{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":814,"total_is_capped":false,"direct_labels_cover":3,"predictions_cover":814,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"189c207923fc","filters":{"topic":"Data Analysis with R"}},"results":[{"id":"W1951724000","doi":"10.18637/jss.v067.i01","title":"Fitting Linear Mixed-Effects Models Using <b>lme4</b>","year":2015,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":85618,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Banff International Research Station for Mathematical Innovation and Discovery","keywords":"Restricted maximum likelihood; Deviance (statistics); Mixed model; Smoothing; Applied mathematics; Likelihood function; Mathematics; Generalized linear model; Linear model; Maximum likelihood; Generalized linear mixed model; Covariate; Algorithm; Statistics; Mathematical optimization; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05709843782498766,"gpt":0.3091346325908944,"spread":0.2520361947659067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009528171,0.0001574766,0.0004106679,0.000163185,0.00008203353,0.0001787019,0.0008681733,0.00006818924,0.000008848665],"category_scores_gemma":[0.002802184,0.0001253954,0.00009875629,0.000386668,0.00005849559,0.001176472,0.00028602,0.0003395146,0.00002376487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001370502,"about_ca_system_score_gemma":0.0002597245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002446738,"about_ca_topic_score_gemma":0.000001687414,"domain_scores_codex":[0.9977947,0.0001709911,0.0006136706,0.0002227692,0.0008701847,0.0003276457],"domain_scores_gemma":[0.997327,0.0008255639,0.0004153922,0.0003406523,0.0005814554,0.0005098938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001876507,0.0009706601,0.01076648,0.0004139777,0.0007772641,0.006939227,0.002703609,0.2079741,0.0004120017,0.1951889,0.06049496,0.5131711],"study_design_scores_gemma":[0.0006922987,0.000262031,0.0004306987,0.0001278861,0.0000992819,0.0003246166,0.00004015134,0.9297093,0.0001729496,0.06743106,0.0004911469,0.000218558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005111812,0.0002128192,0.9939271,0.0001172292,0.0004791062,0.00005101738,0.00002071698,0.00004463909,0.00003560621],"genre_scores_gemma":[0.1532665,0.00000444571,0.8462998,0.0001934798,0.0002033804,5.357288e-7,0.000003158393,0.00001263424,0.00001607407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7217352,"threshold_uncertainty_score":0.5113477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050345155","doi":"10.1186/1471-2105-12-35","title":"VennDiagram: a package for the generation of highly-customizable Venn and Euler diagrams in R","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":3262,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Venn diagram; Computer science; Visualization; Process (computing); Data mining; Engineering drawing; Theoretical computer science; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07426646512308042,"gpt":0.2469729188522922,"spread":0.1727064537292118,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005270793,0.0000915918,0.000155377,0.0001047233,0.00006006901,0.00007819667,0.0005026483,0.00004872609,0.000003939677],"category_scores_gemma":[0.0001137257,0.00006156685,0.00004689202,0.0003116105,0.00005469313,0.000658184,0.0001509718,0.00005428112,0.00001426605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001600294,"about_ca_system_score_gemma":0.0000434027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006256139,"about_ca_topic_score_gemma":0.0002449992,"domain_scores_codex":[0.9991896,0.00002263628,0.0003721202,0.0001024273,0.0001373378,0.0001758968],"domain_scores_gemma":[0.9990003,0.0001713939,0.0001840527,0.0005535925,0.00005205018,0.00003863499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001377777,0.0009115135,0.0748143,0.001638689,0.0004018249,0.000007791928,0.07465129,0.002728878,0.001093994,0.4099987,0.03626603,0.3973492],"study_design_scores_gemma":[0.0004094891,0.00005744044,0.005492472,0.00001361913,0.00002263812,0.000002584316,0.0001367923,0.9904212,0.001483092,0.0005983244,0.001260914,0.0001013997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008552843,0.0001194929,0.9904323,0.00005645338,0.0001307298,0.0002927179,0.00001565787,0.00002261435,0.0003771832],"genre_scores_gemma":[0.362869,0.00008686276,0.6366571,0.0001693182,0.00004499404,0.00006863374,0.0000346327,0.000008695185,0.00006076527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9876924,"threshold_uncertainty_score":0.2510623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753599755","doi":"10.1111/rssa.12378","title":"Visualization in Bayesian Workflow","year":2019,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Data Analysis with R","field":"Computer Science","cited_by":1128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Office of Naval Research; Institute of Education Sciences; Defense Advanced Research Projects Agency; Columbia University; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Workflow; Visualization; Computer science; Bayesian probability; Data science; Data mining; Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.006838517424116364,"gpt":0.2549536180972047,"spread":0.2481151006730883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001271167,0.0002479946,0.0005488798,0.00004920209,0.0001223766,0.0002822634,0.001467936,0.0001641334,0.0001549624],"category_scores_gemma":[0.0004220274,0.0001875454,0.0003329564,0.00122984,0.0002241966,0.0005299011,0.0004495199,0.0007321256,0.00001771218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004493374,"about_ca_system_score_gemma":0.0002822697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005776981,"about_ca_topic_score_gemma":0.0001134169,"domain_scores_codex":[0.9968421,0.0002645242,0.001072737,0.0003415614,0.0009797794,0.0004992739],"domain_scores_gemma":[0.9977453,0.0007672618,0.0005809669,0.0005185475,0.0002436276,0.0001442912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008277285,0.0005766636,0.09664453,0.000289835,0.0003459766,0.00009584354,0.006370958,0.02405983,0.00008449711,0.7197571,0.1362859,0.01540611],"study_design_scores_gemma":[0.001570312,0.0002485745,0.05668954,0.0002341918,0.00006909943,0.00002673152,0.0009750382,0.8287436,0.00004213157,0.103303,0.007621499,0.0004763062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002642754,0.000129516,0.9951335,0.0008698088,0.0006788969,0.0001945092,0.0001020764,0.0000164365,0.0002325461],"genre_scores_gemma":[0.2065503,0.0001921538,0.7909949,0.001146314,0.0001330596,0.000006008839,0.0000187561,0.00003356375,0.0009249605],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8046837,"threshold_uncertainty_score":0.7647879,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; Queen's University","funders":"","keywords":"Inference; Econometrics; Statistics; Computer science; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06334283729434241,"gpt":0.3511636108219209,"spread":0.2878207735275785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001959521,0.0002308226,0.0003172113,0.0002630412,0.0007136814,0.001139268,0.002805403,0.00003867674,0.00001605197],"category_scores_gemma":[0.0005480182,0.0001774549,0.00002442985,0.0004842229,0.0002828952,0.0008347277,0.001753386,0.0008887734,0.00001394432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006524893,"about_ca_system_score_gemma":0.0002038323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002543184,"about_ca_topic_score_gemma":0.0002653206,"domain_scores_codex":[0.9975875,0.00054481,0.0006649462,0.0003754748,0.0004156946,0.0004115687],"domain_scores_gemma":[0.994554,0.00201321,0.0004739452,0.00260377,0.0001820492,0.0001729937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008058441,0.0009111221,0.07460064,0.0002028084,0.0003527928,0.0001062096,0.01841531,0.002693555,0.0007026058,0.5584456,0.001658644,0.3418301],"study_design_scores_gemma":[0.0008486463,0.0003483066,0.01741587,0.0003212553,0.00005174001,0.0001621329,0.001004413,0.9475124,0.00001308508,0.02913528,0.002781559,0.0004052794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.131603,0.001166612,0.8611724,0.003642075,0.0001333081,0.0005595923,0.001188513,0.00005027289,0.0004842386],"genre_scores_gemma":[0.8264369,0.001826464,0.1713376,0.0002277897,0.00001417356,0.00000413421,0.00007820636,0.00002003994,0.00005472962],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9448189,"threshold_uncertainty_score":0.9998977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073175998","doi":"10.1038/nmeth.2811","title":"BoxPlotR: a web tool for generation of box plots","year":2014,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Data Analysis with R","field":"Computer Science","cited_by":875,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institutes of Health; Wellcome Trust","keywords":"Box plot; Plot (graphics); Data set; Bar chart; Scatter plot; Outlier; Range (aeronautics); Computer science; Quartile; Visualization; Statistics; Skewness; Mathematics; Data mining; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.05445951663217588,"gpt":0.3831012404065347,"spread":0.3286417237743589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002904999,0.0003753768,0.0008215018,0.0004461502,0.00007988347,0.00019188,0.002312726,0.002014922,0.00001511159],"category_scores_gemma":[0.001163297,0.0003174497,0.000423085,0.0005903834,0.00004613996,0.0003434194,0.0002955415,0.002078654,0.00001324812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006603195,"about_ca_system_score_gemma":0.0001942566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005165412,"about_ca_topic_score_gemma":0.00000421046,"domain_scores_codex":[0.9963769,0.001057998,0.0005792783,0.000943851,0.0006417246,0.0004002957],"domain_scores_gemma":[0.995768,0.001049423,0.0005833214,0.00212493,0.0004306902,0.00004368952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002518132,0.00001091614,0.000003407109,0.0001311215,0.000117185,0.000006412882,0.0000290487,0.00001023383,0.003806078,0.001929248,0.9585986,0.03535522],"study_design_scores_gemma":[0.0002207593,0.00006416725,0.000006896467,0.00003455473,0.0001447949,0.000009744253,2.922975e-7,0.05322918,0.009576864,0.001607164,0.9347714,0.0003341417],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000006403467,0.0006650425,0.8415898,0.1553349,0.001593706,0.0003587288,0.0000713641,0.0001189218,0.0002611478],"genre_scores_gemma":[0.00002498997,0.00001246764,0.694234,0.3006761,0.003485916,0.00007204437,0.0003961643,0.00003831118,0.001059957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1473558,"threshold_uncertainty_score":0.9999278,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2808135930","doi":"10.1097/ede.0000000000000864","title":"Web Site and R Package for Computing E-values","year":2018,"lang":"en","type":"article","venue":"Epidemiology","topic":"Data Analysis with R","field":"Computer Science","cited_by":755,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"National Institute of Environmental Health Sciences; National Cancer Institute; Medical Research Council","keywords":"Web site; Computer science; R package; Web application; World Wide Web; The Internet; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05159941123569833,"gpt":0.3519743605208481,"spread":0.3003749492851498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003028963,0.000104375,0.0003529688,0.00008221232,0.0001968013,0.00002330167,0.000493373,0.00007058035,0.00001057298],"category_scores_gemma":[0.002862597,0.00008622138,0.00005679614,0.0001557094,0.0002131927,0.0001783922,0.0003900801,0.00008744483,0.0001247035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001200779,"about_ca_system_score_gemma":0.00002160712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002566703,"about_ca_topic_score_gemma":0.00003359082,"domain_scores_codex":[0.9983689,0.0004294456,0.0003149394,0.0004778873,0.00004315951,0.0003657065],"domain_scores_gemma":[0.9961493,0.002981281,0.0001521844,0.0005589381,0.00007090803,0.00008739683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002398818,0.00005555046,0.2038832,0.00005125155,0.0001801239,0.000009372422,0.001552667,0.00003233147,0.003820768,0.3572288,0.294131,0.139031],"study_design_scores_gemma":[0.0004834555,0.0003337086,0.04367607,0.00001833965,0.00002665038,0.00003458904,0.00002064647,0.8182925,0.0004031903,0.06274263,0.07369094,0.0002772557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07265354,0.0002273424,0.9218658,0.004145957,0.0003071115,0.00009572638,0.00001011013,0.0001093542,0.0005850775],"genre_scores_gemma":[0.675795,0.00001684242,0.3185812,0.004924314,0.0004681923,0.000005073246,0.00001623033,0.000007070058,0.0001861163],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8182602,"threshold_uncertainty_score":0.3516006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2924517740","doi":"10.1186/s12874-019-0666-3","title":"A review of spline function procedures in R","year":2019,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Data Analysis with R","field":"Computer