{"meta":{"query_hash":"e685fd8d3153","filters":{"venue":"Journal of Official Statistics"},"cohort_total":34,"direct_labels_cover":0,"predictions_cover":34,"exported":34,"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/e685fd8d3153","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Official+Statistics"},"results":[{"id":"W1011634492","doi":"","title":"The perils of interpreting age differences in attitude reports: question order effects decrease with age","year":2007,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Social and Intergroup Psychology","field":"Social Sciences","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":"McGill University","funders":"","keywords":"Compromise; Psychology; Dimension (graph theory); Age groups; Order (exchange); Survey data collection; Social psychology; Developmental psychology; Cognitive psychology; Demography; Statistics; Mathematics; Sociology; Social science","score_opus":0.01576351587568853,"score_gpt":0.3467779022615133,"score_spread":0.33101438638582475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1011634492","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":[0.93854505,0.0001777983,0.05622481,0.00020368319,0.0011751256,0.00014395895,0.000003225396,0.0000070069464,0.0035193302],"genre_scores_gemma":[0.99529356,0.000099661454,0.004095634,0.000078404526,0.00033776124,9.593658e-7,9.0057006e-7,0.000007165591,0.000085958876],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828804,0.00029908164,0.00064177485,0.0000888518,0.00043531196,0.00024693465],"domain_scores_gemma":[0.9974055,0.0013473572,0.0007427208,0.00006809,0.0003216737,0.00011464744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023177892,0.00008816438,0.00027306812,0.00008449005,0.00020506815,0.000053787528,0.00017570861,0.00008196251,0.000023731873],"category_scores_gemma":[0.004916646,0.000057368103,0.000042349347,0.00026059683,0.0005133954,0.00007626288,0.000017439523,0.0002507194,5.780032e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034302326,0.0012854403,0.5383586,0.000120394514,0.00033747603,0.012086874,0.09731524,0.000035877485,0.0024738477,0.18418172,0.0033948964,0.1569794],"study_design_scores_gemma":[0.0008571744,0.0018741396,0.95332146,0.000771001,0.00010148632,0.000089852605,0.013484777,0.00002928352,0.00016390024,0.0229453,0.0060610357,0.00030059883],"about_ca_topic_score_codex":0.0017923417,"about_ca_topic_score_gemma":0.026251353,"teacher_disagreement_score":0.41496283,"about_ca_system_score_codex":0.00010615788,"about_ca_system_score_gemma":0.00022482107,"threshold_uncertainty_score":0.991517},"labels":[],"label_agreement":null},{"id":"W139414717","doi":"","title":"Raking ratio estimation: an application to the Canadian retail trade survey","year":2006,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Estimation; Statistics; Econometrics; Small area estimation; Retail trade; Business; Mathematics; Geography; Economics; Commerce","score_opus":0.032613119829573704,"score_gpt":0.26791435702851313,"score_spread":0.23530123719893942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W139414717","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":[0.11227776,0.00005366332,0.88065696,0.0031237944,0.0009520292,0.00038116338,0.00008393324,0.000024290594,0.0024463783],"genre_scores_gemma":[0.9951263,8.22259e-7,0.0030575301,0.00047425882,0.0012219169,0.0000018454236,0.00007484771,0.000013822884,0.000028668717],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99902314,0.000034943012,0.0004037264,0.00008413347,0.00028932147,0.00016471917],"domain_scores_gemma":[0.9991388,0.000105207815,0.00034200473,0.00011530476,0.00026861092,0.0000300874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010919913,0.00009167986,0.00013467752,0.00017837666,0.0003914359,0.0004215966,0.00021119951,0.000037712914,0.00007802502],"category_scores_gemma":[0.00024534293,0.00007464058,0.000027347392,0.00034803821,0.000021304508,0.00032496225,0.00001544,0.00015208962,0.000021281894],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021066045,0.00017509119,0.15896876,0.000055474808,0.00003626903,0.00007465214,0.00030059973,0.039410252,0.00027014574,0.04670675,0.06636249,0.68742883],"study_design_scores_gemma":[0.00018512746,0.00001792529,0.8851951,0.0000146217435,0.00009473841,0.0000092895725,0.00004541391,0.04139829,0.0000091469965,0.0010619921,0.07181752,0.00015088344],"about_ca_topic_score_codex":0.16026697,"about_ca_topic_score_gemma":0.818662,"teacher_disagreement_score":0.8828485,"about_ca_system_score_codex":0.00007777149,"about_ca_system_score_gemma":0.0001712813,"threshold_uncertainty_score":0.8453249},"labels":[],"label_agreement":null},{"id":"W1850438056","doi":"","title":"A pseudo-GEE approach to analyzing longitudinal surveys under imputation por missing responses","year":2011,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Statistical Methods and Bayesian Inference","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":"University of Waterloo; University of British Columbia","funders":"","keywords":"Missing data; Estimator; Statistics; Imputation (statistics); Mathematics; Generalized estimating equation; Gee; Marginal model; Econometrics; Estimating equations; Regression analysis","score_opus":0.19174119103394777,"score_gpt":0.39776172296818546,"score_spread":0.2060205319342377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1850438056","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":[0.01343556,0.000023382723,0.9848474,0.000053937998,0.00030991816,0.00013459614,0.00014242229,0.000018160214,0.001034623],"genre_scores_gemma":[0.21223122,0.0000051564,0.7874433,0.00004487539,0.00021018871,0.0000012885658,0.0000027531871,0.000027622522,0.000033583005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99705774,0.0008287164,0.0010432856,0.00020617478,0.000523523,0.00034054674],"domain_scores_gemma":[0.99557024,0.0025385532,0.00071710994,0.00017153955,0.0007090147,0.00029355253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031419224,0.0002172281,0.00055071426,0.00028744078,0.00016008725,0.00010051303,0.00025043948,0.000099121025,0.00012565314],"category_scores_gemma":[0.007237764,0.0001840981,0.000098573415,0.0003667466,0.00009141378,0.00012330768,0.000049434217,0.0003298846,0.000008768439],"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":[0.0008431117,0.00092233345,0.004016563,0.00018472345,0.00024644673,0.00027369516,0.002319008,0.00006519664,0.0005110805,0.8151768,0.0033671514,0.17207389],"study_design_scores_gemma":[0.0004976595,0.0006740488,0.105438724,0.00013174691,0.00027829348,0.00022173877,0.00036019337,0.0026923132,0.00032734056,0.889004,0.000034642573,0.00033928506],"about_ca_topic_score_codex":0.000058040314,"about_ca_topic_score_gemma":0.000023991499,"teacher_disagreement_score":0.19879566,"about_ca_system_score_codex":0.00011072407,"about_ca_system_score_gemma":0.0002939611,"threshold_uncertainty_score":0.86648023},"labels":[],"label_agreement":null},{"id":"W1982870529","doi":"10.2478/jos-2014-0005","title":"A Convenient Method of Decomposing the Gini Index by Population Subgroups","year":2014,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Income, Poverty, and Inequality","field":"Social Sciences","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":"Brock University","funders":"","keywords":"Heteroscedasticity; Index (typography); Statistics; Econometrics; Decomposition; Standard error; Mathematics; Group (periodic table); Population; Regression; Grouped data; Computer science; Demography; Sociology; Biology; Physics; Ecology","score_opus":0.029214403300287045,"score_gpt":0.35819067018633943,"score_spread":0.3289762668860524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982870529","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":[0.08294489,0.000054711712,0.9135534,0.0005239133,0.0010526483,0.000090711954,0.000059607413,0.0000054420266,0.0017146693],"genre_scores_gemma":[0.983238,0.00003104939,0.015910141,0.00019796133,0.0005661111,2.742093e-7,0.0000049990385,0.000007120085,0.00004436898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977349,0.00076614326,0.00062569015,0.00006556477,0.00063462276,0.0001730683],"domain_scores_gemma":[0.9976734,0.0009299205,0.000860274,0.00008204989,0.0003748355,0.0000795105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033114634,0.00007484026,0.0002578949,0.000049248134,0.0003026742,0.000048971808,0.00022481511,0.00007021882,0.000056505865],"category_scores_gemma":[0.0012950744,0.000054516553,0.00007319413,0.0001424526,0.0001267014,0.00010172706,0.000019600096,0.00018945751,0.0000015638885],"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":[0.00041225698,0.0005054848,0.07551601,0.00007194943,0.00013121871,0.000006407872,0.021387842,0.001214236,0.00068347534,0.73540235,0.028619878,0.1360489],"study_design_scores_gemma":[0.003544039,0.001912761,0.3296695,0.00026777803,0.0005406261,0.00003636736,0.011314591,0.03809658,0.0013272702,0.23696798,0.37532744,0.0009950683],"about_ca_topic_score_codex":0.0034015325,"about_ca_topic_score_gemma":0.0012739633,"teacher_disagreement_score":0.90029305,"about_ca_system_score_codex":0.000107923755,"about_ca_system_score_gemma":0.0001318033,"threshold_uncertainty_score":0.51421225},"labels":[],"label_agreement":null},{"id":"W2065371000","doi":"10.2478/jos-2014-0018","title":"Recruiting an Internet Panel Using Respondent-Driven Sampling","year":2014,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","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":"University