{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":810,"total_is_capped":false,"direct_labels_cover":7,"predictions_cover":810,"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":"c4fa1a0a7c51","filters":{"venue":"International Journal for Population Data Science"}},"results":[{"id":"W3012405341","doi":"10.23889/ijpds.v4i2.1135","title":"ICES: Data, Discovery, Better Health","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Health care; Indigenous; Community health; Population health; Health policy; Business; Population; Medicine; Public relations; Environmental health; Political science; Economic growth; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3364591803734862,"gpt":0.5670953455288539,"spread":0.2306361651553677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002773377,0.000114096,0.0002073423,0.0001637835,0.001496518,0.0002356122,0.004839339,0.00004650599,0.0002216412],"category_scores_gemma":[0.001518058,0.00009381883,0.00003443323,0.0002674201,0.00007918162,0.007423012,0.001785476,0.0004640442,0.00009676474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005113112,"about_ca_system_score_gemma":0.002777626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006643177,"about_ca_topic_score_gemma":0.0003847449,"domain_scores_codex":[0.9968926,0.0001226182,0.0008643389,0.000561212,0.00108311,0.0004760643],"domain_scores_gemma":[0.9974483,0.0002894484,0.0006776858,0.0007781339,0.0004352655,0.0003711812],"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":[0.0001375393,0.00003633258,0.2622214,0.00008804264,0.00003808666,0.000006762938,0.0008402385,0.00003191105,0.0000911022,0.006509042,0.6895135,0.04048603],"study_design_scores_gemma":[0.0008178913,0.00006918795,0.1351086,0.00007255547,0.00001031169,0.00001292533,0.0003306223,0.01050113,0.000001781166,0.001376848,0.8515471,0.000151056],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.04125902,0.0003950145,0.1319502,0.7922779,0.020502,0.001350425,0.01034618,0.0001493124,0.001769887],"genre_scores_gemma":[0.5482177,0.0004921366,0.03121988,0.3973192,0.009636609,0.00002390505,0.01216297,0.00004544574,0.0008822171],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.5069587,"threshold_uncertainty_score":0.9998034,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906567312","doi":"10.23889/ijpds.v4i1.586","title":"Consensus Statement on Public Involvement and Engagement with Data-Intensive Health Research","year":2019,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":103,"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 of British Columbia","funders":"Economic and Social Research Council; Engineering and Physical Sciences Research Council; Wellcome Trust; Academy of Medical Sciences; British Heart Foundation; Cancer Research UK; Medical Research Council; National Institute for Social Care and Health Research","keywords":"Premise; Key (lock); Public relations; Public engagement; Statement (logic); Public health; Field (mathematics); Problem statement; Political science; Knowledge management; Medicine; Management science; Computer science; Nursing; Engineering; Law; Computer security; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.8330799193448962,"gpt":0.630687672687338,"spread":0.2023922466575582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01807163,0.0001401972,0.0001893189,0.0005729166,0.002210579,0.0001827888,0.001848353,0.00003500601,0.0001837398],"category_scores_gemma":[0.000699279,0.0001035849,0.0000125121,0.0003028745,0.0001751843,0.001080296,0.001473985,0.000655776,0.00009161606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001207049,"about_ca_system_score_gemma":0.00177946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008674418,"about_ca_topic_score_gemma":0.0008133712,"domain_scores_codex":[0.9943918,0.0005637576,0.0009421648,0.0007421404,0.002576014,0.000784096],"domain_scores_gemma":[0.9947861,0.0007432221,0.0006625043,0.0009965504,0.002321282,0.000490381],"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":[0.00173984,0.0005867072,0.7395835,0.0006816296,0.0001836985,0.00001596227,0.004541279,0.0001962727,0.0001450765,0.06819113,0.134584,0.04955089],"study_design_scores_gemma":[0.007475502,0.004069959,0.1090269,0.002842054,0.0000165024,0.00002971721,0.03014119,0.03916498,0.0000280975,0.003123481,0.8035967,0.0004849595],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.947217,0.0001359774,0.001370494,0.03654793,0.006773958,0.004425311,0.002767207,0.0000340177,0.0007281335],"genre_scores_gemma":[0.9790142,0.0002261673,0.005133685,0.008750546,0.0003513208,0.00006042427,0.005889557,0.00001764255,0.0005564602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6690127,"threshold_uncertainty_score":0.9990884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400654080","doi":"10.23889/ijpds.v9i2.2401","title":"Global trends in prevalence of maternal overweight and obesity: A systematic review and meta-analysis of routinely collected data retrospective cohorts","year":2024,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Gestational Diabetes Research and Management","field":"Medicine","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Overweight; Obesity; Meta-analysis; Medicine; Environmental health; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1645776435780225,"gpt":0.4826370919512163,"spread":0.3180594483731938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002934003,0.0002087754,0.00251764,0.001622127,0.0000493949,0.0001488135,0.001375968,0.0000470363,0.00008941496],"category_scores_gemma":[0.001649827,0.0001374355,0.0002848033,0.002371399,0.0001550057,0.0007626204,0.00108012,0.0001544246,5.210737e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002903246,"about_ca_system_score_gemma":0.0002712994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001274547,"about_ca_topic_score_gemma":0.0001399723,"domain_scores_codex":[0.996087,0.0001214944,0.001407048,0.0006478138,0.001559285,0.0001773231],"domain_scores_gemma":[0.9972259,0.0001189547,0.001076941,0.0007402074,0.0007115687,0.0001264719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.00003876261,0.0001890828,0.01371762,0.881692,0.09310746,0.0000557338,0.00002598177,0.000008169808,5.027308e-7,0.002812306,0.001410503,0.006941905],"study_design_scores_gemma":[0.0003093817,0.0001219313,0.1421863,0.06058484,0.7872759,0.0002524588,0.000006833284,0.006747284,1.195768e-7,0.0003246582,0.001973335,0.0002169918],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001443849,0.981742,0.0001614775,0.0001789684,0.000108007,0.001210847,0.01641076,0.000004941499,0.00003858576],"genre_scores_gemma":[0.003585595,0.9919386,0.0009510008,0.00003801536,0.00001985873,0.00003884463,0.002853135,0.00000882934,0.0005661498],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8211071,"threshold_uncertainty_score":0.5604456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3003985767","doi":"10.23889/ijpds.v5i1.1123","title":"Unlocking the Potential of Electronic Health Records for Health Research","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Alberta Health; University of Calgary; Alberta Health Services","funders":"","keywords":"Health records; Electronic health record; Data science; Computer science; Health care; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.4504956564272377,"gpt":0.6276072710141566,"spread":0.1771116145869189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.02713268,0.0001125406,0.0002904126,0.0003178176,0.003390721,0.00008940218,0.003040363,0.00006132835,0.0000417853],"category_scores_gemma":[0.00481846,0.00008435882,0.00007128641,0.0007369192,0.000155703,0.0009225232,0.0004307048,0.001072049,0.00001019731],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00174989,"about_ca_system_score_gemma":0.01092163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001954107,"about_ca_topic_score_gemma":0.001173518,"domain_scores_codex":[0.9939699,0.000888394,0.001557803,0.0004913578,0.001785662,0.001306858],"domain_scores_gemma":[0.9945871,0.001061259,0.001417792,0.0004752963,0.00207744,0.000381102],"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":[0.002305965,0.0002626245,0.04335991,0.001525494,0.000247937,0.000002323192,0.009964,0.00275559,0.001800962,0.2013156,0.4163315,0.3201281],"study_design_scores_gemma":[0.0029119,0.002226975,0.02410724,0.0008204032,0.00001188728,0.00005785343,0.00386388,0.2601083,0.0000293339,0.01512393,0.6904693,0.0002690003],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06527045,0.001530677,0.3414319,0.5707458,0.01258042,0.006760231,0.001417729,0.0000834045,0.0001794404],"genre_scores_gemma":[0.986845,0.0004035576,0.003338335,0.005875341,0.002939853,0.00009062278,0.0003093685,0.00002652409,0.0001714337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9215745,"threshold_uncertainty_score":0.9979067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2895747123","doi":"10.23889/ijpds.v3i3.433","title":"The Canadian Chronic Disease Surveillance System: A model for collaborative surveillance","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; Alberta Health; University of Calgary; University of Alberta; Manitoba Health; Public Health Agency of Canada; Health PEI; Institute for Clinical Evaluative Sciences; Government of Nunavut; Government of Northwest Territories; Nova Scotia Health Authority; Government of New Brunswick; Nova Scotia Department of Health and Wellness; Veterans Affairs Canada; Government of Saskatchewan; Ministry of Health; Institut National de Santé Publique du Québec; University of Manitoba","funders":"Government of Canada; Ministry of Health, Saskatchewan; Public Health Agency; Public Health Agency of Canada","keywords":"Disease surveillance; Disease registry; Public health; Disease; Chronic disease; Population; Medicine; Agency (philosophy); Environmental health; Business; Family medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.07300541383426135,"gpt":0.4097254394438772,"spread":0.3367200256096159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006953926,0.00008709216,0.0001266282,0.0001657659,0.001721931,0.0003465023,0.0007574745,0.00003409986,0.000007452672],"category_scores_gemma":[0.001518434,0.00006465441,0.0000839827,0.0002804338,0.0002087111,0.0006427855,0.00006785048,0.00009491354,0.000009262245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001286398,"about_ca_system_score_gemma":0.003794004,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001328087,"about_ca_topic_score_gemma":0.0693498,"domain_scores_codex":[0.9980913,0.0001106625,0.0003669036,0.0003119383,0.0008047409,0.0003144064],"domain_scores_gemma":[0.9959747,0.00007190333,0.0002102247,0.0004531169,0.002871687,0.0004183937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002885078,0.0003535016,0.1575313,0.0008652179,0.001475349,0.00007171604,0.001310738,0.01555174,0.00108395,0.1991636,0.07034738,0.5493605],"study_design_scores_gemma":[0.00106488,0.00008506674,0.1175108,0.00009965372,0.00001754568,0.00007325894,0.00004845593,0.8400754,0.000008322892,0.0005635703,0.04035642,0.00009654702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03752936,0.0009281366,0.9202446,0.02274238,0.01088198,0.003407102,0.003542496,0.00008573206,0.0006381925],"genre_scores_gemma":[0.9955405,0.00007027762,0.001939911,0.0001901131,0.001278145,0.00003340403,0.0005411329,0.00001070192,0.0003958093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9580112,"threshold_uncertainty_score":0.9995777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3217141020","doi":"10.23889/ijpds.v6i1.1680","title":"Data Harmonization and Data Pooling from Cohort Studies: A Practical Approach for Data Management","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Gestational Diabetes Research and Management","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"York University; Alberta Health Services; University of Calgary","funders":"","keywords":"Pooling; Harmonization; Matching (statistics); Computer science; Variable (mathematics); Construct (python library); Data mining; Sample (material); Econometrics; Data science; Statistics; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3638508337347413,"gpt":0.5330212202993609,"spread":0.1691703865646197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003331088,0.0001191866,0.0001850905,0.0002161431,0.0003663326,0.0006358256,0.003332434,0.00002769399,0.00002670595],"category_scores_gemma":[0.007890948,0.0001069486,0.00001486937,0.0002699823,0.0001318136,0.005192743,0.007965586,0.000144413,0.000003155382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301317,"about_ca_system_score_gemma":0.0003259052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004127828,"about_ca_topic_score_gemma":0.00004055095,"domain_scores_codex":[0.996514,0.00004129278,0.0004664228,0.001217782,0.00149104,0.0002694337],"domain_scores_gemma":[0.9955125,0.0003328013,0.0002285179,0.002585595,0.001145812,0.0001947205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001433636,0.001926661,0.1151393,0.0009261002,0.007945925,0.0003613212,0.0002230912,0.001274116,0.001587855,0.03706806,0.5032619,0.3288521],"study_design_scores_gemma":[0.001350816,0.00003039248,0.04192725,0.0001090557,0.0003578431,0.00009203387,0.0005526646,0.8501382,0.00001766472,0.001815081,0.1034807,0.0001282811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004522294,0.001001873,0.9596987,0.01222182,0.001189019,0.001180404,0.01999741,0.00002311177,0.0001653313],"genre_scores_gemma":[0.05101548,0.002376674,0.67829,0.0006975921,0.0006795292,0.00002316496,0.266445,0.00001819642,0.0004543406],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8488641,"threshold_uncertainty_score":0.9928533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2788138713","doi":"10.23889/ijpds.v3i1.415","title":"Position Statement on Population Data Science:","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Statistics Canada; University of Calgary; Manitoba Health; University of British Columbia","funders":"Economic and Social Research Council; Medical Research Council","keywords":"Data science; Population; Field (mathematics); Computer science; Discipline; Analytics; Public engagement; Informatics; Big data; Engineering ethics; Knowledge management; Sociology; Public relations; Political science; Data mining; Social science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09722525678110634,"gpt":0.4376056193179299,"spread":0.3403803625368236,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006559669,0.0001713873,0.0001187601,0.000397138,0.001709846,0.0006451153,0.004626764,0.00004052124,0.0007364811],"category_scores_gemma":[0.001380109,0.0001591172,0.0000253559,0.0006745627,0.0009324473,0.01105534,0.001993351,0.0002074831,0.0003550637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00176305,"about_ca_system_score_gemma":0.0001562066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008531043,"about_ca_topic_score_gemma":0.000265125,"domain_scores_codex":[0.9945631,0.00006524516,0.0006362876,0.001268603,0.002933238,0.0005335112],"domain_scores_gemma":[0.9975917,0.00008462517,0.0005071551,0.001331937,0.0001855457,0.0002990901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005048343,0.0008124409,0.4597442,0.00001411855,0.00006348037,0.00003070469,0.0008559135,0.006453455,0.06027175,0.01045552,0.01792182,0.4428718],"study_design_scores_gemma":[0.0005810306,0.0001995744,0.8395335,0.00006246386,0.00001604714,0.00005798534,0.0000814346,0.1343368,0.0007109914,0.002817474,0.02132929,0.0002733425],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9550053,0.000006161021,0.03321651,0.003756674,0.004302535,0.0006857617,0.0008130869,0.00004989795,0.002164028],"genre_scores_gemma":[0.9850699,0.00002941303,0.01174429,0.001102115,0.0006721485,0.000006965482,0.001269764,0.00001573916,0.00008961641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4425984,"threshold_uncertainty_score":0.9995898,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200669805","doi":"10.23889/ijpds.v6i1.1650","title":"Machine learning for identification of frailty in Canadian primary care practices","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Frailty in Older Adults","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Alberta; University of Manitoba; McMaster University; Dalhousie University; Manitoba Health; University of British Columbia; University of Calgary","funders":"Canadian Frailty Network; Michael Smith Health Research BC","keywords":"Machine learning; Context (archaeology); Receiver operating characteristic; Medicine; Artificial intelligence; Medical record; Primary care; Oversampling; Computer science; Family medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.09551632604470203,"gpt":0.4260697510684341,"spread":0.3305534250237321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001100021,0.00006135654,0.0001144668,0.0004042746,0.0001590657,0.000130759,0.00055744,0.00003484581,0.00002576838],"category_scores_gemma":[0.007419151,0.00006157855,0.00003673582,0.0002815588,0.00005366641,0.001468856,0.00008531443,0.0001550186,0.000001529854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005740341,"about_ca_system_score_gemma":0.001393157,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01848004,"about_ca_topic_score_gemma":0.07563113,"domain_scores_codex":[0.9984795,0.00002317755,0.0004577098,0.0002679221,0.0005944411,0.000177216],"domain_scores_gemma":[0.9973482,0.00012929,0.0005652937,0.0002527205,0.001571164,0.0001333378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002209086,0.0001123488,0.8949057,0.0001841609,0.00005608962,0.00003470623,0.0007907731,0.002959913,0.0235317,0.001844465,0.0004880973,0.07487111],"study_design_scores_gemma":[0.001619055,0.00007503126,0.8603371,0.0002638726,0.00003973259,0.0003181343,0.0004417036,0.08955932,0.002661053,0.0004928173,0.04407471,0.0001174165],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9509138,0.001479676,0.01955005,0.01688498,0.00592902,0.001276801,0.00271612,0.00003202614,0.001217544],"genre_scores_gemma":[0.9858609,0.00006802517,0.008637867,0.0001573501,0.0001790653,0.000007418922,0.00471174,0.000007907283,0.0003696714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08659941,"threshold_uncertainty_score":0.988056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2811987522","doi":"10.23889/ijpds.v3i1.448","title":"Identifying Cases of Sleep Disorders through International Classification of Diseases (ICD) Codes in Administrative Data","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Sleep and related disorders","field":"Psychology","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Calgary","funders":"","keywords":"Narcolepsy; Diagnosis code; Medicine; Insomnia; Sleep disorder; Cohort; Obstructive sleep apnea; Population; Psychiatry; Medical record; Pediatrics; Internal medicine; Neurology","retraction":null,"screen_n_in":null,"score":{"opus":0.2209034322523036,"gpt":0.4957804345206004,"spread":0.2748770022682968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007928564,0.0001136184,0.0001567485,0.0004497009,0.0001551965,0.0001044533,0.003281061,0.00006102939,0.0001947553],"category_scores_gemma":[0.001392508,0.0001043114,0.00004557978,0.000427616,0.0006611506,0.002801144,0.000428476,0.0001292809,0.000008393605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007814856,"about_ca_system_score_gemma":0.0001400739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006782624,"about_ca_topic_score_gemma":0.0006859487,"domain_scores_codex":[0.9977982,0.00006452346,0.0007523863,0.0004879423,0.0007071535,0.0001897608],"domain_scores_gemma":[0.9976373,0.0002655914,0.000744517,0.0006803975,0.0006124994,0.00005965956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001603497,0.002065097,0.7764629,0.00002657491,0.001011606,0.00001775132,0.004534909,0.0003852468,0.002669242,0.08945457,0.00546045,0.1163082],"study_design_scores_gemma":[0.002842805,0.0002594794,0.9188805,0.0002186266,0.0001375327,0.0001150091,0.005992496,0.04825184,0.0002564739,0.01704883,0.005681883,0.0003144721],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8884618,0.0006431498,0.08504817,0.00224424,0.0148891,0.0006479661,0.005343603,0.0000488344,0.002673167],"genre_scores_gemma":[0.9947815,0.0001394635,0.003033953,0.00004217402,0.0002439941,0.000006697434,0.001696006,0.00001200573,0.00004424072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1424177,"threshold_uncertainty_score":0.6097082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2944477024","doi":"10.23889/ijpds.v4i1.1103","title":"Sharing linked data sets for research: results from a deliberative public engagement event in British Columbia, Canada","year":2019,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"BC Centre for Disease Control; University of Guelph; Canadian Centre for Applied Research in Cancer Control; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Deliberation; Data sharing; Public relations; Voting; Event (particle physics); Public engagement; Internet privacy; Data governance; Process (computing); Political science; Data quality; Computer science; Business; Medicine; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.3426009505686775,"gpt":0.4858671252356331,"spread":0.1432661746669557,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01495219,0.00006013041,0.0001358842,0.0002153477,0.001410498,0.004133156,0.006027652,0.00002779727,0.0001176629],"category_scores_gemma":[0.01036861,0.00008295157,0.00002860923,0.0005041231,0.0001305379,0.004948488,0.00172543,0.0002704846,0.000002939493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007396125,"about_ca_system_score_gemma":0.002077898,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9358504,"about_ca_topic_score_gemma":0.9970747,"domain_scores_codex":[0.9958799,0.0001946288,0.0006156769,0.000770259,0.00207846,0.0004610078],"domain_scores_gemma":[0.9970841,0.0008556997,0.0002992988,0.0007210242,0.0008527367,0.0001870905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001356117,0.0003170726,0.5763435,0.00001372903,0.000223331,0.00004439916,0.004331679,0.001725692,0.0003234849,0.006490687,0.1019544,0.3080965],"study_design_scores_gemma":[0.001609846,0.00003465438,0.3595766,0.0002948824,0.00001383077,0.000004816827,0.004906692,0.2881881,0.000002123159,0.009931566,0.3351502,0.0002867108],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9696392,0.00003577728,0.002716401,0.006096255,0.002390051,0.0007548188,0.01796235,0.00001203437,0.00039305],"genre_scores_gemma":[0.984377,0.00006271478,0.004876321,0.0001582845,0.0004235693,0.00001171383,0.009412872,0.000007201363,0.0006703498],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3078097,"threshold_uncertainty_score":0.9998896,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883238867","doi":"10.23889/ijpds.v3i1.445","title":"Coding reliability and agreement of international classification of disease, 10th revision (ICD-10) codes in emergency department data","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Audit; Coding (social sciences); Emergency department; Diagnosis code; ICD-10; Medicine; Medical emergency; Reliability (semiconductor); Computer science; Statistics; Nursing; Environmental health; Business; Mathematics; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.3808662722987242,"gpt":0.5501127744964156,"spread":0.1692465021976914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007048487,0.00008351672,0.0001602421,0.0003598506,0.0003996872,0.00002549635,0.001571177,0.00004933169,0.0004371392],"category_scores_gemma":[0.005638048,0.00007087002,0.00001934727,0.0002449028,0.0001891088,0.001947177,0.0007164277,0.0001771896,0.000008229936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002499724,"about_ca_system_score_gemma":0.0003971375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001616502,"about_ca_topic_score_gemma":0.0001625621,"domain_scores_codex":[0.9966888,0.0001217523,0.001508089,0.0003370511,0.0011403,0.000204047],"domain_scores_gemma":[0.9963851,0.0002256499,0.001168772,0.0006100509,0.001443058,0.0001673437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008722387,0.0001993134,0.9280121,0.0003565995,0.00002632091,5.415729e-7,0.0008591519,0.00009249015,0.000656239,0.01170856,0.01890063,0.03831584],"study_design_scores_gemma":[0.0006833974,0.00007794343,0.7573522,0.0005803749,0.00001355091,0.000001328102,0.0002748862,0.2157976,0.00001966523,0.001669739,0.02345018,0.00007919441],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9307145,0.0001264959,0.04870017,0.008201267,0.007249844,0.001144931,0.002790368,0.00001997726,0.001052448],"genre_scores_gemma":[0.9913116,0.0007262802,0.005365643,0.00008956822,0.0004058272,0.000008465869,0.001999602,0.000004355211,0.00008864196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2157051,"threshold_uncertainty_score":0.6749676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4301605997","doi":"10.23889/ijpds.v7i1.1757","title":"A scoping review of preprocessing methods for unstructured text data to assess data quality","year":2022,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation; Manitoba Health","funders":"Canada Research Chairs","keywords":"Computer science; Preprocessor; Punctuation; Data quality; Data pre-processing; Stop words; Information retrieval; Lexical analysis; Natural language processing; Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.9239911994930267,"gpt":0.7624971008446532,"spread":0.1614940986483735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.1192936,0.0003425022,0.00166487,0.001138523,0.0007887261,0.0021249,0.0544372,0.00007620063,0.0004184565],"category_scores_gemma":[0.1551206,0.0002622833,0.0002218469,0.002136638,0.0001927214,0.009437866,0.02545096,0.0003545998,0.000007443812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002766372,"about_ca_system_score_gemma":0.002754723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000859502,"about_ca_topic_score_gemma":0.0000698519,"domain_scores_codex":[0.9858254,0.001375292,0.004651135,0.002719895,0.005014746,0.0004135255],"domain_scores_gemma":[0.9694701,0.008737557,0.007315258,0.01208978,0.002060535,0.0003268091],"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":[0.00001638609,0.00003557527,0.000003198368,0.01516574,0.00007216633,7.113733e-7,0.00001581812,0.00001734407,9.618203e-7,0.001280966,0.01433392,0.9690572],"study_design_scores_gemma":[0.0001476429,0.00002282537,0.00001462649,0.06427237,0.0002488629,0.00004923794,0.00005719169,0.003803544,4.46795e-7,0.002534024,0.9285659,0.0002832889],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.775133e-7,0.5087191,0.459062,0.0005346828,0.003809113,0.001991975,0.0258214,0.00001273481,0.00004884132],"genre_scores_gemma":[7.113046e-7,0.6736616,0.2973722,0.0004914062,0.0003421187,0.00006211572,0.02794647,0.00001974873,0.000103668],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9687739,"threshold_uncertainty_score":0.999983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4241632110","doi":"10.23889/ijpds.v4i2.1133","title":"Population Data BC: Supporting population data science in British Columbia","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"The Quebec Population Health Research Network; University of British Columbia","funders":"","keywords":"Computer science; Data access; Linkage (software); Variety (cybernetics); Data quality; Identifier; Data science; Data management; Linked data; Record linkage; Population; Database; World Wide Web; Service (business); Business","retraction":null,"screen_n_in":null,"score":{"opus":0.4131892460550775,"gpt":0.5216265395244426,"spread":0.1084372934693651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.02786832,0.0001851004,0.0003786746,0.0007195481,0.001369474,0.01266832,0.0282646,0.00007032599,0.0004248983],"category_scores_gemma":[0.04174124,0.0002335582,0.00005093791,0.003016863,0.0003963596,0.04263052,0.01163821,0.0003537286,0.00006007649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003552661,"about_ca_system_score_gemma":0.0004666633,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05802133,"about_ca_topic_score_gemma":0.1004933,"domain_scores_codex":[0.9874048,0.0001968373,0.002374241,0.002528181,0.006818634,0.0006773034],"domain_scores_gemma":[0.9926067,0.0004740238,0.001676288,0.003634226,0.001158315,0.0004504235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004727931,0.0001217217,0.7225228,0.00001209862,0.00001622124,0.0000354007,0.0001483684,0.001601683,0.0001611422,0.001942254,0.03359865,0.2397924],"study_design_scores_gemma":[0.0004827271,0.00002914023,0.6200442,0.00005824766,0.00001440286,0.00004048931,0.0003823851,0.3510511,0.000002042124,0.006311758,0.02135219,0.0002313643],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8865519,0.00005963616,0.07598428,0.01256261,0.009467637,0.001282243,0.01360417,0.0001284257,0.0003591086],"genre_scores_gemma":[0.9646276,0.00004099073,0.01679803,0.001056241,0.0007358834,0.000004779165,0.01654906,0.00001757319,0.0001699069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3494494,"threshold_uncertainty_score":0.9999306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4237117124","doi":"10.23889/ijpds.v4i2.1131","title":"Population Data Centre Profile: The Manitoba Centre for Health Policy","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Manitoba; Manitoba Health","funders":"","keywords":"Government (linguistics); Corporate governance; Population; Population health; Data governance; Political science; Public relations; Public administration; Sociology; Management; Engineering; Operations management; Data quality; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.1808609753963607,"gpt":0.4909925594696052,"spread":0.3101315840732445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003084131,0.0001087445,0.0001518744,0.0001251242,0.00241348,0.0008583328,0.004250953,0.00004268338,0.00006612065],"category_scores_gemma":[0.005709558,0.00008420727,0.00004967931,0.0004311882,0.0001511291,0.003120606,0.0005232838,0.0001510332,0.00001029277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000496449,"about_ca_system_score_gemma":0.001323737,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02663656,"about_ca_topic_score_gemma":0.02374119,"domain_scores_codex":[0.9970478,0.000122801,0.0005582263,0.0004600088,0.001262681,0.0005484285],"domain_scores_gemma":[0.9978525,0.0002715507,0.0004884683,0.0004810612,0.0005017115,0.0004047055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001764528,0.00008823147,0.2096426,0.00009285192,0.00005213558,0.000002208426,0.005491357,0.0002931398,0.000006715065,0.3970481,0.2459656,0.1411406],"study_design_scores_gemma":[0.0005648909,0.00002573156,0.1543481,0.00007287494,0.00001244833,0.000005263564,0.00431796,0.04470638,0.000001862619,0.00366432,0.7921082,0.0001719921],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01161628,0.0001122638,0.009305434,0.9671681,0.004957113,0.001402688,0.005128982,0.00006510832,0.0002440102],"genre_scores_gemma":[0.9452457,0.0003105396,0.01053616,0.02948001,0.008568131,0.000009768119,0.005311751,0.00002384061,0.0005140838],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9376881,"threshold_uncertainty_score":0.9988852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080320223","doi":"10.23889/ijpds.v5i1.1353","title":"Essential Requirements for Establishing and Operating Data Trusts","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University; MaRS; University of British Columbia; Compute Canada; Hospital for Sick Children; BC Centre for Disease Control; Sunnybrook Health Science Centre; British Columbia Environmental and Occupational Health Research Network; Canadian Institute for Health Information; McGill University and Génome Québec Innovation Centre; St. Joseph's Care Group; Institute for Work & Health; Ontario Genomics; Sunnybrook Hospital; Vector Institute; SickKids Foundation; University Health Network; University of Toronto","funders":"Terry Fox Research Institute","keywords":"Computer science; Business; Process management; Risk analysis (engineering); Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.7775022628649542,"gpt":0.6687863492661111,"spread":0.108715913598843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00597129,0.00007131368,0.0001282735,0.0001112405,0.0004160064,0.0008782002,0.002438461,0.00005599007,0.00003652858],"category_scores_gemma":[0.06993772,0.00006150133,0.00002207905,0.0001692053,0.0001756397,0.003882035,0.001670235,0.0004240624,0.000001881346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007030853,"about_ca_system_score_gemma":0.0004856642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004805045,"about_ca_topic_score_gemma":0.00003763364,"domain_scores_codex":[0.9971004,0.00001944258,0.0004921749,0.0005638929,0.001616015,0.0002081357],"domain_scores_gemma":[0.9964739,0.001178986,0.0002083037,0.0005370688,0.001293412,0.0003082914],"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":[0.004266016,0.0007919549,0.3851208,0.001072504,0.000912276,0.0001645798,0.002460786,0.001180336,0.1226658,0.167011,0.05624906,0.258105],"study_design_scores_gemma":[0.003685899,0.0003678534,0.02327273,0.0002674498,0.0001246638,0.0001527607,0.0002997169,0.9425203,0.0007599409,0.01160701,0.01671357,0.0002280785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4495665,0.0001668634,0.3778639,0.1607613,0.005287547,0.001900894,0.003932181,0.00007235476,0.0004484356],"genre_scores_gemma":[0.9100857,0.00008195238,0.08479992,0.001938449,0.001513591,0.000004566907,0.001435342,0.00001238519,0.0001281309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.94134,"threshold_uncertainty_score":0.9378966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3082148444","doi":"10.23889/ijpds.v5i1.1344","title":"Developing and validating a primary care EMR-based frailty definition using machine learning","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Frailty in Older Adults","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Manitoba Health; University of British Columbia; University of Manitoba; Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Medicine; Primary care; Medical record; Vulnerability (computing); Emergency medicine; Machine learning; Artificial intelligence; Internal medicine; Family medicine; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2498109628479395,"gpt":0.4109768209527652,"spread":0.1611658581048256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004755096,0.000104432,0.0001350386,0.0001933981,0.0004403371,0.0002754831,0.0004448861,0.00003414253,0.00001686084],"category_scores_gemma":[0.001978955,0.00009952765,0.00003158545,0.0002423172,0.00008202139,0.001299902,0.0002399183,0.0002380514,0.000002093438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003441279,"about_ca_system_score_gemma":0.0004192771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009261962,"about_ca_topic_score_gemma":0.00001449209,"domain_scores_codex":[0.9983171,0.00002755335,0.0003561608,0.0003393031,0.0007859785,0.0001738857],"domain_scores_gemma":[0.9987416,0.00009335619,0.0002582274,0.0001349565,0.000610222,0.0001616844],"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":[0.0006399436,0.00006560786,0.8017591,0.0004966995,0.0001117231,0.00009240112,0.00209232,0.007354925,0.07723717,0.002625605,0.0001331057,0.1073914],"study_design_scores_gemma":[0.00356912,0.0002406788,0.1247722,0.0010408,0.00009419375,0.0007012386,0.0005070918,0.8603013,0.003440533,0.000559157,0.004409715,0.0003639813],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7637393,0.0001746136,0.2292774,0.005444376,0.0006844322,0.0002785146,0.0002313023,0.00005808715,0.0001119846],"genre_scores_gemma":[0.7980198,0.00001513606,0.1988186,0.001275261,0.0002978236,0.000001715131,0.001554504,0.00001217613,0.000004982769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8529463,"threshold_uncertainty_score":0.405862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014051546","doi":"10.23889/ijpds.v5i1.1155","title":"Is there an agreement between self-reported medical diagnosis in the CARTaGENE cohort and the Québec administrative health databases?","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal; McGill University Health Centre; McGill University; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Concordance; Medicine; Logistic regression; Cohen's kappa; Kappa; Cohort; Medical record; Population; Database; Demography; Family medicine; Gerontology; Statistics; Environmental health; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.195087093308817,"gpt":0.4736725290024802,"spread":0.2785854356936633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004171047,0.000108484,0.0002124659,0.00007537365,0.0002947867,0.0001774505,0.001366929,0.00001942591,0.0001477499],"category_scores_gemma":[0.002565806,0.00006189691,0.00003779812,0.0002663454,0.0002816847,0.0009433388,0.0002803094,0.0002324387,0.000003743596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001418291,"about_ca_system_score_gemma":0.001360192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005472459,"about_ca_topic_score_gemma":0.005641559,"domain_scores_codex":[0.9967778,0.0001833832,0.0005919678,0.0004182157,0.001841755,0.0001868892],"domain_scores_gemma":[0.9981365,0.0003569782,0.0003835369,0.000511903,0.0002592396,0.0003518124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001390463,0.00008313984,0.9859642,0.000009937228,0.000136703,0.00004189921,0.0009417067,0.000004782743,0.000002167315,0.0004895901,0.004607111,0.007579674],"study_design_scores_gemma":[0.00158349,0.0001233602,0.965888,0.00006724768,0.00006829231,0.0001244223,0.0003776509,0.0115178,0.000007725926,0.00007336964,0.02009431,0.00007433937],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8254994,0.0003889062,0.001773701,0.1679778,0.0002888943,0.0009854789,0.002993729,0.000024237,0.00006783791],"genre_scores_gemma":[0.9882386,0.0004004472,0.00102439,0.007747154,0.0004497581,0.00002963607,0.002097799,0.00000646435,0.000005756118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1627392,"threshold_uncertainty_score":0.8272758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786827563","doi":"10.23889/ijpds.v3i1.419","title":"Using the RECORD guidelines to improve transparent reporting of studies based on routinely collected data","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Ottawa","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Wellcome Trust","keywords":"Observational study; Data science; Key (lock); Health care; Quality (philosophy); Data quality; Computer science; Data mining; Medicine; Operations management; Engineering; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.970685801615776,"gpt":0.7130115155502669,"spread":0.2576742860655091,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1530303,0.0001522166,0.0009429941,0.0005938291,0.0006143097,0.001065303,0.009847829,0.00002216577,0.0002343572],"category_scores_gemma":[0.3457011,0.00006783657,0.0002408365,0.001629858,0.0001695602,0.001283908,0.0006973778,0.00008902644,0.00001699984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009867649,"about_ca_system_score_gemma":0.0003236099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001053841,"about_ca_topic_score_gemma":0.0002809915,"domain_scores_codex":[0.9795968,0.0007070507,0.01188769,0.000954504,0.006660484,0.0001935017],"domain_scores_gemma":[0.9519882,0.002494651,0.02076228,0.0059694,0.0186334,0.0001521086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005522158,0.0002759949,0.3057,0.00006090657,0.001038428,0.00001415982,0.001519106,0.05890216,0.01188728,0.003020166,0.3039552,0.3130743],"study_design_scores_gemma":[0.0001656603,0.00007470678,0.01894453,0.0001541885,0.00008123964,0.00001995991,0.0003635394,0.9624191,0.0001602629,0.001394092,0.01612833,0.00009439516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2221853,0.00009400894,0.7592977,0.009498382,0.007058669,0.00090666,0.0007829912,0.000005492379,0.0001707676],"genre_scores_gemma":[0.8600254,0.000005955799,0.1382222,0.0006975084,0.0006647255,0.000004775983,0.00005289343,0.000006443953,0.0003200596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9035169,"threshold_uncertainty_score":0.9999717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2895262614","doi":"10.23889/ijpds.v3i3.437","title":"Challenges Associated with Cross-Jurisdictional Analyses using Administrative Health Data and Primary Care Electronic Medical Records in Canada","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Alberta; University of Calgary; University of Manitoba; Alberta Health Services; University of British Columbia; Manitoba Health","funders":"","keywords":"Custodians; Jurisdiction; Business; Data quality; Health care; Data access; Population health; Population; Medicine; Environmental health; Political science; Computer science; Geography; Database; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.3867880874018707,"gpt":0.4891489664041175,"spread":0.1023608790022469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002298368,0.00008176736,0.0001719468,0.0002762628,0.0003098791,0.0001523332,0.001145934,0.000028355,0.00002845517],"category_scores_gemma":[0.0006317986,0.00008055302,0.00000970049,0.0002181536,0.0001313207,0.001387552,0.000317018,0.0001586737,7.208651e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002118851,"about_ca_system_score_gemma":0.004418519,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4933256,"about_ca_topic_score_gemma":0.9354373,"domain_scores_codex":[0.9983212,0.00002806282,0.0005525745,0.0004606331,0.0003401083,0.0002974726],"domain_scores_gemma":[0.998785,0.00007505838,0.0004731253,0.00029754,0.0002174498,0.0001518699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002553531,0.0001614839,0.7954021,0.00009012835,0.0003084527,0.00002859881,0.001321312,0.0005388514,0.00000299555,0.1217232,0.001174009,0.07899354],"study_design_scores_gemma":[0.0007834499,0.0001829247,0.8808854,0.0001611933,0.000004502117,0.00005998346,0.0003816822,0.09636619,0.000001639412,0.004040003,0.01695308,0.0001800056],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9488323,0.003874986,0.01107758,0.02466184,0.00266225,0.0004804041,0.007174484,0.00001834366,0.001217781],"genre_scores_gemma":[0.9965158,0.0006760657,0.0008538078,0.0007504325,0.0002671263,0.000002383135,0.0009163219,0.000006161181,0.00001196573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4421117,"threshold_uncertainty_score":0.7838262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891377679","doi":"10.23889/ijpds.v3i4.911","title":"First