{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1315,"total_is_capped":false,"direct_labels_cover":11,"predictions_cover":1315,"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":"7a047e194645","filters":{"topic":"Data-Driven Disease Surveillance"}},"results":[{"id":"W3008443627","doi":"10.1016/s1473-3099(20)30120-1","title":"An interactive web-based dashboard to track COVID-19 in real time","year":2020,"lang":"en","type":"letter","venue":"The Lancet Infectious Diseases","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":11164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Johns Hopkins University","keywords":"Dashboard; Coronavirus disease 2019 (COVID-19); Outbreak; Mainland China; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); China; Public health; Track (disk drive); 2019-20 coronavirus outbreak; Coronavirus; Fast track; Mainland; Pneumonia; Geography; Medicine; Computer science; Virology; Disease; Infectious disease (medical specialty); Data science; Operating system; Nursing; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02717864563311139,"gpt":0.3301573479180379,"spread":0.3029787022849265,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002362068,0.0006787688,0.001584979,0.0003680119,0.0001436372,0.0001445312,0.0007766497,0.0002940522,0.001118247],"category_scores_gemma":[0.00161683,0.000535295,0.0003576074,0.0007195656,0.0002375136,0.0001736549,0.0001524275,0.001669832,0.001626294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009740527,"about_ca_system_score_gemma":0.001727376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005736049,"about_ca_topic_score_gemma":0.000278391,"domain_scores_codex":[0.9959035,0.0009320416,0.0005495754,0.001094026,0.0007040949,0.0008167559],"domain_scores_gemma":[0.9957803,0.0009844826,0.0002939804,0.00187271,0.0001375052,0.0009309788],"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":[0.001781459,0.0003776654,0.04888365,0.0006376984,0.0002098827,0.00322434,0.0001770245,0.0003229052,0.0001389797,0.000004146895,0.9436772,0.0005649751],"study_design_scores_gemma":[0.005211885,0.0007932546,0.03888413,0.0003633514,0.00055783,0.00004708843,0.00002636856,0.001197016,0.00001494238,0.0002681329,0.9518514,0.0007845538],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.06018836,0.0002129144,0.00007276915,0.9042699,0.0007013954,0.003754614,0.01600838,0.005413257,0.009378392],"genre_scores_gemma":[0.1144364,0.00007350077,0.00003615177,0.8703074,0.006653714,0.0004649672,0.007533355,0.0001691504,0.0003253552],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.05424802,"threshold_uncertainty_score":0.9997948,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W1984926150","doi":"10.2196/jmir.1157","title":"Infodemiology and Infoveillance: Framework for an Emerging Set of Public Health Informatics Methods to Analyze Search, Communication and Publication Behavior on the Internet","year":2009,"lang":"en","type":"editorial","venue":"Journal of Medical Internet Research","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":1412,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"The Internet; Computer science; Social media; Health informatics; Public health; Public health informatics; Public health surveillance; Population; Data science; World Wide Web; Internet privacy; Health policy; Medicine; Environmental health; HRHIS","retraction":null,"screen_n_in":null,"score":{"opus":0.195690452474405,"gpt":0.563388056423884,"spread":0.367697603949479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05670451,0.0002669182,0.001209758,0.001174248,0.00009401811,0.0002104946,0.001659989,0.0008891579,0.0001370069],"category_scores_gemma":[0.09481916,0.000177987,0.0001454253,0.0005950944,0.0007049226,0.0002843955,0.0007430329,0.004916548,0.000003434225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003894677,"about_ca_system_score_gemma":0.002228558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002640402,"about_ca_topic_score_gemma":0.0001036412,"domain_scores_codex":[0.9894038,0.003704063,0.002330091,0.0002943999,0.003601369,0.0006662745],"domain_scores_gemma":[0.9800333,0.0120388,0.001349447,0.001059112,0.004009085,0.001510233],"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":[0.0005046471,0.0001763894,0.001312858,0.0004474577,0.000184431,0.000004030215,0.003010409,7.359446e-7,0.00000291916,0.001966775,0.7931123,0.1992771],"study_design_scores_gemma":[0.001271787,0.005549931,0.004823325,0.002459699,0.00005729064,0.00006957213,0.001662869,0.003363834,0.00001567252,0.0007117084,0.9798366,0.0001776421],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"editorial","genre_scores_codex":[0.1734181,0.0139156,0.2472429,0.4458555,0.1056483,0.01076545,0.001887804,0.0001649311,0.001101299],"genre_scores_gemma":[0.1952386,0.06522385,0.3230379,0.0178812,0.3882684,0.0008546147,0.007553768,0.0004235303,0.001518085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4279743,"threshold_uncertainty_score":0.9973791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138016069","doi":"10.1177/2053951714541861","title":"Surveillance, Snowden, and Big Data: Capacities, consequences, critique","year":2014,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":825,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Big data; Metadata; Sociology; Transparency (behavior); Panopticon; The Internet; Internet privacy; Data science; Political science; Computer security; Computer science; Law; Politics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.11960032265849,"gpt":0.3182713755477701,"spread":0.1986710528892801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001740046,0.0003228618,0.0006172615,0.00003516781,0.0002039448,0.0001168946,0.00117417,0.0001807006,0.00006052485],"category_scores_gemma":[0.001230798,0.0002946821,0.00007747648,0.0002762832,0.00138108,0.0004435492,0.001518822,0.0003642167,0.00005651725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000641977,"about_ca_system_score_gemma":0.0004930328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001072314,"about_ca_topic_score_gemma":0.001318528,"domain_scores_codex":[0.9970666,0.0002368116,0.0004391488,0.001212045,0.0005074677,0.0005379958],"domain_scores_gemma":[0.9942362,0.000383871,0.0001503704,0.004657909,0.0001741736,0.0003974632],"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":[0.00005779061,0.0001167808,0.04508489,0.0005010053,0.0002298545,0.00004098087,0.0002639195,2.058004e-7,0.0009626541,0.0003314924,0.9082175,0.04419285],"study_design_scores_gemma":[0.001665607,0.00007179078,0.05163749,0.0001473564,0.00009374005,0.0001381476,0.0006318194,0.0009612994,0.00006781839,0.0001941516,0.9439583,0.0004325205],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4736162,0.02989429,0.02249672,0.0226049,0.008887025,0.003819375,0.416134,0.002706264,0.01984123],"genre_scores_gemma":[0.9152864,0.006496533,0.00456774,0.006266064,0.002733365,0.00002436866,0.06382701,0.00007725105,0.0007213072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4416701,"threshold_uncertainty_score":0.9999505,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2069516633","doi":"10.1126/science.346.6213.1063","title":"Social media for large studies of behavior","year":2014,"lang":"en","type":"article","venue":"Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":646,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Social media; Data science; Computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.06830385733705342,"gpt":0.4087486034597391,"spread":0.3404447461226857,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000803102,0.00004768359,0.0001720158,0.00005430269,0.0001116086,0.000004937811,0.0001544305,0.00001355207,0.00001458101],"category_scores_gemma":[0.002083061,0.00003782806,0.0000406137,0.0002351645,0.0004828706,0.00007515604,0.0000721119,0.00002715163,0.00001175484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002361181,"about_ca_system_score_gemma":0.000106028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.541318e-7,"about_ca_topic_score_gemma":0.00001396997,"domain_scores_codex":[0.9991837,0.00001088551,0.0001155843,0.0001747293,0.0003186299,0.0001964327],"domain_scores_gemma":[0.9993201,0.0001171594,0.00005404525,0.0001707669,0.0002702139,0.0000676703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004254292,0.001596411,0.4862278,0.001051665,0.0001046528,0.00001922042,0.01369457,0.000001061437,0.2453014,0.05898741,0.04209256,0.1504979],"study_design_scores_gemma":[0.001510553,0.0001571234,0.9639397,0.00004509697,0.000082015,0.00000258563,0.0007128904,0.0001340119,0.009936659,0.0009064435,0.02245063,0.0001222824],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979253,0.0001869972,0.0002369083,0.000311929,0.0003080859,0.0002425688,0.0001413646,0.0000380688,0.0006087509],"genre_scores_gemma":[0.9986202,0.000005510795,0.001018762,0.0001189575,0.0001246521,0.00002750914,0.000009623612,0.000004053694,0.00007077098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.477712,"threshold_uncertainty_score":0.249377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123737882","doi":"10.1186/1471-2458-14-1144","title":"A systematic review of barriers to data sharing in public health","year":2014,"lang":"en","type":"review","venue":"BMC Public Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":599,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University Health Network","funders":"National Institute of General Medical Sciences; Wellcome Trust; Bill and Melinda Gates Foundation","keywords":"Data sharing; Public health; Systematic review; Medicine; Grey literature; Context (archaeology); Global health; Biostatistics; Public relations; Health policy; Health informatics; Variety (cybernetics); Inclusion (mineral); Knowledge management; Political science; MEDLINE; Computer science; Sociology; Nursing; Alternative medicine; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.2348080518244396,"gpt":0.4521672055233746,"spread":0.217359153698935,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03462689,0.0007585275,0.0123272,0.001320373,0.0001073007,0.0001084864,0.003343407,0.0002249392,0.0003067223],"category_scores_gemma":[0.04211013,0.0006052667,0.0005250754,0.003104909,0.0000744637,0.0003595398,0.001586781,0.0007950734,0.0002597501],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002213896,"about_ca_system_score_gemma":0.04170174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000470942,"about_ca_topic_score_gemma":0.0005558706,"domain_scores_codex":[0.9831925,0.004402159,0.006841298,0.002141161,0.001475102,0.001947783],"domain_scores_gemma":[0.9812155,0.0006306366,0.00343259,0.008957969,0.0003170833,0.005446245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001687877,0.00009640337,0.0001338436,0.8971197,0.0001330621,0.000005476373,0.00005153166,1.366922e-8,7.617785e-10,0.0003023008,0.0263021,0.0758539],"study_design_scores_gemma":[0.0001988325,0.00007960599,0.00003238525,0.4915759,0.0001019066,0.0000458479,0.00002370992,0.00002462468,2.471494e-10,0.000001169735,0.5077199,0.0001961585],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.121865e-7,0.9758155,0.0007315982,0.007904268,0.0002572052,0.01213907,0.002504576,0.0001723688,0.0004751345],"genre_scores_gemma":[0.000006818462,0.9722648,0.001440663,0.01496032,0.0001761689,0.000769396,0.01011022,0.0001549869,0.0001166663],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4814177,"threshold_uncertainty_score":0.9996399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037960575","doi":"10.2196/21820","title":"How to Fight an Infodemic: The Four Pillars of Infodemic Management","year":2020,"lang":"en","type":"editorial","venue":"Journal of Medical Internet Research","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":559,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"JMIR Publications","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06793965571996848,"gpt":0.4266770820376226,"spread":0.3587374263176542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01065546,0.000369305,0.001361233,0.0008020373,0.00004924909,0.0001785524,0.003982921,0.0009191168,0.0009114499],"category_scores_gemma":[0.03300599,0.0002253194,0.0004362218,0.0008004977,0.0005233547,0.0002055015,0.001686944,0.007339899,0.0001045544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000516164,"about_ca_system_score_gemma":0.002339703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009924959,"about_ca_topic_score_gemma":0.00007715288,"domain_scores_codex":[0.9809699,0.001079807,0.001515934,0.0004913715,0.01520155,0.000741413],"domain_scores_gemma":[0.9903011,0.002465585,0.0007684905,0.001116207,0.003128931,0.002219637],"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":[0.00180308,0.0001825721,0.0002614871,0.0009739976,0.0008087546,0.002818029,0.0004002526,0.000001631847,0.0000374944,0.00006253845,0.9766382,0.01601199],"study_design_scores_gemma":[0.001850038,0.002128474,0.0003448636,0.00337782,0.0001636779,0.0001274523,0.0003545688,0.0002082387,0.00005714351,0.00009120309,0.9911191,0.0001774405],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.01436983,0.006055542,0.001801684,0.2007228,0.7647647,0.003477608,0.0009532699,0.000116304,0.007738275],"genre_scores_gemma":[0.02681847,0.008383036,0.0009749998,0.002712877,0.9476955,0.00006233804,0.0004362836,0.0001915353,0.01272498],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.1980099,"threshold_uncertainty_score":0.9979737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947051005","doi":"10.2196/13439","title":"Google Trends in Infodemiology and Infoveillance: Methodology Framework","year":2019,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":509,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Data science; The Internet; Health informatics; World Wide Web; Health