{"meta":{"query_hash":"9fdb53ddc261","filters":{"venue":"The Stata Journal Promoting communications on statistics and Stata"},"cohort_total":31,"direct_labels_cover":1,"predictions_cover":31,"exported":31,"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/9fdb53ddc261","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+Stata+Journal+Promoting+communications+on+statistics+and+Stata"},"results":[{"id":"W1492264985","doi":"10.1177/1536867x1201200106","title":"Respondent Driven Sampling","year":2010,"lang":"en","type":"preprint","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","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","funders":"","keywords":"Snowball sampling; Sampling (signal processing); Respondent; Markov chain; Population; Markov chain Monte Carlo; Statistics; Sampling design; Computer science; Psychology; Econometrics; Demography; Mathematics; Sociology; Monte Carlo method; Telecommunications; Political science","score_opus":0.16081939269678264,"score_gpt":0.43949658983801854,"score_spread":0.2786771971412359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492264985","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":[0.4717604,0.010329262,0.39673442,0.06956417,0.0028887256,0.007161187,0.030547082,0.0005450895,0.010469678],"genre_scores_gemma":[0.6398749,0.012892529,0.34357473,0.0005910533,0.0003822734,0.000055194654,0.0016525441,0.00017570579,0.0008010709],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99635375,0.0007476635,0.0011232642,0.00047055376,0.0007870792,0.0005177216],"domain_scores_gemma":[0.99072593,0.002629424,0.0010365064,0.004475637,0.0006961462,0.0004363714],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028801777,0.0004578268,0.0006742134,0.0003027176,0.0016220127,0.00063323136,0.0021335848,0.00024413991,0.00008290919],"category_scores_gemma":[0.002776262,0.00033491792,0.000101466525,0.00017654705,0.00063186244,0.000081256745,0.0031132498,0.007323102,0.00003906292],"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":[0.0015951926,0.0030531732,0.0030082217,0.0017329341,0.0031032981,0.00045317167,0.12644045,0.00084131677,0.004274883,0.079928786,0.037052043,0.7385165],"study_design_scores_gemma":[0.0091514215,0.0045183557,0.025669206,0.010729082,0.0061309393,0.005188991,0.05319082,0.29522708,0.00036670387,0.34588978,0.23984474,0.0040928945],"about_ca_topic_score_codex":0.00010350657,"about_ca_topic_score_gemma":0.00018045926,"teacher_disagreement_score":0.73442364,"about_ca_system_score_codex":0.00014229654,"about_ca_system_score_gemma":0.00073768245,"threshold_uncertainty_score":0.9999103},"labels":[],"label_agreement":null},{"id":"W1508161314","doi":"10.1177/1536867x0800800406","title":"A Shortcut through Long Loops: An Illustration of Two Alternatives to Looping over Observations","year":2008,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Big Data Technologies and Applications","field":"Decision Sciences","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":"Traffic Injury Research Foundation","funders":"","keywords":"Computer science; Search engine indexing; Key (lock); Mathematical optimization; Identifier; Data mining; Operations research; Information retrieval; Mathematics","score_opus":0.5569936812276851,"score_gpt":0.48027112868617966,"score_spread":0.07672255254150545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1508161314","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":[0.33965778,0.0002520564,0.65078145,0.0061392356,0.000063902036,0.000461139,0.0023045356,0.000039786384,0.00030009888],"genre_scores_gemma":[0.8022426,0.0015622058,0.19558756,0.00028057137,0.000035796118,0.000023452792,0.00014804726,0.000016992002,0.0001028154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970868,0.00042476528,0.0010571802,0.00033850173,0.00082344323,0.0002693041],"domain_scores_gemma":[0.9933288,0.0023273078,0.0007381004,0.002727944,0.0007450552,0.0001327731],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021836427,0.00018051174,0.00028441174,0.00018565348,0.0019794423,0.00038146417,0.0030186158,0.00004255505,0.00003980142],"category_scores_gemma":[0.0025065783,0.00012383042,0.000042474814,0.0007911866,0.000667194,0.0007186542,0.0008382631,0.0005437444,0.000010993668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006175563,0.0007577156,0.012813098,0.000017612785,0.0001393008,0.000015356112,0.017349865,0.0011771343,0.0014686384,0.77585655,0.013303757,0.17703918],"study_design_scores_gemma":[0.0016130253,0.0013978274,0.13961276,0.00033879813,0.00013761253,0.0004509469,0.013006908,0.10678811,0.00082372513,0.6995824,0.035350084,0.00089781266],"about_ca_topic_score_codex":0.00019468134,"about_ca_topic_score_gemma":0.0004192762,"teacher_disagreement_score":0.4625848,"about_ca_system_score_codex":0.000039874583,"about_ca_system_score_gemma":0.00014371234,"threshold_uncertainty_score":0.99931985},"labels":[],"label_agreement":null},{"id":"W1510648344","doi":"10.1177/1536867x1201200205","title":"Faster Estimation of a Discrete-Time Proportional Hazards Model with Gamma Frailty","year":2012,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Hessian matrix; Matrix (chemical analysis); Function (biology); Expression (computer science); Applied mathematics; Point (geometry); Algorithm; Gradient descent; Mathematics; Computer science; Mathematical optimization; Artificial intelligence; Geometry","score_opus":0.1220249435470352,"score_gpt":0.4053798658805197,"score_spread":0.2833549223334845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510648344","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":[0.021987166,0.00010924569,0.9739979,0.000938116,0.000025598423,0.000336874,0.0016309404,0.000019924839,0.00095427176],"genre_scores_gemma":[0.409324,0.00006455744,0.59036,0.000036392477,0.000018410989,0.000013092745,0.000050330138,0.000021960215,0.00011128985],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978246,0.0004658676,0.00070928974,0.00014528443,0.0005184564,0.00033650183],"domain_scores_gemma":[0.9949519,0.0028280644,0.0006695907,0.0010131714,0.00035182567,0.00018543942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022366014,0.00020616209,0.00032365555,0.00007968511,0.0006255211,0.00012312057,0.0006061138,0.00004327967,0.00008276314],"category_scores_gemma":[0.0021831184,0.00012423788,0.00003306596,0.00014386192,0.00050345116,0.00021770355,0.0002655669,0.00056152645,0.000006123237],"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":[0.00013413126,0.00051493786,0.0003206537,0.00015017108,0.00015149574,0.000001980051,0.004371083,0.00036612022,0.00017222755,0.91258514,0.0019885795,0.07924347],"study_design_scores_gemma":[0.0004266139,0.0003395643,0.001146336,0.00022949265,0.00014643482,0.00007830376,0.00029397517,0.5847801,0.00006950057,0.41212663,0.00016250469,0.0002005332],"about_ca_topic_score_codex":0.000009633559,"about_ca_topic_score_gemma":0.000005039883,"teacher_disagreement_score":0.584414,"about_ca_system_score_codex":0.000038430484,"about_ca_system_score_gemma":0.00015916681,"threshold_uncertainty_score":0.5066274},"labels":[],"label_agreement":null},{"id":"W1512757258","doi":"10.1177/1536867x0600600108","title":"Mata Matters: Creating New Variables—sounds Boring, isn't","year":2006,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Column (typography); Quarter (Canadian coin); Focus (optics); Computer science; Programming language; History; Telecommunications; Archaeology","score_opus":0.11892473209141323,"score_gpt":0.38693771596634147,"score_spread":0.2680129838749282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512757258","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":[0.017022114,0.0013665671,0.95023847,0.016437719,0.00031511614,0.00038427196,0.0011579639,0.000089694986,0.012988077],"genre_scores_gemma":[0.6939763,0.0019000772,0.29580283,0.001175261,0.00029156372,0.0000118079915,0.00032247373,0.000076255405,0.006443463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99595994,0.00072067126,0.0013289052,0.000378406,0.0011787532,0.00043332574],"domain_scores_gemma":[0.9913366,0.004746426,0.0009525277,0.0022517468,0.00051632774,0.00019636459],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006576093,0.0002455064,0.0003220567,0.0002871503,0.0022754916,0.0023263085,0.0023467364,0.00005595526,0.00021193965],"category_scores_gemma":[0.0018303577,0.00016616599,0.000066478264,0.00060787634,0.00028776703,0.0004141391,0.0005504918,0.0007509094,0.000062643565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011287697,0.0004719651,0.005396418,0.00003787539,0.00013613589,0.00002630375,0.00745357,0.0032112205,0.00031402693,0.4549858,0.3217094,0.2061444],"study_design_scores_gemma":[0.00093232107,0.00024850905,0.00557558,0.0002233343,0.00012549857,0.00023825337,0.004352252,0.21392313,0.000015034595,0.68072,0.0932146,0.00043151915],"about_ca_topic_score_codex":0.0007693754,"about_ca_topic_score_gemma":0.00022825591,"teacher_disagreement_score":0.67695415,"about_ca_system_score_codex":0.000048009344,"about_ca_system_score_gemma":0.00017655111,"threshold_uncertainty_score":0.99902344},"labels":[],"label_agreement":null},{"id":"W1519629121","doi":"10.1177/1536867x0600600308","title":"Mata