{"meta":{"query_hash":"6766ff4d07c1","filters":{"venue":"Journal of Statistics Education"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"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/6766ff4d07c1","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Statistics+Education"},"results":[{"id":"W108116539","doi":"10.1080/10691898.2004.11910734","title":"The Counter-intuitive Non-informative Prior for the Bernoulli Family","year":2004,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prior probability; Bayesian probability; Bernoulli's principle; Heuristic; Computer science; Simple (philosophy); Artificial intelligence; Mathematics; Machine learning; Econometrics; Epistemology","score_opus":0.015732068671923036,"score_gpt":0.2933123331480379,"score_spread":0.27758026447611484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W108116539","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":[0.0018711055,0.0002330518,0.9931234,0.002966285,0.001413759,0.00016748287,0.000019088468,0.0000050932917,0.0002007508],"genre_scores_gemma":[0.76063806,0.00039460295,0.23770805,0.0008096168,0.00027965472,0.000021134962,0.0000024568449,0.000006462266,0.00013993768],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916047,0.000019471343,0.00035884688,0.00006724214,0.00025354288,0.00014041943],"domain_scores_gemma":[0.99766773,0.0006197149,0.000449022,0.00017333488,0.0010350283,0.000055151053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058749825,0.00007901337,0.00009190056,0.00003852803,0.0003191978,0.0002945026,0.0005851199,0.00002597061,8.2143106e-7],"category_scores_gemma":[0.00019907232,0.00004345137,0.00004308646,0.00010530334,0.00006639852,0.00033594132,0.00002889821,0.0001757695,0.000007841096],"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":[0.00003443774,0.00010993628,0.000015450792,0.000019250192,0.00006394805,9.630368e-7,0.014244425,0.0016603589,0.000084667896,0.55784297,0.014797741,0.41112584],"study_design_scores_gemma":[0.0014093404,0.0012937658,0.011868138,0.00036801293,0.00012686994,0.00016408922,0.009624278,0.13265692,0.0010414829,0.81463605,0.026420869,0.00039017806],"about_ca_topic_score_codex":0.000025481904,"about_ca_topic_score_gemma":0.000007667182,"teacher_disagreement_score":0.75876695,"about_ca_system_score_codex":0.00012980199,"about_ca_system_score_gemma":0.001307044,"threshold_uncertainty_score":0.28398952},"labels":[],"label_agreement":null},{"id":"W2107733460","doi":"10.1080/10691898.2007.11889458","title":"A Bubble Mixture Experiment Project for Use in an Advanced Design of Experiments Class","year":2007,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Camosun College; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Procter and Gamble","keywords":"Class (philosophy); Design of experiments; Computer science; Focus (optics); Soap bubble; Ideal (ethics); Mathematics education; Mathematics; Statistics; Artificial intelligence","score_opus":0.27217178740500675,"score_gpt":0.5405196164625709,"score_spread":0.2683478290575641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107733460","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":[0.18365534,0.00033057606,0.8143634,0.000019641708,0.00091186486,0.00062670384,0.000024802051,0.0000029910157,0.00006463821],"genre_scores_gemma":[0.2609982,0.000011542094,0.7386604,0.00005673278,0.00007688388,0.000023024477,0.0000048564048,0.000015336127,0.00015301225],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966396,0.000393821,0.0014950401,0.00025011544,0.0009802841,0.00024113504],"domain_scores_gemma":[0.9946267,0.0023365226,0.0012707348,0.00029479314,0.0013319644,0.00013927785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005127849,0.00015524412,0.00039466814,0.000684651,0.000050081668,0.00011966305,0.00041623492,0.00008210827,0.00003935681],"category_scores_gemma":[0.0029387572,0.00012632846,0.00006696394,0.0004929711,0.00006822192,0.00085327885,0.000025838997,0.00013396307,0.0000017203388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031918613,0.0028720007,0.0027127457,0.000024765139,0.000031892014,0.000011279999,0.012211299,0.0020281558,0.8329338,0.0050467597,0.010749034,0.1281864],"study_design_scores_gemma":[0.0034751643,0.005852642,0.01046924,0.00021948719,0.000046487774,0.000062132895,0.04262545,0.009512677,0.8988744,0.024249341,0.004099277,0.0005137116],"about_ca_topic_score_codex":0.000023676415,"about_ca_topic_score_gemma":0.000007515749,"teacher_disagreement_score":0.12767269,"about_ca_system_score_codex":0.000285468,"about_ca_system_score_gemma":0.0007856093,"threshold_uncertainty_score":0.5151525},"labels":[],"label_agreement":null},{"id":"W2107913362","doi":"10.1080/10691898.2012.11889630","title":"Developing