Science","cited_by":577,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Univariate; Computer science; Spline (mechanical); Observational study; Software; Data science; Regression analysis; Machine learning; Thin plate spline; Data mining; Management science; Statistics; Mathematics; Multivariate statistics; Spline interpolation; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.7468500022474139,"gpt":0.6371901037000626,"spread":0.1096598985473514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09173721,0.0003259211,0.004242971,0.001617175,0.00003380486,0.00002583585,0.0048497,0.000734403,0.0006804765],"category_scores_gemma":[0.2315358,0.0002219882,0.0005577196,0.004455541,0.0003957652,0.0001675281,0.002303041,0.00219506,0.0005031926],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552832,"about_ca_system_score_gemma":0.01162722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001373875,"about_ca_topic_score_gemma":0.0004306732,"domain_scores_codex":[0.9535694,0.03928413,0.002014477,0.001297405,0.002934546,0.000900034],"domain_scores_gemma":[0.9306318,0.06472965,0.0007106696,0.002796164,0.0006402386,0.0004915264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005397421,0.00005497987,0.000003091493,0.2989516,0.00004435897,0.00001637976,0.000006368865,1.076285e-7,9.702676e-8,0.004603414,0.007411087,0.6889031],"study_design_scores_gemma":[0.0001455988,0.0001498329,0.000004700388,0.1899373,0.0001193777,0.00005897457,0.00000305319,0.0003097339,2.382251e-7,0.000776206,0.8083482,0.0001468629],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.312882e-8,0.7334698,0.2648272,0.0002228065,0.0002411561,0.0008904077,0.000005431768,0.00002182908,0.0003213306],"genre_scores_gemma":[3.952408e-8,0.9056979,0.09307776,0.0003734938,0.0001549303,0.0002719434,0.00006048512,0.00002247025,0.0003409242],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8009371,"threshold_uncertainty_score":0.9939759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297515751","doi":"","title":"glmulti: An R Package for Easy Automated Model Selection with (Generalized) Linear Models","year":2010,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Analysis with R","field":"Computer Science","cited_by":147,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Selection (genetic algorithm); R package; Computer science; Mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02357698296147909,"gpt":0.2616525405533713,"spread":0.2380755575918922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005784629,0.0005596449,0.0006056126,0.0003914184,0.0005582029,0.001157724,0.004034148,0.000523566,0.0000161453],"category_scores_gemma":[0.0005815428,0.0005341813,0.0002572298,0.0007453801,0.0001764954,0.001146677,0.001704102,0.0009125101,0.00001807192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001423749,"about_ca_system_score_gemma":0.0007464312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001245282,"about_ca_topic_score_gemma":0.005358539,"domain_scores_codex":[0.9932638,0.003063223,0.0006774521,0.001696284,0.0007066943,0.0005925202],"domain_scores_gemma":[0.9893574,0.0005945461,0.0007749562,0.004802247,0.00410686,0.0003640247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001363443,0.002594211,0.0004581525,0.0004337443,0.0006137639,0.000009214111,0.01268343,0.3840503,0.02652636,0.5349621,0.003910535,0.03362182],"study_design_scores_gemma":[0.000651812,0.000001315646,0.00008860783,0.0002950713,0.00008122392,0.000009446183,0.000009519075,0.9609699,0.02798382,0.00847206,0.0008471825,0.0005900391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02499169,0.00008603997,0.9672354,0.002251647,0.0001552645,0.000837168,0.0001930859,0.001816571,0.002433157],"genre_scores_gemma":[0.2826431,0.00005833438,0.7125773,0.0001272035,0.00003454518,0.0002386871,0.001531217,0.00007200021,0.002717653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5769196,"threshold_uncertainty_score":0.9998792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149851338","doi":"10.1111/2041-210x.12044","title":"Strategies for fitting nonlinear ecological models in <scp>R</scp>,<scp> AD M</scp>odel <scp>B</scp>uilder, and <scp>BUGS</scp>","year":2013,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Data Analysis with R","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; University of British Columbia Hospital; Dalhousie University; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03835212703600921,"gpt":0.3283769825518429,"spread":0.2900248555158337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006463073,0.0007685451,0.00141338,0.001054398,0.0006283121,0.0005384803,0.001445954,0.0012143,0.000005425005],"category_scores_gemma":[0.01250749,0.0007343633,0.000232431,0.001440145,0.0006019467,0.003156993,0.001241527,0.001151871,0.00004539234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003395371,"about_ca_system_score_gemma":0.0004012076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002465791,"about_ca_topic_score_gemma":0.001233038,"domain_scores_codex":[0.9919968,0.002165746,0.00148081,0.002016325,0.0004121661,0.001928191],"domain_scores_gemma":[0.9779208,0.01951884,0.0007260247,0.001056987,0.0003821131,0.0003951975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003795735,0.006410527,0.3557525,0.001817524,0.00162292,0.0003705951,0.03981806,0.1705617,0.01812792,0.2073161,0.1084049,0.08975936],"study_design_scores_gemma":[0.001425671,0.0004511432,0.1175826,0.00004816202,0.00009000838,0.00005848035,0.005261404,0.7271874,0.0003333701,0.1431193,0.00435088,0.00009157806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4955986,0.0013918,0.4997583,0.0001628183,0.00051509,0.0008714965,0.00003277966,0.0001737009,0.00149544],"genre_scores_gemma":[0.2447096,0.0005766735,0.7517133,0.0006171262,0.0002162964,0.0006386159,0.0000833169,0.00005674161,0.00138833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5566258,"threshold_uncertainty_score":0.9995108,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2412645763","doi":"10.1371/journal.pcbi.1004961","title":"Ten Simple Rules for Effective Statistical Practice","year":2016,"lang":"en","type":"editorial","venue":"PLoS Computational Biology","topic":"Data Analysis with R","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; National Institutes of Health; National Science Foundation","keywords":"Simple (philosophy); Praise; Computer science; Data science; Psychology; Epistemology; Philosophy; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01164210549544279,"gpt":0.3312051418532067,"spread":0.3195630363577638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006304294,0.0003589783,0.0006542554,0.0002522108,0.0001748698,0.00016022,0.001428713,0.0005526521,0.00003435693],"category_scores_gemma":[0.01186718,0.0002736804,0.0001383997,0.0001705503,0.0001873854,0.0004220997,0.0005322942,0.0003688296,0.000496383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001817143,"about_ca_system_score_gemma":0.0006014413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002667213,"about_ca_topic_score_gemma":0.000005289914,"domain_scores_codex":[0.9967796,0.0005534684,0.0005104854,0.001121709,0.0005664846,0.000468206],"domain_scores_gemma":[0.9513789,0.04614949,0.0004810348,0.0005045095,0.00135745,0.0001286469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006219967,0.0001193436,0.000007818152,0.0000417365,0.0005158309,0.000008670379,0.00002257189,0.00007311703,0.0000154846,0.1020088,0.881784,0.01534044],"study_design_scores_gemma":[0.0006340537,0.000385635,0.00004165983,0.00002491337,0.0001404204,0.000003926574,0.000001991834,0.02117245,0.00001054134,0.1585799,0.8186663,0.0003381644],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003391418,0.00007727773,0.8005143,0.0008591529,0.1911054,0.0005174479,0.006531362,0.0001295891,0.0002620403],"genre_scores_gemma":[0.0003197908,0.00001947559,0.4925592,0.000479102,0.4830621,0.0005518926,0.0228298,0.00005036887,0.0001282737],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3079552,"threshold_uncertainty_score":0.9999715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390461978","doi":"10.3929/ethz-b-000073064","title":"Nonparametric Econometrics: The np Package","year":2008,"lang":"en","type":"article","venue":"Repository for Publications and Research Data (ETH Zurich)","topic":"Data Analysis with R","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Econometrics; R package; Statistics; Computer science; Mathematics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2633315052726449,"gpt":0.38542908937566,"spread":0.1220975841030151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004146518,0.0001298693,0.0001849706,0.001453263,0.002244633,0.001340081,0.005859527,0.00007934398,0.000009022984],"category_scores_gemma":[0.002807213,0.00008792341,0.00006005731,0.006427352,0.0004276276,0.002688684,0.002542713,0.0003632879,0.00005477193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000728939,"about_ca_system_score_gemma":0.0003199253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002023396,"about_ca_topic_score_gemma":0.00001221443,"domain_scores_codex":[0.9970993,0.0003406441,0.00038783,0.000948131,0.0006955863,0.0005285217],"domain_scores_gemma":[0.9910557,0.002412356,0.0001451007,0.00538289,0.0007388844,0.0002650216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006040974,0.0003357528,0.00924242,0.00003936634,0.0001622211,0.000009134049,0.000276209,0.000007189775,0.000175771,0.08390609,0.8814934,0.02434635],"study_design_scores_gemma":[0.0002237309,0.00008695037,0.01654216,0.000003949126,0.0000165622,0.0001724188,0.00004868601,0.03703764,0.0002269502,0.0008905353,0.9445742,0.000176238],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009928709,0.006413895,0.9274317,0.03150224,0.0004963799,0.00223574,0.0008278509,0.0003911628,0.0207723],"genre_scores_gemma":[0.8597273,0.00320217,0.1066395,0.0005046216,0.0007474129,0.0008975854,0.002011106,0.00006340969,0.02620681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8497986,"threshold_uncertainty_score":0.9996966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128422078","doi":"10.4310/sii.2016.v9.n4.a1","title":"Statistical methods and computing for big data","year":2016,"lang":"en","type":"article","venue":"Statistics and Its Interface","topic":"Data Analysis with R","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Cancer Institute; Banff International Research Station for Mathematical Innovation and Discovery; National Institutes of Health; National Science Foundation","keywords":"Big data; Computational statistics; Software; Scale (ratio); Selection (genetic algorithm); Data stream mining; Feature selection","retraction":null,"screen_n_in":null,"score":{"opus":0.1010523441108938,"gpt":0.4147756650059232,"spread":0.3137233208950294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007033164,0.0001144992,0.0001898421,0.00004904661,0.00009456071,0.0001837393,0.0006434027,0.00002769857,0.000008335666],"category_scores_gemma":[0.0009653349,0.00007761057,0.000006599635,0.00007092964,0.000073132,0.0002282912,0.001188088,0.00004940128,0.000007958027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001005696,"about_ca_system_score_gemma":0.00002986496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009180972,"about_ca_topic_score_gemma":0.00001216615,"domain_scores_codex":[0.998836,0.00008920198,0.0002268852,0.00052307,0.0001067807,0.0002180843],"domain_scores_gemma":[0.9975086,0.001662271,0.00007948667,0.0005478832,0.00008952541,0.0001122058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005871071,0.00001100667,0.00007089998,0.00003017366,0.00003512947,0.000002350452,0.00009242668,8.657678e-7,0.001125982,0.2016233,0.01297766,0.7840243],"study_design_scores_gemma":[0.0007970812,0.0002571278,0.001889689,0.00008371219,0.00007235798,0.00002535003,0.00003719201,0.8884582,0.002125189,0.04055085,0.06532338,0.0003799097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003943291,0.0003304838,0.9955162,0.0004309678,0.0003464059,0.00009981904,0.002790856,0.00002847651,0.00006244813],"genre_scores_gemma":[0.1128695,0.00006902484,0.8866372,0.00008578092,0.00006482994,0.000001589104,0.0000338329,0.000008436217,0.0002297765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8884573,"threshold_uncertainty_score":0.3164867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792985690","doi":"10.1002/ece3.3807","title":"Count data in biology—Data transformation or model reformation?","year":2018,"lang":"en","type":"article","venue":"Ecology and Evolution","topic":"Data Analysis with R","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Residual; Transformation (genetics); Statistics; Generalized linear model; Econometrics; Type I and type II errors; Data transformation; Statistical model; Plot (graphics); Mathematics; Computer science; Data