Matters: Interactive use","year":2006,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":1,"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":"Column (typography); Computer science; Quarter (Canadian coin); Matrix (chemical analysis); Programming language; History; Archaeology; Telecommunications","score_opus":0.14966491674917273,"score_gpt":0.4148212657270012,"score_spread":0.26515634897782847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1519629121","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":[0.037264325,0.00047296713,0.91543436,0.03322833,0.00019100211,0.0013928595,0.008846285,0.00013869972,0.00303117],"genre_scores_gemma":[0.5602168,0.0008648119,0.43678832,0.00063072285,0.000090241345,0.00003833883,0.00026672622,0.00007454553,0.0010294957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971019,0.00093919213,0.00072894996,0.0002484702,0.00053118996,0.00045027686],"domain_scores_gemma":[0.9841202,0.013290898,0.000351437,0.0016858191,0.00039063074,0.00016104654],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0022952054,0.00022234018,0.00028840377,0.000115564544,0.001379968,0.00091542106,0.0012958877,0.000047693215,0.000104941224],"category_scores_gemma":[0.0044878144,0.00015423943,0.000046170047,0.00018940911,0.0006454626,0.0003520157,0.00074137165,0.0012229625,0.000031032687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010880183,0.0005053935,0.0002863603,0.000087849075,0.00007371087,0.00002826669,0.0012829747,0.000005303439,0.000054369688,0.9241446,0.054129858,0.019292502],"study_design_scores_gemma":[0.0004716656,0.00022110806,0.0023467871,0.00017525358,0.000064283806,0.00014166308,0.0005371607,0.012710601,0.000024139794,0.968564,0.014523716,0.00021966778],"about_ca_topic_score_codex":0.0002556878,"about_ca_topic_score_gemma":0.00024721684,"teacher_disagreement_score":0.5229525,"about_ca_system_score_codex":0.000105180945,"about_ca_system_score_gemma":0.00010660338,"threshold_uncertainty_score":0.99992007},"labels":[],"label_agreement":null},{"id":"W1525417239","doi":"10.1177/1536867x1501500111","title":"Estimating Net Survival using a Life-Table Approach","year":2015,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":33,"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":"Estimator; Statistics; Weighting; Survival analysis; Estimation; Inverse probability weighting; Relative survival; Table (database); Kaplan–Meier estimator; Biometrics; Life table; Mathematics; Computer science; Econometrics; Cancer registry; Medicine; Data mining; Cancer; Artificial intelligence; Population; Engineering","score_opus":0.15841872955145572,"score_gpt":0.37147357368830547,"score_spread":0.21305484413684975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525417239","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":[0.105272405,0.0017457874,0.8853974,0.001827118,0.00034891872,0.000548761,0.00036849096,0.00008825334,0.004402908],"genre_scores_gemma":[0.6394992,0.000119049364,0.35992888,0.00012948399,0.0001394955,0.000007094584,0.000075264914,0.000026993832,0.00007452405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983483,0.00036817166,0.00042772622,0.00017965047,0.0004034912,0.0002726709],"domain_scores_gemma":[0.99757725,0.0004960657,0.0003166268,0.000889728,0.00038175692,0.00033854888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021326784,0.00015855684,0.00026868485,0.00009865644,0.0009972048,0.00027051877,0.00038274963,0.00003992826,0.0000073741508],"category_scores_gemma":[0.0016446457,0.000115046474,0.00002907995,0.00025952124,0.0001689383,0.00012657238,0.00029073755,0.0008058895,0.000003123879],"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":[0.016264552,0.0050740317,0.02671887,0.0016035951,0.0032162147,0.00024789348,0.07559291,0.04578732,0.0014221751,0.09654212,0.04736504,0.6801653],"study_design_scores_gemma":[0.0012837268,0.0012310818,0.0010148938,0.00017277047,0.00017710651,0.00061631197,0.0022194658,0.9863201,0.000009537065,0.004636948,0.0021435232,0.00017454963],"about_ca_topic_score_codex":0.00032911453,"about_ca_topic_score_gemma":0.000021247417,"teacher_disagreement_score":0.94053274,"about_ca_system_score_codex":0.00011358585,"about_ca_system_score_gemma":0.00042431414,"threshold_uncertainty_score":0.7669794},"labels":[],"label_agreement":null},{"id":"W15433897","doi":"10.1177/1536867x1401400310","title":"Csvconvert: A Simple Command to Gather Comma-Separated Value Files into Stata","year":2014,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Variable (mathematics); Value (mathematics); Quarter (Canadian coin); Computer science; Simple (philosophy); Data file; Database; Arithmetic; Mathematics; Geography","score_opus":0.09890068580412437,"score_gpt":0.4163357268686034,"score_spread":0.317435041064479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W15433897","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":[0.039604567,0.00035724317,0.9339144,0.016067194,0.00012246174,0.0016371924,0.004889194,0.00013237278,0.0032753493],"genre_scores_gemma":[0.688404,0.00071939896,0.3087695,0.0010332862,0.000077006516,0.00007456317,0.00036209435,0.000102073995,0.00045802497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948403,0.0022224158,0.0010358557,0.00039985086,0.00079256843,0.0007089746],"domain_scores_gemma":[0.9812312,0.014452236,0.00037540885,0.0028054074,0.00057878386,0.00055697653],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0057794065,0.0003660789,0.0005539134,0.0001747995,0.002441307,0.0007062223,0.0023772859,0.000085014086,0.00020046723],"category_scores_gemma":[0.011755815,0.00026429928,0.0000645517,0.00039113857,0.0007521101,0.00018501953,0.0013483588,0.0014125232,0.00008086508],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020223699,0.0005648634,0.00020968461,0.00021164633,0.00016768835,0.000011024894,0.007833977,0.00004912116,0.00011293772,0.8793288,0.050381564,0.06092648],"study_design_scores_gemma":[0.00080165616,0.0007496619,0.00056396873,0.00018182668,0.00008105917,0.000048145706,0.0006782048,0.08748529,0.000045143035,0.8581472,0.050863624,0.0003541899],"about_ca_topic_score_codex":0.0003067268,"about_ca_topic_score_gemma":0.0005586217,"teacher_disagreement_score":0.6487995,"about_ca_system_score_codex":0.00013014064,"about_ca_system_score_gemma":0.00019896969,"threshold_uncertainty_score":0.9999809},"labels":[],"label_agreement":null},{"id":"W1552664769","doi":"10.1177/1536867x1201200206","title":"Threshold Regression for Time-to-Event Analysis: The Stthreg Package","year":2012,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Centers for Disease Control and Prevention","keywords":"Regression analysis; Proportional hazards model; Computer science; Event (particle physics); Regression; R package; Path (computing); Statistics; Data mining; Mathematics; Machine learning; Programming