877165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964276935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026573444,0.000050997016,0.97196215,0.0005662876,0.00017970723,0.00004677657,0.00026022253,0.000020073978,0.00034032782],"genre_scores_gemma":[0.312186,0.00008819917,0.6870064,0.00026967961,0.00007859768,7.3993186e-7,0.00029739857,0.0000036369006,0.00006929717],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783355,0.00011075826,0.00029595077,0.0007242448,0.00068774144,0.00034773684],"domain_scores_gemma":[0.9974572,0.00042984213,0.00017733799,0.0016149146,0.00013972147,0.00018097376],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004800423,0.000104446844,0.00019494668,0.0002650905,0.0009809582,0.0019260449,0.004284411,0.000026826454,0.00020290514],"category_scores_gemma":[0.0007627705,0.00006286784,0.000016402875,0.0021564837,0.00020403178,0.0047815987,0.0029775728,0.00024038197,0.000036501566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007677697,0.00028157636,0.09560838,0.00004860533,0.0010454518,0.000051062314,0.0018050938,0.0015168737,0.02445184,0.11561353,0.0805766,0.6789242],"study_design_scores_gemma":[0.00012361571,0.000046543908,0.0127844345,0.000027237253,0.0001931208,0.00010576247,0.0003629666,0.9802229,0.00006369477,0.0025134098,0.0034261607,0.00013017503],"about_ca_topic_score_codex":0.00009872089,"about_ca_topic_score_gemma":0.000025209063,"teacher_disagreement_score":0.978706,"about_ca_system_score_codex":0.00001685783,"about_ca_system_score_gemma":0.00023512918,"threshold_uncertainty_score":0.99911004},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"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","score_opus":0.10891862325224824,"score_gpt":0.3994450036008474,"score_spread":0.2905263803485991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998595054","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014147814,0.000045997436,0.9794678,0.005462824,0.00006611114,0.000064544714,0.0007226888,0.000010670055,0.000011546786],"genre_scores_gemma":[0.08515183,0.00009541013,0.91365033,0.00031675317,0.00011344404,0.0000012167841,0.0006616816,0.000002438891,0.0000068796307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759084,0.00013510912,0.00045419286,0.0008856757,0.0006331574,0.0003010396],"domain_scores_gemma":[0.9976345,0.00043339957,0.00020791634,0.0012610687,0.0001291883,0.00033397187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005194842,0.000114894916,0.0003198177,0.00035286002,0.00065001845,0.00076806644,0.003332847,0.000027599637,0.00005291782],"category_scores_gemma":[0.0012236608,0.00007216479,0.00004842279,0.0047596325,0.0001603156,0.002994985,0.0019799112,0.00021671022,0.0000037113778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001685399,0.000118882774,0.015762264,0.000025841184,0.0011868534,0.00001817492,0.0015985157,0.0035375266,0.0018601725,0.0026438748,0.022439439,0.9506399],"study_design_scores_gemma":[0.00018253288,0.000050359697,0.021870844,0.000009070171,0.00082281465,0.000017041755,0.00027699876,0.97534496,0.000059439917,0.00045572565,0.0008029923,0.00010719718],"about_ca_topic_score_codex":0.00015187344,"about_ca_topic_score_gemma":0.000055860786,"teacher_disagreement_score":0.9718075,"about_ca_system_score_codex":0.000016901364,"about_ca_system_score_gemma":0.00027569773,"threshold_uncertainty_score":0.74064827},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06367776533288279,"score_gpt":0.3649556518565307,"score_spread":0.30127788652364795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169835580","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054229077,0.000621793,0.9394533,0.0021995453,0.00011037368,0.00007962598,0.0031908625,0.0000041231515,0.000111270536],"genre_scores_gemma":[0.8755152,0.00080030947,0.11600727,0.0004825113,0.00017545623,0.0000055114533,0.0069589852,0.000007702447,0.00004702156],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981711,0.000109958,0.00031137464,0.0007367361,0.00038158294,0.00028927877],"domain_scores_gemma":[0.99778205,0.00008789184,0.00014610737,0.0015155316,0.00022168092,0.00024676145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019649423,0.00010920769,0.00019737771,0.00009950859,0.0007434927,0.0005158958,0.0016430449,0.000045942797,0.000041150415],"category_scores_gemma":[0.000624014,0.00007060238,0.00004628078,0.0007148282,0.0004759799,0.000074186755,0.0013032793,0.00011941185,6.5601034e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008597083,0.0004881133,0.01132203,0.000041320407,0.0020155362,0.000045633777,0.00037333084,0.00032570885,0.7349174,0.013639029,0.12685163,0.109120555],"study_design_scores_gemma":[0.0023212486,0.00034602004,0.05394613,0.000053573243,0.0031863921,0.00036611478,0.0029002684,0.8605168,0.00813494,0.010315739,0.057172853,0.0007399248],"about_ca_topic_score_codex":0.000011615339,"about_ca_topic_score_gemma":0.000076024335,"teacher_disagreement_score":0.8601911,"about_ca_system_score_codex":0.0000075222483,"about_ca_system_score_gemma":0.00037936307,"threshold_uncertainty_score":0.57184196},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.2786726334383422,"score_gpt":0.4905551637432045,"score_spread":0.21188253030486232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176140770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031114907,0.000024708292,0.98888224,0.0011802928,0.00015944977,0.0002297563,