mining; Algorithm; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04467150556521438,"gpt":0.3145071598013819,"spread":0.2698356542361676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009627964,0.0000670945,0.0001097367,0.0001512605,0.0001369086,0.00003066429,0.00120444,0.0001015768,0.00001480963],"category_scores_gemma":[0.00008887113,0.0000525482,0.000005297218,0.0002782202,0.0001037884,0.003209224,0.000553899,0.00008140488,0.00009208815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007479805,"about_ca_system_score_gemma":0.0001102615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008802972,"about_ca_topic_score_gemma":0.005594368,"domain_scores_codex":[0.999113,0.00007398151,0.0002386684,0.0003373807,0.00006358308,0.0001733838],"domain_scores_gemma":[0.9986525,0.00003525036,0.00007063308,0.001166534,0.00004578063,0.00002926193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004676971,0.0006990912,0.1491435,0.0001479003,0.0002305442,0.00001154188,0.008136614,0.002282688,0.001404968,0.7061658,0.06690027,0.06440943],"study_design_scores_gemma":[0.0002636809,0.00006005562,0.0574196,0.000003753435,0.000008345076,0.00001010314,0.00002620776,0.9333215,0.000006564055,0.007211966,0.001600837,0.00006737771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07124763,0.00004689847,0.925703,0.001837498,0.0001909053,0.0001197364,0.0001266927,0.00005288727,0.0006747296],"genre_scores_gemma":[0.9841953,0.00004857056,0.0145264,0.0002427556,0.00004097273,0.000005199155,0.0009026243,0.000001844602,0.00003636529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9310388,"threshold_uncertainty_score":0.3121788,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W597599483","doi":"10.1017/cbo9780511803642","title":"A First Course in Statistical Programming with R","year":2007,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Data Analysis with R","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Western University","funders":"","keywords":"Computer science; Download; Open source; Code (set theory); Course (navigation); Source code; Programming language; Software engineering; World Wide Web; Core (optical fiber); C programming language; Software; Engineering; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.01447406246458246,"gpt":0.2168288740390328,"spread":0.2023548115744504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002766159,0.0003723005,0.0004972295,0.0003897745,0.0001347404,0.0001788434,0.001858277,0.0002552778,0.000001277872],"category_scores_gemma":[0.00001302425,0.0003898926,0.00008526247,0.00008807975,0.0003263024,0.0002862892,0.0007834735,0.0006319955,0.00001724878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004832069,"about_ca_system_score_gemma":0.0006323371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003762401,"about_ca_topic_score_gemma":0.0002357988,"domain_scores_codex":[0.9977006,0.00006597477,0.0002337116,0.000871406,0.0005728485,0.0005554908],"domain_scores_gemma":[0.9980513,0.0001941949,0.0002223806,0.001129203,0.0001469321,0.0002559667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006869582,0.00006953486,0.00005483839,0.0001287127,0.000156533,0.006223747,0.0001032268,0.00002533149,3.8657e-7,0.9122685,0.07459749,0.006302998],"study_design_scores_gemma":[0.0007529283,0.0001134651,0.0002832776,0.0002815815,0.0001733947,0.00004162186,0.00002292124,0.003182191,0.000006716079,0.00000514704,0.9945886,0.0005482074],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0000152637,0.00004500318,0.3236166,0.00001784921,0.00006819887,0.0003992958,0.000126495,0.0001652643,0.675546],"genre_scores_gemma":[0.0002779827,0.000009793619,0.0278363,0.00005744002,0.00005354057,0.000001738299,0.0001316152,0.00003008474,0.9716015],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9199911,"threshold_uncertainty_score":0.9998553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156242793","doi":"10.1093/aje/kwr241","title":"The Quality of Modern Cross-Sectional Ecologic Studies: A Bibliometric Review","year":2011,"lang":"en","type":"review","venue":"American Journal of Epidemiology","topic":"Data Analysis with R","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Cross-sectional study; Medicine; Fallacy; MEDLINE; Epidemiology; Clinical study design; Environmental health; Pathology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.4254039160845181,"gpt":0.5413397750599583,"spread":0.1159358589754403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04597558,0.0004658514,0.008193985,0.008320661,0.0001716947,0.00002916276,0.005375026,0.0001653065,0.00002669848],"category_scores_gemma":[0.05393843,0.0002354869,0.002296939,0.0324422,0.001870718,0.0003325049,0.000873487,0.001035556,0.00003672645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002449322,"about_ca_system_score_gemma":0.000793092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006110216,"about_ca_topic_score_gemma":0.00001027752,"domain_scores_codex":[0.9803227,0.01111329,0.00684074,0.0006418392,0.0004529304,0.0006285722],"domain_scores_gemma":[0.9323285,0.04087254,0.02305996,0.001862047,0.001627328,0.0002495806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000614855,0.00004790154,0.002958432,0.003158422,0.00151637,0.000007150792,0.00001195225,0.000005083192,1.533097e-8,0.003675755,0.003176097,0.9854367],"study_design_scores_gemma":[0.0001049738,0.0008817221,0.00592843,0.004886542,0.0006717038,0.0006463443,0.000007174314,0.0000305572,1.955403e-8,0.009845168,0.976678,0.000319418],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000007487749,0.9584023,0.04029285,0.0002506743,0.0007009036,0.0002269858,0.00002106513,0.00001309918,0.00008460657],"genre_scores_gemma":[0.00002402156,0.9856914,0.01307376,0.0009488023,0.0001698809,0.00002710384,0.000005562662,0.00001657967,0.00004290579],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9851173,"threshold_uncertainty_score":0.9988225,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2941763735","doi":"10.1002/ece3.6747","title":"A contrast of meta and metafor packages for meta‐analyses in R","year":2020,"lang":"en","type":"article","venue":"Ecology and Evolution","topic":"Data Analysis with R","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; York University","funders":"","keywords":"Contrast (vision); Benchmark (surveying); Consistency (knowledge bases); Computer science; Meta-analysis; Data science; Checklist; Statistics; Artificial intelligence; Psychology; Cartography; Geography; Cognitive psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09534385885876914,"gpt":0.320078127650376,"spread":0.2247342687916068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003187713,0.00007305166,0.0004363527,0.00008809995,0.00003983487,0.00001419274,0.0001388848,0.00004638018,0.00001529878],"category_scores_gemma":[0.000183236,0.0000540395,0.00009050222,0.0002079662,0.00006529847,0.0002866335,0.00008423132,0.00004184616,0.000001480096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006762762,"about_ca_system_score_gemma":0.00002055536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004576421,"about_ca_topic_score_gemma":0.0004178064,"domain_scores_codex":[0.9993245,0.00009765349,0.0001820128,0.0002329272,0.00004653719,0.0001163497],"domain_scores_gemma":[0.9994804,0.0002387139,0.00008742742,0.0001138005,0.00003634858,0.00004336236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0005535049,0.0007907428,0.1568147,0.0008969925,0.1075799,0.00004842433,0.005603984,0.002725688,0.06594207,0.6354007,0.0171096,0.006533757],"study_design_scores_gemma":[0.002421048,0.0009209226,0.6154484,0.000005089521,0.02766973,0.00001748866,0.000254761,0.3166814,0.004821331,0.0291579,0.00219461,0.0004073159],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2026886,0.01439232,0.7709787,0.01119266,0.00008794687,0.000436292,0.00006463811,0.00004826887,0.0001105684],"genre_scores_gemma":[0.9871778,0.00005269828,0.01244096,0.0002423711,0.000010326,0.00005275693,0.000005078713,0.000001902949,0.00001607715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7844893,"threshold_uncertainty_score":0.2203667,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W123767535","doi":"","title":"GETTING STARTED WITH THE R COMMANDER: A BASIC-STATISTICS GRAPHICAL USER INTERFACE TO R","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Analysis with R","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Dialog box; Computer science; Graphical user interface; Interface (matter); Window (computing); Programming language; User interface; Human–computer interaction; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01010641793212767,"gpt":0.2466048792513933,"spread":0.2364984613192656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002783631,0.0001321585,0.0001419435,0.0000871176,0.0001619224,0.0003233775,0.001219199,0.0000244071,0.00003077474],"category_scores_gemma":[0.00003715832,0.00007293653,0.00002805364,0.0007664076,0.00006725064,0.0002950043,0.0003874674,0.0001686128,0.0001352651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003154829,"about_ca_system_score_gemma":0.00005392832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002335541,"about_ca_topic_score_gemma":0.002146374,"domain_scores_codex":[0.9988048,0.00005572271,0.0001659804,0.000336735,0.0003605281,0.0002762462],"domain_scores_gemma":[0.9987125,0.0001337746,0.00005020942,0.0008760113,0.0001051036,0.0001224215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004950992,0.0002666131,0.003810218,0.00001759951,0.0003111428,0.0001146602,0.005042714,0.01172956,0.0008397742,0.8692455,0.09508511,0.01348765],"study_design_scores_gemma":[0.01269597,0.005049565,0.1132295,0.0005582684,0.0007306889,0.0005165736,0.005533344,0.3958037,0.02800285,0.07373261,0.3578811,0.006265799],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.021321,0.00000692447,0.9604032,0.01736933,0.00003531696,0.0001335031,0.000008075562,0.0001289363,0.000593677],"genre_scores_gemma":[0.7129725,9.389424e-7,0.2823001,0.004391883,0.00001644809,0.000008932405,0.000004258618,0.000008576513,0.0002963729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7955129,"threshold_uncertainty_score":0.3118337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968805547","doi":"10.1080/02664760500168648","title":"Interpretable dimension reduction","year":2005,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Data Analysis with R","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University; Acadia University","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Principal component analysis; Linear subspace; Dimensionality reduction; Constraint (computer-aided design); Dimension (graph theory); Mathematics; Homogeneity (statistics); Reduction (mathematics); Mathematical optimization; Computer science; Algorithm; Statistics; Artificial intelligence; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.007379734791390265,"gpt":0.2424087083072268,"spread":0.2350289735158365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003720821,0.00007987432,0.0001808593,0.00014665,0.00005120115,0.000104148,0.0004707895,0.00002845443,0.00004029691],"category_scores_gemma":[0.00003234046,0.0000664933,0.00003485248,0.0002116203,0.00002382748,0.0004081904,0.00009321937,0.000172176,0.00005806506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007676418,"about_ca_system_score_gemma":0.00006566568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001443378,"about_ca_topic_score_gemma":0.000001623536,"domain_scores_codex":[0.9989526,0.00001588962,0.0004237489,0.0001167645,0.0003556952,0.0001352974],"domain_scores_gemma":[0.9990166,0.00005307823,0.0004064199,0.0002664027,0.0001696179,0.00008791959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007956413,0.0002002313,0.00002004469,0.00001310124,0.0001383763,0.00003872175,0.001383244,0.009298204,0.02050885,0.2823666,0.207618,0.4783351],"study_design_scores_gemma":[0.002600694,0.0007308454,0.0009370469,0.0001251804,0.0003937506,0.001125333,0.000455098,0.5768302,0.04233179,0.110907,0.2626173,0.0009457057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002280712,0.00003674617,0.9948702,0.00028994,0.0002690844,0.00003175554,0.000007574401,0.0000145657,0.002199462],"genre_scores_gemma":[0.4071873,0.0000239271,0.5924187,0.0001080431,0.0001494683,4.244484e-7,0.000002491177,0.000004288686,0.0001053895],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.567532,"threshold_uncertainty_score":0.2711518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4294557430","doi":"10.18637/jss.v103.i07","title":"Hierarchical Clustering with Contiguity Constraint in <i>R</i>","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contiguity; Cluster analysis; Computer science; Hierarchical clustering; Theoretical computer science; Function (biology); Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01225028693388872,"gpt":0.2517438408299075,"spread":0.2394935538960188,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007909212,0.0001025944,0.0003215189,0.0001695833,0.0001061172,0.00009456924,0.0008172485,0.00001893696,0.0001905066],"category_scores_gemma":[0.0003849022,0.00008022326,0.00004820684,0.0004133015,0.0001151998,0.0002798076,0.0004303651,0.0006522224,0.000003338227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001453686,"about_ca_system_score_gemma":0.000231762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002381971,"about_ca_topic_score_gemma":0.00003445194,"domain_scores_codex":[0.9981098,0.0002084704,0.0005004951,0.0001933971,0.000735458,0.0002524007],"domain_scores_gemma":[0.9986761,0.0005873595,0.0002295649,0.000230153,0.00009571919,0.0001810557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001104872,0.001885062,0.181386,0.0001620307,0.0004820352,0.02676424,0.002617699,0.02968113,0.0002350807,0.2091577,0.01896568,0.5275584],"study_design_scores_gemma":[0.01911152,0.01072238,0.47259,0.0005444437,0.0003494361,0.02002822,0.001823277,0.270853,0.0001705129,0.1491793,0.05183918,0.00278867],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006641724,0.0000359637,0.9921938,0.0007755124,0.0001180363,0.00005415348,0.00007355095,0.00001903532,0.0000882781],"genre_scores_gemma":[0.6034518,0.000002320131,0.3960732,0.0004219468,0.00002467283,0.000003387658,0.000004274366,0.000005791009,0.00001258797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5968102,"threshold_uncertainty_score":0.327141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044013993","doi":"10.1098/rsos.200566","title":"Are replication rates the same across academic fields? Community forecasts from the DARPA SCORE programme","year":2020,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Data Analysis with R","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bishop's University","funders":"Defense Advanced Research Projects Agency; Royal Marsden NHS Foundation Trust","keywords":"Replication (statistics); Confidence interval; Agency (philosophy); Psychology; Empirical research; Computer science; Applied psychology; Statistics; Social science; Sociology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1294043474949684,"gpt":0.3691238483329833,"spread":0.239719500838015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005026989,0.000179083,0.0002194567,0.000005692477,0.003345956,0.00280792,0.0228605,0.00009222428,0.00001826735],"category_scores_gemma":[0.001512463,0.0001015432,0.0001441018,0.001977401,0.001151759,0.001544833,0.009090939,0.001112089,0.0000788043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000841912,"about_ca_system_score_gemma":0.0002419431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0038587,"about_ca_topic_score_gemma":0.0006315251,"domain_scores_codex":[0.9971298,0.0002977209,0.0003219554,0.0008424534,0.0008142513,0.0005938088],"domain_scores_gemma":[0.9955148,0.000634791,0.000429059,0.002974991,0.0002283217,0.0002180078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003346375,0.0002269467,0.2535667,0.00003458035,0.0001784838,0.000005489327,0.1752819,0.001784258,0.001669617,0.007092845,0.2343203,0.3258055],"study_design_scores_gemma":[0.0004603639,0.00009746511,0.3484289,0.00007147941,0.00003365189,0.000003674272,0.01486117,0.6081251,0.002512044,0.004895462,0.0200342,0.0004765022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7316086,0.000259563,0.1200489,0.145629,0.0002167293,0.001459512,0.0001082421,0.0002047741,0.0004647023],"genre_scores_gemma":[0.9671867,0.00001646335,0.007119799,0.0253508,0.0001059128,0.00007766225,0.00002055761,0.000007459705,0.0001145899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6063408,"threshold_uncertainty_score":0.9989234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2924029102","doi":"10.1080/00031305.2018.1556735","title":"The <i>p</i> -value Function and Statistical Inference","year":2019,"lang":"en","type":"article","venue":"The American Statistician","topic":"Data Analysis with R","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Inference; Function (biology); Statistical inference; Scalar (mathematics); Value (mathematics); Mathematics; Power function; Statistics; Computer science; Artificial intelligence; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.006202599462732283,"gpt":0.2597219331783565,"spread":0.2535193337156242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004483401,0.0001201287,0.000179956,0.00003195403,0.0002808324,0.0003333157,0.0008141983,0.000009298768,0.00001626056],"category_scores_gemma":[0.0002184321,0.00006569122,0.00001805806,0.0004183025,0.0005062866,0.0001753975,0.0002905571,0.0001515528,0.0003310122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002117112,"about_ca_system_score_gemma":0.00006314892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000606121,"about_ca_topic_score_gemma":0.0001117143,"domain_scores_codex":[0.9986452,0.0002417983,0.0001910149,0.0003043102,0.0003261235,0.0002915869],"domain_scores_gemma":[0.996893,0.001965355,0.0001801141,0.0008316489,0.0000503652,0.00007948455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001695096,0.000009349311,0.002885681,0.000002489385,0.00003135307,0.000002449177,0.0001050351,0.0000332045,0.00008153482,0.7695325,0.002784161,0.2245153],"study_design_scores_gemma":[0.0003700695,0.0007513656,0.5829065,0.00001567056,0.0001094374,0.00001736441,0.0006482329,0.2287396,0.0000252814,0.1466296,0.03933896,0.000447874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01348197,0.0000517321,0.9830961,0.001549292,0.0001705531,0.0001418223,0.00005038737,0.00005839025,0.001399801],"genre_scores_gemma":[0.9767864,0.00004884646,0.02072718,0.002118343,0.00003658722,0.00001219294,0.000009563434,0.000008884737,0.0002519869],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9633045,"threshold_uncertainty_score":0.4254602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2277736791","doi":"10.20982/tqmp.09.2.p043","title":"Conducting Simulation Studies in the R Programming Environment","year":2013,"lang":"en","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Data Analysis with R","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute on Alcohol Abuse and Alcoholism","keywords":"Computer science; Bootstrapping (finance); Variety (cybernetics); Syntax; Simulation modeling; Data science; Management science; Artificial intelligence; Econometrics; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.5490431352157252,"gpt":0.6000822268446929,"spread":0.05103909162896769,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008832633,0.0001555155,0.0004025154,0.0002388243,0.00007874324,0.00007318593,0.0007479761,0.0000707642,0.0000106483],"category_scores_gemma":[0.002837811,0.0001104373,0.00006653002,0.0004353185,0.0001818536,0.0005202235,0.000112636,0.0001577153,0.00003684282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007158282,"about_ca_system_score_gemma":0.00001354394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002577356,"about_ca_topic_score_gemma":0.000009776795,"domain_scores_codex":[0.9960298,0.002383422,0.000596527,0.0005287634,0.000141602,0.0003199189],"domain_scores_gemma":[0.9910532,0.00799746,0.000272904,0.0005712601,0.00008362214,0.0000215292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003984602,0.0002884029,0.0008765147,0.00004367329,0.0001671316,0.000006747933,0.03913899,0.005199456,0.009149729,0.4300719,0.0004894363,0.5145282],"study_design_scores_gemma":[0.002355516,0.00101469,0.003371596,0.00006297643,0.00005405246,0.000009035165,0.006929594,0.1042537,0.0008572899,0.8181442,0.0623225,0.0006248297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008518176,0.0006956143,0.9872745,0.0008530851,0.001302958,0.001107827,9.310895e-7,0.00002630013,0.0002205801],"genre_scores_gemma":[0.02892265,0.00002424677,0.9699623,0.0002907475,0.0001031828,0.00062254,0.000003406932,0.000009029628,0.00006192071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5139033,"threshold_uncertainty_score":0.4503503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7074663863","doi":"","title":"Our Own Master Race: Eugenics in Canada, 1885-1945","year":2023,"lang":"en","type":"article","venue":"Project Muse (Johns Hopkins University)","topic":"Data Analysis with R","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Eugenics; George (robot); Subject (documents); Agency (philosophy); Perspective (graphical); Argument (complex analysis)","retraction":null,"screen_n_in":null,"score":{"opus":0.02700623818115424,"gpt":0.2251063727721264,"spread":0.1981001345909722,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0002948092,0.0002473781,0.0003187204,0.01138307,0.0001314024,0.0001222651,0.002090126,0.0000804951,0.00001374049],"category_scores_gemma":[0.0000585774,0.0002673345,0.0001037241,0.02583116,0.00001992495,0.001080155,0.001168412,0.0002932643,0.0002128901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009708012,"about_ca_system_score_gemma":0.003188825,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9517844,"about_ca_topic_score_gemma":0.9859636,"domain_scores_codex":[0.9976798,0.0001800676,0.0002343756,0.0007226762,0.0005192651,0.0006637762],"domain_scores_gemma":[0.9984582,0.0000756013,0.0001305615,0.001090708,0.00009874724,0.0001461805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004116919,0.001051177,0.1642086,0.0005275561,0.001581162,0.04066545,0.04788324,0.01025518,0.0001600679,0.03870514,0.1997989,0.4947518],"study_design_scores_gemma":[0.0006405798,0.00002730184,0.002777051,0.00002468879,0.00002814222,0.000007870449,0.0008018187,0.02935185,0.00009883279,0.000002041944,0.9658929,0.0003469588],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4434349,0.000007184634,0.05062013,0.01104162,0.00270996,0.002087068,0.0003687408,0.002006488,0.4877239],"genre_scores_gemma":[0.9831539,0.0110452,0.004179123,0.0006170514,0.00008863936,0.00000435691,0.0000815421,0.00004105884,0.000789141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.766094,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161482435","doi":"10.1890/04-1655","title":"SAMPLING VARIABILITY AND ESTIMATES OF DENSITY DEPENDENCE: A COMPOSITE-LIKELIHOOD APPROACH","year":2006,"lang":"en","type":"article","venue":"Ecology","topic":"Data Analysis with R","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Sampling (signal processing); Statistics; Population; Inference; Statistical inference; Series (stratigraphy); Computer science; Econometrics; Mathematics; Ecology; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01214202770356461,"gpt":0.2457870415087425,"spread":0.2336450138051779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006560555,0.00009641088,0.0002831564,0.00007723518,0.00008347892,0.00004169311,0.0004712709,0.00007691392,0.0000105101],"category_scores_gemma":[0.00009250258,0.00009033691,0.00003447375,0.0002298882,0.0001128487,0.0002002604,0.000426304,0.00009413568,0.000008870419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002707699,"about_ca_system_score_gemma":0.00004602244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002367135,"about_ca_topic_score_gemma":0.0001305696,"domain_scores_codex":[0.9989179,0.00008617413,0.0002484139,0.0004054349,0.0001163218,0.0002257147],"domain_scores_gemma":[0.9989502,0.0003352329,0.000115664,0.0004743544,0.00007861319,0.00004588812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006181388,0.0002701051,0.9627253,0.00004005806,0.00003621036,0.000006283416,0.00009686586,0.0006720703,0.003501277,0.03053819,0.0001634561,0.001943946],"study_design_scores_gemma":[0.0002145134,0.00004420278,0.8237547,0.000002705697,0.0000319878,0.00004928449,0.000006477469,0.1310783,0.001725818,0.04294597,0.00002686326,0.000119215],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4853588,0.00001868924,0.5137738,0.0000777806,0.00004939954,0.0000653088,0.000002860258,0.00003879351,0.0006145884],"genre_scores_gemma":[0.7016591,9.684658e-7,0.2982683,0.00003729706,0.00001306763,0.000004215571,0.00001011472,0.000002304978,0.000004585633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2163003,"threshold_uncertainty_score":0.3683832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401042314","doi":"10.18653/v1/2024.naacl-long.335","title":"TableLlama: Towards Open Large Generalist Models for Tables","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Analysis with R","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Generalist and specialist species; Computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05470949858411823,"gpt":0.320992085302541,"spread":0.2662825867184228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006595809,0.0001367824,0.0002077213,0.0001116395,0.0001272969,0.002543654,0.002641667,0.00004425889,0.0002317919],"category_scores_gemma":[0.00001608577,0.0001042445,0.00009261104,0.0005921763,0.00001768638,0.002693441,0.001491619,0.00005817208,0.000118114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004257837,"about_ca_system_score_gemma":0.0001784414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006407076,"about_ca_topic_score_gemma":0.0003276638,"domain_scores_codex":[0.9985551,0.00002500528,0.0002174686,0.000606996,0.0002186425,0.0003768252],"domain_scores_gemma":[0.9989363,0.00004700657,0.00002528353,0.0008176273,0.0000798234,0.00009399294],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001188021,0.00002323696,0.00000474389,0.00002061244,0.00004537804,0.000007242006,0.00007371097,0.0009794239,0.00009821718,0.7572579,0.2340512,0.007437109],"study_design_scores_gemma":[0.0001196097,0.00001481419,0.000002749902,0.000009867171,0.00001507032,0.000002846943,0.000009252196,0.6928912,0.0007650931,0.03678529,0.2692599,0.0001242723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006576884,0.0005620282,0.9644563,0.002725398,0.0003219704,0.0002807587,0.0001480013,0.0002357957,0.031204],"genre_scores_gemma":[0.1469489,0.00008996813,0.7529297,0.00307695,0.0002766148,0.0002535664,0.0002741156,0.00004191893,0.09610824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7204726,"threshold_uncertainty_score":0.9984918,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2683414882","doi":"10.1101/156067","title":"BPG: Seamless, Automated and Interactive Visualization of Scientific Data","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data Analysis with R","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Government of Ontario; Canadian Institutes of Health Research; National Science Foundation; Ontario Institute for Cancer Research; University of Pennsylvania; Center for Translational Molecular Medicine; Ontario Genomics Institute; Movember Foundation; Ontario Genomics; Genome Canada; Prostate Cancer Canada","keywords":"Computer science; Personalization; Visualization; Open source; Software; Interactive visualization; Software engineering; Source code; Web application; Data mining; Data science; World Wide Web; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03137588375988596,"gpt":0.2915388983916274,"spread":0.2601630146317415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001588499,0.0004233854,0.0006414007,0.0005790138,0.0003534065,0.002275086,0.005651615,0.0002851589,0.000008425067],"category_scores_gemma":[0.000768071,0.0004442187,0.00006822772,0.0006922329,0.0003745597,0.002032049,0.008985203,0.000366349,0.00003184444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001143731,"about_ca_system_score_gemma":0.0008646427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001111836,"about_ca_topic_score_gemma":0.00001023723,"domain_scores_codex":[0.9961611,0.0002088811,0.0005985379,0.001990034,0.0006555273,0.0003858933],"domain_scores_gemma":[0.9893802,0.00008374654,0.001287461,0.008098203,0.0009436572,0.000206668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005965818,0.001087022,0.03209364,0.002494517,0.001977451,0.0002144739,0.0002331588,0.0002299237,0.9133884,0.02931404,0.0187367,0.0001709819],"study_design_scores_gemma":[0.0005426412,0.00004082099,0.1038846,0.001089631,0.0002826827,4.096833e-8,0.000002861428,0.7378389,0.1488294,0.00001798986,0.006362624,0.001107782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5262941,0.001775645,0.4587921,0.0004731911,0.005400412,0.001432948,0.003143216,0.002650009,0.00003835172],"genre_scores_gemma":[0.9799852,0.00008069694,0.019721,0.00003328925,0.00009135432,0.00002391238,0.00001067523,0.00004666678,0.000007242399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7645591,"threshold_uncertainty_score":0.999801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245274090","doi":"10.1201/9781315380537","title":"Using the R Commander","year":2016,"lang":"en","type":"book","venue":"","topic":"Data Analysis with R","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"History; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06007906383447632,"gpt":0.2889410885068781,"spread":0.2288620246724018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002233887,0.0001406082,0.0001712714,0.00007054034,0.0001031346,0.000208421,0.002451704,0.00008407704,0.0002694494],"category_scores_gemma":[0.000007643134,0.00006196033,0.0001006718,0.00006878642,0.00006257524,0.000243551,0.0008399679,0.0001321938,0.000611573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007889762,"about_ca_system_score_gemma":0.0002297576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001212214,"about_ca_topic_score_gemma":0.00002330786,"domain_scores_codex":[0.9990606,0.00003685182,0.0001514982,0.00028873,0.000302947,0.000159405],"domain_scores_gemma":[0.9979831,0.0001204026,0.0001088543,0.001697385,0.00005268516,0.0000375574],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[1.718679e-7,0.000002598262,0.000003468637,0.000002786057,0.00005987826,0.000005248844,0.00002101972,0.000002151165,0.000004107722,0.352688,0.6399031,0.007307558],"study_design_scores_gemma":[0.00004895225,0.000003796618,0.000003426793,0.00003288613,0.00002909434,0.00001066623,8.566917e-7,0.00657398,0.00001057769,0.02781262,0.9653214,0.0001517713],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[6.587111e-8,0.00005606816,0.504428,0.000563381,0.0001223887,0.00003669505,0.000002632206,0.00004607984,0.4947447],"genre_scores_gemma":[0.00001925371,0.00001119583,0.01249157,0.001363906,0.0001873207,0.000001293318,0.000005414992,0.00001024184,0.9859098],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4919364,"threshold_uncertainty_score":0.7860737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790635366","doi":"10.1177/0962280218759693","title":"MethodCompare: An R package to assess bias and precision in method comparison studies","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Data Analysis with R","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"R package; Statistics; Computer science; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6339406249091168,"gpt":0.7103905885533488,"spread":0.07644996364423196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1069093,0.0002612404,0.001095865,0.001330944,0.0002090765,0.0002937022,0.002433548,0.0002220011,0.0002004412],"category_scores_gemma":[0.1506537,0.0002042454,0.00003442837,0.004157698,0.001059392,0.0004295981,0.003031411,0.001630433,0.00007101271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002892134,"about_ca_system_score_gemma":0.0003439522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004497695,"about_ca_topic_score_gemma":0.001136299,"domain_scores_codex":[0.957796,0.03454702,0.001220452,0.001624818,0.003549658,0.001262028],"domain_scores_gemma":[0.9148766,0.0809546,0.0001006416,0.001665133,0.0008012134,0.001601794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007033278,0.0001919693,0.001997152,0.00005069814,0.00002304328,0.0001827371,0.001778499,0.000004067343,0.0003227699,0.140479,0.001676608,0.8532231],"study_design_scores_gemma":[0.0009697363,0.001337698,0.04167146,0.0003895735,0.00001583739,0.00002442021,0.002875878,0.7867916,0.003245056,0.1550721,0.007149896,0.0004567896],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0024855,0.0002520028,0.9934523,0.002047078,0.0002579976,0.0004067759,0.00001624611,0.00006351718,0.001018637],"genre_scores_gemma":[0.0264273,0.00005886183,0.9729335,0.0002947076,0.0001268008,0.0001020443,0.000006379281,0.00001924927,0.00003114055],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8527663,"threshold_uncertainty_score":0.9196249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075203254","doi":"10.1890/09-0460.1","title":"Multiscale codependence analysis: an integrated approach to analyze relationships across scales","year":2010,"lang":"en","type":"article","venue":"Ecology","topic":"Data Analysis with R","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Ecology; Scale (ratio); Geography; Computer science; Biology; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02587042978143286,"gpt":0.299021606548138,"spread":0.2731511767667051,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001463225,0.0001951789,0.0004229512,0.0004765656,0.0003750375,0.000273058,0.002201507,0.0002280127,0.00005466945],"category_scores_gemma":[0.0005032572,0.0001751477,0.0001352471,0.00347049,0.0001434992,0.0008626462,0.0004805963,0.0006556231,0.0005016715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004499362,"about_ca_system_score_gemma":0.00007296449,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002152202,"about_ca_topic_score_gemma":0.04797224,"domain_scores_codex":[0.9974927,0.0003773955,0.0004136678,0.000938029,0.0002617314,0.0005164752],"domain_scores_gemma":[0.997385,0.0002349382,0.0001478521,0.001676252,0.000222982,0.0003330045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002162974,0.0009694975,0.9215673,0.000007624745,0.0008810681,0.00003739981,0.00388325,0.0263446,0.002699164,0.03112532,0.002416162,0.01004704],"study_design_scores_gemma":[0.0001411885,0.00004478086,0.5689176,7.552485e-7,0.00009774119,0.00001413559,0.000200557,0.4286022,0.0001196551,0.000321857,0.001328458,0.0002110156],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4271232,0.000004677839,0.5714875,0.0003632063,0.000196882,0.0001245099,0.00003265367,0.000155557,0.00051182],"genre_scores_gemma":[0.7796758,7.421221e-7,0.2194678,0.0002315745,0.00003991638,0.00004426462,0.0001620202,0.000007866879,0.0003699777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4022577,"threshold_uncertainty_score":0.9693998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386637689","doi":"10.1007/978-3-031-34583-8","title":"Quantitative Methods for the Social Sciences","year":2023,"lang":"en","type":"book","venue":"Springer texts in political science and international relations","topic":"Data Analysis with R","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Data science; Management science; Computer science; Social science; Sociology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1088483196193201,"gpt":0.4700007971054457,"spread":0.3611524774861256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004213703,0.0001563149,0.0001863511,0.0007236986,0.0009847349,0.0006740058,0.002502221,0.0001009752,0.00003629999],"category_scores_gemma":[0.003903202,0.0001132586,0.00008962715,0.001004753,0.002279646,0.0009450918,0.0008826709,0.0003083528,0.0001168021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005416892,"about_ca_system_score_gemma":0.001383737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004674754,"about_ca_topic_score_gemma":0.00004502973,"domain_scores_codex":[0.9975466,0.0000534169,0.0003659671,0.0006749343,0.0007761987,0.0005829106],"domain_scores_gemma":[0.9959329,0.003158526,0.0001311505,0.0002628166,0.0004115424,0.0001030794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[9.666431e-7,0.000009457902,0.00003889737,0.000002602995,0.00001905939,4.845828e-7,0.0001501666,0.00001981662,0.000008330739,0.9841571,0.004911071,0.01068201],"study_design_scores_gemma":[0.000096785,0.00003735312,0.005175286,0.00004227366,0.00002236228,0.000002469795,0.00007201045,0.1839435,0.000009263137,0.7446569,0.06575902,0.0001827649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00002135261,0.0001770638,0.5430833,0.03020792,0.001304317,0.000377972,0.00006316852,0.00008293916,0.424682],"genre_scores_gemma":[0.01114161,0.00005600005,0.2631204,0.002214322,0.0005912525,0.0002204286,0.0000269975,0.00003253356,0.7225964],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.2979144,"threshold_uncertainty_score":0.8399453,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3027464055","doi":"10.1186/s12859-020-3494-x","title":"MEPHAS: an interactive graphical user interface for medical and pharmaceutical statistical analysis with R and Shiny","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Genetics; Chinese Government Scholarship; China Scholarship Council","keywords":"Computer science; Graphical user interface; Visualization; Interface (matter); Analytics; Workstation; User interface; Scatter plot; OS X; Data visualization; Statistical analysis; Data mining; Software; Programming language; Machine learning; Operating system; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.029111670027292,"gpt":0.333294396465094,"spread":0.304182726437802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004618376,0.0002172182,0.0004345448,0.000184128,0.00009812661,0.0004391486,0.0006324287,0.0001003321,0.00004198588],"category_scores_gemma":[0.00044264,0.000156655,0.00006166896,0.0007789999,0.0002811788,0.001492153,0.0004357298,0.0002797216,0.000008012543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001568843,"about_ca_system_score_gemma":0.00009558841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008546842,"about_ca_topic_score_gemma":0.00008964643,"domain_scores_codex":[0.9981732,0.00008385466,0.0004927076,0.0003831537,0.000558544,0.0003085857],"domain_scores_gemma":[0.998018,0.0005906653,0.0001269885,0.0003478884,0.0001058265,0.0008105864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00478821,0.001866747,0.2148993,0.003792487,0.01431238,0.0002205519,0.06089728,0.002499675,0.0001058081,0.4012848,0.01422712,0.2811056],"study_design_scores_gemma":[0.0009604194,0.0003961503,0.002799059,0.00001609875,0.0005044037,0.0000329961,0.0004674281,0.9927276,0.00004900737,0.000187596,0.001631372,0.0002279153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01257986,0.00003566779,0.9853714,0.001520353,0.00002613603,0.0002211021,0.00009090769,0.0000934402,0.00006110046],"genre_scores_gemma":[0.3026122,0.00002633023,0.695275,0.001953495,0.00003527864,0.0000169962,0.00006562719,0.0000102277,0.000004879071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9902279,"threshold_uncertainty_score":0.6388207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2900082925","doi":"10.1007/978-3-319-96978-7_2","title":"Use of Machine Learning (ML) for Predicting and Analyzing Ecological and ‘Presence Only’ Data: An Overview of Applications