of Waterloo","funders":"","keywords":"Respondent; The Internet; Sampling (signal processing); Population; Selection (genetic algorithm); Psychology; Computer science; Internet privacy; Demography; World Wide Web; Sociology; Political science; Artificial intelligence; Telecommunications","score_opus":0.2555636910933322,"score_gpt":0.4293954125469362,"score_spread":0.17383172145360398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065371000","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":[0.5887973,0.000022949665,0.41030043,0.000046708945,0.000458024,0.00007914719,0.000033028977,0.00001449116,0.0002479241],"genre_scores_gemma":[0.80976653,0.000011639076,0.18800908,0.00019505562,0.0018130048,2.8246882e-7,0.000015251179,0.0000462248,0.00014295576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978569,0.00019268651,0.00088038883,0.00016061547,0.0006028617,0.0003065298],"domain_scores_gemma":[0.99774915,0.00047376164,0.0007247576,0.00018511193,0.0005424551,0.00032479307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009059989,0.00017014795,0.00050021143,0.00024204877,0.00008945723,0.000067172536,0.00018953858,0.000105812025,0.00010196469],"category_scores_gemma":[0.002658141,0.0001545199,0.00007287163,0.00015295102,0.00007106174,0.00014125735,0.000049827853,0.00055003667,0.000018707586],"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":[0.0065577556,0.0017909942,0.032445904,0.0005864052,0.0007389591,0.0022435964,0.040668916,0.018026892,0.13844433,0.0127934385,0.0075434055,0.7381594],"study_design_scores_gemma":[0.013915221,0.016715795,0.059780568,0.0044227163,0.003227139,0.0068982006,0.044326283,0.77478427,0.01232342,0.008634903,0.05276208,0.002209427],"about_ca_topic_score_codex":0.00006938518,"about_ca_topic_score_gemma":0.000065322405,"teacher_disagreement_score":0.7567574,"about_ca_system_score_codex":0.00019544258,"about_ca_system_score_gemma":0.0002665878,"threshold_uncertainty_score":0.63011384},"labels":[],"label_agreement":null},{"id":"W2095109928","doi":"10.2478/jos-2014-0040","title":"An Adaptive Data Collection Procedure for Call Prioritization","year":2014,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Non-response bias; Computer science; Data collection; Context (archaeology); Estimator; Constraint (computer-aided design); Sample (material); Prioritization; Variance (accounting); Statistics; Mathematics","score_opus":0.2708862773070399,"score_gpt":0.4786023429301528,"score_spread":0.2077160656231129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095109928","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":[0.014602183,0.000025860607,0.983671,0.00022518232,0.0009294821,0.00016320783,0.000155975,0.00000951163,0.0002175967],"genre_scores_gemma":[0.5113366,0.00008008713,0.48519155,0.00020356892,0.0027164833,0.000002654167,0.000079157464,0.000018535547,0.00037136042],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995982,0.0032489127,0.00028037117,0.0001032303,0.00024347503,0.00014203056],"domain_scores_gemma":[0.9931731,0.0056115543,0.0003398658,0.00010161264,0.0006779547,0.00009591357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015435326,0.000056898785,0.00016161874,0.00007323675,0.00040863163,0.000036644382,0.00026724467,0.000108255605,0.000019423574],"category_scores_gemma":[0.035520583,0.00005494672,0.000020443766,0.00016092349,0.0001101388,0.00021801169,0.0000120193245,0.00012200943,0.0000012948414],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.080682985,0.0016559411,0.012331769,0.00011515048,0.0003565461,0.00004762054,0.03662832,0.0018834849,0.0016772897,0.29501426,0.29550913,0.27409747],"study_design_scores_gemma":[0.0061073266,0.014622503,0.26022768,0.00018434194,0.00085995696,0.000084789724,0.011042911,0.13343398,0.00077247835,0.11584985,0.4555666,0.0012475577],"about_ca_topic_score_codex":0.00013294768,"about_ca_topic_score_gemma":0.0037488062,"teacher_disagreement_score":0.49847946,"about_ca_system_score_codex":0.00006090886,"about_ca_system_score_gemma":0.0007754207,"threshold_uncertainty_score":0.9726036},"labels":[],"label_agreement":null},{"id":"W2270633939","doi":"10.1515/jos-2017-0013","title":"Cost-Benefit Analysis for a Quinquennial Census: The 2016 Population Census of South Africa","year":2017,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":9,"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 Science Foundation","keywords":"Census; Revenue; Population; Government (linguistics); Geography; American Community Survey; Actuarial science; Economics; Demography; Finance; Sociology","score_opus":0.06657612256202393,"score_gpt":0.35501119912396056,"score_spread":0.2884350765619366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270633939","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":[0.90046805,0.0004341598,0.08558519,0.0030393822,0.001479817,0.0008448928,0.0076287836,0.000011596386,0.000508099],"genre_scores_gemma":[0.9916005,0.000054727487,0.007261643,0.00009873724,0.0008036282,0.0000011501494,0.00004160714,0.000010496517,0.00012751995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99858683,0.000026397496,0.0007039171,0.00008475902,0.00039335623,0.00020473756],"domain_scores_gemma":[0.9973888,0.00012412509,0.0014502505,0.0002167429,0.00068374624,0.00013637668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040392778,0.00010533738,0.00048499828,0.00009832108,0.00026353684,0.000037202535,0.00018838809,0.00006493253,0.000027226704],"category_scores_gemma":[0.00059786916,0.000064066684,0.00020427672,0.0000814325,0.00007846533,0.00003947749,0.000026735568,0.00015400551,0.0000019837669],"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":[0.026523896,0.0021852667,0.6852484,0.0014504689,0.0079433955,0.00047169326,0.008643366,0.00547606,0.0006541861,0.098330215,0.06439842,0.09867465],"study_design_scores_gemma":[0.0021922071,0.0009166452,0.974784,0.00015675125,0.0026507557,0.0000373681,0.00031486954,0.0014944931,0.000043129112,0.0051831384,0.0121094715,0.000117174204],"about_ca_topic_score_codex":0.00037222958,"about_ca_topic_score_gemma":0.0001583241,"teacher_disagreement_score":0.2895356,"about_ca_system_score_codex":0.00007671595,"about_ca_system_score_gemma":0.000111250185,"threshold_uncertainty_score":0.26125634},"labels":[],"label_agreement":null},{"id":"W2318655531","doi":"10.1515/jos-2016-0006","title":"A Discussion of Weighting Procedures for Unit Nonresponse","year":2016,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Weighting; Estimator; Computer science; Context (archaeology); Calibration; Statistics; A-weighting; Econometrics; Non-response bias; Point (geometry); Mathematics; Medicine; Geography","score_opus":0.1907204767361666,"score_gpt":0.45857689614981695,"score_spread":0.26785641941365035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318655531","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":[0.3385189,0.0000841682,0.6574197,0.0023657111,0.0009397594,0.0001866831,0.00024247059,0.000008659169,0.00023397055],"genre_scores_gemma":[0.8827276,0.00015039633,0.11436816,0.000067710134,0.00083270244,0.0000026167597,0.0000013705198,0.000016722572,0.0018326762],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99536496,0.0035234476,0.0005037152,0.00007630297,0.0003217281,0.00020985176],"domain_scores_gemma":[0.9755913,0.022970738,0.00064247416,0.00006236338,0.00062884734,0.00010425103],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016959993,0.00007532508,0.00025804577,0.00013431192,0.00023288223,0.000011314677,0.00020192644,0.00010302613,0.000114343246],"category_scores_gemma":[0.09647717,0.000039505496,0.00008308725,0.00014972808,0.00029144215,0.00010088972,0.000017290475,0.000085540465,0.0000023336966],"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":[0.19928175,0.0016099891,0.03111505,0.00025242756,0.00044284295,0.00019773767,0.040201463,0.000045169927,0.06948197,0.18731771,0.03752465,0.43252924],"study_design_scores_gemma":[0.010124089,0.008194065,0.35307783,0.0018878366,0.00066673907,0.00010383939,0.018238705,0.00010118778,0.031477544,0.17666613,0.3982143,0.0012477343],"about_ca_topic_score_codex":0.00003176996,"about_ca_topic_score_gemma":0.000662587,"teacher_disagreement_score":0.54420877,"about_ca_system_score_codex":0.000039164013,"about_ca_system_score_gemma":0.0011250384,"threshold_uncertainty_score":0.9111336},"labels":[],"label_agreement":null},{"id":"W2344433343","doi":"10.2478/jos-2020-0038","title":"Developing Land and Structure Price Indices for Ottawa Condominium Apartments","year":2020,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Housing Market and Economics","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; Statistics Canada","funders":"","keywords":"Apartment; Depreciation (economics); Stock (firearms); Real estate; Land price; Unit (ring theory); Business; Value (mathematics); Space (punctuation); Service (business); Decomposition; Price index; Agricultural economics; Economics; Finance; Econometrics; Geography; Computer science; Economic growth; Mathematics; Civil