{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":403,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":403,"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":"391c2756a87d","filters":{"venue":"Nature Methods"}},"results":[{"id":"W3003257820","doi":"10.1038/s41592-019-0686-2","title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","year":2020,"lang":"en","type":"article","venue":"Nature Methods","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":37936,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada)","funders":"Los Alamos National Laboratory; Science and Technology Facilities Council; National Nuclear Security Administration; U.S. Department of Energy","keywords":"Python (programming language); Code (set theory); Source code; De facto; Function (biology)","retraction":null,"screen_n_in":null,"score":{"opus":0.06918736113735903,"gpt":0.4267492565917377,"spread":0.3575618954543787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001011458,0.0001114607,0.0001564303,0.00009825653,0.0002166794,0.0003020123,0.0006568187,0.00008935143,0.000003670834],"category_scores_gemma":[0.0001146463,0.0001122679,0.00008425436,0.001275168,0.00004524681,0.0001838125,0.0002440374,0.0003469061,0.0000109008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004113236,"about_ca_system_score_gemma":0.00009094924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002698778,"about_ca_topic_score_gemma":0.000001371363,"domain_scores_codex":[0.9986832,0.0001202785,0.0002118859,0.0005464832,0.0002191555,0.000219029],"domain_scores_gemma":[0.9988914,0.0005488148,0.00007937662,0.0002592358,0.0001152983,0.0001058967],"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":[0.000007227152,0.00007559549,0.00015819,0.00002813517,0.00001094927,0.000001677127,0.001464917,0.002023079,0.009187564,0.3521201,0.002324782,0.6325978],"study_design_scores_gemma":[0.0003318004,0.00003385427,0.002016282,0.00000867799,0.000002795016,0.000001933815,0.00002015999,0.8807248,0.003342279,0.05258584,0.06077611,0.0001554479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002797633,0.0002420718,0.9900469,0.005429353,0.0006453678,0.0003322247,0.0000103699,0.0001147829,0.0003813226],"genre_scores_gemma":[0.2123619,4.671675e-7,0.786177,0.001197424,0.0001928003,0.00001692553,0.00001728766,0.000008802631,0.00002746833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8787017,"threshold_uncertainty_score":0.4578153,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2614081736","doi":"10.1038/nmeth.4285","title":"ModelFinder: fast model selection for accurate phylogenetic estimates","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":18775,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Phylogenetic tree; Selection (genetic algorithm); Computational biology; Evolutionary biology; Model selection; Biology; Phylogenetics; Computer science; Genetics; Artificial intelligence; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.06154516257025337,"gpt":0.4052972905823507,"spread":0.3437521280120973,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000560403,0.0001404111,0.0001987039,0.00005069871,0.001014428,0.00007788956,0.000277036,0.0002881823,0.00006076043],"category_scores_gemma":[0.0005471571,0.000110508,0.00007517826,0.00004471083,0.0001130741,0.0001430106,0.00001213778,0.0002894455,0.00001186909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003457736,"about_ca_system_score_gemma":0.0000378006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001052131,"about_ca_topic_score_gemma":0.007113614,"domain_scores_codex":[0.9991521,0.00008276659,0.0001307288,0.0002739181,0.00009306387,0.0002673781],"domain_scores_gemma":[0.9991782,0.0003012592,0.0001272024,0.0002307194,0.0000992943,0.00006331733],"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":[0.00014532,0.00001812483,0.6138385,0.00004027053,0.0001193061,8.797423e-7,0.0002481554,0.1020767,0.0005661797,0.001757808,0.002758262,0.2784305],"study_design_scores_gemma":[0.0001974623,0.00003876255,0.2441962,0.000003994244,0.00003073268,0.000005178695,0.00001494276,0.7411613,0.0003461981,0.01233129,0.001560165,0.0001137876],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02531503,0.007587229,0.9433647,0.001217946,0.001088502,0.0003532823,0.00008825625,0.00009683563,0.02088826],"genre_scores_gemma":[0.5413075,0.00005590474,0.4577554,0.0001702951,0.00008713238,0.000004752111,0.00001437505,0.000002628233,0.000602007],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6390846,"threshold_uncertainty_score":0.780226,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2587625522","doi":"10.1038/nmeth.4169","title":"cryoSPARC: algorithms for rapid unsupervised cryo-EM structure determination","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10710,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; York University; University of Toronto","funders":"","keywords":"Cryo-electron microscopy; Bottleneck; Computer science; Software; Algorithm; Single particle analysis; Bayesian probability; Gradient descent; Resolution (logic); Image processing; Artificial intelligence; Data mining; Image (mathematics); Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.01897084099966042,"gpt":0.4533618990654899,"spread":0.4343910580658295,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002770657,0.0001673421,0.0001515526,0.00002918161,0.0004337167,0.00007394014,0.0004571352,0.0005162385,0.00001689258],"category_scores_gemma":[0.0002848299,0.0001535854,0.0001066579,0.000036792,0.00006521633,0.000008796712,0.0000925686,0.0002707703,4.546961e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001738546,"about_ca_system_score_gemma":0.000036853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001603497,"about_ca_topic_score_gemma":0.000008852972,"domain_scores_codex":[0.9990864,0.00005371916,0.0001438216,0.0004025197,0.00006933327,0.0002442179],"domain_scores_gemma":[0.9988215,0.00002702906,0.0001505847,0.0007843228,0.00016115,0.00005544],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002070085,0.00001059804,0.00002343288,0.000009678904,0.00000997189,1.426471e-7,0.000008217983,0.000001667576,0.7396436,0.0003444095,0.0009863679,0.2589412],"study_design_scores_gemma":[0.0002872992,0.0001395344,0.0005095697,0.00000471388,0.00001715003,0.000005737539,0.000007060051,0.0002774215,0.7773069,0.004805342,0.2164808,0.000158464],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01580366,0.00169898,0.9809579,0.0003569598,0.000203623,0.0005397084,0.0001059558,0.00003728421,0.0002959597],"genre_scores_gemma":[0.1069918,0.0001442947,0.891023,0.0003966519,0.0004507938,0.0001220415,0.0002162346,0.00003408467,0.0006211528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2587827,"threshold_uncertainty_score":0.6263033,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951583631","doi":"10.1038/s41592-018-0235-4","title":"fMRIPrep: a robust preprocessing pipeline for functional MRI","year":2018,"lang":"en","type":"article","venue":"Nature Methods","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":4204,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; European Commission; Laura and John Arnold Foundation","keywords":"Preprocessor; Computer science; Workflow; Interpretability; Pipeline (software); Data mining; Data pre-processing; Artificial intelligence; Inference; Software; Machine learning; Pattern recognition (psychology); Programming language; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.09735307127302831,"gpt":0.4077897963696672,"spread":0.3104367250966389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001564552,0.000194606,0.0002226472,0.0001243695,0.0006111739,0.00006388324,0.0002080309,0.0002540066,0.0001217212],"category_scores_gemma":[0.04862902,0.0001675332,0.0001238374,0.0005090766,0.0002545677,0.00023782,0.0001342031,0.0004889179,0.00002826769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006857378,"about_ca_system_score_gemma":0.00008679697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001923256,"about_ca_topic_score_gemma":0.000008622912,"domain_scores_codex":[0.9979679,0.0003169725,0.0002079352,0.0008665401,0.0003212306,0.0003194157],"domain_scores_gemma":[0.9890992,0.01000779,0.0001158012,0.0003457696,0.0003670229,0.00006440069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009898933,0.0002329202,0.0003836011,0.0001258416,0.00004603916,0.000004256867,0.0004483665,0.0006224133,0.5202721,0.01476747,0.3380283,0.1240789],"study_design_scores_gemma":[0.000615748,0.0001386791,0.0008188412,0.00002668342,0.00003165742,0.00004351163,0.0000356488,0.02203839,0.5144792,0.01535872,0.4461431,0.0002698546],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001352303,0.0003836954,0.9764845,0.008217993,0.003531989,0.0003722739,0.00002377794,0.0002441294,0.009389322],"genre_scores_gemma":[0.1438922,0.000008809413,0.8239032,0.0192452,0.004303904,0.0001939929,0.000006221325,0.00005919863,0.008387228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1525813,"threshold_uncertainty_score":0.9593848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105916176","doi":"10.1038/nmeth.1237","title":"Robust single-particle tracking in live-cell time-lapse sequences","year":2008,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Fluorescence Microscopy Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2109,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"National Institute of General Medical Sciences","keywords":"Tracking (education); Particle (ecology); Biological system; Endocytic cycle; Particle filter; Computer science; Dynamin; Physics; Biology; Endocytosis; Artificial intelligence; Receptor; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03017384689873241,"gpt":0.3528801372240799,"spread":0.3227062903253475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004830941,0.0001797632,0.0001888784,0.00005015065,0.00007874665,0.00001508223,0.000265298,0.0004667467,0.000032476],"category_scores_gemma":[0.0003314836,0.0001715119,0.00007166575,0.0002146696,0.0001601583,0.00001285188,0.00008860057,0.0004578565,0.00001139398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003860379,"about_ca_system_score_gemma":0.00005287958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008729801,"about_ca_topic_score_gemma":0.000009594377,"domain_scores_codex":[0.9986498,0.0002670237,0.0002163461,0.0004308026,0.0001117419,0.0003242829],"domain_scores_gemma":[0.9993927,0.0000506536,0.0000788138,0.0003359356,0.00007696115,0.00006486486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003735126,0.00008962234,0.002317945,0.00000845665,0.00000441792,0.00002344303,0.0001025867,0.00008993834,0.9915327,0.00001061389,0.0005271835,0.005255781],"study_design_scores_gemma":[0.0002210743,0.0001643719,0.0006583264,0.00002059634,0.000005057667,0.00004414556,0.00003046733,0.0001896255,0.9929907,0.0001391684,0.005327333,0.0002091147],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8806195,0.00690629,0.1099035,0.0001035899,0.000133582,0.0002815816,0.000005727343,0.00009347197,0.001952729],"genre_scores_gemma":[0.357944,0.0001514688,0.6408716,0.0002573462,0.00009282359,0.00001355593,0.00001446332,0.00002472808,0.0006299533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5309681,"threshold_uncertainty_score":0.6994052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987219048","doi":"10.1038/nmeth.2810","title":"Similarity network fusion for aggregating data types on a genomic scale","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2096,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; University of Toronto; SickKids Foundation","funders":"","keywords":"Complementarity (molecular biology); Computer science; Data type; Computational biology; Similarity (geometry); Data mining; Sensor fusion; Biological data; Bioinformatics; Artificial intelligence; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03629640495208623,"gpt":0.4015071126948916,"spread":0.3652107077428053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001461017,0.0001021008,0.0001094207,0.00001948835,0.0001226367,0.00001960478,0.0003380751,0.0003371656,0.000009793023],"category_scores_gemma":[0.0006151896,0.00008622878,0.00004679987,0.00007165055,0.00002040189,0.000002389224,0.0001661689,0.0001939229,0.00000202549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009112514,"about_ca_system_score_gemma":0.00003832065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001299754,"about_ca_topic_score_gemma":0.00001030402,"domain_scores_codex":[0.9989242,0.0002947274,0.0001208672,0.0004255228,0.00007453234,0.0001601553],"domain_scores_gemma":[0.9989381,0.00008824364,0.00009277484,0.0007760149,0.00005597194,0.00004889306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001080053,0.00001919912,0.0002186595,0.00001535547,0.00001248269,3.467152e-8,0.000009916789,0.0001806505,0.694872,0.0003471917,0.02847094,0.2757456],"study_design_scores_gemma":[0.0003200259,0.000111529,0.001606982,0.00002300763,0.00001881401,0.000001095087,0.000009188792,0.006521226,0.1928847,0.001297192,0.797068,0.0001382203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04728657,0.00408188,0.9396948,0.00139874,0.001735509,0.0004956727,0.00005379592,0.00004210126,0.005210903],"genre_scores_gemma":[0.2887183,0.0001187172,0.7051285,0.00243825,0.002129901,0.00003517778,0.000635849,0.00003164197,0.0007637296],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7685971,"threshold_uncertainty_score":0.3516307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3108495343","doi":"10.1038/s41592-020-00990-8","title":"Non-uniform refinement: adaptive regularization improves single-particle cryo-EM reconstruction","year":2020,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1859,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; Canadian Sugar Institute; University of Toronto","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Regularization (linguistics); Algorithm; Computer science; Particle (ecology); Computational