care","retraction":null,"screen_n_in":null,"score":{"opus":0.06683018230169083,"gpt":0.3883553759672504,"spread":0.3215251936655595,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002808504,0.000303709,0.001283951,0.000501445,0.00007358544,0.00003766594,0.0001556714,0.0003309611,0.0002881823],"category_scores_gemma":[0.001562506,0.0002738556,0.00006661435,0.0008453351,0.0002231145,0.000177878,0.0001674599,0.0006290838,0.00005160962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001224722,"about_ca_system_score_gemma":0.0005237127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001332706,"about_ca_topic_score_gemma":0.0002304652,"domain_scores_codex":[0.9962603,0.0009352873,0.0007626973,0.000757584,0.0002427797,0.001041283],"domain_scores_gemma":[0.9968154,0.00111755,0.0002582304,0.0006934255,0.0001013512,0.001014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002122765,0.0000640835,0.9026924,0.0003079331,0.00002181244,0.00001357498,0.0004570232,0.00000106561,0.000009352389,0.002753848,0.003196008,0.09027058],"study_design_scores_gemma":[0.00156634,0.0003835555,0.7921371,0.00003177814,4.533139e-7,0.00009450564,0.0001552551,0.0002836104,1.618483e-7,0.0003439065,0.2047985,0.0002048552],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624197,0.006225337,0.0003530972,0.02344263,0.0003858444,0.0007869765,0.0001119864,0.0002052785,0.006069188],"genre_scores_gemma":[0.9778735,0.001812866,0.004425433,0.01461581,0.0001513725,0.00009927727,0.0002866866,0.00003606407,0.0006989834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2016025,"threshold_uncertainty_score":0.9999714,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120467164","doi":"10.1197/jamia.m2544","title":"HealthMap: Global Infectious Disease Monitoring through Automated Classification and Visualization of Internet Media Reports","year":2007,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":503,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. National Library of Medicine; Canadian Institutes of Health Research; National Institutes of Health","keywords":"The Internet; Visualization; Computer science; Infectious disease (medical specialty); Disease; World Wide Web; Data science; Medicine; Artificial intelligence; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.01329114139984812,"gpt":0.3465297721078122,"spread":0.3332386307079641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00234055,0.0001044089,0.0004055092,0.00008276104,0.00004328997,0.00002140377,0.0001111575,0.00006977813,0.000006714522],"category_scores_gemma":[0.008114773,0.00007489091,0.0001069851,0.0005591713,0.0001366876,0.00028778,0.00006275082,0.0002209682,0.000001372854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007792035,"about_ca_system_score_gemma":0.0004318085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006677956,"about_ca_topic_score_gemma":0.00001194493,"domain_scores_codex":[0.9966576,0.0001135364,0.001465588,0.0000633468,0.001515407,0.0001845797],"domain_scores_gemma":[0.9938548,0.0002802274,0.004738578,0.000189844,0.0006013624,0.0003352559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001423622,0.0001205166,0.9883667,0.0001246388,0.0001219174,0.00001827219,0.0007756286,0.00001549804,0.0000393711,0.00009610878,0.002389852,0.007789095],"study_design_scores_gemma":[0.000585298,0.0001248213,0.9902121,0.000364058,0.0001174067,0.0001197196,0.0004926508,0.007155003,0.00008157606,0.0001764126,0.0005066505,0.0000642812],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914162,0.00009284364,0.006592358,0.0007828979,0.0006515265,0.0001604858,0.00001441192,0.0000581052,0.0002311409],"genre_scores_gemma":[0.99797,0.0002876726,0.0009249775,0.0005563437,0.000220239,0.000001158648,0.00002510014,0.000008040807,0.000006430933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007724814,"threshold_uncertainty_score":0.9714727,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135035282","doi":"10.4269/ajtmh.2012.11-0597","title":"Social and News Media Enable Estimation of Epidemiological Patterns Early in the 2010 Haitian Cholera Outbreak","year":2012,"lang":"en","type":"article","venue":"American Journal of Tropical Medicine and Hygiene","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":445,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases","keywords":"Outbreak; Cholera; Epidemiology; Estimation; Social media; Environmental health; Government (linguistics); Geography; Basic reproduction number; Public health; Demography; Medicine; Socioeconomics; Political science; Virology; Sociology; Population; Pathology; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.04292687554676727,"gpt":0.3292744853614136,"spread":0.2863476098146463,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005983473,0.0001288966,0.0007756599,0.0001301162,0.00003596954,0.000005600619,0.0001105769,0.00004578011,0.00004566953],"category_scores_gemma":[0.001320159,0.00006820265,0.00006522395,0.0001836065,0.0006917586,0.0001358692,0.00003392975,0.0003494958,0.000001104012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002176552,"about_ca_system_score_gemma":0.00003226877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004057265,"about_ca_topic_score_gemma":0.00001964302,"domain_scores_codex":[0.9984342,0.0002543905,0.0006051132,0.0001159984,0.0003337976,0.0002564437],"domain_scores_gemma":[0.9985078,0.0006107709,0.0004013878,0.0001317905,0.00008243219,0.0002658223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003017443,0.0001503949,0.8561288,0.00003573281,0.00003948729,0.00003848063,0.003038722,0.000001100872,0.0001515697,0.0002124644,0.001112551,0.138789],"study_design_scores_gemma":[0.001533098,0.001317118,0.9933848,0.0001520476,0.0001079061,0.0002041931,0.001780574,0.00003711692,0.00001228635,0.0001409113,0.001268094,0.00006187362],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9773349,0.000821754,0.000652309,0.02085458,0.00009930953,0.0001006051,0.00001074824,0.000005042415,0.0001208239],"genre_scores_gemma":[0.9953703,0.0003575881,0.001099535,0.002376155,0.0007726493,0.00000274698,0.000008722958,0.00000744405,0.000004835611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1387272,"threshold_uncertainty_score":0.2781223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2019432915","doi":"10.1016/j.amepre.2011.02.006","title":"Infodemiology and Infoveillance","year":2011,"lang":"en","type":"article","venue":"American Journal of Preventive Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":431,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network","funders":"","keywords":"Health informatics; The Internet; Public health informatics; Informatics; Public health; Health information; World Wide Web; Analytics; Data science; Computer science; Internet privacy; Health policy; Medicine; Political science; HRHIS; Health care; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.02292560272081214,"gpt":0.2937874217530999,"spread":0.2708618190322878,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007366238,0.0001507441,0.0008434677,0.0001996208,0.00002424593,0.000001675755,0.000136194,0.00002647444,0.0003314381],"category_scores_gemma":[0.0009828015,0.0001025177,0.00008395372,0.0002613558,0.001209277,0.0001053584,0.00005372227,0.0002628947,0.0000113304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003622042,"about_ca_system_score_gemma":0.0001049144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005820529,"about_ca_topic_score_gemma":0.000004460981,"domain_scores_codex":[0.9986025,0.0001703344,0.0006094526,0.0001537246,0.0002529017,0.0002110822],"domain_scores_gemma":[0.9981509,0.0001687357,0.0007906745,0.0002291441,0.0003256811,0.0003348825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00139311,0.0001421179,0.8438669,0.00005828092,0.0004226581,0.0004053654,0.002351989,2.947373e-7,0.0009038183,0.0004395185,0.005410181,0.1446058],"study_design_scores_gemma":[0.00222966,0.004663565,0.9749958,0.0003738562,0.0001966431,0.001360727,0.00116102,0.000008579483,0.00009206453,0.000679292,0.01412356,0.0001152246],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834589,0.002293332,0.002499106,0.001581597,0.0002604516,0.0001759036,0.000010596,0.0000246231,0.009695495],"genre_scores_gemma":[0.9928774,0.0007834749,0.004326569,0.001482387,0.0002872278,0.000002286139,0.000004519003,0.00001481234,0.0002213481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1444906,"threshold_uncertainty_score":0.4455632,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1596222673","doi":"","title":"Infodemiology: tracking flu-related searches on the web for syndromic surveillance.","year":2006,"lang":"en","type":"article","venue":"PubMed","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":420,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"The Internet; Public health; Public health surveillance; Medicine; Outbreak; Environmental health; Epidemiology; Tracking (education); Warrant; Population; Medical emergency; Internet privacy; Computer science; Business; World Wide Web; Psychology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.04269425718133486,"gpt":0.2593866065522838,"spread":0.2166923493709489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001639257,0.000194887,0.0004043733,0.0001015502,0.0001225089,0.00002950306,0.0002241464,0.0001260059,0.00005576784],"category_scores_gemma":[0.0015475,0.0001327109,0.0001758951,0.0002453371,0.000179523,0.00006436919,0.00004674913,0.0002666982,0.00008850694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001345048,"about_ca_system_score_gemma":0.00008787487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004104913,"about_ca_topic_score_gemma":0.00006487621,"domain_scores_codex":[0.998165,0.0001818134,0.0003838828,0.000368812,0.0002420801,0.0006584443],"domain_scores_gemma":[0.9979283,0.001140187,0.0001240903,0.0005588725,0.000108997,0.0001395444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00115512,0.0004161075,0.7562301,0.0002245128,0.0004140425,0.00008165701,0.00005779967,0.0002138363,0.0004739084,0.006608912,0.1728355,0.06128854],"study_design_scores_gemma":[0.001480565,0.00004368825,0.9651282,0.00002231427,0.00002948612,0.00002968225,0.0000148223,0.0006090358,0.0001524396,0.0008940944,0.03144279,0.0001528748],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784099,0.0004623972,0.00003372742,0.00845286,0.0002934953,0.002505927,0.0003717642,0.0003039412,0.00916594],"genre_scores_gemma":[0.9950518,0.00003957465,0.00005520172,0.0008460328,0.0002095668,0.001655504,0.0003361877,0.00004150577,0.001764628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2088981,"threshold_uncertainty_score":0.5411793,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063584357","doi":"10.1186/1471-2458-14-147","title":"Measuring underreporting and under-ascertainment in infectious disease datasets: a comparison of methods","year":2014,"lang":"en","type":"article","venue":"BMC Public Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":418,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"International Livestock Research Institute; Universität Bielefeld; Universiteit Utrecht; European Centre for Disease Prevention and Control","keywords":"Medicine; Biostatistics; Public health; Epidemiology; Environmental health; Infectious disease (medical specialty); Disease; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1604070786730905,"gpt":0.4423991248874735,"spread":0.281992046214383,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004570801,0.0001569767,0.0006330521,0.0002433619,0.00007465827,0.00003019532,0.00009517885,0.00004141263,0.00002082757],"category_scores_gemma":[0.003201008,0.0001486636,0.00005102095,0.000337385,0.00008158583,0.0001429792,0.0001370256,0.0001906211,0.000003005246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003455906,"about_ca_system_score_gemma":0.001089446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007840672,"about_ca_topic_score_gemma":0.0009879672,"domain_scores_codex":[0.996992,0.0008980678,0.0009209416,0.0004106478,0.0003247946,0.0004535506],"domain_scores_gemma":[0.9975981,0.0003772354,0.0004826098,0.0006509527,0.00005807035,0.000833029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000492659,0.0004780495,0.9429472,0.00112715,0.00002552077,0.000002873384,0.0001800664,0.00008569012,0.00003425347,0.001002437,0.0005442077,0.05352331],"study_design_scores_gemma":[0.001668505,0.0001596521,0.9734095,0.0002205146,0.00001946274,0.00001242414,0.0003898624,0.01242295,0.0000139748,0.0003577815,0.01117755,0.0001477761],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8213096,0.002277163,0.1684316,0.004896819,0.0002142276,0.001293349,0.0002638676,0.0002238188,0.001089582],"genre_scores_gemma":[0.9890505,0.00004134487,0.009551257,0.0007580295,0.00004594243,0.00002741552,0.0004974112,0.00002159357,0.000006487618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1677409,"threshold_uncertainty_score":0.6062325,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013056994","doi":"10.2196/18828","title":"Predicting COVID-19 Incidence Through Analysis of Google Trends Data in Iran: Data Mining and Deep Learning Pilot Study","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":415,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Mean squared error; Data mining; Metric (unit); Incidence (geometry); Outbreak; Statistics; Computer science; Health care; Medicine; Environmental health; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1985095149059298,"gpt":0.4130092291816802,"spread":0.2144997142757504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003461764,0.0002695218,0.001266634,0.0003879662,0.0002023087,0.00007679676,0.0007467919,0.00005468576,0.00006763113],"category_scores_gemma":[0.007799245,0.0002609793,0.000029853,0.003133878,0.0001690855,0.0007273755,0.001356797,0.0003637479,0.000001134692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000875252,"about_ca_system_score_gemma":0.0007251215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001982905,"about_ca_topic_score_gemma":0.01355425,"domain_scores_codex":[0.9954002,0.0009231888,0.001025104,0.001391231,0.0006184213,0.0006418612],"domain_scores_gemma":[0.995564,0.0007975367,0.0005021679,0.001685829,0.00007952536,0.001370941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003898193,0.0003251598,0.9529732,0.0005382827,0.0002660037,0.00004950712,0.005604511,0.00002225294,0.000004366988,0.000004817195,0.0006469922,0.03917501],"study_design_scores_gemma":[0.00236524,0.001320207,0.89788,0.00002434584,0.00002931826,0.00001014878,0.005017039,0.07736084,3.585277e-8,9.207454e-7,0.01579644,0.0001955157],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981766,0.003996849,0.0005900937,0.01084154,0.00004299847,0.0007195578,0.001584487,0.0001729227,0.0002855238],"genre_scores_gemma":[0.988777,0.0007983856,0.0008716313,0.003637954,0.00008907712,0.00002872533,0.005750191,0.00002700066,0.00001999623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07733858,"threshold_uncertainty_score":0.9999843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068372477","doi":"10.1371/journal.pmed.0050151","title":"Surveillance