engineering; Statistics; Engineering; Marketing","score_opus":0.04359111781766025,"score_gpt":0.2490502035085133,"score_spread":0.20545908569085305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2344433343","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":[0.54750896,0.00054008304,0.44494215,0.001549298,0.0012278014,0.00027538772,0.0018613932,0.000010948793,0.0020839612],"genre_scores_gemma":[0.92603457,0.00025515456,0.07230982,0.0006968231,0.00064775156,9.220118e-7,0.000017808059,0.000022924718,0.000014238893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989918,0.000008160126,0.0006863841,0.00012434783,0.000028960856,0.00016034706],"domain_scores_gemma":[0.9987704,0.00016933803,0.00084613235,0.00004072254,0.000063676234,0.000109740235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002628309,0.00010154999,0.00039706397,0.00007413288,0.000084834595,0.0000912782,0.00011415142,0.000067236855,0.00005329206],"category_scores_gemma":[0.00044727427,0.00010872679,0.00003925268,0.000061007206,0.00003354693,0.0001231334,0.000025653075,0.00011626575,0.000006067214],"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":[0.0019829657,0.00016866896,0.39115232,0.0009783854,0.0009928403,0.00008307394,0.006095356,0.0014170408,0.00009513048,0.5193011,0.04026846,0.037464626],"study_design_scores_gemma":[0.010493489,0.0016065047,0.06574398,0.000095003656,0.00015065531,0.00008300146,0.0004045124,0.0213897,0.00038837446,0.19223657,0.70615685,0.0012513319],"about_ca_topic_score_codex":0.0000072481075,"about_ca_topic_score_gemma":0.000024363662,"teacher_disagreement_score":0.6658884,"about_ca_system_score_codex":0.0000539836,"about_ca_system_score_gemma":0.00007466429,"threshold_uncertainty_score":0.44337496},"labels":[],"label_agreement":null},{"id":"W2526240043","doi":"10.1515/jos-2016-0037","title":"The Marginal Effects in Subgroup Decomposition of the Gini Index","year":2016,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Income, Poverty, and Inequality","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Elasticity (physics); Econometrics; Mathematics; Decomposition; Index (typography); Statistics; Economics; Computer science; Physics; Thermodynamics","score_opus":0.016451505126039493,"score_gpt":0.3218015827864576,"score_spread":0.3053500776604181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2526240043","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":[0.8704603,0.00020316325,0.11604232,0.0041241744,0.0041360757,0.00031861613,0.00008751353,0.0000069625753,0.0046208887],"genre_scores_gemma":[0.9987855,0.00013018145,0.00043773965,0.000081709084,0.00045256224,5.758682e-7,2.0773925e-7,0.0000046104356,0.00010693508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998223,0.0005276925,0.00044396747,0.00005066434,0.0005624448,0.00019219433],"domain_scores_gemma":[0.99762934,0.0014872723,0.00050378003,0.00008665034,0.00024188205,0.000051077415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016781967,0.000063138315,0.0001632357,0.000039482267,0.00029361912,0.000031387863,0.00031683527,0.000059592414,0.000025374446],"category_scores_gemma":[0.0013360302,0.000029886494,0.00006728204,0.00015874983,0.00030540425,0.00009969982,0.00002820147,0.00015597057,0.000002714918],"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":[0.00068861333,0.00033534327,0.19067422,0.000047780257,0.000054865057,0.000034932018,0.0051984983,0.000046114277,0.0009171174,0.7047152,0.009407549,0.087879755],"study_design_scores_gemma":[0.0011531155,0.0003279419,0.8922209,0.00022516973,0.000037425347,0.000006058349,0.0007506915,0.000104539016,0.00043153134,0.08186551,0.022740928,0.00013614917],"about_ca_topic_score_codex":0.0005786944,"about_ca_topic_score_gemma":0.005192586,"teacher_disagreement_score":0.7015467,"about_ca_system_score_codex":0.00017633078,"about_ca_system_score_gemma":0.00031659188,"threshold_uncertainty_score":0.2897585},"labels":[],"label_agreement":null},{"id":"W2589189310","doi":"10.1515/jos-2017-0014","title":"Estimation when the Covariance Structure of the Variable of Interest is Positive Definite","year":2017,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"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":"Estimator; Mathematics; Covariance; Generalization; Statistics; Extension (predicate logic); Consistent estimator; Minimum-variance unbiased estimator; Estimation of covariance matrices; Calibration; Bias of an estimator; Applied mathematics; Computer science; Mathematical analysis","score_opus":0.13893040494127895,"score_gpt":0.37583280289370546,"score_spread":0.2369023979524265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589189310","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":[0.016786763,0.000022098713,0.97896117,0.00034850885,0.00051415374,0.000120899196,0.002852854,0.0000015581155,0.0003919848],"genre_scores_gemma":[0.46690622,0.000006340897,0.53290766,0.000059469046,0.000084533734,2.0464405e-7,9.109712e-7,0.000008021081,0.000026617545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986145,0.00016812333,0.00070712116,0.000071993505,0.000317791,0.00012048733],"domain_scores_gemma":[0.99431956,0.0023566124,0.0022047495,0.000367486,0.00071124465,0.00004034376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005241844,0.00011063388,0.00035601028,0.000027219105,0.00021445159,0.00004852126,0.0006079728,0.00007002305,0.00019036442],"category_scores_gemma":[0.011270029,0.000060594753,0.00006593678,0.000049325787,0.00032421795,0.000073536474,0.00010273309,0.0003064511,8.4632904e-7],"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":[0.00010736091,0.000068553185,0.00023866899,0.000093731236,0.00009069012,0.000003447546,0.00089405384,0.00009028399,0.0013919648,0.9773112,0.004577664,0.01513236],"study_design_scores_gemma":[0.00029165065,0.00019892873,0.008898214,0.00028485735,0.00019869563,0.000019525452,0.00006978283,0.0061718654,0.0035696106,0.98008066,0.00014457807,0.00007164019],"about_ca_topic_score_codex":0.00007898273,"about_ca_topic_score_gemma":0.0000452481,"teacher_disagreement_score":0.45011947,"about_ca_system_score_codex":0.00002835853,"about_ca_system_score_gemma":0.00020049312,"threshold_uncertainty_score":0.99705845},"labels":[],"label_agreement":null},{"id":"W2591159053","doi":"10.1515/jos-2017-0006","title":"Three Methods for Occupation Coding Based on Statistical Learning","year":2017,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":51,"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":"Social Sciences and Humanities Research Council of Canada","keywords":"Coding (social sciences); Computer science; Respondent; Statistical learning; German; Artificial intelligence; Machine learning; Data mining; Statistics; Mathematics; Geography","score_opus":0.35728536526680754,"score_gpt":0.5651666475921359,"score_spread":0.20788128232532832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591159053","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":[0.00026066467,0.0000053977856,0.99676955,0.00060897943,0.00111511,0.00013524278,0.00036793255,0.0000054044194,0.0007317331],"genre_scores_gemma":[0.10454293,0.0000060605453,0.89470845,0.00023265662,0.00037022363,0.0000018842442,0.000021231785,0.000011078139,0.00010544701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742734,0.00030253208,0.00089888886,0.00017937704,0.0010037246,0.00018811226],"domain_scores_gemma":[0.98932046,0.007918413,0.0016032831,0.00035131804,0.00069189334,0.00011463132],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01040329,0.00010481091,0.00034222947,0.00018565689,0.00068196753,0.0007745995,0.00076760934,0.000049952916,0.00017359667],"category_scores_gemma":[0.06395116,0.00008033809,0.000081656224,0.00006545061,0.00011166413,0.0002428289,0.00008340097,0.00023155897,0.000023678806],"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":[0.00052951474,0.0000975878,0.0007651415,0.000014502037,0.00002205814,0.00001952762,0.00006392911,0.003454657,0.000023446906,0.19653015,0.04512209,0.7533574],"study_design_scores_gemma":[0.001402793,0.0014546851,0.040389832,0.000057896435,0.000111047244,0.0000033936578,0.00022193548,0.5142961,0.00010839626,0.26150846,0.18023211,0.0002133708],"about_ca_topic_score_codex":0.00002211103,"about_ca_topic_score_gemma":0.00009711389,"teacher_disagreement_score":0.753144,"about_ca_system_score_codex":0.000056434557,"about_ca_system_score_gemma":0.00014970679,"threshold_uncertainty_score":0.9439336},"labels":[],"label_agreement":null},{"id":"W2741773386","doi":"10.1515/jos-2017-0046","title":"The Effects of the Frequency and Implementation Lag of Basket Updates on the Canadian CPI","year":2017,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Econometrics; Consistency (knowledge bases); Lag; Index (typography); Term (time); Price index; Computer science; Economics; Substitution (logic); Statistics; Mathematics","score_opus":0.039002407272449816,"score_gpt":0.2589289222966028,"score_spread":0.219926515024153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2741773386","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":[0.992436,0.00034512414,0.00023925077,0.0031851965,0.000825275,0.00016733473,0.00092772604,5.589e-7,0.0018735693],"genre_scores_gemma":[0.9992123,0.00027174118,0.00017924837,0.00016811442,0.00012056264,6.5592286e-7,0.0000014722407,0.0000057477814,0.00004011843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99923486,0.00002744243,0.0005037585,0.000054378932,0.000039382907,0.00014018602],"domain_scores_gemma":[0.9979773,0.00039392625,0.0013228474,0.00022099745,0.000030047877,0.000054855293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068332686,0.000066425535,0.0001921581,0.000049718823,0.0005099676,0.00008441363,0.00033205442,0.000032522697,0.000063581545],"category_scores_gemma":[0.00077589793,0.000039182392,0.000052834705,0.000022337734,0.00015107582,0.000078329926,0.000022598539,0.00012698596,0.000004429012],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051096653,0.000037230708,0.16596138,0.00005807516,0.00022876573,0.0000051070037,0.0012360711,0.00014727564,0.000039897295,0.8020419,0.020714419,0.009478782],"study_design_scores_gemma":[0.0004714176,0.00031369276,0.8835219,0.00003432489,0.000030367659,0.0000058857668,0.00012277745,0.00067974126,0.00050145574,0.10758495,0.0066432594,0.0000902109],"about_ca_topic_score_codex":0.04748668,"about_ca_topic_score_gemma":0.09746269,"teacher_disagreement_score":0.7175605,"about_ca_system_score_codex":0.00005982254,"about_ca_system_score_gemma":0.00008410029,"threshold_uncertainty_score":0.95885617},"labels":[],"label_agreement":null},{"id":"W2793476072","doi":"10.1515/jos-2018-0003","title":"Design-Based