language","score_opus":0.14130158352464145,"score_gpt":0.43492133618432316,"score_spread":0.2936197526596817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1552664769","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":[0.0050984146,0.0008096698,0.98243576,0.00716218,0.0001025773,0.00092128466,0.002542551,0.00003439945,0.00089317403],"genre_scores_gemma":[0.28212157,0.000506649,0.71556395,0.00056967745,0.00014407639,0.00010016803,0.00010393087,0.000057034456,0.00083292613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737567,0.0007825071,0.0007129174,0.00019669846,0.00042218628,0.0005100436],"domain_scores_gemma":[0.986405,0.01054506,0.0005038035,0.0019431745,0.0003189902,0.0002839517],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0053984877,0.00024463053,0.0003949827,0.00012877246,0.0018855983,0.00031343175,0.0013644556,0.00004751459,0.00015715025],"category_scores_gemma":[0.004215912,0.00012660767,0.00009922787,0.00041778016,0.0002701461,0.0001047351,0.00054867304,0.00065790955,0.000030824584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113532944,0.00050722604,0.0002913969,0.00007563176,0.0008271782,0.0000018146111,0.007307668,0.00001537226,0.00017188348,0.83737224,0.04054597,0.11277007],"study_design_scores_gemma":[0.00085139135,0.000748914,0.0050256797,0.00037959724,0.0024568061,0.0000544937,0.0020515078,0.09470639,0.00009611926,0.861614,0.031403676,0.00061142154],"about_ca_topic_score_codex":0.000009776473,"about_ca_topic_score_gemma":0.000011600384,"teacher_disagreement_score":0.27702317,"about_ca_system_score_codex":0.000045476387,"about_ca_system_score_gemma":0.000059463164,"threshold_uncertainty_score":0.9994138},"labels":[],"label_agreement":null},{"id":"W1566635326","doi":"10.1177/1536867x0900900202","title":"Updated Tests for Small-study Effects in Meta-analyses","year":2009,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":323,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"","keywords":"Funnel plot; Publication bias; Statistics; Meta-analysis; Test (biology); Statistical hypothesis testing; Mathematics; Econometrics; Medicine; Confidence interval; Internal medicine","score_opus":0.8746962574195007,"score_gpt":0.6167479719745995,"score_spread":0.2579482854449012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566635326","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":[0.14217782,0.009732588,0.8111012,0.023166511,0.00026973392,0.009112092,0.00223067,0.000029124147,0.0021802785],"genre_scores_gemma":[0.88311255,0.00018760585,0.11542454,0.00046476835,0.000024310228,0.00006534654,0.00007464836,0.000017418455,0.0006288171],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97655207,0.0145579865,0.0060615884,0.00058266753,0.001883211,0.00036250456],"domain_scores_gemma":[0.9637128,0.024622945,0.003930758,0.0063010976,0.0012525981,0.00017978945],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09170786,0.0003622728,0.0025899226,0.00047267167,0.0011218892,0.0020289107,0.0043607564,0.00004015696,0.0002402187],"category_scores_gemma":[0.04480632,0.00015428383,0.00056284963,0.0010929609,0.0001226602,0.00018645471,0.00032294716,0.0006028352,0.00005261872],"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":[0.00025847257,0.006402273,0.012040664,0.00017477639,0.015848996,0.00011992185,0.026336659,0.0017784642,0.00040609698,0.16031747,0.19722682,0.5790894],"study_design_scores_gemma":[0.0031107112,0.0032815076,0.074916996,0.00014512318,0.015420861,0.0001623025,0.007763327,0.22532864,0.00002561226,0.62696713,0.041883312,0.0009944753],"about_ca_topic_score_codex":0.000031794287,"about_ca_topic_score_gemma":0.00032123845,"teacher_disagreement_score":0.7409347,"about_ca_system_score_codex":0.000037013204,"about_ca_system_score_gemma":0.000091308335,"threshold_uncertainty_score":0.9990071},"labels":[],"label_agreement":null},{"id":"W2117460710","doi":"10.1177/1536867x0500500408","title":"Speaking Stata: Smoothing in Various Directions","year":2005,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":25,"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":"Smoothing; Bivariate analysis; Diagonal; Mathematics; Computer science; Econometrics; Applied mathematics; Statistics; Geometry","score_opus":0.028361773997640217,"score_gpt":0.29546263712144155,"score_spread":0.2671008631238013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117460710","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":[0.2383749,0.0043168347,0.6702838,0.03448442,0.0009178404,0.0023367023,0.0037456816,0.00028585622,0.04525398],"genre_scores_gemma":[0.8295948,0.0035475383,0.16600253,0.00047544835,0.0000670828,0.000017151928,0.00007199254,0.00004001874,0.00018344111],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979139,0.00036962872,0.000620562,0.0002682377,0.00037961683,0.00044807012],"domain_scores_gemma":[0.99719334,0.0012477286,0.00033911946,0.0010163947,0.000045773035,0.00015766756],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001846708,0.00020549593,0.00021218645,0.00011265025,0.0015882736,0.0003902349,0.0009573366,0.000038242826,0.00019025445],"category_scores_gemma":[0.00064622017,0.00016456613,0.000028215884,0.00033059221,0.0003706011,0.0003063122,0.00078693294,0.0009511759,0.00006081306],"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":[0.000036046295,0.0004304861,0.0062093255,0.00002178085,0.00006388473,0.0000387765,0.017134167,0.0025152173,0.00017590764,0.032182574,0.007621987,0.93356985],"study_design_scores_gemma":[0.0020426612,0.0004319138,0.070403896,0.00042753472,0.00014348996,0.000538606,0.0058078743,0.3438374,0.00003733099,0.08770551,0.48754883,0.0010749388],"about_ca_topic_score_codex":0.0014569355,"about_ca_topic_score_gemma":0.0046431883,"teacher_disagreement_score":0.9324949,"about_ca_system_score_codex":0.00022643131,"about_ca_system_score_gemma":0.000048700193,"threshold_uncertainty_score":0.9997115},"labels":[],"label_agreement":null},{"id":"W2154012562","doi":"10.1177/1536867x0600600407","title":"Mata Matters: Precision","year":2006,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":8,"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":"Column (typography); Computer science; Point (geometry); Programming language; Base (topology); Quarter (Canadian coin); Matrix (chemical analysis); High-level programming language; Arithmetic; Programming paradigm; Mathematics; History; Telecommunications; Geometry","score_opus":0.20005001148871415,"score_gpt":0.44107089794795445,"score_spread":0.2410208864592403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154012562","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":[0.009058677,0.0010159067,0.9583973,0.022861656,0.0006742434,0.000769155,0.0037575983,0.00014213026,0.0033233326],"genre_scores_gemma":[0.05870896,0.0015991688,0.9368097,0.0006458158,0.00014075497,0.000028414217,0.000253363,0.00006417366,0.0017496353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737245,0.0009397231,0.0007451305,0.00021860628,0.00038894254,0.00033514653],"domain_scores_gemma":[0.98765326,0.009741194,0.0005571131,0.0016466397,0.0002949695,0.00010682809],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029657038,0.00022187862,0.00027429592,0.00013726772,0.0013120521,0.00047741752,0.001202716,0.000048464517,0.00011539962],"category_scores_gemma":[0.0030171394,0.00015329517,0.00003981548,0.00017994813,0.0003775512,0.00012063372,0.0004391979,0.0006653617,0.00003147828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003629378,0.00027810418,0.00018426351,0.000058094978,0.000041032858,0.0000069534813,0.0014646988,0.0000065243366,0.00008000005,0.6551277,0.30548438,0.037231952],"study_design_scores_gemma":[0.000435062,0.00013359622,0.0018281896,0.00013335151,0.0000874674,0.0001881107,0.0012705395,0.0027914627,0.00005786088,0.9318357,0.06101059,0.00022804661],"about_ca_topic_score_codex":0.000066569286,"about_ca_topic_score_gemma":0.00005230536,"teacher_disagreement_score":0.27670804,"about_ca_system_score_codex":0.000060467475,"about_ca_system_score_gemma":0.00010454695,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W2585958134","doi":"10.1177/1536867x1601600407","title":"Support Vector Machines","year":2016,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":218,"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":"Categorical variable; Support vector machine; Multinomial distribution; Computer science; Multinomial logistic regression; Artificial intelligence; Binary classification; Statistical learning; Relevance vector machine; Machine learning; Binary number; Data