Nations Data Governance, Privacy, and the Importance of the OCAP® principles","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Acronym; Internet privacy; Information privacy; Privacy by Design; Corporate governance; Realm; Privacy policy; Privacy law; Data governance; Political science; Public relations; Computer science; Business; Law; Data quality","retraction":null,"screen_n_in":null,"score":{"opus":0.5234185834369959,"gpt":0.5876122302660017,"spread":0.06419364682900586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007974903,0.000062516,0.0001122038,0.0000782866,0.0008008002,0.0001683691,0.004824719,0.00004489111,0.00004396916],"category_scores_gemma":[0.08598005,0.00003315423,0.00003453308,0.0003772039,0.002096274,0.001099271,0.002902872,0.0004054407,0.000002452992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008351549,"about_ca_system_score_gemma":0.0006454753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066724,"about_ca_topic_score_gemma":0.003170823,"domain_scores_codex":[0.9969468,0.00003391854,0.0005348416,0.0003384861,0.001998826,0.0001471132],"domain_scores_gemma":[0.991522,0.003701635,0.0006496131,0.001943784,0.002079569,0.0001034113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00028836,0.0000685294,0.3821766,0.00002987494,0.00005595417,0.000001380198,0.0001592564,0.00002795556,0.0000875453,0.6135032,0.002058247,0.001543155],"study_design_scores_gemma":[0.001662859,0.00006001964,0.82928,0.0003773797,0.00003606888,0.0001472952,0.00004773368,0.07526285,0.00009772743,0.03686966,0.05608961,0.00006876534],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7046955,0.0005781519,0.01326273,0.262429,0.007720667,0.00205071,0.003084435,0.00003272107,0.006146054],"genre_scores_gemma":[0.9907113,0.000618732,0.006839987,0.0005121428,0.0006111835,0.000003856773,0.00008023834,0.000006047143,0.0006164851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5766335,"threshold_uncertainty_score":0.9217191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389615820","doi":"10.23889/ijpds.v8i1.2153","title":"De-identification of Free Text Data containing Personal Health Information: A Scoping Review of Reviews","year":2023,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Health Insurance Portability and Accountability Act; Identification (biology); Computer science; Protected health information; Information retrieval; MEDLINE; Personally identifiable information; Digital library; Data science; World Wide Web; Medicine; Confidentiality; Public health; Nursing; Health education","retraction":null,"screen_n_in":null,"score":{"opus":0.7026193400916434,"gpt":0.6308973187983484,"spread":0.07172202129329497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07437966,0.0002260038,0.001452608,0.001358967,0.0003325671,0.000942666,0.01807817,0.00006471051,0.0001177237],"category_scores_gemma":[0.06575675,0.0001738314,0.0002589187,0.001797931,0.0002218254,0.009249598,0.00429955,0.0002499947,0.00006816018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002908427,"about_ca_system_score_gemma":0.00256063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001499297,"about_ca_topic_score_gemma":0.00007457093,"domain_scores_codex":[0.9875827,0.0005568905,0.006617116,0.0007229413,0.004216212,0.0003041784],"domain_scores_gemma":[0.9813532,0.001399557,0.01186457,0.003379878,0.001826005,0.0001768051],"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":[0.000005910315,0.00001944298,0.000008429448,0.02713372,0.00004269615,4.79978e-7,0.00009950463,0.000004131516,1.175437e-7,0.002443268,0.03728007,0.9329622],"study_design_scores_gemma":[0.0001305442,0.00002847095,0.0000380855,0.2207394,0.00009487045,0.00003741265,0.00009098175,0.00204625,1.13359e-7,0.000857024,0.7758035,0.0001333251],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.649742e-7,0.9250688,0.05741154,0.001183291,0.002280572,0.001791003,0.01219702,0.00001425928,0.00005314205],"genre_scores_gemma":[0.000005274331,0.9843192,0.004617844,0.0004737379,0.0002315402,0.0000310523,0.01021494,0.00001095169,0.00009548473],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9328289,"threshold_uncertainty_score":0.9872345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804792234","doi":"10.23889/ijpds.v3i1.450","title":"Unlocking First Nations health information through data linkage","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; Laurentian University; Institute for Work & Health; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Indigenous; Linkage (software); Sovereignty; Context (archaeology); Linked data; Population; Record linkage; Geography; Metis; Economic growth; Database; Political science; Medicine; Environmental health; Biology; Law; Genetics; Ecology; World Wide Web; Computer science; Economics; Politics","retraction":null,"screen_n_in":null,"score":{"opus":0.4724617458589112,"gpt":0.5651324642231068,"spread":0.09267071836419566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01502152,0.0001221754,0.0001615144,0.0009094535,0.002522614,0.003616138,0.0125341,0.00003494312,0.0002236115],"category_scores_gemma":[0.0220649,0.0001002084,0.0000395053,0.001358432,0.0003168304,0.03518074,0.003443755,0.0001451329,0.0002870373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002293958,"about_ca_system_score_gemma":0.0004263196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005746934,"about_ca_topic_score_gemma":0.003017335,"domain_scores_codex":[0.9939378,0.00008994499,0.001325466,0.0006144062,0.003702622,0.0003296967],"domain_scores_gemma":[0.9936618,0.0007339417,0.001183662,0.002199484,0.002058266,0.00016286],"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":[0.00008047523,0.0001453798,0.004913412,0.00001760362,0.0000661957,0.000002300859,0.002133854,0.001027358,0.00001338745,0.2939061,0.3931488,0.3045452],"study_design_scores_gemma":[0.0003572988,0.00005303313,0.0108972,0.00005510094,0.000006018186,0.00003032027,0.0005465501,0.08033777,0.00001047129,0.0213006,0.8862786,0.0001270181],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002437791,0.00003791177,0.946075,0.03202141,0.0105087,0.0004537101,0.005367042,0.00005769749,0.003040721],"genre_scores_gemma":[0.9155758,0.0001838836,0.06947912,0.004671929,0.001823865,0.000007279039,0.007868689,0.000009990669,0.0003794436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.913138,"threshold_uncertainty_score":0.998776,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4306789942","doi":"10.23889/ijpds.v7i4.1759","title":"Representativeness of survey participants in relation to mental disorders: a linkage between national registers and a population-representative survey","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Lundbeckfonden","keywords":"Representativeness heuristic; Linkage (software); Relation (database); Population; Psychology; Record linkage; Medicine; Environmental health; Computer science; Data mining; Social psychology; Genetics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.5850050008153506,"gpt":0.5850696942076199,"spread":0.00006469339226933268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06736235,0.00009409929,0.0001914855,0.0007024994,0.0009832139,0.0001228716,0.001163256,0.00003976543,0.00005688398],"category_scores_gemma":[0.04466752,0.0001046758,0.00003122384,0.001090883,0.0003050447,0.001696122,0.0005358447,0.0001933728,8.996916e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004124814,"about_ca_system_score_gemma":0.0004204338,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04140707,"about_ca_topic_score_gemma":0.0318436,"domain_scores_codex":[0.988903,0.007876519,0.0006763921,0.0005074356,0.001736174,0.0003004074],"domain_scores_gemma":[0.9907472,0.007854765,0.0004851854,0.0002035532,0.0005643895,0.0001449635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001374803,0.00005443177,0.9901475,0.000001325158,0.00002382845,9.163771e-7,0.004478661,0.001361906,0.00006338189,0.0006685194,0.0002336102,0.001591122],"study_design_scores_gemma":[0.0005599608,0.00005139721,0.9935148,0.00001426917,0.000004943797,0.000002295466,0.001362231,0.001285752,0.00001085086,0.002639255,0.0004449464,0.0001092997],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9919427,0.00001941659,0.002758127,0.001094074,0.001268082,0.00045712,0.002396989,0.000008414306,0.0000550904],"genre_scores_gemma":[0.9960713,0.00002128665,0.00196348,0.00006668068,0.00008708389,0.00002817587,0.001650196,0.000007505136,0.0001042367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02269482,"threshold_uncertainty_score":0.9858227,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890787836","doi":"10.23889/ijpds.v3i3.443","title":"Multi-province epidemiological research using linked administrative data: a case study from Canada.","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Institut universitaire en santé mentale de Montréal; Cégep Marie-Victorin; Centre for Addiction and Mental Health; Women's College Hospital; University of Toronto; Manitoba Health; South Health Campus; Simon Fraser University; University of Manitoba; Alberta Hospital Edmonton","funders":"","keywords":"Comparability; Context (archaeology); Scope (computer science); Government (linguistics); Business; Investment (military); Information system; Health care; Data collection; Minimum Data Set; Data science; Computer science; Political science; Geography; Medicine; Politics","retraction":null,"screen_n_in":null,"score":{"opus":0.6286096928129259,"gpt":0.5941129252567702,"spread":0.03449676755615572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005771622,0.0001446144,0.0002645235,0.0002406977,0.0008279444,0.0002861487,0.002900881,0.00004289058,0.00008644802],"category_scores_gemma":[0.01453124,0.0001153439,0.00002667766,0.00040623,0.0005455995,0.001982545,0.001627033,0.0003890333,0.000007691299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007040693,"about_ca_system_score_gemma":0.004058907,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3733717,"about_ca_topic_score_gemma":0.5423651,"domain_scores_codex":[0.9959099,0.000284639,0.000686144,0.0009369647,0.001789976,0.000392428],"domain_scores_gemma":[0.9948595,0.0006660337,0.0003522903,0.001467971,0.002248083,0.0004061137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001139145,0.001081475,0.9587008,0.00001011298,0.0003146401,0.008953528,0.000301017,0.0001121367,0.002871387,0.0001340296,0.01392296,0.01245874],"study_design_scores_gemma":[0.00198196,0.0003549618,0.6179779,0.0001024158,0.00005939305,0.003155086,0.001880427,0.3684755,0.00003476468,0.0001384884,0.005629288,0.0002099038],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786015,0.00003986964,0.008356747,0.0008454478,0.001794092,0.0007080091,0.009609832,0.00002256786,0.00002198124],"genre_scores_gemma":[0.9552788,0.000005492739,0.04032011,0.0002568855,0.001397922,0.000005118544,0.002677404,0.00001104621,0.00004726158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3683633,"threshold_uncertainty_score":0.9937698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4212784128","doi":"10.23889/ijpds.v5i4.1697","title":"Validating the QCOVID risk prediction algorithm for risk of mortality from COVID-19 in the adult population in Wales, UK.","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Immune responses and vaccinations","field":"Immunology and Microbiology","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"NIHR Leicester Biomedical Research Centre; Engineering and Physical Sciences Research Council; Welsh Ambulance Services NHS Trust; Health and Social Care Research and Development Division; Public Health Agency; Queen's University Belfast; Wales Institute of Social and Economic Research and Data; University of Oxford; Queen's University; Economic and Social Research Council; Swansea University; University of Leicester; Medical Research Council; Department of Health and Social Care; Queen Mary University of London; National Institute for Health and Care Research; Scottish Government; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Public Health Wales; Wellcome Trust; University College London; British Heart Foundation; Llywodraeth Cymru; Cardiff University; London School of Hygiene and Tropical Medicine; UK Research and Innovation; Health and Care Research Wales; Imperial College London","keywords":"Medicine; Population; Brier score; Retrospective cohort study; Demography; Cohort; Coronavirus disease 2019 (COVID-19); Cohort study; Pandemic; Risk assessment; Algorithm; Computer science; Machine learning; Disease; Environmental health; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.06150108544015832,"gpt":0.3861917306243675,"spread":0.3246906451842091,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005959176,0.00009167068,0.0001271084,0.0003229433,0.001276307,0.00008971231,0.001696248,0.0000448189,0.00009159847],"category_scores_gemma":[0.004444296,0.00006501889,0.00007447707,0.0004019009,0.00008565449,0.0006346149,0.0002709535,0.0003840913,8.846612e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003936734,"about_ca_system_score_gemma":0.0002166225,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01800576,"about_ca_topic_score_gemma":0.002131857,"domain_scores_codex":[0.9979116,0.0006039048,0.0006958443,0.0002935741,0.0003046958,0.0001904372],"domain_scores_gemma":[0.9973629,0.001183332,0.0008039441,0.0003929243,0.000239642,0.00001726074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003217563,0.0001796952,0.9318564,0.000003684713,0.00009812157,0.00000131296,0.001407787,0.01803641,0.001202032,0.00310479,0.001249269,0.04253875],"study_design_scores_gemma":[0.001640894,0.00008080203,0.9061658,0.00001295682,0.00004901668,0.00004589047,0.001688526,0.07732421,0.00008236316,0.008590882,0.004235562,0.00008307312],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9344309,0.000219958,0.04895058,0.001117402,0.002157622,0.000646813,0.01246036,0.000009849507,0.000006530241],"genre_scores_gemma":[0.9930899,0.0000817874,0.001425963,0.0001801211,0.00009057464,0.00008099787,0.00501683,0.000005763623,0.00002811118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05928781,"threshold_uncertainty_score":0.9885334,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008599113","doi":"10.23889/ijpds.v5i1.1145","title":"The