0.006257812,0.00006822777,0.000086],"genre_scores_gemma":[0.028994637,0.00010741621,0.96832824,0.00016060444,0.00021463797,0.000012355369,0.0019906163,0.0000294815,0.00016200573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947536,0.00094341073,0.0010517992,0.0013424119,0.00092083437,0.0009879726],"domain_scores_gemma":[0.9794387,0.017515296,0.00049922976,0.0016866619,0.00029035792,0.00056973944],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.022131525,0.00033184155,0.00080501754,0.0004152286,0.00220436,0.0017132282,0.002965855,0.000090352914,0.0003677084],"category_scores_gemma":[0.04486051,0.00021211345,0.000068881025,0.0023075482,0.0010369389,0.0008288365,0.0023488987,0.0009167304,0.000012378194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019129095,0.00012442924,0.0011674655,0.000069603135,0.0009798575,0.000047157155,0.000690819,0.00038575358,0.001396394,0.76513696,0.009624267,0.22018602],"study_design_scores_gemma":[0.00036906553,0.00020001638,0.009489488,0.000018611241,0.0014639394,0.000032099426,0.0010295043,0.7648632,0.000010194782,0.22086231,0.0013907311,0.00027083326],"about_ca_topic_score_codex":0.00016406254,"about_ca_topic_score_gemma":0.00010289002,"teacher_disagreement_score":0.76447743,"about_ca_system_score_codex":0.000040383246,"about_ca_system_score_gemma":0.00047204454,"threshold_uncertainty_score":0.99932307},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.13471235951114346,"score_gpt":0.3734952579050034,"score_spread":0.2387828983938599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195567601","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18463096,0.0011471704,0.73879695,0.008207059,0.0004431681,0.00023337408,0.06628105,0.000039629977,0.00022063208],"genre_scores_gemma":[0.19340059,0.00055732095,0.77727866,0.0012749232,0.0006078321,0.0000038325134,0.026548702,0.000004265388,0.00032386297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954311,0.0004718402,0.00072329404,0.0016354144,0.0010233574,0.0007149424],"domain_scores_gemma":[0.9891897,0.007562738,0.00032714952,0.0017826769,0.000618469,0.0005192871],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008981525,0.0002530801,0.0006252759,0.000070988426,0.0022027094,0.0015089357,0.005208759,0.000071006616,0.0005189924],"category_scores_gemma":[0.020758884,0.0000923381,0.00006860676,0.0030922266,0.0010055215,0.0014245741,0.0048256093,0.00035278383,0.000011033176],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009905051,0.0005670072,0.018173665,0.000025683403,0.0026414304,0.0003384849,0.00015944244,0.00035028518,0.010843301,0.032055046,0.12990142,0.80484515],"study_design_scores_gemma":[0.00043421125,0.00019505814,0.18372898,0.00003164138,0.0040567657,0.0002472892,0.00230917,0.7490188,0.000063505526,0.0123742,0.047198094,0.0003423215],"about_ca_topic_score_codex":0.00023880381,"about_ca_topic_score_gemma":0.0008884701,"teacher_disagreement_score":0.80450284,"about_ca_system_score_codex":0.000016219621,"about_ca_system_score_gemma":0.00016177921,"threshold_uncertainty_score":0.9995276},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11421512759505388,"score_gpt":0.3767657191606953,"score_spread":0.2625505915656414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208584122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011967275,0.0005243613,0.99533975,0.0009812521,0.00012909019,0.000048967773,0.0016695552,0.0000074358195,0.00010288678],"genre_scores_gemma":[0.06981896,0.00020860002,0.9294482,0.00027579482,0.000066744884,0.0000010202932,0.0001599512,0.000004032351,0.00001673279],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759156,0.00015090198,0.00045808224,0.00082760473,0.00061022956,0.00036165467],"domain_scores_gemma":[0.99569994,0.00076252234,0.00022642608,0.0027822377,0.0003103498,0.00021852463],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0066537624,0.00012699275,0.0003590082,0.00019294865,0.00061883504,0.0009568013,0.0054740496,0.00003314498,0.0000085194715],"category_scores_gemma":[0.0012498514,0.000078168116,0.00004956126,0.0017806108,0.00042305022,0.0026241257,0.004622164,0.00018732384,2.9357813e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028275701,0.00010564874,0.00037469144,0.000041978394,0.0005754113,0.00006649732,0.0010139056,0.00037438277,0.0045834626,0.23281266,0.007316781,0.7527063],"study_design_scores_gemma":[0.00014474426,0.00003061146,0.0011921007,0.000021111717,0.00036802038,0.00010363193,0.00015704944,0.95978165,0.000077994475,0.037464816,0.0005448508,0.000113442606],"about_ca_topic_score_codex":0.000029823485,"about_ca_topic_score_gemma":0.000029767773,"teacher_disagreement_score":0.95940727,"about_ca_system_score_codex":0.000011212892,"about_ca_system_score_gemma":0.00043652116,"threshold_uncertainty_score":0.99990684},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval","score_opus":0.07724045282164911,"score_gpt":0.3726486626682964,"score_spread":0.2954082098466473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206662956","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009498989,0.00084717525,0.95917124,0.0005487679,0.005025131,0.00011609894,0.023300651,0.000035906825,0.010005118],"genre_scores_gemma":[0.030138563,0.039499514,0.3476554,0.0027144344,0.016147632,0.000020499789,0.53940976,0.00014387643,0.02427031],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976568,0.000095027055,0.00058004534,0.00039139393,0.00