Sans Frontières: Internet-Based Emerging Infectious Disease Intelligence and the HealthMap Project","year":2008,"lang":"en","type":"article","venue":"PLoS Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":398,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. National Library of Medicine; Canadian Institutes of Health Research; National Institutes of Health","keywords":"The Internet; Infectious disease (medical specialty); Emerging infectious disease; Medicine; Data science; Disease surveillance; Public health; Disease; Computer science; World Wide Web; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.03276349917636651,"gpt":0.2926836683852794,"spread":0.2599201692089129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006866512,0.0003301801,0.0007828131,0.0002140615,0.0001907815,0.00001125098,0.0002296013,0.00005632539,0.0002605224],"category_scores_gemma":[0.00263215,0.0002024554,0.0001034485,0.0004784871,0.001284732,0.00008844498,0.00009531187,0.000383527,0.00005436877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001041936,"about_ca_system_score_gemma":0.000367534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006282374,"about_ca_topic_score_gemma":0.0003167378,"domain_scores_codex":[0.9973546,0.0003270694,0.0005969038,0.0005734744,0.0006883753,0.0004595595],"domain_scores_gemma":[0.9976633,0.0006529605,0.0002107758,0.0007983706,0.0002140578,0.0004605342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005878003,0.000717051,0.9368414,0.001575336,0.0004199251,0.0009743334,0.005142667,0.00005840005,0.0001166084,0.0005520031,0.03863572,0.009088508],"study_design_scores_gemma":[0.02501687,0.001811696,0.8233347,0.003747102,0.0006753507,0.0004627057,0.001262769,0.07252119,0.0003039724,0.0004539947,0.06921691,0.00119276],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.925195,0.01685302,0.01207554,0.03362128,0.0009647521,0.00422195,0.0002124452,0.0008453391,0.006010693],"genre_scores_gemma":[0.9918503,0.001970437,0.0001803474,0.004705159,0.0005066116,0.0001427038,0.0001563322,0.00004840096,0.0004397219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1135068,"threshold_uncertainty_score":0.8255892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2610490986","doi":"10.1371/journal.pone.0056176","title":"Influenza Forecasting with Google Flu Trends","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":360,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Division of Civil, Mechanical and Manufacturing Innovation; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Homeland Security; National Science Foundation","keywords":"Seasonal influenza; Statistics; Autoregressive integrated moving average; Autoregressive model; Sample (material); Computer science; Negative binomial distribution; Coronavirus disease 2019 (COVID-19); Econometrics; Time series; Mathematics; Medicine; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.08243873784778845,"gpt":0.2499382646985501,"spread":0.1674995268507617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006451866,0.0001310322,0.0002905239,0.00009288241,0.00004443206,0.00002596381,0.00009011543,0.00003899856,0.001685857],"category_scores_gemma":[0.0001453602,0.000102228,0.0000353088,0.0002572701,0.00005546779,0.0001733423,0.00004779923,0.0001285092,0.0007475337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003970757,"about_ca_system_score_gemma":0.00004196968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007209941,"about_ca_topic_score_gemma":0.00002252998,"domain_scores_codex":[0.9989302,0.00001956702,0.0001777704,0.0002349321,0.0003604154,0.0002771418],"domain_scores_gemma":[0.9990866,0.00004345203,0.00007018166,0.0004313866,0.0001516011,0.0002168338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004124645,0.003343209,0.8857616,0.0006248883,0.001170538,0.0001388862,0.0003553487,0.000009383042,0.02562333,0.00007318042,0.01467322,0.06781393],"study_design_scores_gemma":[0.006130861,0.001283476,0.9581803,0.001659912,0.0007432732,0.0000465405,0.0001319044,0.006967355,0.01260964,0.0001090079,0.0114486,0.0006891497],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746442,0.000217117,0.00001498237,0.0004089388,0.00001184181,0.0002506712,0.00004545012,0.0002130681,0.02419367],"genre_scores_gemma":[0.9874873,0.000007488746,0.007285609,0.001076506,0.0001844245,0.00009669059,0.0001264319,0.00004247739,0.003693061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07241867,"threshold_uncertainty_score":0.9992267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2564356125","doi":"10.1146/annurev-publhealth-031816-044348","title":"Public Health Surveillance Systems: Recent Advances in Their Use and Evaluation","year":2016,"lang":"en","type":"review","venue":"Annual Review of Public Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":331,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Centers for Disease Control and Prevention","keywords":"Public health surveillance; Public health; Public health informatics; Health informatics; Context (archaeology); Health surveillance; Population health; Health care; Environmental health; Public relations; Data science; HRHIS; Business; Health policy; Risk analysis (engineering); Medicine; Computer science; Political science; Nursing; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.2196387305540262,"gpt":0.4496767715969359,"spread":0.2300380410429096,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03214478,0.0007413158,0.006790422,0.0006490446,0.00009512612,0.00007855481,0.0004572681,0.0002160173,0.0001272855],"category_scores_gemma":[0.01064706,0.000476662,0.0003719096,0.001719942,0.0001944213,0.001190466,0.0002017781,0.0005298433,0.00004790552],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001850171,"about_ca_system_score_gemma":0.01733187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000172827,"about_ca_topic_score_gemma":0.0002405374,"domain_scores_codex":[0.9807303,0.01064801,0.004296172,0.001316886,0.001556556,0.001452106],"domain_scores_gemma":[0.9901707,0.001137408,0.003591819,0.001672397,0.001967375,0.001460273],"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":[0.000002296594,0.0001223946,0.0002669243,0.3010551,0.00005986727,0.000001866674,0.00005248152,1.04017e-8,1.360399e-9,0.0001801669,0.006683096,0.6915758],"study_design_scores_gemma":[0.0004447265,0.0002185633,0.0007938553,0.236367,0.00002957387,0.00005885634,0.00005455453,0.000002996088,9.385135e-10,0.000004628682,0.7617695,0.0002558359],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002553633,0.9726908,0.000061042,0.01324658,0.0004568534,0.007865296,0.005298688,0.00008807061,0.0002900838],"genre_scores_gemma":[0.00002226324,0.9921072,0.00007402282,0.002978937,0.000216864,0.0006419736,0.003812076,0.0000926029,0.00005405339],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7550864,"threshold_uncertainty_score":0.9997685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151485425","doi":"10.1371/journal.pone.0064323","title":"Monitoring Influenza Epidemics in China with Search Query from Baidu","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":254,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"University of Chinese Academy of Sciences; National Institutes of Health; Chinese Academy of Sciences; U.S. National Library of Medicine; National Natural Science Foundation of China","keywords":"Computer science; Web search query; China; Index (typography); Data mining; Information retrieval; Selection (genetic algorithm); Query expansion; Search engine; Geography; Artificial intelligence; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.05947158787726732,"gpt":0.2765700579275676,"spread":0.2170984700503003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001846636,0.0001446178,0.0003978315,0.0001026053,0.00002787632,0.00002335957,0.0001415352,0.00006769589,0.0002715021],"category_scores_gemma":[0.000292468,0.0001231593,0.0000280488,0.0002328709,0.00005720501,0.0002266353,0.00008474654,0.000362737,0.0005271399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001111008,"about_ca_system_score_gemma":0.00009162217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00294223,"about_ca_topic_score_gemma":0.00006319895,"domain_scores_codex":[0.9985581,0.00007799926,0.0002561456,0.0003063944,0.0004681135,0.0003332344],"domain_scores_gemma":[0.998922,0.0001385667,0.00005019976,0.0005501129,0.0001069891,0.0002320964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001224104,0.0006289418,0.9860582,0.0001077595,0.0001538282,0.00004640651,0.0002069992,0.0000141197,0.01099049,0.00000513798,0.0001394161,0.001526247],"study_design_scores_gemma":[0.001159522,0.00008629294,0.9888674,0.001058823,0.00005068225,0.000001133092,0.00007276407,0.0007564822,0.007672902,0.00008644455,0.00004766259,0.0001398985],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9971095,0.0005874402,0.00001659881,0.0004832762,0.00002441665,0.0005090426,0.00006119315,0.0001168125,0.00109166],"genre_scores_gemma":[0.9911055,0.0001081292,0.007866922,0.0002816055,0.0003003786,0.0000774058,0.00006344284,0.00003887499,0.0001577285],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007850323,"threshold_uncertainty_score":0.6775492,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3098000326","doi":"10.1016/j.ssci.2020.105093","title":"An overview of scientometric mapping for the safety science community: Methods, tools, and framework","year":2020,"lang":"en","type":"article","venue":"Safety Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":251,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Scientometrics; Data science; Computer science; Context (archaeology); Domain (mathematical analysis); Thematic map; Process (computing); Management science; Engineering; World Wide Web; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.2517380484306804,"gpt":0.466025153135134,"spread":0.2142871047044536,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.01293996,0.0001672098,0.0004095852,0.0004637828,0.001632236,0.0001615419,0.001822903,0.0000426577,0.00003669393],"category_scores_gemma":[0.0168317,0.000117829,0.00007863587,0.01351032,0.004653006,0.0009498869,0.0007459696,0.0003828436,0.000005563235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001165604,"about_ca_system_score_gemma":0.001017682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004167324,"about_ca_topic_score_gemma":0.000003877059,"domain_scores_codex":[0.9970626,0.0002456568,0.000440715,0.0005923325,0.001119028,0.0005396158],"domain_scores_gemma":[0.9951622,0.002098536,0.0002167525,0.001316354,0.0006140066,0.0005920977],"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":[0.0005449447,0.0002786349,0.0320561,0.0009349271,0.00004577116,0.000003879863,0.006744713,0.0001377894,0.07332747,0.05017739,0.0001523118,0.8355961],"study_design_scores_gemma":[0.0008286294,0.00040708,0.9402328,0.0003512038,0.00006763453,0.00001664711,0.002553424,0.02434866,0.003130597,0.0021275,0.02565765,0.0002781639],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1531539,0.02283062,0.7893535,0.02304434,0.001314908,0.004436931,0.001742595,0.0004042938,0.003718921],"genre_scores_gemma":[0.869115,0.0007381891,0.1270571,0.002970237,0.00007098072,0.00001298219,0.00001556394,0.00001263884,0.000007341672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9081767,"threshold_uncertainty_score":0.9996675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107192955","doi":"10.1073/pnas.1006219107","title":"Global capacity for emerging infectious disease detection","year":2010,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":250,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Agency of Canada; McGill University","funders":"U.S. National Library of Medicine; National Institutes of Health; World Health Organization","keywords":"Outbreak; Public health; Infectious disease (medical specialty); Medicine; Pandemic; Hazard ratio; Geography; Disease; Environmental health; Demography; Coronavirus disease 2019 (COVID-19); Confidence interval; Internal medicine; Virology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.02992397184798421,"gpt":0.3246273635576289,"spread":0.2947033917096447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007636569,0.00007080437,0.0001220875,0.00007939523,0.0001658997,0.00001294153,0.000266177,0.00004732001,0.00000996371],"category_scores_gemma":[0.002304968,0.00004962997,0.00009968061,0.0005668909,0.0005580046,0.0002833859,0.00006072857,0.000111585,8.632567e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003806227,"about_ca_system_score_gemma":0.00005227659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008850806,"about_ca_topic_score_gemma":0.000001007447,"domain_scores_codex":[0.9987432,0.000002532281,0.0002037027,0.0002004721,0.0007243773,0.0001257504],"domain_scores_gemma":[0.9991938,0.00005388581,0.0002510266,0.00000973866,0.0004082403,0.00008331699],"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":[0.0002010271,0.0001834653,0.4381453,0.000408764,0.00004467105,1.122012e-8,0.00005058981,0.00005421411,0.5123183,0.03975905,0.001216611,0.007618096],"study_design_scores_gemma":[0.0004176501,0.00004790733,0.9006276,0.00005347711,0.0000396534,0.00001096995,0.00001835584,0.001997927,0.04790151,0.04718315,0.001627296,0.00007446697],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955523,0.00002149223,0.00001632141,0.001436202,0.00006749076,0.000306199,0.0001357034,0.00002954605,0.002434754],"genre_scores_gemma":[0.9982451,0.000003345496,0.001325177,0.0002256844,0.0001483857,0.00002117351,4.185684e-7,0.00000289032,0.00002784675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4644167,"threshold_uncertainty_score":0.2759429,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968335419","doi":"10.1186/1471-2458-13-16","title":"Ascertainment