Estimation with Record-Linked Administrative Files and a Clerical Review Sample","year":2018,"lang":"en","type":"review","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","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":"Statistics Canada","funders":"","keywords":"Estimator; Sample (material); Statistics; Record linkage; Estimation; Linkage (software); Population; Econometrics; Regression analysis; Computer science; Missing data; Regression; Mathematics; Demography; Sociology; Engineering","score_opus":0.49991367302203166,"score_gpt":0.5189310698110305,"score_spread":0.019017396788998886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793476072","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.00300866e-7,0.41526237,0.5832051,0.000065911016,0.00019324027,0.0003844906,0.00085557933,0.0000044837802,0.000028738543],"genre_scores_gemma":[4.774076e-7,0.64266986,0.35684144,0.00018343331,0.00017863272,0.0000060262373,0.00007899581,0.000013335187,0.000027827735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99453074,0.0012088551,0.002267866,0.00032721565,0.0014689668,0.00019635582],"domain_scores_gemma":[0.9847565,0.009841784,0.003754211,0.00034964242,0.0011098093,0.0001880057],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005265758,0.00030947023,0.0019505094,0.0002499511,0.00013570677,0.00031171629,0.0006343974,0.0001164896,0.00034745247],"category_scores_gemma":[0.019001905,0.00018451698,0.00016202025,0.00057050964,0.00025647724,0.00017595166,0.00007878456,0.00034561753,0.000042235624],"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":[0.000071089926,0.00007531152,4.414461e-7,0.003467249,0.00007440508,0.00005985954,0.000037327878,0.0000123141135,2.2583588e-9,0.0005700364,0.10242252,0.89320946],"study_design_scores_gemma":[0.00019026901,0.0014591631,0.0000064507326,0.018003386,0.0010350212,0.00003778264,0.000035564815,0.0009291022,5.8703552e-8,0.0031867719,0.9748866,0.00022981751],"about_ca_topic_score_codex":0.000012442977,"about_ca_topic_score_gemma":0.000047514983,"teacher_disagreement_score":0.8929796,"about_ca_system_score_codex":0.00008696061,"about_ca_system_score_gemma":0.0013092386,"threshold_uncertainty_score":0.98926145},"labels":[],"label_agreement":null},{"id":"W2808060227","doi":"10.2478/jos-2018-0019","title":"Business Data Collection: Toward Electronic Data Interchange. Experiences in Portugal, Canada, Sweden, and the Netherlands with EDI","year":2018,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Electronic data interchange; Data collection; Work (physics); Computer science; Supply chain; Data exchange; Session (web analytics); Order (exchange); Business; Marketing; Finance; Engineering; World Wide Web; Sociology","score_opus":0.2051197202859155,"score_gpt":0.38195051189860085,"score_spread":0.17683079161268536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808060227","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":[0.36946335,0.0009514692,0.62338465,0.003953413,0.0015113186,0.00017296158,0.0002431333,0.0000055759,0.00031410984],"genre_scores_gemma":[0.9964216,0.00040226593,0.002428386,0.00017756119,0.00046455106,0.0000012670199,0.000026569767,0.0000068178415,0.000071007686],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975622,0.00017439749,0.0006817345,0.0002449759,0.0011111199,0.00022555617],"domain_scores_gemma":[0.9972283,0.00081631204,0.0005556094,0.0004892854,0.0008451243,0.00006532205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039017121,0.00009982312,0.00028093654,0.00014175613,0.00019139813,0.00021589408,0.0012484253,0.000034087632,0.00007426933],"category_scores_gemma":[0.002072198,0.000053099575,0.000008968378,0.00083323417,0.0003375825,0.00032180393,0.00022301936,0.0001984328,7.6526806e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009867102,0.00033138724,0.024757167,0.000035520196,0.00030268636,0.00035140428,0.04111525,0.0010770521,0.000016640011,0.006823007,0.6926157,0.22270708],"study_design_scores_gemma":[0.0072860965,0.0021402927,0.061586447,0.00028267258,0.00031118334,0.0010506284,0.117455676,0.6838547,0.00001724672,0.022712791,0.1025453,0.0007569442],"about_ca_topic_score_codex":0.04472249,"about_ca_topic_score_gemma":0.7722067,"teacher_disagreement_score":0.7274842,"about_ca_system_score_codex":0.000044195465,"about_ca_system_score_gemma":0.0015478083,"threshold_uncertainty_score":0.9616388},"labels":[],"label_agreement":null},{"id":"W2808290492","doi":"10.2478/jos-2018-0018","title":"Response Burden Management for Establishment Surveys at Four National Statistical Institutes","year":2018,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Census; Tracking (education); Business; Computer science; Statistics; Psychology; Medicine; Mathematics; Environmental health","score_opus":0.22612066471443887,"score_gpt":0.45716343223446565,"score_spread":0.23104276752002678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808290492","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":[0.066909134,0.00003877908,0.9253207,0.0013575074,0.002662545,0.0003237233,0.0010115164,0.0000168232,0.002359281],"genre_scores_gemma":[0.4319321,0.00011314027,0.5594615,0.00046597747,0.0034122132,0.000013853056,0.000044213237,0.000032070566,0.0045249863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9872394,0.010614753,0.0006285198,0.00017297246,0.0009669457,0.00037737825],"domain_scores_gemma":[0.9726077,0.025172772,0.00041359148,0.00008935107,0.0015124519,0.0002041797],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06556252,0.00013093532,0.00028847592,0.00022399577,0.00080149336,0.000074598414,0.00031493552,0.00012516188,0.00050406985],"category_scores_gemma":[0.048067983,0.00012537441,0.00007075508,0.00022841204,0.00069621217,0.0001423018,0.00006575378,0.00014906505,0.00003962636],"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":[0.113864556,0.0005585237,0.0029192837,0.00006287061,0.0006849664,0.0006656838,0.010511162,0.00032072683,0.0004197027,0.41363785,0.3803068,0.076047875],"study_design_scores_gemma":[0.0023244896,0.0015928932,0.17072894,0.000048072103,0.00014930287,0.000042065698,0.001468294,0.00025648734,0.00020481762,0.03536049,0.78745407,0.0003700872],"about_ca_topic_score_codex":0.00012573563,"about_ca_topic_score_gemma":0.0017354214,"teacher_disagreement_score":0.40714726,"about_ca_system_score_codex":0.0004649061,"about_ca_system_score_gemma":0.0009759455,"threshold_uncertainty_score":0.96220005},"labels":[],"label_agreement":null},{"id":"W2934046129","doi":"10.2478/jos-2019-0007","title":"An Evolutionary Schema for Using “it-is-what-it-is” Data in Official Statistics","year":2019,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","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":"Health Canada","funders":"","keywords":"Data science; Schema (genetic algorithms); Computer science; Set (abstract data type); Big data; Agency (philosophy); Process (computing); Data mining; Information retrieval; Sociology; Social science","score_opus":0.33696849945233176,"score_gpt":0.4966412882000322,"score_spread":0.15967278874770047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2934046129","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":[0.011483361,0.0001333379,0.9682086,0.0018387107,0.0026195382,0.0004382275,0.015124715,0.000007211541,0.00014628067],"genre_scores_gemma":[0.09019985,0.00027292917,0.8973669,0.008431269,0.0018686241,0.0000027176307,0.0010183573,0.000073521245,0.000765849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99397725,0.00031227103,0.0022535902,0.0005497779,0.0024373701,0.00046973588],"domain_scores_gemma":[0.99385136,0.0021596244,0.0014963086,0.0011158109,0.0011489337,0.00022796888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006157867,0.0002464796,0.0006951622,0.00047227647,0.00019193994,0.0007018609,0.0021894332,0.00013923927,0.0009098162],"category_scores_gemma":[0.0041536763,0.00022088287,0.000081779646,0.0005337969,0.00014705694,0.0020680255,0.0004614216,0.00035916799,0.00012403181],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092266,0.0009422553,0.0009819509,0.00009058269,0.000104797735,0.00011836451,0.0013598157,0.003834347,0.000114893046,0.042906225,0.88247424,0.06614987],"study_design_scores_gemma":[0.002490888,0.0011697888,0.0033423195,0.00024115384,0.00019792652,0.000043971308,0.010802235,0.43748865,0.000055314144,0.09223348,0.4513006,0.0006336812],"about_ca_topic_score_codex":0.000110316534,"about_ca_topic_score_gemma":0.0005898482,"teacher_disagreement_score":0.4336543,"about_ca_system_score_codex":0.00018756544,"about_ca_system_score_gemma":0.0009848382,"threshold_uncertainty_score":0.9961849},"labels":[],"label_agreement":null},{"id":"W3012530420","doi":"10.2478/jos-2020-0009","title":"A Procedure for Estimating the Variance of the Population Mean in Rejective