biology; Biological system; Physics; Artificial intelligence; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01291264938910066,"gpt":0.3460975753854251,"spread":0.3331849259963245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001518061,0.0001295392,0.0001143834,0.00001640177,0.00009874303,0.000021264,0.0001272426,0.0002837447,0.00001251609],"category_scores_gemma":[0.0000869278,0.0001259672,0.00006005848,0.0002130037,0.00004244958,0.000009356178,0.00006135838,0.0002549856,0.000002367602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000241863,"about_ca_system_score_gemma":0.00002843164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001144938,"about_ca_topic_score_gemma":0.000002560049,"domain_scores_codex":[0.9991823,0.00004663201,0.0001726688,0.0003503556,0.0000645018,0.0001835041],"domain_scores_gemma":[0.9994754,0.000008290326,0.000106328,0.0002334605,0.0001029983,0.0000735178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005703325,0.00001881151,0.00001245177,0.0000059556,0.0000138779,1.385796e-7,0.0000300982,0.00001978884,0.8864765,0.0009210361,0.0004482947,0.111996],"study_design_scores_gemma":[0.0001859669,0.0003648355,0.00005072758,0.000005751644,0.00001674879,0.000006646188,0.00006242939,0.001611374,0.9585435,0.001239592,0.03777041,0.0001420365],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04987108,0.0005418226,0.9473021,0.0007244161,0.00007232048,0.0002809799,0.000009507797,0.00006091836,0.001136844],"genre_scores_gemma":[0.2188451,0.00007234378,0.7793472,0.001036051,0.0002312583,0.00004399481,0.00007722038,0.00002338438,0.0003233824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.168974,"threshold_uncertainty_score":0.5136791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167844024","doi":"10.1038/nmeth.2557","title":"The CRAPome: a contaminant repository for affinity purification–mass spectrometry data","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1804,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto; Université de Montréal; Montreal Clinical Research Institute; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse; National Cancer Institute; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Computational biology; Mass spectrometry; Tandem affinity purification; Chemistry; Protein purification; Proteome; Chromatography; Affinity chromatography; Biology; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.02834747888140295,"gpt":0.390944764862205,"spread":0.3625972859808021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008172279,0.0001475832,0.0001655849,0.00002705424,0.000483719,0.0001107459,0.001137454,0.0003399998,0.00005220613],"category_scores_gemma":[0.0007740139,0.00010386,0.00007167215,0.0001793911,0.00009263693,0.0001422211,0.0001481945,0.0007303248,0.000005340549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006477764,"about_ca_system_score_gemma":0.00004766299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001258647,"about_ca_topic_score_gemma":0.000001468178,"domain_scores_codex":[0.998834,0.00006111724,0.0002834884,0.000443626,0.000124867,0.0002529638],"domain_scores_gemma":[0.996416,0.00112683,0.00021422,0.001995196,0.0001803143,0.00006739314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001377097,0.00003583892,0.00006011103,0.00003338122,0.00003060023,2.874895e-7,0.00001352146,4.884423e-7,0.9317422,0.01926312,0.008094177,0.0407125],"study_design_scores_gemma":[0.0001223808,0.000009530288,0.0001468958,0.000008739044,0.00002244737,0.000006947897,0.00005285689,0.0009229359,0.6789585,0.04160862,0.2780058,0.000134268],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001758529,0.002303375,0.982827,0.001866239,0.0001537348,0.0006989294,0.00009613654,0.0002111737,0.01008488],"genre_scores_gemma":[0.01849716,0.0001572419,0.975526,0.0001125058,0.0003061267,0.001115564,0.0001068064,0.00002964753,0.004148908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2699116,"threshold_uncertainty_score":0.4235286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008003211","doi":"10.1038/s41592-020-0772-5","title":"Author Correction: SciPy 1.0: fundamental algorithms for scientific computing in Python","year":2020,"lang":"en","type":"erratum","venue":"Nature Methods","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":1605,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada)","funders":"","keywords":"Python (programming language); Computer science; Programming language; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.05646006578559967,"gpt":0.4217380919404318,"spread":0.3652780261548322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002141622,0.0004152122,0.0005816485,0.0004652396,0.0005801536,0.0009610235,0.001582331,0.000829022,0.00001069525],"category_scores_gemma":[0.0003278157,0.0004409676,0.0003131093,0.002617534,0.0001108473,0.0002430297,0.0006193827,0.002892951,0.00002571182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002726172,"about_ca_system_score_gemma":0.0007420637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001231458,"about_ca_topic_score_gemma":0.00001415566,"domain_scores_codex":[0.9964309,0.0003751093,0.000573874,0.00151361,0.0006344179,0.0004721071],"domain_scores_gemma":[0.9971519,0.001091059,0.0004004627,0.0007802381,0.0003848094,0.0001915208],"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":[0.000004896183,0.00006197886,0.000003957256,0.00005915833,0.0000224465,0.000002897327,0.0003874599,0.0002708102,0.00006225893,0.02131853,0.7575359,0.2202697],"study_design_scores_gemma":[0.0001552437,0.00003440058,0.0002138253,0.00006406404,0.00001094249,0.000007071891,0.00001289509,0.4250129,0.0000694441,0.01674794,0.557402,0.0002692918],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003072195,0.001159234,0.8451936,0.004005762,0.145346,0.0007468059,0.00004734577,0.0002417165,0.003256518],"genre_scores_gemma":[0.0003426624,0.000005317936,0.9471742,0.000785731,0.004577854,0.000113455,0.0007192175,0.00006076508,0.04622083],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.424742,"threshold_uncertainty_score":0.9998042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3148042916","doi":"10.1038/s41592-021-01098-3","title":"Martini 3: a general purpose force field for coarse-grained molecular dynamics","year":2021,"lang":"en","type":"article","venue":"Nature Methods","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1565,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Engineering and Physical Sciences Research Council; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Molecular dynamics; Dynamics (music); Field (mathematics); Force field (fiction); Computer science; Nanotechnology; Computational biology; Chemistry; Statistical physics; Biology; Physics; Materials science; Computational chemistry; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.005701356502087055,"gpt":0.3456961324673609,"spread":0.3399947759652739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000390079,0.0002156156,0.000236583,0.00003390191,0.00008102795,0.00003615365,0.0002287297,0.0008019567,0.00001891844],"category_scores_gemma":[0.001209949,0.0002071462,0.0002603187,0.0001470257,0.00003424551,0.000003523356,0.0001556917,0.0003505646,6.812306e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002830313,"about_ca_system_score_gemma":0.0001987189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003543327,"about_ca_topic_score_gemma":0.00004748957,"domain_scores_codex":[0.9986504,0.0001958076,0.0002176015,0.0004883447,0.0001168562,0.0003309991],"domain_scores_gemma":[0.9989416,0.00008120033,0.00008165248,0.0005635142,0.0002350333,0.00009701129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001627027,0.00002701262,0.00006421316,0.00004745676,0.00009953621,0.00002860486,0.00002004285,0.00006665551,0.8991717,0.01485731,0.001532056,0.08392271],"study_design_scores_gemma":[0.0007029463,0.0002146559,0.00003096055,0.000008446852,0.00005667992,0.00007901556,0.00002420496,0.008631498,0.8793232,0.01213766,0.09848434,0.0003063561],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05398415,0.003641991,0.9375804,0.0009577471,0.0006545105,0.0003749834,0.00007529014,0.00002797161,0.002702961],"genre_scores_gemma":[0.07819549,0.00004180017,0.9095846,0.005613314,0.0004255233,0.00005879554,0.0007381791,0.00005005149,0.005292256],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09695229,"threshold_uncertainty_score":0.8447177,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000860171","doi":"10.1038/nmeth.2212","title":"A travel guide to Cytoscape plugins","year":2012,"lang":"en","type":"article","venue":"Nature Methods","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1560,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Cancer Institute","keywords":"Plug-in; Computer science; Visualization; Set (abstract data type); Data science; Software; World Wide Web; Data mining; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0102531177485946,"gpt":0.3616017069744648,"spread":0.3513485892258702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009592228,0.0001460256,0.0001440443,0.00004068423,0.00005606506,0.00001746236,0.0002113101,0.0004745489,0.00003658122],"category_scores_gemma":[0.0001457193,0.0001249466,0.00009337974,0.0001140887,0.00002050064,0.000003389287,0.0001276708,0.0002807271,0.00003036335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001430954,"about_ca_system_score_gemma":0.0000315624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004422918,"about_ca_topic_score_gemma":0.000004636656,"domain_scores_codex":[0.9990928,0.00008809839,0.0001923828,0.0001646426,0.00008873135,0.0003733601],"domain_scores_gemma":[0.9992996,0.00002213653,0.00004678742,0.000374713,0.00004760832,0.0002091514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005983633,0.00005906169,0.0004200067,0.00001979775,0.00008718466,5.96353e-7,0.0003080707,0.00003463576,0.698526,0.002934036,0.1290313,0.1685195],"study_design_scores_gemma":[0.0002019479,0.00006963,0.003221867,0.000005225842,0.00001685165,0.0000197746,0.00006198448,0.00009479487,0.1605719,0.0001227856,0.8354073,0.0002059718],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02415998,0.00619096,0.9076605,0.0005853636,0.001707959,0.0003235631,0.00002501448,0.0000230461,0.05932355],"genre_scores_gemma":[0.2426427,0.00005373691,0.7470352,0.005178189,0.001412309,0.0000185037,0.0000498414,0.00002776586,0.003581716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.706376,"threshold_uncertainty_score":0.5095174,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020098484","doi":"10.1038/nmeth.1455","title":"Coding of facial expressions of pain in the laboratory mouse","year":2010,"lang":"en","type":"article","venue":"Nature Methods","topic":"Neuroendocrine regulation and behavior","field":"Psychology","cited_by":1539,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; McGill University","funders":"","keywords":"Facial expression; Coding (social sciences); Facial Action Coding System; Noxious stimulus; Pain assessment; Audiology; Psychology; Neuroscience; Medicine; Pain management; Nociception; Anesthesia; Communication; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03204713607894186,"gpt":0.4560872276518789,"spread":0.424040091572937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001372262,0.00006485407,0.0001388372,0.00009951353,0.00002074788,0.000003175942,0.0001979018,0.000143347,0.0003899834],"category_scores_gemma":[0.0005459629,0.00004296898,0.00004879237,0.0002682414,0.00006176587,0.00002234215,0.00002019523,0.0007859094,0.000001363196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002473123,"about_ca_system_score_gemma":0.00001647109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008433435,"about_ca_topic_score_gemma":0.00001431343,"domain_scores_codex":[0.9981048,0.00136609,0.0001932449,0.0001166338,0.0001160649,0.0001032034],"domain_scores_gemma":[0.9989011,0.0006137499,0.00009064707,0.0003175593,0.00005652897,0.00002045377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002109859,0.0001303519,0.005832223,0.000007972303,0.000003679954,0.000005729719,0.000783037,4.018311e-7,0.9397813,0.007095173,0.002770465,0.04356853],"study_design_scores_gemma":[0.0008520584,0.00009188105,0.1482753,0.0000169332,0.0000256759,0.00001010037,0.0009036356,0.00001555693,0.6164012,0.0003311519,0.2329388,0.0001377851],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956631,0.00009435898,0.001133403,0.0005428998,0.0008037754,0.00016285,0.00002748239,0.00001605484,0.001556072],"genre_scores_gemma":[0.9650091,9.297436e-7,0.0340615,0.0002445539,0.00007289668,0.0000157635,0.000002277445,0.000009118587,0.0005838962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3233801,"threshold_uncertainty_score":0.4270045,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1519765314","doi":"10.1038/nmeth.3444","title":"A complete bacterial genome assembled de novo using only nanopore sequencing data","year":2015,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1513,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Medical Research Council","keywords":"Nanopore sequencing; Contig; Nanopore; Sequence assembly; Computational biology; Genome; Bacterial genome