of chronic diseases using population health data: a comparison of health administrative data and patient self-report","year":2013,"lang":"en","type":"article","venue":"BMC Public Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":244,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Ottawa Hospital; Institute for Clinical Evaluative Sciences; Élisabeth Bruyère Hospital","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Medicine; Stroke (engine); Myocardial infarction; Population; Concordance; Biostatistics; COPD; Epidemiology; Heart failure; Cohen's kappa; Diabetes mellitus; Public health; Emergency medicine; Physical therapy; Internal medicine; Environmental health; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1825045158645577,"gpt":0.4437111929780997,"spread":0.2612066771135421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001683035,0.0002364031,0.001219995,0.0001750805,0.0001726563,0.00003665579,0.0003750706,0.00004822367,0.00005314978],"category_scores_gemma":[0.0004865425,0.0002135167,0.00004226154,0.0003552643,0.0001100474,0.0006328931,0.0005350389,0.0001531833,0.000002627579],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103596,"about_ca_system_score_gemma":0.01087691,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01375378,"about_ca_topic_score_gemma":0.001590161,"domain_scores_codex":[0.9950548,0.0006446625,0.002053783,0.0008177168,0.0007940221,0.0006349886],"domain_scores_gemma":[0.9938276,0.0001432741,0.002283848,0.002514733,0.0002046735,0.001025834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004449092,0.002240349,0.9103139,0.004100079,0.0001346494,0.00000300321,0.000861516,0.00001443566,0.000004247964,0.0001288049,0.01397252,0.06818201],"study_design_scores_gemma":[0.001227537,0.001554764,0.9443028,0.0004363215,0.00003078325,0.00004096867,0.001398143,0.04016893,0.000001610445,0.00002198993,0.01065051,0.0001656602],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.948858,0.01694027,0.005059105,0.01600821,0.000269201,0.00505505,0.007602028,0.0001730312,0.00003506543],"genre_scores_gemma":[0.9701858,0.0002730056,0.008821676,0.0007654461,0.00007928517,0.00002308261,0.0198184,0.00002881598,0.000004542141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06801634,"threshold_uncertainty_score":0.9947305,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013917522","doi":"10.2196/18717","title":"Assessment of Health Information About COVID-19 Prevention on the Internet: Infodemiological Study","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":240,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"The Internet; Public health; Medicine; Odds ratio; Coronavirus disease 2019 (COVID-19); Upload; Pandemic; Internet privacy; Environmental health; Family medicine; Disease; World Wide Web; Infectious disease (medical specialty); Nursing; Computer science; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.0996359349607142,"gpt":0.4116395862603601,"spread":0.3120036512996459,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004254287,0.0001800606,0.0006637261,0.00008835181,0.0001455446,0.00004669463,0.0001828263,0.00005986335,0.0001108802],"category_scores_gemma":[0.002501063,0.0001187927,0.00007286482,0.0003638266,0.0001013641,0.0001963216,0.0001071655,0.0003232759,0.00001520313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002295984,"about_ca_system_score_gemma":0.00286748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001291221,"about_ca_topic_score_gemma":0.00006951647,"domain_scores_codex":[0.9962817,0.001456142,0.00104104,0.0003096798,0.0004944672,0.000416998],"domain_scores_gemma":[0.9972939,0.0003934629,0.0006536845,0.0003856724,0.0001258025,0.001147405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001688027,0.0004009485,0.9338034,0.0007712549,0.00004648821,0.000002069822,0.001979997,0.00000929761,5.667443e-7,0.002704204,0.02648535,0.03362765],"study_design_scores_gemma":[0.001390269,0.002741267,0.823054,0.00002056959,6.225246e-7,0.000003900529,0.001038377,0.001480938,4.89355e-8,0.00002169304,0.1701635,0.0000848374],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7715046,0.0006387394,0.008966329,0.2110582,0.000136458,0.005110072,0.0002145797,0.0002606531,0.002110436],"genre_scores_gemma":[0.9344557,0.0002267687,0.000106701,0.0645429,0.00005246387,0.0001438961,0.0004314143,0.00000825929,0.00003188869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1629511,"threshold_uncertainty_score":0.5086786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110349231","doi":"10.1140/epjds/s13688-015-0054-0","title":"Enhancing disease surveillance with novel data streams: challenges and opportunities","year":2015,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":239,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of General Medical Sciences; Economic and Social Research Council; National Institutes of Health; Santa Fe Institute","keywords":"Computer science; Data science; Public health surveillance; Social media; Public health; Key (lock); Big data; Management science; Computer security; Data mining; World Wide Web; Engineering; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2809649834510432,"gpt":0.349388351430047,"spread":0.06842336797900378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002388034,0.000213357,0.0003123267,0.0001267842,0.0001403518,0.0001241859,0.001997999,0.00002402518,0.00001748331],"category_scores_gemma":[0.001866544,0.0001647302,0.000008689292,0.0002650831,0.001318246,0.002806684,0.002764277,0.0001263065,0.00001750232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005098374,"about_ca_system_score_gemma":0.001901258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007822122,"about_ca_topic_score_gemma":0.0004962185,"domain_scores_codex":[0.9969103,0.00004501318,0.0002377401,0.001305895,0.001036141,0.0004649216],"domain_scores_gemma":[0.9932521,0.0001141957,0.0001207,0.005026563,0.0002629769,0.001223466],"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":[0.004306178,0.00329751,0.2516147,0.002801885,0.0004747644,0.003965703,0.004473478,0.00004233699,0.01000939,0.01391057,0.04613005,0.6589734],"study_design_scores_gemma":[0.005964432,0.000639134,0.6634562,0.001166581,0.0002245035,0.0004627774,0.007252555,0.02477258,0.0003060361,0.0001575678,0.2939999,0.001597773],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7751907,0.06946392,0.006442674,0.02535396,0.001283554,0.002383196,0.100505,0.00123511,0.0181419],"genre_scores_gemma":[0.985813,0.00358789,0.005029009,0.0004913386,0.0001917333,0.000008925834,0.004632716,0.0000285175,0.0002168411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6573756,"threshold_uncertainty_score":0.6717502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124170079","doi":"10.1503/cmaj.090215","title":"Early detection of disease outbreaks using the Internet","year":2009,"lang":"en","type":"review","venue":"Canadian Medical Association Journal","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":231,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Outbreak; Public health; Government (linguistics); Disease surveillance; The Internet; Disease; Infectious disease (medical specialty); Internet privacy; Environmental health; Medicine; Computer science; Computer security; World Wide Web; Virology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.0219338277227732,"gpt":0.3034691342146786,"spread":0.2815353064919054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001593844,0.0002457758,0.001056094,0.0003147821,0.0001188264,0.00006847134,0.000354408,0.000474469,0.0007874765],"category_scores_gemma":[0.00326481,0.0001672701,0.000621012,0.0003847794,0.00006459127,0.00007895903,0.00002458112,0.001591481,0.00007306931],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002095015,"about_ca_system_score_gemma":0.007750125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0018791,"about_ca_topic_score_gemma":0.003822179,"domain_scores_codex":[0.9963598,0.0005237128,0.0009399446,0.0002104114,0.001544356,0.000421776],"domain_scores_gemma":[0.9957515,0.0001968647,0.0009669813,0.0002835246,0.0003737668,0.002427375],"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":[0.00001237413,0.00002536428,0.0008297087,0.0006080075,0.0003401298,0.0003641995,0.00003307014,2.401826e-7,1.109733e-7,0.000009053981,0.007481177,0.9902965],"study_design_scores_gemma":[0.0003139855,0.0000462414,0.004218997,0.006420222,0.0009925303,0.0003304736,0.00001355946,0.00006420264,1.179815e-7,0.00001637412,0.9874393,0.0001439349],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000458568,0.9961655,0.0001501445,0.00106194,0.0009058323,0.0004416233,0.0003307206,0.00002112747,0.0004645456],"genre_scores_gemma":[0.003029684,0.9922843,0.00002870402,0.001637942,0.002419024,0.000007644302,0.0001075319,0.00004518505,0.0004399653],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9901527,"threshold_uncertainty_score":0.997875,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147627663","doi":"10.3201/eid1505.081114","title":"Use of Unstructured Event-Based Reports for Global Infectious Disease Surveillance","year":2009,"lang":"en","type":"review","venue":"Emerging infectious diseases","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":203,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Public Health Agency of Canada; University Health Network","funders":"U.S. National Library of Medicine","keywords":"Public health; Public health surveillance; Disease surveillance; Infectious disease (medical specialty); Context (archaeology); Outbreak; The Internet; Event monitoring; Computer science; Information Dissemination; International Health Regulations; Event (particle physics); Psychological intervention; Unstructured data; Data science; Medicine; Process (computing); Disease; Data mining; World Wide Web; Big data; Geography; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.02745826120509893,"gpt":0.3412254162712001,"spread":0.3137671550661011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002863313,0.001251469,0.00394382,0.0004849305,0.0002310538,0.0001147369,0.0002584198,0.0003477691,0.0001139887],"category_scores_gemma":[0.003928171,0.001149714,0.00290099,0.001324402,0.000258933,0.0002463016,0.0001124842,0.0003384097,0.00001347207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007706915,"about_ca_system_score_gemma":0.002929436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008945701,"about_ca_topic_score_gemma":0.00007723389,"domain_scores_codex":[0.9942719,0.0004311849,0.00205046,0.00152003,0.0008424221,0.0008840498],"domain_scores_gemma":[0.9933749,0.0005632142,0.002041534,0.002179753,0.0006851093,0.001155457],"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":[0.0004268879,0.001677847,0.1721892,0.05487236,0.001579772,0.0009850392,0.000005282983,0.001300025,5.927314e-7,0.0001556615,0.01283381,0.7539735],"study_design_scores_gemma":[0.001560576,0.0003856749,0.0342127,0.0113004,0.005678212,0.0002564747,0.000001333497,0.0002041778,6.205855e-7,0.0004202827,0.9447522,0.001227305],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000819481,0.9806846,0.001435358,0.0000420335,0.001576263,0.004597593,0.009498576,0.001205223,0.0001408187],"genre_scores_gemma":[0.03705126,0.9461076,0.0002087819,0.0003898226,0.0008781781,0.0008666125,0.01404841,0.000288297,0.0001609804],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9319184,"threshold_uncertainty_score":0.9990953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104931818","doi":"10.1177/1524839909334624","title":"Geographic Information Systems (GIS) for Health Promotion and Public Health: A Review","year":2009,"lang":"en","type":"review","venue":"Health Promotion Practice","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Health promotion; Public health; GIS and public health; Geographic information system; Profiling (computer programming); Health policy; Public participation GIS; Environmental health; Medicine; Public relations; Political science; Geography; Computer science; Nursing; Remote sensing","retraction":null,"screen_n_in":null,"score":{"opus":0.1523135964450655,"gpt":0.4622337925787041,"spread":0.3099201961336386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01483831,0.0007754659,0.004319801,0.0008697159,0.0006571901,0.0002447198,0.0002449222,0.0003666476,0.00002442334],"category_scores_gemma":[0.005669109,0.0006864893,0.0004404711,0.001448344,0.0000775817,0.002735289,0.00008089525,0.001115403,0.0001405932],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001561597,"about_ca_system_score_gemma":0.009518566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002907896,"about_ca_topic_score_gemma":0.00002664031,"domain_scores_codex":[0.9878329,0.004575122,0.004150308,0.0009691382,0.001123245,0.001349299],"domain_scores_gemma":[0.9870697,0.0005535742,0.008329778,0.001219102,0.001147012,0.001680821],"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":[0.00001603477,0.0006036566,0.000003552598,0.3857925,0.00009278989,0.000002173472,0.00005319726,5.124858e-8,1.379834e-9,0.0004294939,0.02208963,0.5909169],"study_design_scores_gemma":[0.0008192805,0.003570535,0.00005542874,0.1441113,0.0003545079,0.001322354,0.00004191968,0.00003850191,1.32465e-9,0.000009317253,0.8493393,0.0003375538],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.859984e-7,0.852016,0.002884934,0.1175049,0.0005604469,0.02548203,0.0009456821,0.0004128692,0.0001929894],"genre_scores_gemma":[0.000004403932,0.9615237,0.002242822,0.01762243,0.0003768341,0.002610909,0.01544233,0.00009021109,0.00008634153],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8272496,"threshold_uncertainty_score":0.9995586,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094152559","doi":"10.2196/23173","title":"A