Sampling","year":2020,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","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":"Statistics Canada","funders":"","keywords":"Mathematics; Estimator; Statistics; Sample size determination; Sampling (signal processing); Sample (material); Variance (accounting); Unit cube; Monte Carlo method; Population; Population variance; Simple random sample; Computer science; Combinatorics","score_opus":0.142898274363777,"score_gpt":0.386249078736028,"score_spread":0.24335080437225098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012530420","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":[0.05363287,0.000014033855,0.94528615,0.00054678,0.00015494446,0.00027429286,0.000065534194,0.000010975418,0.00001441601],"genre_scores_gemma":[0.5187643,9.729066e-7,0.48101985,0.000053391395,0.00014630979,0.0000025728762,0.0000014611463,0.0000093710505,0.0000017355184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886405,0.00009323836,0.00063865137,0.00006691705,0.00024198675,0.0000951447],"domain_scores_gemma":[0.9969205,0.0017025134,0.0009296646,0.00008013322,0.00034218596,0.000024960655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010109214,0.00007749071,0.00022606377,0.000032898948,0.00009876844,0.000021382713,0.00018731238,0.000044089047,0.0000027933932],"category_scores_gemma":[0.012707185,0.000047674657,0.00005970047,0.00020737191,0.000030193938,0.000052961637,0.000021886244,0.0002052521,1.18438614e-7],"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":[0.0024589235,0.0009544339,0.0457549,0.003837104,0.0004321382,0.000013320917,0.06727215,0.24956402,0.0024728498,0.506872,0.017439693,0.10292848],"study_design_scores_gemma":[0.000668518,0.00035878274,0.03533741,0.0006642583,0.00012857563,0.000020238487,0.0006562237,0.32452297,0.00084210804,0.63655865,0.00007070699,0.00017156523],"about_ca_topic_score_codex":0.000036895708,"about_ca_topic_score_gemma":0.00008261892,"teacher_disagreement_score":0.46513146,"about_ca_system_score_codex":0.000048044218,"about_ca_system_score_gemma":0.000111398105,"threshold_uncertainty_score":0.9956092},"labels":[],"label_agreement":null},{"id":"W3122391284","doi":"10.1515/jos-2016-0045","title":"From Quality to Information Quality in Official Statistics","year":2016,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Census and Population Estimation","field":"Mathematics","cited_by":15,"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":"U.S. Environmental Protection Agency; U.S. Department of Energy; U.S. Department of Defense","keywords":"Official statistics; Statistics; Quality (philosophy); Context (archaeology); Data quality; Economic statistics; Computer science; Data science; Mathematics; Business; Marketing; Geography","score_opus":0.09452006622091148,"score_gpt":0.41334364315541133,"score_spread":0.31882357693449986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122391284","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":[0.21718869,0.000004545902,0.77851814,0.0004487512,0.00063882454,0.00015775628,0.0029133332,0.000013462344,0.00011652165],"genre_scores_gemma":[0.7263685,0.000012349056,0.27258164,0.00019842296,0.0006872696,0.0000020292698,0.00008146947,0.000019755656,0.000048576618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99639785,0.00027490113,0.002197412,0.000107874606,0.00078331126,0.00023865153],"domain_scores_gemma":[0.9952318,0.0021651094,0.0014443395,0.00019007009,0.0008007546,0.00016790869],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015051888,0.00017311222,0.000499708,0.00023145664,0.00006936828,0.000057084988,0.00018463306,0.00011809677,0.0002713827],"category_scores_gemma":[0.008399964,0.00013338635,0.00006175647,0.00020772593,0.000041008785,0.0003887895,0.00003957674,0.00018580626,0.000063468935],"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":[0.0015779265,0.0005680677,0.018485114,0.00015909236,0.00008504785,0.000031124666,0.0050712167,0.0011755057,0.0005916759,0.6497559,0.05174748,0.27075186],"study_design_scores_gemma":[0.002912529,0.00038097543,0.43325397,0.00027283825,0.0000876894,0.000008845545,0.00040653432,0.0013488454,0.00028399608,0.5483573,0.012142008,0.0005444845],"about_ca_topic_score_codex":0.0005942361,"about_ca_topic_score_gemma":0.0018782928,"teacher_disagreement_score":0.50917983,"about_ca_system_score_codex":0.00029684446,"about_ca_system_score_gemma":0.000254226,"threshold_uncertainty_score":0.99995273},"labels":[],"label_agreement":null},{"id":"W3214883885","doi":"10.1016/j.jtha.2023.08.026","title":"Nonresponse in U.S. Government Household Surveys: Consistent Measures, Recent Trends, and New Insights","year":2001,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Health disparities and outcomes","field":"Social Sciences","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 Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Government (linguistics); Current Population Survey; Economics; Econometrics; Demographic economics; Geography; Political science; Public economics; Sociology; Demography; Population","score_opus":0.11466481610682609,"score_gpt":0.3415034171812778,"score_spread":0.2268386010744517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214883885","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":[0.86372524,0.015078012,0.04548456,0.052386858,0.006990858,0.00070912763,0.0006185619,0.00005610524,0.014950677],"genre_scores_gemma":[0.9626077,0.02953059,0.0034814281,0.0016719558,0.0009171167,0.000001072556,0.0000030829651,0.000022232653,0.0017648324],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722236,0.00078363874,0.0006345521,0.00010266597,0.00092690263,0.00032986066],"domain_scores_gemma":[0.998319,0.00074470835,0.0003265232,0.000069990914,0.00012479964,0.00041500758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002413194,0.00010751475,0.00031958745,0.00010100673,0.00018960432,0.000084893,0.00013117309,0.00008532823,0.000119789365],"category_scores_gemma":[0.0016949135,0.00009517416,0.00003947196,0.00026568715,0.00010385882,0.000104155704,0.000022825028,0.0002263812,0.0000015871744],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011212775,0.0004969223,0.12796342,0.000037235994,0.00007106667,0.0010895818,0.010854077,0.00019453731,0.000007690136,0.028628584,0.07212985,0.75740576],"study_design_scores_gemma":[0.0007420044,0.00012253504,0.4397795,0.000054244734,0.000019874704,0.000014582524,0.0014084551,0.000013672819,0.000002783748,0.00076170824,0.5569695,0.00011113984],"about_ca_topic_score_codex":0.007810646,"about_ca_topic_score_gemma":0.12180984,"teacher_disagreement_score":0.7572946,"about_ca_system_score_codex":0.00054321653,"about_ca_system_score_gemma":0.0009698119,"threshold_uncertainty_score":0.9987964},"labels":[],"label_agreement":null},{"id":"W37429839","doi":"10.1038/s41539-023-00170-1","title":"Accounting for Biases in Election Surveys: The Case of the 1998 Quebec Election","year":2002,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Electoral Systems and Political Participation","field":"Social Sciences","cited_by":22,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Deafness and Other Communication Disorders; Agence Nationale de la Recherche","keywords":"Political science; Accounting; Geography; Econometrics; Economics","score_opus":0.09360078621369777,"score_gpt":0.37272482672264773,"score_spread":0.27912404050894996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37429839","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":[0.98279595,0.00007952327,0.014882656,0.000945863,0.0008186183,0.00025595186,0.00003297697,0.000004107742,0.00018432795],"genre_scores_gemma":[0.99897873,0.000010163355,0.00011156904,0.00003650289,0.00068079995,0.0000026295718,6.239037e-7,0.000005190764,0.00017377363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99847907,0.00058985513,0.00046197808,0.00004808435,0.00021413011,0.00020687202],"domain_scores_gemma":[0.997943,0.0012347852,0.00044870612,0.00004845789,0.00028804826,0.000037039437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020231283,0.000052799154,0.00013553868,0.000049377253,0.00035393785,0.00005016695,0.00009394349,0.00005539258,0.000019164096],"category_scores_gemma":[0.003292391,0.000032799377,0.00005924371,0.00034167318,0.000099225465,0.000105746716,0.0000058019687,0.00014358955,0.0000012218989],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042019074,0.0019095618,0.1128667,0.00037779094,0.00028172144,0.0001936029,0.04258933,0.0086014345,0.0051784916,0.3835275,0.06820891,0.37584478],"study_design_scores_gemma":[0.006062979,0.0041917823,0.6466011,0.0013956566,0.0011307658,0.0009079049,0.018927628,0.12904377,0.010107013,0.08692892,0.09294436,0.0017581399],"about_ca_topic_score_codex":0.117593795,"about_ca_topic_score_gemma":0.62961745,"teacher_disagreement_score":0.5337344,"about_ca_system_score_codex":0.00018948485,"about_ca_system_score_gemma":0.00015081595,"threshold_uncertainty_score":0.88828224},"labels":[],"label_agreement":null},{"id":"W4200097000","doi":"10.2478/jos-2021-0043","title":"Nowcasting Register Labour Force Participation Rates in Municipal Districts Using Survey Data","year":2021,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":2,"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":"Nowcasting; Bivariate analysis; Quarter (Canadian coin); Underemployment; Register (sociolinguistics); Unit (ring theory); Econometrics; Data source; Demographic economics; Economics; Statistics; Computer science; Geography; Database; Mathematics; Economic