{"meta":{"query_hash":"12114726b7e6","filters":{"venue":"Biostatistics"},"cohort_total":82,"direct_labels_cover":0,"predictions_cover":82,"exported":82,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/12114726b7e6","api":"https://metacan.xera.ac/api/v1/cohort?venue=Biostatistics"},"results":[{"id":"W1528102277","doi":"10.1093/biostatistics/kxl026","title":"Cluster-based network model for time-course gene expression data","year":2006,"lang":"en","type":"article","venue":"Biostatistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"National Cancer Institute","keywords":"Cluster analysis; Computer science; Data mining; Gene cluster; Computational biology; Gene regulatory network; Expression (computer science); Cluster (spacecraft); Gene expression; Gene; Artificial intelligence; Biology; Genetics; Computer network","score_opus":0.026755659162620793,"score_gpt":0.29276575341318256,"score_spread":0.26601009425056177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528102277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037749154,0.00041034629,0.9935406,0.0001929592,0.0001747933,0.0002923239,0.0013449577,0.000021778345,0.00024734242],"genre_scores_gemma":[0.51793724,0.000042741867,0.45429868,0.0007973938,0.001225488,0.00008649274,0.02011018,0.00006303178,0.0054387655],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990094,0.000031416963,0.0002048267,0.00041206783,0.00011879865,0.00022352654],"domain_scores_gemma":[0.99892974,0.000024853127,0.00011553815,0.0007774285,0.000093708,0.000058713693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001503935,0.00013376531,0.000100712416,0.00001714276,0.000113596114,0.000028949891,0.0003098026,0.00012714262,0.000012950516],"category_scores_gemma":[0.000050014605,0.00012677566,0.000033383338,0.000051830524,0.000042022446,0.0000033995977,0.00010905623,0.00003675719,0.000009789947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009841013,0.00006342341,0.00011950953,0.000012518058,0.0000054312277,2.764144e-7,0.0000020473315,0.023752743,0.4763557,0.00013111274,0.4985073,0.00095152116],"study_design_scores_gemma":[0.0009363799,0.000082265426,0.00031220462,0.00001880356,0.000038448925,0.0000011844754,0.000004145803,0.7552335,0.15519246,0.0006855859,0.08724692,0.0002481045],"about_ca_topic_score_codex":0.00000345614,"about_ca_topic_score_gemma":0.000009274437,"teacher_disagreement_score":0.7314808,"about_ca_system_score_codex":0.000009701497,"about_ca_system_score_gemma":0.00014631481,"threshold_uncertainty_score":0.5169761},"labels":[],"label_agreement":null},{"id":"W1994381110","doi":"10.1093/biostatistics/kxl035","title":"A hierarchical clustering method for estimating copy number variation","year":2006,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute; SickKids Foundation; Mount Sinai Hospital","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Cluster analysis; Outlier; Computer science; Statistic; Tree (set theory); Change detection; Data mining; Scan statistic; Hierarchical clustering; Copy-number variation; Statistics; Pattern recognition (psychology); Mathematics; Artificial intelligence; Genome; Biology; Genetics","score_opus":0.009536162042363535,"score_gpt":0.2802942228825624,"score_spread":0.2707580608401989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994381110","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014190025,0.000016532938,0.9841039,0.000084554355,0.00023135086,0.00015846167,0.00032963033,0.000014685496,0.000870816],"genre_scores_gemma":[0.3630773,0.0000014620643,0.6354251,0.00007064153,0.0004243861,0.000026086123,0.00044912702,0.000013252104,0.00051263976],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993304,0.00003446623,0.00020958888,0.00018714635,0.0000643959,0.0001740255],"domain_scores_gemma":[0.9996277,0.00005654898,0.000076551376,0.0001279107,0.0000802659,0.000030991174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014616971,0.00009932019,0.00009176383,0.00001530678,0.0001237871,0.000040954525,0.00006994392,0.000081903025,0.000027198004],"category_scores_gemma":[0.00010001284,0.000102582984,0.000040772375,0.000034710392,0.00002083397,0.0000023896525,0.0000438676,0.000035577104,0.000007821991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000607953,0.00058845495,0.020157948,0.00073153357,0.00036507082,0.000016495955,0.0010652698,0.04046412,0.5443173,0.29303697,0.059336297,0.039312575],"study_design_scores_gemma":[0.0037574703,0.0007009409,0.023939501,0.00005836484,0.00023148354,0.00020951022,0.000220716,0.76122135,0.06871587,0.04786121,0.09167802,0.0014055556],"about_ca_topic_score_codex":0.0001376376,"about_ca_topic_score_gemma":0.000056647546,"teacher_disagreement_score":0.72075725,"about_ca_system_score_codex":0.000016020545,"about_ca_system_score_gemma":0.00004712919,"threshold_uncertainty_score":0.41832125},"labels":[],"label_agreement":null},{"id":"W2011218435","doi":"10.1093/biostatistics/kxt052","title":"Analysis of counts with two latent classes, with application to risk assessment based on physician-visit records of cancer survivors","year":2013,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"BC Cancer Agency","keywords":"Estimator; Statistics; Consistency (knowledge bases); Unobservable; Normality; Variance (accounting); Inference; Mathematics; Latent class model; Asymptotic distribution; Econometrics; Delta method; Computer science; Artificial intelligence","score_opus":0.009125071757745046,"score_gpt":0.2977986433723875,"score_spread":0.28867357161464247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011218435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061144447,0.000007813947,0.99244815,0.00010363198,0.00003714062,0.00021374537,0.00015256651,0.000012477767,0.00091003877],"genre_scores_gemma":[0.4631993,0.000007639143,0.536571,0.0001438736,0.000008146589,0.000024899762,0.000010008116,0.000005068791,0.00003002019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921376,0.00006258065,0.0001521048,0.00021098317,0.00025745571,0.00010310436],"domain_scores_gemma":[0.9990058,0.00010530929,0.00020433617,0.00037609081,0.00025684314,0.000051614035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013842905,0.00009129601,0.00020611948,0.00011871829,0.000022904667,0.000022401202,0.00018073696,0.000020688434,0.000015869726],"category_scores_gemma":[0.0000058382066,0.00006428225,0.00002436662,0.0007114671,0.000025299456,0.000042042837,0.000017740771,0.000051966123,0.000003845691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049459908,0.00033076663,0.10240594,0.00007129887,0.0006212793,0.000002269452,0.00019131039,0.03160256,0.0008039968,0.07621808,0.0013954666,0.7863076],"study_design_scores_gemma":[0.00019225806,0.00027119298,0.15798499,0.000031869135,0.0002454834,5.737732e-8,0.0000036129316,0.8393471,0.00057289744,0.00087780063,0.00033978655,0.00013294216],"about_ca_topic_score_codex":0.0026976173,"about_ca_topic_score_gemma":0.0007724636,"teacher_disagreement_score":0.80774456,"about_ca_system_score_codex":0.000039199742,"about_ca_system_score_gemma":0.00008848509,"threshold_uncertainty_score":0.40780085},"labels":[],"label_agreement":null},{"id":"W2015295476","doi":"10.1093/biostatistics/kxt054","title":"Efficient panel designs for longitudinal recurrent event studies recording panel counts","year":2013,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control; Western University","funders":"Western Canada Research Grid; Compute Canada","keywords":"Panel data; Covariate; Computer science; Outcome (game theory); Event (particle physics); Econometrics; Panel analysis; Statistics; Set (abstract data type); Piecewise; Mathematics","score_opus":0.8361934892466871,"score_gpt":0.5864674015450662,"score_spread":0.24972608770162097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015295476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023360054,0.00024958112,0.9915536,0.00029602146,0.0030656806,0.0013257671,0.0006560192,0.00009661726,0.0004207124],"genre_scores_gemma":[0.0394834,0.00009901745,0.9591258,0.00008245968,0.00038534313,0.00022461299,0.0000073131982,0.000045980745,0.00054603274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978374,0.00024075527,0.0008270253,0.00037497445,0.0003263344,0.0003934579],"domain_scores_gemma":[0.9633168,0.03548335,0.0002915278,0.00031950243,0.00045083463,0.00013796313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001459043,0.00022749553,0.0005538985,0.000054133252,0.00013167257,0.0000481551,0.00018364041,0.00010688106,0.0004347356],"category_scores_gemma":[0.073611304,0.00018578263,0.00010954003,0.000119134,0.00015969657,0.000015438161,0.00008561476,0.0001536803,0.00033811777],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013441891,0.0006155354,0.00029730168,0.0011767156,0.0004598675,0.000016287313,0.0003251653,0.000040919072,0.0002261718,0.4520864,0.36398947,0.18063179],"study_design_scores_gemma":[0.00069260976,0.00037127562,0.00059220725,0.00023765856,0.00024437776,0.000005301514,0.00018722525,0.010324947,0.00015174258,0.98389345,0.0029338705,0.00036530336],"about_ca_topic_score_codex":0.000006101,"about_ca_topic_score_gemma":0.0000014281827,"teacher_disagreement_score":0.5318071,"about_ca_system_score_codex":0.00012836981,"about_ca_system_score_gemma":0.00005208861,"threshold_uncertainty_score":0.93419206},"labels":[],"label_agreement":null},{"id":"W2095702029","doi":"10.1093/biostatistics/kxn034","title":"Exact and efficient inference procedure for meta-analysis and its application to the analysis of independent 2 x 2 tables with all available data but without artificial continuity correction","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; Université du Québec à Montréal","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute","keywords":"Computer science; Inference; Simple (philosophy); Meta-analysis; Data mining; Continuity correction; Statistics; Econometrics; Mathematics; Artificial intelligence; Medicine; Internal medicine","score_opus":0.5257705219849328,"score_gpt":0.5038448131116642,"score_spread":0.021925708873268612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095702029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03421656,0.00009659882,0.9565046,0.00012657748,0.00005149193,0.001402277,0.007552418,0.000022466855,0.00002704406],"genre_scores_gemma":[0.63398325,0.00003515729,0.3654271,0.00006202205,0.000031156123,0.0001692241,0.0001005484,0.000015250949,0.00017627953],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760616,0.0002873314,0.000802589,0.00063645694,0.00045544739,0.000212013],"domain_scores_gemma":[0.9816052,0.016434973,0.000588758,0.00075722573,0.00048798075,0.00012590668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024987995,0.00020804943,0.0012616115,0.00020233492,0.00015857846,0.00004811703,0.00027176325,0.00010055547,0.00008741433],"category_scores_gemma":[0.029424801,0.00012978053,0.000114778275,0.0010190312,0.00016773555,0.000040846317,0.00016775898,0.0001236644,0.0000026347432],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00585093,0.0042159557,0.052898865,0.0023155764,0.61929,0.000025883308,0.0059236228,0.015864117,0.006984565,0.2310822,0.017743075,0.03780521],"study_design_scores_gemma":[0.0005957601,0.0003711851,0.016829316,0.00001331504,0.43670517,0.000006964473,0.00021683605,0.52822345,0.0032737844,0.0127842575,0.0005151564,0.00046480718],"about_ca_topic_score_codex":0.00015694294,"about_ca_topic_score_gemma":0.0014572414,"teacher_disagreement_score":0.5997667,"about_ca_system_score_codex":0.000021848626,"about_ca_system_score_gemma":0.00007791476,"threshold_uncertainty_score":0.97875077},"labels":[],"label_agreement":null},{"id":"W2095887717","doi":"10.1093/biostatistics/3.2.229","title":"A Bayesian approach to case-control studies with errors in covariables","year":2002,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Computer science; Control (management); Econometrics; Statistics; Artificial intelligence; Mathematics","score_opus":0.1371729806175621,"score_gpt":0.361720640302282,"score_spread":0.2245476596847199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095887717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022095556,0.00014460427,0.9913793,0.00018143072,0.00007357489,0.00047431493,0.00038036026,0.000051398638,0.00510544],"genre_scores_gemma":[0.33287513,0.0000104009505,0.6666384,0.00021070243,0.000027263995,0.000051057537,0.0000011935332,0.000021098855,0.00016480443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985739,0.00016944343,0.0003732512,0.00031228637,0.00021291838,0.000358196],"domain_scores_gemma":[0.9965531,0.0028029594,0.000084778374,0.00028264773,0.00013256614,0.00014389874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039552504,0.0002141185,0.00044096215,0.00011130774,0.000081508864,0.00003417386,0.00011464677,0.000064084124,0.00010399877],"category_scores_gemma":[0.0049841423,0.00015931045,0.000019148587,0.00035122182,0.00011701825,0.000031481217,0.000033603115,0.00015058708,0.000020198491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066954686,0.00044685617,0.0012654309,0.0003696451,0.00015616138,0.0014377815,0.0034501278,0.000106517415,0.00002713621,0.9632318,0.014101172,0.01534044],"study_design_scores_gemma":[0.0052813385,0.0016596755,0.0022446231,0.00059118215,0.0006246601,0.002027957,0.008594589,0.2604175,0.00011872809,0.71444094,0.0020851374,0.0019137051],"about_ca_topic_score_codex":0.000050361108,"about_ca_topic_score_gemma":0.00009008117,"teacher_disagreement_score":0.3306656,"about_ca_system_score_codex":0.000063727915,"about_ca_system_score_gemma":0.00001788348,"threshold_uncertainty_score":0.64964914},"labels":[],"label_agreement":null},{"id":"W2097681968","doi":"10.1093/biostatistics/2.3.323","title":"Efficiency considerations in the analysis of inter-observer agreement","year":2001,"lang":"en","type":"article","venue":"Biostatistics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cohen's kappa; Replicate; Statistics; Inter-rater reliability; Reliability (semiconductor); Statistic; Kappa; Mathematics; Binary number; Computer science; Binomial distribution; Econometrics; Arithmetic; Physics","score_opus":0.23113506979270315,"score_gpt":0.40521817031104557,"score_spread":0.17408310051834242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097681968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82730573,0.0001551022,0.15947591,0.0047084456,0.00035604378,0.00052876445,0.00019989398,0.000009547115,0.007260562],"genre_scores_gemma":[0.99684566,0.000020638226,0.0024713185,0.00047356015,0.0000123585205,0.000007414286,0.000009034284,0.0000016518524,0.00015838661],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99717414,0.00036686196,0.0008408043,0.0002481063,0.0012138607,0.00015622073],"domain_scores_gemma":[0.9964512,0.00238932,0.00020572735,0.0005977027,0.00032414965,0.000031920565],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004319277,0.00008682029,0.00023774954,0.00032961622,0.00008877992,0.000105676765,0.00042311038,0.000029459794,0.0015348521],"category_scores_gemma":[0.0040573995,0.000050311533,0.00010438814,0.0019602573,0.00013317085,0.00005766561,0.00005186372,0.00007584735,0.00005976952],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029891105,0.0013374675,0.8517873,0.000011358577,0.00028521413,0.000053213676,0.0062540094,0.01117279,0.00062281,0.07529371,0.032562364,0.020589838],"study_design_scores_gemma":[0.000325485,0.00013651798,0.93634456,0.00001395574,0.00026359851,0.0000019763793,0.0034783967,0.0154708335,0.00011236907,0.035753552,0.007955147,0.00014360766],"about_ca_topic_score_codex":0.00012718576,"about_ca_topic_score_gemma":0.0015706324,"teacher_disagreement_score":0.1695399,"about_ca_system_score_codex":0.000033956716,"about_ca_system_score_gemma":0.000043356216,"threshold_uncertainty_score":0.9993779},"labels":[],"label_agreement":null},{"id":"W2098860533","doi":"10.1093/biostatistics/kxq016","title":"Surface shape analysis with an application to brain surface asymmetry in schizophrenia","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Asymmetry; Surface (topology); Bayesian probability; Shape analysis (program analysis); Mathematics; Artificial intelligence; Pattern recognition (psychology); Computer science; Principal component analysis; Scale (ratio); Geometry; Physics","score_opus":0.02034049229156815,"score_gpt":0.30548675897984356,"score_spread":0.2851462666882754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098860533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6485675,0.0000036580814,0.35017732,0.00039730957,0.000035948724,0.0002628357,0.00020943518,0.000059902326,0.00028607174],"genre_scores_gemma":[0.5590819,7.38862e-7,0.44057146,0.00014946764,0.0000248162,0.0000059490476,0.00007562992,0.00001565206,0.00007438744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99858487,0.00008315351,0.00035643793,0.00042551933,0.0002725921,0.00027744958],"domain_scores_gemma":[0.998238,0.0007070262,0.00014032645,0.0005921298,0.00012573191,0.0001967813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005388862,0.00019368825,0.00032722868,0.00017645303,0.000086624954,0.00007409849,0.0002571187,0.00014692187,0.00021694413],"category_scores_gemma":[0.0006013854,0.00015922498,0.000040571093,0.0018778106,0.00004887948,0.00007818758,0.000053877695,0.0002934058,0.0000627242],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034798417,0.0014481439,0.11007928,0.00008463505,0.00034228983,0.000059461225,0.0004084147,0.002744145,0.040618498,0.82123506,0.0069768857,0.015655197],"study_design_scores_gemma":[0.0029122778,0.0009793261,0.62933546,0.000040025432,0.000859803,0.000022161457,0.00051353674,0.30418086,0.003418156,0.05013631,0.005704676,0.0018974012],"about_ca_topic_score_codex":0.00019361138,"about_ca_topic_score_gemma":0.001886943,"teacher_disagreement_score":0.77109873,"about_ca_system_score_codex":0.000031807587,"about_ca_system_score_gemma":0.000044215136,"threshold_uncertainty_score":0.6493006},"labels":[],"label_agreement":null},{"id":"W2100420476","doi":"10.1093/biostatistics/kxr010","title":"Classifying tissue samples from measurements on cells with within-class tissue sample heterogeneity","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute","keywords":"Latent class model; Computer science; Macro; Replicate; Class (philosophy); Heuristic; Object (grammar); Focus (optics); Sample (material); Cluster analysis; Statistics; Mixture model; Artificial intelligence; Pattern recognition (psychology); Mathematics; Machine learning","score_opus":0.13299273575744242,"score_gpt":0.2858008119355312,"score_spread":0.15280807617808878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100420476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022340858,0.00004372763,0.9748521,0.00005192388,0.0012609586,0.0002822722,0.00034514518,0.00022112562,0.00060191465],"genre_scores_gemma":[0.52146643,0.000006102833,0.47813988,0.000218862,0.00008708599,0.000015557825,0.000016557437,0.000024640896,0.00002487042],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99791265,0.00011703238,0.0003217842,0.00065482414,0.0006293426,0.00036436322],"domain_scores_gemma":[0.99835145,0.00025464655,0.0002543472,0.00081508514,0.00015590555,0.00016853838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020342092,0.00027790602,0.00023795445,0.00009144655,0.00026025026,0.00018512431,0.0006756952,0.000104541956,0.00006653022],"category_scores_gemma":[0.0000854205,0.00024785023,0.000022767257,0.0002613049,0.00012614999,0.00022523453,0.00014084102,0.00018341842,0.00015771243],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00104196,0.0015607848,0.040820822,0.00036026156,0.0010638591,0.0004471067,0.021708146,0.0020013675,0.31295663,0.05703414,0.01839606,0.54260886],"study_design_scores_gemma":[0.00059804064,0.0010429858,0.009889972,0.000086023094,0.000044102486,0.000008078038,0.000048684342,0.003524546,0.9707023,0.0050348747,0.008464078,0.0005563052],"about_ca_topic_score_codex":0.0020630253,"about_ca_topic_score_gemma":0.0013494601,"teacher_disagreement_score":0.65774566,"about_ca_system_score_codex":0.00020926846,"about_ca_system_score_gemma":0.00013166186,"threshold_uncertainty_score":0.9999974},"labels":[],"label_agreement":null},{"id":"W2102283511","doi":"10.1093/biostatistics/kxv007","title":"Hypothesis testing at the extremes: fast and robust association for high-throughput data","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; National Institute of Mental Health; Ontario Genomics Institute; Cystic Fibrosis Canada; National Institute of Environmental Health Sciences; Genome Canada; Ontario Genomics; Cystic Fibrosis Foundation","keywords":"Computer science; Throughput; Association (psychology); Data mining; Statistics; Mathematics; Psychology","score_opus":0.1521403879759942,"score_gpt":0.3005252873365745,"score_spread":0.14838489936058033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102283511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61320347,0.0033145433,0.35754222,0.008863742,0.001357815,0.001513309,0.011600519,0.00006647018,0.0025379588],"genre_scores_gemma":[0.6294985,0.0002650314,0.3611007,0.0009027051,0.00076047867,0.00004616548,0.002124863,0.000043467488,0.0052580847],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99907774,0.00009448673,0.00020401919,0.0003070921,0.000095695694,0.00022097396],"domain_scores_gemma":[0.99843395,0.0006980362,0.0002020704,0.00039960633,0.00020413645,0.00006218583],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00080038497,0.00010545239,0.00012882288,0.000011600688,0.00017007129,0.000026009038,0.00018444218,0.00013062109,0.0000035866763],"category_scores_gemma":[0.011487061,0.00008241407,0.000014674431,0.00005263755,0.0000553207,0.0000028362026,0.0002750949,0.000039622773,0.000007843449],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060690694,0.00006405262,0.17463295,0.000030498717,0.00022352084,0.0000013245356,0.00014427226,0.0009145054,0.009283296,0.0005548674,0.7758807,0.03820934],"study_design_scores_gemma":[0.005202282,0.0016665433,0.52516854,0.000042597414,0.0008238914,0.000059091395,0.0019204136,0.038983796,0.0043775425,0.016633697,0.4035549,0.0015667051],"about_ca_topic_score_codex":0.000111464404,"about_ca_topic_score_gemma":0.0003797872,"teacher_disagreement_score":0.37232578,"about_ca_system_score_codex":0.000059286976,"about_ca_system_score_gemma":0.00007969995,"threshold_uncertainty_score":0.9968396},"labels":[],"label_agreement":null},{"id":"W2105004777","doi":"10.1093/biostatistics/kxr005","title":"Weighted scores method for regression models with dependent data","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Univariate; Copula (linguistics); Statistics; Mathematics; Weighting; Multivariate statistics; Negative binomial distribution; Regression; Regression analysis; Inference; Binomial regression; Econometrics; Computer science; Poisson distribution; Artificial