Data Visualization and Dissemination Resource to Support HIV Prevention and Care at the Local Level: Analysis and Uses of the AIDSVu Public Data Resource","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; Center for AIDS Research, University of Washington; Petroleum Technology Alliance Canada; Emory University; Gilead Sciences","keywords":"Infographic; Population; Data visualization; Census; Public health; Data science; Computer science; Resource (disambiguation); American Community Survey; Social media; Geocoding; Geography; Medicine; Visualization; World Wide Web; Environmental health; Data mining; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.18371200007225,"gpt":0.4728071293570879,"spread":0.2890951292848379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005357036,0.0000955872,0.0003319657,0.0002364379,0.00007842835,0.00009615609,0.001168824,0.00008669584,0.0002517766],"category_scores_gemma":[0.01274427,0.00005348345,0.00004468096,0.000876988,0.0005647438,0.0002355534,0.003910716,0.0004491057,0.000001690826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006248194,"about_ca_system_score_gemma":0.000249387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005080317,"about_ca_topic_score_gemma":0.0007004429,"domain_scores_codex":[0.9956028,0.0008690397,0.0005340455,0.0003651391,0.002435057,0.0001939478],"domain_scores_gemma":[0.9972141,0.0007788228,0.0002190118,0.0008126495,0.0004119806,0.0005633805],"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":[0.001164907,0.0001965701,0.2376791,0.0006457187,0.001024078,0.0001173784,0.004809942,0.000003489536,0.0003369645,0.0001302826,0.5601872,0.1937045],"study_design_scores_gemma":[0.00225918,0.001933822,0.3257355,0.001707971,0.001212079,0.0004010988,0.01517806,0.06250828,0.0007437688,0.00001919169,0.588092,0.0002091104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9192041,0.002304785,0.01126935,0.06545924,0.00002828216,0.0005068251,0.001043834,0.00001051207,0.0001730617],"genre_scores_gemma":[0.9978964,0.0002450823,0.0000697408,0.0003467521,0.0001400472,0.000001997227,0.0008197926,0.00001282294,0.0004673837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1934953,"threshold_uncertainty_score":0.9955718,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1988370432","doi":"10.1016/j.jbi.2006.09.003","title":"Outbreak detection through automated surveillance: A review of the determinants of detection","year":2006,"lang":"en","type":"review","venue":"Journal of Biomedical Informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":191,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Canada Research Chairs","keywords":"Outbreak; Disease surveillance; Public health surveillance; Medicine; Representativeness heuristic; Warning system; Epidemiologic Surveillance; Public health; Medical emergency; Environmental health; Computer science; Data mining; Virology; Pathology; Statistics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02795356172380398,"gpt":0.3590521525335417,"spread":0.3310985908097377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001854981,0.0003914809,0.003617553,0.0003335223,0.00004934562,0.00001212671,0.0005311015,0.0004339848,0.00003507704],"category_scores_gemma":[0.001898244,0.0002166304,0.001393208,0.00137605,0.0004016479,0.0002329808,0.0001564323,0.0007540025,0.00001162056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002562886,"about_ca_system_score_gemma":0.001025407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001754932,"about_ca_topic_score_gemma":0.00001164881,"domain_scores_codex":[0.9923524,0.0003182751,0.00539229,0.0001076342,0.001546927,0.00028249],"domain_scores_gemma":[0.9895996,0.0002936203,0.008410663,0.0006818447,0.000827076,0.0001871452],"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":[0.0000302026,0.000159636,0.00006149674,0.2686382,0.0002599314,0.00001483462,0.0000353807,2.567704e-7,0.000005283654,3.566835e-7,0.003670367,0.7271241],"study_design_scores_gemma":[0.0007069068,0.0004200917,0.0005159038,0.1975928,0.00147828,0.001894299,0.0000211192,0.0003495475,0.00005683522,0.000005925899,0.7967714,0.0001869044],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002991319,0.9965063,0.0005384356,0.00002908692,0.001036616,0.0009056843,0.0004117906,0.00005058427,0.0002223146],"genre_scores_gemma":[0.0006626802,0.9982102,0.0006183946,0.0001368822,0.0002277707,0.000008590906,0.00008042291,0.00003385383,0.00002120471],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.793101,"threshold_uncertainty_score":0.8833931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951946244","doi":"10.1371/journal.pone.0165085","title":"Dynamic Forecasting of Zika Epidemics Using Google Trends","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":187,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"State Key Laboratory of Pathogen and Biosecurity","keywords":"Zika virus; Autoregressive integrated moving average; Autoregressive model; Computer science; Outbreak; Warning system; Time series; Data mining; Statistics; Machine learning; Medicine; Virology; Mathematics; Virus","retraction":null,"screen_n_in":null,"score":{"opus":0.1844407715912718,"gpt":0.3325520008115284,"spread":0.1481112292202567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002342929,0.0001125426,0.0004632946,0.0000891645,0.0001205221,0.00001576199,0.0002007758,0.00005515014,0.0001167444],"category_scores_gemma":[0.001202418,0.0001105517,0.00007939035,0.00007299501,0.0001166575,0.0001339873,0.0001297234,0.0001237778,0.00001724825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006955559,"about_ca_system_score_gemma":0.00005681453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008296019,"about_ca_topic_score_gemma":0.00004813089,"domain_scores_codex":[0.9989643,0.0000251025,0.0002831556,0.0002140629,0.0002828539,0.0002305216],"domain_scores_gemma":[0.9984757,0.00006429592,0.0003358046,0.0008823982,0.0001162674,0.0001255441],"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":[0.0003874821,0.002491202,0.787842,0.001444439,0.001079277,0.0001552194,0.0001980284,0.00006413169,0.1578388,0.0001034143,0.0005304766,0.04786556],"study_design_scores_gemma":[0.003050406,0.0002798991,0.4129165,0.002931843,0.00114258,0.00003290574,0.0000516899,0.5656754,0.01288105,0.0002879518,0.0003169942,0.0004326944],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920582,0.0002118664,0.0001148342,0.0002541461,0.0000447846,0.0001139918,0.0002038465,0.00005117444,0.00694712],"genre_scores_gemma":[0.9788052,0.00002678303,0.01994057,0.00006152494,0.00007945271,0.000003930195,0.00009418952,0.00002931002,0.0009590004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5656113,"threshold_uncertainty_score":0.4508169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974165922","doi":"10.6064/2012/875253","title":"The Past, Present, and Future of Public Health Surveillance","year":2012,"lang":"en","type":"review","venue":"Scientifica","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Public health; Public health surveillance; Dichotomy; Public relations; Political science; Environmental health; Medicine; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.102693151396566,"gpt":0.3664852955211397,"spread":0.2637921441245737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003821922,0.00030307,0.001394695,0.0001667515,0.0002862806,0.0001197684,0.000478606,0.0001265708,0.00008026634],"category_scores_gemma":[0.00008334725,0.0001739674,0.0002974864,0.0008629317,0.0006232034,0.00008901386,0.0002521485,0.0003153812,0.00008356717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007897543,"about_ca_system_score_gemma":0.0008313215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008790046,"about_ca_topic_score_gemma":0.00001567282,"domain_scores_codex":[0.9966885,0.0006500272,0.0007273597,0.0005853333,0.0006551595,0.000693664],"domain_scores_gemma":[0.9966989,0.0002666265,0.0006958427,0.001539723,0.0002060907,0.000592819],"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":[0.000003143062,0.00006497934,0.0003011535,0.009710065,0.00008602253,0.000001751199,0.00002618529,2.210317e-9,1.332564e-7,0.0001701285,0.06777762,0.9218588],"study_design_scores_gemma":[0.0001355051,0.00002534743,0.002482078,0.0007657393,0.00008026979,0.00003373861,0.00002237761,0.000001209552,5.262463e-8,0.000005210351,0.9963104,0.0001381404],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004702084,0.9912775,0.000006930416,0.003450084,0.001688463,0.001073956,0.001172978,0.00006130821,0.001264153],"genre_scores_gemma":[0.00002689191,0.9944434,0.00007464228,0.00003873431,0.00203227,0.0000476208,0.0007742845,0.00003928431,0.002522897],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9285327,"threshold_uncertainty_score":0.7094184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116148325","doi":"10.2196/jmir.2740","title":"Scoping Review on Search Queries and Social Media for Disease Surveillance: A Chronology of Innovation","year":2013,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Agency of Canada; University of Guelph","funders":"College of Engineering, Michigan State University; Centers for Disease Control and Prevention; Public Health Agency; Public Health Agency of Canada; University of Guelph; Michigan State University","keywords":"Social media; Disease surveillance; Pandemic; Outbreak; Internet privacy; Disease; Influenza A virus subtype H5N1; Warning system; Coronavirus disease 2019 (COVID-19); Computer science; Medicine; Medical emergency; Data science; World Wide Web; Infectious disease (medical specialty); Virology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1141964403520584,"gpt":0.466556180000762,"spread":0.3523597396487037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007249435,0.0001118147,0.0006706412,0.000449111,0.00004086566,0.00002707293,0.0003339452,0.0001244187,0.001448927],"category_scores_gemma":[0.01773834,0.00008026481,0.00009221834,0.0004580266,0.0007212911,0.0001187387,0.0001898195,0.000780776,0.000019124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025034,"about_ca_system_score_gemma":0.001454932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003769956,"about_ca_topic_score_gemma":0.00003021911,"domain_scores_codex":[0.9957091,0.0005081192,0.0009864522,0.0002049504,0.002235444,0.0003559836],"domain_scores_gemma":[0.9944637,0.001827004,0.000283847,0.0002019692,0.0028271,0.0003963598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.006688116,0.001480581,0.05385024,0.0889836,0.0007062606,0.000505651,0.001424276,6.077495e-7,0.001462689,0.008601675,0.4618101,0.3744862],"study_design_scores_gemma":[0.02157891,0.008861309,0.5776148,0.3519002,0.0002216032,0.0005770021,0.001641964,0.002984624,0.002270552,0.003733142,0.02773747,0.0008784063],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9217743,0.01980173,0.0005667835,0.05559768,0.0002801159,0.001699013,0.00006293924,0.00001622699,0.0002012577],"genre_scores_gemma":[0.9878506,0.01008352,0.000194776,0.0009155432,0.0006922399,0.00006473369,0.00007259112,0.00002217246,0.0001038155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5237646,"threshold_uncertainty_score":0.9994639,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014820621","doi":"10.2196/18941","title":"Tracking COVID-19 in Europe: Infodemiology Approach","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Preparedness; Pandemic; Outbreak; Public health; Epidemiology; Middle East respiratory syndrome; Coronavirus disease 2019 (COVID-19); Disease surveillance; Geography; Measles; Environmental health; Medicine; Demography; Disease; Vaccination; Virology; Political science; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.1076621781573023,"gpt":0.3650213314746952,"spread":0.2573591533173929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001717597,0.0002335949,0.000807557,0.0001505448,0.0001095386,0.00004481311,0.0001948558,0.0001179524,0.00005915023],"category_scores_gemma":[0.006570236,0.0002145049,0.00004863544,0.001170839,0.0001586373,0.0001662703,0.0001171073,0.0004626465,0.00003483751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001609392,"about_ca_system_score_gemma":0.00269737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009958737,"about_ca_topic_score_gemma":0.00007395208,"domain_scores_codex":[0.9967968,0.0007318321,0.0006835515,0.0006959242,0.0002711326,0.0008207433],"domain_scores_gemma":[0.995998,0.0002786401,0.0001932258,0.00038592,0.0001373413,0.003006931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002120301,0.0001176505,0.9581037,0.001021278,0.0000136171,0.00005949688,0.001172549,0.0000106085,0.000006707896,0.000560661,0.02184145,0.01688024],"study_design_scores_gemma":[0.001698157,0.0001954731,0.452168,0.00000724193,3.228117e-7,0.00005754299,0.0001893396,0.002006091,5.903815e-8,0.000009262671,0.5435094,0.0001591451],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5795898,0.01003933,0.007007707,0.3801382,0.0002763689,0.003755062,0.0005036898,0.001260226,0.01742958],"genre_scores_gemma":[0.8899831,0.0008472366,0.0006531682,0.1075738,0.0001977885,0.00009234966,0.0005470637,0.00003298916,0.00007248524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.521668,"threshold_uncertainty_score":0.8747256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2777924017","doi":"10.2196/publichealth.7373","title":"A Smartphone App (AfyaData) for Innovative One Health Disease Surveillance from Community to National Levels in Africa: Intervention in Disease Surveillance","year":2017,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":163,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Disease surveillance; Smartphone app; Public health surveillance; Environmental health; Disease; Intervention (counseling); Smartphone application; Medicine; Public health; Internet privacy; mHealth; Psychological intervention; Computer