size; Biology; Chromosome; Genetics; Gene; Nanotechnology; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.140605227442007,"gpt":0.408737940380948,"spread":0.268132712938941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00138384,0.0001963394,0.0002458936,0.00003830424,0.00009729513,0.00004184507,0.0005433437,0.0003714178,0.00000705021],"category_scores_gemma":[0.0004531062,0.0001827867,0.0000585324,0.00009983129,0.00004270732,0.000001758541,0.0006689111,0.0002402771,0.000001729012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006947826,"about_ca_system_score_gemma":0.0005652552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000412044,"about_ca_topic_score_gemma":0.00004353693,"domain_scores_codex":[0.9985251,0.0003236591,0.0002069129,0.0004904133,0.0001191167,0.0003348411],"domain_scores_gemma":[0.9987556,0.00003251821,0.0001018046,0.0008208934,0.0001499099,0.0001393288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006062161,0.00001133869,0.0005429533,0.000009836849,0.00009829366,0.000007152707,0.0001142347,0.00009316621,0.9969649,0.0000321554,0.0002019606,0.001863386],"study_design_scores_gemma":[0.002034815,0.0003401059,0.003738743,0.00002347715,0.0002113879,0.0005567403,0.0004915753,0.002194849,0.3200468,0.001097227,0.6683688,0.0008955012],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9605343,0.00400326,0.03334662,0.0000818503,0.0007968819,0.0001595726,0.0001618462,0.000007507792,0.0009082046],"genre_scores_gemma":[0.4734,0.00005474668,0.5249541,0.0003436193,0.0008819848,0.00000276947,0.0002666065,0.0000296846,0.00006640976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6769181,"threshold_uncertainty_score":0.7453824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059699217","doi":"10.1038/nmeth1068","title":"Genome-wide profiles of STAT1 DNA association using chromatin immunoprecipitation and massively parallel sequencing","year":2007,"lang":"en","type":"article","venue":"Nature Methods","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1491,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"Genome British Columbia; Canada's Michael Smith Genome Sciences Centre","keywords":"Chromatin immunoprecipitation; Massive parallel sequencing; Biology; ChIP-sequencing; Immunoprecipitation; DNA sequencing; Chromatin; Computational biology; Molecular biology; Genome; Massively parallel; DNA; Human genome; Genetics; Gene; Promoter; Gene expression; Chromatin remodeling; Computer science; Parallel computing","retraction":null,"screen_n_in":null,"score":{"opus":0.01875624537308387,"gpt":0.3527361961198546,"spread":0.3339799507467707,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001457308,0.00008991139,0.0001203925,0.00005336693,0.00006561819,0.00001419373,0.0000700669,0.0002975599,0.000005108044],"category_scores_gemma":[0.0004292101,0.00008602112,0.00004064562,0.0001091452,0.00002751393,0.000007248264,0.00002973192,0.0001449765,2.113852e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001443574,"about_ca_system_score_gemma":0.000101116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001631275,"about_ca_topic_score_gemma":0.000007231964,"domain_scores_codex":[0.9991642,0.0001522816,0.0002211249,0.000190487,0.0001139738,0.0001579497],"domain_scores_gemma":[0.9992971,0.00008114239,0.0002612711,0.0001523279,0.0001760816,0.00003209607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002496418,0.000008440242,0.003482234,0.00002098144,0.00004403964,2.565634e-7,0.0001815866,0.00009732175,0.9874982,0.00006796046,0.00001825633,0.008555737],"study_design_scores_gemma":[0.0002739071,0.00005031063,0.2034402,0.00001331927,0.0000319448,0.000002921156,0.0002921261,0.0001959032,0.7919431,0.0002849273,0.003338456,0.000132863],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7943631,0.002859249,0.2021262,0.00003245074,0.00009468549,0.00015108,0.00001089782,0.000005256358,0.0003570269],"genre_scores_gemma":[0.6472743,0.0001054493,0.3522133,0.00005816506,0.00007855184,0.000008909667,0.0000460199,0.00001058147,0.0002046884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.199958,"threshold_uncertainty_score":0.3507839,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792919287","doi":"10.1038/nmeth.4642","title":"Statistics versus machine learning","year":2018,"lang":"en","type":"article","venue":"Nature Methods","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1490,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Institute of Mental Health","keywords":"Computer science; Statistics; Computational biology; Artificial intelligence; Machine learning; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02982139966341541,"gpt":0.4125295686340756,"spread":0.3827081689706602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003866513,0.00007241018,0.00007851949,0.00002949892,0.0001739495,0.00006464415,0.000434364,0.00009604434,0.00003503096],"category_scores_gemma":[0.0001659767,0.0000598747,0.00002200786,0.0003495865,0.00003982949,0.00007670196,0.0001414544,0.0005244471,0.00004007155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001137918,"about_ca_system_score_gemma":0.00001463402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004844168,"about_ca_topic_score_gemma":0.000006864556,"domain_scores_codex":[0.9992747,0.0001614074,0.00008544438,0.0002156506,0.0001083402,0.0001545011],"domain_scores_gemma":[0.9990788,0.000439866,0.00004538825,0.0002986443,0.00008227558,0.00005504736],"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":[0.00000770559,0.0000103932,0.00003920195,0.000001862228,0.000007813067,0.000001967966,0.00005851593,0.00002788398,0.001118475,0.3299319,0.006085683,0.6627086],"study_design_scores_gemma":[0.0002398149,0.0001285674,0.0004184403,0.000003162122,0.000006566474,0.000004651032,0.000002247658,0.2451328,0.004626358,0.01446938,0.734838,0.0001299858],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001255978,0.0003676185,0.9930895,0.0006495796,0.0009980379,0.00004865931,0.000002856095,0.0001282558,0.004589885],"genre_scores_gemma":[0.02861033,0.0000170672,0.9699241,0.0003990953,0.0003432235,0.000004700017,0.000004128671,0.000006137806,0.0006912137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7287523,"threshold_uncertainty_score":0.2441619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2725171488","doi":"10.1038/nmeth.4346","title":"Principal component analysis","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Data Mining and Machine Learning Applications","field":"Computer Science","cited_by":1399,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Principal component analysis; Component (thermodynamics); Computational biology; Computer science; Biology; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02683354521457981,"gpt":0.4465176621825136,"spread":0.4196841169679338,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001403989,0.00009144628,0.0001761903,0.0001332216,0.0005592072,0.0003975374,0.002188739,0.0001259773,0.00001182646],"category_scores_gemma":[0.0005682755,0.00007710826,0.0001114888,0.0002792868,0.00004431514,0.0002224176,0.0005903717,0.0005618266,0.00002947774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001511561,"about_ca_system_score_gemma":0.00002321199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000615145,"about_ca_topic_score_gemma":0.00000933129,"domain_scores_codex":[0.9989833,0.0001993806,0.0001176542,0.0003712502,0.0001641057,0.0001642922],"domain_scores_gemma":[0.9972376,0.0001751537,0.000163395,0.00228931,0.00005396213,0.00008057408],"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":[0.000002504584,0.00006099746,0.007355157,0.000005565767,0.0003047526,0.00000611312,0.0002742806,0.0002241853,0.001333523,0.2606017,0.001712788,0.7281185],"study_design_scores_gemma":[0.0001724448,0.00001877826,0.4301294,0.000004322633,0.0001567563,0.000006438401,0.000004407341,0.1487022,0.001280094,0.003377536,0.4159323,0.0002153502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002531118,0.0001244114,0.9810972,0.002764844,0.0003102655,0.00004977244,0.000004276017,0.0001608927,0.01295728],"genre_scores_gemma":[0.2795486,0.000003308863,0.7194675,0.0002094708,0.00005307204,0.000009713109,0.000009866034,0.000003545073,0.0006949496],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7279031,"threshold_uncertainty_score":0.4301026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385302529","doi":"10.1038/s41592-023-01940-w","title":"CheckM2: a rapid, scalable and accurate tool for assessing microbial genome quality using machine learning","year":2023,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1386,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Parks Canada","funders":"Australian Government; McMaster University; Queensland University of Technology; National Science Foundation","keywords":"Genome; Metagenomics; Computational biology; Scalability; Bacterial genome size; Biology; Computer science; Genome size; Gene; Genetics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05349198636756088,"gpt":0.4172533937874246,"spread":0.3637614074198637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001838075,0.0001747559,0.0002455885,0.00005239685,0.0002884665,0.00007177374,0.0001105302,0.0003126388,0.000003740443],"category_scores_gemma":[0.000607276,0.0001628897,0.000101172,0.0001563675,0.00005542873,0.000001884675,0.0002166394,0.0002486855,5.549455e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001314324,"about_ca_system_score_gemma":0.00004794978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001242433,"about_ca_topic_score_gemma":0.000004707709,"domain_scores_codex":[0.9987074,0.0003031709,0.0002191013,0.0004052944,0.00006208642,0.0003029802],"domain_scores_gemma":[0.9994598,0.0001284987,0.0001114038,0.0001870033,0.00006729578,0.00004602105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004392956,0.000007927234,0.002022096,0.0000528197,0.00007674395,5.910361e-7,0.00006526511,0.0002053242,0.9858388,0.00002133151,0.00005306767,0.01161212],"study_design_scores_gemma":[0.001720266,0.0001852628,0.05976642,0.00002420669,0.0001276918,0.00002809705,0.0002372083,0.006841247,0.6844006,0.0005633691,0.245327,0.000778612],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9678394,0.008342216,0.02295976,0.0001532572,0.0003142652,0.0002427329,0.00004730391,0.00001426452,0.00008678491],"genre_scores_gemma":[0.6648521,0.0005875888,0.3333418,0.0002939194,0.0004125006,0.00001937866,0.000120733,0.00004180419,0.0003301067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.310382,"threshold_uncertainty_score":0.6642448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594599876","doi":"10.1038/nmeth.4185","title":"EV-TRACK: transparent reporting and centralizing knowledge in extracellular vesicle research","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Extracellular vesicles in disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1300,"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":"Agence Nationale de la Recherche","keywords":"Extracellular vesicles; Extracellular vesicle; Crowdsourcing; Track (disk drive); Replication (statistics); Computer science; Interpretation (philosophy); Data science; Field (mathematics); Computational biology; Biology; Cell biology; World Wide Web; Genetics; Gene; Microvesicles; Virology","retraction":null,"screen_n_in":null,"score":{"opus":0.1456247315802752,"gpt":0.530227373266305,"spread":0.3846026416860298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007402109,0.000196826,0.0002619724,0.00009849063,0.0004210495,0.0001452005,0.000522625,0.0005515088,0.00001356688],"category_scores_gemma":[0.004364901,0.0001970746,0.0001044372,0.0001052603,0.0002879662,0.00001599887,0.0002107068,0.0009800799,0.000002964641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000446788,"about_ca_system_score_gemma":0.0001194911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000307466,"about_ca_topic_score_gemma":0.00007258968,"domain_scores_codex":[0.9970105,0.0008565245,0.0006163018,0.0007138862,0.0002320071,0.0005707611],"domain_scores_gemma":[0.9980195,0.0001056268,0.0003833565,0.001143745,0.0001455527,0.0002022526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006880869,0.0001186267,0.01993683,0.00008460793,0.00002220489,0.00009470551,0.0001836697,0.000007156355,0.9235393,0.0006778504,0.0002452395,0.05502094],"study_design_scores_gemma":[0.0006785917,0.00007350914,0.07139827,0.0001046559,0.00002202355,0.00003405838,0.0002328955,0.0003808538,0.888351,0.001142423,0.03727992,0.0003018325],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9318974,0.05893862,0.004117702,0.0002628099,0.0003596336,0.0003093123,0.000005716139,0.00001742264,0.004091397],"genre_scores_gemma":[0.940257,0.0003998007,0.05817814,0.00002711199,0.0002951323,0.00002302213,0.00001809355,0.00004054865,0.0007611735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05853882,"threshold_uncertainty_score":0.803647,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970740744","doi":"10.1038/s41592-019-0506-8","title":"Promoting transparency and reproducibility in enhanced molecular simulations","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1286,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Novelis (Canada)","funders":"Engineering and Physical Sciences Research Council; Lundbeckfonden","keywords":"Transparency (behavior); Reproducibility; Molecular dynamics; Sampling (signal processing); Computer science; Profiling (computer programming); Data science; Nanotechnology; Computational biology; Chemistry; Biology; Materials science; Computational chemistry; Telecommunications; Chromatography; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.007208511328255314,"gpt":0.3456477465606405,"spread":0.3384392352323852,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009057797,0.0001087442,0.0001401162,0.00003436656,0.00002136917,0.000009294011,0.00009870334,0.0003344171,0.00001078459],"category_scores_gemma":[0.0007130441,0.0001002747,0.00003823635,0.0001323029,0.00002559806,0.000003717931,0.00004852192,0.0002919718,4.289712e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007959539,"about_ca_system_score_gemma":0.00002811327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005066224,"about_ca_topic_score_gemma":0.00001802332,"domain_scores_codex":[0.9986399,0.0002046049,0.0001674533,0.0007729192,0.0000669271,0.0001481907],"domain_scores_gemma":[0.9990516,0.00002598735,0.00004508434,0.0007980313,0.00004464447,0.00003466061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002330174,0.00001299648,0.004353019,0.00003330766,0.000008919652,7.134963e-7,0.0001111177,0.0001767188,0.9742755,0.0001744317,0.000001483112,0.02082854],"study_design_scores_gemma":[0.0003561557,0.00008004592,0.01238815,0.00001380596,0.000008288598,0.000003903589,0.00001033533,0.001255008,0.9798586,0.00460313,0.001267001,0.0001555589],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9625254,0.001802384,0.03421551,0.0001035313,0.000175987,0.0003692633,0.000006921726,0.00000974708,0.0007912873],"genre_scores_gemma":[0.9077122,0.00001366222,0.09194927,0.0001532022,0.00003675751,0.00000690134,0.00003352887,0.00001102524,0.00008349917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05773376,"threshold_uncertainty_score":0.4089083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2591367881","doi":"10.1038/nmeth.4184","title":"Detecting