growth; Unemployment","score_opus":0.2912054384215383,"score_gpt":0.35655456230968796,"score_spread":0.06534912388814967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200097000","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":[0.71551067,0.0007407669,0.2767361,0.00006696219,0.0004942622,0.000039741135,0.006219764,0.0000026964024,0.00018903824],"genre_scores_gemma":[0.98894954,0.00017720352,0.009749153,0.00007023592,0.0002527271,2.7487718e-7,0.0006681913,0.000013856058,0.00011880824],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982631,0.00009730831,0.001143051,0.00019780014,0.00008536437,0.00021333277],"domain_scores_gemma":[0.9980278,0.0003829135,0.0009866421,0.00031445897,0.00021206042,0.00007613539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012985641,0.000103220875,0.00044860036,0.00016284572,0.00007355706,0.00012015952,0.0003038854,0.000059898906,0.00018439344],"category_scores_gemma":[0.0038705454,0.00011436846,0.000042084037,0.00052043545,0.000028595685,0.00030286264,0.0001330649,0.00019314757,0.000016210797],"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":[0.0001654626,0.00037367243,0.96280974,0.00007119553,0.00019513433,0.00044580307,0.00073652103,0.016324673,0.000077367884,0.013464157,0.0013133938,0.0040228865],"study_design_scores_gemma":[0.0008659552,0.000087052555,0.63394135,0.00007334641,0.000072677256,0.000031447144,0.00020972642,0.35547993,0.000060999544,0.005533721,0.0033340282,0.00030977902],"about_ca_topic_score_codex":0.0037744842,"about_ca_topic_score_gemma":0.011147325,"teacher_disagreement_score":0.33915526,"about_ca_system_score_codex":0.00008210662,"about_ca_system_score_gemma":0.0001020526,"threshold_uncertainty_score":0.6220469},"labels":[],"label_agreement":null},{"id":"W4200328216","doi":"10.2478/jos-2021-0045","title":"Estimation of Domain Means from Business Surveys in the Presence of Stratum Jumpers and Nonresponse","year":2021,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"Institute for Work & Health","funders":"","keywords":"Estimator; Statistics; Smoothing; Context (archaeology); Estimation; Econometrics; Variance (accounting); Stratum; Computer science; Non-response bias; Mathematics; Geography; Economics; Engineering","score_opus":0.11798255746632565,"score_gpt":0.40832944307167995,"score_spread":0.2903468856053543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200328216","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":[0.7793068,0.00019782227,0.2195252,0.00033950715,0.00030631915,0.000051832478,0.00018413388,0.0000010414899,0.0000872904],"genre_scores_gemma":[0.9533547,0.0001895239,0.046323206,0.000022316797,0.00007798421,3.797242e-7,0.000006253464,0.000003910066,0.000021684597],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9692893,0.029457862,0.0005516458,0.00008691811,0.00047930324,0.00013494055],"domain_scores_gemma":[0.9691937,0.029717458,0.00044486957,0.000089494235,0.0005129457,0.000041510753],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036428332,0.000065713175,0.0002740478,0.00008712006,0.000093155555,0.000020824245,0.00018572221,0.00009165886,0.00005077463],"category_scores_gemma":[0.04511831,0.000052906304,0.000032175434,0.00046757268,0.0004248729,0.00009901317,0.000018762856,0.00018480896,3.0470295e-7],"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":[0.038445655,0.0033920084,0.19672985,0.00032697193,0.000663633,0.0032675269,0.3979573,0.025942633,0.030398061,0.08516095,0.0053019538,0.21241347],"study_design_scores_gemma":[0.0004128906,0.00009065179,0.97811174,0.000061318766,0.000036400514,0.000010039375,0.009859031,0.00025118643,0.00046113814,0.01047311,0.00016784878,0.000064644315],"about_ca_topic_score_codex":0.0017341842,"about_ca_topic_score_gemma":0.009391839,"teacher_disagreement_score":0.7813819,"about_ca_system_score_codex":0.000021710037,"about_ca_system_score_gemma":0.0009357769,"threshold_uncertainty_score":0.9921998},"labels":[],"label_agreement":null},{"id":"W4220870615","doi":"10.2478/jos-2022-0012","title":"Measuring Inflation under Pandemic Conditions","year":2022,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","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 British Columbia","funders":"","keywords":"Inflation (cosmology); Pandemic; Coronavirus disease 2019 (COVID-19); Economics; Goods and services; Econometrics; Public economics; Economy; Medicine","score_opus":0.06401511578221898,"score_gpt":0.27510776819238314,"score_spread":0.21109265241016417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220870615","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":[0.93170506,0.00010093071,0.06264923,0.00026773565,0.001907806,0.000120799996,0.00005986549,0.000036606827,0.0031519781],"genre_scores_gemma":[0.998529,0.0000053696654,0.0003857828,0.00033200398,0.00065319834,0.0000016727728,0.000021644728,0.0000128413985,0.000058487116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99903435,0.00002218095,0.00037019872,0.000060796083,0.00039125586,0.00012125239],"domain_scores_gemma":[0.9991258,0.000111860696,0.00046982768,0.000056257457,0.00022510038,0.000011180396],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005157367,0.00007279242,0.00013598385,0.00023698712,0.0003765969,0.00009456234,0.00012699772,0.000017362083,0.0011295975],"category_scores_gemma":[0.00013764542,0.0000763316,0.000050099417,0.00023841318,0.000020913416,0.00028838226,0.000084363244,0.00026760524,0.000013108452],"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":[0.0006666758,0.00062250777,0.6384852,0.00018005348,0.0002492009,0.00036253515,0.00047620313,0.058036443,0.005492375,0.11948242,0.049696423,0.12624998],"study_design_scores_gemma":[0.0018389606,0.00008134945,0.8192903,0.000051718736,0.00068936,0.00014641833,0.0014645322,0.007010758,0.000019198194,0.036678214,0.1322248,0.0005043817],"about_ca_topic_score_codex":0.00009215499,"about_ca_topic_score_gemma":0.00010116305,"teacher_disagreement_score":0.18080513,"about_ca_system_score_codex":0.000071784976,"about_ca_system_score_gemma":0.00007463054,"threshold_uncertainty_score":0.9997835},"labels":[],"label_agreement":null},{"id":"W4231932021","doi":"10.2478/jos-2019-0038","title":"Editorial Collaborators","year":2019,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Academic Writing and Publishing","field":"Arts and Humanities","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; Brock University","funders":"","keywords":"Probability and statistics; Statistics; Mathematics","score_opus":0.013124035190031615,"score_gpt":0.2353507570498915,"score_spread":0.2222267218598599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231932021","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15057653,0.00033484484,0.0033161992,0.00083158794,0.7622336,0.00019471902,0.0009246563,0.00005156139,0.0815363],"genre_scores_gemma":[0.4321267,0.000027322372,0.0014854562,0.00025695,0.56319493,2.938609e-7,0.000010221319,0.000025738394,0.0028723932],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897134,0.000036738697,0.0003805642,0.000052162566,0.00042450338,0.00013466676],"domain_scores_gemma":[0.99853903,0.00022360092,0.00037434066,0.000048710343,0.0007468091,0.000067531655],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045396475,0.00007150093,0.00018257987,0.00007091635,0.00010110055,0.00024644015,0.00016267181,0.00006060504,0.0010556277],"category_scores_gemma":[0.00045376978,0.0000594777,0.00003736939,0.000037094345,0.00005274348,0.00025321927,0.000015818228,0.00037318346,0.00007261721],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041131396,0.000019189676,0.00021977395,0.0000106088755,0.000014984208,0.000004421981,0.00281956,0.000029287554,0.000014406719,0.15404251,0.84181935,0.0009647999],"study_design_scores_gemma":[0.00029960516,0.00017007606,0.000035333196,0.00002762973,0.000020659265,0.0000035651133,0.0021643494,0.000041283947,0.000007990376,0.0026105596,0.9945402,0.000078755045],"about_ca_topic_score_codex":0.00003545046,"about_ca_topic_score_gemma":0.00004365312,"teacher_disagreement_score":0.28155017,"about_ca_system_score_codex":0.000037427868,"about_ca_system_score_gemma":0.00024156272,"threshold_uncertainty_score":0.99985754},"labels":[],"label_agreement":null},{"id":"W4244512878","doi":"10.2478/jos-2013-0014","title":"Discussion","year":2013,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Pharmacy and Medical Practices","field":"Pharmacology, Toxicology and Pharmaceutics","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":"Statistics Canada","funders":"","keywords":"Probability and statistics; Statistics; Mathematics","score_opus":0.14532132913703902,"score_gpt":0.4908799424175553,"score_spread":0.3455586132805163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244512878","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":[0.59346783,0.0028544178,0.27068838,0.056303184,0.034764122,0.0014546318,0.000514552,0.00014526852,0.039807636],"genre_scores_gemma":[0.9871792,0.00048362493,0.005559562,0.003947575,0.0015994521,0.0000032829196,0.000006636801,0.000016550539,0.0012041257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851894,0.00030367903,0.0005572977,0.00007871553,0.0002897866,0.00025155672],"domain_scores_gemma":[0.9980309,0.000716831,0.0005159646,0.000060270668,0.0002873833,0.00038865724],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007130295,0.00011400891,0.00023109441,0.00007740179,0.00013923293,0.000028003016,0.00022469963,0.00013328997,0.007855805],"category_scores_gemma":[0.0010798427,0.000068818605,0.00006694892,0.00010049851,0.00014047163,0.0002991298,0.000037424725,0.0010015835,0.00039475976],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039411118,0.0007073432,0.0015633351,0.000042669817,0.00018326513,0.00025121035,0.0005348788,0.00021658992,0.0092568975,0.00392376,0.5703224,0.41260356],"study_design_scores_gemma":[0.0014645684,0.0003541409,0.0033153864,0.000020682168,0.00022240735,0.00014514184,0.0002154668,0.0024118759,0.0033920887,0.0085299425,0.9797678,0.00016050367],"about_ca_topic_score_codex":0.0000140033135,"about_ca_topic_score_gemma":0.000004436527,"teacher_disagreement_score":0.41244304,"about_ca_system_score_codex":0.000040686733,"about_ca_system_score_gemma":0.00016357118,"threshold_uncertainty_score":0.9930512},"labels":[],"label_agreement":null},{"id":"W4282823413","doi":"10.2478/jos-2022-0020","title":"Assessing