096910755,0.00030760936],"domain_scores_gemma":[0.9973861,0.00017796516,0.00018250413,0.0018461616,0.00019145751,0.00021579857],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038244054,0.00019000152,0.00035056463,0.00043561988,0.00075977953,0.0022990657,0.0026106164,0.00007897646,0.05425288],"category_scores_gemma":[0.00083842984,0.00012970368,0.000030964296,0.0011466059,0.00043568364,0.0033987586,0.0012213566,0.0005339399,0.0055979425],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001733122,0.0000046400573,0.000017596936,0.000020702475,0.00019542334,0.000001974795,0.00026977964,0.0013068387,0.000016273105,0.000007785901,0.94473845,0.053418804],"study_design_scores_gemma":[0.000065613815,0.000008788436,0.0022283902,0.000030167748,0.0007125619,0.000025933701,0.00087282894,0.4657682,9.87719e-7,0.00001286957,0.5301157,0.00015793214],"about_ca_topic_score_codex":0.000009215492,"about_ca_topic_score_gemma":0.00005776683,"teacher_disagreement_score":0.6115159,"about_ca_system_score_codex":0.00006378987,"about_ca_system_score_gemma":0.00028383711,"threshold_uncertainty_score":0.9987366},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","score_opus":0.08550868619541674,"score_gpt":0.3686068909417464,"score_spread":0.2830982047463297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210695710","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034834677,0.00033562363,0.961793,0.0011025432,0.0033474842,0.0001288262,0.024647705,0.00004459183,0.008251859],"genre_scores_gemma":[0.057772934,0.031272043,0.39304593,0.005940717,0.023616543,0.000024475647,0.47616473,0.00019288338,0.011969741],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772745,0.00007698203,0.00057625957,0.00038507502,0.00094664126,0.00028756942],"domain_scores_gemma":[0.99781966,0.0001555477,0.00019278271,0.00143486,0.00012030382,0.00027684504],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029038968,0.00019481989,0.00034664516,0.00037796592,0.00069559,0.0018701815,0.0030685049,0.00007039502,0.03379505],"category_scores_gemma":[0.0008327688,0.0001305705,0.000028458044,0.0010917794,0.00044577062,0.0034320415,0.0011765768,0.0005686318,0.01176779],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030640576,0.0000029613796,0.000013709044,0.000020767677,0.00016802883,0.000001235604,0.0003552857,0.0010897537,0.000013275621,0.000007894195,0.95162904,0.04669497],"study_design_scores_gemma":[0.000055938784,0.000011970932,0.0013407493,0.000015129848,0.00057287776,0.000010752869,0.00047687299,0.5013105,5.014188e-7,0.000013896498,0.49606323,0.00012753729],"about_ca_topic_score_codex":0.00000713483,"about_ca_topic_score_gemma":0.000026336347,"teacher_disagreement_score":0.5687471,"about_ca_system_score_codex":0.000053656273,"about_ca_system_score_gemma":0.00020645556,"threshold_uncertainty_score":0.99916595},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","score_opus":0.08550868619541674,"score_gpt":0.3686068909417464,"score_spread":0.2830982047463297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213289775","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034834677,0.00033562363,0.961793,0.0011025432,0.0033474842,0.0001288262,0.024647705,0.00004459183,0.008251859],"genre_scores_gemma":[0.057772934,0.031272043,0.39304593,0.005940717,0.023616543,0.000024475647,0.47616473,0.00019288338,0.011969741],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772745,0.00007698203,0.00057625957,0.00038507502,0.00094664126,0.00028756942],"domain_scores_gemma":[0.99781966,0.0001555477,0.00019278271,0.00143486,0.00012030382,0.00027684504],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029038968,0.00019481989,0.00034664516,0.00037796592,0.00069559,0.0018701815,0.0030685049,0.00007039502,0.03379505],"category_scores_gemma":[0.0008327688,0.0001305705,0.000028458044,0.0010917794,0.00044577062,0.0034320415,0.0011765768,0.0005686318,0.01176779],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030640576,0.0000029613796,0.000013709044,0.000020767677,0.00016802883,0.000001235604,0.0003552857,0.0010897537,0.000013275621,0.000007894195,0.95162904,0.04669497],"study_design_scores_gemma":[0.000055938784,0.000011970932,0.0013407493,0.000015129848,0.00057287776,0.000010752869,0.00047687299,0.5013105,5.014188e-7,0.000013896498,0.49606323,0.00012753729],"about_ca_topic_score_codex":0.00000713483,"about_ca_topic_score_gemma":0.000026336347,"teacher_disagreement_score":0.5687471,"about_ca_system_score_codex":0.000053656273,"about_ca_system_score_gemma":0.00020645556,"threshold_uncertainty_score":0.99916595},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Citation; Information retrieval; Data science; World Wide