Mortality After Release from Incarceration Consortium (MARIC): Protocol for a multi-national, individual participant data meta-analysis","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Criminal Justice and Corrections Analysis","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Provincial Health Services Authority; McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Economic and Social Research Council; World Health Organization","keywords":"Protocol (science); Meta-analysis; Computer science; Medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.7107215386385041,"gpt":0.5645774302861782,"spread":0.1461441083523258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005020518,0.000141109,0.0002859332,0.0002156191,0.002157794,0.002036864,0.003578996,0.00005091884,0.0002559901],"category_scores_gemma":[0.007521336,0.0001027837,0.0003282464,0.0009724244,0.000342315,0.003261255,0.0005885157,0.0001594051,0.000007043276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000105216,"about_ca_system_score_gemma":0.0007930768,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005993094,"about_ca_topic_score_gemma":0.03201506,"domain_scores_codex":[0.9957833,0.0002063927,0.000788738,0.0006856023,0.002229908,0.0003060935],"domain_scores_gemma":[0.995957,0.000618699,0.0006400654,0.000627198,0.001903103,0.0002539722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00667535,0.003336043,0.1746015,0.0001132421,0.3973625,0.00006377131,0.05352298,0.06514375,0.0005242702,0.05798567,0.09150251,0.1491684],"study_design_scores_gemma":[0.0007956678,0.00004392149,0.02503046,0.000005438563,0.07536034,0.00000181472,0.008461843,0.8013542,0.00001342914,0.001342507,0.08728579,0.0003046431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03172538,0.0003471628,0.8224364,0.04364182,0.002531983,0.06425449,0.03470401,0.0001813719,0.0001774005],"genre_scores_gemma":[0.9612318,0.00002220221,0.01403754,0.001577159,0.001462699,0.01831485,0.003224804,0.00001415847,0.0001147341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9295065,"threshold_uncertainty_score":0.9991413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965977938","doi":"10.23889/ijpds.v4i1.1106","title":"Notches on the dial: a call to action to develop plain language communication with the public about users and uses of health data","year":2019,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of British Columbia; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Call to action; Action (physics); Dial; Computer science; Plain language; Psychology; Linguistics; Engineering; Business; Advertising","retraction":null,"screen_n_in":null,"score":{"opus":0.3586367229366417,"gpt":0.5420807147469173,"spread":0.1834439918102756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01287928,0.00006009782,0.00009044789,0.0001451111,0.0008320878,0.0004207846,0.002607404,0.00001571264,0.00001143078],"category_scores_gemma":[0.004115862,0.00003379396,0.00000900626,0.0005648389,0.0002281287,0.001436375,0.000425215,0.0001074885,0.000003485094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001330914,"about_ca_system_score_gemma":0.0003567601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003281179,"about_ca_topic_score_gemma":0.01012806,"domain_scores_codex":[0.9980145,0.0005106765,0.0002474895,0.0002244793,0.000843425,0.0001594709],"domain_scores_gemma":[0.9975144,0.00101776,0.0003017909,0.0005628866,0.000514856,0.00008835133],"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":[0.000285058,0.0001080539,0.03589005,0.0000159209,0.00008058005,5.743011e-7,0.07106634,0.0003146612,0.001010628,0.3654448,0.01725433,0.508529],"study_design_scores_gemma":[0.0007503546,0.0004345505,0.4064499,0.0003795767,0.00001822751,0.00001788724,0.0760693,0.006533591,0.0002104132,0.002101519,0.5066528,0.0003817778],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7973341,0.00009048507,0.03351772,0.1669795,0.000666693,0.0007526636,0.0003998366,0.00001318621,0.0002457801],"genre_scores_gemma":[0.977978,0.00005527664,0.02021071,0.001424835,0.00008329764,0.00000712968,0.0001090171,0.000005042896,0.0001267126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5081472,"threshold_uncertainty_score":0.6399831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3156103863","doi":"10.23889/ijpds.v6i1.1406","title":"Mapping Three Versions of the International Classification of Diseases to Categories of Chronic Conditions","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"Winnipeg Foundation","keywords":"Schema crosswalk; ICD-10; Diagnosis code; Medical diagnosis; Computer science; Medicine; Data mining; Geography; Population; Pathology; Psychiatry; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.3742762050581117,"gpt":0.5272327507167389,"spread":0.1529565456586273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00117049,0.00005886846,0.0001353209,0.0002809467,0.0005777618,0.00002024799,0.001388201,0.0000440215,0.0002258367],"category_scores_gemma":[0.004400376,0.00004554653,0.00005586351,0.0004801342,0.0001705844,0.0008309072,0.0004396186,0.0001798426,0.00000496948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002909,"about_ca_system_score_gemma":0.001730517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001373044,"about_ca_topic_score_gemma":0.0002083054,"domain_scores_codex":[0.9976472,0.000058781,0.0009348689,0.0001549106,0.001049107,0.0001551183],"domain_scores_gemma":[0.9958547,0.0003558319,0.0009590919,0.0003768257,0.002345325,0.0001081856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002283189,0.0003275762,0.6736937,0.0005000339,0.0001497549,0.000001151699,0.003289791,0.002464836,0.03798388,0.2276594,0.03122883,0.02247272],"study_design_scores_gemma":[0.0006149842,0.00003735111,0.9395033,0.0006948804,0.0000210598,0.000007169767,0.00165388,0.03210879,0.0006555734,0.004423994,0.02020813,0.00007095206],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8587564,0.0001011765,0.09752964,0.02131687,0.01585639,0.0007996601,0.004335906,0.00002176342,0.001282266],"genre_scores_gemma":[0.9972232,0.00003760935,0.001424159,0.000247487,0.0003078867,0.00001301061,0.0006151442,0.000003962863,0.0001275374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2658096,"threshold_uncertainty_score":0.5267978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176469351","doi":"10.23889/ijpds.v6i1.1417","title":"SEEDS of Indigenous Population Health Data Linkage","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"First Nations Health and Social Secretariat of Manitoba; Laurentian University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canadian Institutes of Health Research","keywords":"Linkage (software); Indigenous; Geography; Population; Genetics; Biology; Sociology; Demography; Gene; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.09291446882645245,"gpt":0.4530017228340472,"spread":0.3600872540075947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006130624,0.0001006628,0.0001864365,0.00036417,0.005516765,0.0003917206,0.003275933,0.00007245209,0.00008995493],"category_scores_gemma":[0.0003310782,0.00009477534,0.00004169574,0.0006661,0.0002192525,0.003845236,0.00005350196,0.0001755941,0.00000700609],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005592809,"about_ca_system_score_gemma":0.0202775,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07993927,"about_ca_topic_score_gemma":0.3325344,"domain_scores_codex":[0.9964646,0.0002068527,0.0007722233,0.0004865996,0.001628911,0.0004408348],"domain_scores_gemma":[0.9963893,0.0001551398,0.0008067436,0.0008494753,0.00154044,0.0002588744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001067571,0.001122081,0.1779838,0.0001391612,0.0001682073,0.00002089549,0.1860411,0.0006323751,0.0001252638,0.5596936,0.003396446,0.07057036],"study_design_scores_gemma":[0.000663358,0.00008567411,0.1985572,0.0001968242,0.00002892148,0.0001075115,0.004059036,0.002900035,0.00009452266,0.01054451,0.7824262,0.0003362369],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9450424,0.001047608,0.01675655,0.007649786,0.0207799,0.001294583,0.002677911,0.00009141635,0.004659883],"genre_scores_gemma":[0.9685302,0.00415621,0.01580705,0.0002783508,0.002293774,0.000001113533,0.00736643,0.0000157395,0.001551092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7790298,"threshold_uncertainty_score":0.9957779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081563555","doi":"10.23889/ijpds.v5i1.1351","title":"Individual and neighbourhood socioeconomic status increase risk of avoidable hospitalizations among Canadian adults: A retrospective cohort study of linked population health data","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; University of Guelph","keywords":"Medicine; Socioeconomic status; Population; Neighbourhood (mathematics); Demography; Cohort; Household income; Environmental health; Gerontology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.05890006155872704,"gpt":0.4195591434814562,"spread":0.3606590819227291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003329675,0.0001320436,0.0003881157,0.0004301736,0.001272558,0.00007272435,0.001564949,0.00007315232,0.0001235851],"category_scores_gemma":[0.002861762,0.0001282749,0.00002805527,0.0003143929,0.0001089634,0.002692263,0.0006927051,0.0004120995,0.00000233768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001134094,"about_ca_system_score_gemma":0.003299856,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5623971,"about_ca_topic_score_gemma":0.3849643,"domain_scores_codex":[0.9967108,0.0002780151,0.001278592,0.0005436778,0.0007788605,0.0004101062],"domain_scores_gemma":[0.9958975,0.0002448873,0.001828465,0.0005855695,0.0008637116,0.000579865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007139148,0.00006134179,0.9929647,0.0000359489,0.00008466434,6.407863e-7,0.002535347,0.00009690479,0.000001046754,0.0005295181,0.00247749,0.001140972],"study_design_scores_gemma":[0.001390448,0.0002459418,0.9798164,0.00005822709,0.0000560015,0.000001355225,0.002584673,0.01502117,1.751252e-7,0.0004011925,0.0003215934,0.0001028056],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825875,0.00006768583,0.0004897522,0.002686078,0.0008759989,0.001552276,0.01165951,0.00001659878,0.00006463595],"genre_scores_gemma":[0.9913915,0.0002288658,0.00123913,0.001422552,0.0002667897,0.00001833095,0.00540876,0.00001491807,0.000009136706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1774328,"threshold_uncertainty_score":0.9787615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2989899073","doi":"10.23889/ijpds.v4i2.1132","title":"Achieving quality primary care data: a description of the Canadian Primary Care Sentinel Surveillance Network data capture, extraction, and processing in Alberta","year":2019,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Health Sciences Centre; University of Alberta; University of Calgary","funders":"","keywords":"Data extraction; Documentation; Raw data; Data quality; Computer science; Data collection; Automatic identification and data capture; Data science; Data mining; Medicine; Database; MEDLINE; Engineering; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.2909527357169971,"gpt":0.4888541672552275,"spread":0.1979014315382304,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005193072,0.00009837972,0.0001837453,0.0001910601,0.00124828,0.0001433324,0.002344615,0.00009905454,0.00001267866],"category_scores_gemma":[0.001631924,0.00007640447,0.00001387012,0.000338528,0.00009183306,0.004281268,0.0009937094,0.0005648831,0.000002910461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008854155,"about_ca_system_score_gemma":0.00316227,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.09855752,"about_ca_topic_score_gemma":0.4346467,"domain_scores_codex":[0.9971808,0.0002163429,0.0009427501,0.0003982617,0.0009146724,0.0003472025],"domain_scores_gemma":[0.9968905,0.0002510842,0.0009024037,0.0009624037,0.0008320537,0.0001614844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004373896,0.000007633464,0.988712,0.0005730494,0.000003471207,2.514331e-7,0.001321269,0.0002723762,0.00002822704,0.0003000844,0.001030558,0.007707313],"study_design_scores_gemma":[0.0004568723,0.000006061717,0.9656177,0.0008326602,0.000006027236,0.000009702547,0.001034969,0.02018518,1.808503e-7,0.00007231588,0.01169412,0.00008427548],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9729468,0.001107262,0.003765868,0.00558381,0.008795547,0.001643143,0.002719476,0.0000235091,0.003414599],"genre_scores_gemma":[0.9870045,0.00006804211,0.001932526,0.0009749649,0.0004324217,0.000004963855,0.009477524,0.000007797293,0.00009722487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3360891,"threshold_uncertainty_score":0.9600884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206039573","doi":"10.23889/ijpds.v5i4.1682","title":"Pivoting data and analytic capacity to support Ontario’s COVID-19 response","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Health Sciences Centre; Vector Institute; Trillium Health Centre; University of Toronto; University Health Network; Public Health Ontario; Hospital for Sick Children; Sunnybrook Health Science Centre; McMaster University; Women's College Hospital","funders":"Agency for Healthcare Research and Quality","keywords":"Public health; Pandemic; Population; Health care; Analytics; Population health; Public relations; Business; Political science; Environmental health; Coronavirus disease 2019 (COVID-19); Medicine; Nursing; Data science; Computer