mining; Mathematics; Statistics; Arithmetic","score_opus":0.03801075982839052,"score_gpt":0.30926332236989607,"score_spread":0.27125256254150554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2585958134","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":[0.004316144,0.0002493501,0.9624788,0.030663496,0.00021332485,0.00019727933,0.0006857838,0.00006978323,0.0011260019],"genre_scores_gemma":[0.7529537,0.0044042035,0.24079266,0.0008626495,0.000075006996,0.000019282445,0.000050660714,0.000026992828,0.0008148155],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99864453,0.00032824653,0.00034420955,0.0001766106,0.00026663943,0.00023976223],"domain_scores_gemma":[0.99685425,0.0012187435,0.00024526496,0.0013696264,0.000181441,0.0001306829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009921005,0.00012881223,0.00012963855,0.0000783691,0.0010204612,0.000386097,0.0017807358,0.000024963865,0.00006362639],"category_scores_gemma":[0.00039014075,0.00006634058,0.00002636493,0.00012755251,0.00016909988,0.0003687345,0.0006743449,0.0002966243,0.00006855529],"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":[0.000018545965,0.00013688808,0.00021028012,0.000013840644,0.000044585242,0.000014002255,0.001903348,0.0000015043539,0.0011970074,0.14915602,0.032113507,0.8151905],"study_design_scores_gemma":[0.0038058222,0.0020642064,0.0109506,0.0011017277,0.00012009408,0.0012952669,0.0007079629,0.093483105,0.0014436296,0.61666554,0.26700878,0.0013532323],"about_ca_topic_score_codex":0.000012977706,"about_ca_topic_score_gemma":0.000013652911,"teacher_disagreement_score":0.81383723,"about_ca_system_score_codex":0.000024155139,"about_ca_system_score_gemma":0.00008071874,"threshold_uncertainty_score":0.7848666},"labels":[],"label_agreement":null},{"id":"W2606619291","doi":"10.1177/1536867x1701700111","title":"Biasplot: A Package to Effective Plots to Assess Bias and Precision in Method Comparison Studies","year":2017,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Plot (graphics); Statistics; Computer science; Accuracy and precision; Data mining; Scatter plot; Mathematics","score_opus":0.6425845793989605,"score_gpt":0.5792506941073572,"score_spread":0.06333388529160333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606619291","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":[0.5223638,0.0011364118,0.44999245,0.02234395,0.00035695065,0.0023215166,0.0008434519,0.000028391045,0.0006130842],"genre_scores_gemma":[0.8300692,0.0006537357,0.16893739,0.00019304384,0.000025015761,0.000046765254,0.000004582099,0.000014833595,0.000055455614],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99409956,0.0028085231,0.0010820801,0.00045209928,0.0012265107,0.00033124723],"domain_scores_gemma":[0.9796349,0.015700003,0.0007480275,0.0028999741,0.00076313945,0.0002539813],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.026647221,0.00022128438,0.0005333433,0.00029041362,0.0029311785,0.0018429703,0.0027248752,0.00003660729,0.000006908124],"category_scores_gemma":[0.03660919,0.00013347526,0.000036129008,0.00029474712,0.0003013283,0.0002950076,0.0022109603,0.0006609109,0.000024400506],"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":[0.00027375025,0.00044503552,0.024652958,0.000050181756,0.00014107865,0.000015234707,0.03486708,0.00049314974,0.00039569798,0.01731669,0.008134353,0.9132148],"study_design_scores_gemma":[0.0025626791,0.0033725563,0.619732,0.0022483554,0.00018245967,0.00007171032,0.05088929,0.07113797,0.0005865076,0.2258365,0.022459533,0.0009204246],"about_ca_topic_score_codex":0.00012077231,"about_ca_topic_score_gemma":0.0007499783,"teacher_disagreement_score":0.9122944,"about_ca_system_score_codex":0.00012491288,"about_ca_system_score_gemma":0.000060482238,"threshold_uncertainty_score":0.9991932},"labels":[],"label_agreement":null},{"id":"W2788623952","doi":"10.1177/1536867x1801700406","title":"Text Mining with n-gram Variables","year":2017,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"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":"Social Sciences and Humanities Research Council of Canada; Universiteit van Tilburg; University of Waterloo","keywords":"n-gram; Computer science; Gram; Categorization; Process (computing); Text categorization; Natural language processing; Sequence (biology); Artificial intelligence; Language model; Programming language","score_opus":0.046007961283892104,"score_gpt":0.321158498507218,"score_spread":0.2751505372233259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788623952","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":[0.0019780514,0.00020123573,0.98471105,0.009860522,0.000070089605,0.00020163604,0.00060784334,0.000048321268,0.0023212745],"genre_scores_gemma":[0.22028255,0.00085896754,0.77836245,0.00016566413,0.000039879553,0.000020421623,0.000048892554,0.00001857632,0.00020260493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865824,0.00016170264,0.00033384454,0.00025857397,0.0002936679,0.00029399229],"domain_scores_gemma":[0.99394876,0.0009198689,0.0005760848,0.0041888608,0.000218263,0.0001481651],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013404243,0.00016530583,0.00017288288,0.00006359065,0.005596771,0.0029721204,0.005000227,0.000025636233,0.0000064414166],"category_scores_gemma":[0.0004306071,0.00010706653,0.000018042088,0.00011254777,0.0004475929,0.00056604337,0.0014004402,0.00049594097,0.000009972704],"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":[0.000009271261,0.00015663389,0.0003255789,0.000013530531,0.00008170773,0.0000143046,0.0025412033,0.000022046015,0.000023099386,0.43896407,0.0059482413,0.5519003],"study_design_scores_gemma":[0.0014148591,0.00084404927,0.013275681,0.0004991471,0.0001186916,0.00078204734,0.0013663943,0.8058097,0.000044009186,0.08010905,0.095012024,0.0007243751],"about_ca_topic_score_codex":0.00009771233,"about_ca_topic_score_gemma":0.00005165714,"teacher_disagreement_score":0.8057876,"about_ca_system_score_codex":0.000023145809,"about_ca_system_score_gemma":0.00013829318,"threshold_uncertainty_score":0.9980629},"labels":[],"label_agreement":null},{"id":"W2810242367","doi":"10.1177/1536867x1801800109","title":"Fitting and Interpreting Correlated Random-coefficient Models Using Stata","year":2018,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Estimator; Interpretation (philosophy); Random effects model; Estimation; Econometrics; Statistics; Computer science; Sample (material); Mathematics; Panel data; Economics","score_opus":0.09588883221840087,"score_gpt":0.2989027927085462,"score_spread":0.2030139604901453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810242367","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":[0.0909538,0.0033570922,0.8990952,0.0012540021,0.00020027506,0.00031251647,0.003413536,0.000031063562,0.0013825312],"genre_scores_gemma":[0.9618416,0.0024646583,0.035147022,0.00023317646,0.000060686212,0.0000042595066,0.00015052973,0.000033237207,0.000064841726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799037,0.00022340368,0.0009942313,0.00032913074,0.00010463252,0.0003582253],"domain_scores_gemma":[0.996666,0.0010267695,0.0008665941,0.0010972514,0.00019170418,0.00015164177],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0027413373,0.00021204507,0.00040391376,0.00021954515,0.0019318233,0.0005963467,0.0008498408,0.00005149366,0.00007789349],"category_scores_gemma":[0.00084343605,0.00017715374,0.00004645747,0.00029414496,0.00048400986,0.0002951892,0.0006874999,0.00060609885,0.000018120427],"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":[0.0010434221,0.0009878493,0.012559994,0.00032535393,0.002014086,0.000050463805,0.07739262,0.007168252,0.0003314317,0.7319311,0.0057343817,0.16046107],"study_design_scores_gemma":[0.00075030903,0.00018274892,0.00018809686,0.00014542016,0.00006697304,0.000067385314,0.0009414106,0.9444121,0.000007023882,0.051219713,0.0017940797,0.00022475388],"about_ca_topic_score_codex":0.00060070475,"about_ca_topic_score_gemma":0.00009436605,"teacher_disagreement_score":0.9372438,"about_ca_system_score_codex":0.000059307753,"about_ca_system_score_gemma":0.000041360545,"threshold_uncertainty_score":0.99936754},"labels":[],"label_agreement":null},{"id":"W2891445448","doi":"10.1177/1536867x19830877","title":"Fast and wild: Bootstrap inference in Stata using boottest","year":2019,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Data Analysis with R","field":"Computer Science","cited_by":884,"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; Queen's University","funders":"","keywords":"Inference; Econometrics; Statistics; Computer science; Mathematics; Artificial