Web","score_opus":0.07724045282164911,"score_gpt":0.3726486626682964,"score_spread":0.2954082098466473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214902008","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009498989,0.00084717525,0.95917124,0.0005487679,0.005025131,0.00011609894,0.023300651,0.000035906825,0.010005118],"genre_scores_gemma":[0.030138563,0.039499514,0.3476554,0.0027144344,0.016147632,0.000020499789,0.53940976,0.00014387643,0.02427031],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976568,0.000095027055,0.00058004534,0.00039139393,0.00096910755,0.00030760936],"domain_scores_gemma":[0.9973861,0.00017796516,0.00018250413,0.0018461616,0.00019145751,0.00021579857],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038244054,0.00019000152,0.00035056463,0.00043561988,0.00075977953,0.0022990657,0.0026106164,0.00007897646,0.05425288],"category_scores_gemma":[0.00083842984,0.00012970368,0.000030964296,0.0011466059,0.00043568364,0.0033987586,0.0012213566,0.0005339399,0.0055979425],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001733122,0.0000046400573,0.000017596936,0.000020702475,0.00019542334,0.000001974795,0.00026977964,0.0013068387,0.000016273105,0.000007785901,0.94473845,0.053418804],"study_design_scores_gemma":[0.000065613815,0.000008788436,0.0022283902,0.000030167748,0.0007125619,0.000025933701,0.00087282894,0.4657682,9.87719e-7,0.00001286957,0.5301157,0.00015793214],"about_ca_topic_score_codex":0.000009215492,"about_ca_topic_score_gemma":0.00005776683,"teacher_disagreement_score":0.6115159,"about_ca_system_score_codex":0.00006378987,"about_ca_system_score_gemma":0.00028383711,"threshold_uncertainty_score":0.9987366},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04998375380142114,"score_gpt":0.37110303310567316,"score_spread":0.32111927930425205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231631488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04005169,0.000114921,0.95827645,0.00028578273,0.000008282562,0.00006949441,0.0011570225,0.0000022328925,0.00003414971],"genre_scores_gemma":[0.8999087,0.00029553066,0.09507871,0.000067500485,0.000037941954,0.0000020113362,0.004599843,0.0000025073236,0.0000072413036],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836606,0.000061848936,0.00037152023,0.0007285735,0.0003013888,0.00017061118],"domain_scores_gemma":[0.99714994,0.000025087604,0.0002455386,0.002402206,0.00008936419,0.0000878814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031600744,0.00008825453,0.00019411069,0.0003413763,0.0002034785,0.00011595878,0.0026867893,0.000043813183,0.000009733284],"category_scores_gemma":[0.00038916495,0.00006205279,0.000022195856,0.002041051,0.00022936094,0.00009190332,0.00097645744,0.00011669981,3.0502736e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105100626,0.00016678235,0.03295345,0.000006167884,0.0004759506,9.067872e-7,0.0000731061,0.0053046886,0.8409288,0.0006281099,0.0030240119,0.1163329],"study_design_scores_gemma":[0.00009782268,0.000034356206,0.07728657,0.0000034085604,0.00079351617,0.000008586549,0.00011849725,0.91866577,0.0021979422,0.00029410017,0.00041013886,0.0000893083],"about_ca_topic_score_codex":0.000056996676,"about_ca_topic_score_gemma":0.0001828307,"teacher_disagreement_score":0.9133611,"about_ca_system_score_codex":0.000014874263,"about_ca_system_score_gemma":0.00020221084,"threshold_uncertainty_score":0.49927676},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","score_opus":0.07162451266438453,"score_gpt":0.3683286561938265,"score_spread":0.29670414352944197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231764799","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009747503,0.00040719265,0.9526601,0.00042045946,0.006845149,0.0001803465,0.025473798,0.000037624126,0.013000574],"genre_scores_gemma":[0.08468768,0.032073908,0.29144934,0.003603202,0.019372493,0.000024701862,0.516661,0.00022119924,0.051906504],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997686,0.00007561005,0.0005684084,0.0003797703,0.0009719082,0.00031824713],"domain_scores_gemma":[0.99729663,0.00019143613,0.00020887851,0.0019725247,0.00014266938,0.00018786677],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041198162,0.0001968899,0.00035306445,0.000520993,0.00059793383,0.0018372155,0.0030996455,0.00008266781,0.04040167],"category_scores_gemma":[0.0005704757,0.00012940307,0.000028890627,0.0009026439,0.00040427325,0.003911602,0.0010922112,0.00052904146,0.021219252],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027475965,0.0000037066295,0.000030293098,0.000023946941,0.00016748499,5.3852165e-7,0.00024474235,0.0026543562,0.000011785908,0.00000830256,0.9549817,0.041870426],"study_design_scores_gemma":[0.00006819697,0.0000119394335,0.0024545486,0.000021989572,0.0004994433,0.000011963004,0.0004538442,0.5135813,4.1992337e-7,0.000011608514,0.48274252,0.000142217],"about_ca_topic_score_codex":0.000009407612,"about_ca_topic_score_gemma":0.000029669856,"teacher_disagreement_score":0.6612108,"about_ca_system_score_codex":0.00006559319,"about_ca_system_score_gemma":0.00022544056,"threshold_uncertainty_score":0.999199},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","score_opus":0.07753281751408107,"score_gpt":0.3766135914705343,"score_spread":0.2990807739564532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236215018","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012010336,0.0003013072,0.9564448,0.0003891815,0.0054504233,0.00013825623,0.023613784,0.00004305546,0.012418174],"genre_scores_gemma":[0.04737784,0.025595533,0.4506448,0.0032078547,0.034821857,0.000025864942,0.40841806,0.0001980355,0.029710144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768156,0.00007872543,0.0005798048,0.00038127755,0.0009517169,0.0003269061],"domain_scores_gemma":[0.9973494,0.00015238063,0.00020723276,0.001874884,0.00019418106,0.00022193807],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046353373,0.00019655863,0.00032031536,0.00051737775,0.000883456,0.0019507166,0.0032082547,0.00008216043,0.056499805],"category_scores_gemma":[0.0007409742,0.00012867684,0.000026373395,0.0009864349,0.00076073984,0.0037846034,0.0011493419