science; Nursing; Multimedia; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1243439950746771,"gpt":0.3859843105109424,"spread":0.2616403154362653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009067073,0.000615647,0.001722353,0.0006815174,0.0009031545,0.0003368257,0.0008905045,0.0001450456,0.00005029613],"category_scores_gemma":[0.01109984,0.0006639695,0.0001711913,0.001211785,0.0003598957,0.0007416749,0.0005886689,0.0008704129,0.00002635014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001192822,"about_ca_system_score_gemma":0.00399884,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004039437,"about_ca_topic_score_gemma":0.02559234,"domain_scores_codex":[0.9920877,0.002055563,0.001784081,0.001321193,0.001056495,0.001694934],"domain_scores_gemma":[0.9917722,0.001112579,0.001082091,0.002038894,0.001021617,0.002972614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002501877,0.001789704,0.9542403,0.001397297,0.00006625623,0.0000252953,0.001033012,0.000008751729,0.00001176307,0.0004878463,0.008221997,0.03021595],"study_design_scores_gemma":[0.006789887,0.0003713737,0.9566563,0.0004256082,8.641379e-7,0.000002109721,0.0002338222,0.0007884832,3.960644e-7,0.000678358,0.03351061,0.0005422213],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8846762,0.003654711,0.002250066,0.07748225,0.0005378118,0.006057811,0.02473691,0.0002776061,0.0003266697],"genre_scores_gemma":[0.9851804,0.0003472753,0.0008543839,0.004946407,0.0002793798,0.001314483,0.006811954,0.00008480337,0.0001809503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1005042,"threshold_uncertainty_score":0.9995812,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2761296717","doi":"10.2196/publichealth.7540","title":"Participatory Disease Surveillance: Engaging Communities Directly in Reporting, Monitoring, and Responding to Health Threats","year":2017,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Disease surveillance; Citizen journalism; Citizen science; Participatory sensing; Participatory GIS; Disease; Best practice; Public health surveillance; Business; Public health; Public relations; Medicine; Knowledge management; Data science; Computer science; Political science; World Wide Web; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1396849339788591,"gpt":0.4251206091289365,"spread":0.2854356751500773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.008972986,0.0004041261,0.00128231,0.0006260966,0.001426768,0.0004130081,0.0003411218,0.00008789444,0.00001567467],"category_scores_gemma":[0.005149818,0.0003983436,0.00007909363,0.0004332852,0.0003172038,0.0004195812,0.0004304283,0.00058233,0.000007325164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003516895,"about_ca_system_score_gemma":0.001775878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001235407,"about_ca_topic_score_gemma":0.001763915,"domain_scores_codex":[0.9944707,0.001152777,0.001566519,0.0007744593,0.0005630017,0.00147256],"domain_scores_gemma":[0.9927623,0.0004355465,0.001441662,0.001805208,0.0001964703,0.00335881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003103371,0.0001214235,0.9447587,0.0008037693,0.00002264075,0.00009753296,0.0027663,0.000001250667,0.000008154216,0.0001438357,0.001019542,0.0499465],"study_design_scores_gemma":[0.001292723,0.0002118361,0.9611835,0.0003969088,8.232844e-7,0.00002754034,0.001286283,0.000169773,0.00000119667,0.00004075981,0.03506078,0.0003278251],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9626829,0.009490767,0.00002278032,0.02485264,0.000363632,0.001303353,0.0001718626,0.0002521561,0.0008599269],"genre_scores_gemma":[0.9934529,0.002927658,0.0002601763,0.002181245,0.0002532235,0.0002940565,0.0001299404,0.0000622356,0.0004385613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04961868,"threshold_uncertainty_score":0.9998732,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080381308","doi":"10.1016/j.prevetmed.2011.05.004","title":"Veterinary syndromic surveillance: Current initiatives and potential for development","year":2011,"lang":"en","type":"review","venue":"Preventive Veterinary Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":153,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Prince Edward Island","funders":"Ministry of Agriculture, Food and Rural Affairs; Ontario Ministry of Agriculture, Food and Rural Affairs","keywords":"Veterinary public health; Disease surveillance; Public health surveillance; Animal health; Public health; Population; One Health; Data science; Grey literature; Medicine; Risk analysis (engineering); Computer science; Environmental health; Veterinary medicine; MEDLINE; Pathology; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1437555848130295,"gpt":0.4120846947216823,"spread":0.2683291099086528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001136923,0.00113303,0.003964308,0.0005871351,0.0001953815,0.00002023469,0.0004104889,0.0002947245,0.000372602],"category_scores_gemma":[0.0004200317,0.0008907401,0.0005326531,0.0003305689,0.0005715162,0.0002084053,0.0006200635,0.0005894115,0.00007701704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003600994,"about_ca_system_score_gemma":0.0006605383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005890761,"about_ca_topic_score_gemma":6.971239e-7,"domain_scores_codex":[0.995162,0.0007024566,0.001552085,0.001394174,0.0004355405,0.0007538136],"domain_scores_gemma":[0.9970439,0.0004498175,0.0008744187,0.0008278399,0.0002559919,0.0005480503],"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":[0.0006522466,0.0003601872,0.00005143867,0.06851049,0.001101153,0.0005450308,0.0002858075,1.957777e-8,0.00001539664,0.00006196686,0.001063774,0.9273525],"study_design_scores_gemma":[0.002346266,0.003672072,0.003647696,0.04081582,0.001317024,0.002528279,0.00003358047,0.000005050772,8.145426e-7,0.00004565364,0.9448096,0.0007781946],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00232596,0.989735,0.0007275658,0.00002792013,0.001514535,0.004294735,0.0007896908,0.0001982719,0.0003862871],"genre_scores_gemma":[0.003048726,0.9887864,0.001515051,0.00004007322,0.0007307709,0.001350694,0.00405817,0.0001932681,0.0002768683],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9437458,"threshold_uncertainty_score":0.9993543,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297774607","doi":"10.1007/bf03405213","title":"The Global Public Health Intelligence Network and Early Warning Outbreak Detection","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":153,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"York University","funders":"University of Toronto","keywords":"Public health; Outbreak; Global health; Warning system; Credibility; Infectious disease (medical specialty); International Health Regulations; Global network; The Internet; Public health surveillance; Political science; Public relations; Environmental health; Medicine; Disease; Coronavirus disease 2019 (COVID-19); Computer science; Telecommunications; Virology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.03860613809635945,"gpt":0.2939615298437185,"spread":0.2553553917473591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005237389,0.0001577677,0.0004126314,0.0001933851,0.0007794003,0.0003194485,0.0002414738,0.00006490531,0.00002338518],"category_scores_gemma":[0.001003767,0.0001227805,0.00008935468,0.0007452382,0.000212148,0.0003201572,0.00002242859,0.0004576238,0.000008788152],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001978821,"about_ca_system_score_gemma":0.01534012,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0543161,"about_ca_topic_score_gemma":0.326589,"domain_scores_codex":[0.9967905,0.0005089363,0.0008613886,0.0002042846,0.0003575155,0.001277403],"domain_scores_gemma":[0.9943701,0.0001216592,0.0006746172,0.0002913275,0.0004217403,0.004120551],"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":[0.00001153824,0.00001809894,0.4664193,0.00004586271,0.00004384232,0.00005165764,0.0002232662,0.00002349868,2.867363e-7,0.002549246,0.01009553,0.5205178],"study_design_scores_gemma":[0.0002443902,0.0003430893,0.6122575,0.00007177088,0.000004400282,0.0005210808,0.0002934974,0.0001156004,2.163008e-7,0.0005060519,0.3855658,0.00007663365],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6185648,0.04834878,0.04506654,0.2820335,0.002581869,0.0009476559,0.0001910683,0.00009919011,0.002166563],"genre_scores_gemma":[0.9950488,0.0003930995,0.0004343807,0.003095198,0.0009101149,0.000002933059,0.0000153455,0.00001875914,0.00008139561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5204412,"threshold_uncertainty_score":0.990242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1975706048","doi":"10.1016/j.sste.2009.12.001","title":"Review of methods for space–time disease surveillance","year":2010,"lang":"en","type":"review","venue":"Spatial and Spatio-temporal Epidemiology","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":152,"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; Child and Family Research Institute; University of Victoria","funders":"","keywords":"Variety (cybernetics); Disease surveillance; Scope (computer science); Context (archaeology); Computer science; Data science; Suite; Focus (optics); Risk analysis (engineering); Disease; Medicine; Artificial intelligence; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.09295426642670605,"gpt":0.4570538062112592,"spread":0.3640995397845531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00653521,0.0008070213,0.008566046,0.0002237958,0.00008571691,0.000006174784,0.0003483257,0.0006398094,0.0004151038],"category_scores_gemma":[0.02281224,0.0005976479,0.001413551,0.0002991292,0.0005329979,0.00006385078,0.000221253,0.0006841134,0.00005173175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006181595,"about_ca_system_score_gemma":0.001006201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003844019,"about_ca_topic_score_gemma":0.0001025904,"domain_scores_codex":[0.9924787,0.002940279,0.002625654,0.001168936,0.0001411666,0.000645268],"domain_scores_gemma":[0.9898863,0.005273762,0.002303838,0.001330205,0.0004145032,0.0007914159],"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":[0.0001655383,0.00007601488,0.003178094,0.1897486,0.0001982836,0.000006619744,0.000001958081,8.830954e-8,5.035876e-7,0.0002458999,0.01254254,0.7938359],"study_design_scores_gemma":[0.0005004911,0.0002548917,0.0008286678,0.04336334,0.001219666,0.0000316677,3.077505e-7,0.0003163842,2.252651e-7,0.0005134668,0.9524836,0.000487291],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003163914,0.9818417,0.009043933,0.001325009,0.0005461875,0.003867307,0.003114736,0.0001010651,0.000156831],"genre_scores_gemma":[0.000003851276,0.9474015,0.03467741,0.001311543,0.0006105033,0.0005418678,0.01501086,0.0001041407,0.0003383155],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.939941,"threshold_uncertainty_score":0.9996475,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014936749","doi":"10.1503/cmaj.75262","title":"Open access epidemiologic data and an interactive dashboard to monitor the COVID-19 outbreak in Canada","year":2020,"lang":"en","type":"letter","venue":"Canadian Medical Association Journal","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Outbreak; Coronavirus disease 2019 (COVID-19); Dashboard; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Public health; Coronavirus; Public health surveillance; Pandemic; Medicine; Environmental health; Virology; Disease; Data science; Infectious disease (medical specialty); Computer science; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.08771267780075678,"gpt":0.402889161340072,"spread":0.3151764835393153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003157187,0.0003042643,0.000922101,0.0002133271,0.0002559343,0.000567791,0.004464301,0.0004965779,0.001876593],"category_scores_gemma":[0.04342071,0.0002249356,0.00005084965,0.0003975927,0.00006526739,0.0005894074,0.001276972,0.00511902,0.00003954067],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.009766106,"about_ca_system_score_gemma":0.05086593,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9656789,"about_ca_topic_score_gemma":0.9965314,"domain_scores_codex":[0.994461,0.001687208,0.0008392612,0.0007077611,0.001547754,0.0007569926],"domain_scores_gemma":[0.9910924,0.001907203,0.0006008976,0.0007561248,0.0002615303,0.005381785],"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":[0.00003716725,0.000006379277,0.1383693,0.00002799438,0.000150038,0.009027964,0.0001002374,0.00000310411,8.447758e-8,0.000001117711,0.8465766,0.005700045],"study_design_scores_gemma":[0.0007698603,0.00004174621,0.06796597,0.000131239,0.00006501842,0.000325193,0.0003318867,0.0004394417,7.002345e-8,0.00007479568,0.9296297,0.0002250725],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.002224933,0.0001435249,0.00002838768,0.9890518,0.00110395,0.0007488804,0.006089247,0.00001499248,0.0005942535],"genre_scores_gemma":[0.01460031,0.0001385972,0.00006970765,0.9748569,0.007272789,0.00003346404,0.002812569,0.00003768091,0.0001780369],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.08305316,"threshold_uncertainty_score":0.9990358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073382943","doi":"10.1016/s0277-9536(02)00380-5","title":"Geographic analysis of diabetes prevalence in an urban area","year":2003,"lang":"en","type":"article","venue":"Social Science & Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":144,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Manitoba Health","funders":"","keywords":"Socioeconomic status; Regression analysis; Population; Geography; Demography; Statistic; Ecological study; Scan statistic; Logistic regression; Medicine; Linear regression; Environmental health; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01801143006629395,"gpt":0.3103154386158636,"spread":0.2923040085495697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002027333,0.0001444848,0.0006314448,0.001007486,0.0001225662,0.000009145607,0.0003438311,0.00005503787,0.0004576295],"category_scores_gemma":[0.001368451,0.0001153981,0.0001078507,0.007500594,0.002376941,0.0002477609,0.00002812243,0.0001443375,0.00000216367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001169011,"about_ca_system_score_gemma":0.0002458053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008370707,"about_ca_topic_score_gemma":0.0001053522,"domain_scores_codex":[0.9974926,0.0001255809,0.000406836,0.0004853812,0.001018574,0.00047105],"domain_scores_gemma":[0.9987332,0.00008079946,0.0001677551,0.0004411203,0.0002784839,0.0002985954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001162252,0.0001386344,0.986937,0.00004901458,0.00005318414,0.000006324293,0.001699357,0.00000327952,0.009102805,0.000968088,0.00008693735,0.0009437454],"study_design_scores_gemma":[0.0006471932,0.0001851165,0.9969931,0.00009611857,0.0004951163,3.47561e-7,0.0004364199,0.0003232074,0.0002422925,0.0001577104,0.0003142054,0.0001092024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942596,0.0005673956,0.00001680585,0.0002572058,0.0001064383,0.0002288314,0.00003543017,0.0000404697,0.004487805],"genre_scores_gemma":[0.999414,0.00003699604,0.00003345945,0.0003470909,0.00007107533,0.00001311831,0.0000366073,0.000007419314,0.00004026833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01005606,"threshold_uncertainty_score":0.8757938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3024129393","doi":"10.2196/19702","title":"Correlations of Online Search Engine Trends With Coronavirus Disease (COVID-19) Incidence: Infodemiology Study","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Dysgeusia; Pandemic; Medicine; Public health; Epidemiology; Population; Outbreak; Anosmia; Public health surveillance; Disease surveillance; Disease; Incidence (geometry); Demography; Environmental health; Coronavirus disease 2019 (COVID-19); Virology; Infectious disease (medical specialty); Internal medicine; Pathology; Adverse effect","retraction":null,"screen_n_in":null,"score":{"opus":0.1415129679389227,"gpt":0.4234611878803751,"spread":0.2819482199414525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001070177,0.0002677919,0.0008735271,0.0002359791,0.0001628502,0.00002141841,0.0002113967,0.00007432368,0.0002066499],"category_scores_gemma":[0.002299887,0.0002176007,0.00006560772,0.001163788,0.0002858647,0.0001661759,0.0001421296,0.0004149118,0.00001364272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001488972,"about_ca_system_score_gemma":0.004225548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003199136,"about_ca_topic_score_gemma":0.0007472531,"domain_scores_codex":[0.9967909,0.0006369842,0.0007345371,0.0006371954,0.0005688654,0.0006314822],"domain_scores_gemma":[0.9941949,0.0004469318,0.0002247808,0.0005793786,0.0002819604,0.004272029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00117402,0.0006913882,0.9761958,0.0005083392,0.00006177439,0.00007886083,0.001309096,0.0001156037,0.000002021659,0.00009580439,0.002372239,0.01739511],"study_design_scores_gemma":[0.003275167,0.001826333,0.9455038,0.00001611265,0.000004570273,0.00002120913,0.0006379951,0.004387842,4.056271e-8,0.000004291648,0.04413883,0.0001838438],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9304352,0.001679431,0.001062567,0.06366504,0.00005644892,0.001221709,0.001486249,0.0002374886,0.0001558115],"genre_scores_gemma":[0.9841586,0.000283404,0.0003764434,0.01323779,0.0001385599,0.00009830901,0.001517489,0.00003111918,0.000158306],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05372332,"threshold_uncertainty_score":0.8873499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2414792569","doi":"10.2196/publichealth.5814","title":"Utilizing Nontraditional Data Sources for Near Real-Time Estimation of Transmission Dynamics During the 2015-2016 Colombian Zika Virus Disease Outbreak","year":2016,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"U.S. National Library of Medicine; University of California, San Diego; National Institutes of Health; United States Agency for International Development","keywords":"Zika virus; Outbreak; Transmission (telecommunications); Disease surveillance; Disease; Exponential smoothing; Incidence (geometry); Estimation; Basic reproduction number; Medicine; Demography; Statistics; Virology; Population; Environmental health; Computer science; Virus; Mathematics; Telecommunications; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02861590574009464,"gpt":0.3141996389414115,"spread":0.2855837332013169,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001405155,0.0002179955,0.0005046948,0.00008606513,0.0003938017,0.00006322472,0.0003274277,0.00007373232,0.00007205249],"category_scores_gemma":[0.0006539067,0.0001367259,0.00008074111,0.0001949702,0.0002943634,0.0003840909,0.00009536935,0.00009852144,0.00001069258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001558652,"about_ca_system_score_gemma":0.001494049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001047905,"about_ca_topic_score_gemma":0.0001072962,"domain_scores_codex":[0.9975864,0.0002478736,0.0006103436,0.000558038,0.0004262729,0.0005710889],"domain_scores_gemma":[0.9969754,0.0005912221,0.0003275351,0.0009251697,0.0001783164,0.00100231],"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":[0.006295056,0.001293606,0.4016661,0.006220357,0.0003071495,0.00002906747,0.0008259895,0.00004312077,0.001830806,0.001603866,0.04437647,0.5355084],"study_design_scores_gemma":[0.003505739,0.0002252155,0.8659377,0.0002999968,0.000007766061,0.00002091952,0.0000665145,0.07248615,0.000006215516,0.0001326595,0.05704371,0.0002674501],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9125316,0.001777829,0.009324217,0.05261841,0.0001641142,0.002940878,0.0200839,0.0002736627,0.0002854084],"genre_scores_gemma":[0.9923338,0.001121367,0.00120016,0.0005338271,0.000148665,0.0001379198,0.00407943,0.00004392925,0.0004009122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5352409,"threshold_uncertainty_score":0.5575522,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127523571","doi":"10.1093/aje/kwq248","title":"Mapping Health Data: Improved Privacy Protection With Donut Method Geomasking","year":2010,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; School of Medicine, University of North Carolina at Chapel Hill; National Institutes of Health; University of Toronto","keywords":"Geocoding; Computer science; Cluster (spacecraft); Masking (illustration); Data mining; Privacy protection; Statistics; Mathematics; Computer security; Geography; Remote sensing; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.06779756625519004,"gpt":0.3958230970778868,"spread":0.3280255308226967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00856581,0.0001961551,0.001421335,0.000249169,0.00009111743,0.000007061521,0.000444613,0.00005857073,0.00004109129],"category_scores_gemma":[0.008072001,0.0001354564,0.0001111107,0.0003888577,0.0003964748,0.0002274737,0.0001500587,0.001134306,0.000005982643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009101089,"about_ca_system_score_gemma":0.0006746976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008076683,"about_ca_topic_score_gemma":0.00009906261,"domain_scores_codex":[0.9964752,0.00127996,0.001137919,0.0004210961,0.0001637429,0.0005221223],"domain_scores_gemma":[0.9944266,0.001137015,0.002655806,0.001036645,0.0002652943,0.0004786207],"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":[0.002152285,0.0002155743,0.1622755,0.0001502338,0.000641561,0.0001213872,0.0003754624,0.00005899567,0.01636453,0.0001517837,0.00311884,0.8143739],"study_design_scores_gemma":[0.004389716,0.008486978,0.6759955,0.0005747307,0.0001947256,0.01307947,0.001023312,0.01049128,0.0001615037,0.0007583429,0.284288,0.0005564291],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3171248,0.0004248296,0.658605,0.02250011,0.0005403305,0.0005707928,0.00005750929,0.00006774239,0.0001088792],"genre_scores_gemma":[0.4887899,0.0001209059,0.5056633,0.004510526,0.0007853234,0.000008766357,0.00006524254,0.0000342069,0.00002178297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8138174,"threshold_uncertainty_score":0.9663523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020766884","doi":"10.1186/1476-072x-12-14","title":"Detecting activity locations from raw GPS data: a novel kernel-based algorithm","year":2013,"lang":"en","type":"article","venue":"International Journal of Health Geographics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Global Positioning System; Computer science; Algorithm; Context (archaeology); Noise (video); Kernel (algebra); Data mining; Artificial intelligence; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04901334359892456,"gpt":0.3578677350127343,"spread":0.3088543914138098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009947979,0.0001682843,0.000408499,0.0004715628,0.0001168556,0.00009553821,0.0007437357,0.00007678344,0.0001736819],"category_scores_gemma":[0.0005929199,0.0001531565,0.0001667745,0.0002945634,0.0001105506,0.0005891222,0.0001494488,0.0005762111,0.00003421414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001734296,"about_ca_system_score_gemma":0.001120487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002421608,"about_ca_topic_score_gemma":0.0001630054,"domain_scores_codex":[0.9974769,0.000105581,0.0008193913,0.0002878296,0.001033959,0.0002763759],"domain_scores_gemma":[0.9961846,0.0004121898,0.001035151,0.0005719694,0.001437956,0.0003581411],"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":[0.0002968955,0.002012053,0.1320222,0.00008756428,0.001169784,0.0001023655,0.0001305678,0.0002839975,0.001296256,0.00007007181,0.006047058,0.8564812],"study_design_scores_gemma":[0.004980367,0.000363243,0.8772696,0.0007090282,0.0001075567,0.0002525705,0.0001583737,0.09602349,0.0002474872,0.0006113596,0.01900225,0.000274687],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2770417,0.002254572,0.6936013,0.02270128,0.002396111,0.0005541433,0.001275057,0.00008647037,0.00008935411],"genre_scores_gemma":[0.9520974,0.0003205531,0.04321665,0.003016277,0.0007687945,0.000009261484,0.000534687,0.00002752671,0.000008851225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8562065,"threshold_uncertainty_score":0.624554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3087523322","doi":"10.1016/j.vaccine.2020.09.017","title":"Improving the quality and use of immunization and surveillance data: Summary report of the Working Group of the Strategic Advisory Group of Experts on Immunization","year":2020,"lang":"en","type":"article","venue":"Vaccine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Izaak Walton Killam Health Centre; Dalhousie University","funders":"Pan American Health Organization; Centers for Disease Control and Prevention; GAVI Alliance; Universiteit Stellenbosch; UNICEF; World Health Organization; Bill and Melinda Gates Foundation","keywords":"Context (archaeology); Data quality; Immunization; Disease surveillance; Medicine; Psychological intervention; Quality management; Working group; Quality (philosophy); Data management; Public health; Business; Process management; Environmental health; Political science; Computer science; Geography; Nursing; Marketing; Data mining; Immunology","retraction":null,"screen_n_in":null,"score":{"opus":0.08034385236043289,"gpt":0.2978253452281929,"spread":0.21748149286776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009151243,0.0001354338,0.0004121269,0.00003314536,0.00006687655,0.00001048493,0.0003377439,0.00005262687,0.00000665183],"category_scores_gemma":[0.001095259,0.00007474214,0.00005270104,0.0004778257,0.00009123717,0.0001536986,0.0005344762,0.0001302958,4.736815e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001330885,"about_ca_system_score_gemma":0.00006244548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005092563,"about_ca_topic_score_gemma":0.0001432607,"domain_scores_codex":[0.998121,0.0004189254,0.0007562675,0.0002726228,0.0003248149,0.0001063188],"domain_scores_gemma":[0.9968721,0.0003792923,0.001022539,0.001517196,0.0001709509,0.00003786518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005828617,0.0001351191,0.8808637,0.0006111176,0.00009701498,0.000002858707,0.0004339711,0.00006276072,0.1139776,0.0004030854,0.0001704113,0.002659441],"study_design_scores_gemma":[0.0009870126,0.0001131583,0.9936517,0.0003237019,0.00005119155,0.00001008411,0.0006137065,0.001854865,0.002124261,0.00002578921,0.0001669664,0.00007748613],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967759,0.001566827,0.0001974532,0.0006194761,0.00008642648,0.0005052618,0.0001799831,0.00001521753,0.00005340354],"genre_scores_gemma":[0.998881,0.0004413111,0.0001325011,0.0001369843,0.00003961428,0.0000032675,0.0003346297,0.00001882337,0.00001187479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.112788,"threshold_uncertainty_score":0.3047896,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145244857","doi":"10.15265/iy-2014-0008","title":"A Review and Framework for Categorizing Current Research and Development in Health Related Geographical Information Systems (GIS) Studies","year":2014,"lang":"en","type":"review","venue":"Yearbook of Medical Informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Algoma University","funders":"","keywords":"Geographic information system; GIS and public health; Categorization; Data science; Conceptual framework; Information system; Geography; Spatial analysis; Knowledge management; Computer science; Cartography; Political science; Sociology; Social science; Remote sensing","retraction":null,"screen_n_in":null,"score":{"opus":0.1830686673938387,"gpt":0.4896014633139451,"spread":0.3065327959201064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009304757,0.0002942871,0.002953776,0.0005995372,0.00007813267,0.00003229971,0.00023208,0.0004013587,0.000006204702],"category_scores_gemma":[0.004851019,0.0002139112,0.00009471511,0.0004986528,0.0004026587,0.0001633547,0.0003367457,0.001326018,0.00001822686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001964809,"about_ca_system_score_gemma":0.001558227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002041581,"about_ca_topic_score_gemma":0.000004505201,"domain_scores_codex":[0.9944035,0.0002651819,0.003432618,0.0001654237,0.001292633,0.000440605],"domain_scores_gemma":[0.9964864,0.001261404,0.001019145,0.0003810058,0.0003759603,0.00047614],"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":[0.000005397372,0.0000272756,0.00001549293,0.4785981,0.000123101,6.948946e-7,0.000455035,5.147688e-8,1.64528e-10,0.002406093,0.002056825,0.516312],"study_design_scores_gemma":[0.0003839381,0.0001188719,0.000008263818,0.2812264,0.0001065235,0.00003513338,0.0001717787,0.0001350999,6.706879e-9,0.00009056331,0.7176009,0.0001224737],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006735171,0.995227,0.0008084376,0.0002579543,0.0001692963,0.003392601,0.00004957812,0.00003332246,0.00005504521],"genre_scores_gemma":[0.00000721607,0.9963971,0.002430959,0.0002255684,0.00005071359,0.000385117,0.0004788942,0.00001896932,0.000005501863],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7155441,"threshold_uncertainty_score":0.8723045,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3167386324","doi":"10.1038/s41746-021-00459-8","title":"Leveraging