intelligence; Medicine","score_opus":0.2664853473612795,"score_gpt":0.4255545416501072,"score_spread":0.1590691942888277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105004777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000060379072,0.000039043796,0.9945168,0.000034866945,0.00013339966,0.00046864495,0.0028325978,0.00007821245,0.0018360657],"genre_scores_gemma":[0.0036520234,0.000019717303,0.995856,0.00006685209,0.000059980124,0.000038390845,0.0001274502,0.000046251087,0.00013336464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984241,0.00014747304,0.0003578548,0.0004683329,0.00028300087,0.00031923552],"domain_scores_gemma":[0.9961622,0.0023803655,0.00019883139,0.0009048082,0.00021100939,0.00014279243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061303144,0.00022377424,0.00033886565,0.000060827257,0.00012028504,0.000039134175,0.0005022145,0.000095628544,0.0001455474],"category_scores_gemma":[0.0012356824,0.00014621088,0.000023014181,0.000110083114,0.000091726826,0.00012880504,0.00016930069,0.00012042145,0.000006629196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019860988,0.00011702816,0.00007817786,0.00015425148,0.00004533664,0.000025993935,0.00023615474,1.4391426e-7,0.000070082446,0.92065525,0.0053359047,0.07308307],"study_design_scores_gemma":[0.00050980627,0.0002425832,0.00012716696,0.00012927348,0.00016433591,0.000017573988,0.00006779291,0.08027188,0.0014846381,0.91651833,0.00022052856,0.00024609882],"about_ca_topic_score_codex":0.00007115286,"about_ca_topic_score_gemma":0.000056548317,"teacher_disagreement_score":0.080271736,"about_ca_system_score_codex":0.000021465874,"about_ca_system_score_gemma":0.00008749293,"threshold_uncertainty_score":0.5962307},"labels":[],"label_agreement":null},{"id":"W2107365898","doi":"10.1093/biostatistics/kxp029","title":"Second-order estimating equations for the analysis of clustered current status data","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Copula (linguistics); Marginal model; Quantile; Marginal distribution; Estimating equations; Statistics; Generalized estimating equation; Econometrics; Mathematics; Joint probability distribution; Order statistic; Regression analysis; Maximum likelihood","score_opus":0.3129426196990909,"score_gpt":0.48874706451441663,"score_spread":0.17580444481532576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107365898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024704472,0.00017620024,0.9885695,0.00015711958,0.00023852277,0.00035480445,0.010058836,0.000023058114,0.00017488898],"genre_scores_gemma":[0.04416894,0.000022095277,0.9551704,0.00007739639,0.00006114352,0.000011890162,0.00044062917,0.0000104927985,0.000037019676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862176,0.00008383096,0.00056242634,0.00024502384,0.00022684205,0.0002601381],"domain_scores_gemma":[0.9856326,0.012850116,0.00030661336,0.0008092687,0.00033042967,0.00007096739],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006305359,0.00013442368,0.00034510015,0.000101504134,0.00014068792,0.000046440506,0.00038145168,0.00003906906,0.00025330062],"category_scores_gemma":[0.019973038,0.00009484386,0.0000556824,0.00057267974,0.00008441645,0.000046830155,0.000086808875,0.00010306511,0.0000021286764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001556653,0.00012305347,0.000068603586,0.000099624725,0.0003004928,3.7060892e-7,0.0003004295,0.00016943722,0.000045136432,0.6214309,0.0060139154,0.37143248],"study_design_scores_gemma":[0.00020558522,0.00006422412,0.0033685006,0.000022323195,0.0014396239,1.9640073e-7,0.00007174186,0.78592443,0.000018419198,0.20710357,0.0016687709,0.00011262154],"about_ca_topic_score_codex":0.000013483214,"about_ca_topic_score_gemma":0.00006585229,"teacher_disagreement_score":0.785755,"about_ca_system_score_codex":0.000021659303,"about_ca_system_score_gemma":0.00009589044,"threshold_uncertainty_score":0.98828214},"labels":[],"label_agreement":null},{"id":"W2107721271","doi":"10.1093/biostatistics/kxv012","title":"Semiparametric likelihood inference for left-truncated and right-censored data","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Health Canada; Medical Research Council; Pfizer Canada; University of Ottawa; National Cancer Institute; National Institutes of Health; Pfizer","keywords":"Mathematics; Censoring (clinical trials); Estimator; Truncation (statistics); Multiplicative function; Statistics; Semiparametric model; Parametric statistics; Test statistic; Parametric model; Applied mathematics; Statistical hypothesis testing","score_opus":0.20177109706344662,"score_gpt":0.42213631169961596,"score_spread":0.22036521463616934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107721271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005904623,0.00017219502,0.987694,0.00016007599,0.0003201166,0.00048325158,0.004235667,0.00010232423,0.0009277401],"genre_scores_gemma":[0.104735285,0.000044745502,0.89458233,0.000113295966,0.00008802456,0.00001227803,0.00024132908,0.000032203752,0.00015050017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829555,0.00011359635,0.0004454218,0.00046416366,0.00028671316,0.00039455973],"domain_scores_gemma":[0.9923299,0.005980176,0.00017134001,0.00074504147,0.00042489995,0.0003486742],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008452356,0.00022624111,0.00038030703,0.000107359796,0.000090374444,0.00010664486,0.00041419352,0.00012644725,0.000066285196],"category_scores_gemma":[0.039186273,0.00018906801,0.000018423867,0.00024047778,0.00016090447,0.00009354492,0.0002591696,0.00014392455,0.00002315357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092619346,0.00020463408,0.0023223718,0.00030525788,0.00007192116,0.000018065793,0.00034451485,6.103334e-7,0.00018852294,0.8596416,0.08479442,0.052015435],"study_design_scores_gemma":[0.001079473,0.0003349527,0.001662136,0.000050611543,0.00014876772,0.000016206905,0.000110034875,0.039322328,0.000404022,0.9467729,0.009716434,0.00038213196],"about_ca_topic_score_codex":0.000042730844,"about_ca_topic_score_gemma":0.000027696899,"teacher_disagreement_score":0.09883066,"about_ca_system_score_codex":0.000038121572,"about_ca_system_score_gemma":0.00018374082,"threshold_uncertainty_score":0.96890706},"labels":[],"label_agreement":null},{"id":"W2109802067","doi":"10.1093/biostatistics/1.4.441","title":"Monitoring surgical performance using risk-adjusted cumulative sum charts","year":2000,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":473,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"CUSUM; Context (archaeology); Computer science; Quality (philosophy); Surgical procedures; Statistics; Variable (mathematics); Medicine; Surgery; Mathematics","score_opus":0.19504895291578445,"score_gpt":0.43317991759428615,"score_spread":0.2381309646785017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109802067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90031,0.0002770767,0.094649985,0.000035365527,0.0010977392,0.00022915349,0.00037916974,0.0001298709,0.0028916604],"genre_scores_gemma":[0.92113215,0.00025482944,0.076409906,0.000009731538,0.0005614497,0.000006100987,0.0000060060215,0.000036233774,0.0015835934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99582034,0.00022508096,0.00094980415,0.0007124726,0.001656006,0.00063626835],"domain_scores_gemma":[0.99535185,0.0029821256,0.00034679842,0.0005336165,0.00047528086,0.00031035263],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009734448,0.00030695318,0.00044093185,0.00016859258,0.000587786,0.00022995893,0.0005403832,0.00012362882,0.0009114675],"category_scores_gemma":[0.0030302247,0.0002596203,0.00006804789,0.00088765693,0.0002611114,0.00051198486,0.00010264374,0.00040213106,0.00070910476],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019334651,0.00008299267,0.124606326,0.000023146973,0.00002615634,0.0001936078,0.00059259287,0.01633832,0.00011942318,0.0009097556,0.00023519898,0.85667914],"study_design_scores_gemma":[0.002473486,0.00041972028,0.26560324,0.00032074034,0.00014668466,0.00014187493,0.0009835425,0.64862144,0.00582102,0.04089521,0.03280447,0.0017685434],"about_ca_topic_score_codex":0.00006034223,"about_ca_topic_score_gemma":0.000002450477,"teacher_disagreement_score":0.8549106,"about_ca_system_score_codex":0.00014375863,"about_ca_system_score_gemma":0.00007723223,"threshold_uncertainty_score":0.9999856},"labels":[],"label_agreement":null},{"id":"W2116887614","doi":"10.1093/biostatistics/kxq079","title":"A particular diffusion model for incomplete longitudinal data: application to the multicenter AIDS cohort study","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Missing data; Covariate; Bayesian probability; Gibbs sampling; Longitudinal data; Multicenter AIDS Cohort Study; Statistics; Sampling (signal processing); Computer science; Econometrics; Mathematics; Medicine; Data mining; Human immunodeficiency virus (HIV)","score_opus":0.09837403590722711,"score_gpt":0.33226683152782255,"score_spread":0.23389279562059545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116887614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003874804,0.000014673783,0.9936572,0.00016497145,0.00017211377,0.0018573597,0.00017248176,0.000047293965,0.000039153812],"genre_scores_gemma":[0.4472567,0.0000018544865,0.55229706,0.0002063234,0.00003551471,0.00014725994,0.000019734776,0.000007566211,0.00002796068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862635,0.00009298721,0.00025656415,0.0005550499,0.00022765493,0.00024141744],"domain_scores_gemma":[0.9980541,0.00011413332,0.000083653984,0.001510293,0.00013225993,0.000105598156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008270429,0.00014007806,0.0001628853,0.000039007922,0.00019323592,0.00008175383,0.001212801,0.0000334014,0.0000018611638],"category_scores_gemma":[0.0001170452,0.00009580039,0.000026482236,0.00015767434,0.000028142033,0.00014895023,0.00065837655,0.00007067902,0.000016832566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020414297,0.0024932802,0.11710702,0.0000840053,0.0002656516,0.000025585268,0.016071232,0.0005396048,0.0011462268,0.4976882,0.013964294,0.35041076],"study_design_scores_gemma":[0.00030850281,0.00015611156,0.04151784,0.000004681583,0.000058506626,0.0000016146703,0.000020173069,0.949558,0.00004837927,0.0074508493,0.0007363123,0.00013901234],"about_ca_topic_score_codex":0.00007477395,"about_ca_topic_score_gemma":0.00009678097,"teacher_disagreement_score":0.9490184,"about_ca_system_score_codex":0.00002154401,"about_ca_system_score_gemma":0.00002953429,"threshold_uncertainty_score":0.39066264},"labels":[],"label_agreement":null},{"id":"W2117015589","doi":"10.1093/biostatistics/kxu011","title":"Composite likelihood for joint analysis of multiple multistate processes via copulas","year":2014,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Copula (linguistics); Inference; Computer science; Joint (building); Econometrics; Markov model; Markov chain; Machine learning; Mathematics; Artificial intelligence","score_opus":0.07492729461245784,"score_gpt":0.35729605603842446,"score_spread":0.2823687614259666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117015589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011472877,0.00002744951,0.98518825,0.00003610596,0.00015311195,0.00036036439,0.0025264067,0.000051244795,0.00018420344],"genre_scores_gemma":[0.35690373,0.000009656256,0.6428114,0.00004848413,0.000029492448,0.000027081145,0.000104226274,0.000021422864,0.000044482942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983231,0.00011587835,0.00070133375,0.0002959483,0.0002490037,0.0003147274],"domain_scores_gemma":[0.9919018,0.006588691,0.00039172935,0.00033056363,0.0006522501,0.00013494553],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004818273,0.000207538,0.0007060208,0.00018335483,0.00009041814,0.00003077553,0.00016198495,0.00007793548,0.00005465023],"category_scores_gemma":[0.012140648,0.00018082124,0.00011619972,0.00053796556,0.0001329818,0.000029008137,0.000047881036,0.000078500394,0.000006138586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050819584,0.0019179897,0.02619505,0.008447324,0.0036514048,0.000012054202,0.0021046193,0.00024612932,0.034162242,0.6302718,0.009730759,0.28275245],"study_design_scores_gemma":[0.0013309648,0.0005289915,0.017459419,0.00012829997,0.002720797,0.000002072049,0.00006457541,0.5357099,0.016710699,0.42310718,0.001709375,0.00052769826],"about_ca_topic_score_codex":0.00008474614,"about_ca_topic_score_gemma":0.00015089088,"teacher_disagreement_score":0.5354638,"about_ca_system_score_codex":0.000025121752,"about_ca_system_score_gemma":0.00004526227,"threshold_uncertainty_score":0.99618053},"labels":[],"label_agreement":null},{"id":"W2121713677","doi":"10.1093/biostatistics/kxq067","title":"Functional mixture regression","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Regression; Functional principal component analysis; Regression analysis; Computer science; Principal component analysis; Functional data analysis; Scalar (mathematics); Linear regression; Artificial intelligence; Machine learning; Econometrics; Mathematics; Statistics","score_opus":0.015400804457123302,"score_gpt":0.2671184447815994,"score_spread":0.2517176403244761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121713677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036985628,0.000035296533,0.99342406,0.0010153805,0.0019285121,0.00004919361,0.000016308672,0.000089579524,0.0030718173],"genre_scores_gemma":[0.04736201,0.0000062676263,0.9507889,0.0004961089,0.0002177587,0.0000029207868,0.000009022011,0.000006441692,0.0011105554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993039,0.000033599885,0.000110270834,0.00022327348,0.00017440964,0.00015454233],"domain_scores_gemma":[0.9992948,0.00010432858,0.00004901352,0.00037724143,0.00007813203,0.00009644566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017397254,0.00009409017,0.00008218046,0.000041843417,0.00009947536,0.00007572865,0.00028935933,0.00009242862,0.00007460444],"category_scores_gemma":[0.00011597344,0.000070519425,0.000027721922,0.00013099417,0.000037973256,0.0001056461,0.000088409695,0.00023436887,0.000064401254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020108582,0.000016641681,0.00006017929,0.000003951957,0.000002671268,0.000012452653,0.000046232737,2.203669e-7,0.011973201,0.77519184,0.050330747,0.16235985],"study_design_scores_gemma":[0.0006090283,0.00010173925,0.01710529,0.000027796888,0.00001625632,0.0001754477,0.0000047379035,0.03474798,0.017222308,0.70572364,0.22368376,0.0005820002],"about_ca_topic_score_codex":0.000002801586,"about_ca_topic_score_gemma":0.000005601333,"teacher_disagreement_score":0.17335302,"about_ca_system_score_codex":0.0000056378585,"about_ca_system_score_gemma":0.000052296684,"threshold_uncertainty_score":0.28756985},"labels":[],"label_agreement":null},{"id":"W2123633327","doi":"10.1093/biostatistics/kxm025","title":"Regression analysis of multivariate panel count data","year":2007,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multivariate statistics; Covariate; Statistics; Count data; Regression analysis; Econometrics; Regression; Marginal model; Event (particle physics); Multivariate analysis; Reliability (semiconductor); Mathematics","score_opus":0.3188325730028094,"score_gpt":0.47258056925801745,"score_spread":0.15374799625520802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123633327","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071609993,0.000032930013,0.9882907,0.000024679473,0.00015435969,0.00010264491,0.0026615064,0.000029448323,0.0015427027],"genre_scores_gemma":[0.22801445,0.000017140652,0.7715826,0.000036170524,0.000030090083,7.70199e-7,0.00019015958,0.000012455045,0.00011613929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984717,0.00008550464,0.0005791015,0.00027994756,0.00034780538,0.00023596459],"domain_scores_gemma":[0.9937393,0.004771648,0.00030212564,0.00087708596,0.00020672343,0.000103133876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001411691,0.00013808574,0.0004258426,0.00016951913,0.00005034887,0.000015611537,0.0003670451,0.00008335063,0.00022243855],"category_scores_gemma":[0.008204971,0.000104432685,0.00004140738,0.0005940326,0.00012600166,0.000034876633,0.00018353295,0.000105258565,0.000006500243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063668915,0.00020047998,0.0027305735,0.00011282842,0.00048551042,0.000034211505,0.00027754557,0.0000025412585,0.0023910953,0.93086123,0.0034587055,0.05938159],"study_design_scores_gemma":[0.0012028413,0.0002842576,0.27946413,0.0002682072,0.0061906655,0.000006671907,0.00050795916,0.22844855,0.0045545553,0.46857202,0.009599261,0.00090090337],"about_ca_topic_score_codex":0.00012984009,"about_ca_topic_score_gemma":0.00007489056,"teacher_disagreement_score":0.46228924,"about_ca_system_score_codex":0.000024419936,"about_ca_system_score_gemma":0.000036265188,"threshold_uncertainty_score":0.98227096},"labels":[],"label_agreement":null},{"id":"W2126930228","doi":"10.1093/biostatistics/4.3.365","title":"A closer look at the distribution of number needed to treat (NNT): a Bayesian approach","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Number needed to treat; Point estimation; Posterior probability; Bayesian probability; Mathematics; Statistics; Prior probability; Econometrics; Computer science; Confidence interval; Relative risk","score_opus":0.28032836460518146,"score_gpt":0.4902424701533613,"score_spread":0.20991410554817985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126930228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012922354,0.00001626567,0.97039866,0.0003365202,0.00030726148,0.00092354073,0.0024173416,0.000051830368,0.012626251],"genre_scores_gemma":[0.09978774,0.000010512475,0.89761835,0.00033316153,0.000099903125,0.00006852095,0.000045676337,0.000048879487,0.0019872684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967859,0.0010019038,0.00095730484,0.00038191877,0.0004794747,0.00039354223],"domain_scores_gemma":[0.9769889,0.021569451,0.00029306047,0.000727247,0.00020886281,0.00021249444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018797398,0.00025854114,0.00060140196,0.00002606835,0.000137092,0.000033283617,0.0002563727,0.00018066411,0.0007246483],"category_scores_gemma":[0.078827664,0.00017592641,0.00013157849,0.00038933792,0.00029539564,0.000023817498,0.00010649168,0.00018830634,0.00014129355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017741151,0.0003863674,0.0005621281,0.00021542849,0.00006278856,0.000009160707,0.00026547024,0.000005836242,0.00026831782,0.86992437,0.12464483,0.0034778866],"study_design_scores_gemma":[0.0014021824,0.00021625275,0.0005381785,0.00006227921,0.00037441452,0.000031301548,0.00042998398,0.00038973018,0.00967009,0.9772959,0.009173545,0.00041617025],"about_ca_topic_score_codex":0.00003928067,"about_ca_topic_score_gemma":0.000008023766,"teacher_disagreement_score":0.11547128,"about_ca_system_score_codex":0.00014113433,"about_ca_system_score_gemma":0.00007268114,"threshold_uncertainty_score":0.9289318},"labels":[],"label_agreement":null},{"id":"W2127195807","doi":"10.1093/biostatistics/4.3.479","title":"Conditional analysis of mixed Poisson processes with baseline counts: implications for trial design and analysis","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Baseline (sea); Sample size determination; Count data; Negative binomial distribution; Multiple baseline design; Poisson distribution; Randomization; Mathematics; Computer science; Econometrics; Clinical trial; Medicine; Internal medicine","score_opus":0.4690235198847609,"score_gpt":0.5372107865117601,"score_spread":0.06818726662699925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127195807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005008145,0.00002975597,0.9923706,0.00007336487,0.00004436851,0.0005629467,0.006285072,0.00001757499,0.00011549907],"genre_scores_gemma":[0.03500222,0.00002936666,0.9645604,0.000035701625,0.00002860806,0.00008893089,0.00017230796,0.0000134942975,0.00006896687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99858886,0.0003274641,0.0005655847,0.00022843048,0.00016534804,0.00012430768],"domain_scores_gemma":[0.9353122,0.0635751,0.0003138401,0.00020700869,0.00052227813,0.000069540445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015280409,0.00011276119,0.0005863684,0.00020857342,0.000055875244,0.000019080358,0.00006927474,0.0000716982,0.00021980323],"category_scores_gemma":[0.087930724,0.000089609464,0.00008131832,0.0012382467,0.0001487896,0.000017987564,0.0000070449587,0.000044347038,0.0000011744531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022413216,0.0003842437,0.0011152249,0.00023870742,0.0055674454,9.724079e-7,0.000025350642,0.00013026754,0.000034556804,0.98313016,0.0058415756,0.0012901529],"study_design_scores_gemma":[0.0062875156,0.0005412538,0.002406667,0.000016319773,0.023819964,9.696606e-7,0.000022502543,0.0040330947,0.00035526042,0.96161246,0.0006856323,0.00021835527],"about_ca_topic_score_codex":0.0000017113479,"about_ca_topic_score_gemma":0.000010806445,"teacher_disagreement_score":0.086402684,"about_ca_system_score_codex":0.000016348997,"about_ca_system_score_gemma":0.00015620141,"threshold_uncertainty_score":0.919752},"labels":[],"label_agreement":null},{"id":"W2128514707","doi":"10.1093/biostatistics/kxm029","title":"Joint inference for nonlinear mixed-effects models and time to event at the presence of missing data","year":2007,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Covariate; Inference; Missing data; Event (particle physics); Computer science; Econometrics; Proportional hazards model; Mixed model; Process (computing); Statistical inference; Longitudinal data; Counting process; Event data; Statistics; Data mining; Artificial intelligence; Mathematics; Machine learning","score_opus":0.13065622976442884,"score_gpt":0.41384063250208264,"score_spread":0.2831844027376538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128514707","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013242038,0.000072759016,0.99527717,0.00023208752,0.00009222819,0.0006676343,0.0021045539,0.000017877801,0.00021147098],"genre_scores_gemma":[0.016598478,0.000008978365,0.98301166,0.00009788621,0.000052409705,0.000009973479,0.0000440026,0.000019965868,0.00015661519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986217,0.000090154965,0.0004439459,0.0003069498,0.00024914194,0.00028809108],"domain_scores_gemma":[0.98636115,0.012521143,0.00016966666,0.00063597824,0.00016465771,0.00014743574],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013380821,0.000155503,0.00030304756,0.000041370226,0.00012228424,0.000035143836,0.00031184667,0.00006136353,0.00003677754],"category_scores_gemma":[0.012828625,0.00010935076,0.000022743769,0.000112811955,0.00016441519,0.000056299807,0.00043521036,0.000082116996,0.00001052047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011902974,0.0001391736,0.000043019878,0.0009189491,0.00004656073,0.000016826498,0.00046845168,0.000008921218,0.0053771785,0.5740626,0.016630385,0.4021689],"study_design_scores_gemma":[0.0002954506,0.00024710767,0.0007051636,0.00027892357,0.00010227599,0.000010569542,0.0000346762,0.19834098,0.00899775,0.7896129,0.0011485238,0.00022566845],"about_ca_topic_score_codex":0.00001693537,"about_ca_topic_score_gemma":0.000018228138,"teacher_disagreement_score":0.40194324,"about_ca_system_score_codex":0.000027099633,"about_ca_system_score_gemma":0.000050844246,"threshold_uncertainty_score":0.99548674},"labels":[],"label_agreement":null},{"id":"W2128581110","doi":"10.1093/biostatistics/3.3.299","title":"Experimental