Critical Thinking About Reporting of Bayesian Analyses","year":2012,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Health Sciences Research and Education","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Guideline; Medical education; Psychology; Bayesian probability; Peer review; Process (computing); Critical thinking; Computer science; Mathematics education; Medicine; Political science","score_opus":0.4104494937703346,"score_gpt":0.6454579766893039,"score_spread":0.23500848291896936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107913362","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":[0.39254603,0.0011719194,0.5896261,0.004736101,0.008320528,0.00027296587,0.000013873815,0.000009493439,0.003303042],"genre_scores_gemma":[0.750894,0.000110451874,0.24732512,0.00031347544,0.0012358549,0.000005791166,0.0000065222393,0.0000066822245,0.0001020668],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961577,0.00036895063,0.0023524067,0.00007318754,0.00058662234,0.00046115546],"domain_scores_gemma":[0.99267054,0.0017120468,0.0031823788,0.000116429364,0.0019576298,0.00036096488],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065341103,0.000069249465,0.00025999232,0.00030079804,0.00052234496,0.00001551519,0.00014753254,0.00006994601,0.0002445135],"category_scores_gemma":[0.029034242,0.00005576461,0.000035585945,0.00035794004,0.000070720445,0.00042664292,0.000025362855,0.00045309486,0.000013199176],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000405823,0.000394316,0.74042594,0.0019446809,0.00003669245,0.0000024027174,0.0412956,0.000012285194,0.0014294009,0.108227536,0.074346796,0.03184377],"study_design_scores_gemma":[0.00016632267,0.0001250251,0.9143048,0.001506161,0.00005852663,0.000040371717,0.039781183,0.00024449208,0.0004422729,0.035749346,0.0074343034,0.00014719361],"about_ca_topic_score_codex":0.00023310646,"about_ca_topic_score_gemma":0.00002104172,"teacher_disagreement_score":0.358348,"about_ca_system_score_codex":0.00034741897,"about_ca_system_score_gemma":0.008418887,"threshold_uncertainty_score":0.99720246},"labels":[],"label_agreement":null},{"id":"W2132821706","doi":"10.1080/10691898.2013.11889659","title":"Using Fun in the Statistics Classroom: An Exploratory Study of College Instructors' Hesitations and Motivations","year":2013,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Innovations in Educational Methods","field":"Social Sciences","cited_by":20,"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":"Context (archaeology); Psychology; Statistics education; Data collection; Medical education; Statistics; Mathematics education; Geography; Mathematics; Medicine","score_opus":0.103685059743507,"score_gpt":0.4355331004324211,"score_spread":0.3318480406889141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132821706","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":[0.9594359,0.000027793312,0.03823063,0.00042875498,0.0010042826,0.0005029579,0.00008629721,0.0000028669292,0.00028054728],"genre_scores_gemma":[0.68202215,0.000014209337,0.31761795,0.000063034604,0.0002193453,0.000019627003,0.00000921112,0.0000070093442,0.000027436783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9975772,0.0009571354,0.00072516093,0.00009735412,0.00051345833,0.00012970976],"domain_scores_gemma":[0.9956031,0.0012304164,0.00071237265,0.0001474273,0.0022393696,0.0000673319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017883377,0.00008513754,0.00016077077,0.0004604245,0.000384409,0.00008258965,0.00022362809,0.00004889875,0.000060637758],"category_scores_gemma":[0.0023982876,0.00007519846,0.000011179962,0.0008715972,0.0001981664,0.00070055545,0.000012162359,0.0002124827,0.000001202426],"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":[0.000008735133,0.0024714628,0.08535214,0.000029322966,0.000033414413,0.0000010581986,0.22995602,0.00017514877,0.00030388133,0.66315323,0.00600117,0.012514444],"study_design_scores_gemma":[0.00022958608,0.00017316494,0.3683825,0.000027002932,0.00004549489,0.0000064539618,0.51724106,0.00022394603,0.0000066719435,0.11323606,0.0003432854,0.000084765874],"about_ca_topic_score_codex":0.00076188194,"about_ca_topic_score_gemma":0.0013697934,"teacher_disagreement_score":0.54991716,"about_ca_system_score_codex":0.00021563392,"about_ca_system_score_gemma":0.0021105062,"threshold_uncertainty_score":0.3743947},"labels":[],"label_agreement":null},{"id":"W2141523535","doi":"10.1080/10691898.2009.11889537","title":"Teaching