intelligence","score_opus":0.06334283729434241,"score_gpt":0.35116361082192094,"score_spread":0.2878207735275785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891445448","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":[0.13160297,0.001166612,0.86117244,0.0036420745,0.00013330813,0.00055959227,0.0011885131,0.000050272894,0.0004842386],"genre_scores_gemma":[0.8264369,0.0018264642,0.17133757,0.00022778973,0.000014173555,0.0000041342105,0.00007820636,0.000020039937,0.000054729622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975875,0.00054480997,0.0006649462,0.00037547477,0.00041569464,0.00041156873],"domain_scores_gemma":[0.99455404,0.0020132102,0.00047394523,0.0026037702,0.00018204922,0.00017299372],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019595213,0.00023082264,0.0003172113,0.00026304123,0.0007136814,0.0011392682,0.0028054032,0.00003867674,0.000016051968],"category_scores_gemma":[0.0005480182,0.00017745492,0.000024429854,0.0004842229,0.0002828952,0.00083472766,0.0017533855,0.0008887734,0.000013944318],"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":[0.00008058441,0.0009111221,0.074600644,0.00020280843,0.0003527928,0.00010620961,0.018415313,0.002693555,0.00070260576,0.55844563,0.0016586444,0.3418301],"study_design_scores_gemma":[0.0008486463,0.00034830655,0.017415868,0.00032125533,0.000051740015,0.00016213286,0.001004413,0.94751245,0.000013085083,0.029135277,0.0027815595,0.0004052794],"about_ca_topic_score_codex":0.00025431838,"about_ca_topic_score_gemma":0.00026532062,"teacher_disagreement_score":0.94481885,"about_ca_system_score_codex":0.00006524893,"about_ca_system_score_gemma":0.00020383227,"threshold_uncertainty_score":0.99989766},"labels":[],"label_agreement":null},{"id":"W2896918891","doi":"10.1177/1536867x1801800209","title":"Qfactor: A Command for Q-methodology Analysis","year":2018,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Q Methodology Applications","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Computer science; Factor (programming language); Set (abstract data type); Quantitative analysis (chemistry); Statistical analysis; Qualitative analysis; Data mining; Statistics; Mathematics; Qualitative research; Programming language","score_opus":0.5959575052896716,"score_gpt":0.5707345326609626,"score_spread":0.025222972628708984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896918891","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":[0.013010153,0.00025375755,0.9737751,0.009500886,0.00013851607,0.00045018722,0.0021797188,0.000023580531,0.0006681267],"genre_scores_gemma":[0.33542013,0.000310556,0.66303414,0.00058423844,0.00010031544,0.000046966183,0.000093815586,0.000020848487,0.00038897738],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933745,0.0041476917,0.0011275139,0.00040827325,0.00055327103,0.0003887373],"domain_scores_gemma":[0.94298404,0.051216226,0.0009500835,0.003338656,0.0013259263,0.00018505896],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.023041975,0.00019817853,0.0005128447,0.0004957181,0.0033102785,0.000573629,0.0034075028,0.000078970246,0.00016854619],"category_scores_gemma":[0.02070577,0.00012676459,0.0001189877,0.0011639318,0.0015571855,0.00015494756,0.0007385669,0.0006557615,0.0000474813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033837263,0.00039290971,0.007889136,0.00001328192,0.0014516523,0.000003213102,0.01533091,0.00007797179,0.0006535912,0.61991835,0.065907545,0.28802305],"study_design_scores_gemma":[0.0006476289,0.00059589447,0.017017115,0.000013302231,0.00065195083,0.000078229226,0.0023735468,0.049905628,0.000088176464,0.8241676,0.10420539,0.00025555465],"about_ca_topic_score_codex":0.000039933868,"about_ca_topic_score_gemma":0.00047903258,"teacher_disagreement_score":0.32240996,"about_ca_system_score_codex":0.000040368748,"about_ca_system_score_gemma":0.00013927456,"threshold_uncertainty_score":0.9979873},"labels":[],"label_agreement":null},{"id":"W2897092992","doi":"10.1177/1536867x1801800206","title":"Attrition Diagrams for Clinical Trials and Meta-analyses in Stata","year":2018,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Attrition; Documentation; Computer science; Diagram; Set (abstract data type); Programming language; Database; Medicine","score_opus":0.9846130439606658,"score_gpt":0.7497721060674238,"score_spread":0.234840937893242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897092992","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":[0.027889028,0.016838737,0.917348,0.024219668,0.00035589962,0.004041232,0.008501693,0.0000136911,0.0007920002],"genre_scores_gemma":[0.7227942,0.009625616,0.26471195,0.0009799713,0.00023831105,0.00014782717,0.0002579495,0.000047206275,0.0011969818],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.940099,0.043611076,0.013102475,0.00075745746,0.0020432684,0.0003867497],"domain_scores_gemma":[0.8880188,0.095510945,0.00821835,0.0058546257,0.0021007003,0.0002966104],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31855217,0.00034379293,0.0041744043,0.0003768518,0.0012947442,0.002398841,0.0029622503,0.000076819495,0.0006778249],"category_scores_gemma":[0.18646908,0.00014845302,0.0008294189,0.00069408317,0.0007124861,0.00029913284,0.00058533857,0.0006547998,0.000058115893],"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":[0.00034192795,0.0011661239,0.006449492,0.00017838177,0.01184104,0.000014815867,0.007822931,0.00002835247,0.00009704492,0.11801763,0.30168307,0.5523592],"study_design_scores_gemma":[0.0027711198,0.0016568735,0.013015737,0.00012579626,0.019375537,0.00013760173,0.0064956835,0.14658485,0.000021513091,0.557754,0.25130418,0.0007571387],"about_ca_topic_score_codex":0.00003837054,"about_ca_topic_score_gemma":0.0003762013,"teacher_disagreement_score":0.69490516,"about_ca_system_score_codex":0.000027054852,"about_ca_system_score_gemma":0.00012090654,"threshold_uncertainty_score":0.9986368},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3013330736","doi":"10.1177/1536867x20909688","title":"The random forest algorithm for statistical learning","year":2020,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":1264,"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":"Random forest; Computer science; Key (lock); Artificial intelligence; Credit card; Machine learning; Algorithm; Statistical learning; World Wide Web","score_opus":0.03533706308133225,"score_gpt":0.2758883826175839,"score_spread":0.24055131953625167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013330736","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":[0.0009814247,0.00049722986,0.9827126,0.013587127,0.00017583721,0.0005379662,0.00075313146,0.000050874154,0.0007037565],"genre_scores_gemma":[0.9093821,0.0036486178,0.080635555,0.0028518261,0.0017373534,0.00013600056,0.0012669831,0.00010805715,0.00023350187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986544,0.00010540053,0.00047298954,0.00017899822,0.00027624686,0.00031195174],"domain_scores_gemma":[0.9969028,0.0018938512,0.00041813616,0.0004306064,0.00031204388,0.000042553354],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012967308,0.00016759076,0.00019101928,0.000039815048,0.0040097046,0.0012559853,0.00083488075,0.000031333588,0.000017721139],"category_scores_gemma":[0.002028254,0.000101853926,0.00004445439,0.00016732188,0.00030565113,0.00027647108,0.00038034088,0.00064440066,0.000020664022],"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":[0.00019713967,0.00006918341,0.00038762437,0.00006741741,0.000069690024,0.0000049381356,0.00044237048,0.00013750851,0.000009247097,0.34078485,0.0261665,0.63166356],"study_design_scores_gemma":[0.0011727028,0.00014082392,0.0017973412,0.0000486403,0.00010418844,0.000008037396,0.00084847776,0.6957911,8.8292626e-7,0.04200962,0.2579222,0.00015596472],"about_ca_topic_score_codex":0.00006417658,"about_ca_topic_score_gemma":0.00007038097,"teacher_disagreement_score":0.90840065,"about_ca_system_score_codex":0.000018348122,"about_ca_system_score_gemma":0.000039251507,"threshold_uncertainty_score":0.99978083},"labels":[],"label_agreement":null},{"id":"W3088227231","doi":"10.1177/1536867x20953572","title":"Causal mediation analysis in instrumental-variables regressions","year":2020,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Instrumental variable; Mediation; Causal inference; Econometrics; Mediator; Psychology; Causal analysis; Causal model; Variables; Estimation; Statistics; Mathematics; Medicine; Sociology; Economics; Social science; Internal