artificial intelligence for pandemic preparedness and response: a scoping review to identify key use cases","year":2021,"lang":"en","type":"review","venue":"npj Digital Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Grey literature; Preparedness; Operationalization; Triage; Pandemic; Public health; Psychological intervention; Preprint; Delphi method; Computer science; Medicine; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Data science; MEDLINE; Medical emergency; Infectious disease (medical specialty); Disease; Nursing; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.3057232721842525,"gpt":0.5010962774777272,"spread":0.1953730052934747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001344296,0.0007016451,0.004127028,0.0003655208,0.0001031364,0.0001903973,0.0003002977,0.000195296,0.0001103355],"category_scores_gemma":[0.04150988,0.0005539457,0.0004069979,0.0008650242,0.0002398483,0.0003726825,0.0003495096,0.0003602836,0.00004848584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003496424,"about_ca_system_score_gemma":0.001537135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001597258,"about_ca_topic_score_gemma":0.00001680748,"domain_scores_codex":[0.995432,0.0002589326,0.001812773,0.001272135,0.0006582374,0.0005659146],"domain_scores_gemma":[0.9924488,0.004821296,0.0004882732,0.001114282,0.0004442884,0.0006830547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0002479815,0.00005573273,0.00002732215,0.1521396,0.0001732454,0.0006452629,0.0002008927,1.113132e-7,0.000003183772,0.00001864537,0.003651171,0.8428369],"study_design_scores_gemma":[0.0001422147,0.0002548515,0.00001407925,0.5810097,0.001122532,0.001141882,0.0001093478,0.000001715312,7.764255e-7,0.00001309713,0.415849,0.0003408209],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004893329,0.9906271,0.001024895,0.0003491698,0.0005074621,0.005887534,0.0008660555,0.0001811845,0.00006731776],"genre_scores_gemma":[0.0003951346,0.99457,0.0002179352,0.0009962048,0.0005544228,0.0006726468,0.002124632,0.0001249405,0.0003441506],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.842496,"threshold_uncertainty_score":0.9996912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3033100354","doi":"10.2196/19457","title":"A New System for Surveillance and Digital Contact Tracing for COVID-19: Spatiotemporal Reporting Over Network and GPS","year":2020,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Central South University; U.S. Department of Transportation","keywords":"Contact tracing; Internet privacy; Global Positioning System; Pandemic; Computer science; Population; Coronavirus disease 2019 (COVID-19); Transmission (telecommunications); mHealth; Disease; Computer security; Medicine; Infectious disease (medical specialty); Medical emergency; Environmental health; Telecommunications; Psychological intervention","retraction":null,"screen_n_in":null,"score":{"opus":0.07767299889355897,"gpt":0.3888836172684709,"spread":0.3112106183749119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008145169,0.0002311556,0.0008075676,0.00004254649,0.0003093537,0.00009082221,0.00004578661,0.0001010162,0.000003793934],"category_scores_gemma":[0.00134264,0.0002118061,0.00006626957,0.000145201,0.00004183332,0.0001714452,0.00004244133,0.0001534724,5.711037e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001285028,"about_ca_system_score_gemma":0.00120365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002583792,"about_ca_topic_score_gemma":0.0001371678,"domain_scores_codex":[0.997497,0.00005533802,0.001032581,0.0006371529,0.0001858998,0.0005920128],"domain_scores_gemma":[0.9959173,0.0004556233,0.0009744189,0.0002078772,0.00007431189,0.002370479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00466724,0.00004146064,0.8889908,0.03663728,0.00006631616,0.00006362925,0.001163696,0.00001419536,0.00001430975,0.0008103501,0.03142392,0.03610681],"study_design_scores_gemma":[0.01330995,0.002453244,0.8999906,0.0007307818,0.0001290073,0.0003587659,0.0007722109,0.01465383,0.000003546233,0.000236885,0.06679963,0.0005616079],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9456412,0.006414689,0.0236331,0.01672057,0.0002738329,0.005305834,0.001463845,0.0003877512,0.0001592115],"genre_scores_gemma":[0.9919623,0.0001560859,0.001924152,0.004426675,0.0009368719,0.00009718897,0.0004159721,0.00004188108,0.00003888484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04632111,"threshold_uncertainty_score":0.8637203,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1984510198","doi":"10.1186/1476-072x-7-8","title":"Online GIS services for mapping and sharing disease information","year":2008,"lang":"en","type":"article","venue":"International Journal of Health Geographics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of New Brunswick","funders":"Natural Resources Canada; U.S. Geological Survey; University of Southern Maine","keywords":"Health geography; Health informatics; Geographic information system; Geospatial analysis; GIS and public health; Public health; Computer science; World Wide Web; Geography; Data science; Cartography; Medicine; Health policy; International health; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.03317065035558611,"gpt":0.3308298480443543,"spread":0.2976591976887682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004389954,0.00008567634,0.0002163206,0.0004593609,0.00009437121,0.00002926445,0.0001759964,0.00002666504,0.000009734205],"category_scores_gemma":[0.0001456022,0.00007674247,0.000110456,0.0001186851,0.00004866915,0.0005335686,0.00005340777,0.0001424097,0.000001378306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005182509,"about_ca_system_score_gemma":0.0002501195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004641086,"about_ca_topic_score_gemma":0.00001243481,"domain_scores_codex":[0.9986122,0.00001858049,0.0006680341,0.00008511598,0.0004735431,0.0001425735],"domain_scores_gemma":[0.9981266,0.0000589529,0.0005854236,0.0001023182,0.0008549666,0.0002717301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007160036,0.0002401489,0.9688497,0.0006497744,0.0002507009,0.00006877791,0.0006062962,0.00005754489,0.000007721734,0.0003514538,0.0008443387,0.02735751],"study_design_scores_gemma":[0.001687975,0.0001196165,0.9392545,0.0004847038,0.00001915236,0.0003049926,0.0001709019,0.002340879,0.000001273361,0.0004367497,0.05511237,0.000066838],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807464,0.002407285,0.003521366,0.01197827,0.0005308713,0.0002522065,0.0005073634,0.00002589631,0.00003026994],"genre_scores_gemma":[0.9856864,0.003741281,0.004518406,0.005202719,0.0003244166,0.00000407606,0.0005025701,0.000009121512,0.00001100919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05426803,"threshold_uncertainty_score":0.3129467,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141021700","doi":"10.3201/eid1610.100249","title":"Mobile Phone–based Infectious Disease Surveillance System, Sri Lanka","year":2010,"lang":"en","type":"article","venue":"Emerging infectious diseases","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Victoria","funders":"University of Peradeniya; University of Victoria; Infectious Diseases Society of America","keywords":"Sri lanka; Disease surveillance; Infectious disease (medical specialty); Mobile phone; Medicine; Internet privacy; Virology; Medical emergency; Computer security; Environmental health; Disease; World Wide Web; Geography; Computer science; Telecommunications; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.004918977340039656,"gpt":0.2535361712553088,"spread":0.2486171939152691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003116397,0.0006214747,0.0008489672,0.0004339294,0.0004471315,0.0001369728,0.0002913381,0.0001517685,0.0009413998],"category_scores_gemma":[0.0009768398,0.0006082157,0.0005323804,0.0008513606,0.0002854341,0.0002674551,0.0001377933,0.0005747501,0.000880315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002461378,"about_ca_system_score_gemma":0.0006376392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002400186,"about_ca_topic_score_gemma":0.0002174975,"domain_scores_codex":[0.9964866,0.0002147526,0.0006600611,0.001003192,0.0007741023,0.0008612857],"domain_scores_gemma":[0.9958824,0.000242303,0.0003154773,0.001675731,0.0004183316,0.001465782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004469233,0.001177986,0.9859225,0.001116771,0.0002130674,0.0004974966,0.0001062095,0.0009425138,0.001085087,0.0002461113,0.005529869,0.00271543],"study_design_scores_gemma":[0.008208948,0.0005190235,0.8491647,0.0004837969,0.0007361243,0.0001827149,0.0001769267,0.008313593,0.0003004941,0.0001061699,0.1301225,0.00168507],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9757787,0.001261779,0.0005923514,0.0001209269,0.003000482,0.001447443,0.001400862,0.004508757,0.01188869],"genre_scores_gemma":[0.9962686,0.00006379756,0.00006515025,0.0006614146,0.001017547,0.0005211266,0.001025724,0.0001281548,0.0002484531],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1367579,"threshold_uncertainty_score":0.9999719,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042271503","doi":"10.1186/1476-072x-6-17","title":"Using GIS-based methods of multicriteria analysis to construct socio-economic deprivation indices","year":2007,"lang":"en","type":"article","venue":"International Journal of Health Geographics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Geographic information system; Health geography; Index (typography); Social deprivation; Socioeconomic status; Geocoding; Geography; Construct (python library); Variable (mathematics); Population; Econometrics; Statistics; Computer science; Public health; Mathematics; Cartography; Medicine; Environmental health; Health policy; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.06077023611313951,"gpt":0.4817446342364156,"spread":0.4209743981232761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004033845,0.0001233305,0.0005679228,0.002193133,0.00005098118,0.00002163909,0.0002778466,0.00006771449,0.00009336741],"category_scores_gemma":[0.0004136545,0.0001187593,0.0003609615,0.0005692125,0.0001197742,0.0001316662,0.00004212304,0.0001981883,0.00000166071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002887921,"about_ca_system_score_gemma":0.0006716458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003572706,"about_ca_topic_score_gemma":0.00009832121,"domain_scores_codex":[0.9975,0.0001618055,0.001405176,0.0001649699,0.0005546869,0.0002133405],"domain_scores_gemma":[0.996729,0.0003869794,0.00150908,0.000189197,0.0009208876,0.0002648663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006214818,0.0001449499,0.9576958,0.00006031434,0.001847294,0.00003165902,0.0002054755,0.001923368,0.001931044,0.0002681239,0.00004906296,0.03522136],"study_design_scores_gemma":[0.00192291,0.0002431028,0.9874799,0.0002144592,0.0004313069,0.00008172815,0.000298351,0.006300546,0.001345181,0.0002856937,0.001260206,0.0001366718],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7651566,0.000310341,0.2325784,0.00107036,0.0005939327,0.0001290159,0.0001276545,0.000009795928,0.00002386836],"genre_scores_gemma":[0.7934049,0.0000617039,0.2052245,0.001097428,0.0001435253,5.838709e-7,0.00005602976,0.000010253,9.835487e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03508469,"threshold_uncertainty_score":0.4842863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2605545985","doi":"10.2196/publichealth.6925","title":"Zika in Twitter: Temporal Variations of Locations, Actors, and Concepts","year":2017,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Zika virus; Geography; Computer science; Data science; Biology; Virology","retraction":null,"screen_n_in":null,"score":{"opus":0.04625401294774238,"gpt":0.3721192092418688,"spread":0.3258651962941264,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009356932,0.0001369263,0.0004946231,0.0001358732,0.000208625,0.00007402174,0.0001416779,0.0000719644,0.00003018804],"category_scores_gemma":[0.0008281539,0.0001274791,0.0000290209,0.000130735,0.0002545922,0.0002457067,0.00008923275,0.0001531543,0.000003967405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005135627,"about_ca_system_score_gemma":0.0008599084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006035384,"about_ca_topic_score_gemma":0.0007648029,"domain_scores_codex":[0.9984813,0.0001675176,0.0004569292,0.0003266969,0.0002070524,0.0003604637],"domain_scores_gemma":[0.9981516,0.0001218723,0.000349334,0.000672698,0.0001378057,0.0005667183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003934796,0.0001073527,0.9796249,0.0002802175,0.00001310781,0.000004320897,0.0003717534,8.260906e-8,0.00001161448,0.000622288,0.002961109,0.01596394],"study_design_scores_gemma":[0.001359688,0.0001028643,0.9265366,0.0000404323,5.293289e-7,0.00001048137,0.0001133477,0.000213067,7.331023e-7,0.0000474666,0.07147639,0.00009842798],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.971154,0.001954863,0.0002254762,0.02378641,0.0001500375,0.0008804753,0.0002650553,0.00006223515,0.001521426],"genre_scores_gemma":[0.9973301,0.0005866964,0.0004015731,0.001078115,0.00007080494,0.00005538435,0.0002708417,0.00001358012,0.0001929456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06851529,"threshold_uncertainty_score":0.5198446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}