Residual Seasonality in the U.S. National Income and Product Accounts Aggregates","year":2022,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Monetary Policy and Economic Impact","field":"Economics, Econometrics and Finance","cited_by":4,"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":"Seasonality; Residual; Econometrics; Gross domestic product; National Income and Product Accounts; Economics; Quarter (Canadian coin); Seasonal adjustment; National accounts; CLARITY; Product (mathematics); Statistics; Geography; Mathematics; Macroeconomics; Variable (mathematics)","score_opus":0.122759077335815,"score_gpt":0.3063373154680497,"score_spread":0.18357823813223473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282823413","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":[0.99475384,0.0010655923,0.00054628105,0.0013687887,0.00030805895,0.00007553198,0.00090292154,0.0000016718403,0.0009773023],"genre_scores_gemma":[0.99768627,0.00006401063,0.0013508517,0.00043126981,0.00041459367,0.0000018295926,0.000009095263,0.000007184447,0.00003487921],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99889845,0.00007403991,0.0006436636,0.000115933355,0.00011158372,0.00015635097],"domain_scores_gemma":[0.99894553,0.0002435734,0.0006841721,0.000060976858,0.000029738549,0.0000360175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026723922,0.00007856501,0.00024002911,0.00012855248,0.00020296812,0.0001444032,0.00020000589,0.000019109826,0.00020772671],"category_scores_gemma":[0.00056765793,0.00007416817,0.000031939377,0.00012449917,0.000049477163,0.00030834327,0.00005189616,0.00032201866,0.000008084966],"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":[0.00026134466,0.0005070878,0.77472544,0.00007254127,0.00016052887,0.00010874835,0.004005755,0.023677211,0.000008109565,0.17194757,0.017267713,0.0072579756],"study_design_scores_gemma":[0.0004934232,0.00011399936,0.8911997,0.000008097757,0.0000074035547,0.00014999628,0.00028589205,0.0043744487,0.0000023834407,0.089679055,0.013553371,0.00013223934],"about_ca_topic_score_codex":0.00018232252,"about_ca_topic_score_gemma":0.00004252703,"teacher_disagreement_score":0.11647427,"about_ca_system_score_codex":0.00016427418,"about_ca_system_score_gemma":0.000080152364,"threshold_uncertainty_score":0.30244902},"labels":[],"label_agreement":null},{"id":"W4380082198","doi":"10.2478/jos-2023-0012","title":"From Quarterly to Monthly Turnover Figures Using Nowcasting Methods","year":2023,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","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":"","keywords":"Nowcasting; Benchmarking; Econometrics; Computer science; Term (time); Quarter (Canadian coin); Population; Value (mathematics); Statistics; Actuarial science; Economics; Geography; Mathematics; Meteorology","score_opus":0.2574621406827492,"score_gpt":0.5106699989748312,"score_spread":0.25320785829208203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380082198","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":[0.15105328,0.000018652008,0.8472723,0.00030680458,0.00052887585,0.000079410034,0.00043257044,0.00003291048,0.0002752552],"genre_scores_gemma":[0.13116363,0.000001388462,0.86775786,0.00008961382,0.0008226678,0.0000012302835,0.0000054477964,0.000017499526,0.00014065206],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974308,0.00016342018,0.0010597375,0.00019215791,0.0009271395,0.00022676573],"domain_scores_gemma":[0.99514556,0.0029625925,0.000735084,0.00024338691,0.00074164575,0.00017172654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026540344,0.00011750279,0.0003345998,0.00035345476,0.00018025524,0.00025536655,0.0005811818,0.00006401936,0.00014763299],"category_scores_gemma":[0.0053443206,0.00009156638,0.000099277226,0.0011047188,0.00004247057,0.000120082565,0.000070575355,0.00021586774,0.000090768575],"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":[0.00010863328,0.000088256784,0.00047478566,0.0000055365804,0.000048451213,0.00013310582,0.0034902962,0.029887017,0.010323068,0.004400698,0.2718558,0.6791844],"study_design_scores_gemma":[0.00040167576,0.0009358869,0.014588705,0.00017569227,0.00011055243,0.00004422611,0.0026478942,0.36153373,0.0019130073,0.5142866,0.10288445,0.00047760812],"about_ca_topic_score_codex":0.00022893226,"about_ca_topic_score_gemma":0.00006611284,"teacher_disagreement_score":0.67870677,"about_ca_system_score_codex":0.000055582834,"about_ca_system_score_gemma":0.00013465839,"threshold_uncertainty_score":0.6398037},"labels":[],"label_agreement":null},{"id":"W4389522795","doi":"10.2478/jos-2023-0026","title":"Application of Sampling Variance Smoothing Methods for Small Area Proportion Estimation","year":2023,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Smoothing; Variance (accounting); Sampling (signal processing); Statistics; Estimation; Small area estimation; Sampling design; Variance function; One-way analysis of variance; Unbiased Estimation; Computer science; Mathematics; Econometrics; Analysis of variance; Estimator","score_opus":0.29063111415678117,"score_gpt":0.49706859571595846,"score_spread":0.2064374815591773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389522795","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":[0.01593707,0.000033706125,0.98308975,0.00014884397,0.0004799048,0.00019612972,0.000061107,0.000017660625,0.00003585908],"genre_scores_gemma":[0.2614838,0.000025777077,0.7383159,0.00001746204,0.000092581104,0.000005365549,0.00002522518,0.0000096854055,0.000024199153],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748844,0.00012961974,0.0014179915,0.0001578579,0.0006645116,0.0001415946],"domain_scores_gemma":[0.9935304,0.0025680403,0.0019474638,0.00015708084,0.0017401,0.00005692634],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007672518,0.00008583474,0.00030099525,0.0004031456,0.00013047358,0.0000842592,0.00024844173,0.000070615315,0.000006899271],"category_scores_gemma":[0.008987272,0.00007047403,0.000100876445,0.0008000016,0.00004032459,0.00015597393,0.000019971296,0.000111324975,0.000004323671],"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":[0.00009895057,0.00003946453,0.00026558552,0.000028440201,0.000016523716,7.5852375e-7,0.00041503046,0.22327873,0.002449421,0.015465,0.0002802753,0.7576618],"study_design_scores_gemma":[0.00019275703,0.00012247376,0.0027464353,0.000029040593,0.000043925123,0.0000044101917,0.00027838664,0.7633686,0.00024731338,0.23203784,0.00087090646,0.000057923062],"about_ca_topic_score_codex":0.000020585407,"about_ca_topic_score_gemma":0.000021781347,"teacher_disagreement_score":0.7576039,"about_ca_system_score_codex":0.000030443423,"about_ca_system_score_gemma":0.00013316923,"threshold_uncertainty_score":0.99936044},"labels":[],"label_agreement":null},{"id":"W4402995867","doi":"10.1177/0282423x241266523","title":"Synthetic Census Microdata Generation: A Comparative Study of Synthesis Methods Examining the Trade-Off Between Disclosure Risk and Utility","year":2024,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","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":"","keywords":"Microdata (statistics); Census; Econometrics; Computer science; Actuarial science; Geography; Business; Demography; Mathematics; Sociology; Population","score_opus":0.15426719079168927,"score_gpt":0.38564611672681126,"score_spread":0.231378925935122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402995867","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":[0.19832851,0.0012357938,0.7977783,0.0010936492,0.000391287,0.0001702719,0.0009497716,0.00003776396,0.000014664681],"genre_scores_gemma":[0.6235114,0.00008103446,0.3762773,0.0000036502001,0.00011475836,0.0000017727591,0.0000026981052,0.0000064784945,9.4132525e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971339,0.0010943862,0.00080691586,0.000319582,0.00045304175,0.00019217389],"domain_scores_gemma":[0.99212897,0.005327905,0.00055179815,0.0018019282,0.00012780822,0.000061620885],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.0029514492,0.00017785815,0.00049993536,0.00014393961,0.00021538684,0.0002573779,0.005558958,0.00007575597,0.000005314926],"category_scores_gemma":[0.014904196,0.000119630145,0.000043210406,0.0004363581,0.00024581797,0.00029211308,0.0056728814,0.00058214687,5.779673e-7],"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":[0.00003694317,0.0003574315,0.0045202994,0.00008397168,0.00066010124,0.00013586576,0.0055003506,0.000080783226,0.0004357236,0.00185716,0.03680995,0.9495214],"study_design_scores_gemma":[0.00081438024,0.0025261184,0.12189873,0.0004710781,0.0017703132,0.00027957902,0.0053008073,0.7778172,0.0074806795,0.0746843,0.006189983,0.0007668343],"about_ca_topic_score_codex":0.00003448521,"about_ca_topic_score_gemma":0.000045321547,"teacher_disagreement_score":0.9487546,"about_ca_system_score_codex":0.00005769693,"about_ca_system_score_gemma":0.00016847167,"threshold_uncertainty_score":0.9998214},"labels":[],"label_agreement":null},{"id":"W4410049805","doi":"10.1177/0282423x251329407","title":"Linking