design issues for the early detection of disease: novel designs","year":2002,"lang":"en","type":"article","venue":"Biostatistics","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Family medicine; Group (periodic table); Outcome (game theory); Medical physics; Mathematics","score_opus":0.23445914822665576,"score_gpt":0.37581462923286985,"score_spread":0.1413554810062141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128581110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013692123,0.0039703557,0.98119265,0.00028423587,0.00013788106,0.0005327755,0.00011093133,0.00002204628,0.000057025274],"genre_scores_gemma":[0.958041,0.000054483993,0.04131938,0.0001409347,0.00011253633,0.00003473577,0.0000040871532,0.000010306462,0.00028253117],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944806,0.000011587022,0.00013775966,0.00010170321,0.00017855683,0.00012232966],"domain_scores_gemma":[0.9994697,0.00018494288,0.000054902004,0.00013370969,0.00008916414,0.00006760925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008664827,0.00007187031,0.000101566664,0.000021511507,0.000079215766,0.000012189924,0.00005492469,0.000026025096,0.000059461807],"category_scores_gemma":[0.00019572006,0.000051766645,0.00003998418,0.00007204111,0.00006820286,0.000032769927,0.000009607681,0.000037124515,0.0000072476855],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031247283,0.00058739656,0.0030707296,0.00021227819,0.00024279338,0.00003230937,0.0024798382,0.0002578303,0.90041286,0.006123445,0.034187507,0.04926829],"study_design_scores_gemma":[0.003908729,0.0050925026,0.06368142,0.00028454707,0.00072177453,0.000032434993,0.0015757859,0.08591311,0.8215536,0.00051021343,0.01628812,0.00043779484],"about_ca_topic_score_codex":0.00007792556,"about_ca_topic_score_gemma":0.0000021785559,"teacher_disagreement_score":0.9443489,"about_ca_system_score_codex":0.000036396625,"about_ca_system_score_gemma":0.000017725093,"threshold_uncertainty_score":0.21109825},"labels":[],"label_agreement":null},{"id":"W2134647083","doi":"10.1093/biostatistics/kxn037","title":"Statistical monitoring of clinical trials with multivariate response and/or multiple arms: a flexible approach","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Interim; Multivariate statistics; Clinical trial; Robustness (evolution); Computer science; Randomized controlled trial; Interim analysis; Multivariate analysis; Statistics; Medicine; Mathematics; Machine learning; Internal medicine","score_opus":0.8559835100558566,"score_gpt":0.644237374207395,"score_spread":0.21174613584846158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134647083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09901484,0.000045617922,0.89688945,0.00006602363,0.0005710262,0.0010907385,0.002035609,0.00014212959,0.0001445635],"genre_scores_gemma":[0.2086388,0.00013651226,0.79048365,0.000030024587,0.00035756483,0.000056868386,0.000007907564,0.00007422724,0.00021441287],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9847631,0.008692994,0.0042870934,0.00082944473,0.0008563355,0.0005710188],"domain_scores_gemma":[0.6825101,0.31504798,0.0011466305,0.0005794104,0.00031198753,0.00040394304],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.023402935,0.00044518826,0.0028309838,0.00014729323,0.00017006454,0.00003651802,0.00031377058,0.00039160278,0.00010524506],"category_scores_gemma":[0.62918097,0.00029506543,0.0001692872,0.00035465558,0.0013517899,0.00007553144,0.00016724234,0.00062019797,0.000011307708],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24616756,0.009590223,0.3115653,0.0037034082,0.00308989,0.002122219,0.004679816,0.000051390885,0.003339944,0.27343056,0.011486635,0.13077305],"study_design_scores_gemma":[0.04035088,0.0102179665,0.5279213,0.0012160289,0.0022657204,0.0005399532,0.002369328,0.01729994,0.0067141615,0.3870822,0.0014181524,0.0026043737],"about_ca_topic_score_codex":0.000042449803,"about_ca_topic_score_gemma":0.000001736209,"teacher_disagreement_score":0.605778,"about_ca_system_score_codex":0.00004106017,"about_ca_system_score_gemma":0.00044516084,"threshold_uncertainty_score":0.9999502},"labels":[],"label_agreement":null},{"id":"W2135189416","doi":"10.1093/biostatistics/kxg041","title":"Analysis of longitudinal marginal structural models","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Censoring (clinical trials); Inverse probability; Marginal structural model; Confounding; Statistics; Econometrics; Mathematics; Computer science","score_opus":0.15749982260053155,"score_gpt":0.4178060521425315,"score_spread":0.260306229542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135189416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12177934,0.000025267354,0.8768933,0.000029404015,0.00003493088,0.000105963736,0.00035237978,0.000105160216,0.00067425874],"genre_scores_gemma":[0.6052962,0.000008639602,0.39461133,0.000010090134,0.00001044963,0.0000032067676,0.000028134871,0.000009938022,0.000022006981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99900246,0.000018182758,0.00034955036,0.00018181035,0.00025140084,0.00019658598],"domain_scores_gemma":[0.99903154,0.00020944414,0.0002009848,0.00031404968,0.00018423819,0.000059731137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010278928,0.0001453607,0.00035979907,0.00022473851,0.00004083445,0.000013010552,0.00016131932,0.000064451975,0.00009019829],"category_scores_gemma":[0.00023859993,0.00013177094,0.00008715982,0.00053193077,0.00013042313,0.00011021927,0.000049625785,0.00009758246,0.0000024013082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015838139,0.000030635303,0.0016163848,0.0000389739,0.00026807832,0.000015779098,0.00016410052,0.002741324,0.0003888974,0.99377096,0.00008819301,0.0008608267],"study_design_scores_gemma":[0.00017485602,0.000084952815,0.005529739,0.000021477746,0.00067715766,0.0000050506424,0.000044078635,0.008599961,0.003125367,0.98156255,0.000008937463,0.0001658609],"about_ca_topic_score_codex":0.00006711926,"about_ca_topic_score_gemma":0.000084062856,"teacher_disagreement_score":0.48351687,"about_ca_system_score_codex":0.00008435136,"about_ca_system_score_gemma":0.000048389073,"threshold_uncertainty_score":0.5373463},"labels":[],"label_agreement":null},{"id":"W2138916823","doi":"10.1093/biostatistics/kxs024","title":"Targeted maximum likelihood estimation for marginal time-dependent treatment effects under density misspecification","year":2012,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Estimator; Statistics; Generalized estimating equation; Mathematics; Econometrics; Delta method; Parametric statistics; Confounding; Random effects model; Variance (accounting); Computer science; Medicine; Meta-analysis","score_opus":0.08074750171030778,"score_gpt":0.3757055195828782,"score_spread":0.29495801787257037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138916823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010366244,0.000089693116,0.9873368,0.000111751,0.00018420535,0.0011656233,0.00017456572,0.00035467502,0.00021642196],"genre_scores_gemma":[0.35529116,0.000020656425,0.64384556,0.00004524639,0.000114248694,0.00015222638,0.00023437921,0.000044066303,0.00025245355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987628,0.00007339808,0.00030641668,0.00022497038,0.00021579872,0.000416625],"domain_scores_gemma":[0.99804837,0.0010761986,0.00021480149,0.00033977974,0.00016994955,0.00015090186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025808287,0.00024759703,0.00026655043,0.00007567987,0.00012505816,0.000033314507,0.00009523938,0.00012566401,0.000059839414],"category_scores_gemma":[0.0006104006,0.00022576582,0.000054914814,0.00008503012,0.000046501795,0.00016035917,0.000025869966,0.000070381844,0.00012607107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037018987,0.0025555447,0.0011088533,0.00082286174,0.00030509316,0.000014581096,0.0012148406,0.00005080237,0.095572725,0.66402406,0.024154523,0.20980595],"study_design_scores_gemma":[0.0008218311,0.00051891065,0.0026177731,0.000051933326,0.00023692522,0.000015975753,0.000050192317,0.004841069,0.18111208,0.8083027,0.0010101544,0.00042043033],"about_ca_topic_score_codex":0.000009375449,"about_ca_topic_score_gemma":0.0000058741916,"teacher_disagreement_score":0.3449249,"about_ca_system_score_codex":0.00044259452,"about_ca_system_score_gemma":0.000045412256,"threshold_uncertainty_score":0.9206463},"labels":[],"label_agreement":null},{"id":"W2146901830","doi":"10.1093/biostatistics/kxu026","title":"Multiple comparison procedures for neuroimaging genomewide association studies","year":2014,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Genentech; IXICO; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Novartis Pharmaceuticals Corporation; Wellcome Trust; Synarc; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; National Science Foundation","keywords":"Neuroimaging; Imaging genetics; Univariate; False discovery rate; Computer science; Alzheimer's Disease Neuroimaging Initiative; Multiple comparisons problem; Dimensionality reduction; Genome-wide association study; Brain size; Statistical power; Computational biology; Artificial intelligence; Machine learning; Single-nucleotide polymorphism; Neuroscience; Magnetic resonance imaging; Biology; Multivariate statistics; Medicine; Statistics; Genetics; Gene; Genotype; Mathematics; Cognition","score_opus":0.03238930918415187,"score_gpt":0.3310335732112797,"score_spread":0.2986442640271278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146901830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54844576,0.0017424058,0.44528493,0.0021971874,0.00095056166,0.0006411397,0.00033935768,0.000047584992,0.0003510457],"genre_scores_gemma":[0.94779295,0.00016848637,0.0498687,0.0008629338,0.00034749927,0.000048793863,0.00029012977,0.00001947302,0.00060105795],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990538,0.00009024058,0.00027423224,0.00024603782,0.00007610203,0.00025962267],"domain_scores_gemma":[0.99875057,0.00056959625,0.00023406613,0.00014727822,0.00025507956,0.00004343045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004313058,0.00011580203,0.00020856423,0.000026186302,0.00014452901,0.000016039789,0.00009031414,0.00009776873,0.0000015189852],"category_scores_gemma":[0.014200329,0.00011408203,0.000050244893,0.00004052021,0.000032427346,0.000001468241,0.000049502243,0.000046456607,0.000007415411],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037538168,0.00006816727,0.7596996,0.00009572175,0.00019972525,1.8657744e-7,0.00017783503,0.0008481422,0.03432302,0.00078049675,0.1980958,0.0056737983],"study_design_scores_gemma":[0.0020256697,0.0008888318,0.48975858,0.000023577031,0.00019140163,0.0000040616524,0.0005294672,0.028755099,0.008967101,0.0040623527,0.4641142,0.00067968527],"about_ca_topic_score_codex":0.0000074504114,"about_ca_topic_score_gemma":0.00009787112,"teacher_disagreement_score":0.39934716,"about_ca_system_score_codex":0.000040974548,"about_ca_system_score_gemma":0.00003975583,"threshold_uncertainty_score":0.9941035},"labels":[],"label_agreement":null},{"id":"W2148628375","doi":"10.1093/biostatistics/4.2.167","title":"Analysis of a molecular genetic neuro-oncology study with partially biased selection","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Ottawa Regional Cancer Foundation","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Chemotherapy; Oncology; Internal medicine; Disease; Radiation therapy; Population; Cancer; Radiation oncology","score_opus":0.01655065745641814,"score_gpt":0.29282907121953483,"score_spread":0.2762784137631167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148628375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898827,0.000063441985,0.009358534,0.000052301282,0.0000267202,0.0004257068,0.000028055987,0.000014081609,0.00014846548],"genre_scores_gemma":[0.9865937,0.000011523341,0.013202932,0.000113916954,0.000005366054,0.00003253455,0.000023105558,0.000011866558,0.0000050499916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99919015,0.00010550326,0.00020837827,0.00018585012,0.00018304626,0.00012705746],"domain_scores_gemma":[0.9993855,0.0001216142,0.00009915128,0.00016668135,0.00014779127,0.00007931215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000063101725,0.000099532175,0.00032197376,0.00021590607,0.000025815105,0.000006019401,0.00002148018,0.000032366068,0.000070089605],"category_scores_gemma":[0.00016198558,0.00007603253,0.000048428738,0.00080350373,0.000033395998,0.0000061381397,0.0000047362205,0.000040350882,0.000003871608],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016415417,0.0029067388,0.9710041,0.000014445914,0.0025104193,0.0010211259,0.00016882562,0.0016932219,0.017924884,0.00040186706,0.00010648653,0.0020837104],"study_design_scores_gemma":[0.0035745772,0.008869575,0.94291157,0.000009157722,0.013488635,0.000050043116,0.00020474938,0.0027632648,0.027454056,0.000019620986,0.00053119083,0.00012356418],"about_ca_topic_score_codex":0.00007750253,"about_ca_topic_score_gemma":0.0002876465,"teacher_disagreement_score":0.028092556,"about_ca_system_score_codex":0.000044665216,"about_ca_system_score_gemma":0.00011732465,"threshold_uncertainty_score":0.31005165},"labels":[],"label_agreement":null},{"id":"W2153510570","doi":"10.1093/biostatistics/kxq048","title":"Feature selection in finite mixture of sparse normal linear models in high-dimensional feature space","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"","keywords":"Feature selection; Curse of dimensionality; Computer science; Bayesian information criterion; Maximization; Feature vector; Feature (linguistics); Boosting (machine learning); Bayesian probability; Data mining; Machine learning; Algorithm; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.03465438392887245,"score_gpt":0.3177505091851537,"score_spread":0.28309612525628125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153510570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37449875,0.00007566534,0.6189557,0.0021529994,0.0008537216,0.00069539447,0.0018468314,0.00007636912,0.0008446194],"genre_scores_gemma":[0.29945257,0.000008960307,0.69998044,0.00008324857,0.0000821548,0.0000069647526,0.000032589123,0.000021775804,0.00033129766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986579,0.00012446105,0.0003131857,0.00028070752,0.00030813328,0.00031564257],"domain_scores_gemma":[0.99763936,0.0016942364,0.00017315606,0.00019624212,0.00020094775,0.00009605123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004031589,0.0002211216,0.00039338224,0.00017396607,0.00003702161,0.000015621756,0.00014006607,0.00037447718,0.000102761514],"category_scores_gemma":[0.003047716,0.00019550236,0.000037142992,0.00044495435,0.00010168338,0.000072762334,0.000056260407,0.00096220546,0.0000065154577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002166833,0.00038913844,0.0035974237,0.00027578804,0.000021068767,0.00007670955,0.00040269695,0.0012461755,0.014203818,0.95858395,0.016820863,0.004165708],"study_design_scores_gemma":[0.0016421333,0.00028216763,0.032885626,0.00024740607,0.000055885615,0.000032455915,0.000045442674,0.33338398,0.0063188123,0.62350535,0.0010382849,0.00056245347],"about_ca_topic_score_codex":0.00015806027,"about_ca_topic_score_gemma":0.0010303751,"teacher_disagreement_score":0.33507857,"about_ca_system_score_codex":0.000032432545,"about_ca_system_score_gemma":0.000113087386,"threshold_uncertainty_score":0.79723555},"labels":[],"label_agreement":null},{"id":"W2156745572","doi":"10.1093/biostatistics/kxp041","title":"Bayesian random-effects threshold regression with application to survival data with nonproportional hazards","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute for Occupational Safety and Health","keywords":"Bayesian probability; Regression; Statistics; Proportional hazards model; Regression analysis; Econometrics; Computer science; Mathematics","score_opus":0.03665299856253803,"score_gpt":0.35921251095346285,"score_spread":0.32255951239092484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156745572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00069655484,0.000009153455,0.9918276,0.003337659,0.000040055806,0.0010723285,0.0016450133,0.0001726904,0.0011989336],"genre_scores_gemma":[0.6561767,0.0000042482607,0.34030196,0.0007899307,0.00006486179,0.00010050458,0.0023901272,0.00002650134,0.0001451795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981394,0.000044721663,0.00036911998,0.00052138075,0.0006439452,0.000281439],"domain_scores_gemma":[0.99777657,0.00054588146,0.0001949787,0.0009370524,0.00027816882,0.00026732555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027275734,0.00024631532,0.00029621212,0.00006769978,0.00023334497,0.00007715284,0.00035331075,0.00006538976,0.00007064237],"category_scores_gemma":[0.0006173083,0.00017207203,0.000018810631,0.0004317725,0.000101460995,0.00011155644,0.000051854993,0.00014460663,0.000048325997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039441691,0.0004074502,0.00028699276,0.000063904474,0.000032444725,0.000019689154,0.000045000066,0.00007757792,0.00036803677,0.92081255,0.057607405,0.019884525],"study_design_scores_gemma":[0.012766661,0.0023855856,0.064247295,0.00086376537,0.00081442983,0.00016630087,0.00023953358,0.48559213,0.0029163635,0.39397487,0.033441447,0.0025915953],"about_ca_topic_score_codex":0.000007863588,"about_ca_topic_score_gemma":0.00003494596,"teacher_disagreement_score":0.65548015,"about_ca_system_score_codex":0.00006270405,"about_ca_system_score_gemma":0.00013565629,"threshold_uncertainty_score":0.70168936},"labels":[],"label_agreement":null},{"id":"W2159353629","doi":"10.1093/biostatistics/5.1.129","title":"Tests for multivariate recurrent events in the presence of a terminal event","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Univariate; Multivariate statistics; Medicine; Event (particle physics); Inference; Statistical hypothesis testing; Statistics; Breast cancer; Multivariate analysis; Econometrics; Cancer; Computer science; Internal medicine; Mathematics; Artificial intelligence","score_opus":0.5050057957657591,"score_gpt":0.5862204328749212,"score_spread":0.0812146371091621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159353629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02305116,0.0000307359,0.9727254,0.00047424974,0.0006638001,0.0017858462,0.001158879,0.000020141026,0.00008982123],"genre_scores_gemma":[0.31942186,0.000009469637,0.6803173,0.000048248043,0.00007419078,0.00009558794,0.000003803801,0.000014138836,0.000015399095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99770707,0.0004412963,0.0009458718,0.00025257602,0.00037783175,0.00027536682],"domain_scores_gemma":[0.9521536,0.046932787,0.00034869285,0.0003764613,0.00013126494,0.000057180365],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026459543,0.00015571465,0.00039677866,0.00005187522,0.000042555923,0.0000084239955,0.00038509312,0.00009030328,0.000015830226],"category_scores_gemma":[0.13393886,0.00010681761,0.000087029046,0.0001835357,0.00012631273,0.000025046309,0.000063238076,0.00016850106,0.000005104196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004986702,0.0020179981,0.0009090003,0.00083538285,0.00005502657,0.00003661433,0.00160107,0.000038463593,0.00050482433,0.95139277,0.0015691732,0.04054099],"study_design_scores_gemma":[0.0018181208,0.00046041064,0.010779195,0.00030913256,0.00006568938,0.0000061839537,0.00008097186,0.00046298653,0.00045518254,0.98527384,0.00015663754,0.00013165042],"about_ca_topic_score_codex":0.000032770626,"about_ca_topic_score_gemma":0.000033375334,"teacher_disagreement_score":0.29637071,"about_ca_system_score_codex":0.00005577249,"about_ca_system_score_gemma":0.000098598204,"threshold_uncertainty_score":0.87335634},"labels":[],"label_agreement":null},{"id":"W2163180646","doi":"10.1093/biostatistics/kxm053","title":"Efficient p-value estimation in massively parallel testing problems","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; Toronto Public Health","funders":"National Cancer Institute","keywords":"Computer science; Bayesian probability; Test statistic; Statistic; Null (SQL); Set (abstract data type); Massively parallel; Fraction (chemistry); Null distribution; Permutation (music); Algorithm; Statistical hypothesis testing; Mathematics; Statistics; Data mining; Artificial intelligence; Parallel computing","score_opus":0.02946165175741932,"score_gpt":0.2710030859782423,"score_spread":0.24154143422082297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163180646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8071849,0.00017671529,0.19130455,0.00016617711,0.000101927006,0.00020322573,0.00004899995,0.000012659721,0.00080085377],"genre_scores_gemma":[0.8016528,0.000037316502,0.19784676,0.00012900787,0.000038170092,0.000019378338,0.00011825118,0.000010919679,0.00014742406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9990847,0.00007628268,0.00028117016,0.00023302643,0.00008454481,0.00024023587],"domain_scores_gemma":[0.9995243,0.00007374326,0.00012355523,0.00014956003,0.00008010789,0.00004872468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019843112,0.00010868455,0.00012993226,0.00004240745,0.00009526992,0.000005338847,0.00008169551,0.00011600179,0.000004582211],"category_scores_gemma":[0.0012588964,0.00010871672,0.000023840399,0.00012370344,0.00007217831,6.5523744e-7,0.00004630728,0.0000658909,0.000020423466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021110865,0.00017569688,0.25030637,0.000029600302,0.000028036804,0.00002278522,0.00020996692,0.7201912,0.018979756,0.0013219432,0.005027426,0.0036861498],"study_design_scores_gemma":[0.00060530764,0.00021332197,0.68514764,0.000016968459,0.000009708121,0.000044200937,0.000036444108,0.31156218,0.00030319317,0.0006841212,0.0011439482,0.00023294784],"about_ca_topic_score_codex":0.00008341653,"about_ca_topic_score_gemma":0.000022044833,"teacher_disagreement_score":0.43484128,"about_ca_system_score_codex":0.000028073662,"about_ca_system_score_gemma":0.000092864124,"threshold_uncertainty_score":0.44333392},"labels":[],"label_agreement":null},{"id":"W2163628937","doi":"10.1093/biostatistics/kxn044","title":"Bias in 2-part mixed models for longitudinal semicontinuous data","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Toronto","keywords":"Random effects model; Mixed model; Censoring (clinical trials); Statistics; Missing