Bayesian Statistics in a Health Research Methodology Program","year":2009,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Bayesian probability; Bayesian statistics; Computer science; Data science; Statistics; Bayesian inference; Artificial intelligence; Mathematics","score_opus":0.32150312114316804,"score_gpt":0.5846462743249152,"score_spread":0.2631431531817472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141523535","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":[0.000653778,0.00013116797,0.995023,0.002478269,0.00044824684,0.00039707517,0.0000729451,0.000015045338,0.0007804325],"genre_scores_gemma":[0.020491786,0.00008849259,0.97865474,0.00028390632,0.00030137555,0.000011892291,0.000010775813,0.000020026439,0.00013697235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99368733,0.0034210423,0.0014747529,0.0002091859,0.00069285795,0.00051484985],"domain_scores_gemma":[0.98937094,0.008364956,0.0008403275,0.00023130365,0.0009064183,0.00028608076],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0119863115,0.00016562812,0.0005774372,0.0006455932,0.00016363441,0.00009108676,0.00028613966,0.00010023676,0.00008803547],"category_scores_gemma":[0.02248317,0.00014736335,0.00003934707,0.00039024145,0.00011416342,0.00012408372,0.000021965716,0.0012781239,0.0000041825],"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":[0.00002938436,0.00063898356,0.00010961467,0.00011018858,0.000006709497,0.000012690877,0.0012107175,7.050677e-7,0.000032884596,0.5049764,0.013533315,0.47933838],"study_design_scores_gemma":[0.0003059425,0.0016395921,0.006170307,0.0003150312,0.000017449396,0.00010348824,0.001130274,0.0010925173,0.000017965063,0.9867406,0.002338694,0.00012817325],"about_ca_topic_score_codex":0.00018921823,"about_ca_topic_score_gemma":0.000075079275,"teacher_disagreement_score":0.48176414,"about_ca_system_score_codex":0.0003809752,"about_ca_system_score_gemma":0.0017705957,"threshold_uncertainty_score":0.98575085},"labels":[],"label_agreement":null},{"id":"W2144301732","doi":"10.1080/10691898.2010.11889587","title":"Fun with the R Grid Package","year":2010,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Data Analysis with R","field":"Computer Science","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":"Western University","funders":"","keywords":"Popularity; Computer science; Graphics; Grid; Plot (graphics); Visualization; R package; Base (topology); Computer graphics (images); Core (optical fiber); Data science; Human–computer interaction; Computational science; Data mining; Psychology; Mathematics","score_opus":0.0052408527638861495,"score_gpt":0.24763405717400264,"score_spread":0.2423932044101165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144301732","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":[0.017197425,0.000028181481,0.97664165,0.0041373027,0.0014337226,0.000039454015,0.000014916396,0.0000053645053,0.00050196634],"genre_scores_gemma":[0.5297497,0.00001567821,0.4687109,0.0005239759,0.0006451616,0.0000019346207,0.000009426266,0.000006396303,0.00033681194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99928427,0.000035024175,0.00019612402,0.000076307646,0.0003189185,0.000089381705],"domain_scores_gemma":[0.99854845,0.00015156312,0.00040191063,0.00035851836,0.00046760502,0.000071966315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000421355,0.000058486967,0.00008642184,0.00008790764,0.000079681864,0.0002005832,0.00066539814,0.000017003022,0.000035687215],"category_scores_gemma":[0.00013964756,0.00003236818,0.000019912128,0.00022817984,0.000043919394,0.00038921283,0.00003146808,0.00026284633,0.000023726063],"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":[0.0000122142355,0.00026494605,0.0029092892,0.000013601396,0.000079869176,0.000016393824,0.0016812478,0.000031763724,0.0027618336,0.25068742,0.57505685,0.16648453],"study_design_scores_gemma":[0.001274974,0.0011386151,0.3535985,0.00011801721,0.0005316058,0.0021814404,0.001980663,0.010386763,0.004263702,0.07125237,0.5524467,0.0008265884],"about_ca_topic_score_codex":0.000012440732,"about_ca_topic_score_gemma":0.00006489896,"teacher_disagreement_score":0.51255226,"about_ca_system_score_codex":0.000018248164,"about_ca_system_score_gemma":0.0005252694,"threshold_uncertainty_score":0.19342284},"labels":[],"label_agreement":null},{"id":"W2148723688","doi":"10.1080/10691898.2010.11889486","title":"Normal