DNA cytosine methylation using nanopore sequencing","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1257,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Minion; Nanopore sequencing; Nanopore; 5-Methylcytosine; DNA sequencer; DNA methylation; Cytosine; DNA; Computational biology; DNA sequencing; Hidden Markov model; Sequencing by ligation; genomic DNA; Human genome; Computer science; Biology; Genetics; Genome; Genomic library; Nanotechnology; Gene; Base sequence; Materials science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04533398034043244,"gpt":0.41577286745941,"spread":0.3704388871189775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001647982,0.0001720335,0.0001725713,0.00006118816,0.0005822048,0.0001125895,0.0002727402,0.0005739398,0.000009552516],"category_scores_gemma":[0.001961928,0.0001646009,0.0001047527,0.00006336345,0.0000594132,0.00001168212,0.0001607203,0.0003272513,0.000001176453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004685235,"about_ca_system_score_gemma":0.00008351327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000359331,"about_ca_topic_score_gemma":0.00002529331,"domain_scores_codex":[0.9987282,0.000270593,0.0002207942,0.0003926392,0.0001504229,0.0002374126],"domain_scores_gemma":[0.9986717,0.00004497364,0.0003100224,0.0007312885,0.0001720603,0.00006991579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000151932,0.00000500712,0.001333448,0.00001137295,0.00002408918,0.000001548862,0.00003109981,0.0001903566,0.9462127,0.0000568544,0.000005521733,0.05211282],"study_design_scores_gemma":[0.0002320905,0.00005627139,0.002880396,0.00001788238,0.0000330576,0.000005599891,0.00002712997,0.002319819,0.9870489,0.001056779,0.006120665,0.0002014648],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.758453,0.003296594,0.235416,0.00006392464,0.0005964694,0.0001273858,0.000003920445,0.00001590838,0.002026799],"genre_scores_gemma":[0.6688136,0.00005669969,0.3304488,0.00005157686,0.0004530618,0.000003069985,0.00001949651,0.0000246149,0.0001290397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09503283,"threshold_uncertainty_score":0.6712229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117486996","doi":"10.1038/nmeth.2340","title":"A large-scale evaluation of computational protein function prediction","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1095,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute; Office of Science; Biotechnology and Biological Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Directorate for Biological Sciences; Ministero dell’Istruzione, dell’Università e della Ricerca; Biological and Environmental Research; National Natural Science Foundation of China; University of Miami; Alexander von Humboldt-Stiftung; U.S. Department of Energy; National Science Foundation","keywords":"Annotation; Computer science; Protein function prediction; Function (biology); Protein function; Set (abstract data type); Scale (ratio); Computational biology; Machine learning; Artificial intelligence; Data mining; Biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01041951972596435,"gpt":0.3501743383184968,"spread":0.3397548185925325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001824708,0.00008216713,0.00008538494,0.00004896144,0.00004505897,0.00001166118,0.00007437269,0.0003045453,0.0001533519],"category_scores_gemma":[0.0005366442,0.00007323622,0.00005095325,0.0001027796,0.00002260698,0.000008039958,0.00004051509,0.0002348536,0.000007965159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001836792,"about_ca_system_score_gemma":0.00005782675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003517431,"about_ca_topic_score_gemma":0.000002127903,"domain_scores_codex":[0.9988378,0.000406484,0.0002064397,0.0001382851,0.0003094892,0.0001015139],"domain_scores_gemma":[0.9991103,0.00001902607,0.0001408183,0.0001793866,0.0005211197,0.00002939598],"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":[0.0001277861,0.0002154941,0.00553749,0.0001761402,0.0001805234,5.120175e-8,0.0005389171,0.02677101,0.7789689,0.001610679,0.007993629,0.1778793],"study_design_scores_gemma":[0.001903218,0.0006136087,0.1061362,0.0000421806,0.0001396988,0.00001060863,0.0002398681,0.7386695,0.1023189,0.01558889,0.03406348,0.0002738339],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3827606,0.0002669493,0.6120525,0.00008234633,0.0002230801,0.0005389331,0.00001291349,0.00001723259,0.004045377],"genre_scores_gemma":[0.6471722,0.000001123431,0.3520708,0.0001103212,0.000112573,0.0000629096,0.0002895785,0.000008509102,0.0001719725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7118985,"threshold_uncertainty_score":0.2986487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015182193","doi":"10.1038/nmeth.2883","title":"PyClone: statistical inference of clonal population structure in cancer","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1081,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Biology; Somatic cell; Inference; Computational biology; Approximate Bayesian computation; Cluster analysis; Population; Genetics; Bayesian probability; Somatic evolution in cancer; Statistical inference; Evolutionary biology; Cancer; Gene; Computer science; Artificial intelligence; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.009637945817347011,"gpt":0.3976675843009224,"spread":0.3880296384835754,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000249666,0.00008983741,0.0001478854,0.00003812493,0.00001483332,0.000006672733,0.000098528,0.0003076697,0.00003951516],"category_scores_gemma":[0.0007590685,0.00008328642,0.00002797415,0.00008276069,0.000033098,0.000001474054,0.0000513521,0.0002238409,1.856886e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001847407,"about_ca_system_score_gemma":0.00005462694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002914396,"about_ca_topic_score_gemma":0.0007937429,"domain_scores_codex":[0.9992902,0.0001328464,0.0001687565,0.0002016028,0.00008430098,0.0001222909],"domain_scores_gemma":[0.999511,0.0001404126,0.00006938271,0.0001771778,0.00006271158,0.00003933776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001830161,0.00005957315,0.1624834,0.00007875772,0.0000341132,0.000001097813,0.00005934392,0.002302077,0.5755621,0.02418514,0.0009577211,0.2340937],"study_design_scores_gemma":[0.0008844371,0.0002427938,0.7127111,0.00003404091,0.00003250343,0.000003449971,0.0000112318,0.002066445,0.2230234,0.01671295,0.04395371,0.0003238977],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9013968,0.001884088,0.09546101,0.00008868481,0.0005328652,0.0001089325,0.0002151021,0.00000389386,0.0003086888],"genre_scores_gemma":[0.8649095,0.0001221277,0.1343493,0.0002372915,0.0001928278,0.000004947225,0.0001586754,0.00000924498,0.0000160574],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5502277,"threshold_uncertainty_score":0.3396322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060297895","doi":"10.1038/nmeth.2641","title":"Engineering the Caenorhabditis elegans genome using Cas9-triggered homologous recombination","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1066,"is_retracted":false,"has_abstract":false,"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; Canadian Institutes of Health Research; National Institutes of Health; Howard Hughes Medical Institute","keywords":"CRISPR; Cas9; Caenorhabditis elegans; Homologous recombination; Biology; Genome editing; Genome; Genetics; Computational biology; Genome engineering; Gene; Homologous chromosome; Caenorhabditis","retraction":null,"screen_n_in":null,"score":{"opus":0.007549201337362386,"gpt":0.352403741526412,"spread":0.3448545401890496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004410258,0.0001681017,0.0001386146,0.00005898389,0.00009190573,0.00004486846,0.0002257492,0.0003684705,0.00005490724],"category_scores_gemma":[0.0002838628,0.0001344438,0.00009002685,0.0001678775,0.00002553998,0.000005273663,0.00007810032,0.0003829433,0.000006926974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003003907,"about_ca_system_score_gemma":0.00002821433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005494357,"about_ca_topic_score_gemma":0.000006140594,"domain_scores_codex":[0.9990791,0.0001124275,0.0001687158,0.0002724188,0.00009559174,0.0002717444],"domain_scores_gemma":[0.9993605,0.00005619567,0.00004635092,0.0003746481,0.0001007211,0.00006155847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002798058,0.00001067651,0.00004512466,0.00001432759,0.00004269309,0.000002128394,0.0000515684,0.003610888,0.983201,0.00006731458,0.000305815,0.01264567],"study_design_scores_gemma":[0.0004859782,0.0001275224,0.01246844,0.00001643237,0.00006824423,0.0002749447,0.00008558208,0.01515731,0.8819788,0.0002984702,0.08848681,0.000551533],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5362944,0.007144987,0.4542365,0.000274088,0.00105716,0.0003958995,0.000008829883,0.00004472263,0.0005434079],"genre_scores_gemma":[0.8251352,0.0001075207,0.1735802,0.0001770729,0.0004118151,0.00003614866,0.00004053071,0.00003997074,0.0004715913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2888408,"threshold_uncertainty_score":0.5482458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112888168","doi":"10.1038/nmeth.1517","title":"De novo assembly and analysis of RNA-seq data","year":2010,"lang":"en","type":"article","venue":"Nature Methods","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1050,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; BC Cancer Agency; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Contig; Sequence assembly; Substring; Pipeline (software); Computational biology; RNA-Seq; Transcriptome; Biology; De novo transcriptome assembly; RNA; Genetics; Gene; Computer science; Genome; Gene expression; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.0223015164198906,"gpt":0.3865809976313916,"spread":0.364279481211501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001605309,0.00009285389,0.0001934729,0.0000790081,0.00003099197,0.00001604945,0.0003666233,0.0004894665,0.00003825357],"category_scores_gemma":[0.0008789318,0.00007861172,0.00006605687,0.0002003736,0.00004063101,0.000003100709,0.0002005803,0.0002458682,3.063097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001625594,"about_ca_system_score_gemma":0.00003911455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001157407,"about_ca_topic_score_gemma":0.00003799567,"domain_scores_codex":[0.9991586,0.0001983374,0.0001257938,0.0003045998,0.00008275275,0.0001298801],"domain_scores_gemma":[0.9989076,0.00007711061,0.00007582782,0.0008251994,0.00005398464,0.00006031218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000191341,0.00001260713,0.0006280143,0.00000679142,0.0002697382,9.37398e-7,0.000009726004,0.00000110492,0.920467,0.00051367,0.00009473761,0.07797659],"study_design_scores_gemma":[0.0000902603,0.00003347671,0.002946696,0.000002156828,0.0003302368,0.000007589196,0.000007812471,0.0003055964,0.9618781,0.0003772955,0.0339262,0.00009457684],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7670053,0.002384145,0.2279719,0.0001818941,0.0002658577,0.00009766794,0.00009664262,0.000008768236,0.001987891],"genre_scores_gemma":[0.4469337,0.00008018483,0.5523679,0.0002030047,0.00009903013,0.000003312829,0.00009782463,0.000009773458,0.0002051987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3243961,"threshold_uncertainty_score":0.3775214,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392168151","doi":"10.1038/s41592-024-02201-0","title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","year":2024,"lang":"en","type":"article","venue":"Nature Methods","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1044,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University Health Network","keywords":"Generative grammar; Inference; Synthetic biology; Computer science; Systems biology; Computational biology; Transformer; Annotation; Generative model; Artificial intelligence; Language model; Biology; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08220096878827339,"gpt":0.4072693791762135,"spread":0.3250684103879401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006009239,0.0002423415,0.0002074374,0.00008968017,0.0001321079,0.0001537287,0.0001735057,0.0006272895,0.000003318521],"category_scores_gemma":[0.0001594656,0.0002299247,0.0002161935,0.000145218,0.00005042708,0.0000142301,0.00005213007,0.0003999416,8.792309e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007759497,"about_ca_system_score_gemma":0.000172566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007258745,"about_ca_topic_score_gemma":0.000007211403,"domain_scores_codex":[0.9986721,0.0001313592,0.0002459807,0.000558555,0.0001054214,0.00028656],"domain_scores_gemma":[0.9994176,0.00006216478,0.00005428544,0.0002248128,0.000168774,0.000072339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008463851,0.0000666258,0.00001140942,0.0001161924,0.00005569941,0.000001346433,0.0002218323,0.008596994,0.9737595,0.000444689,0.0001371955,0.01650389],"study_design_scores_gemma":[0.0002906807,0.00006828258,6.809817e-7,0.00001741274,0.00004936623,0.000006141147,0.00001213457,0.4866533,0.5052712,0.0004876729,0.006977683,0.0001654481],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05457624,0.004008688,0.9393919,0.0001743921,0.001303329,0.0003416199,0.00004488058,0.00004553125,0.0001134027],"genre_scores_gemma":[0.3309457,0.00004440833,0.6674102,0.000630388,0.0004687729,0.00001810747,0.000111904,0.00005307915,0.0003174279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4780563,"threshold_uncertainty_score":0.9376057,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947763854","doi":"10.1038/s41592-019-0426-7","title":"Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":979,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Bundesministerium