Trade Data from Different National Statistical Offices Through a Private Set Intersection","year":2025,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","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":"Statistics Canada","funders":"","keywords":"Intersection (aeronautics); Set (abstract data type); Data set; Statistics; Probability and statistics; Geography; Computer science; Business; Mathematics; Cartography","score_opus":0.31712642016439646,"score_gpt":0.4808368688614867,"score_spread":0.16371044869709023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410049805","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":[0.0117763905,0.00006378878,0.9744309,0.001290301,0.0021935874,0.000100878606,0.009290415,0.00001065127,0.0008430612],"genre_scores_gemma":[0.8999696,0.00010774628,0.095826976,0.001536779,0.0009640514,0.00000138649,0.0013803384,0.000014306351,0.00019885153],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99554324,0.00037311603,0.0014832403,0.00033559612,0.002074997,0.00018982563],"domain_scores_gemma":[0.9944495,0.003903771,0.00085994985,0.00041593224,0.00029560953,0.0000752412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024614716,0.00015273133,0.00042041633,0.0002317943,0.00016994798,0.00050586567,0.0014730683,0.00007009008,0.00037331006],"category_scores_gemma":[0.0061255195,0.00011474424,0.000056842804,0.0003102681,0.00012644373,0.0005816017,0.000530984,0.00034790835,0.000033956676],"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":[0.0004938663,0.00046483078,0.0010189252,0.000031926356,0.00028909213,0.00007270389,0.0008045369,0.0005606453,0.00007999237,0.42347977,0.49572772,0.076976],"study_design_scores_gemma":[0.0008781415,0.00019298187,0.03239788,0.00014467422,0.00017045697,0.0000067412684,0.001230931,0.02037464,0.00006688205,0.6102806,0.3340668,0.00018929092],"about_ca_topic_score_codex":0.00007138902,"about_ca_topic_score_gemma":0.0006302715,"teacher_disagreement_score":0.8881932,"about_ca_system_score_codex":0.00013817886,"about_ca_system_score_gemma":0.00024821918,"threshold_uncertainty_score":0.73332614},"labels":[],"label_agreement":null},{"id":"W4412362054","doi":"10.1177/0282423x251341944","title":"Decomposing Residential Resale House Prices into Structure and Land Components","year":2025,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Housing Market and Economics","field":"Economics, Econometrics and Finance","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":"Statistics Canada; University of British Columbia","funders":"","keywords":"Geography; Agricultural economics; Environmental science; Econometrics; Statistics; Architectural engineering; Economics; Mathematics; Engineering","score_opus":0.01659761010724232,"score_gpt":0.2430735915536377,"score_spread":0.22647598144639539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412362054","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":[0.9382918,0.0007408539,0.057572857,0.00023922317,0.0014173024,0.00006508933,0.00012414821,0.00001152657,0.0015371905],"genre_scores_gemma":[0.9744876,0.0005214072,0.024560593,0.00009024765,0.00026624714,1.8589846e-7,0.000005196804,0.000019155397,0.000049342492],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890435,0.000016147143,0.0007513219,0.00013495582,0.000037908016,0.00015529666],"domain_scores_gemma":[0.9990163,0.00013366001,0.00062359904,0.0000951903,0.000063113745,0.000068176014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034196116,0.000107675885,0.0003853585,0.0002713369,0.00015266456,0.00017912888,0.00015374001,0.00008217052,0.000042772393],"category_scores_gemma":[0.0001911127,0.00012009994,0.000043408832,0.00010105583,0.00006400461,0.00015240988,0.000059663278,0.00019323397,0.000007162445],"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":[0.0013834999,0.0003473463,0.74529713,0.00048302193,0.0006616089,0.00017666722,0.0025986263,0.00297999,0.0006344604,0.1819378,0.02468961,0.03881021],"study_design_scores_gemma":[0.0039290697,0.000379325,0.44321877,0.00025992733,0.00014679326,0.00007959555,0.00016966814,0.0140756685,0.00039454777,0.45244336,0.08415415,0.00074910553],"about_ca_topic_score_codex":0.00022474687,"about_ca_topic_score_gemma":0.00035756535,"teacher_disagreement_score":0.30207837,"about_ca_system_score_codex":0.0000944068,"about_ca_system_score_gemma":0.000055603563,"threshold_uncertainty_score":0.48975334},"labels":[],"label_agreement":null},{"id":"W4414187965","doi":"10.1177/0282423x251354908","title":"Why are Measures of Aggregate Hours Worked by the Unincorporated Self-Employed So Volatile?","year":2025,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Digital Economy and Work Transformation","field":"Social Sciences","cited_by":0,"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":"Current Population Survey; Quarter (Canadian coin); Sample (material); Volatility (finance); Imputation (statistics); Population; Panel data","score_opus":0.0203096038983748,"score_gpt":0.2680159344286548,"score_spread":0.24770633053028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414187965","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":[0.34940374,0.002102468,0.5907391,0.013662069,0.0036050847,0.0010054834,0.00089251326,0.000119580414,0.038469996],"genre_scores_gemma":[0.99751824,0.00025371095,0.0014854264,0.00039481893,0.00012791716,0.0000010741234,0.00000822378,0.00000780977,0.00020276099],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985636,0.00019029585,0.0006124574,0.00006434889,0.00039077623,0.0001785155],"domain_scores_gemma":[0.9980286,0.00035396343,0.00087492017,0.00007574252,0.0005925732,0.000074240044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000844493,0.000098731005,0.00025974202,0.000095718344,0.00035865925,0.00016449024,0.00030083978,0.00008388464,0.000027950302],"category_scores_gemma":[0.0003960324,0.000075647884,0.00007721059,0.00047236145,0.00027887258,0.0002810244,0.000012004988,0.00020202606,0.000002395403],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008339428,0.00075012574,0.019953284,0.000089398614,0.0007542457,0.000030292795,0.013208132,0.0018576478,0.00006073152,0.13679378,0.55439514,0.2712733],"study_design_scores_gemma":[0.002306676,0.000496723,0.015988328,0.0009256654,0.0005836279,0.0000063913617,0.010732395,0.00093556946,0.0011440591,0.069320485,0.89701444,0.00054564356],"about_ca_topic_score_codex":0.00038063686,"about_ca_topic_score_gemma":0.0025453512,"teacher_disagreement_score":0.6481145,"about_ca_system_score_codex":0.00009704846,"about_ca_system_score_gemma":0.00067882455,"threshold_uncertainty_score":0.30848312},"labels":[],"label_agreement":null},{"id":"W58258328","doi":"","title":"Research and Development in Official Statistics and Scientific Co-operation with Universities: A Follow-Up Study","year":2009,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Innovation Policy and R&D","field":"Economics, Econometrics and Finance","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":"Rogers Communications (Canada)","funders":"","keywords":"Microdata (statistics); Agency (philosophy); Funding Agency; Work (physics); Official statistics; Statistical survey; Statistical analysis; European union; Statistics; Political science; Business; Census; Public relations; Mathematics; Engineering; Sociology; Population; Demography; Social science","score_opus":0.0851294079096981,"score_gpt":0.3278706506238815,"score_spread":0.2427412427141834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W58258328","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":[0.9102761,0.00010753451,0.08823063,0.00014131988,0.00023049544,0.00020031964,0.00030981353,0.0000032456344,0.0005005165],"genre_scores_gemma":[0.98897254,0.000022173828,0.010377188,0.000042594962,0.000090956004,5.4652986e-7,0.000017296563,0.000007517116,0.0004691759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987776,0.000038157534,0.0006498789,0.0001619289,0.00016410043,0.00020829886],"domain_scores_gemma":[0.9991309,0.00011627242,0.00031398123,0.00006737794,0.00030412513,0.000067313944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015209874,0.00009253548,0.00026612775,0.00071354304,0.00034668928,0.00020757162,0.00008934332,0.000048670914,0.00004337787],"category_scores_gemma":[0.00009032732,0.00009209633,0.000006616403,0.00029973686,0.0001519654,0.00017008604,0.000018921472,0.00026007285,0.000009496154],"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":[0.00090343977,0.00097359595,0.022418791,0.00004018949,0.00008036776,0.00019813913,0.023174247,0.0005797878,0.000020388783,0.9374121,0.005860163,0.008338821],"study_design_scores_gemma":[0.017289061,0.0130195115,0.7683357,0.00018727008,0.000047360878,0.00012283346,0.041467015,0.0066632675,0.00021227822,0.075910196,0.07544423,0.0013012937],"about_ca_topic_score_codex":0.000080049744,"about_ca_topic_score_gemma":0.0007033637,"teacher_disagreement_score":0.8615019,"about_ca_system_score_codex":0.00018426376,"about_ca_system_score_gemma":0.00042128874,"threshold_uncertainty_score":0.37555793},"labels":[],"label_agreement":null}]}