science; Disease; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.6458393543368621,"gpt":0.5551504100211131,"spread":0.09068894431574903,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01578888,0.0001222852,0.0002110722,0.0003373569,0.001485132,0.0002555309,0.003764311,0.00002030561,0.0003350099],"category_scores_gemma":[0.06925625,0.0001078978,0.00003411615,0.0003481382,0.000146602,0.00124975,0.0054867,0.0002755714,0.000003361032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001613562,"about_ca_system_score_gemma":0.0006223646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005917625,"about_ca_topic_score_gemma":0.01071506,"domain_scores_codex":[0.9970167,0.0001997204,0.0006181971,0.0006880952,0.001188069,0.000289223],"domain_scores_gemma":[0.9954477,0.002732769,0.0004176866,0.0008300866,0.0002375214,0.0003342176],"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":[0.002240949,0.0003363244,0.7928723,0.00004580905,0.0002271803,0.0001083177,0.004676656,0.007501139,0.00101947,0.04432713,0.1388694,0.007775351],"study_design_scores_gemma":[0.001281634,0.0004720372,0.3057705,0.00002961038,0.00008611905,0.0007402432,0.0007641385,0.07551602,0.00000839431,0.1462155,0.468598,0.0005177455],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8987742,0.00001196225,0.07503817,0.02166373,0.001450231,0.0004106813,0.002554889,0.00004747061,0.00004865149],"genre_scores_gemma":[0.9624501,0.000003283238,0.0329342,0.003911045,0.0001493993,0.00001444357,0.0002490505,0.000008358749,0.0002801067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4871017,"threshold_uncertainty_score":0.9998148,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901139437","doi":"10.23889/ijpds.v3i3.441","title":"Expanding the impact of a longstanding Canadian cardiac registry through data linkage: challenges and opportunities","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Calgary Laboratory Services; Alberta Children's Hospital; Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"","keywords":"Medicine; Cardiac catheterization; Cohort; Record linkage; Data collection; Work (physics); Disease registry; Disease; Cohort study; Coronary artery disease; Medical emergency; Intensive care medicine; Environmental health; Surgery; Cardiology; Internal medicine; Engineering; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.474061428872933,"gpt":0.5621709100179619,"spread":0.08810948114502898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003641096,0.00009146617,0.0001623291,0.0002110476,0.001616957,0.00009354844,0.002202898,0.00005783432,0.00007605664],"category_scores_gemma":[0.001168475,0.00006071527,0.0000326157,0.0001002799,0.0003124647,0.002737775,0.0007521758,0.0002614939,0.000002581519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006186758,"about_ca_system_score_gemma":0.003120638,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03965475,"about_ca_topic_score_gemma":0.0182162,"domain_scores_codex":[0.9982893,0.0001076032,0.0004734268,0.0002788907,0.0005018629,0.0003488999],"domain_scores_gemma":[0.997515,0.0003889762,0.0004475524,0.0007734426,0.00068645,0.0001886012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003987799,0.00006145423,0.3108416,0.0002765098,0.0005429939,0.0000426977,0.02461044,0.00002156627,0.0006646647,0.09537671,0.2578368,0.3093258],"study_design_scores_gemma":[0.001001479,0.0002415,0.677946,0.0006643981,0.00007571937,0.0001892717,0.0137666,0.00434463,0.00001902643,0.01210907,0.2892452,0.0003970941],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7878951,0.01115724,0.006224036,0.1164643,0.02687608,0.002189238,0.01971779,0.00009158282,0.0293847],"genre_scores_gemma":[0.9906835,0.005011759,0.001191967,0.000914899,0.001461717,0.000004325176,0.0005451904,0.000009597778,0.0001770458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3671045,"threshold_uncertainty_score":0.9996988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890386437","doi":"10.23889/ijpds.v3i4.913","title":"Access to palliative care in Canada","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Palliative Care and End-of-Life Issues","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Canadian Institute for Health Information","funders":"","keywords":"Palliative care; Medicine; Health care; Emergency department; End-of-life care; Intensive care; Acute care; Family medicine; Medical emergency; Nursing; Gerontology; Intensive care medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.3086607104873588,"gpt":0.5490978795579466,"spread":0.2404371690705879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002662361,0.00005790951,0.0001104451,0.0002575257,0.00007445143,0.0000647276,0.001004262,0.00001278349,0.00004570449],"category_scores_gemma":[0.00121821,0.00004919844,0.0000167843,0.0003348106,0.00005884353,0.0008159369,0.0002141835,0.00006674248,0.000002531677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008092555,"about_ca_system_score_gemma":0.001381555,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2987562,"about_ca_topic_score_gemma":0.6739876,"domain_scores_codex":[0.998663,0.000008940151,0.0002760751,0.0001975804,0.0007141127,0.000140255],"domain_scores_gemma":[0.9982366,0.00005873536,0.0001330068,0.0001915143,0.001263361,0.0001167817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001635671,0.00001221824,0.9805794,0.000007440918,0.0000143334,0.00000972113,0.0008141679,0.0001098542,0.0003228165,0.0002288871,0.002169217,0.01556839],"study_design_scores_gemma":[0.0006788801,0.0001117403,0.9492783,0.0004783461,0.000009526048,0.000009981569,0.001225403,0.003305538,0.003048564,0.0002068269,0.0415591,0.00008781581],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917997,0.0001013286,0.00303338,0.001981811,0.002048847,0.0001979775,0.0003451198,0.00000394198,0.000487917],"genre_scores_gemma":[0.9925824,0.0000388632,0.006105467,0.0007038914,0.0003772081,0.000002899553,0.0001581159,0.000004040666,0.00002705504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3752314,"threshold_uncertainty_score":0.7059134,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3107106297","doi":"10.23889/ijpds.v5i1.1374","title":"The SPOR-Canadian Data Platform: a national initiative to facilitate data rich multi-jurisdictional research","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Public Health Policies and Education","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Manitoba; University of British Columbia; Canadian Institute for Health Information; Université de Sherbrooke; Sunnybrook Hospital; University Health Network; University of New Brunswick; University of Toronto; Laurentian University; Institute for Clinical Evaluative Sciences; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Jurisdiction; Health care; Research data; Public relations; Population; Political science; Medicine; Data science; Computer science; Environmental health; Data curation; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.8477296566595001,"gpt":0.6540354937349164,"spread":0.1936941629245836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.01907116,0.0001450649,0.0001500086,0.0006388673,0.006867431,0.0005351788,0.01113892,0.00009303077,0.0002143579],"category_scores_gemma":[0.02491763,0.0001134836,0.00002071266,0.001260173,0.000261404,0.006283298,0.003582827,0.001009892,0.000393444],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260528,"about_ca_system_score_gemma":0.01144721,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02435611,"about_ca_topic_score_gemma":0.0406726,"domain_scores_codex":[0.9940088,0.0003150894,0.001017401,0.0008689103,0.002793363,0.0009963808],"domain_scores_gemma":[0.9905681,0.001754164,0.0003982023,0.001462465,0.004574513,0.001242535],"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":[0.000147835,0.00005017683,0.01398859,0.00001711993,0.0000517165,0.00000238033,0.004287124,0.0002422169,0.00002778927,0.01557295,0.9549725,0.01063962],"study_design_scores_gemma":[0.0004351503,0.00003851256,0.06857409,0.00004496812,0.000004521799,0.00001023473,0.002803835,0.1311532,5.055631e-7,0.001887418,0.7949318,0.000115813],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.04770182,0.0001892764,0.03603979,0.796338,0.02324973,0.003815343,0.0873806,0.0001170147,0.005168369],"genre_scores_gemma":[0.880255,0.0003652405,0.0237652,0.03653906,0.01299536,0.0001812485,0.04400085,0.00005866375,0.001839423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8325531,"threshold_uncertainty_score":0.9944255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2900610889","doi":"10.23889/ijpds.v3i1.451","title":"Longitudinal child data: What can be gained by linking administrative data and cohort data?","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal; Research Unit on Children's Psychosocial Maladjustment; Statistics Canada","funders":"","keywords":"Record linkage; Linkage (software); Cohort; False positive paradox; Psychological intervention; Cohort study; Longitudinal data; Population; Longitudinal study; Actuarial science; Medicine; Psychology; Environmental health; Statistics; Computer science; Business; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.5285046649674737,"gpt":0.5641351279824764,"spread":0.03563046301500272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.04720439,0.0001365869,0.0001716791,0.0001966955,0.00230628,0.00167606,0.01079482,0.00008422964,0.00009717789],"category_scores_gemma":[0.02734369,0.0001274393,0.00001318329,0.000360768,0.001511944,0.0153607,0.003617496,0.0002612505,0.000003920671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000100598,"about_ca_system_score_gemma":0.0007711916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001564813,"about_ca_topic_score_gemma":0.01034521,"domain_scores_codex":[0.9956863,0.001113077,0.0004533453,0.001104607,0.001277502,0.0003651826],"domain_scores_gemma":[0.99432,0.002344913,0.0004306726,0.002020954,0.0006364221,0.0002470106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003370865,0.0003039872,0.7979608,0.00001101274,0.0005019813,0.00006073975,0.00505831,0.000008789206,0.0006800009,0.009414043,0.1006663,0.08196328],"study_design_scores_gemma":[0.001136253,0.0001787727,0.4829088,0.0002358109,0.0001343504,0.0003448766,0.004005072,0.03065522,0.000133242,0.002185302,0.4774781,0.0006041916],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6988325,0.001472284,0.123892,0.06982984,0.03079794,0.00161074,0.07217151,0.0001550898,0.00123807],"genre_scores_gemma":[0.9457677,0.0009320791,0.01979171,0.000987541,0.002569531,0.000002946173,0.02971505,0.00001269895,0.0002207186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3768118,"threshold_uncertainty_score":0.9993603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3049257903","doi":"10.23889/ijpds.v5i1.1150","title":"Effect of Study Duration and Outcome Measurement Frequency on Estimates of Change for Longitudinal Cohort Studies in Routinely-Collected Administrative Data","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Manitoba Health; University of Manitoba; CancerCare Manitoba","funders":"University of Manitoba","keywords":"Cohort; Statistics; Duration (music); Cohort study; Linear regression; Demography; Medicine; Longitudinal study; Repeated measures design; Standard error; Regression analysis; Psychology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.88409621524642,"gpt":0.6454970174625501,"spread":0.23859919778387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04189762,0.00008660344,0.0002536287,0.0001955116,0.0002883827,0.00005063897,0.001030667,0.00003030311,0.000005719801],"category_scores_gemma":[0.112213,0.00007039258,0.0000215951,0.000349754,0.0003111119,0.001185116,0.0001812931,0.000081589,1.745766e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001138105,"about_ca_system_score_gemma":0.0001828575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005567912,"about_ca_topic_score_gemma":0.002155853,"domain_scores_codex":[0.9968128,0.001147679,0.0006322635,0.0003659036,0.0009061001,0.0001352275],"domain_scores_gemma":[0.994103,0.004258535,0.0005173256,0.0002081391,0.0008492356,0.00006375112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002777112,0.00008522387,0.9914028,0.00001835569,0.000095832,0.000002668816,0.00291216,0.00001115263,0.0003961985,0.0006125968,0.0000355087,0.001650405],"study_design_scores_gemma":[0.001008661,0.001129358,0.992891,0.00006056326,0.00005826947,0.000002558864,0.001030597,0.002882162,0.0004006083,0.0004411739,0.00002171272,0.00007338697],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935142,0.0000879592,0.002834189,0.001123664,0.000778261,0.001173047,0.0004700398,0.000006678079,0.00001190171],"genre_scores_gemma":[0.9955077,0.00002830452,0.004166248,0.00002908173,0.0001328167,0.00003142298,0.00009871307,0.000003368901,0.000002393761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07031533,"threshold_uncertainty_score":0.986568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386888372","doi":"10.23889/ijpds.v8i4.2142","title":"Essential requirements for the governance and management of data trusts, data repositories, and other data collaborations","year":2023,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Research Data Management Practices","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of British Columbia; University of Toronto; Université de Sherbrooke; Health Sciences Centre; Centre for Addiction and Mental Health; North York General Hospital; St. Michael's Hospital; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Public Health Agency of Canada; St. Paul's Hospital; Diabetes Canada; University of New Brunswick; Indoc Research; Vector Institute","funders":"Canadian Institutes of Health Research","keywords":"Data governance; Corporate governance; Stakeholder; Data management; Data sharing; Computer science; Business; Engineering; Political science; Public relations; Operations management; Data