medicine","score_opus":0.19406576556761382,"score_gpt":0.43369128149908953,"score_spread":0.2396255159314757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088227231","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":[0.04410705,0.00039765728,0.9339352,0.017200433,0.000055513545,0.0007253061,0.0024212697,0.00014823937,0.0010093354],"genre_scores_gemma":[0.73017955,0.0016946244,0.2675782,0.0002571064,0.000025191619,0.000018812716,0.00020354736,0.000023995013,0.000018960814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979799,0.00056127255,0.00068658375,0.00019553801,0.00032681684,0.00024993924],"domain_scores_gemma":[0.9956335,0.0026187177,0.0005201558,0.0009178163,0.00015055023,0.0001592973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012672431,0.00017832528,0.0003216113,0.00018613687,0.0006177296,0.00017946862,0.00087811594,0.000047808324,0.000067539884],"category_scores_gemma":[0.0027731725,0.00012901131,0.00003787665,0.0006976724,0.00021736757,0.00021613733,0.00046332623,0.0008550542,0.0000031708355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097089054,0.00044006374,0.008439199,0.000096851785,0.0005589162,0.000033917004,0.01588289,0.0001834527,0.00063849584,0.92674184,0.0066963434,0.040190928],"study_design_scores_gemma":[0.0007797037,0.00041638777,0.0029812714,0.00020662548,0.00040229445,0.000035935518,0.0034741992,0.12886366,0.00015761264,0.86027414,0.0019966918,0.0004114998],"about_ca_topic_score_codex":0.000049249156,"about_ca_topic_score_gemma":0.00027753934,"teacher_disagreement_score":0.6860725,"about_ca_system_score_codex":0.00007991783,"about_ca_system_score_gemma":0.00008836107,"threshold_uncertainty_score":0.5260929},"labels":[],"label_agreement":null},{"id":"W3125007939","doi":"10.1177/1536867x1501500113","title":"A Robust Test for Weak Instruments in Stata","year":2015,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":168,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Heteroscedasticity; Econometrics; Estimator; Mathematics; Statistics; Homoscedasticity; Autocorrelation; Null hypothesis; Economics","score_opus":0.28920500800699944,"score_gpt":0.3125236596126829,"score_spread":0.02331865160568347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125007939","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":[0.53908855,0.009767642,0.28542578,0.048964925,0.0014573529,0.004527696,0.08365578,0.00013295113,0.026979301],"genre_scores_gemma":[0.9459536,0.0020783935,0.050715208,0.00037450745,0.00006935281,0.000034377343,0.0002917158,0.000041401207,0.00044145045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820715,0.00009343737,0.0009585349,0.0002541809,0.00005954716,0.00042713183],"domain_scores_gemma":[0.9970446,0.0009463605,0.0006267775,0.0011065702,0.00005283061,0.00022286743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029065218,0.00019037118,0.0003597043,0.00022284858,0.00054534123,0.00034809625,0.001015862,0.000048177328,0.00003750018],"category_scores_gemma":[0.0015857064,0.0001713452,0.000039975508,0.00014543258,0.00018388938,0.00032077683,0.0002923269,0.0005067845,0.000053900854],"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":[0.00040396233,0.0016882408,0.08923415,0.00017990262,0.0004294519,0.000012844439,0.02164557,0.0044923914,0.000010068423,0.73650295,0.07658821,0.06881225],"study_design_scores_gemma":[0.0037442003,0.00094620255,0.01091693,0.00012256914,0.000030328702,0.00009973767,0.0021829267,0.4646135,0.000005429446,0.40318668,0.1135993,0.00055220485],"about_ca_topic_score_codex":0.00050631765,"about_ca_topic_score_gemma":0.00023745178,"teacher_disagreement_score":0.4601211,"about_ca_system_score_codex":0.00015386984,"about_ca_system_score_gemma":0.00007581547,"threshold_uncertainty_score":0.69872546},"labels":[],"label_agreement":null},{"id":"W3143332811","doi":"10.1177/1536867x211000008","title":"msreg: A command for consistent estimation of linear regression models using matched data","year":2021,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Estimator; Ordinary least squares; Matching (statistics); Statistics; Econometrics; Sample (material); Parametric statistics; Linear regression; Least-squares function approximation; Regression; Mathematics; Computer science","score_opus":0.4693799478599424,"score_gpt":0.4955069563491542,"score_spread":0.02612700848921179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143332811","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":[0.004999455,0.00054274325,0.9870858,0.0011543534,0.00006694265,0.00036681947,0.005653911,0.0000139438735,0.000115990115],"genre_scores_gemma":[0.1121787,0.0008059955,0.8865254,0.000061277926,0.000021824144,0.00000776812,0.00033917424,0.000028870172,0.00003101499],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757165,0.0007350937,0.00087950466,0.00024344552,0.00033078113,0.00023949976],"domain_scores_gemma":[0.98723793,0.00884199,0.0007473842,0.0023637954,0.0006938027,0.00011509599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026684254,0.00018535602,0.00042262892,0.000061970444,0.0009791668,0.00015874005,0.0010343492,0.00005151335,0.000018014074],"category_scores_gemma":[0.006807721,0.00012944489,0.000038672086,0.00015524599,0.00032649678,0.00016126569,0.00087905367,0.00044450932,4.2533895e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012840911,0.0005151091,0.000024940526,0.0005176136,0.00022370298,0.000009723805,0.0029939325,0.0007665122,0.0004911138,0.8981333,0.0029685395,0.093227126],"study_design_scores_gemma":[0.0003755892,0.0000852958,0.0000149789375,0.00035129138,0.00013362727,0.00005598179,0.00057570165,0.5731102,0.00009180122,0.42496407,0.00015143205,0.00009002851],"about_ca_topic_score_codex":0.00002624296,"about_ca_topic_score_gemma":0.00002010115,"teacher_disagreement_score":0.5723437,"about_ca_system_score_codex":0.000035108053,"about_ca_system_score_gemma":0.0002461029,"threshold_uncertainty_score":0.81499696},"labels":[],"label_agreement":null},{"id":"W3194795045","doi":"10.1177/1536867x251341145","title":"netivreg: Estimation of peer effects in endogenous social networks","year":2025,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Game Theory and Applications","field":"Decision Sciences","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":"Bank of Canada","funders":"","keywords":"Estimation; Endogeny; Computer science; Economics; Biology; Endocrinology","score_opus":0.11036322647690112,"score_gpt":0.419005568832524,"score_spread":0.3086423423556229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194795045","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":[0.04677633,0.0008218317,0.937114,0.009989002,0.00013543632,0.0006495833,0.0004257904,0.00001832346,0.0040697213],"genre_scores_gemma":[0.98228395,0.00022874419,0.016995672,0.0001417458,0.000016854015,0.00002023102,0.000038698046,0.000008955754,0.0002651411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970449,0.0011531605,0.0008564302,0.000191295,0.00053425547,0.0002199567],"domain_scores_gemma":[0.98920476,0.008607615,0.0005359148,0.001139186,0.0004585361,0.000054009583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062800897,0.0001300479,0.00027662126,0.00024242084,0.0011242228,0.00029567728,0.0016470971,0.00004585353,0.000018228031],"category_scores_gemma":[0.0040006097,0.00009024291,0.000040611787,0.0007536909,0.00044537007,0.00012244713,0.0004283479,0.0006098569,0.0000064851065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057402947,0.00025126402,0.00038302157,0.000019187815,0.000039687784,0.0000028711922,0.004430822,0.0035087697,0.00008710708,0.6350558,0.0036398112,0.35252425],"study_design_scores_gemma":[0.0006379387,0.0001283214,0.010453038,0.00011974595,0.000049705162,0.000023835513,0.0015143654,0.23997591,0.000051588308,0.744028,0.0028905077,0.0001270645],"about_ca_topic_score_codex":0.000030566836,"about_ca_topic_score_gemma":0.000045188663,"teacher_disagreement_score":0.93550766,"about_ca_system_score_codex":0.000036697806,"about_ca_system_score_gemma":0.000110460045,"threshold_uncertainty_score":0.8646726},"labels":[],"label_agreement":null},{"id":"W4205090414","doi":"10.1177/1536867x211063410","title":"Review of Michael N. Mitchell’s Interpreting and Visualizing Regression Models Using Stata, Second Edition","year":2021,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; Lakehead University","funders":"","keywords":"Computer