,0.0004404324,0.015575249],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027881053,0.0000036389886,0.000016339916,0.000014839923,0.00015675485,6.01102e-7,0.00028871134,0.0003739985,0.000009104084,0.000005413903,0.9611536,0.037974212],"study_design_scores_gemma":[0.000060174993,0.000016169706,0.002011712,0.00002179505,0.0005986734,0.000015354313,0.00042286993,0.44757834,7.026019e-7,0.000021515758,0.54910845,0.00014421399],"about_ca_topic_score_codex":0.000009360851,"about_ca_topic_score_gemma":0.000053261232,"teacher_disagreement_score":0.5058,"about_ca_system_score_codex":0.00006262758,"about_ca_system_score_gemma":0.00020133196,"threshold_uncertainty_score":0.99908537},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","score_opus":0.08550868619541674,"score_gpt":0.3686068909417464,"score_spread":0.2830982047463297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239375881","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034834677,0.00033562363,0.961793,0.0011025432,0.0033474842,0.0001288262,0.024647705,0.00004459183,0.008251859],"genre_scores_gemma":[0.057772934,0.031272043,0.39304593,0.005940717,0.023616543,0.000024475647,0.47616473,0.00019288338,0.011969741],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772745,0.00007698203,0.00057625957,0.00038507502,0.00094664126,0.00028756942],"domain_scores_gemma":[0.99781966,0.0001555477,0.00019278271,0.00143486,0.00012030382,0.00027684504],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029038968,0.00019481989,0.00034664516,0.00037796592,0.00069559,0.0018701815,0.0030685049,0.00007039502,0.03379505],"category_scores_gemma":[0.0008327688,0.0001305705,0.000028458044,0.0010917794,0.00044577062,0.0034320415,0.0011765768,0.0005686318,0.01176779],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030640576,0.0000029613796,0.000013709044,0.000020767677,0.00016802883,0.000001235604,0.0003552857,0.0010897537,0.000013275621,0.000007894195,0.95162904,0.04669497],"study_design_scores_gemma":[0.000055938784,0.000011970932,0.0013407493,0.000015129848,0.00057287776,0.000010752869,0.00047687299,0.5013105,5.014188e-7,0.000013896498,0.49606323,0.00012753729],"about_ca_topic_score_codex":0.00000713483,"about_ca_topic_score_gemma":0.000026336347,"teacher_disagreement_score":0.5687471,"about_ca_system_score_codex":0.000053656273,"about_ca_system_score_gemma":0.00020645556,"threshold_uncertainty_score":0.99916595},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.15298434666212693,"score_gpt":0.3608533658037779,"score_spread":0.20786901914165098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240834168","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008458452,0.00019790088,0.983438,0.00043863445,0.000059460137,0.000113097885,0.007276137,0.000011207038,0.0000071029303],"genre_scores_gemma":[0.21086462,0.00014879965,0.7863024,0.00008775213,0.0000524308,0.0000027680696,0.002533975,0.0000038020062,0.0000034848356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745095,0.00018283394,0.00057162496,0.0008597904,0.0005532171,0.00038157127],"domain_scores_gemma":[0.9969312,0.0012331404,0.00022220294,0.0013052037,0.0001279588,0.00018028908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063297777,0.000150293,0.00030310758,0.00026486415,0.00090416765,0.0008220832,0.00147667,0.00001828518,0.0000072482685],"category_scores_gemma":[0.0058007156,0.0000956272,0.000012097444,0.0010770045,0.0004987154,0.0075720716,0.0017897761,0.00018752579,3.6575926e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003167095,0.00029009292,0.12412135,0.00009263062,0.00034020303,0.00011166885,0.0024217265,0.029179715,0.00040771696,0.6242599,0.0027974457,0.21566084],"study_design_scores_gemma":[0.00019056204,0.00004633636,0.07783312,0.000054150718,0.00006917073,0.000055428947,0.0006678676,0.9202632,0.0000028392226,0.00040649244,0.00025910957,0.00015175217],"about_ca_topic_score_codex":0.00040134697,"about_ca_topic_score_gemma":0.0007196285,"teacher_disagreement_score":0.8910835,"about_ca_system_score_codex":0.000028326014,"about_ca_system_score_gemma":0.0002481088,"threshold_uncertainty_score":0.7927367},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.048545103820620786,"score_gpt":0.3262234257958047,"score_spread":0.27767832197518394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244236454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019396246,0.0006601235,0.9379987,0.00013772775,0.0027844019,0.000102005164,0.05309363,0.000019185836,0.005010272],"genre_scores_gemma":[0.3835256,0.018189088,0.26624504,0.0010807142,0.004788039,0.000013007828,0.31574297,0.0001360515,0.010279471],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764454,0.00004136755,0.0007516591,0.00038411058,0.00082862016,0.00034969085],"domain_scores_gemma":[0.9970503,0.0002888144,0.00026099806,0.0020444952,0.00015378384,0.0002016012],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027628285,0.00021727575,0.00046853189,0.0004236654,0.0004450563,0.0015642245,0.003378693,0.00009011688,0.001485418],"category_scores_gemma":[0.00036194976,0.00013645095,0.00003111105,0.0011176572,0.00041044477,0.0026605388,0.0005372377,0.0005142207,0.0011850221],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054834672,0.000006620901,0.00034119558,0.00010058277,0.0005355849,0.0000048763823,0.00034789747,0.0066737337,0.0000053964095,0.00034428513,0.96200347,0.029630847],"study_design_scores_gemma