and a Good Outlook","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Analysis with R","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; Mount Allison University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Boosting (machine learning); Artificial neural network; Field (mathematics); Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1424685242687778,"gpt":0.3336138633195477,"spread":0.1911453390507699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007265609,0.0002298528,0.0005799604,0.0001891253,0.0001373673,0.0001675367,0.0008150543,0.0001502014,0.00002612094],"category_scores_gemma":[0.0001629388,0.0001897269,0.00004307668,0.00008480011,0.0002697493,0.000998191,0.002065121,0.0001951317,6.777387e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009510298,"about_ca_system_score_gemma":0.00005488123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001302447,"about_ca_topic_score_gemma":0.0006178525,"domain_scores_codex":[0.9981204,0.00004722594,0.0005104379,0.0009378149,0.0002133866,0.0001706919],"domain_scores_gemma":[0.9972754,0.0007037228,0.0005315854,0.001205114,0.0001585252,0.0001256945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005405757,0.0002658773,0.0896216,0.001964513,0.001474346,0.000008751877,0.0008643327,0.00008319843,0.0004177032,0.6524678,0.0006495219,0.2521283],"study_design_scores_gemma":[0.0006660685,0.0009162548,0.006586479,0.000506944,0.001025237,0.00006761214,0.00004697173,0.9122849,0.00004117828,0.01144104,0.06566754,0.0007498347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005116483,0.00875082,0.9769509,0.0002290807,0.00005575808,0.001836074,0.001663233,0.000185582,0.005212113],"genre_scores_gemma":[0.07501229,0.01413827,0.8618227,0.0002991527,0.0003361774,0.00009147076,0.002038489,0.0001188686,0.04614258],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9122016,"threshold_uncertainty_score":0.7736838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W103961220","doi":"","title":"The R software: Fundamentals of programming and statistical analysis","year":2013,"lang":"en","type":"preprint","venue":"QUT ePrints (Queensland University of Technology)","topic":"Data Analysis with R","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Fortran; Debugging; Documentation; Section (typography); Software; Programming language; Biostatistics; Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.008401666252845294,"gpt":0.2194462348443054,"spread":0.2110445685914601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004042169,0.0002153075,0.0006482853,0.0007651692,0.0001951187,0.0000783894,0.002378094,0.000341032,0.0000369464],"category_scores_gemma":[0.0001234939,0.0001858401,0.0001751129,0.000941936,0.0009890551,0.0001313344,0.005083277,0.0004695047,0.0000144302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005618273,"about_ca_system_score_gemma":0.00009838394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001100763,"about_ca_topic_score_gemma":0.0002975902,"domain_scores_codex":[0.9983217,0.00007978547,0.0003277764,0.0006753817,0.0003098794,0.0002854582],"domain_scores_gemma":[0.9973044,0.0001917397,0.0005630639,0.001634068,0.0002269888,0.00007968156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003381586,0.0002339932,0.4037099,0.000235961,0.005427031,0.00007012187,0.000494675,0.0001526845,0.0001053819,0.092824,0.001274404,0.4954381],"study_design_scores_gemma":[0.002052564,0.0004287522,0.7698864,0.0004129531,0.006307117,0.00002866821,0.002588941,0.03453007,0.001868973,0.1258471,0.05411377,0.001934787],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2854103,0.0002608903,0.7119633,0.001503739,0.00005991525,0.0003584886,0.0001050785,0.0001951596,0.0001431161],"genre_scores_gemma":[0.7054519,0.0003573913,0.2939094,0.000007123779,0.000004442112,0.000001823717,0.0000333386,0.000006754111,0.0002278569],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4935033,"threshold_uncertainty_score":0.7578341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3168850057","doi":"10.32614/rj-2022-012","title":"RFpredInterval: An R Package for Prediction Intervals with Random Forests and Boosted Forests","year":2022,"lang":"en","type":"article","venue":"The R Journal","topic":"Data Analysis with R","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; HEC Montréal; Fondation HEC","keywords":"Random forest; R package; Computer science; Reliability (semiconductor); Predictive modelling; Prediction interval; Data mining; Point (geometry); Mean squared prediction error; Set (abstract data type); Statistics; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01908452781822515,"gpt":0.2593394716969587,"spread":0.2402549438787336,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002168128,0.0001315482,0.000195711,0.0001386591,0.0007696414,0.0003445004,0.001189319,0.00001892116,0.00003118586],"category_scores_gemma":[0.00009271535,0.00007882922,0.00007690475,0.0002484579,0.00005937066,0.0009893012,0.0004089452,0.0003087301,0.000001568527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005895826,"about_ca_system_score_gemma":0.00005465336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001334291,"about_ca_topic_score_gemma":0.0002351851,"domain_scores_codex":[0.9984153,0.000379163,0.0002914333,0.0002190082,0.0004247384,0.0002703863],"domain_scores_gemma":[0.9987532,0.0001933982,0.0002448031,0.0005261135,0.0001430046,0.0001394084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01463518,0.001527264,0.3122586,0.0001876825,0.003575695,0.0003881984,0.0448355,0.0266161,0.004189688,0.01160489,0.3149568,0.2652245],"study_design_scores_gemma":[0.01616493,0.007509931,0.1802204,0.0001429646,0.0006188175,0.006178374,0.001762004,0.7483498,0.00135506,0.02228006,0.01475355,0.0006641392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2685713,0.0001408481,0.7295001,0.000983455,0.0003372814,0.0002879193,0.00006608071,0.00006406679,0.00004896252],"genre_scores_gemma":[0.9965457,0.00001440897,0.002728677,0.0002512738,0.0002120479,0.0000451208,0.00002256039,0.00001703138,0.000163196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7279744,"threshold_uncertainty_score":0.5919537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4300185383","doi":"10.1017/cbo9781316451090","title":"A First Course in Statistical Programming with R","year":2016,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Data Analysis with R","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Advice (programming); Graphics; Markov chain; Code (set theory); Programming language; Software engineering; Computer graphics (images); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01250430285110974,"gpt":0.2057397241362296,"spread":0.1932354212851199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000173421,0.0003570899,0.0004818521,0.0002707436,0.000127176,0.0001602296,0.001921981,0.0002111371,0.000001938543],"category_scores_gemma":[0.00001411595,0.0003130646,0.00008229727,0.00005140291,0.000312187,0.000336449,0.0008654404,0.0004003038,0.00002954432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004573182,"about_ca_system_score_gemma":0.0007155098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001647085,"about_ca_topic_score_gemma":0.00009774,"domain_scores_codex":[0.9978662,0.00008441308,0.0002021842,0.0008731419,0.0004814992,0.0004925623],"domain_scores_gemma":[0.9980261,0.0001973597,0.0002182811,0.001195004,0.0001336942,0.0002295233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005163115,0.00004394519,0.00004063157,0.00009626194,0.0001484516,0.00291488,0.00006262449,0.000004695649,8.216937e-7,0.8872427,0.1018552,0.007538147],"study_design_scores_gemma":[0.0008483519,0.00009969032,0.0001577503,0.0004464875,0.0001414399,0.00002835304,0.000009640103,0.00110291,0.000006632406,0.000009025878,0.9966494,0.0005002645],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001007838,0.0000386838,0.2884435,0.00005483556,0.00007820889,0.0004208149,0.0002766599,0.0001786961,0.7104985],"genre_scores_gemma":[0.000240976,0.00001374624,0.01205323,0.00003816992,0.00005652355,0.000002993533,0.00006626899,0.00002803779,0.9875001],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8947943,"threshold_uncertainty_score":0.9999322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W982522955","doi":"10.1007/978-1-4614-9020-3_8","title":"Programming in R","year":2013,"lang":"en","type":"book-chapter","venue":"Statisctics and computing/Statistics and computing","topic":"Data Analysis with R","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Programming language; Computer science; Programming paradigm; Order (exchange); Programming domain; C programming language; Object-oriented programming; Inductive programming; Artificial intelligence; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.01385810052166029,"gpt":0.2451940253181226,"spread":0.2313359247964624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005027733,0.0006644272,0.000901841,0.0004308245,0.0003674149,0.001273937,0.0007145357,0.0002396311,0.00002514324],"category_scores_gemma":[0.00006041024,0.0006864188,0.00006466689,0.000168835,0.0002206395,0.000204905,0.001626044,0.0008038849,0.00003051768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004949653,"about_ca_system_score_gemma":0.0001138586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048313,"about_ca_topic_score_gemma":0.0000452781,"domain_scores_codex":[0.9964592,0.00006236446,0.001041907,0.001229263,0.0004961339,0.0007111087],"domain_scores_gemma":[0.9974537,0.0007153373,0.000705044,0.0006653416,0.0001749291,0.0002856339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001234099,0.00001559891,0.0001476535,0.0001044119,0.00005516647,0.00008708463,0.0003976401,0.00005926005,9.394652e-7,0.542779,0.0007297952,0.4556222],"study_design_scores_gemma":[0.0005977418,0.000201681,0.00115051,0.0005814822,0.00009451387,0.0001140723,0.00007197584,0.816619,0.000001479691,0.1511187,0.02831689,0.001131931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003569327,0.00123422,0.9750584,0.0001610469,0.0003575903,0.000445492,0.00009209826,0.0001408187,0.02215337],"genre_scores_gemma":[0.04505215,0.0005251796,0.9389243,0.0003994329,0.000242345,0.000004481535,0.0001780773,0.0001155535,0.01455854],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8165597,"threshold_uncertainty_score":0.9997628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3000522262","doi":"10.1002/ece3.5970","title":"A checklist for choosing between R packages in ecology and evolution","year":2020,"lang":"en","type":"article","venue":"Ecology and Evolution","topic":"Data Analysis with R","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; York University","funders":"","keywords":"Workflow; Ecology; Computer science; Evolutionary ecology; Data science; Checklist; Process (computing); Management science; Biology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01662091244123715,"gpt":0.25156243227777,"spread":0.2349415198365328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710638,0.00009927735,0.0002284691,0.000130525,0.0001652258,0.00003762619,0.0001851465,0.00014979,0.000003285103],"category_scores_gemma":[0.0002233803,0.0001029543,0.00002614474,0.0002761654,0.00009768922,0.0004521017,0.0001778846,0.0001237365,0.00001273856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000110751,"about_ca_system_score_gemma":0.00005555801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004662804,"about_ca_topic_score_gemma":0.000600757,"domain_scores_codex":[0.9989512,0.0001092205,0.0002102648,0.000414323,0.00005285361,0.0002621708],"domain_scores_gemma":[0.9994766,0.0001754491,0.00008795336,0.0001390179,0.00003531764,0.00008566168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001510072,0.00001932683,0.9832228,0.00002572529,0.0000220103,0.000002748667,0.0002913364,0.00003626569,0.0004380626,0.01343358,0.001253084,0.001239975],"study_design_scores_gemma":[0.0005492356,0.0001862777,0.9494672,0.000004761326,0.00002493311,0.000005485382,0.00004112013,0.04168638,0.0000316363,0.007351156,0.0005488107,0.0001029614],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7950004,0.0002576856,0.1949748,0.009271924,0.000128656,0.0002188848,0.00001235642,0.00005715102,0.00007819249],"genre_scores_gemma":[0.9942607,0.00001984508,0.005219129,0.000305485,0.0001125366,0.00002742856,0.00002356228,0.000004357031,0.00002694858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1992603,"threshold_uncertainty_score":0.4198356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3088716273","doi":"10.1111/2041-210x.13494","title":"Going further with model verification and deep learning","year":2020,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Data Analysis with R","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Center for Northern Studies; Université de Moncton","funders":"New Brunswick Innovation Foundation; Polar Knowledge Canada","keywords":"Deep learning; Workflow; Computer science; Artificial intelligence; Machine learning; Data