science; Regression; Statistics; Econometrics; Mathematics","score_opus":0.07237149430034216,"score_gpt":0.40096340195799957,"score_spread":0.3285919076576574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205090414","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":[0.15609545,0.31664297,0.49193472,0.016900487,0.0011414334,0.0027742852,0.0053320536,0.00013186595,0.009046749],"genre_scores_gemma":[0.63876164,0.28771362,0.07235573,0.0008194218,0.00008082588,0.000009757118,0.0001486395,0.000036067617,0.000074320305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99660766,0.0015984636,0.0007686877,0.00023559957,0.00048421114,0.00030539747],"domain_scores_gemma":[0.99653393,0.0010434708,0.00083001715,0.00085309317,0.0006113034,0.00012820617],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004528692,0.00016723169,0.00032572364,0.00011281952,0.0019566102,0.00027961537,0.0006418124,0.00004333474,0.00004678031],"category_scores_gemma":[0.0008258488,0.00014115925,0.00005393432,0.000307916,0.0006089736,0.0003772734,0.0005726875,0.0005553838,6.4438e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014461683,0.001020404,0.0025611687,0.011503513,0.00086742773,0.000086769636,0.09978311,0.00012832946,0.0015387146,0.54572815,0.021440683,0.3151971],"study_design_scores_gemma":[0.0028271223,0.0008405698,0.0022889508,0.09614595,0.001509892,0.0003359349,0.10025662,0.2513394,0.0004826472,0.4392678,0.10256598,0.0021391308],"about_ca_topic_score_codex":0.00025684593,"about_ca_topic_score_gemma":0.0005994762,"teacher_disagreement_score":0.4826662,"about_ca_system_score_codex":0.00006818283,"about_ca_system_score_gemma":0.0002077591,"threshold_uncertainty_score":0.9993427},"labels":[],"label_agreement":null},{"id":"W4233989131","doi":"10.1177/1536867x1701700406","title":"Text Mining with n-gram Variables","year":2017,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":19,"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","funders":"","keywords":"n-gram; Gram; Computer science; Statistics; Natural language processing; Mathematics; Geology","score_opus":0.046007961283892104,"score_gpt":0.321158498507218,"score_spread":0.2751505372233259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233989131","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":[0.0019780514,0.00020123573,0.98471105,0.009860522,0.000070089605,0.00020163604,0.00060784334,0.000048321268,0.0023212745],"genre_scores_gemma":[0.22028255,0.00085896754,0.77836245,0.00016566413,0.000039879553,0.000020421623,0.000048892554,0.00001857632,0.00020260493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865824,0.00016170264,0.00033384454,0.00025857397,0.0002936679,0.00029399229],"domain_scores_gemma":[0.99394876,0.0009198689,0.0005760848,0.0041888608,0.000218263,0.0001481651],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013404243,0.00016530583,0.00017288288,0.00006359065,0.005596771,0.0029721204,0.005000227,0.000025636233,0.0000064414166],"category_scores_gemma":[0.0004306071,0.00010706653,0.000018042088,0.00011254777,0.0004475929,0.00056604337,0.0014004402,0.00049594097,0.000009972704],"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":[0.000009271261,0.00015663389,0.0003255789,0.000013530531,0.00008170773,0.0000143046,0.0025412033,0.000022046015,0.000023099386,0.43896407,0.0059482413,0.5519003],"study_design_scores_gemma":[0.0014148591,0.00084404927,0.013275681,0.0004991471,0.0001186916,0.00078204734,0.0013663943,0.8058097,0.000044009186,0.08010905,0.095012024,0.0007243751],"about_ca_topic_score_codex":0.00009771233,"about_ca_topic_score_gemma":0.00005165714,"teacher_disagreement_score":0.8057876,"about_ca_system_score_codex":0.000023145809,"about_ca_system_score_gemma":0.00013829318,"threshold_uncertainty_score":0.9980629},"labels":[],"label_agreement":null},{"id":"W4313563060","doi":"10.1177/1536867x221141002","title":"qpair: A command for analyzing paired Q-sorts in Q-methodology","year":2022,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Q Methodology Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Computer science; Factor (programming language); Statistical analysis; Data mining; Quantitative analysis (chemistry); Operations research; Statistics; Mathematics; Programming language","score_opus":0.5272660379772833,"score_gpt":0.5212253227442247,"score_spread":0.006040715233058602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313563060","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":[0.02253089,0.00089206034,0.94995785,0.022527369,0.00020516898,0.0010533577,0.002545926,0.000032644046,0.00025474917],"genre_scores_gemma":[0.36739942,0.0005263629,0.630413,0.000707346,0.000035997826,0.00029570062,0.00011712809,0.00003344652,0.00047161704],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98875904,0.008477147,0.0013221457,0.00040667903,0.0006195728,0.00041543978],"domain_scores_gemma":[0.9365653,0.059755873,0.0008803953,0.0023359335,0.00033813683,0.00012440873],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03787939,0.00018221384,0.00045284326,0.00047737744,0.003802014,0.00031339808,0.0032470387,0.0000432504,0.00017191611],"category_scores_gemma":[0.019026332,0.00012427552,0.000068993235,0.0009449804,0.0005078492,0.00013958069,0.001498947,0.0012299126,0.0000053307085],"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":[0.0011060657,0.00090952247,0.013108921,0.000030564275,0.00022959824,0.00004355797,0.026358454,0.0023918217,0.00026229402,0.3314149,0.052215073,0.5719292],"study_design_scores_gemma":[0.0014410831,0.0007232292,0.009349731,0.000026467269,0.00007457596,0.00046378947,0.009445743,0.07048868,0.000010394769,0.8242432,0.08344225,0.0002908946],"about_ca_topic_score_codex":0.00006424189,"about_ca_topic_score_gemma":0.00053690973,"teacher_disagreement_score":0.57163835,"about_ca_system_score_codex":0.00010682135,"about_ca_system_score_gemma":0.00026595924,"threshold_uncertainty_score":0.9974949},"labels":[],"label_agreement":null},{"id":"W4362636314","doi":"10.1177/1536867x231161978","title":"Extended biasplot command to assess bias, precision, and agreement in method comparison studies","year":2023,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","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 Calgary","funders":"","keywords":"Statistics; Computer science; Limits of agreement; Accuracy and precision; Data mining; Mathematics; Nuclear medicine; Medicine","score_opus":0.6821565065636919,"score_gpt":0.5640156980598392,"score_spread":0.11814080850385267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362636314","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":[0.51187795,0.005431054,0.41568282,0.059616495,0.00085175625,0.0032535666,0.001890371,0.00014123875,0.00125474],"genre_scores_gemma":[0.8281842,0.0056084697,0.16539657,0.00038341313,0.00003846412,0.000057826303,0.00003810112,0.000024407605,0.0002685657],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99291074,0.0030314156,0.0015748508,0.00044810044,0.0016294083,0.0004054655],"domain_scores_gemma":[0.9803253,0.016219396,0.00057685457,0.0019276943,0.0007368457,0.000213958],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032106325,0.00023268905,0.00052968663,0.00047458755,0.0015873901,0.0008534907,0.0019261874,0.000036797694,0.000020037396],"category_scores_gemma":[0.011596926,0.00014233957,0.000038514085,0.001092348,0.0003012477,0.00019159852,0.001696773,0.0006847375,0.00004360394],"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":[0.00022188728,0.0006836731,0.017668886,0.000091096896,0.00024997236,0.000027782842,0.03665916,0.0020092872,0.00024466336,0.04566475,0.07490741,0.8215714],"study_design_scores_gemma":[0.00250304,0.0018716543,0.19335875,0.0011916632,0.00016437222,0.00007568775,0.11731057,0.2688134,0.0001709505,0.35358772,0.06012063,0.0008315455],"about_ca_topic_score_codex":0.000059315676,"about_ca_topic_score_gemma":0.00039189836,"teacher_disagreement_score":0.82073987,"about_ca_system_score_codex":0.000110758694,"about_ca_system_score_gemma":0.00007938226,"threshold_uncertainty_score":0.9997124},"labels":[],"label_agreement":null},{"id":"W4390051166","doi":"10.1177/1536867x231212432","title":"csa2sls: A complete subset approach for many instruments using Stata","year":2023,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","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":"McMaster University","funders":"","keywords":"Estimator; Mean squared error; Statistics; Monte Carlo method; Econometrics; Instrumental variable; Least-squares function approximation; Mathematics; Bias