Approximations to the Distributions of the Wilcoxon Statistics: Accurate to What <i>N</i> ? Graphical Insights","year":2010,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Wilcoxon signed-rank test; Nonparametric statistics; Mathematics; Statistics; Sample size determination; Normality; Context (archaeology); Sample (material); Surprise; Rank (graph theory); Combinatorics","score_opus":0.059291291120859554,"score_gpt":0.38629966617560957,"score_spread":0.32700837505475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148723688","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":[0.04231649,0.000049042752,0.9402332,0.0070519806,0.008453498,0.0005904696,0.0011308214,0.000011105303,0.00016339486],"genre_scores_gemma":[0.21297294,0.000094134644,0.7852052,0.0006935604,0.00050434057,0.000056291305,0.000055596483,0.000025474985,0.00039245523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997786,0.00030226234,0.0009777388,0.00015158852,0.00055819534,0.00022423128],"domain_scores_gemma":[0.9931748,0.0032689332,0.00091270654,0.0005264904,0.0018872073,0.00022987499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001071618,0.00017818686,0.0002943747,0.00021795448,0.00032252466,0.00018512344,0.00061748526,0.00008270439,0.000104516796],"category_scores_gemma":[0.014328994,0.00010932218,0.000082897895,0.0006578592,0.00017881571,0.00023243827,0.00008776673,0.00055614044,0.000017852515],"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":[0.00003161197,0.00039202877,0.00022337426,0.000059470367,0.00004192388,5.373376e-7,0.0040285513,0.000043805714,0.0016236984,0.7085213,0.27082065,0.0142130675],"study_design_scores_gemma":[0.00037840815,0.00026813452,0.03045682,0.00023922959,0.00037920912,0.00011653971,0.007789241,0.00022613796,0.0046906862,0.862979,0.092140295,0.0003362895],"about_ca_topic_score_codex":0.00002295071,"about_ca_topic_score_gemma":0.00026923182,"teacher_disagreement_score":0.17868036,"about_ca_system_score_codex":0.00007090114,"about_ca_system_score_gemma":0.0011264049,"threshold_uncertainty_score":0.99397373},"labels":[],"label_agreement":null},{"id":"W2149081627","doi":"10.1080/10691898.2011.11889615","title":"What Does the Mean Mean?","year":2011,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Conceptualization; Variety (cybernetics); Mathematics education; Concept learning; Psychology; Computer science; Artificial intelligence","score_opus":0.2435365307724326,"score_gpt":0.4328745020513,"score_spread":0.18933797127886742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149081627","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":[0.04678681,0.0010924442,0.8966187,0.0025024961,0.04672351,0.0005482993,0.00011213389,0.000050053823,0.0055655297],"genre_scores_gemma":[0.08352632,0.0010530999,0.91024387,0.0004586948,0.00068460894,0.000012287601,0.000007849599,0.000030125671,0.0039831325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853426,0.0002784481,0.00061264005,0.00009975738,0.00032097023,0.00015390223],"domain_scores_gemma":[0.99579644,0.0020784244,0.00085131894,0.00027621142,0.00089961337,0.00009799439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001442721,0.00012516718,0.00021309072,0.00013233646,0.00011683755,0.00011221939,0.00030886778,0.000049731134,0.00057465077],"category_scores_gemma":[0.0033349523,0.00006941589,0.000057583464,0.00012721114,0.00011620194,0.00026179233,0.000023571041,0.00023028787,0.000020613403],"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":[0.000044018358,0.00046738744,0.0003633294,0.000076817705,0.000085057225,0.000003474071,0.04733678,4.543767e-7,0.00009601042,0.6722178,0.21293162,0.06637727],"study_design_scores_gemma":[0.00014494022,0.0000918224,0.0029029741,0.00008416507,0.00016098497,0.00008587444,0.041775513,0.000010966036,0.0011863202,0.94189173,0.011553138,0.000111571506],"about_ca_topic_score_codex":0.00002268593,"about_ca_topic_score_gemma":0.000061098704,"teacher_disagreement_score":0.26967394,"about_ca_system_score_codex":0.000076946,"about_ca_system_score_gemma":0.00058729993,"threshold_uncertainty_score":0.62920225},"labels":[],"label_agreement":null},{"id":"W2150432176","doi":"10.1080/10691898.2012.11889638","title":"Naive