quality; Finance; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.3443295514248307,"gpt":0.4959817831033048,"spread":0.1516522316784741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.007250003,0.0001023598,0.0001037754,0.0001630815,0.0007237981,0.004348347,0.02727944,0.00001897629,0.000003011103],"category_scores_gemma":[0.001975407,0.00008044591,0.000007744201,0.0008148894,0.0002275601,0.06922189,0.02671198,0.00008676236,0.000001160982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004302723,"about_ca_system_score_gemma":0.0001685239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002549242,"about_ca_topic_score_gemma":0.0002264053,"domain_scores_codex":[0.9966263,0.00005085731,0.0004856134,0.001056556,0.001534705,0.0002459265],"domain_scores_gemma":[0.9928012,0.0004527681,0.0005878474,0.00569497,0.0003821534,0.00008103732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001808106,0.0001434133,0.01016171,0.0001595051,0.0006471059,0.00002626235,0.0001333935,0.0002665177,0.0004897859,0.7090134,0.1477572,0.1310209],"study_design_scores_gemma":[0.0004869152,0.00002273424,0.01897346,0.00006319433,0.00004658144,0.00002188982,0.0001110996,0.6084289,0.0000150478,0.0009621468,0.3707704,0.00009761436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001782524,0.000489359,0.9476822,0.01738743,0.003740143,0.001238638,0.02750972,0.00004774836,0.0001222061],"genre_scores_gemma":[0.26402,0.02356311,0.6703753,0.0006519221,0.002010376,0.00008692658,0.03668428,0.00005765575,0.002550488],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7080513,"threshold_uncertainty_score":0.9966852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3204448007","doi":"10.23889/ijpds.v6i1.1686","title":"Multigenerational Health Research using Population-Based Linked Databases: An International Review","year":2021,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Manitoba Health; University of Manitoba","funders":"Canadian Institutes of Health Research; European Commission","keywords":"Population; Geography; Database; Population health; Construct (python library); Health care; Environmental health; Medicine; Economic growth; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.7325304048142112,"gpt":0.6767003649026033,"spread":0.05583003991160784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.02238853,0.0003496945,0.001071063,0.001282715,0.004074357,0.001856504,0.005956075,0.000173767,0.0005859522],"category_scores_gemma":[0.01375376,0.0003311163,0.0003243072,0.001375897,0.0003539853,0.00574166,0.0006530739,0.0008855978,0.00001436679],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003592965,"about_ca_system_score_gemma":0.01620183,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01757106,"about_ca_topic_score_gemma":0.005306363,"domain_scores_codex":[0.9887092,0.001659614,0.002157075,0.001207713,0.005271599,0.0009948298],"domain_scores_gemma":[0.9913747,0.001230583,0.001587737,0.00112649,0.003844649,0.0008358413],"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":[0.00001239094,0.0002607589,0.002647046,0.003576695,0.0001259308,0.00001989163,0.0001639126,0.0003099189,1.558347e-7,0.05325262,0.009686811,0.9299439],"study_design_scores_gemma":[0.0002030917,0.0000164562,0.0007147593,0.02278649,0.0000604432,0.0000390182,0.0001213687,0.005298247,2.91862e-8,0.00012046,0.9703271,0.0003125342],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002909741,0.9669788,0.00536623,0.006876145,0.01396787,0.001827749,0.004794358,0.00005600374,0.0001037099],"genre_scores_gemma":[0.00006649356,0.9369887,0.02515672,0.00259327,0.004671625,0.00005740285,0.03023212,0.00004540079,0.0001882435],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9606403,"threshold_uncertainty_score":0.9999141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4206902948","doi":"10.23889/ijpds.v7i1.1701","title":"Closing the loop: From system-based data to evidence-influenced policy and practice","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Manitoba; Manitoba Health","funders":"","keywords":"Work (physics); Evidence-based policy; Government (linguistics); Public relations; Population; Research policy; Data sharing; Political science; Public administration; Sociology; Engineering; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2677070467198933,"gpt":0.5371566112385167,"spread":0.2694495645186234,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009591267,0.00007029757,0.00009146702,0.000208422,0.004018392,0.001192243,0.00464367,0.0000179755,0.00004773926],"category_scores_gemma":[0.02555161,0.00005689183,0.00001873134,0.0005322697,0.0001915665,0.004421588,0.001368193,0.0001754745,0.000003793962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007457155,"about_ca_system_score_gemma":0.001757464,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05206061,"about_ca_topic_score_gemma":0.002030084,"domain_scores_codex":[0.9967414,0.0003501324,0.0003659362,0.0003885509,0.001849989,0.0003040026],"domain_scores_gemma":[0.9958832,0.00251121,0.000324903,0.0006156812,0.000439835,0.0002251756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001530286,0.0002592744,0.1693998,0.00008436456,0.0001719529,0.00007066243,0.01725765,0.02045261,0.0006635577,0.5749792,0.05928791,0.1558426],"study_design_scores_gemma":[0.0005204775,0.00005966966,0.1067608,0.000277844,0.00004721256,0.00007744853,0.01940521,0.065635,0.000006147012,0.001428054,0.8055152,0.0002669799],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2572145,0.0008883129,0.02129662,0.6982001,0.01420054,0.001577762,0.0054726,0.0001055933,0.001043906],"genre_scores_gemma":[0.9798827,0.00006002067,0.006875785,0.01146249,0.001419336,0.00001451781,0.0001894994,0.000006392021,0.00008921542],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7462273,"threshold_uncertainty_score":0.9998446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891961677","doi":"10.23889/ijpds.v3i3.431","title":"A Pan-Canadian Data Resource for Monitoring Child Developmental Health: The Canadian Neighbourhoods Early Child Development (CanNECD) Database","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Saskatchewan; Saskatchewan Health; Saskatchewan Health Authority; Manitoba Health; Learning Partnership; University of Manitoba; University of British Columbia; McMaster University","funders":"","keywords":"Socioeconomic status; Geography; Database; Population; Census; Neighbourhood (mathematics); Record linkage; Context (archaeology); Environmental health; Medicine; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.140514140808634,"gpt":0.4312693904114818,"spread":0.2907552496028478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.006629932,0.0001436952,0.0001402529,0.0004376982,0.01278228,0.00158811,0.005632964,0.00005925976,0.00007245702],"category_scores_gemma":[0.002264066,0.0001213111,0.00003065843,0.0004100979,0.0003638691,0.002988164,0.0004620636,0.0002471135,0.00001810376],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002340813,"about_ca_system_score_gemma":0.01063557,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8700641,"about_ca_topic_score_gemma":0.9868929,"domain_scores_codex":[0.9965483,0.00007933912,0.0005865202,0.0005368437,0.001231368,0.001017626],"domain_scores_gemma":[0.997286,0.0001641686,0.0002936465,0.0005667015,0.0005810272,0.001108483],"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":[0.0001331205,0.00009589705,0.4321519,0.0000560217,0.0001889629,0.00001351396,0.02123241,0.00003397524,0.000002942915,0.09346477,0.0874023,0.3652242],"study_design_scores_gemma":[0.0002066174,0.00001450795,0.2883768,0.0001454629,0.000003973888,0.00002103829,0.001310583,0.0005256901,0.000004667313,0.0001420205,0.7091158,0.0001328381],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1312846,0.001076592,0.01277626,0.7654237,0.03860545,0.006305104,0.0241118,0.0001789806,0.02023756],"genre_scores_gemma":[0.9689289,0.00006312638,0.01947422,0.005841026,0.003655112,0.0000227887,0.001760344,0.00001848294,0.0002359393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8376443,"threshold_uncertainty_score":0.999747,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901669259","doi":"10.23889/ijpds.v3i3.440","title":"Lessons Learned: It Takes a Village to Understand Inter-Sectoral Care Using Administrative Data across Jurisdictions","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"CancerCare Manitoba; Nova Scotia Health Authority; University Health Network; University of Toronto; CARE Canada; Dalhousie University; University of Manitoba; BC Cancer Agency; Cancer Care Ontario; Queen's University","funders":"","keywords":"Documentation; Health care; Comparability; Population; Breast cancer; Cancer registry; Data dictionary; Medicine; Cancer; Business; Family medicine; Geography; Computer science; Political science; Environmental health; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.6811977416736362,"gpt":0.6086569179741187,"spread":0.07254082369951753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009807623,0.0001308324,0.0001589923,0.0002220434,0.0008907624,0.00064325,0.002023979,0.0000460081,0.00009135032],"category_scores_gemma":[0.001208561,0.0001169944,0.00004384275,0.0004416898,0.0003043737,0.002824186,0.0006401535,0.0001838186,0.00001346388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006074863,"about_ca_system_score_gemma":0.0006701899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006729342,"about_ca_topic_score_gemma":0.003422395,"domain_scores_codex":[0.9975797,0.0000227072,0.0004069592,0.0005929359,0.001060774,0.0003369524],"domain_scores_gemma":[0.997327,0.00004941177,0.0002249028,0.0007489158,0.001369482,0.0002802912],"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":[0.00935782,0.0008074059,0.3786651,0.0001669828,0.001412282,0.0006208767,0.08360801,0.004021956,0.06058348,0.01866007,0.1090765,0.3330195],"study_design_scores_gemma":[0.006903794,0.003873634,0.2141149,0.003320917,0.0005154594,0.005464882,0.1486752,0.2486282,0.00355395,0.002710527,0.3604677,0.001770913],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.686147,0.0001050384,0.2854566,0.01473291,0.005072606,0.0005672975,0.006775241,0.00005554431,0.001087774],"genre_scores_gemma":[0.9768488,0.00001099677,0.02016678,0.0008503541,0.001236322,0.000001685713,0.0007750768,0.00001143976,0.00009856095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3312486,"threshold_uncertainty_score":0.6851114,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891009223","doi":"10.23889/ijpds.v5i1.1343","title":"Can Linked Electronic Medical Record and Administrative Data Help Us Identify Those Living with Frailty?","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Frailty in Older Adults","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Calgary; University of Manitoba; University of British Columbia","funders":"","keywords":"Demographics; Medicine; Medical record; Population; Electronic medical record; Health care; Health data; Gerontology; Demography; Medical emergency; Environmental health; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.160259386906965,"gpt":0.4435024283304713,"spread":0.2832430414235064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001217443,0.0001378397,0.0001848513,0.0001481065,0.0002506376,0.0003624201,0.002129492,0.00005756871,0.0001641715],"category_scores_gemma":[0.00724503,0.0001101325,0.00002168024,0.0002902621,0.0002487981,0.002123104,0.0007892064,0.0004557621,0.000005266993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00016239,"about_ca_system_score_gemma":0.001303006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000236291,"about_ca_topic_score_gemma":0.001242369,"domain_scores_codex":[0.9968563,0.00003722177,0.0004360694,0.0006300691,0.001735229,0.0003050527],"domain_scores_gemma":[0.9979348,0.0002423947,0.0002814112,0.0005438846,0.0004982369,0.0004993016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000971581,0.0003349813,0.7929959,0.00009885639,0.0005366615,0.0003056692,0.00173683,0.00005224582,0.002880916,0.003548894,0.01678049,0.1797569],"study_design_scores_gemma":[0.003089206,0.001301186,0.7480406,0.001235609,0.00015841,0.003288586,0.000587718,0.2106804,0.0001255876,0.0008442642,0.03021595,0.0004324968],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8947057,0.0001584205,0.02547238,0.07639281,0.001383094,0.0005983088,0.001049031,0.00006939722,0.0001708445],"genre_scores_gemma":[0.9884551,0.0001730768,0.007435245,0.00181992,0.0009340796,0.000004390939,0.001050787,0.00001529873,0.0001120653],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2106281,"threshold_uncertainty_score":0.8673501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3129961804","doi":"10.23889/ijpds.v6i1.1407","title":"Use of administrative record linkage to measure medical and social risk factors for early developmental vulnerability in Ontario, Canada","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Institute for Clinical Evaluative Sciences; Hospital for Sick Children; McMaster University; University of Toronto","funders":"","keywords":"Medical record; Population; Concordance; Vulnerability (computing); Record linkage; Residence; Medicine; Demography; Psychology; Gerontology; Environmental health; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.485136854754962,"gpt":0.4814978207620087,"spread":0.003639033992953344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006223134,0.00008309659,0.0001761596,0.0002012706,0.0003143885,0.0005349795,0.001464283,0.0000363927,0.0001617668],"category_scores_gemma":[0.02476783,0.00006870209,0.0000335421,0.0003106715,0.0001058956,0.00205383,0.0005824234,0.000167809,4.950027e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004920113,"about_ca_system_score_gemma":0.002942187,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6119447,"about_ca_topic_score_gemma":0.9866593,"domain_scores_codex":[0.9957493,0.0001317442,0.0008077153,0.0004679415,0.002675541,0.0001677664],"domain_scores_gemma":[0.9970105,0.001203998,0.0003664862,0.0002155599,0.001046976,0.0001565138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001947285,0.00009999465,0.9307928,0.00000422215,0.0000387058,0.0000140612,0.00170134,0.00007327213,0.0000674438,0.002728905,0.005824177,0.05846035],"study_design_scores_gemma":[0.000339984,0.00003695442,0.9611774,0.00002353011,0.000005873716,0.000009383715,0.001192071,0.001179928,0.0001090608,0.003089428,0.0327403,0.00009605643],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.973317,0.000001896779,0.02112836,0.002034239,0.001220074,0.0002019148,0.00207072,0.000002121707,0.00002371789],"genre_scores_gemma":[0.9851521,0.000002108267,0.01407123,0.0002462538,0.00005049428,0.000005085031,0.0002911317,0.000002704203,0.0001788972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3747147,"threshold_uncertainty_score":0.983447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3107592974","doi":"10.23889/ijpds.v5i3.1369","title":"Impact