":[0.00009982035,0.000016391932,0.004506537,0.000046972735,0.00088209845,0.000026550639,0.0007425482,0.36606458,6.984091e-7,0.000016384076,0.6273673,0.00023007975],"about_ca_topic_score_codex":0.0001285389,"about_ca_topic_score_gemma":0.00007463417,"teacher_disagreement_score":0.67175364,"about_ca_system_score_codex":0.00003145794,"about_ca_system_score_gemma":0.0002357862,"threshold_uncertainty_score":0.99959266},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","score_opus":0.07753281751408107,"score_gpt":0.3766135914705343,"score_spread":0.2990807739564532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244973481","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012010336,0.0003013072,0.9564448,0.0003891815,0.0054504233,0.00013825623,0.023613784,0.00004305546,0.012418174],"genre_scores_gemma":[0.04737784,0.025595533,0.4506448,0.0032078547,0.034821857,0.000025864942,0.40841806,0.0001980355,0.029710144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768156,0.00007872543,0.0005798048,0.00038127755,0.0009517169,0.0003269061],"domain_scores_gemma":[0.9973494,0.00015238063,0.00020723276,0.001874884,0.00019418106,0.00022193807],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046353373,0.00019655863,0.00032031536,0.00051737775,0.000883456,0.0019507166,0.0032082547,0.00008216043,0.056499805],"category_scores_gemma":[0.0007409742,0.00012867684,0.000026373395,0.0009864349,0.00076073984,0.0037846034,0.0011493419,0.0004404324,0.015575249],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027881053,0.0000036389886,0.000016339916,0.000014839923,0.00015675485,6.01102e-7,0.00028871134,0.0003739985,0.000009104084,0.000005413903,0.9611536,0.037974212],"study_design_scores_gemma":[0.000060174993,0.000016169706,0.002011712,0.00002179505,0.0005986734,0.000015354313,0.00042286993,0.44757834,7.026019e-7,0.000021515758,0.54910845,0.00014421399],"about_ca_topic_score_codex":0.000009360851,"about_ca_topic_score_gemma":0.000053261232,"teacher_disagreement_score":0.5058,"about_ca_system_score_codex":0.00006262758,"about_ca_system_score_gemma":0.00020133196,"threshold_uncertainty_score":0.99908537},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; World Wide Web; Data science","score_opus":0.07162451266438453,"score_gpt":0.3683286561938265,"score_spread":0.29670414352944197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245052885","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009747503,0.00040719265,0.9526601,0.00042045946,0.006845149,0.0001803465,0.025473798,0.000037624126,0.013000574],"genre_scores_gemma":[0.08468768,0.032073908,0.29144934,0.003603202,0.019372493,0.000024701862,0.516661,0.00022119924,0.051906504],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997686,0.00007561005,0.0005684084,0.0003797703,0.0009719082,0.00031824713],"domain_scores_gemma":[0.99729663,0.00019143613,0.00020887851,0.0019725247,0.00014266938,0.00018786677],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041198162,0.0001968899,0.00035306445,0.000520993,0.00059793383,0.0018372155,0.0030996455,0.00008266781,0.04040167],"category_scores_gemma":[0.0005704757,0.00012940307,0.000028890627,0.0009026439,0.00040427325,0.003911602,0.0010922112,0.00052904146,0.021219252],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027475965,0.0000037066295,0.000030293098,0.000023946941,0.00016748499,5.3852165e-7,0.00024474235,0.0026543562,0.000011785908,0.00000830256,0.9549817,0.041870426],"study_design_scores_gemma":[0.00006819697,0.0000119394335,0.0024545486,0.000021989572,0.0004994433,0.000011963004,0.0004538442,0.5135813,4.1992337e-7,0.000011608514,0.48274252,0.000142217],"about_ca_topic_score_codex":0.000009407612,"about_ca_topic_score_gemma":0.000029669856,"teacher_disagreement_score":0.6612108,"about_ca_system_score_codex":0.00006559319,"about_ca_system_score_gemma":0.00022544056,"threshold_uncertainty_score":0.999199},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","score_opus":0.07753281751408107,"score_gpt":0.3766135914705343,"score_spread":0.2990807739564532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245325236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012010336,0.0003013072,0.9564448,0.0003891815,0.0054504233,0.00013825623,0.023613784,0.00004305546,0.012418174],"genre_scores_gemma":[0.04737784,0.025595533,0.4506448,0.0032078547,0.034821857,0.000025864942,0.40841806,0.0001980355,0.029710144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768156,0.00007872543,0.0005798048,0.00038127755,0.0009517169,0.0003269061],"domain_scores_gemma":[0.9973494,0.00015238063,0.00020723276,0.001874884,0.00019418106,0.00022193807],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0046353373,0.00019655863,0.00032031536,0.00051737775,0.000883456,0.0019507166,0.0032082547,0.00008216043,0.056499805],"category_scores_gemma":[0.0007409742,0.00012867684,0.000026373395,0.0009864349,0.00076073984,0.0037846034,0.0011493419,0.0004404324,0.015575249],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027881053,0.0000036389886,0.000016339916,0.000014839923,0.00015675485,6.01102e-7,0.00028871134,0.0003739985,0.000009104084,0.000005413903,0.9611536,0.037974212],"study_design_scores_gemma":[0.000060174993,0.000016169706,0.002011712,0.00002179505,0.0005986734,0.000015354313,0.00042286993,0.44757834,7.026019e-7,0.000021515758,0.54910845,0.00014421399],"about_ca_topic_score_codex":0.000009360851,"about_ca_topic_score_gemma":0.000053261232,"teacher_disagreement_score":0.5058,"about_ca_system_score_codex":0.00006262758,"about_ca_system_score_gemma":0.00020133196,"threshold_uncertainty_score":0.99908537},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","score_opus":0.07724045282164911,"score_gpt":0.3726486626682964,"score_spread":0.2954082098466473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254812759","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009498989,0.00084717525,0.95917124,0.0005487679,0.005025131,0.00011609894,0.023300651,0.000035906825,0.010005118],"genre_scores_gemma":[0.030138563,0.039499514,0.3476554,0.0027144344,0.016147632,0.000020499789,0.53940976,0.00014387643,0.02427031],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976568,0.000095027055,0.00058004534,0.00039139393,0.00096910755,0.00030760936],"domain_scores_gemma":[0.9973861,0.00017796516,0.00018250413,0.0018461616,0.00019145751,0.00021579857],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0038244054,0.00019000152,0.00035056463,0.00043561988,0.00075977953,0.0022990657,0.0026106164,0.00007897646,0.05425288],"category_scores_gemma":[0.00083842984,0.00012970368,0.000030964296,0.0011466059,0.00043568364,0.0033987586,0.0012213566,0.0005339399,0.0055979425],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001733122,0.0000046400573,0.000017596936,0.000020702475,0.00019542334,0.000001974795,0.00026977964,0.0013068387,0.000016273105,0.000007785901,0.94473845,0.053418804],"study_design_scores_gemma":[0.000065613815,0.000008788436,0.0022283902,0.000030167748,0.0007125619,0.000025933701,0.00087282894,0.4657682,9.87719e-7,0.00001286957,0.5301157,0.00015793214],"about_ca_topic_score_codex":0.000009215492,"about_ca_topic_score_gemma":0.00005776683,"teacher_disagreement_score":0.6115159,"about_ca_system_score_codex":0.00006378987,"about_ca_system_score_gemma":0.00028383711,"threshold_uncertainty_score":0.9987366},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Citation; Data science; World Wide Web","score_opus":0.07162451266438453,"score_gpt":0.3683286561938265,"score_spread":0.29670414352944197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255653278","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009747503,0.00040719265,0.9526601,0.00042045946,0.006845149,0.0001803465,0.025473798,0.000037624126,0.013000574],"genre_scores_gemma":[0.08468768,0.032073908,0.29144934,0.003603202,0.019372493,0.000024701862,0.516661,0.00022119924,0.051906504],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997686,0.00007561005,0.0005684084,0.0003797703,0.0009719082,0.00031824713],"domain_scores_gemma":[0.99729663,0.00019143613,0.00020887851,0.0019725247,0.00014266938,0.00018786677],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0041198162,0.0001968899,0.00035306445,0.000520993,0.00059793383,0.0018372155,0.0030996455,0.00008266781,0.04040167],"category_scores_gemma":[0.0005704757,0.00012940307,0.000028890627,0.0009026439,0.00040427325,0.003911602,0.0010922112,0.00052904146,0.021219252],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027475965,0.0000037066295,0.000030293098,0.000023946941,0.00016748499,5.3852165e-7,0.00024474235,0.0026543562,0.000011785908,0.00000830256,0.9549817,0.041870426],"study_design_scores_gemma":[0.00006819697,0.0000119394335,0.0024545486,0.000021989572,0.0004994433,0.000011963004,0.0004538442,0.5135813,4.1992337e-7,0.000011608514,0.48274252,0.000142217],"about_ca_topic_score_codex":0.000009407612,"about_ca_topic_score_gemma":0.000029669856,"teacher_disagreement_score":0.6612108,"about_ca_system_score_codex":0.00006559319,"about_ca_system_score_gemma":0.00022544056,"threshold_uncertainty_score":0.999199},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0727690246232361,"score_gpt":0.38694199091094134,"score_spread":0.31417296628770525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392370559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01675037,0.0009966784,0.93660474,0.0018280143,0.00008803126,0.0005074354,0.043063577,0.00004811343,0.00011301993],"genre_scores_gemma":[0.7059674,0.00027342438,0.28662145,0.00029479095,0.00019678359,0.000020979945,0.0065359864,0.000019523643,0.00006965266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969112,0.00006540007,0.0005586228,0.00091518206,0.0010132886,0.0005362567],"domain_scores_gemma":[0.99537283,0.0018043579,0.00025431797,0.0015563814,0.000568408,0.00044372454],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032803377,0.00023783238,0.00048422956,0.0002732124,0.00072092394,0.0016125968,0.0017137503,0.00002891526,0.00008944123],"category_scores_gemma":[0.0038377258,0.00012282527,0.0000401392,0.0017805308,0.0014889144,0.004390135,0.0014710703,0.00030985137,0.0000054583347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0210323,0.0017244259,0.15347819,0.009048446,0.026946789,0.0057237386,0.015345705,0.0043520667,0.00013391284,0.010517534,0.26163873,0.49005815],"study_design_scores_gemma":[0.0009457997,0.00031895787,0.029718323,0.00044321478,0.0033328093,0.00089748285,0.0013579315,0.96021897,0.0000039113006,0.0005750611,0.0019397953,0.00024776504],"about_ca_topic_score_codex":0.000028282306,"about_ca_topic_score_gemma":0.00018774875,"teacher_disagreement_score":0.9558669,"about_ca_system_score_codex":0.00005052706,"about_ca_system_score_gemma":0.0014408325,"threshold_uncertainty_score":0.9994238},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