für Bildung und Forschung; Agence Nationale de la Recherche; Nvidia","keywords":"Tandem mass spectrometry; Database search engine; Proteome; Computer science; Bottom-up proteomics; Proteomics; Computational biology; Mass spectrometry; Peptide; Deep learning; Artificial intelligence; Chemistry; Chromatography; Search engine; Protein mass spectrometry; Biology; Biochemistry; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.00743944056699306,"gpt":0.3140974849949114,"spread":0.3066580444279183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004664181,0.0001637108,0.0002418524,0.0000408075,0.00007325201,0.00001558843,0.0002219485,0.0004802508,0.0002922285],"category_scores_gemma":[0.0002107008,0.0001555531,0.00009333423,0.0001978348,0.00003685643,0.00008911801,0.00004590677,0.001341013,0.000006445788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008694639,"about_ca_system_score_gemma":0.00002103382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003310098,"about_ca_topic_score_gemma":3.110755e-7,"domain_scores_codex":[0.9989117,0.000061463,0.0002767952,0.0003499904,0.0001860477,0.0002139779],"domain_scores_gemma":[0.9990621,0.0001640065,0.0002452839,0.0003820834,0.00009130087,0.00005518924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000164693,0.00002670132,0.009008902,0.00009854829,0.00001789749,2.688962e-7,0.00004491424,0.00006070033,0.9831238,0.0007457185,0.0002122867,0.006643787],"study_design_scores_gemma":[0.000215619,0.00003864289,0.0002752813,0.00005022322,0.00001843363,0.000003258463,0.0000420289,0.001086831,0.9320642,0.007280839,0.05879077,0.0001339041],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04840807,0.0007999536,0.9209361,0.0001631365,0.00005896905,0.0006752239,0.00003381305,0.0003378206,0.0285869],"genre_scores_gemma":[0.1442117,0.00007488621,0.8502774,0.00004006214,0.00008155197,0.0002048438,0.0000595726,0.00003865757,0.005011334],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09580367,"threshold_uncertainty_score":0.6343271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035312069","doi":"10.1038/nmeth.2524","title":"Biowire: a platform for maturation of human pluripotent stem cell–derived cardiomyocytes","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Tissue Engineering and Regenerative Medicine","field":"Medicine","cited_by":951,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; Toronto General Hospital; Heart and Stroke Foundation; Hospital for Sick Children; University of Toronto","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Induced pluripotent stem cell; Electrophysiology; Stimulation; Cell biology; Stem cell; In vitro; Biology; Limiting; Myocyte; Human Induced Pluripotent Stem Cells; Neuroscience; Anatomy; Embryonic stem cell; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02573909737419226,"gpt":0.3563196504564288,"spread":0.3305805530822365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004421631,0.0001773751,0.0004804575,0.0001426563,0.0000642277,0.000009774877,0.00007128101,0.0003101882,0.00004057374],"category_scores_gemma":[0.00008266876,0.0001198232,0.0001527921,0.0001773412,0.00005618086,0.00005659388,0.00001835421,0.0003886692,0.000002966773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005277934,"about_ca_system_score_gemma":0.00003180643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001535763,"about_ca_topic_score_gemma":5.220124e-7,"domain_scores_codex":[0.9990522,0.00005527048,0.0002828494,0.0002151392,0.0001989076,0.0001956549],"domain_scores_gemma":[0.9991264,0.0001525467,0.000101173,0.0002659754,0.000247385,0.0001064676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003973106,0.00003509887,0.00003569737,0.0003558141,0.0000868528,0.000002049177,0.0003356861,0.00002618533,0.9568475,0.000797097,0.001973083,0.03946513],"study_design_scores_gemma":[0.001560822,0.0005303394,0.004731377,0.00013274,0.0001579834,0.00002201775,0.0002627892,0.001291056,0.9706423,0.0001303981,0.02039223,0.0001459113],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6657422,0.03858675,0.2888654,0.001610081,0.001843333,0.002211627,0.00001687511,0.0001927942,0.0009309229],"genre_scores_gemma":[0.7159261,0.00002820104,0.2773958,0.00006724632,0.0005613446,0.0001032717,0.00005197257,0.00003189208,0.005834114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05018391,"threshold_uncertainty_score":0.488625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773939681","doi":"10.1038/nmeth.4458","title":"Critical Assessment of Metagenome Interpretation—a benchmark of metagenomics software","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":948,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Engineering and Physical Sciences Research Council; National Institute of Allergy and Infectious Diseases; Medical Research Council; Isaac Newton Institute for Mathematical Sciences; Deutsche Forschungsgemeinschaft; Biotechnology and Biological Sciences Research Council; Office of Science; Australian Research Council; Agency for Science, Technology and Research; Joint Genome Institute; U.S. Department of Energy; Division of Mathematical Sciences; Villum Fonden; H. Lundbeck A/S; Lundbeckfonden; National Science Foundation","keywords":"Metagenomics; Computational biology; Benchmark (surveying); Software; Computer science; Interpretation (philosophy); Biology; Genetics; Gene; Programming language; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.01749655809789689,"gpt":0.4659042282284851,"spread":0.4484076701305882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001100137,0.0001269273,0.0003216286,0.00005102763,0.0001105852,0.00002103402,0.0004180846,0.0003612247,0.00004600067],"category_scores_gemma":[0.001262109,0.0001135843,0.0001689535,0.00003296173,0.0001865384,0.000006672423,0.0001944518,0.0002850422,4.74237e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001432635,"about_ca_system_score_gemma":0.0001670741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001135519,"about_ca_topic_score_gemma":0.000008127377,"domain_scores_codex":[0.9989093,0.000251589,0.0003110924,0.0002624498,0.00009765258,0.0001679261],"domain_scores_gemma":[0.9985663,0.0001061839,0.0002633323,0.0007399902,0.0002640432,0.00006011649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003635617,0.00005908704,0.002416963,0.0001318118,0.0001282693,8.462294e-7,0.00004562399,0.000006191614,0.9822875,0.002138156,0.0001795122,0.01256966],"study_design_scores_gemma":[0.0005771549,0.0004355721,0.187742,0.00004962743,0.0002692898,0.00001308617,0.00005933814,0.000163221,0.7800742,0.001612343,0.02870547,0.000298701],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2807111,0.008718172,0.7011687,0.0005846858,0.001458068,0.0003949252,0.0002260638,0.00001254866,0.006725806],"genre_scores_gemma":[0.5254588,0.00007684168,0.4741438,0.000134012,0.00005010066,0.000003252898,0.00003051863,0.000009545645,0.00009305378],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2447477,"threshold_uncertainty_score":0.4631832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3108232640","doi":"10.1038/s41592-020-00998-0","title":"diaPASEF: parallel accumulation–serial fragmentation combined with data-independent acquisition","year":2020,"lang":"en","type":"article","venue":"Nature Methods","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":947,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Occupational Cancer Research Centre; University of Toronto","funders":"Leibniz-Gemeinschaft; Gottfried Wilhelm Leibniz Universität Hannover; Max-Planck-Gesellschaft; Deutsche Forschungsgemeinschaft; National Science Foundation; Government of Canada; Genome Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Fragmentation (computing); Computer science; Parallel computing; Computational biology; Biology; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.05565742389623501,"gpt":0.4026625808432744,"spread":0.3470051569470394,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002929228,0.0001808175,0.000210825,0.00003857782,0.0001190106,0.00007657924,0.0004676383,0.0003241779,0.004066477],"category_scores_gemma":[0.00009671436,0.0001558225,0.00004366823,0.000330513,0.00002749905,0.0002131477,0.0001463164,0.0005961047,0.00001157609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005644316,"about_ca_system_score_gemma":0.00003552261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001082229,"about_ca_topic_score_gemma":0.000004238284,"domain_scores_codex":[0.9986799,0.00007800019,0.0002388001,0.00051083,0.0003103366,0.0001821673],"domain_scores_gemma":[0.9988178,0.0001497493,0.0001658057,0.0006675263,0.00007432736,0.0001247837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002724716,0.0006635091,0.004904007,0.0004727683,0.0004521612,0.0000323965,0.0005722162,0.0008948142,0.7477107,0.1341971,0.02214314,0.08523243],"study_design_scores_gemma":[0.007272374,0.0006352136,0.008703124,0.0001003928,0.0005677974,0.00003275556,0.0003785843,0.06389186,0.6481187,0.02640077,0.2421542,0.001744248],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04472168,0.0002909222,0.917504,0.007205233,0.0001451722,0.0006294356,0.0003500745,0.0009406445,0.02821283],"genre_scores_gemma":[0.4557949,0.0000146455,0.5413817,0.0006776736,0.0003516186,0.00006592845,0.001593505,0.00002371767,0.0000963533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4110732,"threshold_uncertainty_score":0.9968439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030260413","doi":"10.1038/nmeth.2935","title":"Olfactory exposure to males, including men, causes stress and related analgesia in rodents","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Olfactory and Sensory Function Studies","field":"Neuroscience","cited_by":944,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Hôpital du Sacré-Cœur de Montréal; McGill University","funders":"","keywords":"Affect (linguistics); Adult male; Olfactory perception; Physiology; Sex characteristics; Biology; Endocrinology; Olfaction; Psychology; Neuroscience; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.128728066108058,"gpt":0.3731182745542014,"spread":0.2443902084461434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008933941,0.0002020298,0.000304083,0.0002600509,0.000220736,0.00004274643,0.0001616737,0.0002927714,0.00005490876],"category_scores_gemma":[0.003304079,0.0001712881,0.00004188428,0.0004979171,0.00007335316,0.0001628077,0.0001569261,0.0007660107,0.00001370761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004658568,"about_ca_system_score_gemma":0.00001109552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007057117,"about_ca_topic_score_gemma":0.00002110556,"domain_scores_codex":[0.9973243,0.001336838,0.0002653341,0.0005467532,0.0002487696,0.0002779956],"domain_scores_gemma":[0.998551,0.0009452054,0.00008463383,0.0002624125,0.00004008101,0.0001167375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002616479,0.0001642202,0.2093795,0.0001514047,0.00005227149,0.00008820425,0.005783367,0.0004402934,0.7441995,0.007268635,0.001630619,0.03058025],"study_design_scores_gemma":[0.001017286,0.0002488417,0.617995,0.0001323364,0.00003768754,0.00003217358,0.0007153244,0.0002615611,0.3418764,0.001636658,0.03545915,0.0005876084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879482,0.0007392921,0.001133556,0.0005059154,0.001039403,0.0002213919,0.00001256098,0.0001066441,0.008293007],"genre_scores_gemma":[0.9936777,0.00005804519,0.004023937,0.0007650705,0.00006584739,0.000009388332,0.00000119237,0.00001918629,0.001379584],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4086154,"threshold_uncertainty_score":0.6984925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1869516088","doi":"10.1038/nmeth.f.202","title":"Protein production and purification","year":2008,"lang":"en","type":"review","venue":"Nature Methods","topic":"Viral Infectious Diseases and Gene Expression in Insects","field":"Biochemistry, Genetics and Molecular Biology","cited_by":921,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Biological and Environmental Research; Medical Research Council; Knut och Alice Wallenbergs Stiftelse; Karolinska Institutet; Stiftelsen för Strategisk Forskning; Ministry of Education, Culture, Sports, Science and Technology; U.S. Department of Energy; European Commission; RIKEN; Ontario Genomics Institute; Directorate for Biological Sciences; National Institutes of Health; Ontario Genomics; Genome Canada; GlaxoSmithKline; Ontario Innovation Trust; Wellcome Trust; National Institute of General Medical Sciences; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Protein expression; Computational biology; Data science; Operations