science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02567183586669051,"gpt":0.3102287904532507,"spread":0.2845569545865602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006730247,0.00005709976,0.0001094554,0.00006294592,0.00007533053,0.00002384808,0.0001073247,0.00005662666,0.000001976563],"category_scores_gemma":[0.0001666271,0.00005104221,0.000007217984,0.0002309883,0.00004924154,0.0003068495,0.00008569372,0.0001366508,0.00000364876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002545415,"about_ca_system_score_gemma":0.00001667631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005793386,"about_ca_topic_score_gemma":0.0000496238,"domain_scores_codex":[0.9991311,0.0003444742,0.0001027329,0.0002673387,0.0000404802,0.0001139079],"domain_scores_gemma":[0.9996755,0.0001103595,0.00005335575,0.0001043089,0.00001802129,0.00003853111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006858663,0.00003913099,0.6469844,0.00003875863,0.00004152191,0.000006864752,0.006684125,0.06981612,0.005949865,0.03480945,0.0000226059,0.2355386],"study_design_scores_gemma":[0.0001473687,0.00005741129,0.1598407,0.000002352799,0.000008005116,0.000004465744,0.0000599749,0.8372026,0.00004760577,0.002486453,0.00008949437,0.0000535908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08244342,0.0001888727,0.9162309,0.0008891454,0.00001818566,0.00004431967,1.238781e-7,0.0000330958,0.0001518861],"genre_scores_gemma":[0.5101151,0.00002351105,0.4897291,0.0001069009,0.000006139755,0.000005032449,9.108622e-7,0.00000191008,0.00001140574],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7673865,"threshold_uncertainty_score":0.2081441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W6943970825","doi":"10.17605/osf.io/p46mb","title":"ChrontouR","year":2020,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Data Analysis with R","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"","retraction":null,"screen_n_in":null,"score":{"opus":0.01921679443882397,"gpt":0.2496680565044222,"spread":0.2304512620655983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002186629,0.0002959463,0.0004134589,0.0001066098,0.000165182,0.0004043812,0.005092475,0.0001308506,0.2586565],"category_scores_gemma":[0.002130641,0.0003181359,0.0002337374,0.0006589741,0.00009366956,0.001103955,0.004758348,0.000407825,0.9136101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001397472,"about_ca_system_score_gemma":0.0001848384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001367264,"about_ca_topic_score_gemma":0.00003098148,"domain_scores_codex":[0.9951255,0.0004118418,0.0005409381,0.002787526,0.0006206914,0.0005135377],"domain_scores_gemma":[0.993288,0.0002155707,0.0002331808,0.005616892,0.0001326489,0.0005137274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009608894,0.0006463414,0.02850235,0.0001938888,0.0007268975,0.000356453,0.008877218,0.004558021,0.0203393,0.05878881,0.655895,0.2210197],"study_design_scores_gemma":[0.001105503,0.000003185507,0.01741743,0.00004692394,0.0001002978,0.00005494931,0.0001143899,0.1214437,0.02085385,0.006051891,0.831749,0.001058858],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005479111,0.000002159721,0.4125453,0.005660156,0.0002336095,0.0004016602,0.000009189251,0.0005558396,0.575113],"genre_scores_gemma":[0.7836401,0.00008352914,0.06704885,0.006134671,0.0004373773,0.0001837268,0.00003694302,0.00007729911,0.1423575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.778161,"threshold_uncertainty_score":0.999927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406534133","doi":"10.1016/0967-0653(93)94868-y","title":"10.1016/0967-0653(93)94868-y","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Data Analysis with R","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Multivariate statistics; Multivariate analysis; Econometrics; Environmental science; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.006010319443260933,"gpt":0.1739484471530853,"spread":0.1679381277098244,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002492851,0.0001624567,0.0002062022,0.0001358759,0.00009498157,0.0002360858,0.001676819,0.00004944794,0.9927971],"category_scores_gemma":[0.00003412754,0.0001521555,0.00008416911,0.0007696665,0.0000281014,0.0005575355,0.0002545103,0.0001067616,0.9990594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003847796,"about_ca_system_score_gemma":0.00004123492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003863172,"about_ca_topic_score_gemma":6.162339e-7,"domain_scores_codex":[0.9985058,0.0000608409,0.0002244807,0.0004816235,0.0003584491,0.0003688174],"domain_scores_gemma":[0.9984252,0.00005060651,0.00004067293,0.001211516,0.000052587,0.0002193875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004803995,0.00002978068,8.994927e-8,0.000001392594,0.00001596092,0.00001004578,0.00001737613,0.00009128445,0.000008824964,0.00001700011,0.3593646,0.6404389],"study_design_scores_gemma":[0.0001205629,0.00006577592,0.00002471734,0.000007920538,0.00001404354,0.000009993613,2.653404e-7,0.009171455,0.00008018097,0.00003564051,0.9902635,0.0002059709],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00003634768,0.00003773067,0.000714189,0.0007574504,0.000002486776,0.0001034689,0.00001247077,0.0002828958,0.998053],"genre_scores_gemma":[0.00005716425,1.524537e-7,0.004166448,0.0001666212,0.0000909694,0.00001230554,0.00002176912,0.00001358084,0.995471],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6402329,"threshold_uncertainty_score":0.6204721,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1486450196","doi":"10.18637/jss.v069.i04","title":"Parallel and Other Simulations in<i>R</i>Made Easy: An End-to-End Study","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Eidgenössische Technische Hochschule Zürich","keywords":"Computer science; Graphics; Computation; Set (abstract data type); Table (database); Scale (ratio); Contrast (vision); Contingency table; Algorithm; Computational science; Data mining; Computer graphics (images); Artificial intelligence; Programming language; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02613877045930482,"gpt":0.3101626526354363,"spread":0.2840238821761315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004828884,0.0001210394,0.0002876167,0.0002149228,0.00006044372,0.0001357485,0.0005501485,0.00003285046,0.0001852825],"category_scores_gemma":[0.0009009088,0.00007595955,0.00002891779,0.0002873663,0.00005609051,0.0006947822,0.0001555552,0.0001344881,0.00002440515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000522532,"about_ca_system_score_gemma":0.00007227833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004631328,"about_ca_topic_score_gemma":0.0001749647,"domain_scores_codex":[0.9983597,0.0001725447,0.0005003291,0.0002522159,0.0004843613,0.0002308064],"domain_scores_gemma":[0.998134,0.0009100978,0.0001612896,0.0003288275,0.0001293904,0.0003364618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001188557,0.001282488,0.7211863,0.00001294167,0.0001629407,0.0005537773,0.001761117,0.001741552,0.0003026386,0.01879176,0.001333498,0.2527521],"study_design_scores_gemma":[0.002366704,0.001358336,0.9609758,0.0000873117,0.00007601031,0.00007468704,0.0001246709,0.006039424,0.00001232507,0.02410753,0.004436296,0.000340957],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0670562,0.00002179962,0.9321252,0.0004888421,0.00006209196,0.00009744676,0.0001162219,0.00001804709,0.00001414548],"genre_scores_gemma":[0.7557872,0.000001966823,0.2437742,0.000334274,0.00004903072,0.000001622916,8.777165e-7,0.000008151104,0.00004265553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.688731,"threshold_uncertainty_score":0.309754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200001778","doi":"10.3233/sji-210875","title":"A quality framework for statistical algorithms","year":2021,"lang":"en","type":"article","venue":"Statistical Journal of the IAOS","topic":"Data Analysis with R","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University; Statistics Canada","funders":"","keywords":"Toolbox; Computer science; Quality (philosophy); Machine learning; Statistical learning; Transparency (behavior); Artificial intelligence; Data science; Process management; Operations research; Algorithm; Mathematics; Engineering; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.04160504749905197,"gpt":0.3772035243872404,"spread":0.3355984768881884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001125406,0.000128812,0.0003903509,0.00004267252,0.0001392748,0.0002437712,0.001311905,0.00006534805,0.0001344643],"category_scores_gemma":[0.007567965,0.00008305888,0.0001838037,0.0003527405,0.0001341662,0.000225525,0.0003348631,0.000416831,0.0000176308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006483158,"about_ca_system_score_gemma":0.0005149205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007177237,"about_ca_topic_score_gemma":0.000009424538,"domain_scores_codex":[0.9974978,0.0004283682,0.0007290281,0.0002497729,0.0007862107,0.00030884],"domain_scores_gemma":[0.9944167,0.003783785,0.0003620291,0.0006681065,0.0005426972,0.0002267437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002097009,0.0001028209,0.0001670901,0.00001991871,0.000105198,0.0001141122,0.00007557491,0.00002540408,0.00008603573,0.9395455,0.008702597,0.05103474],"study_design_scores_gemma":[0.0004718103,0.0001156839,0.009089807,0.0000559909,0.00009390929,0.0002410514,0.00005710813,0.01484371,0.0005410378,0.9680117,0.006312425,0.0001657386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001417831,0.00008980586,0.9933606,0.005017813,0.0007781758,0.00007556666,0.0004171288,0.000011207,0.0001079378],"genre_scores_gemma":[0.03728299,0.000008618669,0.961444,0.0009343637,0.0002193911,0.000003177156,0.000007043322,0.000009328728,0.00009104193],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05086901,"threshold_uncertainty_score":0.9060107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3117276733","doi":"","title":"NbClust Package. An examination of indices for determining the number of clusters","year":2012,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Analysis with R","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"R package; Statistics; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03115078739807493,"gpt":0.2749493531850409,"spread":0.243798565786966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01661547,0.0004059566,0.0006490687,0.0002210529,0.0004239398,0.0004364673,0.004471168,0.0003216139,0.0001085931],"category_scores_gemma":[0.002341138,0.0003673905,0.0003550144,0.0007803228,0.0007412969,0.001127905,0.002583128,0.0004468989,0.00002503889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144336,"about_ca_system_score_gemma":0.0002937604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001011376,"about_ca_topic_score_gemma":0.001492726,"domain_scores_codex":[0.987689,0.008984087,0.001167762,0.0008631095,0.0007909783,0.0005050419],"domain_scores_gemma":[0.9843917,0.004462672,0.002405098,0.004104018,0.004429446,0.0002070873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002264675,0.00203742,0.04229041,0.0008549033,0.0003806879,9.624515e-7,0.08430658,0.0002118367,0.001739115,0.3082079,0.000420407,0.5595272],"study_design_scores_gemma":[0.002421696,0.000004684459,0.4820411,0.004769078,0.0008337818,0.00002699253,0.001708578,0.3983446,0.08969886,0.004882828,0.01376989,0.001497949],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2728826,0.00037734,0.710866,0.003113926,0.0004714427,0.0007989426,0.0002247525,0.00006291935,0.01120212],"genre_scores_gemma":[0.8632663,0.0001412173,0.1329679,0.00006119237,0.00004098448,0.00007950079,0.0006846238,0.00003818692,0.002719989],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5903838,"threshold_uncertainty_score":0.9998778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406887161","doi":"10.21105/joss.07492","title":"ssdtools v2: An R package to fit Species Sensitivity Distributions","year":2025,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Ministry of Environment","keywords":"R package; Sensitivity (control systems); Mathematics; Statistics; Environmental science; Statistical physics; Physics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03521525920627432,"gpt":0.3171296502199887,"spread":0.2819143910137144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002403185,0.0001475656,0.0003403692,0.0001472874,0.0004260769,0.001029233,0.003638919,0.00003881922,0.00003605826],"category_scores_gemma":[0.0008763185,0.00009786092,0.000120762,0.001019474,0.00007535878,0.00148464,0.001888737,0.0003147716,0.00005173999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009123,"about_ca_system_score_gemma":0.0001911671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000849253,"about_ca_topic_score_gemma":0.0001227135,"domain_scores_codex":[0.9982254,0.0005079968,0.0004039533,0.0001951848,0.000402414,0.000265078],"domain_scores_gemma":[0.997454,0.0005407656,0.0002844033,0.001177258,0.0003669575,0.000176566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004649004,0.001411011,0.05072842,0.00007232797,0.001535902,0.000582358,0.01486877,0.01821874,0.009623182,0.03487357,0.5698124,0.2978084],"study_design_scores_gemma":[0.00200406,0.0008047266,0.4119951,0.0007687599,0.0007687554,0.0009275523,0.004340447,0.005299282,0.01475604,0.01029353,0.5467947,0.001247036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07660031,0.00004703406,0.9162905,0.006290703,0.0001526936,0.0001695059,0.00005494926,0.00004165963,0.0003526298],"genre_scores_gemma":[0.9551823,0.00001429476,0.039048,0.001968139,0.0001338691,0.000002784301,0.00001143581,0.00001252982,0.003626721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8785819,"threshold_uncertainty_score":0.9924914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285465633","doi":"10.1017/9781108993456","title":"A