3030961333940841,"score_gpt":0.48760745701371816,"score_spread":0.18451132361963407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394687825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060174778,0.010899931,0.820339,0.0047240597,0.000077738,0.0004925054,0.10326517,0.000018268518,0.0000085130105],"genre_scores_gemma":[0.97786903,0.00020311124,0.015755728,0.000087614455,0.00014496343,0.000007001783,0.0059155324,0.0000134305155,0.000003604025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970093,0.00011084957,0.0004589347,0.0010310684,0.0008426069,0.0005472386],"domain_scores_gemma":[0.9952319,0.0016072539,0.00009353108,0.0022324366,0.000090419904,0.000744412],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004112665,0.00019653104,0.0003972652,0.00034318122,0.0007929211,0.0011257621,0.002310713,0.000027406051,0.000032938085],"category_scores_gemma":[0.0014528739,0.000098738354,0.000041045474,0.0009446062,0.0011935434,0.0016338602,0.0032664337,0.00038908754,0.0000041534495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020265514,0.0010606324,0.3721925,0.00044480886,0.08522366,0.0020513104,0.0032278537,0.0022166027,0.00011721198,0.008621981,0.029556392,0.4932605],"study_design_scores_gemma":[0.00034236745,0.000054077023,0.09359394,0.0001301243,0.010856491,0.00003696411,0.00038053113,0.8939207,5.3199307e-7,0.00050582323,0.0000683413,0.00011010977],"about_ca_topic_score_codex":0.00011034279,"about_ca_topic_score_gemma":0.00017169405,"teacher_disagreement_score":0.9176942,"about_ca_system_score_codex":0.00003239545,"about_ca_system_score_gemma":0.0008881197,"threshold_uncertainty_score":0.9999112},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Stochastic dominance; Dominance (genetics); Econometrics; Statistics; Mathematics; Computer science; Economics; Mathematical optimization; Biology","score_opus":0.14582943694385603,"score_gpt":0.4572373035182113,"score_spread":0.31140786657435526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413289142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015072787,0.0002048321,0.97732174,0.0022815287,0.00021645929,0.00006689362,0.0046903966,0.0000068775194,0.00013847851],"genre_scores_gemma":[0.87983966,0.00027778637,0.1178821,0.00035755668,0.000087484164,0.0000016501856,0.0014162733,0.0000036086635,0.00013385773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99580467,0.0002226315,0.0009113569,0.0009977409,0.0016787658,0.00038481923],"domain_scores_gemma":[0.99151975,0.004557347,0.00050676905,0.0024639573,0.0007308873,0.00022129259],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.017363546,0.00015127892,0.00039269283,0.0005202839,0.002013274,0.0022496693,0.005821222,0.00003478034,0.00016493844],"category_scores_gemma":[0.022477955,0.00008494105,0.000039430535,0.005674806,0.0017255241,0.0024344376,0.0026808234,0.00027630114,0.000013354232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032122168,0.0002269856,0.20927307,0.000005665837,0.0010571302,0.000068195746,0.00085952895,0.015631648,0.0001840186,0.092156835,0.09351248,0.58670324],"study_design_scores_gemma":[0.00016643603,0.000019041736,0.18048581,0.000016362199,0.0005259099,0.00003495087,0.0007997002,0.79580075,0.0000029786424,0.019220771,0.002805837,0.00012145941],"about_ca_topic_score_codex":0.00011595843,"about_ca_topic_score_gemma":0.00018373772,"teacher_disagreement_score":0.8647669,"about_ca_system_score_codex":0.00003474141,"about_ca_system_score_gemma":0.00066521025,"threshold_uncertainty_score":0.99955773},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pairwise comparison; Computer science; Mathematics; Statistics; Algorithm; Artificial intelligence","score_opus":0.04648949380676017,"score_gpt":0.3791487152178348,"score_spread":0.3326592214110746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413868413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029547212,0.00019328036,0.9932385,0.0024217395,0.00011908504,0.00006803388,0.0009124978,0.000016657039,0.0000754581],"genre_scores_gemma":[0.30995727,0.00066616293,0.68683106,0.0019815257,0.00007216722,0.0000021605667,0.00039577883,0.0000061055275,0.00008779773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972861,0.00016938438,0.0004524258,0.0009880076,0.0007067956,0.00039733245],"domain_scores_gemma":[0.9959993,0.00097555574,0.00017129474,0.0023101617,0.00017471414,0.00036897874],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0062863394,0.00015627957,0.00031411782,0.0006007738,0.0013308467,0.0029940447,0.0062353816,0.000026441057,0.000021179732],"category_scores_gemma":[0.0050900863,0.00009822986,0.000022880296,0.0041172868,0.000591613,0.002804536,0.007018029,0.00022678432,0.0000050626027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010313763,0.00007526356,0.019544749,0.000032132994,0.0008339642,0.00012407312,0.0014606661,0.00027482666,0.00039918226,0.13777213,0.046008028,0.79337186],"study_design_scores_gemma":[0.0004174699,0.000056367033,0.019360388,0.00007451593,0.0006364189,0.00006855779,0.0006055891,0.96991086,0.000029190362,0.00407003,0.004545508,0.00022510023],"about_ca_topic_score_codex":0.000072193245,"about_ca_topic_score_gemma":0.00014673808,"teacher_disagreement_score":0.969636,"about_ca_system_score_codex":0.000022925593,"about_ca_system_score_gemma":0.00030509284,"threshold_uncertainty_score":0.9999693},"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"}]}