research; Biology; Genetics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02896211272572656,"gpt":0.4097533592668457,"spread":0.3807912465411191,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002420405,0.0002754586,0.0004391369,0.00007783141,0.0001288562,0.00002319672,0.0001288117,0.001074584,0.000008429559],"category_scores_gemma":[0.0006889013,0.000212969,0.0002282924,0.0001467791,0.00006361629,0.000002957676,0.00008728904,0.0004962608,0.000004754321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001562603,"about_ca_system_score_gemma":0.0001199448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001745705,"about_ca_topic_score_gemma":7.234346e-7,"domain_scores_codex":[0.9983639,0.0005442938,0.0002442682,0.0005998713,0.00009786886,0.0001497748],"domain_scores_gemma":[0.9991488,0.0000109987,0.0002098491,0.0004763382,0.00007789005,0.00007607385],"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":[0.000007409154,0.00003024008,7.152098e-7,0.001617791,0.00006023682,0.000001061438,0.000004096365,2.383343e-7,0.00670831,0.0000401871,0.009042501,0.9824872],"study_design_scores_gemma":[0.00003940889,0.00007170769,0.000002443744,0.0009004966,0.00007982856,0.000128585,0.000001320307,4.400531e-7,0.007577604,0.00006489844,0.9908967,0.0002365821],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00004078881,0.9970425,0.000993022,0.00001878968,0.0006196255,0.0007635563,0.00001364008,0.0000239297,0.0004840945],"genre_scores_gemma":[0.00001790117,0.9739937,0.02262292,0.00003999403,0.0009885586,0.0002846626,0.0001852479,0.00004307976,0.001823887],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9822506,"threshold_uncertainty_score":0.8684623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067305633","doi":"10.1038/nmeth.1280","title":"An empirical framework for binary interactome mapping","year":2008,"lang":"en","type":"article","venue":"Nature Methods","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":908,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Human Genome Research Institute","keywords":"Interactome; Computer science; Computational biology; Human genome; Human proteins; Genome; Biology; Data mining; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03496269584809562,"gpt":0.4188631605501531,"spread":0.3839004647020575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004981151,0.0001442285,0.0001658522,0.00004662161,0.0001267311,0.00001720507,0.000243035,0.0007803157,0.00001601456],"category_scores_gemma":[0.0002055724,0.000124876,0.0001263372,0.0001025963,0.00005384828,0.000005043319,0.00007191231,0.0004755521,0.00000280402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001102867,"about_ca_system_score_gemma":0.00004728457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.629997e-7,"about_ca_topic_score_gemma":4.975008e-7,"domain_scores_codex":[0.9991298,0.0001048606,0.0002041454,0.0002498756,0.00006761999,0.0002437002],"domain_scores_gemma":[0.9992601,0.00009343022,0.00007652057,0.0003970623,0.00007215659,0.0001007307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007951683,0.0004263567,0.005455822,0.0001777506,0.0004164503,0.00002168928,0.002403538,0.0003692762,0.5644699,0.004894359,0.08573204,0.3348376],"study_design_scores_gemma":[0.0006804965,0.000777729,0.005652694,0.00003999594,0.00002566298,0.0001361192,0.0001909634,0.009998213,0.04662653,0.0134498,0.9218131,0.0006087453],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1066338,0.001672222,0.8899264,0.000272951,0.0007018086,0.0001853311,0.00001338381,0.00002022607,0.0005738884],"genre_scores_gemma":[0.2451196,0.00007439608,0.7513972,0.002344675,0.0007501303,0.00001877361,0.000111431,0.00001985641,0.0001639161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.836081,"threshold_uncertainty_score":0.6018509,"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":"W2047077861","doi":"10.1038/nmeth.1541","title":"SAINT: probabilistic scoring of affinity purification–mass spectrometry data","year":2010,"lang":"en","type":"article","venue":"Nature Methods","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":831,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Cancer Institute; Canadian Institutes of Health Research","keywords":"Interactome; Probabilistic logic; Mass spectrometry; Computer science; Computational biology; Protein–protein interaction; Quantitative proteomics; Proteomics; Chemistry; Data mining; Chromatography; Biology; Artificial intelligence; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02159183885167357,"gpt":0.3463741186204375,"spread":0.3247822797687639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00163648,0.0001254954,0.0001670849,0.00004933493,0.00005129394,0.00002065271,0.0006822675,0.0004835647,0.00003341067],"category_scores_gemma":[0.0009507805,0.000110842,0.00005487115,0.0001663468,0.00009191543,0.000005672312,0.000248452,0.0006893282,0.000003012315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008536153,"about_ca_system_score_gemma":0.0000762029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005394432,"about_ca_topic_score_gemma":0.00001821496,"domain_scores_codex":[0.9990466,0.00008755058,0.0002705291,0.0003009209,0.0001077845,0.0001866483],"domain_scores_gemma":[0.998231,0.00006845237,0.0001619409,0.001371736,0.00009961395,0.00006728456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002323591,0.0000364855,0.0003056979,0.00005456274,0.00004454756,3.120436e-7,0.00001684925,0.00002238195,0.9580495,0.006813479,0.0008708883,0.03376211],"study_design_scores_gemma":[0.0006322306,0.0001823446,0.006645487,0.00002758083,0.00009777433,0.00003313445,0.00005256321,0.005490779,0.799172,0.01571028,0.1714082,0.000547597],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3158868,0.003386971,0.6642489,0.0004194443,0.002684426,0.0006045814,0.0001848267,0.00003494665,0.01254911],"genre_scores_gemma":[0.3937765,0.00003583464,0.6054258,0.00008123487,0.0003556485,0.000003822547,0.0001886178,0.00001139121,0.0001211585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1705373,"threshold_uncertainty_score":0.4520005,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145909957","doi":"10.1038/nmeth.3000","title":"All-optical electrophysiology in mammalian neurons using engineered microbial rhodopsins","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Photoreceptor and optogenetics research","field":"Neuroscience","cited_by":825,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Division of Chemical, Bioengineering, Environmental, and Transport Systems; National Institute of Environmental Health Sciences; National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada; National Science Foundation; Canadian Institutes of Health Research; McGovern Institute for Brain Research, Massachusetts Institute of Technology; Alberta Innovates; Division of Emerging Frontiers in Research and Innovation; New York Stem Cell Foundation; Massachusetts Institute of Technology; University of Alberta; Defense Advanced Research Projects Agency; National Institute of Biomedical Imaging and Bioengineering; Skolkovo Institute of Science and Technology; National Institute on Deafness and Other Communication Disorders; National Institute on Drug Abuse; Alberta Innovates - Technology Futures; National Institutes of Health","keywords":"Channelrhodopsin; Electrophysiology; Voltage-sensitive dye; Optogenetics; Microsecond; Biophysics; Neuroscience; Biology; Physics; Optics","retraction":null,"screen_n_in":null,"score":{"opus":0.05431565892744326,"gpt":0.416285465913153,"spread":0.3619698069857097,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007972378,0.00019681,0.0002860743,0.0002586664,0.00007229437,0.00004408517,0.0004852702,0.0004324221,0.00007288699],"category_scores_gemma":[0.003052344,0.0001817832,0.00009277431,0.0005745104,0.0001391057,0.00005329364,0.0001436729,0.001533439,0.00001832911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008517113,"about_ca_system_score_gemma":0.00006730087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001651542,"about_ca_topic_score_gemma":0.000009465954,"domain_scores_codex":[0.9966627,0.001607974,0.0002250191,0.0005662242,0.000229399,0.0007086345],"domain_scores_gemma":[0.9984505,0.0009525431,0.00003686227,0.0003638207,0.00003733358,0.0001590042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006694887,0.00005249281,0.00004172456,0.000009065569,0.000002301482,0.00001118338,0.00003822349,0.0001522506,0.9931911,0.001718732,0.0001300875,0.004585887],"study_design_scores_gemma":[0.0003617034,0.0001210782,0.001598959,0.000004641533,0.000006535997,0.00003474425,0.000001802784,0.01287932,0.965867,0.0005569918,0.01838607,0.0001811408],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700354,0.00006347134,0.02668687,0.0003023479,0.0009502831,0.000230928,0.00000859279,0.00005629695,0.001665823],"genre_scores_gemma":[0.8416726,0.00001890272,0.1567639,0.001175556,0.0002375363,0.000006789925,0.000003058582,0.0000355518,0.00008613078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.130077,"threshold_uncertainty_score":0.7412905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2038186289","doi":"10.1038/nmeth895","title":"A comprehensive library of fluorescent transcriptional reporters for Escherichia coli","year":2006,"lang":"en","type":"article","venue":"Nature Methods","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":813,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Promoter; Operon; Escherichia coli; Biology; Transcription (linguistics); Plasmid; Computational biology; lac operon; Genomic library; Genetics; Gene; Gene expression; Base sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.01131983190637461,"gpt":0.3048933324768018,"spread":0.2935735005704272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000201702,0.0001376213,0.000228431,0.00004921191,0.00004058611,0.000009101209,0.0001353229,0.0003465834,0.00001957314],"category_scores_gemma":[0.00002611766,0.000129142,0.0003005885,0.0001612948,0.00006885175,0.000003254849,0.00003075223,0.0001293751,2.338073e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006743298,"about_ca_system_score_gemma":0.00006925231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004236319,"about_ca_topic_score_gemma":0.000002738914,"domain_scores_codex":[0.9989637,0.0001690976,0.000284068,0.0003017574,0.0001155274,0.0001658112],"domain_scores_gemma":[0.9993685,0.00003460799,0.0001440046,0.0002936731,0.0001154417,0.00004376338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001236328,0.00005134846,0.001051501,0.00004249969,0.0001392961,0.000001100534,0.000006221268,0.000532679,0.9848823,0.0005204974,0.01051283,0.002136121],"study_design_scores_gemma":[0.0003814622,0.00008071118,0.01864687,0.000007035813,0.00009003878,0.000004870778,0.00001379552,0.0003912341,0.7113587,0.0006593874,0.2682269,0.000139057],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8156592,0.01685121,0.1652693,0.00035786,0.000472705,0.0004348264,0.00006600215,0.00002750341,0.0008613701],"genre_scores_gemma":[0.4921533,0.00004440775,0.5059451,0.0002927892,0.0003979844,0.00002495024,0.0004073614,0.00002780584,0.0007063492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3406758,"threshold_uncertainty_score":0.526626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751625431","doi":"10.1038/nmeth.4397","title":"Data-analysis strategies for image-based cell profiling","year":2017,"lang":"en","type":"article","venue":"Nature Methods","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":790,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Toronto","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council","keywords":"Profiling (computer programming); Workflow; Computer science; Image processing; Artificial intelligence; Data mining; Image (mathematics); Computational biology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04139847263322192,"gpt":0.4617714973079955,"spread":0.4203730246747736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001919899,0.0001864769,0.0003292133,0.0001113442,0.0002581966,0.0003163636,0.001319191,0.0004119563,0.00001920873],"category_scores_gemma":[0.0009169665,0.0001630143,0.0003645397,0.000113819,0.0001064256,0.0000203073,0.0003236647,0.000259744,0.000001179622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008800054,"about_ca_system_score_gemma":0.0001262249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002115263,"about_ca_topic_score_gemma":0.00005454826,"domain_scores_codex":[0.9985437,0.0001841958,0.0002202695,0.0006996471,0.0001261716,0.0002260216],"domain_scores_gemma":[0.9960479,0.0000700623,0.0002778637,0.003296834,0.0002534426,0.00005391245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000390414,0.00004170794,0.0002849132,0.00003688402,0.000522105,0.000002335336,0.0000032455,0.0000288101,0.9875088,0.00007697604,0.006776502,0.00467866],"study_design_scores_gemma":[0.000216385,0.00004704176,0.0001405897,0.000001816961,0.001467517,4.811016e-7,0.00002887254,0.005360351,0.9274033,0.0005323563,0.06460439,0.0001968967],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003423745,0.001088812,0.9883439,0.0001692372,0.00004560859,0.0002606232,0.0001002221,0.00003392787,0.00653395],"genre_scores_gemma":[0.1647284,0.00002232154,0.8326449,0.0003018227,0.0001900658,0.00003729559,0.001369775,0.00002417657,0.0006812007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1613047,"threshold_uncertainty_score":0.6647531,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2037200077","doi":"10.1038/nmeth.3125","title":"Neuronal morphometry directly from bitmap images","year":2014,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":783,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Bitmap; Artificial intelligence; Computer science; Computer graphics (images); Biology; Computational biology","retraction":null,"screen_n_in":null,"score":{"opus":0.009759045810074932,"gpt":0.3401319994007074,"spread":0.3303729535906325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0008250817,0.0005981401,0.0007162676,0.0002815145,0.00007093904,0.0001026294,0.0009393949,0.004183015,0.0002243733],"category_scores_gemma":[0.0009681808,0.0005489017,0.0005226351,0.0002783308,0.000146779,0.000004055399,0.0003828187,0.004085668,0.00002798049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002830774,"about_ca_system_score_gemma":0.00006788861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006572192,"about_ca_topic_score_gemma":0.000003743847,"domain_scores_codex":[0.996244,0.001254405,0.0003889522,0.001263663,0.0003918492,0.0004571762],"domain_scores_gemma":[0.9974567,0.0002860104,0.0003096236,0.001654789,0.0002172503,0.00007564077],"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":[0.000007570074,0.000009810907,0.00002552563,0.00001872989,0.0001530895,0.00003739279,0.000001259518,1.856042e-7,0.4075065,4.235793e-7,0.5838658,0.008373766],"study_design_scores_gemma":[0.00007417065,0.00004490888,0.00006905823,0.00001172147,0.0001465675,0.000009195829,4.665037e-7,0.000005413192,0.4645149,0.0001476251,0.5346643,0.0003116426],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.004649478,0.05967911,0.5423805,0.3346715,0.002510556,0.001240611,0.0005590129,0.0007972228,0.05351198],"genre_scores_gemma":[0.0004272206,0.000455704,0.3797126,0.5960319,0.009743403,0.00004199547,0.00450553,0.0001726738,0.008908906],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.2613604,"threshold_uncertainty_score":0.9996963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2955168413","doi":"10.1038/s41592-019-0459-y","title":"Recommendations