data; Econometrics; Monte Carlo method; Independence (probability theory); Mathematics; Variance (accounting); Computer science; Medicine; Meta-analysis","score_opus":0.45668331579765237,"score_gpt":0.4407942544428088,"score_spread":0.01588906135484358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163628937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005491724,0.00007225349,0.98902607,0.00023936242,0.00027345694,0.00040479947,0.0031553567,0.000055526867,0.0012814512],"genre_scores_gemma":[0.12216425,0.000031117474,0.8771074,0.0001529486,0.000120828045,0.000012724679,0.00018252457,0.000020174019,0.00020808252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839324,0.00008715456,0.0005220519,0.00042223587,0.00019915373,0.00037618703],"domain_scores_gemma":[0.9960042,0.0029295871,0.00013929376,0.0007027226,0.0001222167,0.00010194835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007977887,0.00018775393,0.00037048003,0.00007179427,0.00005507528,0.000055501565,0.00041376974,0.00009467952,0.00004265748],"category_scores_gemma":[0.0075804465,0.00017103786,0.00002951887,0.00015020867,0.000058184338,0.00009648411,0.00008323654,0.00013365295,0.00000921945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050067814,0.00017768877,0.0002464791,0.00006782379,0.000011958382,0.00002288795,0.000079924175,0.000011948049,0.00008663034,0.8890145,0.053210605,0.057019524],"study_design_scores_gemma":[0.0005546626,0.00018282312,0.0015388086,0.00008078473,0.000044962944,0.000007156122,0.0000411092,0.11176584,0.00014207057,0.88322645,0.0021772387,0.00023806623],"about_ca_topic_score_codex":0.000021141135,"about_ca_topic_score_gemma":0.000059993068,"teacher_disagreement_score":0.11667252,"about_ca_system_score_codex":0.000034316374,"about_ca_system_score_gemma":0.00006801661,"threshold_uncertainty_score":0.90750504},"labels":[],"label_agreement":null},{"id":"W2163976725","doi":"10.1093/biostatistics/3.3.407","title":"A generalized mover-stayer model for panel data","year":2002,"lang":"en","type":"article","venue":"Biostatistics","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Heart, Lung, and Blood Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Markov model; Markov chain; Markov process; Mathematics; Applied mathematics; Markov property; Computer science; Maximum likelihood; Statistics; Econometrics","score_opus":0.31346745460044456,"score_gpt":0.3641039722663774,"score_spread":0.050636517665932856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163976725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049071326,0.00009649763,0.98048025,0.0044747735,0.00016317274,0.00051902106,0.0055996915,0.00006707994,0.0036923653],"genre_scores_gemma":[0.14341956,0.00025613606,0.8283409,0.016574496,0.00013241888,0.000024687031,0.00046132,0.000038862207,0.0107515985],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897915,0.000025658926,0.00020734499,0.00026779098,0.00019710464,0.00032294574],"domain_scores_gemma":[0.9991384,0.00010724595,0.00006916663,0.00050135714,0.0000069661937,0.00017685229],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021661208,0.000100267236,0.00011868111,0.000010968347,0.00014694287,0.000023944407,0.00030536568,0.000059800557,0.0013274881],"category_scores_gemma":[0.00025262806,0.00009337496,0.000015843758,0.00006390885,0.00008436686,0.00014101993,0.00017594319,0.000057047993,0.0004405794],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023470599,0.00010068959,0.0003768255,0.0000394524,0.000006535756,0.0000029780808,0.00067412265,0.0027191208,0.000093983195,0.0057707033,0.95140994,0.0387822],"study_design_scores_gemma":[0.00035818398,0.0000340874,0.0005354428,0.000002889652,0.000011645142,0.0000013432721,0.000012555046,0.84481233,0.00001329395,0.0038586801,0.15024215,0.000117404285],"about_ca_topic_score_codex":0.00016679769,"about_ca_topic_score_gemma":0.00013232455,"teacher_disagreement_score":0.84209317,"about_ca_system_score_codex":0.00006931081,"about_ca_system_score_gemma":0.000010882746,"threshold_uncertainty_score":0.99958545},"labels":[],"label_agreement":null},{"id":"W2165213086","doi":"10.1093/biostatistics/kxj007","title":"Hybrid hierarchical clustering with applications to microarray data","year":2005,"lang":"en","type":"article","venue":"Biostatistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":161,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs; National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Data mining; Single-linkage clustering; Correlation clustering; Identification (biology); Cluster (spacecraft); CURE data clustering algorithm; Consensus clustering; Brown clustering; Artificial intelligence","score_opus":0.02578921853755773,"score_gpt":0.29945617986579215,"score_spread":0.2736669613282344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165213086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076715252,0.00013064624,0.9893462,0.0011140804,0.000042829626,0.0002483823,0.00045063833,0.000017052129,0.0009786349],"genre_scores_gemma":[0.74383354,0.00007185816,0.25108135,0.0013291909,0.00051907013,0.00007685903,0.0015913063,0.00002617219,0.0014706431],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928087,0.000017027807,0.00012051363,0.00034880245,0.00009314002,0.00013964843],"domain_scores_gemma":[0.99908036,0.000007215912,0.000037007998,0.00071351766,0.00004941837,0.00011246303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059730915,0.00008799963,0.0000609722,0.000030415107,0.00006981022,0.000027437998,0.00030829888,0.000032958687,0.000020071242],"category_scores_gemma":[0.000025600655,0.000077620985,0.000009257311,0.000060641414,0.00003873948,0.0000026756531,0.00016452951,0.000047904632,0.000047376136],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108308945,0.00008227721,0.00026315646,0.000017298213,0.000023797582,0.0000013673157,0.000032496075,0.0002731814,0.7777805,0.00076618255,0.092083275,0.12856817],"study_design_scores_gemma":[0.00020629092,0.00007529495,0.0007591657,0.0000069258767,0.000009515743,0.000013933743,0.000019394818,0.0006842291,0.061058626,0.000020198038,0.9370084,0.00013807134],"about_ca_topic_score_codex":0.000002938585,"about_ca_topic_score_gemma":0.000039760915,"teacher_disagreement_score":0.8449251,"about_ca_system_score_codex":0.000011873031,"about_ca_system_score_gemma":0.00006442649,"threshold_uncertainty_score":0.31652918},"labels":[],"label_agreement":null},{"id":"W2166050184","doi":"10.1093/biostatistics/kxq041","title":"A multistate model for events defined by prolonged observation","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Duration (music); Event (particle physics); Spontaneous remission; Complete remission; State (computer science); Medicine; Computer science; Statistics; Mathematics; Internal medicine; Algorithm; Physics; Alternative medicine","score_opus":0.5493913029206225,"score_gpt":0.544768454180002,"score_spread":0.004622848740620578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166050184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016658118,0.000006156317,0.97503346,0.0004783812,0.0008827472,0.0012565318,0.005468068,0.00013662038,0.00007993528],"genre_scores_gemma":[0.028244812,0.0000074593327,0.96974057,0.00027084505,0.00015832268,0.00024616384,0.00010034527,0.000071427625,0.001160039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99780715,0.00015759154,0.0008904955,0.00041535005,0.00032894328,0.00040047028],"domain_scores_gemma":[0.9722064,0.026461724,0.00037322522,0.0004485253,0.00033078957,0.0001793474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016878496,0.0002419592,0.00046840945,0.000040639356,0.00013187222,0.00003725796,0.00026785204,0.00024982993,0.000057834513],"category_scores_gemma":[0.14238667,0.00022247985,0.000093869356,0.000119644785,0.00011699368,0.000058049893,0.000055522945,0.00031178602,0.000022071627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048960146,0.00089430134,0.00085691107,0.00047387768,0.0001169148,0.000004784389,0.00025373997,0.00001622899,0.028882684,0.8013471,0.12623717,0.040426698],"study_design_scores_gemma":[0.0013896237,0.00010443162,0.00030801876,0.000015805459,0.00009564103,0.0000011583256,0.0000050740655,0.20794438,0.0012016824,0.7876537,0.0010472125,0.00023329235],"about_ca_topic_score_codex":0.000007953976,"about_ca_topic_score_gemma":0.00003961045,"teacher_disagreement_score":0.20792815,"about_ca_system_score_codex":0.00003123379,"about_ca_system_score_gemma":0.00008466709,"threshold_uncertainty_score":0.90724653},"labels":[],"label_agreement":null},{"id":"W2168126634","doi":"10.1093/biostatistics/kxs028","title":"Testing multiple variance components in linear mixed-effects models","year":2012,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Mathematics; Statistics; Test statistic; Null distribution; Estimator; Variance (accounting); Statistical hypothesis testing; Variance-based sensitivity analysis; One-way analysis of variance; Context (archaeology); Analysis of variance","score_opus":0.17829970945503099,"score_gpt":0.36776649057259386,"score_spread":0.18946678111756288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168126634","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012879236,0.000064424465,0.98487306,0.000017787252,0.00065677863,0.00030116047,0.0001862077,0.00007434246,0.0009470058],"genre_scores_gemma":[0.4166419,0.00000269168,0.58315736,0.00004489686,0.000090472306,0.00001618669,0.000008368973,0.00002126139,0.00001688979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983423,0.00022604901,0.00042071755,0.00021984575,0.00024366123,0.00054747186],"domain_scores_gemma":[0.99029446,0.009022687,0.00013683918,0.00026621926,0.00009222258,0.00018755913],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005312062,0.00020836985,0.0003383442,0.00007372894,0.0000757434,0.000024938094,0.00016071103,0.000103040686,0.000018991199],"category_scores_gemma":[0.010494066,0.00019421756,0.000026552345,0.00026783562,0.000075345495,0.00013276224,0.000082573846,0.00021486677,0.000047197682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019890647,0.0004220424,0.027378801,0.0003736289,0.000015601416,0.00003789537,0.00033017984,0.000013124163,0.0018679488,0.9342376,0.0008470415,0.034456253],"study_design_scores_gemma":[0.0006478045,0.00006324928,0.07043312,0.00022518933,0.000033831653,0.000011951245,0.000029321058,0.17162068,0.0006343875,0.7558316,0.0001303018,0.0003385839],"about_ca_topic_score_codex":0.00008504954,"about_ca_topic_score_gemma":0.000008914762,"teacher_disagreement_score":0.40376264,"about_ca_system_score_codex":0.00005978022,"about_ca_system_score_gemma":0.00002534824,"threshold_uncertainty_score":0.99784094},"labels":[],"label_agreement":null},{"id":"W2170016983","doi":"10.1093/biostatistics/kxm054","title":"A simulation-based marginal method for longitudinal data with dropout and mismeasured covariates","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Heart, Lung, and Blood Institute","keywords":"Covariate; Missing data; Estimator; Observational error; Statistics; Computer science; Econometrics; Dropout (neural networks); Framingham Heart Study; Data set; Inference; Mathematics; Artificial intelligence; Machine learning","score_opus":0.18878984038607685,"score_gpt":0.42635502145611714,"score_spread":0.2375651810700403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170016983","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023249895,0.000033324613,0.996365,0.00016667358,0.00005753211,0.00040802485,0.00261963,0.000052753905,0.000064529384],"genre_scores_gemma":[0.09244496,0.0000034510078,0.9071747,0.00007630724,0.00006414667,0.000018712612,0.0001473077,0.00003072499,0.00003970124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985952,0.00013055948,0.0003033619,0.0004372695,0.00026944352,0.00026420096],"domain_scores_gemma":[0.9835678,0.0153790545,0.00015026156,0.00049386633,0.0002797989,0.00012925337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054837286,0.00020509447,0.00034173514,0.00005711436,0.00023036671,0.000049889382,0.00020342467,0.00007358916,0.000060451617],"category_scores_gemma":[0.008088784,0.00016160557,0.000019335232,0.00012672815,0.00019808943,0.000062288214,0.000049648137,0.000099574194,0.000002605718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009673245,0.000362369,0.01466574,0.00085180934,0.00021329027,0.00017096166,0.0002865019,0.00032391306,0.0001597521,0.94220895,0.004798123,0.03499129],"study_design_scores_gemma":[0.0012192169,0.0002894839,0.0043002134,0.00006030785,0.00019159335,0.000023227518,0.00001997701,0.7749585,0.0000782042,0.21779518,0.00078277325,0.0002813558],"about_ca_topic_score_codex":0.00003869481,"about_ca_topic_score_gemma":0.00002371732,"teacher_disagreement_score":0.77463454,"about_ca_system_score_codex":0.000021510306,"about_ca_system_score_gemma":0.00018058646,"threshold_uncertainty_score":0.9683615},"labels":[],"label_agreement":null},{"id":"W2171600077","doi":"10.1093/biostatistics/kxp050","title":"Confidence intervals that match Fisher's exact or Blaker's exact tests","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Exact test; Exact statistics; Confidence interval; Mathematics; Statistics; Credible interval; Coverage probability; Robust confidence intervals; CDF-based nonparametric confidence interval; Tolerance interval; Binomial proportion confidence interval; Confidence region; Confidence distribution; Poisson distribution","score_opus":0.1830855602638954,"score_gpt":0.4425573308257128,"score_spread":0.25947177056181736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171600077","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020284397,0.00006117324,0.99254215,0.00054230687,0.00031802966,0.00045903277,0.0005971782,0.00021048616,0.003241223],"genre_scores_gemma":[0.24371824,0.00008812795,0.75297314,0.0008693583,0.000112230926,0.000014755675,0.000017628265,0.000046825528,0.0021597135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99763256,0.0001844881,0.0006074898,0.0005104932,0.00046578556,0.0005991904],"domain_scores_gemma":[0.9939487,0.00467184,0.00028406098,0.0006191847,0.00018053564,0.00029570758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049205165,0.00039405335,0.00060440256,0.000075235075,0.00014010216,0.0001223562,0.00036308242,0.00016139829,0.0007640657],"category_scores_gemma":[0.006250305,0.00030616697,0.00008560779,0.00018544929,0.00015366166,0.00018714399,0.000070404574,0.00029440355,0.0000775456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023537254,0.00039389252,0.0001516617,0.00023124262,0.000067101086,0.00054925855,0.0005647254,0.000010661487,0.0012752899,0.8230228,0.054037288,0.1194607],"study_design_scores_gemma":[0.00056685525,0.0006466093,0.0020969254,0.00022694719,0.000093706534,0.00007195934,0.00014713804,0.0017304679,0.0015164244,0.98832446,0.004053721,0.0005248055],"about_ca_topic_score_codex":0.000021862204,"about_ca_topic_score_gemma":0.000040965646,"teacher_disagreement_score":0.2416898,"about_ca_system_score_codex":0.00008638298,"about_ca_system_score_gemma":0.000089529276,"threshold_uncertainty_score":0.999939},"labels":[],"label_agreement":null},{"id":"W2198637531","doi":"10.1093/biostatistics/kxv028","title":"Double robust and efficient estimation of a prognostic model for events in the presence of dependent censoring","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Institutes of Health; National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Censoring (clinical trials); Inverse probability weighting; Inverse probability; Estimator; Computer science; Inference; Statistics; Econometrics; Weighting; Missing data; Estimation; Causal inference; Parametric model; Parametric statistics; Mathematics; Artificial intelligence; Posterior probability","score_opus":0.2544352714323289,"score_gpt":0.4149531699672734,"score_spread":0.16051789853494447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198637531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16599455,0.000024222221,0.83313286,0.000017415217,0.00001856662,0.0006934373,0.00006165053,0.000014633611,0.00004267407],"genre_scores_gemma":[0.62993556,0.0000031670338,0.3699932,0.0000018890138,0.0000025929724,0.00004470617,0.0000038021797,0.000005736115,0.000009306256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926466,0.000026053716,0.00027954788,0.000099913865,0.00021871917,0.00011109973],"domain_scores_gemma":[0.99873006,0.0007572192,0.00017422545,0.00015600924,0.00015669416,0.00002581133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047260808,0.000075180826,0.00014532707,0.000046433535,0.000015131724,0.00000420447,0.00010880316,0.000034975757,3.2244884e-7],"category_scores_gemma":[0.0018016566,0.00005705328,0.000011046731,0.00007567147,0.000049304286,0.000035908724,0.000039585506,0.00004789505,1.2710588e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018149165,0.00042517352,0.0022110783,0.0009258334,0.000013705319,0.000002053535,0.006348228,0.38734615,0.00062561355,0.5996433,0.00017065043,0.002106746],"study_design_scores_gemma":[0.00043355438,0.000092994225,0.00022647006,0.000107676395,0.000022439912,0.000001690718,0.00026898878,0.7896598,0.0023856256,0.20674461,6.7313766e-7,0.000055460358],"about_ca_topic_score_codex":0.000015502743,"about_ca_topic_score_gemma":0.000019274778,"teacher_disagreement_score":0.46394104,"about_ca_system_score_codex":0.000028415898,"about_ca_system_score_gemma":0.00004430723,"threshold_uncertainty_score":0.23265652},"labels":[],"label_agreement":null},{"id":"W2254245873","doi":"10.1093/biostatistics/kxv015","title":"Methods to assess an exercise intervention trial based on 3-level functional data","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Ministerio de Ciencia e Innovación; National Science Foundation","keywords":"Random effects model; Functional data analysis; Inference; Principal component analysis; Model selection; Functional principal component analysis; Mathematics; Computer science; Statistics; Artificial intelligence; Medicine; Meta-analysis","score_opus":0.7722899850188043,"score_gpt":0.5685272321347117,"score_spread":0.20376275288409262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2254245873","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006490716,0.0000061006594,0.99308157,0.00011202015,0.0014610247,0.0004824876,0.0031313032,0.00007431965,0.001002116],"genre_scores_gemma":[0.006620752,7.6456683e-7,0.99198186,0.00023773989,0.00025081108,0.00004209246,0.0005601206,0.000033590193,0.00027224963],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975894,0.0006997319,0.00049630913,0.00046453843,0.00050471653,0.00024526485],"domain_scores_gemma":[0.9951539,0.0029811885,0.00014765644,0.0009890925,0.0003294542,0.0003987297],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031674784,0.00019934146,0.0003274174,0.000115439856,0.00006789426,0.00010642666,0.00043049775,0.000098811026,0.00042199498],"category_scores_gemma":[0.022599973,0.00017459069,0.000037882404,0.00020096301,0.00005263037,0.00010135296,0.00016691121,0.00016513786,0.000101306694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011463491,0.0015762633,0.000057851335,0.00012187938,0.000032208995,0.000020159834,0.000111643305,0.000047447025,0.00013608891,0.37941322,0.13170815,0.4753116],"study_design_scores_gemma":[0.02438934,0.0042155883,0.0025561952,0.0003075748,0.00031663993,0.000004751627,0.00031565718,0.26521352,0.0010139053,0.6863954,0.014430056,0.00084134715],"about_ca_topic_score_codex":0.000035548634,"about_ca_topic_score_gemma":0.000015410798,"teacher_disagreement_score":0.47447026,"about_ca_system_score_codex":0.00007311,"about_ca_system_score_gemma":0.0001620404,"threshold_uncertainty_score":0.9856331},"labels":[],"label_agreement":null},{"id":"W2259606755","doi":"10.1093/biostatistics/kxv054","title":"Augmented composite likelihood for copula modeling in family studies under biased sampling","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Psoriasis Foundation","keywords":"Copula (linguistics); Statistics; Quasi-maximum likelihood; Marginal likelihood; Econometrics; Heritability; Maximum likelihood; Sampling bias; Sampling scheme; Marginal model; Importance sampling; Computer science; Mathematics; Sample size determination; Likelihood function; Regression analysis; Biology; Estimator; Genetics; Monte Carlo method","score_opus":0.4362143197409914,"score_gpt":0.46424727938488547,"score_spread":0.028032959643894073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2259606755","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045420814,0.00022973535,0.95253986,0.0002471939,0.00026264458,0.0003931537,0.0007796329,0.000061348066,0.000065591725],"genre_scores_gemma":[0.27717528,0.000099266384,0.7223971,0.0001595237,0.00004798852,0.00004486216,0.000009303432,0.000030763415,0.00003588899],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998404,0.00009930503,0.0005820213,0.00030688508,0.00019932192,0.0004084311],"domain_scores_gemma":[0.9929072,0.0063822977,0.000121216195,0.000224309,0.00027200163,0.00009297126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051442796,0.00021079587,0.00042179244,0.00010105269,0.00009546463,0.000028616661,0.00013247639,0.00007893045,0.000020611176],"category_scores_gemma":[0.0043899086,0.00014751308,0.000047525053,0.00013373204,0.00008531779,0.000040843406,0.00006324717,0.00007936078,0.000010073316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022372125,0.00029837486,0.0006518672,0.0005409918,0.00018599421,0.000013512781,0.00048432164,0.00012681885,0.030897345,0.86220145,0.0021726997,0.102202885],"study_design_scores_gemma":[0.0015404336,0.00014556675,0.000600337,0.00056197186,0.000071148366,0.0000014762213,0.0004108758,0.06113174,0.00061761576,0.93449146,0.00012080974,0.00030654],"about_ca_topic_score_codex":0.000022796678,"about_ca_topic_score_gemma":0.000031206346,"teacher_disagreement_score":0.23175448,"about_ca_system_score_codex":0.00012872858,"about_ca_system_score_gemma":0.000053119253,"threshold_uncertainty_score":0.6015409},"labels":[],"label_agreement":null},{"id":"W2271845266","doi":"10.1093/biostatistics/kxv042","title":"Sieve estimation in a Markov illness-death process under dual censoring","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Censoring (clinical trials); Estimator; Statistics; Inference; Sieve (category theory); Imputation (statistics); Markov chain; Mathematics; Computer science; Parametric statistics; Econometrics; Missing data; Artificial