First Course in Statistical Programming with R","year":2021,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Data Analysis with R","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; University of British Columbia","funders":"","keywords":"Computer science; Code (set theory); Course (navigation); Programming language; C programming language; Software engineering; Data science; Software; Engineering; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.01345541887272999,"gpt":0.2065228774397496,"spread":0.1930674585670196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001563612,0.0003476832,0.0005332372,0.0002279469,0.0001324805,0.0002560009,0.001626212,0.0002123608,0.000002132858],"category_scores_gemma":[0.00001691155,0.0003735471,0.00009409861,0.00008572945,0.0002325374,0.0002707828,0.001037102,0.0005784898,0.00001034247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004129033,"about_ca_system_score_gemma":0.001076868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002722458,"about_ca_topic_score_gemma":0.0002076118,"domain_scores_codex":[0.9977951,0.0001042728,0.0002052102,0.0009373225,0.0005061454,0.0004519576],"domain_scores_gemma":[0.998034,0.0001619099,0.0001894922,0.00122086,0.0001754723,0.0002182467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003551215,0.00008081444,0.00004533151,0.0001801228,0.0002255651,0.0105684,0.0001226797,0.00003602378,7.583471e-7,0.8867995,0.09776334,0.004141978],"study_design_scores_gemma":[0.000681542,0.00007809867,0.0001823107,0.0004038054,0.0002016258,0.0000520908,0.00003678349,0.003895827,0.000008542626,0.00000334179,0.9939335,0.0005225273],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00002143713,0.000119858,0.2268866,0.00004654052,0.0001000035,0.0004236272,0.0002204334,0.0001765917,0.7720049],"genre_scores_gemma":[0.0001877745,0.00001705665,0.02399157,0.00005103268,0.0000461177,0.000002697386,0.0002336976,0.00002715799,0.9754429],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8961701,"threshold_uncertainty_score":0.9998717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2801007199","doi":"10.18637/jss.v084.c01","title":"<b>stampr</b>: Spatial-Temporal Analysis of Moving Polygons in <i>R</i>","year":2018,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Polygon (computer graphics); Computer science; R package; Core (optical fiber); Computer graphics (images); Algorithm; Computational science","retraction":null,"screen_n_in":null,"score":{"opus":0.01174774280374646,"gpt":0.2764526692167041,"spread":0.2647049264129577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008289578,0.0001420103,0.0006928263,0.0009017899,0.00005106394,0.00008692711,0.0009753344,0.00006215694,0.0002646181],"category_scores_gemma":[0.001278484,0.0001170268,0.0001934292,0.002205038,0.0001792416,0.0004925092,0.0002255704,0.0002381936,0.00001476478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007748092,"about_ca_system_score_gemma":0.0001890888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007530392,"about_ca_topic_score_gemma":0.001054551,"domain_scores_codex":[0.9975657,0.0001412948,0.001044935,0.0002414787,0.0007148074,0.0002917866],"domain_scores_gemma":[0.9975651,0.000660954,0.0006539068,0.0004492647,0.0004634703,0.0002072861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001800223,0.0007953543,0.8024803,0.00006475028,0.002231806,0.0007877509,0.001642515,0.001023144,0.0006044765,0.02012024,0.006582755,0.1634868],"study_design_scores_gemma":[0.001398793,0.001110306,0.8240443,0.0001755907,0.001604397,0.00006354679,0.0001362689,0.1495364,0.0007640462,0.01904575,0.001564832,0.0005556513],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02466681,0.00006037252,0.9746336,0.0002487954,0.0001481464,0.00003611225,0.0001156157,0.00001584388,0.00007465028],"genre_scores_gemma":[0.7287952,0.000006322825,0.2709761,0.0001266236,0.00006320373,5.079624e-7,0.00000992399,0.000005922328,0.00001626254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7041284,"threshold_uncertainty_score":0.4772215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3010960300","doi":"10.1002/eap.2123","title":"Ecological prediction at macroscales using big data: Does sampling design matter?","year":2020,"lang":"en","type":"article","venue":"Ecological Applications","topic":"Data Analysis with R","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Cégep Marie-Victorin","funders":"National Institute of Food and Agriculture; Directorate for Biological Sciences","keywords":"Sampling (signal processing); Ecology; Sampling design; Big data; Environmental science; Geography; Computer science; Biology; Data mining; Population; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.204191952903336,"gpt":0.319121722104141,"spread":0.1149297692008051,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003850559,0.0001941393,0.0002803575,0.00005361357,0.0005661657,0.0002465486,0.002417396,0.0001525628,0.0003139364],"category_scores_gemma":[0.0001340104,0.000134102,0.00007028613,0.0007413688,0.0001421128,0.000439272,0.0025445,0.0002079948,0.001072744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001339623,"about_ca_system_score_gemma":0.00004227282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005102887,"about_ca_topic_score_gemma":0.00001628077,"domain_scores_codex":[0.9976271,0.0001562511,0.0004488463,0.001137926,0.0002515118,0.0003783054],"domain_scores_gemma":[0.9978326,0.0004692716,0.0001767673,0.001200204,0.00006127919,0.0002599075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001931351,0.007050614,0.3806453,0.000290495,0.0009671375,0.000149463,0.001061178,0.07463625,0.1748983,0.07469854,0.1217869,0.1636227],"study_design_scores_gemma":[0.0004490997,0.0001896639,0.2159008,0.000007463103,0.0001360933,0.000035081,0.00004411914,0.6860693,0.001033576,0.009407019,0.08611543,0.0006123649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01473894,0.0000315497,0.9789736,0.004723992,0.0001189958,0.000585941,0.0002291502,0.000391398,0.0002064793],"genre_scores_gemma":[0.5530399,0.00002992642,0.4425494,0.003090616,0.0005130137,0.0003346821,0.0003532758,0.00001383968,0.00007538201],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.611433,"threshold_uncertainty_score":0.999705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1907586038","doi":"10.1201/9780429031069","title":"Graphics for Statistics and Data Analysis with R","year":2010,"lang":"en","type":"book","venue":"","topic":"Data Analysis with R","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Graphics; Statistical graphics; Bar chart; Computer science; Scatter plot; Plot (graphics); Chart; Pie chart; Nonparametric statistics; Visualization; Data mining; Computer graphics; Parametric statistics; Statistics; Computer graphics (images); Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02855733066667223,"gpt":0.2883750817602925,"spread":0.2598177510936203,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004501837,0.0002558182,0.000536728,0.0005587547,0.00009637667,0.0004661818,0.003179191,0.0001857172,0.00003571409],"category_scores_gemma":[0.00005735108,0.0001860508,0.00005742026,0.0005272696,0.0001353369,0.0004561317,0.001178192,0.0002909657,0.000008204232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001286542,"about_ca_system_score_gemma":0.0003567915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005968437,"about_ca_topic_score_gemma":0.00643525,"domain_scores_codex":[0.9980085,0.00001564703,0.0002624532,0.001094002,0.0004026463,0.0002167854],"domain_scores_gemma":[0.9946758,0.000356001,0.0002433773,0.00437633,0.0002163624,0.0001321223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003786059,0.00001581683,0.0001424798,0.00005037603,0.002423807,0.00001213915,0.00001928843,0.000004375708,4.284795e-7,0.6310375,0.3565957,0.00969422],"study_design_scores_gemma":[0.0002101561,0.00007900272,0.000147168,0.00001074152,0.004491927,0.000006172984,0.000001640088,0.3002128,0.000001324537,0.0271858,0.667172,0.0004813141],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[3.243182e-7,0.00006327271,0.9796072,0.00014144,0.00005118292,0.0001811343,0.003891773,0.00006668572,0.01599698],"genre_scores_gemma":[0.000006010686,0.00006264359,0.7008207,0.0002776126,0.00005371146,0.000007209997,0.008120753,0.00001717523,0.2906341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6038517,"threshold_uncertainty_score":0.7586932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4280635309","doi":"10.1371/journal.pone.0268426","title":"Addressing the need for interactive, efficient, and reproducible data processing in ecology with the datacleanr R package","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data Analysis with R","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"Helmholtz-Gemeinschaft; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Workflow; Data science; Data quality; Data processing; Outlier; Data type; Data mining; Quality (philosophy); Database; Service (business); Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1763984246597676,"gpt":0.3123639623910735,"spread":0.1359655377313059,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001568805,0.00009747095,0.0001753193,0.00009858283,0.0005639865,0.0003204013,0.00241856,0.00001216407,0.000009001542],"category_scores_gemma":[0.0003053367,0.00005660767,0.000009982145,0.0007250584,0.00009749462,0.0006399695,0.00294468,0.000268643,0.000001969577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003818736,"about_ca_system_score_gemma":0.00009155957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003836243,"about_ca_topic_score_gemma":0.0002013557,"domain_scores_codex":[0.9983256,0.0001972855,0.0001645731,0.0007659938,0.0003059177,0.0002406669],"domain_scores_gemma":[0.9970704,0.0003222065,0.0001707744,0.002359499,0.00005129319,0.00002580703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003632299,0.03318485,0.1918999,0.002575579,0.004232252,0.0005073327,0.1107527,0.02523788,0.1031652,0.01742195,0.1008568,0.4065332],"study_design_scores_gemma":[0.0008445724,0.0001939943,0.007806205,0.00009881966,0.000166914,0.00002266683,0.002139973,0.9843316,0.001711476,0.0002042339,0.002246503,0.0002330547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.859912,0.0007581398,0.1032476,0.03315304,0.0000943687,0.001900684,0.0003213533,0.0001501249,0.0004626739],"genre_scores_gemma":[0.9868762,0.000003926556,0.01197009,0.0007284147,0.00003895243,0.000133937,0.0001236339,0.00001264498,0.0001121832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9590937,"threshold_uncertainty_score":0.4494326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118093838","doi":"10.25336/p6531z","title":"Multistate Analysis of Life Histories with R","year":2015,"lang":"en","type":"article","venue":"Canadian Studies in Population","topic":"Data Analysis with R","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Sociology; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.08285411426822298,"gpt":0.3129009743640734,"spread":0.2300468600958504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000254742,0.00007925068,0.0003012908,0.0009029049,0.00004216325,0.00001765589,0.0002580124,0.00002141311,0.000001683092],"category_scores_gemma":[0.0002847894,0.00006964882,0.00002981825,0.002322175,0.00006080931,0.0003273418,0.00004499165,0.00003796649,0.000002076411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006098873,"about_ca_system_score_gemma":0.0001830274,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2285278,"about_ca_topic_score_gemma":0.9013144,"domain_scores_codex":[0.9991361,0.00004627747,0.0002444229,0.0002100409,0.0002002735,0.000162807],"domain_scores_gemma":[0.9990669,0.00003262883,0.0001186951,0.0003906186,0.0002034047,0.0001877226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006138519,0.0000085989,0.9649621,0.000009349352,0.0007306649,0.00001930867,0.005778243,0.01480697,6.107005e-7,0.009308207,0.00189158,0.002478176],"study_design_scores_gemma":[0.0004915751,0.00006064317,0.8960726,0.00002166688,0.000413465,0.000001030753,0.00180757,0.09607092,0.000004149941,0.0007091668,0.004052635,0.0002946365],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.953445,0.003584093,0.03752183,0.001633422,0.0008804825,0.000336691,0.00009494173,0.00009250468,0.002410998],"genre_scores_gemma":[0.9936088,0.000007804588,0.006142629,0.00009557477,0.00001111593,0.000006698184,0.0000463849,0.000003398026,0.00007762002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6727866,"threshold_uncertainty_score":0.7766095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}