for performing, interpreting and reporting hydrogen deuterium exchange mass spectrometry (HDX-MS) experiments","year":2019,"lang":"en","type":"review","venue":"Nature Methods","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":769,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; Western University; University of Calgary; University of Victoria","funders":"National Institute of General Medical Sciences; Villum Fonden","keywords":"Hydrogen–deuterium exchange; Mass spectrometry; Deuterium; Chemistry; Chromatography; Physics; Nuclear physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1234264784907558,"gpt":0.4903123539235472,"spread":0.3668858754327914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002490898,0.000671701,0.001987724,0.0004041091,0.000254561,0.0001353744,0.0005781729,0.001462309,0.002194418],"category_scores_gemma":[0.00120814,0.0006058288,0.0007355905,0.000512758,0.00004205084,0.0001133386,0.0003608732,0.001866563,0.000005266605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000395835,"about_ca_system_score_gemma":0.00009798724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006994398,"about_ca_topic_score_gemma":4.671511e-7,"domain_scores_codex":[0.9962014,0.0001691478,0.001751945,0.001095487,0.000215603,0.0005664313],"domain_scores_gemma":[0.9948295,0.0008576022,0.002993776,0.001074125,0.00009848884,0.0001464533],"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":[0.00000416632,0.00003848557,0.00001030357,0.01609064,0.0002492216,0.000002426999,0.00006583949,1.483047e-8,0.003311069,0.0009112951,0.001667177,0.9776493],"study_design_scores_gemma":[0.0001118713,0.00003246066,1.654447e-7,0.003882894,0.0005581143,0.0001119963,0.0000440336,0.0000810097,0.01405786,0.0007835407,0.9797542,0.0005818177],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006362225,0.9360986,0.0281369,0.000112134,0.0002857398,0.00100108,0.0001819922,0.0002770412,0.03390012],"genre_scores_gemma":[0.00001055527,0.5260738,0.4700225,0.0000503587,0.0003617076,0.0009270348,0.0004050328,0.0001126374,0.002036412],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9780871,"threshold_uncertainty_score":0.999834,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2989499631","doi":"10.1038/s41592-019-0617-2","title":"Nanopore native RNA sequencing of a human poly(A) transcriptome","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":750,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Michael Smith Health Research BC; University of British Columbia; University of Toronto; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Biotechnology and Biological Sciences Research Council; National Institute of General Medical Sciences; Medical Research Council; Canadian Institutes of Health Research; Research Councils UK; U.S. Department of Health and Human Services; Ontario Institute for Cancer Research; Government of Canada; Wellcome Trust","keywords":"Nanopore sequencing; Minion; Nanopore; RNA; Biology; Computational biology; Transcriptome; DNA sequencing; Deep sequencing; Illumina dye sequencing; Base pair; Genetics; DNA; Genome; Gene; Gene expression; Nanotechnology","retraction":null,"screen_n_in":null,"score":{"opus":0.01892523567595729,"gpt":0.3755406347950257,"spread":0.3566153991190684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004105505,0.0001055391,0.0001560705,0.00005095361,0.00004057595,0.00000694196,0.0001822016,0.0003096422,0.00007576588],"category_scores_gemma":[0.00004438468,0.0000922515,0.0001068758,0.0001357956,0.00004798656,0.000003330957,0.00002397247,0.0002291534,0.000001852231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002415797,"about_ca_system_score_gemma":0.00007828275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001472001,"about_ca_topic_score_gemma":0.000004741933,"domain_scores_codex":[0.9992009,0.0001421675,0.0001585429,0.0002543557,0.0001089191,0.0001350784],"domain_scores_gemma":[0.9993874,0.00001351288,0.00009017954,0.0003489992,0.0001241523,0.0000357279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001670833,0.00001341446,0.0002001798,0.00002238292,0.00004025333,2.331926e-7,0.0001336467,0.000004266868,0.9882686,0.001868056,0.0001935831,0.009238704],"study_design_scores_gemma":[0.0002791795,0.0001380927,0.001094346,0.0000151065,0.00001511442,0.000002470079,0.0001658369,0.00002030436,0.9749059,0.0004141839,0.02283213,0.0001173517],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9599742,0.008304612,0.0133395,0.0001164321,0.0003654675,0.0002108112,0.00002617906,0.00001168689,0.01765111],"genre_scores_gemma":[0.9549404,0.0000490352,0.04192726,0.0002062833,0.0000937745,0.00001195845,0.00003800242,0.00001645472,0.002716813],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02858776,"threshold_uncertainty_score":0.3761907,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507380695","doi":"10.1038/nmeth.3968","title":"Model selection and overfitting","year":2016,"lang":"en","type":"article","venue":"Nature Methods","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":700,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Overfitting; Selection (genetic algorithm); Computational biology; Model selection; Computer science; Biology; Artificial intelligence; Machine learning; Evolutionary biology; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.02306701447789608,"gpt":0.3722396874107607,"spread":0.3491726729328647,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003189602,0.0000480989,0.00005182037,0.00002286889,0.00007715759,0.00003374386,0.0001492667,0.00008613395,0.000001601959],"category_scores_gemma":[0.00004686155,0.00002919524,0.00001597368,0.0001770282,0.000009030587,0.0001658063,0.0000746213,0.0001424604,0.000001449808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009363249,"about_ca_system_score_gemma":0.000009392493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.61991e-7,"about_ca_topic_score_gemma":8.852691e-7,"domain_scores_codex":[0.9995359,0.0000566428,0.0000591586,0.0001925057,0.00005665531,0.00009914064],"domain_scores_gemma":[0.9995788,0.0001852521,0.00002829291,0.0001429918,0.00002930691,0.00003536171],"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":[6.351469e-7,0.000003689367,0.00007017406,0.000001180232,0.000001879859,1.08612e-7,0.00001495483,0.00007521735,0.06195602,0.1986304,0.0007687099,0.7384771],"study_design_scores_gemma":[0.0001304128,0.00001319138,0.000820375,0.0000116154,0.000003097838,0.000012966,6.553666e-7,0.8457634,0.02691128,0.1071918,0.01903541,0.0001057483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003598488,0.0002073566,0.9926758,0.002516842,0.00009788419,0.00004388994,3.222205e-7,0.00008579596,0.0007736261],"genre_scores_gemma":[0.2677854,0.00001977089,0.7314329,0.000356574,0.00006128383,0.00000554644,4.965431e-8,0.000002599128,0.0003359072],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8456882,"threshold_uncertainty_score":0.1190547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045117578","doi":"10.1038/nmeth.3255","title":"DIA-Umpire: comprehensive computational framework for data-independent acquisition proteomics","year":2015,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":695,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Lunenfeld-Tanenbaum Research Institute","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"Workflow; Computer science; Multiplex; Proteomics; Tandem mass spectrometry; Mass spectrometry; Software; Fragmentation (computing); Data acquisition; Database search engine; Data mining; Computational biology; Chemistry; Chromatography; Bioinformatics; Database; Information retrieval; Biology; Search engine; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.09065455223700448,"gpt":0.4644961570090743,"spread":0.3738416047720698,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005026348,0.0001916629,0.0002389811,0.00003865585,0.0001325416,0.00005025668,0.0005723297,0.000633844,0.00003900533],"category_scores_gemma":[0.0004082139,0.0001891431,0.00007022611,0.0001397906,0.00005713895,0.0001447282,0.0002515843,0.0008644162,0.000005982631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263898,"about_ca_system_score_gemma":0.0001054493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003336304,"about_ca_topic_score_gemma":5.880856e-7,"domain_scores_codex":[0.9986862,0.00005659466,0.0002736873,0.0005163812,0.0002400015,0.0002271588],"domain_scores_gemma":[0.997845,0.000610527,0.0002066132,0.0008156369,0.0003851898,0.0001370397],"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":[0.0006421226,0.0004910066,0.0003564244,0.0004407459,0.0002575212,0.000007368324,0.0004225469,0.004533911,0.2266515,0.5955649,0.0180052,0.1526268],"study_design_scores_gemma":[0.0004789953,0.00002457143,0.00003018892,0.00003998312,0.00003710625,0.00001537355,0.00006500587,0.01782152,0.1821547,0.7187673,0.08029769,0.0002675756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002419049,0.000559959,0.9938924,0.0008174122,0.0001301659,0.0006342768,0.0003908897,0.0002305471,0.0009253307],"genre_scores_gemma":[0.01506503,0.00001443112,0.9816936,0.0006628899,0.000443226,0.0004616996,0.001507427,0.00004263114,0.0001091029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1523592,"threshold_uncertainty_score":0.7713032,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115610250","doi":"10.1038/nmeth.1185","title":"SNP discovery and allele frequency estimation by deep sequencing of reduced representation libraries","year":2008,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":676,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Genetics; Biology; Single-nucleotide polymorphism; Genotyping; SNP genotyping; Allele frequency; Genome; Genotype; DNA sequencing; SNP; Deep sequencing; Allele; Population; Computational biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02242832749851655,"gpt":0.3323102235550311,"spread":0.3098818960565146,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001608452,0.0001042186,0.0001308405,0.0000258269,0.00006998863,0.00001256797,0.00009589717,0.0002695189,0.000007255516],"category_scores_gemma":[0.0003314346,0.00009587218,0.00003864302,0.000080937,0.0001320579,0.00001627252,0.0000459912,0.000150355,2.212897e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006642182,"about_ca_system_score_gemma":0.00006564089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001643259,"about_ca_topic_score_gemma":0.000001536462,"domain_scores_codex":[0.9991984,0.0001736131,0.0001750063,0.0002514198,0.00009295257,0.0001085446],"domain_scores_gemma":[0.999548,0.00005170057,0.0000966911,0.0002200155,0.00004557235,0.00003805828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003801937,0.00001796787,0.001219445,0.00002457236,0.00003656197,3.671456e-7,0.0003779409,0.0002842507,0.9796881,0.004988744,0.00108857,0.01223547],"study_design_scores_gemma":[0.0002754158,0.0001708652,0.0235441,0.000008859985,0.0000234226,0.00003278503,0.0001093415,0.000163706,0.9550329,0.02001459,0.0004734886,0.0001504878],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5334649,0.005962585,0.4592314,0.00005679085,0.0001085879,0.00009731095,0.000008878787,0.000007771871,0.00106173],"genre_scores_gemma":[0.4463899,0.00006615397,0.5531114,0.00005686506,0.00004990474,0.000005099246,0.00009117753,0.000007845619,0.0002216835],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.09387993,"threshold_uncertainty_score":0.3909554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507306980","doi":"10.1038/nmeth.3995","title":"A proposal for validation of antibodies","year":2016,"lang":"en","type":"article","venue":"Nature Methods","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":645,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"National Institute on Drug Abuse","keywords":"Antibody; Computer science; Computational biology; Medicine; Immunology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04220168583204635,"gpt":0.4691830622997801,"spread":0.4269813764677337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008443005,0.00008394788,0.0002411669,0.00009661594,0.00003578077,0.00000371436,0.00007146091,0.0001754547,0.0001012107],"category_scores_gemma":[0.001047574,0.00004182228,0.0001292616,0.000110812,0.00009924081,0.00004241605,0.00003232171,0.0001516572,0.000005143798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001679699,"about_ca_system_score_gemma":0.0001292006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005109647,"about_ca_topic_score_gemma":8.217146e-7,"domain_scores_codex":[0.9991637,0.0001161855,0.0001707993,0.0001605078,0.0002172324,0.0001716142],"domain_scores_gemma":[0.9987938,0.0006367695,0.00005626123,0.0001528064,0.0002969892,0.00006340078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008050661,0.00006473326,0.008098812,0.0002862946,0.00007772447,0.000002628876,0.00005358585,6.063922e-8,0.7663702,0.01506671,0.002708035,0.2064662],"study_design_scores_gemma":[0.0007586768,0.0003396931,0.01103038,0.0001185662,0.00003935428,0.00001994354,0.0000104664,0.00002184881,0.9126247,0.0103765,0.06459359,0.00006633002],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7175425,0.004540327,0.2173967,0.04232699,0.001008327,0.002111074,0.0001907744,0.000111949,0.01477134],"genre_scores_gemma":[0.1766181,0.0001199663,0.8133273,0.0001614453,0.0003220283,0.00002482137,0.00001649259,0.00001533419,0.009394496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5959306,"threshold_uncertainty_score":0.1705463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977416347","doi":"10.1038/nmeth.1199","title":"BAC