intelligence","score_opus":0.15012141993189768,"score_gpt":0.4187033755424467,"score_spread":0.268581955610549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2271845266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06907449,0.000027030823,0.92600286,0.0001398026,0.00029186747,0.00026667776,0.00014555422,0.00007926928,0.0039724545],"genre_scores_gemma":[0.5060496,0.0000031311115,0.49372616,0.000055638797,0.000034973706,0.000017058312,0.000010651465,0.000019762918,0.00008304176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985339,0.00012573956,0.00041548378,0.00025241467,0.000356859,0.00031557743],"domain_scores_gemma":[0.9979896,0.0012924109,0.00012688406,0.0002106075,0.0002116549,0.0001688407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005619571,0.00018166199,0.00027308147,0.00008992495,0.000041249874,0.00005352995,0.00010978401,0.00009562835,0.000059687958],"category_scores_gemma":[0.0075028543,0.00016480648,0.000018981782,0.00023778423,0.000052166455,0.00007884058,0.000046182493,0.00017200164,0.000036927613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005592259,0.00016061992,0.0016623775,0.0002005479,0.0000144410815,0.000065847686,0.001335442,0.00016860594,0.00005358365,0.97129625,0.0014005931,0.023585761],"study_design_scores_gemma":[0.00063473906,0.000106064035,0.0053641563,0.00010381653,0.000029631474,0.000017103219,0.00081879087,0.047977768,0.00038013878,0.9441546,0.000108515655,0.00030463954],"about_ca_topic_score_codex":0.000045185112,"about_ca_topic_score_gemma":0.000021285208,"teacher_disagreement_score":0.4369751,"about_ca_system_score_codex":0.000114364106,"about_ca_system_score_gemma":0.00014057293,"threshold_uncertainty_score":0.89821595},"labels":[],"label_agreement":null},{"id":"W2320372797","doi":"10.1093/biostatistics/kxt057","title":"Monitoring risk-adjusted medical outcomes allowing for changes over time","year":2013,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Chart; Computer science; Variety (cybernetics); Failure rate; Measure (data warehouse); Data mining; Statistics; Artificial intelligence; Mathematics","score_opus":0.10301405804493143,"score_gpt":0.4256607621804991,"score_spread":0.3226467041355677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320372797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07068125,0.00022011476,0.9233178,0.0011730136,0.002568764,0.00078436814,0.0005962771,0.00021236464,0.00044607473],"genre_scores_gemma":[0.72493154,0.00006094134,0.27003652,0.00024766303,0.000904308,0.00017681123,0.00001905372,0.00007534471,0.0035478063],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99568707,0.00012400259,0.00075441226,0.00062283047,0.0021992777,0.0006123954],"domain_scores_gemma":[0.985795,0.012300516,0.00034641701,0.00048321718,0.0006289382,0.00044589041],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012622041,0.00028064832,0.00050700485,0.00018089205,0.00032936086,0.00031283812,0.00078729214,0.00017801835,0.0011287034],"category_scores_gemma":[0.056233287,0.00021172826,0.00008869148,0.0003774459,0.00015806041,0.0003158646,0.00021655275,0.00026756476,0.0010527464],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031623025,0.000092204835,0.22140835,0.000043757333,0.0000845245,0.000032477466,0.00035288793,0.00006832063,0.0007321706,0.002981221,0.018200358,0.7559721],"study_design_scores_gemma":[0.0021604362,0.0003234525,0.73812455,0.00017345585,0.00012127075,0.000008317335,0.00071256753,0.08159984,0.0022008955,0.15600972,0.017405981,0.0011595319],"about_ca_topic_score_codex":0.00009175008,"about_ca_topic_score_gemma":0.000017080809,"teacher_disagreement_score":0.7548126,"about_ca_system_score_codex":0.0000826791,"about_ca_system_score_gemma":0.0000776819,"threshold_uncertainty_score":0.9997844},"labels":[],"label_agreement":null},{"id":"W2465707019","doi":"10.1093/biostatistics/kxw022","title":"Prediction of cancer drug sensitivity using high-dimensional omic features","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Institute of General Medical Sciences; National Cancer Institute","keywords":"Feature selection; Sensitivity (control systems); Curse of dimensionality; Computational biology; Omics; Computer science; Set (abstract data type); Personalized medicine; Machine learning; Bioinformatics; Artificial intelligence; Biology","score_opus":0.017586134820108467,"score_gpt":0.27013563471640223,"score_spread":0.25254949989629377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465707019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96910536,0.00033457717,0.028474268,0.00028305396,0.00047608078,0.000085463325,0.001196345,0.000008811129,0.00003604347],"genre_scores_gemma":[0.99606997,0.00014662369,0.0027598422,0.00008724583,0.00018104666,0.0000045113816,0.000074250085,0.000011123091,0.0006653718],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941266,0.000052131174,0.00013111424,0.00018898532,0.000115723706,0.000099362864],"domain_scores_gemma":[0.9995466,0.000017602211,0.00010506093,0.0001685584,0.0001201138,0.00004206584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007904086,0.00008016867,0.00007992897,0.000029814324,0.000041068644,0.000004254964,0.000038186226,0.000067776695,0.000027184262],"category_scores_gemma":[0.000055769557,0.000058113877,0.000026691234,0.000043109023,0.000070898044,0.0000023676532,0.000034713274,0.000025253377,0.0000017660212],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056366567,0.0000207115,0.0035171085,0.000009500916,0.000018758183,6.6858655e-7,0.000008504611,0.0000677081,0.97721857,0.00036686397,0.012629816,0.0060854373],"study_design_scores_gemma":[0.00041797294,0.00003688166,0.09214196,0.00004590975,0.000023910066,0.0000045951506,0.000010953811,0.00022784097,0.90288615,0.0001390567,0.0039756065,0.00008915382],"about_ca_topic_score_codex":0.00011788861,"about_ca_topic_score_gemma":0.000055730157,"teacher_disagreement_score":0.08862486,"about_ca_system_score_codex":0.000024497807,"about_ca_system_score_gemma":0.00009718528,"threshold_uncertainty_score":0.23698153},"labels":[],"label_agreement":null},{"id":"W2470470131","doi":"10.1093/biostatistics/kxw026","title":"The positive effects of population-based preferential sampling in environmental epidemiology","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Army Research Office; Defense Advanced Research Projects Agency; National Institute of Environmental Health Sciences; Natural Sciences and Engineering Research Council of Canada; U.S. Environmental Protection Agency; National Science Foundation","keywords":"Sampling (signal processing); Statistics; Population; Context (archaeology); Population density; Econometrics; Estimation; Environmental epidemiology; Sampling bias; Sampling design; Sample (material); Computer science; Environmental science; Sample size determination; Environmental health; Mathematics; Geography; Medicine","score_opus":0.0380394959602653,"score_gpt":0.3242569791752058,"score_spread":0.2862174832149405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470470131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.913131,0.00007518732,0.08363031,0.00218174,0.00021298326,0.00039806703,0.00023264303,0.000012135785,0.00012595938],"genre_scores_gemma":[0.99302894,0.000038421458,0.006376363,0.00048076367,0.00001555768,0.0000048428633,0.00002468355,0.0000059319027,0.000024518507],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99899215,0.00025055459,0.00028651324,0.00013261165,0.00010529668,0.00023290167],"domain_scores_gemma":[0.9955946,0.0040729605,0.0001373581,0.0001258559,0.0000013962419,0.00006781255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037948965,0.00007158021,0.0001236154,0.000014026946,0.000099240555,0.0000023203688,0.000089008325,0.00005452596,0.00012753042],"category_scores_gemma":[0.0009687645,0.000042094423,0.000018950543,0.000037325364,0.00018960313,0.000033955374,0.00004239253,0.00005051731,0.000052577776],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099371624,0.00009244075,0.88518333,0.000032100594,0.000005945773,0.000001663775,0.00015039399,0.00021553307,0.0024478408,0.0052530263,0.0005075105,0.106010854],"study_design_scores_gemma":[0.00033961996,0.00010649472,0.9919529,0.00003555828,0.0000049097835,3.7763348e-7,0.000008163575,0.00048768622,0.0008365127,0.0057138284,0.0004534881,0.000060493912],"about_ca_topic_score_codex":0.0007044063,"about_ca_topic_score_gemma":0.00029919748,"teacher_disagreement_score":0.10676955,"about_ca_system_score_codex":0.00018069701,"about_ca_system_score_gemma":0.000008678715,"threshold_uncertainty_score":0.17165607},"labels":[],"label_agreement":null},{"id":"W2788646752","doi":"10.1093/biostatistics/kxy083","title":"Fast nonconvex deconvolution of calcium imaging data","year":2018,"lang":"en","type":"preprint","venue":"Biostatistics","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Drug Abuse; Canadian Institutes of Health Research; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Deconvolution; Python (programming language); Computer science; Algorithm; Set (abstract data type); Artificial intelligence; Programming language","score_opus":0.10155622646636496,"score_gpt":0.3378078324847482,"score_spread":0.23625160601838324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788646752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09489096,0.0001674944,0.8457513,0.0009276744,0.016227648,0.0011005339,0.03598513,0.00025448555,0.004694782],"genre_scores_gemma":[0.9881992,0.00010715847,0.009243217,0.00042371135,0.00045689015,0.000005767111,0.0011732592,0.000043535456,0.00034730576],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998206,0.00009290139,0.00040831056,0.000754101,0.0003017273,0.00023693204],"domain_scores_gemma":[0.99797535,0.00025654247,0.0004214369,0.0011455856,0.0001291932,0.000071887516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020166373,0.00021444377,0.0002530427,0.00010757907,0.000087185406,0.00007126897,0.0007684056,0.00011612326,0.00007256193],"category_scores_gemma":[0.0010390702,0.0002119101,0.000042088817,0.00011450995,0.00030833596,0.000094267,0.0016400147,0.0002863084,0.000063454354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024012478,0.0005318033,0.007484539,0.0020281246,0.00006602415,0.00021329444,0.00037889194,0.0003821586,0.6860715,0.030105656,0.1712985,0.10119937],"study_design_scores_gemma":[0.00044527493,0.00011735985,0.006372797,0.0002528759,0.00012578299,0.000042040432,0.000034856912,0.92017835,0.048470963,0.01427668,0.008980378,0.0007026178],"about_ca_topic_score_codex":0.00012108964,"about_ca_topic_score_gemma":0.000019841442,"teacher_disagreement_score":0.9197962,"about_ca_system_score_codex":0.000059192844,"about_ca_system_score_gemma":0.00015442287,"threshold_uncertainty_score":0.86414427},"labels":[],"label_agreement":null},{"id":"W2795107686","doi":"10.1093/biostatistics/kxx036","title":"Lagged kernel machine regression for identifying time windows of susceptibility to exposures of complex mixtures","year":2017,"lang":"en","type":"article","venue":"Biostatistics","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"FAS Division of Science, Harvard University; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Environmental Health Sciences; National Science Foundation; National Institutes of Health; Harvard University","keywords":"Regression; Kernel (algebra); Kernel regression; Statistics; Computer science; Regression analysis; Econometrics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.0819267791111343,"score_gpt":0.3532885025019369,"score_spread":0.27136172339080256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795107686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9740325,0.000022168319,0.023326812,0.00013063355,0.00023074643,0.0004039491,0.00093945715,0.000021745544,0.0008919482],"genre_scores_gemma":[0.9332465,0.0000017831666,0.06618242,0.000012438269,0.000045656405,0.0000044170306,0.00003117298,0.0000103767225,0.0004652713],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99900573,0.000044088927,0.00032943883,0.00020996983,0.00024189931,0.00016888526],"domain_scores_gemma":[0.99891526,0.00020576398,0.0003660655,0.00040735299,0.000031355972,0.00007419512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046345044,0.0001070489,0.00021848934,0.000019769062,0.0002563297,0.000025184541,0.00030952386,0.000048913073,0.00027924275],"category_scores_gemma":[0.00096736505,0.00009102438,0.000050624207,0.000033654636,0.00023512123,0.00004797248,0.0002259265,0.00004985552,0.000023162771],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021813683,0.00015307484,0.23944096,0.0002580462,0.000023374292,0.0000025921258,0.0014868671,0.00019057994,0.700949,0.00013190645,0.01136586,0.045779567],"study_design_scores_gemma":[0.0005722875,0.00031097556,0.8771849,0.00016986027,0.00003448311,0.0000013571112,0.000112869515,0.0056511117,0.11360065,0.0009168768,0.0012229573,0.00022165073],"about_ca_topic_score_codex":0.0007997832,"about_ca_topic_score_gemma":0.00010292775,"teacher_disagreement_score":0.63774395,"about_ca_system_score_codex":0.000029977191,"about_ca_system_score_gemma":0.000006625641,"threshold_uncertainty_score":0.37118664},"labels":[],"label_agreement":null},{"id":"W2795350022","doi":"10.1093/biostatistics/kxx047","title":"A joint model for mixed and truncated longitudinal data and survival data, with application to HIV vaccine studies","year":2017,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Bill and Melinda Gates Foundation","keywords":"Inference; Computer science; Likelihood function; Missing data; Generalized estimating equation; Statistics; Longitudinal data; Statistical inference; Algorithm; Maximum likelihood; Mathematics; Data mining; Estimation theory; Artificial intelligence","score_opus":0.33641280286451325,"score_gpt":0.45578092942858783,"score_spread":0.11936812656407458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795350022","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075753266,0.00007209003,0.9816746,0.0007285029,0.00005448724,0.00054110336,0.009300874,0.000023749473,0.000029226114],"genre_scores_gemma":[0.15793985,0.000074095995,0.8414961,0.000030908854,0.000048124755,0.000035100693,0.00028241694,0.000020648433,0.00007272438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988322,0.00003102381,0.0002683143,0.00052971026,0.00014773742,0.00019100361],"domain_scores_gemma":[0.99674916,0.0011882337,0.00018997736,0.0015298224,0.00022240549,0.00012042399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006586105,0.00016779308,0.00037132628,0.000029672798,0.00029961273,0.0001233363,0.00042718396,0.000039135106,0.0000019356378],"category_scores_gemma":[0.0077123465,0.00012512598,0.000005012421,0.000030932675,0.00012043332,0.000114087765,0.00079406565,0.00006279368,0.0000016439204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005914635,0.00021750275,0.00840406,0.0014415161,0.0004151612,0.000013520261,0.0007794862,0.000011154058,0.0006559719,0.80492425,0.05370733,0.12883857],"study_design_scores_gemma":[0.0010227708,0.00018609036,0.021328539,0.00008651053,0.00028233856,0.0000074524505,0.00017660306,0.7915935,0.000055107314,0.18451294,0.00047247158,0.00027568312],"about_ca_topic_score_codex":0.000028020144,"about_ca_topic_score_gemma":0.0003350797,"teacher_disagreement_score":0.79158235,"about_ca_system_score_codex":0.000012637496,"about_ca_system_score_gemma":0.00003857332,"threshold_uncertainty_score":0.9232956},"labels":[],"label_agreement":null},{"id":"W2890289581","doi":"10.1093/biostatistics/kxy041","title":"Pointless spatial modeling","year":2018,"lang":"en","type":"article","venue":"Biostatistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Medical Research Council; National Institutes of Health; Applied Molecular Biosciences Unit; Kurdistan University Of Medical Sciences; Mekelle University; Đại học Quốc gia Hà Nội; University of Peradeniya; Addis Ababa University; University of Gondar; University of Tabriz; Universidade Federal de Sergipe; Universitatea de Medicină şi Farmacie \"Carol Davila\" Bucureşti; Universidade do Porto; Bahir Dar University; Alexandria University; Bill and Melinda Gates Foundation; Karolinska Institutet; Tabriz University of Medical Sciences; Shahroud University of Medical Sciences; Babol University of Medical Sciences; Tehran University of Medical Sciences and Health Services; Mazandaran University of Medical Sciences; Universität Bielefeld; Aksum University; Public Health Foundation of India; Kaiser Permanente; Australian Catholic University; Mansoura University; Hamadan University of Medical Sciences; University of Oxford; Universidad Autónoma de Sinaloa; Maragheh University of Medical Sciences; Universidad Nacional Autónoma de México; Indian Institute of Technology Delhi; Istituto di Ricerche Farmacologiche Mario Negri - IRCCS; University of Southampton; University of Washington; A.T. Still University; Simon Fraser University; University of Ottawa; U.S. Department of Veterans Affairs","keywords":"Computer science; Laplace's method; Bayesian inference; Smoothing; Random field; Markov random field; Bayesian probability; Variable-order Bayesian network; Algorithm; Theoretical computer science; Applied mathematics; Mathematics; Artificial intelligence; Statistics","score_opus":0.059526377990475644,"score_gpt":0.23771309163695656,"score_spread":0.17818671364648092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890289581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020977158,0.00014852425,0.96218014,0.0001931819,0.0005563706,0.000052410152,0.0016897401,0.000033465545,0.014169031],"genre_scores_gemma":[0.9884331,0.0000446852,0.010228855,0.00026814063,0.00048767755,0.000002551046,0.00016121916,0.000014100063,0.00035967273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921364,0.0000059544523,0.00033462123,0.00023722375,0.000028690574,0.00017986033],"domain_scores_gemma":[0.9995153,0.000023559393,0.00010642322,0.00024148438,0.000050250124,0.00006298506],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014254832,0.00008946798,0.00019323436,0.00010300183,0.00010040888,0.000053085445,0.00014915253,0.000051145536,0.0014398491],"category_scores_gemma":[0.00013949818,0.00010015819,0.00004228321,0.00014289691,0.000057671008,0.00006148244,0.00004534009,0.00005219608,0.0030900147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049882154,0.00012600103,0.033267867,0.00003897327,0.00017422457,0.00001954066,0.00078254996,0.0003165294,0.00010526907,0.9321737,0.013568194,0.019377226],"study_design_scores_gemma":[0.00026049558,0.000103348604,0.002926896,0.0000084364765,0.00001958268,0.0000028723484,0.000045959274,0.88051814,0.00014419995,0.08343822,0.032195497,0.000336332],"about_ca_topic_score_codex":0.00331803,"about_ca_topic_score_gemma":0.00043318278,"teacher_disagreement_score":0.9674559,"about_ca_system_score_codex":0.000023478213,"about_ca_system_score_gemma":0.000009644209,"threshold_uncertainty_score":0.999473},"labels":[],"label_agreement":null},{"id":"W2910244130","doi":"10.1093/biostatistics/kxz001","title":"Are clusterings of multiple data views independent?","year":2019,"lang":"en","type":"preprint","venue":"Biostatistics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Spurious relationship; Data type; Computer science; Data set; Set (abstract data type); Exploit; Data mining; Data science; Information retrieval; Psychology; Machine learning; Artificial intelligence","score_opus":0.07597877536538193,"score_gpt":0.3191912477251362,"score_spread":0.24321247235975424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910244130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7166921,0.024440497,0.18075415,0.00035229744,0.0073619247,0.0024932714,0.0641147,0.00005412838,0.0037369614],"genre_scores_gemma":[0.9649875,0.004188101,0.024252398,0.00019111676,0.00033717387,0.000014700223,0.004932429,0.000056542445,0.0010400477],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832195,0.00005444121,0.00045097535,0.00072335487,0.0002115031,0.00023777303],"domain_scores_gemma":[0.99709976,0.000037317026,0.00081081694,0.0018290114,0.00016383237,0.00005924798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025848503,0.0002952091,0.0005372724,0.00007372232,0.000035418958,0.000028767266,0.00088795286,0.00033132685,0.000022162585],"category_scores_gemma":[0.0007258019,0.00028592657,0.000084854124,0.00005175891,0.0000897112,0.0000017724215,0.0049265535,0.00023647619,0.000014559452],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006507799,0.0008646305,0.15914641,0.0060956036,0.0033047,0.0000586056,0.0002563388,0.0008985309,0.42718452,0.0014100589,0.3890395,0.011090356],"study_design_scores_gemma":[0.0027758735,0.00051650987,0.13545272,0.00045809743,0.00071111735,0.000022960961,0.00049611466,0.0054939277,0.065155454,0.0013875888,0.7852293,0.0023002964],"about_ca_topic_score_codex":0.000053749678,"about_ca_topic_score_gemma":0.00019068936,"teacher_disagreement_score":0.39618987,"about_ca_system_score_codex":0.000013567378,"about_ca_system_score_gemma":0.00009939674,"threshold_uncertainty_score":0.9999593},"labels":[],"label_agreement":null},{"id":"W2941651377","doi":"10.1093/biostatistics/kxz011","title":"Parallel repulsive logic regression with biological adjacency","year":2019,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; National Institutes of Health","keywords":"Adjacency list; Adjacency matrix; Computer science; SNP; Regression; Function (biology); Similarity (geometry); Mathematics; Single-nucleotide polymorphism; Algorithm; Theoretical computer science; Artificial intelligence; Biology; Statistics; Genetics; Graph","score_opus":0.009814861069642562,"score_gpt":0.23850521024042726,"score_spread":0.2286903491707847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941651377","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971334,0.00036613827,0.025218878,0.00011843273,0.00018855758,0.00029930708,0.0001519595,0.000019914081,0.0023028282],"genre_scores_gemma":[0.9485087,0.0003962217,0.048943907,0.0002904509,0.00007739941,0.000009013258,0.0005555465,0.000021789681,0.0011969788],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99911433,0.00003514972,0.00016761215,0.00035301002,0.0000998652,0.00023002112],"domain_scores_gemma":[0.9993437,0.000017781502,0.00011509759,0.00037075885,0.000078981044,0.00007370369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006748166,0.00016953381,0.00015074301,0.000020122297,0.000052422027,0.000020042771,0.00016557984,0.00015526092,0.00007579094],"category_scores_gemma":[0.000054293967,0.000114957336,0.000038227525,0.000054008833,0.00007456009,0.0000019005593,0.000099090896,0.000078978264,0.00005262338],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011146558,0.0004573887,0.11638087,0.00015938903,0.00023577939,0.0001301719,0.00018129946,0.0012867564,0.8102258,0.04591687,0.017030187,0.006880852],"study_design_scores_gemma":[0.025144007,0.042033978,0.40261325,0.0008930254,0.00043713025,0.0016127991,0.0041610715,0.034862626,0.11649627,0.049274962,0.3117572,0.0107136555],"about_ca_topic_score_codex":0.00000547763,"about_ca_topic_score_gemma":0.000008969747,"teacher_disagreement_score":0.6937295,"about_ca_system_score_codex":0.000013688867,"about_ca_system_score_gemma":0.000054422548,"threshold_uncertainty_score":0.4687824},"labels":[],"label_agreement":null},{"id":"W2963817914","doi":"10.1093/biostatistics/kxy049","title":"Bayesian model averaging for the X-chromosome inactivation dilemma in genetic association study","year":2018,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bayesian probability; Association (psychology); Dilemma; Genetics; Chromosome; Genetic association; Genetic model; Computer science; Biology; Computational biology; Statistics; Econometrics; Mathematics; Artificial intelligence; Psychology; Genotype; Gene; Single-nucleotide polymorphism","score_opus":0.018205598656295813,"score_gpt":0.2923468390028399,"score_spread":0.2741412403465441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963817914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5709965,0.0000373346,0.42779744,0.0003299139,0.00017685446,0.0004966854,0.00007682907,0.000006387055,0.00008203859],"genre_scores_gemma":[0.98250717,0.000033255,0.01631624,0.0002977902,0.00032922995,0.000103141196,0.00008555022,0.000018364193,0.0003092629],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989894,0.00010268935,0.00028699733,0.00025572666,0.000105546445,0.00025962858],"domain_scores_gemma":[0.9991702,0.00018943878,0.0001788287,0.00022778171,0.00020327079,0.000030474645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051521003,0.00011337107,0.0001302024,0.000039975264,0.00018022883,0.000023881756,0.00013277233,0.00012035713,0.00000715307],"category_scores_gemma":[0.0011815456,0.000096594325,0.000034261324,0.00010080857,0.000036353682,0.000002779368,0.000051440627,0.000062918196,0.0000050099034],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011939873,0.00039580165,0.93281174,0.000018263028,0.00022085912,0.0000016215388,0.0010822834,0.013033629,0.02273373,0.0007256223,0.019224491,0.009632574],"study_design_scores_gemma":[0.0012992596,0.0007598614,0.69233704,0.000006510531,0.00007114022,0.0000014168437,0.00045340377,0.29737282,0.0010056916,0.0025830744,0.0038371128,0.00027268752],"about_ca_topic_score_codex":0.00008721905,"about_ca_topic_score_gemma":0.00053829426,"teacher_disagreement_score":0.41151065,"about_ca_system_score_codex":0.00010141439,"about_ca_system_score_gemma":0.00007651112,"threshold_uncertainty_score":0.39390025},"labels":[],"label_agreement":null},{"id":"W2986102733","doi":"10.1093/biostatistics/kxz047","title":"Independence conditions and the analysis of life history studies with intermittent observation","year":2019,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Independence (probability theory); Econometrics; Statistics; Computer science; Psychology; Mathematics","score_opus":0.15193314052114745,"score_gpt":0.370486172072266,"score_spread":0.21855303155111852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986102733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6513607,0.0007369148,0.34545466,0.00039956276,0.00025237346,0.00051414774,0.00041693464,0.000029883671,0.00083481276],"genre_scores_gemma":[0.8419638,0.00008750741,0.15741087,0.00021549435,0.000008312763,0.000014188941,0.000010198059,0.0000068762665,0.00028271286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9991641,0.00012200833,0.00028291898,0.00013430494,0.0002118095,0.00008485983],"domain_scores_gemma":[0.9948968,0.004344101,0.00022381886,0.00021464068,0.0002841642,0.000036446683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038044303,0.00008863615,0.00037107992,0.00007374522,0.00003172924,0.000007853649,0.000081326,0.000030775645,0.00012960113],"category_scores_gemma":[0.0034163573,0.000051121187,0.000030179044,0.00018536266,0.00042373544,0.000028640856,0.00004128703,0.00008454799,0.0000028050833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000619842,0.000027396078,0.019233204,0.00012293259,0.00076277484,0.0000011852279,0.0010947933,0.000007024196,0.00004972409,0.9763357,0.0011723146,0.0011309682],"study_design_scores_gemma":[0.0019537853,0.00030258248,0.5739023,0.0001710178,0.003751216,0.0000031620418,0.0033183633,0.028097108,0.00005739057,0.38765362,0.00046166108,0.00032777493],"about_ca_topic_score_codex":0.000038537117,"about_ca_topic_score_gemma":0.00004207304,"teacher_disagreement_score":0.58868206,"about_ca_system_score_codex":0.00004276273,"about_ca_system_score_gemma":0.000055582677,"threshold_uncertainty_score":0.40899456},"labels":[],"label_agreement":null},{"id":"W2990086743","doi":"10.1093/biostatistics/kxz048","title":"The illness-death model for family studies","year":2019,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Family history; Disease; Psoriatic arthritis; Sampling (signal processing); Construct (python library); Medicine; Sampling bias; Statistics; Missing data; Demography; Computer science; Sample size determination; Mathematics; Internal medicine","score_opus":0.24790220017718542,"score_gpt":0.4473781306493679,"score_spread":0.19947593047218246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990086743","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005586706,0.0003397701,0.9904384,0.00020266601,0.0005837243,0.0005429486,0.00056992663,0.00004921204,0.0016866265],"genre_scores_gemma":[0.09092017,0.00025089493,0.90445626,0.00025417042,0.00006768672,0.00007858716,0.0000058739784,0.000032360243,0.00393398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99896413,0.00005034263,0.00030570306,0.00019938163,0.0001919895,0.0002884566],"domain_scores_gemma":[0.990627,0.008587714,0.000108157365,0.0003310602,0.00029256594,0.00005352999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050438097,0.00014906388,0.0002594249,0.00001818857,0.00023039304,0.000047868816,0.00019229995,0.000050707516,0.000009970496],"category_scores_gemma":[0.0057421294,0.00009101628,0.000047605266,0.00005787491,0.00010392069,0.000022963099,0.000065168344,0.00008485965,0.00003951242],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023164546,0.000018555053,0.00006290108,0.000112211594,0.000042151554,6.8310686e-7,0.00029862858,0.000011755326,0.00011630402,0.96764576,0.015336408,0.016331488],"study_design_scores_gemma":[0.00023677097,0.00008469119,0.00015669635,0.000026422118,0.000041237545,7.2189323e-7,0.00050285715,0.16796549,0.00006942984,0.8267696,0.0039954274,0.0001506611],"about_ca_topic_score_codex":0.0000027224457,"about_ca_topic_score_gemma":0.000003984713,"teacher_disagreement_score":0.16795373,"about_ca_system_score_codex":0.000033971894,"about_ca_system_score_gemma":0.00005567455,"threshold_uncertainty_score":0.687428},"labels":[],"label_agreement":null},{"id":"W2993029184","doi":"10.1093/biostatistics/kxz053","title":"Pair-based likelihood approximations for stochastic epidemic models","year":2019,"lang":"en","type":"article","venue":"Biostatistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Engineering and Physical Sciences Research Council","keywords":"Markov chain Monte Carlo; Computer science; Approximate Bayesian computation; Markov chain; Mathematical optimization; Epidemic model; Algorithm; Machine learning; Artificial intelligence; Mathematics; Bayesian probability; Inference","score_opus":0.2613787351654007,"score_gpt":0.41705189516470365,"score_spread":0.15567315999930292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993029184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045967265,0.000096888325,0.9903209,0.0017598686,0.00030432173,0.0014555978,0.000978047,0.00022240468,0.00026521785],"genre_scores_gemma":[0.5341959,0.000005419788,0.4634004,0.0013909928,0.0000934883,0.00027737545,0.00008873534,0.00004811538,0.0004995874],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981771,0.00011034686,0.0006000646,0.00040790663,0.00021204092,0.0004925138],"domain_scores_gemma":[0.9830509,0.015928285,0.00026088767,0.00043729096,0.0002061007,0.00011657015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008579407,0.00025368208,0.0005465839,0.000072922536,0.00015229666,0.000020702282,0.00022415534,0.00013780412,0.00008609413],"category_scores_gemma":[0.011953216,0.00020964735,0.00014040296,0.00015876905,0.00008719616,0.000056871217,0.00007842645,0.00014717139,0.00011344668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008639296,0.00035146408,0.0010540261,0.0010962728,0.00011422025,0.000001876562,0.0002395924,0.013391383,0.00016523064,0.8953107,0.08495039,0.0032384708],"study_design_scores_gemma":[0.00052031997,0.00013877873,0.00018143214,0.0000422472,0.000059262566,4.8210313e-7,0.000043512773,0.41017216,0.000019064244,0.58684826,0.0017712327,0.00020324517],"about_ca_topic_score_codex":0.000024279267,"about_ca_topic_score_gemma":0.00001720024,"teacher_disagreement_score":0.5295992,"about_ca_system_score_codex":0.00013813983,"about_ca_system_score_gemma":0.000100393234,"threshold_uncertainty_score":0.99636954},"labels":[],"label_agreement":null},{"id":"W3010419042","doi":"10.1093/biostatistics/kxaa009","title":"Geographically dependent individual-level models for infectious diseases transmission","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University of Calgary","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Transmission (telecommunications); Computer science; Econometrics; Statistics; Mathematics","score_opus":0.31380845844225735,"score_gpt":0.39699155322202456,"score_spread":0.08318309477976721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010419042","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003899616,0.00030784355,0.98843527,0.0032771798,0.00007230355,0.0006953464,0.0029437956,0.00026796653,0.000100699755],"genre_scores_gemma":[0.82587284,0.00030247867,0.16869943,0.00461896,0.00017156251,0.0001389463,0.00011267943,0.00004558163,0.00003752006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983702,0.000096128824,0.00047595744,0.00040068734,0.00031031767,0.00034674106],"domain_scores_gemma":[0.99492043,0.0043318025,0.00015039499,0.0001666395,0.00013444998,0.0002962704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023842561,0.00023957857,0.0004467334,0.00004338177,0.00020716351,0.000037327933,0.000218611,0.000124291,0.00004228716],"category_scores_gemma":[0.006026518,0.00018815734,0.00015424438,0.00017142542,0.00010122777,0.00005307754,0.000119141216,0.00014062825,0.000007706565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004896745,0.0011038223,0.031746794,0.0027456519,0.00084163115,0.000078258614,0.0021586008,0.0017045786,0.00044287718,0.7479918,0.1079783,0.10271799],"study_design_scores_gemma":[0.0011514479,0.00047962417,0.009656057,0.000039508304,0.00037617385,0.0000017903634,0.000050776747,0.019897364,0.000053542266,0.9623743,0.0055187074,0.00040067598],"about_ca_topic_score_codex":0.000019635814,"about_ca_topic_score_gemma":0.00001396759,"teacher_disagreement_score":0.8219732,"about_ca_system_score_codex":0.000034145833,"about_ca_system_score_gemma":0.000050635248,"threshold_uncertainty_score":0.7672834},"labels":[],"label_agreement":null},{"id":"W3011802598","doi":"10.1093/biostatistics/kxaa011","title":"Assessing the accuracy of predictive models with interval-censored data","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; University of Waterloo; National Natural Science Foundation of China","keywords":"Estimator; Inverse probability; Statistics; Computer science; Event (particle physics); Imputation (statistics); Context (archaeology); Receiver operating characteristic; Inverse probability weighting; Coverage probability; Confidence interval; Mathematics; Bayesian probability; Missing data; Posterior probability","score_opus":0.337170611191294,"score_gpt":0.44963140921643074,"score_spread":0.11246079802513675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011802598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021069176,0.000029849418,0.99336535,0.0006926287,0.000050634146,0.00023471903,0.0018480604,0.00003937131,0.0016324873],"genre_scores_gemma":[0.39802176,0.000011440254,0.6016794,0.00018981812,0.000042731208,0.0000034822663,0.000029133387,0.000016192098,0.000006079853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872845,0.00017466901,0.00036336153,0.0002649573,0.00029804738,0.00017049724],"domain_scores_gemma":[0.9935856,0.005256106,0.00027233828,0.00058959745,0.00020376897,0.00009258685],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00030718386,0.00014128929,0.0002753499,0.000014819529,0.000066972265,0.00007422647,0.0005498271,0.0000414294,0.000058547175],"category_scores_gemma":[0.010435316,0.00008221291,0.00001813536,0.00016594116,0.00023692398,0.00020179867,0.0002712103,0.00017624786,0.0000035780379],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012464644,0.000117814736,0.00033357696,0.00036506102,0.00015149958,0.00002357739,0.0021975907,0.000079577454,0.0003795905,0.948433,0.013228885,0.034565218],"study_design_scores_gemma":[0.00040523484,0.00033372897,0.0011910726,0.00016582773,0.00020236892,0.0000062505937,0.0012954379,0.6660392,0.00052833086,0.3292907,0.00035519552,0.0001866676],"about_ca_topic_score_codex":0.000018001207,"about_ca_topic_score_gemma":0.0000025236632,"teacher_disagreement_score":0.6659596,"about_ca_system_score_codex":0.000011522253,"about_ca_system_score_gemma":0.00010185791,"threshold_uncertainty_score":0.9979002},"labels":[],"label_agreement":null},{"id":"W3015827596","doi":"10.1093/biostatistics/kxaa012","title":"Two-part joint model for a longitudinal semicontinuous marker and a terminal event with application to metastatic colorectal cancer data","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Colorectal Cancer Treatments and Studies","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Biomarker; Event (particle physics); Colorectal cancer; Proportional hazards model; Outcome (game theory); Oncology; Computer science; Statistics; Cancer; Medicine; Internal medicine; Mathematics; Biology; Physics","score_opus":0.0662028208738954,"score_gpt":0.3436616069784594,"score_spread":0.277458786104564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015827596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45851555,0.001118318,0.5201591,0.006970064,0.00008496191,0.003755311,0.00915348,0.00007058256,0.00017263115],"genre_scores_gemma":[0.9409569,0.00008019894,0.05726889,0.0006473523,0.00010348495,0.00050607417,0.00028795985,0.000022995637,0.00012615995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990436,0.000008905476,0.00019215334,0.00041343004,0.00015457501,0.00018733925],"domain_scores_gemma":[0.9994178,0.00005261955,0.000072856805,0.0001619292,0.00011378043,0.00018104212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006528984,0.00015851414,0.0003148166,0.000025342782,0.000077762015,0.000020720001,0.00005746237,0.000015693884,0.000012192233],"category_scores_gemma":[0.00008448749,0.00011685207,0.000019565894,0.00009093777,0.00005390841,0.000034643264,0.00010212557,0.000051966243,0.0000024619344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.049427055,0.0020014015,0.17716983,0.0041980413,0.0062336195,0.00086108554,0.014167085,0.0025152417,0.024458893,0.0030901462,0.1781378,0.5377398],"study_design_scores_gemma":[0.006127214,0.0037024028,0.049230997,0.00020779634,0.0023222927,0.00013984871,0.00047166867,0.92854446,0.00066695263,0.00012762858,0.007992572,0.00046617346],"about_ca_topic_score_codex":0.00013486964,"about_ca_topic_score_gemma":0.00074955507,"teacher_disagreement_score":0.9260292,"about_ca_system_score_codex":0.00007354038,"about_ca_system_score_gemma":0.00014627188,"threshold_uncertainty_score":0.47650892},"labels":[],"label_agreement":null},{"id":"W3021772758","doi":"10.1093/biostatistics/kxy075","title":"Sequence kernel association test for survival outcomes in the presence of a non-susceptible fraction","year":2018,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Sinai Health System; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Association (psychology); Fraction (chemistry); Statistics; Test (biology); Kernel (algebra); Computer science; Mathematics; Psychology; Biology; Genetics; Combinatorics; Chemistry","score_opus":0.02798905792391057,"score_gpt":0.3321394866421573,"score_spread":0.3041504287182467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021772758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8774658,0.000030278357,0.119458936,0.0008880259,0.00039734185,0.0004404008,0.0006347333,0.0000049840564,0.0006795222],"genre_scores_gemma":[0.9857014,0.00004642094,0.013347007,0.00018647825,0.00015806749,0.00003117017,0.000121403515,0.0000070019787,0.00040109587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99925226,0.000082314735,0.0002328479,0.00015559462,0.00010258222,0.0001744005],"domain_scores_gemma":[0.9987201,0.00064533635,0.00022403031,0.00017418206,0.00021941935,0.00001689923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068889605,0.000075354634,0.00014106353,0.000022703629,0.000061119266,0.000008548687,0.00013803245,0.00012427158,0.0000056542694],"category_scores_gemma":[0.0044547156,0.000059422582,0.00003769006,0.00007967868,0.00006139012,0.0000023199937,0.000025665158,0.000045968936,0.000005195864],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015913974,0.00008449058,0.9074301,0.000012703328,0.0000234485,2.04364e-7,0.00011282504,0.000019521018,0.08141412,0.00022483518,0.009895242,0.0007665718],"study_design_scores_gemma":[0.00047550074,0.00079811085,0.9835363,0.0000072433704,0.000025337036,8.8591406e-7,0.00032856647,0.002384491,0.005669313,0.0011140489,0.005537702,0.00012249124],"about_ca_topic_score_codex":0.0001438074,"about_ca_topic_score_gemma":0.00045353168,"teacher_disagreement_score":0.10823558,"about_ca_system_score_codex":0.00003204876,"about_ca_system_score_gemma":0.000059560116,"threshold_uncertainty_score":0.53330326},"labels":[],"label_agreement":null},{"id":"W3026963084","doi":"10.1093/biostatistics/kxaa020","title":"Causal inference for recurrent event data using pseudo-observations","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; HEC Montréal; Jewish General Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut de Valorisation des Données","keywords":"Estimator; Inverse probability weighting; Statistics; Inverse probability; Mathematics; Weighting; Regression; Event (particle physics); Regression analysis; Computer science; Econometrics; Bayesian probability; Medicine","score_opus":0.5969398403880808,"score_gpt":0.49798059002811046,"score_spread":0.09895925035997033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026963084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022231448,0.000031543703,0.98811597,0.0007815579,0.00031061305,0.00043315598,0.007975884,0.00006446961,0.00006365574],"genre_scores_gemma":[0.04005379,0.000018633278,0.9589221,0.00043135628,0.00021901524,0.000017090588,0.000290532,0.000028936563,0.000018546816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985112,0.00008681904,0.0004918482,0.0003937796,0.00023459739,0.00028175593],"domain_scores_gemma":[0.99555093,0.003319554,0.00018439723,0.00050356006,0.00023824841,0.00020332923],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00031106142,0.00017914604,0.0002819567,0.000024992187,0.00013699298,0.00006223905,0.00043994468,0.00006750043,0.00010292295],"category_scores_gemma":[0.021986868,0.00016691299,0.00003105758,0.00018452723,0.00007501293,0.00008246743,0.0002539709,0.00013777356,0.000012434021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049916198,0.000103275306,0.00039534553,0.0003424342,0.000039289032,0.0000058672767,0.00027744382,0.0000179371,0.0007781119,0.951691,0.02470402,0.021595385],"study_design_scores_gemma":[0.0003876748,0.00030952733,0.000769938,0.000075664,0.00015439246,0.0000022759168,0.00008274344,0.6756305,0.00013856497,0.31576437,0.006379098,0.0003052415],"about_ca_topic_score_codex":0.000017816525,"about_ca_topic_score_gemma":0.000014636412,"teacher_disagreement_score":0.67561257,"about_ca_system_score_codex":0.000035884303,"about_ca_system_score_gemma":0.00017687956,"threshold_uncertainty_score":0.98625135},"labels":[],"label_agreement":null},{"id":"W3027831021","doi":"10.1093/biostatistics/kxab016","title":"Bayesian integrative analysis and prediction with application to atherosclerosis cardiovascular disease","year":2021,"lang":"en","type":"preprint","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Disease; Atherosclerotic cardiovascular disease; Genome-wide association study; Computational biology; Genetic variants; Risk factor; Bioinformatics; Medicine; Gene; Biology; Genetics; Internal medicine; Single-nucleotide polymorphism; Genotype","score_opus":0.00791382655362262,"score_gpt":0.23941766280060273,"score_spread":0.2315038362469801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027831021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20071007,0.0006758973,0.79671305,0.00013708592,0.00006165404,0.00034346266,0.0013067287,0.000011013407,0.00004102721],"genre_scores_gemma":[0.9405147,0.00090906274,0.05306805,0.00014465979,0.00012162731,0.00020298074,0.004942832,0.000023976043,0.00007213272],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985276,0.00016097065,0.00024526412,0.0007340389,0.00015330277,0.0001788228],"domain_scores_gemma":[0.99870425,0.000025083506,0.00012986832,0.0006863551,0.0002608436,0.00019358554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021120853,0.00023556635,0.00039674438,0.000091103946,0.00008527655,0.000055161894,0.0001080143,0.00023133226,0.0000053187937],"category_scores_gemma":[0.0002389417,0.0002089575,0.00018528002,0.00022253822,0.00006712162,0.0000013828227,0.00024879124,0.00012921852,0.000001201869],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016227906,0.00020417589,0.8391372,0.00019950299,0.01853489,0.000008351255,0.0006903034,0.108995624,0.0061272033,0.00020532713,0.0023833883,0.023351744],"study_design_scores_gemma":[0.00025602186,0.00018858041,0.97676426,0.000046182955,0.0044975174,0.0000016852644,0.00037550507,0.013985896,0.0005014876,0.00015314498,0.002791902,0.00043784082],"about_ca_topic_score_codex":0.0002855856,"about_ca_topic_score_gemma":0.00037279146,"teacher_disagreement_score":0.743645,"about_ca_system_score_codex":0.000040765666,"about_ca_system_score_gemma":0.00013258708,"threshold_uncertainty_score":0.85210395},"labels":[],"label_agreement":null},{"id":"W3080340456","doi":"10.1093/biostatistics/kxaa033","title":"Adaptive treatment strategies for chronic conditions: shared-parameter G-estimation with an application to rheumatoid arthritis","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé","keywords":"Estimation; Computer science; Robustness (evolution); Rheumatoid arthritis; Mathematical optimization; Machine learning; Estimation theory; Point estimation; Artificial intelligence; Econometrics; Data