through Engagement","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Economic and Social Research Council; Queen's University; Ulster University; Queen's University Belfast; Health and Social Care Northern Ireland; UK Research and Innovation","keywords":"Public engagement; General partnership; Publics; Public relations; Work (physics); Key (lock); Community engagement; Business; Political science; Knowledge management; Computer science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.5733097696198401,"gpt":0.5698511322761074,"spread":0.003458637343732751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005096086,0.0000997204,0.0001294005,0.0002576902,0.0005261045,0.001557961,0.004199477,0.00002581902,0.000282916],"category_scores_gemma":[0.008333358,0.00007062548,0.0001050103,0.0008136348,0.00009902214,0.005203754,0.0004431965,0.0001522805,0.0000754911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007320975,"about_ca_system_score_gemma":0.000176662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006152542,"about_ca_topic_score_gemma":0.000008624264,"domain_scores_codex":[0.995339,0.00006745777,0.0007128512,0.0005415028,0.003121188,0.0002179834],"domain_scores_gemma":[0.9971684,0.0003113193,0.0004639093,0.0004601449,0.001401251,0.0001949325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006476931,0.0002663375,0.2426414,0.000005778903,0.0002003095,0.00002778665,0.00428444,0.1063574,0.005488085,0.05699373,0.1066406,0.4764464],"study_design_scores_gemma":[0.0007542807,0.0001570116,0.09699062,0.00001600787,0.00001713119,0.00005105095,0.0006621483,0.7754239,0.00005000569,0.05863683,0.06702655,0.0002144545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3571129,0.00004729986,0.6259856,0.01187531,0.003500433,0.0001978979,0.0004271822,0.00004499678,0.0008084681],"genre_scores_gemma":[0.9811763,0.00003629689,0.01701493,0.001025777,0.0005309057,0.00000240294,0.000159887,0.000006456413,0.00004709532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6690665,"threshold_uncertainty_score":0.9994785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891132725","doi":"10.23889/ijpds.v3i4.1033","title":"Development and Characteristics of the Provincial Overdose Cohort in British Columbia, Canada","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Opioid Use Disorder Treatment","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Ministry of Health; Provincial Health Services Authority; BC Centre for Disease Control","funders":"","keywords":"Opioid overdose; Medicine; Coroner; Medical emergency; Emergency medicine; Drug overdose; Cohort; Emergency department; Psychological intervention; Medical prescription; Population; Public health; Polysubstance dependence; Poison control; Family medicine; Suicide prevention; Environmental health; Opioid; Substance abuse; Psychiatry; (+)-Naloxone; Nursing","retraction":null,"screen_n_in":null,"score":{"opus":0.01982517065981657,"gpt":0.3052223206039213,"spread":0.2853971499441047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003405505,0.00003373688,0.00007972466,0.00003918503,0.0001527376,0.0001297144,0.0003661574,0.00001285515,0.00001739066],"category_scores_gemma":[0.0004381414,0.00003612433,0.000008823471,0.0001089751,0.0001038084,0.0002810332,0.000168855,0.00005098301,1.910552e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003395959,"about_ca_system_score_gemma":0.001653535,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4401268,"about_ca_topic_score_gemma":0.9184994,"domain_scores_codex":[0.9988635,0.000006434248,0.0002793867,0.00014971,0.000605949,0.00009504232],"domain_scores_gemma":[0.9992815,0.00001423711,0.0001588871,0.0001410593,0.0003548702,0.00004946817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001319111,0.00004006366,0.9775039,0.000004770091,0.00001192256,0.000004966576,0.00006875501,3.050861e-7,0.00009591316,0.00002174587,0.0003121135,0.02192238],"study_design_scores_gemma":[0.0004292147,0.00001964647,0.9940232,0.00009624855,0.000009098949,0.00009711905,0.00005183333,0.0007060363,0.00007042718,0.00003508671,0.004426249,0.00003581338],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981527,0.000009454538,0.00004747604,0.0002735443,0.001021358,0.0002338407,0.000231968,0.000001774903,0.00002787057],"genre_scores_gemma":[0.9972222,0.000008491331,0.002269651,0.0001396968,0.0001214808,0.00000365894,0.0001174384,0.000003386219,0.0001140409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4783726,"threshold_uncertainty_score":0.5636015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404528517","doi":"10.23889/ijpds.v9i1.2407","title":"Secondary use of routinely collected administrative health data for epidemiologic research: Answering research questions using data collected for a different purpose","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of British Columbia; Simon Fraser University; AIDS Vancouver","funders":"","keywords":"Data science; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.9660910023644246,"gpt":0.746661212221578,"spread":0.2194297901428466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04235104,0.0001497497,0.000383881,0.001283863,0.004376642,0.0003787348,0.003927568,0.0001430837,0.00005695351],"category_scores_gemma":[0.06946225,0.0001203323,0.0000425725,0.001335572,0.0003800323,0.004150196,0.001897895,0.001258404,0.000003130855],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125973,"about_ca_system_score_gemma":0.009368939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00146288,"about_ca_topic_score_gemma":0.001614269,"domain_scores_codex":[0.9934256,0.001166663,0.002044932,0.0008175721,0.001628742,0.0009164783],"domain_scores_gemma":[0.9786837,0.01402375,0.0008112534,0.001525328,0.00450219,0.0004538065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003446424,0.0005388604,0.01063616,0.004698489,0.0003297201,0.00001046136,0.005244431,0.0009403388,0.001641741,0.09661145,0.8113747,0.0645273],"study_design_scores_gemma":[0.0007687825,0.0003602091,0.01070227,0.001900735,0.0000158317,0.000021686,0.0007774686,0.8665441,0.00000746509,0.00529416,0.113493,0.000114273],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126835,0.0005721088,0.7507873,0.02467745,0.00889396,0.008614871,0.09353854,0.0001383639,0.00009393619],"genre_scores_gemma":[0.7960751,0.000564425,0.1436401,0.0007107657,0.002200359,0.0003425737,0.05548481,0.00005100225,0.0009309087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8656038,"threshold_uncertainty_score":0.9969195,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3111951434","doi":"10.23889/ijpds.v5i5.1530","title":"Opioid Agonist Treatment and Risk of Mortality During an Opioid Overdose Public Health Emergency: A Population-Based Retrospective Cohort Study","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Opioid Use Disorder Treatment","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University; Ministry of Health; BC Children's Hospital; BC Centre for Disease Control; AIDS Vancouver","funders":"","keywords":"Medicine; Fentanyl; Cohort; Population; Drug overdose; Opioid use disorder; Emergency medicine; Retrospective cohort study; Cohort study; Public health; Opioid; Anesthesia; Internal medicine; Poison control; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.082721987471555,"gpt":0.4074192937123322,"spread":0.3246973062407772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009764216,0.0001854867,0.0003562957,0.000260359,0.000508879,0.000153584,0.0005023846,0.00002941184,0.00005855934],"category_scores_gemma":[0.0007475,0.00015725,0.00007380882,0.0003735129,0.00007188512,0.001292296,0.00013451,0.0001220742,0.000001064237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009135493,"about_ca_system_score_gemma":0.0006499863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005778262,"about_ca_topic_score_gemma":0.0006702393,"domain_scores_codex":[0.9971365,0.0000894983,0.0007410505,0.0006534607,0.001127829,0.000251651],"domain_scores_gemma":[0.9977011,0.00002689197,0.000724815,0.0005104428,0.0005996514,0.0004370675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001496843,0.000895208,0.9959555,0.00001991113,0.000253261,0.000004877336,0.000954563,0.0001834705,0.00009411089,0.0001297028,0.00001697131,0.001342777],"study_design_scores_gemma":[0.002354955,0.001167606,0.9775151,0.0000239903,0.0001366871,0.00001353796,0.0003458597,0.01806438,0.00003957337,0.0001732505,0.0000498696,0.0001151669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943932,0.0000813296,0.0009585139,0.00126213,0.0005988709,0.001280593,0.00138361,0.00003216293,0.000009547032],"genre_scores_gemma":[0.9957569,0.0002816831,0.001812096,0.00007288674,0.0002189477,0.00002990813,0.001799815,0.00001674226,0.00001098101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01844034,"threshold_uncertainty_score":0.8735042,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891745186","doi":"10.23889/ijpds.v3i4.715","title":"The Canadian Urban Environmental Health Research Consortium (CANUE): a national data linkage initiative","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":8,"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 of Victoria; McGill University Health Centre","funders":"","keywords":"Data sharing; Environmental data; Biobank; Geospatial analysis; Metadata; Confidentiality; Data science; Environmental resource management; Environmental health; Business; Environmental planning; Geography; Computer science; Political science; Medicine; World Wide Web; Environmental science","retraction":null,"screen_n_in":null,"score":{"opus":0.2979085823781145,"gpt":0.4758946121106599,"spread":0.1779860297325455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.01750191,0.0001523246,0.0001158918,0.0003121525,0.005864227,0.0008155745,0.005621052,0.00005696502,0.0005802679],"category_scores_gemma":[0.003676794,0.000128082,0.00002709646,0.000453028,0.002484473,0.003733494,0.002137884,0.0005605025,0.0004423987],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00398679,"about_ca_system_score_gemma":0.001409553,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02534261,"about_ca_topic_score_gemma":0.1573022,"domain_scores_codex":[0.9937135,0.0003341373,0.000612491,0.0009863947,0.003480719,0.0008727317],"domain_scores_gemma":[0.9971931,0.0005334583,0.0003898414,0.001048134,0.0001980883,0.0006373733],"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":[0.0002272953,0.0003757822,0.4157868,0.000008615908,0.0001541341,0.00004177257,0.003575743,0.0004511239,0.001527832,0.009672127,0.3467831,0.2213957],"study_design_scores_gemma":[0.0004803813,0.0001302419,0.4180608,0.00003573433,0.000005094329,0.00009952398,0.0004141633,0.0459431,0.00005886553,0.003878559,0.5306768,0.0002167787],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6469719,0.0007854197,0.02950685,0.202284,0.02369164,0.00894131,0.04034803,0.0001964577,0.04727434],"genre_scores_gemma":[0.9914324,0.0001343721,0.002945876,0.002815196,0.0009854673,0.00001695258,0.001384407,0.00001857529,0.0002667611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3444605,"threshold_uncertainty_score":0.9998367,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3202418933","doi":"10.23889/ijpds.v6i1.1653","title":"Factors Affecting Access to Administrative Health Data for Research in Canada: A Study Protocol","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Public Health Policies and Education","field":"Health Professions","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Nova Scotia Health Authority; Dalhousie University","funders":"","keywords":"Receipt; Stakeholder; Protocol (science); Inclusion (mineral); Data collection; Health data; Business; Medicine; Public relations; Psychology; Political science; Health care; Accounting; Alternative medicine; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.8544295047813003,"gpt":0.7599307233599555,"spread":0.09449878142134482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01354302,0.0001014518,0.0001992758,0.0004760651,0.002089092,0.0003350349,0.003617068,0.00003204338,0.00005253825],"category_scores_gemma":[0.01085356,0.00008634619,0.00001335951,0.001067114,0.00003081576,0.002784767,0.001709577,0.0005054673,0.000001782276],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.003961893,"about_ca_system_score_gemma":0.04626256,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7093573,"about_ca_topic_score_gemma":0.94745,"domain_scores_codex":[0.9956977,0.0005677041,0.0009690211,0.0006265775,0.001354409,0.0007845746],"domain_scores_gemma":[0.9945829,0.001576868,0.0004697354,0.0008428076,0.002084153,0.0004435591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001858168,0.000385587,0.8392473,0.0001679738,0.00002460816,0.000004764052,0.00720036,0.0001799045,0.00001895215,0.001118227,0.135826,0.01564048],"study_design_scores_gemma":[0.0009976134,0.0001579744,0.852033,0.0002649015,0.000001930416,0.000004562349,0.04257565,0.005456801,0.000005674259,0.0003984052,0.09798987,0.0001135949],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7596382,0.000008605151,0.004683504,0.09191959,0.01045725,0.1285532,0.004495774,0.00002261759,0.0002213143],"genre_scores_gemma":[0.9773135,0.000002752809,0.002262647,0.002578534,0.00155663,0.01431745,0.001779932,0.00001920814,0.0001693269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2380927,"threshold_uncertainty_score":0.9998617,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}