TransgeneOmics: a high-throughput method for exploration of protein function in mammals","year":2008,"lang":"en","type":"article","venue":"Nature Methods","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":628,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Human Genome Research Institute; Wellcome Trust","keywords":"Recombineering; Transgene; Biology; Computational biology; Bacterial artificial chromosome; Gene; Genome; Function (biology); Transfection; Molecular biology; Cell biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02256918009807363,"gpt":0.3982031726603523,"spread":0.3756339925622787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007074137,0.0001223336,0.00019075,0.00007201196,0.00002813381,0.000003202684,0.00008564324,0.0003827952,0.000005453869],"category_scores_gemma":[0.000169779,0.0001203479,0.00009319161,0.0001347017,0.00002070122,0.000006475073,0.00001661198,0.0001530147,2.693258e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001054874,"about_ca_system_score_gemma":0.00003894043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001271122,"about_ca_topic_score_gemma":0.00002130353,"domain_scores_codex":[0.9991145,0.0001560845,0.0002350579,0.0002694977,0.00007425305,0.000150625],"domain_scores_gemma":[0.9995813,0.00003836069,0.00005714678,0.0002146417,0.00007944816,0.00002914018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001969089,0.00002811178,0.00002901125,0.00005446594,0.00002495648,4.731765e-7,0.0001031274,0.002065214,0.9663626,0.0004607728,0.00008176775,0.03059261],"study_design_scores_gemma":[0.0006956611,0.0002609814,0.0006199382,0.00001290277,0.00001635359,0.000005367768,0.00003469216,0.0007435076,0.9815168,0.001703592,0.014258,0.0001321739],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09042253,0.00212443,0.9066114,0.00009683042,0.0002100036,0.0004521997,0.0000123887,0.000008872178,0.00006136905],"genre_scores_gemma":[0.3256454,0.00008426188,0.6737539,0.0000479158,0.0001573152,0.0001047493,0.0000509582,0.00001775422,0.0001377556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2352229,"threshold_uncertainty_score":0.4907644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971311915","doi":"10.1038/s41592-019-0530-8","title":"FRET as a biomolecular research tool — understanding its potential while avoiding pitfalls","year":2019,"lang":"en","type":"review","venue":"Nature Methods","topic":"Advanced Fluorescence Microscopy Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":624,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Förster resonance energy transfer; Computer science; Nanotechnology; Computational biology; Data science; Fluorescence; Biology; Materials science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1846688276168323,"gpt":0.5444501364991512,"spread":0.3597813088823189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00473209,0.0007126135,0.001351013,0.0005010529,0.000337988,0.0001573265,0.00121714,0.003548038,0.0000596851],"category_scores_gemma":[0.001803472,0.0006380902,0.0007356281,0.0008287058,0.0001975349,0.00001310241,0.000947354,0.004082258,0.0000725524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004201724,"about_ca_system_score_gemma":0.0006976952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003431316,"about_ca_topic_score_gemma":9.779831e-7,"domain_scores_codex":[0.9930282,0.003300598,0.0006305365,0.001501005,0.0005901205,0.0009494993],"domain_scores_gemma":[0.9975572,0.0002788875,0.0003258834,0.001381051,0.0003114537,0.0001455204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005056735,0.0000636582,4.771317e-7,0.006619844,0.0003719112,0.00008076512,0.00002634306,0.00000138646,0.6450535,0.003642669,0.006492869,0.337596],"study_design_scores_gemma":[0.0001376333,0.0002261628,5.728379e-8,0.003086718,0.0002105006,0.0001197744,0.00003340262,0.000006394874,0.1278078,0.001289301,0.8664212,0.0006610758],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002435641,0.6539302,0.3434031,0.00001837802,0.0005372,0.001102906,0.00006069095,0.00005523102,0.0008898745],"genre_scores_gemma":[0.00003081626,0.7628705,0.234796,0.0000964697,0.0004771766,0.0001047195,0.0003683484,0.0001782686,0.0010777],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8599283,"threshold_uncertainty_score":0.999607,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112493011","doi":"10.1038/nmeth.2365","title":"Critical assessment of automated flow cytometry data analysis techniques","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":622,"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; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Neurological Disorders and Stroke; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Cancer Institute","keywords":"Computer science; Identification (biology); Population; Gating; Data mining; Sample (material); Artificial intelligence; Biology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02645300500086839,"gpt":0.4456054761658771,"spread":0.4191524711650087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000835013,0.000145332,0.0002988687,0.0001584526,0.00003958622,0.00003288767,0.0005112852,0.0005447829,0.00008677365],"category_scores_gemma":[0.000644835,0.0001229633,0.0001363505,0.0005265286,0.00009122398,0.000009306868,0.0001817917,0.0003177813,9.245275e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001263385,"about_ca_system_score_gemma":0.00005772277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005222247,"about_ca_topic_score_gemma":0.000009885563,"domain_scores_codex":[0.9986415,0.0003186762,0.0002631464,0.0004205252,0.0001678359,0.0001883145],"domain_scores_gemma":[0.9985468,0.0001099893,0.00005994067,0.0009664401,0.0002423005,0.00007457631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008513775,0.0001063266,0.005192302,0.00003385969,0.0003500385,9.047656e-7,0.00000554616,0.00001120011,0.9665443,0.00007867484,0.002042978,0.02562533],"study_design_scores_gemma":[0.0001809881,0.0001633452,0.02923192,0.00001259382,0.0004798515,0.000004478162,0.00001539533,0.08844111,0.8726056,0.0001634126,0.008440016,0.000261329],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04423653,0.001188535,0.9515116,0.0002354306,0.0002792449,0.0002013231,0.0001344046,0.0001234468,0.002089486],"genre_scores_gemma":[0.4518287,0.00003513795,0.5475111,0.0001725835,0.00007293392,0.000007586962,0.0003263433,0.0000106586,0.00003499313],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4075921,"threshold_uncertainty_score":0.50143,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140600399","doi":"10.1038/nmeth.1313","title":"Global mapping of protein-DNA interactions in vivo by digital genomic footprinting","year":2009,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":586,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Research Resources; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; University of Washington; National Human Genome Research Institute; Howard Hughes Medical Institute","keywords":"Footprinting; Biology; Chromatin; Nucleosome; Genetics; DNA footprinting; Computational biology; ChIP-sequencing; DNA; Deoxyribonuclease I; Genome; ChIA-PET; DNA binding site; Regulatory sequence; Gene; Transcription factor; DNA-binding protein; Promoter; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.007049966486937587,"gpt":0.3132668481578181,"spread":0.3062168816708805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002349072,0.0001171925,0.0001468836,0.00003668867,0.00002625338,0.00002619247,0.000177952,0.0001800625,0.00000475822],"category_scores_gemma":[0.0001395448,0.0001204442,0.00008213522,0.0001333333,0.00002185259,0.000004087596,0.00007752,0.0001825746,3.624112e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004213713,"about_ca_system_score_gemma":0.0000354133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005724519,"about_ca_topic_score_gemma":0.000009843104,"domain_scores_codex":[0.9992461,0.0000572963,0.0002353821,0.0002339723,0.00005770855,0.0001696011],"domain_scores_gemma":[0.9995783,0.00001116727,0.0001141878,0.0002186998,0.00004175257,0.0000358723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001378684,0.000046484,0.001759199,0.00001088383,0.00001599042,6.781448e-7,0.00002027145,0.00003644298,0.9618898,0.0001952007,0.000117955,0.03589331],"study_design_scores_gemma":[0.0007602024,0.0001999533,0.02508289,0.00007065236,0.00001348373,0.00003696905,0.0002038196,0.0009368163,0.9102691,0.0042297,0.05774768,0.0004487809],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9707332,0.0006449372,0.02276759,0.000102144,0.000110382,0.0001547253,0.00003338995,0.000007278814,0.005446387],"genre_scores_gemma":[0.8935392,0.0000112239,0.1060805,0.00008352525,0.00005849458,0.000004249664,0.00002284238,0.000007884584,0.0001921042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08331288,"threshold_uncertainty_score":0.4911573,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1995683190","doi":"10.1038/nmeth.1931","title":"Protein interaction data curation: the International Molecular Exchange (IMEx) consortium","year":2012,"lang":"en","type":"article","venue":"Nature Methods","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":576,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; University of British Columbia; Ontario Institute for Cancer Research; Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; Simon Fraser University","funders":"FP7 Health; National Institutes of Health; Canadian Institutes of Health Research; European Commission; National Institute of General Medical Sciences; Wellcome Trust","keywords":"Data curation; Interface (matter); Set (abstract data type); Computer science; Data exchange; Quality (philosophy); Data science; Computational biology; World Wide Web; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0334129335883011,"gpt":0.3805758814059726,"spread":0.3471629478176715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00128507,0.0001143512,0.00008036459,0.0000235449,0.00007060375,0.00005036921,0.0005663179,0.0002748055,0.00007849424],"category_scores_gemma":[0.0002125501,0.00008101614,0.00004777012,0.00006338131,0.0000423496,0.00002714198,0.0004207396,0.0003775071,0.00001168633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001391638,"about_ca_system_score_gemma":0.00002820182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003385901,"about_ca_topic_score_gemma":0.000004621759,"domain_scores_codex":[0.9991683,0.0001571867,0.0001828302,0.0001791554,0.000128227,0.0001843485],"domain_scores_gemma":[0.999046,0.00002578669,0.0001193241,0.0006858376,0.00007032006,0.00005270625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001243201,0.00009529966,0.0002177246,0.00003299513,0.0002911164,0.000001368978,0.000257836,0.00003468471,0.698313,0.007344513,0.06138063,0.2319065],"study_design_scores_gemma":[0.0001672166,0.00002446149,0.0001349998,0.000008236253,0.00002041084,0.00002894294,0.00007491197,0.002019194,0.1118542,0.0002883002,0.8852507,0.0001283597],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0386958,0.01740474,0.9014565,0.005801028,0.006482598,0.0009609728,0.0001024627,0.00004088772,0.02905501],"genre_scores_gemma":[0.8204587,0.0001180653,0.1715221,0.003178179,0.002393672,0.00005137769,0.00103658,0.00002567438,0.001215683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8238701,"threshold_uncertainty_score":0.3303742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046601740","doi":"10.1038/nmeth.1374","title":"Computational methods for discovering structural variation with next-generation sequencing","year":2009,"lang":"en","type":"review","venue":"Nature Methods","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":575,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Structural variation; DNA sequencing; Sanger sequencing; Computational biology; Genome; Biology; Copy-number variation; Computer science; Genetics; DNA; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.08984392777199943,"gpt":0.43823913743128,"spread":0.3483952096592805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092722,0.0004096977,0.0007739485,0.00008182037,0.0001865778,0.0000862856,0.0002048647,0.0006977867,0.000002232762],"category_scores_gemma":[0.0002325271,0.0003062375,0.0002980517,0.0001432416,0.00003293538,0.00000252203,0.00006819699,0.0003427529,2.417317e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008695859,"about_ca_system_score_gemma":0.0003168882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004490423,"about_ca_topic_score_gemma":0.000005031919,"domain_scores_codex":[0.9980773,0.0005738248,0.0003867252,0.0006166354,0.0001024252,0.0002431342],"domain_scores_gemma":[0.9989473,0.0001930847,0.0003394323,0.0002927475,0.0001752781,0.00005211803],"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":[0.0000124924,0.00000400943,5.65975e-7,0.000618974,0.0002847553,2.870228e-7,0.00004446449,0.001250744,0.01090573,0.000357111,0.00004656219,0.9864743],"study_design_scores_gemma":[0.0003104754,0.0002929144,0.00002698589,0.000357111,0.0007579853,0.00005959039,0.00001459926,0.004054964,0.001449662,0.001401113,0.9906396,0.0006350406],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.00003889192,0.5653304,0.4337675,0.00000987653,0.0003235579,0.0004490116,0.0000309619,0.000003882468,0.00004595407],"genre_scores_gemma":[0.00004618771,0.3844618,0.6138858,0.00007338606,0.0007555885,0.0000681384,0.0006240004,0.00003626335,0.00004880519],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.990593,"threshold_uncertainty_score":0.999939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}