mining; Medicine; Mathematics; Algorithm; Statistics","score_opus":0.09362554207553095,"score_gpt":0.3750745637280131,"score_spread":0.2814490216524822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080340456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029779705,0.000043547454,0.9915686,0.00030080107,0.000029518336,0.0012900601,0.003575537,0.0001081153,0.0001057985],"genre_scores_gemma":[0.2513946,0.000030249077,0.7475045,0.00015630948,0.000049042334,0.0005844396,0.000248752,0.000026254593,0.000005875663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892354,0.000056212062,0.00030742565,0.000339141,0.00015400417,0.00021967497],"domain_scores_gemma":[0.99804854,0.0012103175,0.00012949517,0.00021088972,0.00018976866,0.00021101463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007292239,0.00019920048,0.00027753995,0.00003579815,0.00012162139,0.00011707224,0.00009677617,0.000056430723,0.0000878526],"category_scores_gemma":[0.0006946813,0.00016566447,0.000027021133,0.00013726129,0.000071869115,0.00013506247,0.000013733958,0.000051582123,0.00003834047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015774883,0.00011526309,0.000011112666,0.00007759879,0.000044430453,0.000003602035,0.00088866526,0.00029913508,0.00045523205,0.84026676,0.001200343,0.1564801],"study_design_scores_gemma":[0.0010638431,0.0075156447,0.0003706022,0.00011567758,0.00005139336,0.0000071279424,0.00068395445,0.38737032,0.0008734363,0.6003024,0.0012849175,0.00036068534],"about_ca_topic_score_codex":0.000034818546,"about_ca_topic_score_gemma":0.00008592896,"teacher_disagreement_score":0.38707116,"about_ca_system_score_codex":0.00011682423,"about_ca_system_score_gemma":0.00018127897,"threshold_uncertainty_score":0.6755601},"labels":[],"label_agreement":null},{"id":"W3186606527","doi":"10.1093/biostatistics/kxab028","title":"Bayesian adaptive model selection design for optimal biological dose finding in phase I/II clinical trials","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Bayesian probability; Selection (genetic algorithm); Computer science; Model selection; Maximum tolerated dose; Adaptive design; Econometrics; Clinical trial; Statistics; Artificial intelligence; Mathematics; Medicine; Internal medicine","score_opus":0.8908728524028277,"score_gpt":0.6664937251343948,"score_spread":0.2243791272684329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186606527","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039624567,0.000039655453,0.9917418,0.0002154732,0.0007368213,0.0017321598,0.001368112,0.000099326986,0.000104212726],"genre_scores_gemma":[0.0538286,0.00008840015,0.9449158,0.00020963153,0.00051194517,0.00018978189,0.000033647924,0.000056367306,0.00016586512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98808724,0.0065437914,0.0035497139,0.0008700064,0.00033213155,0.0006171061],"domain_scores_gemma":[0.79702663,0.20119098,0.0007914509,0.00033213847,0.00038880424,0.00026997994],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024386188,0.00036257037,0.001949607,0.00012169524,0.00020693197,0.00006682968,0.0002398582,0.0006444564,0.00021714927],"category_scores_gemma":[0.52557033,0.00031241903,0.0003744748,0.00042410722,0.00023807952,0.000064516484,0.00014980373,0.00057578343,0.000009114299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008612515,0.006640166,0.0002037286,0.00018875508,0.00046630244,0.00022056537,0.00036834908,0.003975763,0.0031145061,0.7750022,0.022990128,0.17821707],"study_design_scores_gemma":[0.005946103,0.0017504512,0.000028112418,0.000062801664,0.00016230406,0.000006674365,0.00005614398,0.4448297,0.0013039482,0.5454979,0.00008538425,0.00027048966],"about_ca_topic_score_codex":0.0000024876654,"about_ca_topic_score_gemma":0.000006091979,"teacher_disagreement_score":0.50118417,"about_ca_system_score_codex":0.00014072841,"about_ca_system_score_gemma":0.0005129743,"threshold_uncertainty_score":0.99993277},"labels":[],"label_agreement":null},{"id":"W3193894044","doi":"10.1093/biostatistics/kxab031","title":"Estimation for the bivariate quantile varying coefficient model with application to diffusion tensor imaging data analysis","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institutes of Health; National Cancer Institute; National Institute of Mental Health; Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Interpretability; Bivariate analysis; Computer science; Quantile; Diffusion MRI; Quantile regression; Data set; Artificial intelligence; Mathematics; Econometrics; Machine learning","score_opus":0.085489773200644,"score_gpt":0.39188917805165296,"score_spread":0.30639940485100897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193894044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008085672,0.000040208175,0.9928052,0.004689255,0.000012742515,0.00076100026,0.00075020245,0.00010322932,0.000029627283],"genre_scores_gemma":[0.3963839,0.00002148457,0.6015606,0.00063107774,0.000017729335,0.00010387351,0.0011974439,0.000016650194,0.00006724321],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910575,0.000008887756,0.00018582003,0.0003923817,0.00016510709,0.00014203842],"domain_scores_gemma":[0.9984291,0.00021727713,0.00008860653,0.0009872254,0.00021504847,0.000062704494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001097967,0.00009942883,0.00015080083,0.000073880045,0.0002167416,0.000039419963,0.00014956208,0.000016209875,0.0000032500136],"category_scores_gemma":[0.00020519485,0.000070233946,0.000027729606,0.00062895456,0.000032867938,0.000039786362,0.00011524972,0.000064418084,0.0000031829707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002938858,0.00063363183,0.0067086266,0.00018702015,0.0003054106,0.000020459911,0.00032506388,0.6636387,0.035328105,0.048925314,0.008062713,0.23557104],"study_design_scores_gemma":[0.00023769758,0.000022425003,0.0029053264,0.000021188955,0.0008672673,0.000011660654,0.000029390076,0.9909968,0.00082614477,0.00057243276,0.003419153,0.00009053501],"about_ca_topic_score_codex":0.000022776541,"about_ca_topic_score_gemma":0.000008418841,"teacher_disagreement_score":0.39557534,"about_ca_system_score_codex":0.000031558728,"about_ca_system_score_gemma":0.00006330606,"threshold_uncertainty_score":0.2864057},"labels":[],"label_agreement":null},{"id":"W3196024289","doi":"10.1093/biostatistics/kxab032","title":"Predicting the onset of breast cancer using mammogram imaging data with irregular boundary","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Breast cancer; Computer science; Artificial intelligence; Mammography; Pattern recognition (psychology); Benchmark (surveying); Breast cancer screening; Boundary (topology); Machine learning; Medicine; Cancer; Mathematics","score_opus":0.02508658907445413,"score_gpt":0.2886221632118421,"score_spread":0.26353557413738793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196024289","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01358042,0.00077074027,0.9825446,0.001035996,0.00060906424,0.00009860457,0.0012553745,0.00006187687,0.000043329328],"genre_scores_gemma":[0.6590741,0.00006463503,0.34036687,0.00023544591,0.00016315767,0.000005001659,0.000045754085,0.000020736175,0.00002427871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885726,0.0000744207,0.00019036484,0.00034828074,0.00032930315,0.00020038696],"domain_scores_gemma":[0.99835736,0.00013141555,0.00016675114,0.0010796146,0.0002235714,0.00004127465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022019842,0.000104076695,0.00011333945,0.000032526834,0.0002174131,0.00017907062,0.00071202166,0.000021670106,0.0000131296465],"category_scores_gemma":[0.000046867455,0.00007951217,0.000014178997,0.00045540684,0.00017832279,0.00030303624,0.00053725817,0.0001231888,8.6602597e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007553364,0.00015752648,0.2306684,0.00036431092,0.00031006554,0.0005152583,0.0019505817,0.002785411,0.005217794,0.0045512673,0.008768682,0.74463516],"study_design_scores_gemma":[0.00033201033,0.000030089557,0.0489377,0.00025529112,0.000102180784,0.0013754449,0.00034184198,0.9400447,0.0025038568,0.00079958234,0.0050229058,0.00025441076],"about_ca_topic_score_codex":0.0006501518,"about_ca_topic_score_gemma":0.00030089886,"teacher_disagreement_score":0.93725926,"about_ca_system_score_codex":0.00008553967,"about_ca_system_score_gemma":0.0006232313,"threshold_uncertainty_score":0.32424122},"labels":[],"label_agreement":null},{"id":"W4210676319","doi":"10.1093/biostatistics/kxac007","title":"Semiparametric Bayesian inference for optimal dynamic treatment regimes via dynamic marginal structural models","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; ViiV Healthcare; Gilead Sciences","keywords":"Frequentist inference; Inference; Bayesian probability; Computer science; Bayesian inference; Posterior probability; Econometrics; Marginal structural model; Machine learning; Causal inference; Artificial intelligence; Mathematics","score_opus":0.05764133595221096,"score_gpt":0.379869733491707,"score_spread":0.32222839753949606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210676319","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016176244,0.00013936362,0.97762007,0.00012171235,0.00037762462,0.0007962551,0.0043942225,0.00010354065,0.00027098492],"genre_scores_gemma":[0.44348913,0.000020590429,0.5555202,0.000036567428,0.00001755792,0.00018506714,0.0001449402,0.0000380839,0.0005478967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774015,0.00020529734,0.00054804847,0.0005175525,0.00041800685,0.0005709226],"domain_scores_gemma":[0.99507916,0.0038616778,0.0002702728,0.00046190753,0.00014659912,0.00018040628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029262435,0.0003716881,0.0005151935,0.00021032616,0.00046506606,0.000074475574,0.00034022785,0.00008023909,0.00041194583],"category_scores_gemma":[0.0011574638,0.00033741293,0.00011610005,0.00040044112,0.00013530992,0.000072244475,0.00015230992,0.00022348009,0.000005145368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027839313,0.0002585986,0.00015704255,0.00021348015,0.00015670771,0.000055875378,0.0006008599,0.003466166,0.00018284356,0.8440613,0.000947739,0.14962098],"study_design_scores_gemma":[0.00049879716,0.0007487025,0.00021116518,0.000008405876,0.00009713799,0.000027615708,0.00011800157,0.56087875,0.000026161046,0.43689743,0.00022747426,0.00026032137],"about_ca_topic_score_codex":0.00006021877,"about_ca_topic_score_gemma":0.000018638839,"teacher_disagreement_score":0.5574126,"about_ca_system_score_codex":0.00057319144,"about_ca_system_score_gemma":0.00019074901,"threshold_uncertainty_score":0.9999078},"labels":[],"label_agreement":null},{"id":"W4229024550","doi":"10.1093/biostatistics/kxac029","title":"A flexible approach for predictive biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Computer science; False positive paradox; Estimator; Inference; Identification (biology); Nonparametric statistics; False positives and false negatives; Metric (unit); Biomarker discovery; Multiple comparisons problem; Predictive inference; Biomarker; Data mining; False discovery rate; Truncation (statistics); Machine learning; Artificial intelligence; Statistics; Frequentist inference; Mathematics; Bayesian probability; Bayesian inference","score_opus":0.5564742844991701,"score_gpt":0.5379670415846817,"score_spread":0.018507242914488464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229024550","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002054326,0.000036215206,0.9808348,0.00011647489,0.00087976444,0.001298468,0.012697919,0.00015194195,0.003778973],"genre_scores_gemma":[0.017495252,0.0000060027096,0.9787448,0.000253806,0.0002067643,0.0008528697,0.00010460835,0.00007007119,0.0022658494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997259,0.00060254283,0.0007280234,0.0004941092,0.00051097816,0.00040531665],"domain_scores_gemma":[0.96538717,0.033646982,0.00028447926,0.0004508413,0.0001112302,0.00011932063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023526617,0.00021546865,0.00050689775,0.00008806228,0.0003520396,0.000065288696,0.00035502817,0.00008013376,0.00027379327],"category_scores_gemma":[0.044077322,0.00020128555,0.00015261101,0.00029862364,0.00018862993,0.00006244162,0.00031454355,0.00024870882,0.0000045918005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009384062,0.00078870193,0.00014564168,0.00029305377,0.00021288129,0.000011367391,0.00015883976,0.000063853826,0.00023309197,0.8488368,0.13774206,0.010575344],"study_design_scores_gemma":[0.0013284115,0.00056383415,0.0002771264,0.000008812118,0.00019764883,0.000009783034,0.00032922497,0.016282814,0.00026673943,0.97274876,0.007691543,0.0002953025],"about_ca_topic_score_codex":0.0000057634015,"about_ca_topic_score_gemma":3.0804776e-7,"teacher_disagreement_score":0.13005051,"about_ca_system_score_codex":0.00014212095,"about_ca_system_score_gemma":0.000120657394,"threshold_uncertainty_score":0.96397483},"labels":[],"label_agreement":null},{"id":"W4230814105","doi":"10.1093/biostatistics/5.3.361","title":"Analysis of longitudinal marginal structural models","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Marginal structural model; Econometrics; Marginal model; Computer science; Statistics; Mathematics; Regression analysis; Causal inference","score_opus":0.08612267330736914,"score_gpt":0.3841181678001392,"score_spread":0.2979954944927701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230814105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026992554,0.000022999495,0.97091556,0.00004320663,0.00008700505,0.000087043125,0.0008917612,0.000028359014,0.0009314956],"genre_scores_gemma":[0.46007156,0.00000423708,0.5398603,0.000011518635,0.0000154868,0.0000018274596,0.000016766995,0.0000074057893,0.000010866734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987915,0.00004837159,0.00041732335,0.00021836688,0.00029568834,0.00022871443],"domain_scores_gemma":[0.998555,0.0007129449,0.00017850679,0.0002809658,0.00017601621,0.00009656832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017693194,0.00015206277,0.00044776738,0.00019031588,0.000056543235,0.000023129494,0.00016056137,0.00006403211,0.00025232154],"category_scores_gemma":[0.0006916434,0.00012886211,0.00010261135,0.000604767,0.00016291614,0.00005580078,0.00004216948,0.000100361154,0.0000040687532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021810587,0.000036822625,0.0021735616,0.000058329777,0.0003217971,0.000021476817,0.00013443602,0.00022977161,0.00006998922,0.9911659,0.00006697496,0.0056991577],"study_design_scores_gemma":[0.0002654219,0.00007936125,0.027973348,0.00002155228,0.0010160344,0.0000052272667,0.000034010758,0.02016905,0.00025481242,0.9500191,0.000005932035,0.00015615708],"about_ca_topic_score_codex":0.00009833002,"about_ca_topic_score_gemma":0.000047701713,"teacher_disagreement_score":0.43307903,"about_ca_system_score_codex":0.000046426718,"about_ca_system_score_gemma":0.0000638744,"threshold_uncertainty_score":0.52548444},"labels":[],"label_agreement":null},{"id":"W4283823477","doi":"10.1093/biostatistics/kxac023","title":"Constrained groupwise additive index models","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ouranos; University of Ottawa; Health Canada; Institut National de Santé Publique du Québec; Institut National de la Recherche Scientifique","funders":"Mitacs; Institut National de Santé Publique du Québec","keywords":"Computer science; Context (archaeology); Index (typography); Variance (accounting); Predictive power; Variable (mathematics); Inference; Data mining; Sensitivity (control systems); Econometrics; Statistics; Mathematics; Artificial intelligence","score_opus":0.017002022804621625,"score_gpt":0.23908750135535406,"score_spread":0.22208547855073243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283823477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24727143,0.00008556778,0.5875637,0.0014724055,0.0007974281,0.0021376715,0.009985717,0.00029758038,0.1503885],"genre_scores_gemma":[0.9911532,0.00002671165,0.0061634365,0.0018367679,0.000028382072,0.00008739005,0.00014890317,0.000027151671,0.00052809657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982272,0.00018396681,0.00023155687,0.00045370322,0.00051170785,0.0003918765],"domain_scores_gemma":[0.9992467,0.00021618391,0.00011135631,0.00024848906,0.0000051454344,0.00017213689],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003532792,0.00015265141,0.0001352316,0.00003828956,0.00042998415,0.00001698485,0.00020137156,0.000034324148,0.012230725],"category_scores_gemma":[0.00009595425,0.00017558964,0.000030244883,0.00019833878,0.0003247883,0.00012661186,0.00043052292,0.00028790632,0.00040598732],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034529474,0.0017988094,0.06600511,0.000070256196,0.00017115887,0.0017122102,0.012365434,0.094986364,0.006815819,0.05581775,0.1332926,0.6266192],"study_design_scores_gemma":[0.0038950606,0.0009976982,0.21212538,0.000028101838,0.00011720241,0.00019530964,0.007679357,0.4479565,0.0007247887,0.076888084,0.24720399,0.00218852],"about_ca_topic_score_codex":0.00028041244,"about_ca_topic_score_gemma":0.000037188238,"teacher_disagreement_score":0.7438817,"about_ca_system_score_codex":0.0004749422,"about_ca_system_score_gemma":0.00003412418,"threshold_uncertainty_score":0.98867226},"labels":[],"label_agreement":null},{"id":"W4311239350","doi":"10.1093/biostatistics/kxac047","title":"Inference after latent variable estimation for single-cell RNA sequencing data","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Simons Foundation","keywords":"Inference; Latent variable; Count data; Computer science; Type I and type II errors; Latent variable model; Context (archaeology); Poisson distribution; Statistical inference; Data set; Data mining; Algorithm; Latent class model; Statistics; Mathematics; Machine learning; Artificial intelligence; Biology","score_opus":0.04935330434777099,"score_gpt":0.2670004868434502,"score_spread":0.2176471824956792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311239350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08322625,0.00045217382,0.9095521,0.00006367347,0.0007244315,0.0004887124,0.0049211257,0.000027822809,0.00054369174],"genre_scores_gemma":[0.8666774,0.000024730853,0.12841178,0.00028559216,0.00010715559,0.00007739298,0.0040386105,0.000027389238,0.00034994388],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990435,0.000038941034,0.00021178815,0.0003532149,0.00013395557,0.00021856725],"domain_scores_gemma":[0.9992736,0.000049274742,0.000081706654,0.0004679295,0.00007213606,0.000055365323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001791741,0.00012919979,0.00010829891,0.000028362092,0.000168053,0.000043004075,0.00030641,0.00005860226,0.000058470796],"category_scores_gemma":[0.00014816238,0.00014245276,0.000026227524,0.00007280815,0.000034995108,0.0000061853534,0.00023384714,0.00008220421,0.000003321527],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021065834,0.0002353805,0.0004537728,0.00013993241,0.000029369321,0.000007646642,0.000086192544,0.0033391013,0.98659855,0.00045817185,0.00444275,0.003998461],"study_design_scores_gemma":[0.004112302,0.003058633,0.00032678852,0.00006560612,0.0003283598,0.0000530171,0.00030710612,0.35675228,0.39678562,0.0031110812,0.23349176,0.0016074384],"about_ca_topic_score_codex":0.00004502813,"about_ca_topic_score_gemma":0.000014502777,"teacher_disagreement_score":0.78345114,"about_ca_system_score_codex":0.000053534415,"about_ca_system_score_gemma":0.00016109574,"threshold_uncertainty_score":0.5809055},"labels":[],"label_agreement":null},{"id":"W4321611071","doi":"10.1093/biostatistics/kxad002","title":"Assessing the causal effects of a stochastic intervention in time series data: are heat alerts effective in preventing deaths and hospitalizations?","year":2023,"lang":"en","type":"review","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Minority Health and Health Disparities; National Institute of Environmental Health Sciences; Wellcome Trust; Alfred P. Sloan Foundation; National Institute on Aging; National Institutes of Health; Harvard University","keywords":"Causal inference; Estimator; Context (archaeology); Computer science; Time series; Inference; Econometrics; Series (stratigraphy); Nonparametric statistics; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.13287255036280732,"score_gpt":0.4694060812927,"score_spread":0.3365335309298927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321611071","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003524683,0.63058954,0.3628299,0.000008610722,0.00019059738,0.0052014776,0.0006291559,0.00018655544,0.000011662206],"genre_scores_gemma":[0.002594856,0.949761,0.044545107,0.00000773422,0.00010852907,0.0012863587,0.0012089785,0.0003094996,0.00017794472],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9976269,0.0006088704,0.0008823143,0.00041107435,0.00022484001,0.0002460172],"domain_scores_gemma":[0.99252355,0.0062077334,0.0006359481,0.00052859646,0.00007268015,0.000031515712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009248536,0.0003550107,0.0012221808,0.0002878563,0.000055987664,0.000106779364,0.00035196735,0.00020083514,0.0000023339098],"category_scores_gemma":[0.007827202,0.000276519,0.00006508705,0.0005452819,0.00014562768,0.00033895767,0.0005557932,0.00034135798,0.0000028850523],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001417557,0.000580884,0.00055732654,0.25733182,0.00041674313,0.0002909683,0.0013040184,0.000018520326,0.0000100277375,0.018384451,0.0005126168,0.72057843],"study_design_scores_gemma":[0.0013406741,0.0007983744,0.003919378,0.72595555,0.003459052,0.00014168791,0.0006999509,0.0042242752,0.00007882481,0.2550743,0.0021276786,0.002180232],"about_ca_topic_score_codex":0.000049396214,"about_ca_topic_score_gemma":0.00015809215,"teacher_disagreement_score":0.7183982,"about_ca_system_score_codex":0.00020715591,"about_ca_system_score_gemma":0.000093972,"threshold_uncertainty_score":0.9999687},"labels":[],"label_agreement":null},{"id":"W4323350268","doi":"10.1093/biostatistics/kxad003","title":"A Bayesian approach to estimating COVID-19 incidence and infection fatality rates","year":2023,"lang":"en","type":"article","venue":"Biostatistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; Centre for Global Health Research; St. Michael's Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Coronavirus disease 2019 (COVID-19); Statistics; Medicine; Proxy (statistics); Case fatality rate; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Multivariate statistics; Pandemic; Econometrics; Computer science; Mathematics; Disease; Epidemiology; Infectious disease (medical specialty); Internal