of an estimator; Computer science; Minimum-variance unbiased estimator","score_opus":0.15639166263670332,"score_gpt":0.3397580369528209,"score_spread":0.1833663743161176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390051166","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":[0.55333793,0.0009832818,0.42154023,0.006445488,0.00090910087,0.0039751586,0.00819676,0.00049973035,0.0041123363],"genre_scores_gemma":[0.9330062,0.0005830327,0.06368809,0.0005304419,0.00020543116,0.000053648346,0.0016946944,0.000095694784,0.00014274105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997982,0.00014123372,0.00065730937,0.00029907067,0.00038643627,0.0005339051],"domain_scores_gemma":[0.9969979,0.00082012615,0.0005777236,0.0012328571,0.00031992787,0.00005146458],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0026494768,0.00027197707,0.00031120086,0.00034959428,0.0027230622,0.0012353004,0.0013696543,0.00004251341,0.00003305243],"category_scores_gemma":[0.00044730635,0.00021658881,0.00006528777,0.0006150785,0.00025114193,0.0005421758,0.0010771822,0.00057584525,0.000019489951],"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":[0.0009843999,0.0012992976,0.043603152,0.002306318,0.0010035195,0.000057746773,0.005922775,0.00068637636,0.0019320857,0.23707981,0.046845097,0.6582794],"study_design_scores_gemma":[0.0019244566,0.0000916412,0.011760821,0.00027108213,0.0004563939,0.000070165144,0.0032491717,0.8981785,0.0000052664645,0.0262837,0.057080254,0.000628506],"about_ca_topic_score_codex":0.000274295,"about_ca_topic_score_gemma":0.000053854903,"teacher_disagreement_score":0.8974922,"about_ca_system_score_codex":0.00004429427,"about_ca_system_score_gemma":0.00006996967,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W4390051293","doi":"10.1177/1536867x231212433","title":"Leverage, influence, and the jackknife in clustered regression models: Reliable inference using summclust","year":2023,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada; Danmarks Grundforskningsfond; National Research Foundation; York University","keywords":"Leverage (statistics); Jackknife resampling; Estimator; Inference; Computer science; Regression; Econometrics; Variance (accounting); Data mining; Linear regression; Cluster (spacecraft); Statistics; Mathematics; Artificial intelligence; Machine learning; Accounting","score_opus":0.1913882021901753,"score_gpt":0.4374128927053959,"score_spread":0.2460246905152206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390051293","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":[0.09946884,0.00053688465,0.89300066,0.004142016,0.000115708994,0.0009120302,0.0009037806,0.00007019037,0.00084987003],"genre_scores_gemma":[0.516767,0.005101875,0.4777456,0.0001740569,0.00002477673,0.000023453447,0.000027147275,0.00003807601,0.00009804067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967666,0.0013056826,0.00084183464,0.00025777848,0.00040874546,0.0004193599],"domain_scores_gemma":[0.98468447,0.0131739015,0.00047316847,0.0012755285,0.00025952636,0.00013340866],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0049931146,0.0002447612,0.00041283367,0.00018538132,0.001527644,0.00048237108,0.0010208628,0.000059926897,0.000011944365],"category_scores_gemma":[0.0061367415,0.00013830746,0.000030062247,0.0005451878,0.0008345997,0.00025916778,0.0009852637,0.0011077187,0.0000038040328],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015695569,0.00008909035,0.0003936402,0.00013375381,0.00004650048,0.000023112498,0.0058578104,0.0004117537,0.00002876177,0.95157224,0.0012882793,0.03999813],"study_design_scores_gemma":[0.0007149573,0.000050249386,0.00080263685,0.000420757,0.000035324083,0.000040661893,0.00072239636,0.3884981,0.0000025764875,0.6084638,0.00012778012,0.000120733246],"about_ca_topic_score_codex":0.00024275876,"about_ca_topic_score_gemma":0.0001271539,"teacher_disagreement_score":0.41729817,"about_ca_system_score_codex":0.000053188523,"about_ca_system_score_gemma":0.00014090702,"threshold_uncertainty_score":0.99977225},"labels":[],"label_agreement":null},{"id":"W4392957163","doi":"10.1177/1536867x241233671","title":"A Bayesian method for addressing multinomial misclassification with applications for alcohol epidemiological modeling","year":2024,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"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":"Multinomial distribution; Computer science; Bayesian probability; Estimation; Statistics; Data mining; Econometrics; Data science; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.32862457902786585,"score_gpt":0.49844971980345915,"score_spread":0.1698251407755933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392957163","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":[0.000045771485,0.00042397113,0.99021983,0.0042797085,0.000056598645,0.0017523074,0.0030018406,0.00007664217,0.00014332632],"genre_scores_gemma":[0.034027055,0.000288057,0.9644122,0.00012310209,0.00014325322,0.00072417245,0.00017912405,0.000060491962,0.00004254002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734986,0.0007321535,0.00086112256,0.00041536163,0.00022763052,0.00041388304],"domain_scores_gemma":[0.9714764,0.026596786,0.0003484675,0.0009862263,0.0004201518,0.00017199745],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0048368326,0.00027567617,0.00042625217,0.00011861976,0.0017508679,0.0006033144,0.000792834,0.00008512768,0.000012008239],"category_scores_gemma":[0.0042115063,0.00016905647,0.000082507046,0.0001945478,0.00027303555,0.00012842084,0.00014452526,0.0006880577,0.0000014442099],"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":[0.00009242679,0.000093927425,0.0000056473145,0.00026109882,0.00010098596,0.0000012790179,0.000653724,0.00006488447,0.00009508474,0.71983904,0.0010922496,0.27769968],"study_design_scores_gemma":[0.00030007443,0.00017847972,0.0000070449314,0.00021203973,0.00015045787,0.00004821428,0.0002685721,0.5249945,0.000009825354,0.471069,0.0026291548,0.00013262156],"about_ca_topic_score_codex":0.000014323179,"about_ca_topic_score_gemma":0.00001938402,"teacher_disagreement_score":0.52492964,"about_ca_system_score_codex":0.00007372252,"about_ca_system_score_gemma":0.00018458054,"threshold_uncertainty_score":0.99954873},"labels":[],"label_agreement":null},{"id":"W4392957219","doi":"10.1177/1536867x241233672","title":"sendemails: An automated email package with multiple applications","year":2024,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Names, Identity, and Discrimination Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis","funders":"","keywords":"Computer science; Audit; Audit trail; World Wide Web; Human–computer interaction","score_opus":0.07348863440698308,"score_gpt":0.43156710264762865,"score_spread":0.3580784682406456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392957219","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":[0.045340795,0.010309049,0.8332053,0.05978055,0.000532087,0.0049665202,0.008941565,0.002063147,0.034860983],"genre_scores_gemma":[0.964775,0.0055658296,0.027973717,0.00011802827,0.000121338155,0.000079399404,0.00026720803,0.000037997208,0.0010614527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99743295,0.0009843955,0.00035347528,0.00023032076,0.00064413,0.00035475843],"domain_scores_gemma":[0.99630976,0.001882821,0.00014699534,0.00097257795,0.0004237528,0.00026412137],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002886861,0.00013803224,0.00014514482,0.00018317188,0.004309521,0.0019370179,0.0011486097,0.00004337197,0.00009000677],"category_scores_gemma":[0.0006482184,0.000096637,0.00002672814,0.00049689104,0.0009295535,0.00046271645,0.00021564323,0.0006629658,0.000033520028],"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":[0.000043424516,0.0005729066,0.0019590857,0.00017662215,0.0001839081,0.00004416984,0.040281497,0.00003298448,0.000074714335,0.8025245,0.021559134,0.13254704],"study_design_scores_gemma":[0.0016287467,0.0009865495,0.009541198,0.0006500832,0.0004076039,0.00020972203,0.08406214,0.27143648,0.000030841464,0.20393328,0.4260475,0.0010658365],"about_ca_topic_score_codex":0.00085829775,"about_ca_topic_score_gemma":0.004962003,"teacher_disagreement_score":0.91943425,"about_ca_system_score_codex":0.0000988155,"about_ca_system_score_gemma":0.0004847874,"threshold_uncertainty_score":0.9990991},"labels":[],"label_agreement":null}]}