medicine","score_opus":0.2973987214825874,"score_gpt":0.47669000304276166,"score_spread":0.17929128156017426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323350268","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043946534,0.00002201411,0.9531417,0.0014415672,0.000117411124,0.00045589913,0.00014872437,0.0004433206,0.00028285175],"genre_scores_gemma":[0.4868088,0.000035496127,0.51110417,0.0017240222,0.000094200055,0.00008945465,0.0000372112,0.000020158097,0.000086502725],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984987,0.00018954116,0.00038994072,0.0004061716,0.00019831122,0.0003173852],"domain_scores_gemma":[0.9931734,0.006131512,0.00013681031,0.00023106592,0.00006600056,0.00026120475],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013761229,0.00018421149,0.00033646278,0.0000932194,0.00033509723,0.00005234832,0.00010398129,0.00008310846,0.000012434107],"category_scores_gemma":[0.07401284,0.00015508142,0.00003092353,0.0005394214,0.00013438382,0.00005162582,0.00032964727,0.0001275543,0.000041986495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000757127,0.00026501837,0.40791917,0.004339996,0.00015217958,0.00007990409,0.0061257305,0.002976357,0.00026283597,0.3823599,0.18095072,0.014492489],"study_design_scores_gemma":[0.0003574956,0.00015027515,0.14330216,0.00006472181,0.00007125885,0.000016658927,0.00033314293,0.18979813,0.00003560845,0.66144013,0.0039330106,0.00049737695],"about_ca_topic_score_codex":0.00078899186,"about_ca_topic_score_gemma":0.00014124987,"teacher_disagreement_score":0.44286227,"about_ca_system_score_codex":0.00015217195,"about_ca_system_score_gemma":0.000059656344,"threshold_uncertainty_score":0.93378717},"labels":[],"label_agreement":null},{"id":"W4386404572","doi":"10.1093/biostatistics/kxad022","title":"Variable selection in high dimensions for discrete-outcome individualized treatment rules: Reducing severity of depression symptoms","year":2023,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Depression (economics); Outcome (game theory); Feature selection; Selection (genetic algorithm); Variable (mathematics); Econometrics; Medicine; Statistics; Computer science; Internal medicine; Artificial intelligence; Mathematics; Mathematical economics; Economics","score_opus":0.10470571346149896,"score_gpt":0.41863948485896896,"score_spread":0.31393377139747003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386404572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3295379,0.000016902739,0.6671747,0.00003204938,0.00012815309,0.0010488615,0.0014813003,0.00044006776,0.00014005078],"genre_scores_gemma":[0.40534538,0.000021150081,0.59410495,0.0000070123433,0.000018460492,0.00015678357,0.00016003213,0.000029669007,0.00015657986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867433,0.00007252917,0.00053276046,0.0002611017,0.00017469321,0.00028455644],"domain_scores_gemma":[0.99797374,0.0014183318,0.0002419153,0.00020994798,0.000102517995,0.000053576317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031329435,0.0001810413,0.00038749777,0.00019465697,0.000090752124,0.000014730357,0.00009402465,0.00012493841,0.000024040126],"category_scores_gemma":[0.0013738928,0.00015590171,0.00004265869,0.0004006488,0.00004726927,0.00008638029,0.000051309682,0.000084537045,0.0000041066205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021331903,0.00058716687,0.04112671,0.0007132052,0.00014040878,0.000010785102,0.0015385429,0.00039751688,0.044512883,0.89795536,0.0027530396,0.010051091],"study_design_scores_gemma":[0.0013388749,0.00043915046,0.011983367,0.0003092057,0.0001351202,0.0000043459195,0.00014202681,0.0051404773,0.038294937,0.941454,0.00043237425,0.0003261547],"about_ca_topic_score_codex":0.00026677514,"about_ca_topic_score_gemma":0.0000414387,"teacher_disagreement_score":0.0758075,"about_ca_system_score_codex":0.00021102409,"about_ca_system_score_gemma":0.00006530483,"threshold_uncertainty_score":0.6357487},"labels":[],"label_agreement":null},{"id":"W4399476155","doi":"10.1093/biostatistics/kxae016","title":"Fast matrix completion in epigenetic methylation studies with informative covariates","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; HEC Montréal","funders":"Institut de Valorisation des Données","keywords":"Covariate; Missing data; Imputation (statistics); DNA methylation; Epigenetics; Leverage (statistics); Computer science; Statistics; Computational biology; Mathematics; Data mining; Biology; Genetics; Gene; Gene expression","score_opus":0.020573476340981032,"score_gpt":0.3349433991800419,"score_spread":0.31436992283906084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399476155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4951721,0.019228505,0.4836697,0.00020145034,0.00038981426,0.00045050422,0.0002373381,0.000042237767,0.00060834887],"genre_scores_gemma":[0.9764806,0.001768989,0.02096221,0.000027277292,0.000094855386,0.000022007644,0.00046026858,0.000021152633,0.00016262404],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991226,0.00006480254,0.00027052793,0.00022639292,0.00014695112,0.00016870284],"domain_scores_gemma":[0.99953586,0.000084541934,0.00006257078,0.00014313476,0.00013633125,0.000037582588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024207655,0.00014784,0.00014544716,0.00011523637,0.000051249623,0.00005465989,0.00006268722,0.00008186701,0.00000859359],"category_scores_gemma":[0.00012299405,0.00012338434,0.00002460782,0.00021284231,0.00006728019,0.000007379803,0.00004184954,0.000076783246,0.000020938462],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065588165,0.00028682992,0.02188209,0.0017596867,0.0011117776,0.0001171899,0.009421499,0.040950436,0.7452568,0.0922272,0.0025383746,0.08379228],"study_design_scores_gemma":[0.0034177122,0.004472866,0.114022695,0.000906296,0.00037332476,0.00003682446,0.0044898433,0.06867504,0.68813294,0.03229964,0.08081604,0.0023567507],"about_ca_topic_score_codex":0.00002435801,"about_ca_topic_score_gemma":0.00016885437,"teacher_disagreement_score":0.4813085,"about_ca_system_score_codex":0.000038135462,"about_ca_system_score_gemma":0.000069094924,"threshold_uncertainty_score":0.5031467},"labels":[],"label_agreement":null},{"id":"W4400446963","doi":"10.1093/biostatistics/kxae019","title":"A marginal structural model for normal tissue complication probability","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Colorectal and Anal Carcinomas","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Sanofi","keywords":"Radiation therapy; Context (archaeology); Estimator; Marginal structural model; Medicine; Computer science; Mathematics; Statistics; Radiology; Pathology; Causal inference","score_opus":0.04386924663779295,"score_gpt":0.32703391561408884,"score_spread":0.2831646689762959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400446963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52282834,0.00044995022,0.47004867,0.0023091778,0.00028538654,0.0011283205,0.0014409964,0.00017768855,0.0013314557],"genre_scores_gemma":[0.9507356,0.0000025482361,0.0474004,0.00008939439,0.00014084224,0.000029951956,0.000264407,0.000010425107,0.0013264326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994728,0.0000053943722,0.00012840056,0.00016810904,0.00009795434,0.00012734847],"domain_scores_gemma":[0.9996758,0.000057811,0.000015347989,0.00009339595,0.000089324574,0.00006832786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000052881478,0.000077583216,0.00010732741,0.000030374025,0.000045649158,0.000024332316,0.000031719846,0.00003421736,0.000039727714],"category_scores_gemma":[0.00005383705,0.00006234077,0.000035374524,0.00007282275,0.000048092024,0.000029186247,0.000016504386,0.000066264314,0.00001605511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016855055,0.00018964027,0.008434628,0.006906844,0.00015959861,0.00013142293,0.0017405414,0.00043678077,0.083108,0.60707,0.034871124,0.25526592],"study_design_scores_gemma":[0.00026899306,0.00032894927,0.024112547,0.000040082326,0.000089942965,0.00006802781,0.0000116082365,0.9457396,0.0011750952,0.024220597,0.0038425114,0.000102026504],"about_ca_topic_score_codex":0.000012115621,"about_ca_topic_score_gemma":0.000019908557,"teacher_disagreement_score":0.94530284,"about_ca_system_score_codex":0.000058172947,"about_ca_system_score_gemma":0.00009614724,"threshold_uncertainty_score":0.25421828},"labels":[],"label_agreement":null},{"id":"W4403798551","doi":"10.1093/biostatistics/kxae039","title":"Selection processes, transportability, and failure time analysis in life history studies","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Demographic Trends and Gender Preferences","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Selection (genetic algorithm); Computer science; Econometrics; Artificial intelligence; Mathematics","score_opus":0.04926000744727137,"score_gpt":0.3216940800327122,"score_spread":0.27243407258544083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403798551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76682466,0.18802458,0.0067484356,0.015578322,0.0019342058,0.001127778,0.0009234852,0.0012822917,0.017556222],"genre_scores_gemma":[0.9961752,0.0018755831,0.00091004046,0.00003525952,0.00005143005,0.000008533908,0.000017106242,0.000004368656,0.0009224668],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991919,0.00007819073,0.00016338825,0.0002344665,0.00018398206,0.00014806903],"domain_scores_gemma":[0.99956125,0.00022144796,0.000025379804,0.00004458609,0.00007849464,0.00006886368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037622356,0.00007797866,0.00016706379,0.00026488022,0.00009015012,0.000043798307,0.000057152985,0.000058519487,0.00018933209],"category_scores_gemma":[0.00022700746,0.00006979018,0.000028834576,0.0012198382,0.00025997547,0.00009642335,0.0000073607835,0.000081601735,0.000005314723],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033040837,0.00020932833,0.5516101,0.001584155,0.0021631375,0.00006179595,0.24673387,0.000042931773,0.000051664985,0.081275135,0.06335371,0.052881125],"study_design_scores_gemma":[0.0003374455,0.00018136585,0.3785042,0.00015805755,0.0019648075,0.0000015770963,0.025490163,0.0022926936,0.000008755374,0.031883888,0.55834955,0.0008274901],"about_ca_topic_score_codex":0.00095338223,"about_ca_topic_score_gemma":0.103737384,"teacher_disagreement_score":0.49499583,"about_ca_system_score_codex":0.00008334512,"about_ca_system_score_gemma":0.0003336599,"threshold_uncertainty_score":0.9126171},"labels":[],"label_agreement":null},{"id":"W4404260614","doi":"10.1093/biostatistics/kxae043","title":"Fast standard error estimation for joint models of longitudinal and time-to-event data based on stochastic EM algorithms","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Distributed Sensor Networks and Detection Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Computer science; Algorithm; Joint (building); Event (particle physics); Estimation; Event data; Data mining","score_opus":0.04732250925768137,"score_gpt":0.30083655796217923,"score_spread":0.25351404870449784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404260614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052844363,0.00006160388,0.99295795,0.00040650237,0.0003895739,0.0003708469,0.005626156,0.000109770335,0.000024752673],"genre_scores_gemma":[0.22650315,0.0000023136406,0.7727808,0.00008308115,0.00007419501,0.000018234223,0.00040292682,0.000020296375,0.00011501223],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986662,0.000024734725,0.0002968781,0.00048053102,0.00033054195,0.00020110545],"domain_scores_gemma":[0.99889094,0.00026389686,0.00007144588,0.00050030055,0.00014574798,0.00012765307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003145848,0.0001505383,0.00020084073,0.00014080452,0.00008162072,0.00024177766,0.00028483782,0.000048228118,0.000013164548],"category_scores_gemma":[0.00012714179,0.0001387183,0.000031027106,0.00028576332,0.0000354206,0.00017754601,0.0001488825,0.00007991083,0.000019764786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047033114,0.000046164656,2.3922433e-7,0.0000941532,0.000026685242,0.000012141186,0.00008653367,0.5970286,0.000020316547,0.00709273,0.011955713,0.38358968],"study_design_scores_gemma":[0.0002502794,0.0005460605,0.000037075188,0.00013987877,0.000029089473,0.0000073265264,0.000009189367,0.99472797,0.00008886449,0.0035528035,0.00045801885,0.00015343384],"about_ca_topic_score_codex":0.0000055779083,"about_ca_topic_score_gemma":0.0000027524202,"teacher_disagreement_score":0.3976994,"about_ca_system_score_codex":0.000053740598,"about_ca_system_score_gemma":0.00009847398,"threshold_uncertainty_score":0.5656768},"labels":[],"label_agreement":null},{"id":"W4405942876","doi":"10.1093/biostatistics/kxae046","title":"Testing for a difference in means of a single feature after clustering","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Cluster analysis; Type I and type II errors; Feature (linguistics); Computer science; Hierarchical clustering; Data mining; Statistical hypothesis testing; Algorithm; Word error rate; Pattern recognition (psychology); Statistics; Artificial intelligence; Mathematics","score_opus":0.023888730904485327,"score_gpt":0.2522287114570061,"score_spread":0.22833998055252078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405942876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69443715,0.0020833027,0.3016324,0.00009078767,0.00047597487,0.0003442515,0.0006560149,0.000021866188,0.0002582304],"genre_scores_gemma":[0.9547591,0.000015358739,0.044770774,0.00004640558,0.00010414432,0.000026041555,0.00006050129,0.000019640816,0.00019801056],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946815,0.000011478992,0.00013810459,0.00018814745,0.00005118501,0.00014291587],"domain_scores_gemma":[0.9997403,0.00006148475,0.000021730139,0.000101688354,0.00004807877,0.000026709537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053035255,0.00009436678,0.00010169886,0.000037592417,0.000013969184,0.000023410063,0.000067800436,0.00008695392,0.000002070946],"category_scores_gemma":[0.00014742014,0.000088711415,0.00003526368,0.00008368504,0.000037645867,0.0000013770047,0.00002514178,0.000049717954,5.231303e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090787,0.00006456196,0.003136412,0.0004551863,0.000014416072,0.000009638918,0.00013454026,0.000027710943,0.9824482,0.00006709031,0.00023787915,0.013313583],"study_design_scores_gemma":[0.0038351319,0.005166203,0.07849775,0.0031562622,0.00024787014,0.00008676022,0.00040808765,0.11122947,0.7437839,0.0025212534,0.049206734,0.0018605794],"about_ca_topic_score_codex":0.000018349196,"about_ca_topic_score_gemma":0.00023404208,"teacher_disagreement_score":0.26032194,"about_ca_system_score_codex":0.000011554628,"about_ca_system_score_gemma":0.00003873377,"threshold_uncertainty_score":0.36175466},"labels":[],"label_agreement":null},{"id":"W4415333191","doi":"10.1093/biostatistics/kxaf033","title":"Wastewater-based reproduction rates for epidemic curve reconstruction","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Inference; Autoregressive model; Bayesian inference; Key (lock); Poisson distribution; Estimator; Gaussian","score_opus":0.25291431894758687,"score_gpt":0.4580066023355928,"score_spread":0.20509228338800595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415333191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047915015,0.0013801239,0.93562335,0.0087870285,0.0033990885,0.0011370842,0.0007279707,0.0008371309,0.00019323628],"genre_scores_gemma":[0.47734866,0.00022141676,0.5192316,0.0003988741,0.0011688718,0.00027967006,0.0001351588,0.00007890853,0.001136797],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983995,0.00013848969,0.00052969414,0.00053923926,0.00011265819,0.0002803973],"domain_scores_gemma":[0.99219924,0.007197779,0.0001243122,0.00029501138,0.00012956215,0.00005409352],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001317781,0.00018889508,0.00032922646,0.00008452917,0.00014779363,0.00004632318,0.00008659219,0.000108582935,0.00006370739],"category_scores_gemma":[0.019174555,0.00014603547,0.00010575381,0.00018407163,0.00013376834,0.00006300258,0.0000340337,0.00013599257,0.000048544196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024819444,0.00018003536,0.006637866,0.004954515,0.00037267237,0.000031046613,0.00042462145,0.0003169802,0.007832963,0.3648473,0.42905697,0.18509682],"study_design_scores_gemma":[0.00032438737,0.0002732324,0.00065316085,0.0002842884,0.00017933197,0.000020766794,0.00012757113,0.03546795,0.009106394,0.8931421,0.06003819,0.0003826166],"about_ca_topic_score_codex":0.000034621284,"about_ca_topic_score_gemma":0.000018214114,"teacher_disagreement_score":0.5282948,"about_ca_system_score_codex":0.00016285105,"about_ca_system_score_gemma":0.00005939998,"threshold_uncertainty_score":0.98908734},"labels":[],"label_agreement":null},{"id":"W4415615025","doi":"10.1093/biostatistics/kxaf032","title":"A novel high-dimensional model for identifying regional DNA methylation QTLs","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; Université du Québec à Montréal; Mila - Quebec Artificial Intelligence Institute; Jewish General Hospital; York University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Covariate; Flexibility (engineering); Smoothness; Selection (genetic algorithm); Regression; Feature selection; Variable (mathematics); Regression analysis","score_opus":0.2821465805369406,"score_gpt":0.4362327932265029,"score_spread":0.1540862126895623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415615025","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014087396,0.00010953153,0.99526167,0.00036088462,0.00052806607,0.00030013488,0.0017902731,0.00012716145,0.00011352079],"genre_scores_gemma":[0.07298415,0.000007158878,0.92574894,0.00016315315,0.00016600933,0.00004964372,0.000104113176,0.000042511867,0.00073429267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861455,0.000036780897,0.00041270698,0.0003402997,0.0003355658,0.00026011764],"domain_scores_gemma":[0.99530596,0.0041296696,0.000080674654,0.00018276813,0.0002037093,0.0000972114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005257334,0.00017859621,0.00023326912,0.00010100484,0.00011920773,0.000114090726,0.00010805579,0.00010121362,0.00008497407],"category_scores_gemma":[0.0023642029,0.00015810011,0.000073092175,0.00014797332,0.00007645635,0.000076711825,0.00004500241,0.00013098889,0.000026295422],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020054873,0.00004789934,8.7629553e-7,0.00031164972,0.000042100863,0.000005773217,0.00015501048,0.000102443824,0.0128373355,0.957724,0.0150076365,0.013745248],"study_design_scores_gemma":[0.00014824742,0.000026965752,0.000045113175,0.00008573525,0.000061437946,0.000007526562,0.0000080289965,0.4741269,0.00060889457,0.524441,0.00031820167,0.00012194015],"about_ca_topic_score_codex":0.000012963297,"about_ca_topic_score_gemma":0.000007221388,"teacher_disagreement_score":0.47402447,"about_ca_system_score_codex":0.000065575434,"about_ca_system_score_gemma":0.00013792585,"threshold_uncertainty_score":0.6447135},"labels":[],"label_agreement":null},{"id":"W4416052855","doi":"10.1093/biostatistics/kxaf034","title":"Markov switching zero-inflated space-time multinomial models for comparing multiple infectious diseases","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canada First Research Excellence Fund; Fundação Oswaldo Cruz; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Escola Nacional de Saúde Pública Sérgio Arouca; Compute Canada","keywords":"Markov chain Monte Carlo; Markov chain; Multinomial distribution; Bayesian probability; Univariate; Inference; Bayesian inference; Autoregressive model; Multivariate statistics","score_opus":0.13757555115086603,"score_gpt":0.38399366470267043,"score_spread":0.2464181135518044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416052855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06931867,0.0005042468,0.92592555,0.0003902944,0.0005627433,0.000993234,0.0008516447,0.0010396835,0.0004139078],"genre_scores_gemma":[0.92626125,0.000044406224,0.07286246,0.0001300376,0.00023538066,0.00009386503,0.00006860986,0.00006376971,0.0002402084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981621,0.00010138954,0.0005721429,0.00049165613,0.00018688609,0.00048585393],"domain_scores_gemma":[0.9852687,0.014076954,0.00013850363,0.00025721584,0.00011039464,0.0001482437],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040232946,0.000326501,0.0006288575,0.00010048569,0.0002908129,0.00012679385,0.00016255917,0.00012652046,0.000026159685],"category_scores_gemma":[0.010548532,0.00027266575,0.00017399726,0.00017410239,0.00007784901,0.00011024363,0.0002184299,0.00020708384,0.000059171212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092867773,0.0011356393,0.081125595,0.008245004,0.0023660639,0.00032229954,0.0035665017,0.024173912,0.0067282687,0.5009544,0.3152127,0.055240974],"study_design_scores_gemma":[0.0006465032,0.00007638769,0.0015325486,0.00014545859,0.00019760756,0.0000032276841,0.000020299707,0.7616436,0.000044671382,0.23299465,0.002371211,0.00032387656],"about_ca_topic_score_codex":0.00015039621,"about_ca_topic_score_gemma":0.000066868975,"teacher_disagreement_score":0.8569426,"about_ca_system_score_codex":0.00023060355,"about_ca_system_score_gemma":0.000059775863,"threshold_uncertainty_score":0.9999726},"labels":[],"label_agreement":null},{"id":"W939145883","doi":"10.1093/biostatistics/kxw049","title":"Inequality in treatment benefits: Can we determine if a new treatment benefits the many or the few?","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; Patient-Centered Outcomes Research Institute; U.S. Food and Drug Administration; National Institute on Aging; National Institutes of Health; Hamilton Health Sciences Foundation","keywords":"Randomized controlled trial; Estimator; Fraction (chemistry); Computer science; Statistics; Econometrics; Randomized response; Outcome (game theory); Mathematics; Medicine; Mathematical optimization; Mathematical economics","score_opus":0.2502387195907997,"score_gpt":0.4054696846381312,"score_spread":0.15523096504733153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W939145883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59969634,0.0027699014,0.28918976,0.07818333,0.0010802641,0.0119621195,0.013507704,0.001963117,0.0016474839],"genre_scores_gemma":[0.89044607,0.0068498976,0.09357225,0.00048885855,0.00032784388,0.00059252995,0.000039095383,0.00013046752,0.007553008],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982081,0.00014635973,0.0005736999,0.00034972493,0.0002588545,0.000463231],"domain_scores_gemma":[0.9957225,0.0028930723,0.00025859944,0.000920674,0.000077241006,0.00012794306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021497897,0.0004007481,0.00041384925,0.00006667107,0.00013929348,0.000048530597,0.00033672148,0.00010943891,0.00013297715],"category_scores_gemma":[0.000755597,0.00013903064,0.00007307849,0.00021514262,0.00014290062,0.00006763846,0.00009097594,0.000083575884,0.000025585468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012329694,0.0003348755,0.0013006963,0.000024572204,0.000072144685,0.000049558508,0.0019692737,0.000006724904,0.00021145157,0.21639727,0.001642969,0.7778672],"study_design_scores_gemma":[0.0060455995,0.0056861388,0.013727851,0.0011017014,0.0005380912,0.0001240198,0.00129407,0.00051194814,0.033937495,0.8852222,0.050303027,0.0015078353],"about_ca_topic_score_codex":0.0009943891,"about_ca_topic_score_gemma":0.012356794,"teacher_disagreement_score":0.7763593,"about_ca_system_score_codex":0.00078899553,"about_ca_system_score_gemma":0.00023295953,"threshold_uncertainty_score":0.6895381},"labels":[],"label_agreement":null}]}