Analysis of Variance","year":2012,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Variance (accounting); Statistic; Statistics; Computer science; Mathematics education; Mathematics","score_opus":0.1715423374109225,"score_gpt":0.47143337148178155,"score_spread":0.29989103407085904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150432176","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":[0.03691952,0.00035409795,0.957994,0.00011966084,0.0031851367,0.0000741006,0.00015191968,0.000005735885,0.0011958431],"genre_scores_gemma":[0.3107836,0.000093335635,0.6882283,0.000051709878,0.00022662946,0.000002421383,0.000016503707,0.000008553085,0.0005889075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986989,0.00017244428,0.00066279504,0.00005619985,0.000271167,0.00013849654],"domain_scores_gemma":[0.9951167,0.0024384938,0.001228606,0.00016461809,0.0009407915,0.000110751935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012308154,0.00008525084,0.00035701584,0.00046589473,0.000032591062,0.000012847383,0.00012905318,0.000044858654,0.00031783673],"category_scores_gemma":[0.006786012,0.00007443677,0.00008485095,0.0005231362,0.000053550157,0.00011727136,0.0000116737465,0.00011594801,0.0000044491217],"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":[0.000041277213,0.000958103,0.020092694,0.00012288585,0.00092422194,4.8583644e-7,0.005270095,0.000024437419,0.0004932658,0.8262155,0.1285331,0.017323911],"study_design_scores_gemma":[0.00042639667,0.00024874284,0.32614484,0.00011154977,0.0074559473,0.000056962555,0.007797762,0.0002744297,0.0023736886,0.6388589,0.01591548,0.00033527619],"about_ca_topic_score_codex":0.000012807573,"about_ca_topic_score_gemma":0.0000027288656,"teacher_disagreement_score":0.30605215,"about_ca_system_score_codex":0.00007913774,"about_ca_system_score_gemma":0.00042931366,"threshold_uncertainty_score":0.812398},"labels":[],"label_agreement":null},{"id":"W2182369956","doi":"10.1080/10691898.2003.11910725","title":"Estimation of a Proportion with Survey Data","year":2003,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Water Quality and Resources Studies","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Stratified sampling; Estimator; Survey sampling; Statistics; Sampling (signal processing); Survey data collection; Sampling design; Sample (material); Logistic regression; Econometrics; Small area estimation; Regression analysis; Mathematics; Computer science; Population","score_opus":0.08993871589539788,"score_gpt":0.3105950526521686,"score_spread":0.2206563367567707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182369956","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":[0.7733223,0.00006270148,0.2250613,0.00008785154,0.00020468402,0.000102284015,0.00006646396,0.0000019693525,0.0010904837],"genre_scores_gemma":[0.9254382,0.000023866454,0.0743172,0.000013258183,0.0000128841675,5.3754945e-7,0.00004298597,0.0000032603002,0.00014780744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992514,0.000104540944,0.00027194511,0.00006238426,0.000256359,0.000053323965],"domain_scores_gemma":[0.999273,0.000065603665,0.0004432112,0.00012645956,0.00006165969,0.000030074929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081263424,0.00004211673,0.000088524226,0.000025680181,0.00004058565,0.000009832508,0.00009913563,0.000014366405,0.00009068891],"category_scores_gemma":[0.00040075934,0.000028893148,0.000005901749,0.00009989264,0.00008533902,0.0001631721,0.000018625775,0.00005109573,0.0000059729828],"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":[0.00022833937,0.0018427041,0.77416885,0.00021911228,0.00013453304,0.0000049098085,0.00875238,0.020329569,0.0009241782,0.0029821699,0.060486678,0.12992659],"study_design_scores_gemma":[0.00033896547,0.00040645944,0.9863592,0.00007746333,0.00008703938,0.00007198605,0.0010840703,0.0018742847,0.0013955574,0.0052657863,0.0029087632,0.00013045636],"about_ca_topic_score_codex":0.00020941072,"about_ca_topic_score_gemma":0.00013458384,"teacher_disagreement_score":0.21219033,"about_ca_system_score_codex":0.00004388786,"about_ca_system_score_gemma":0.000082621664,"threshold_uncertainty_score":0.11782283},"labels":[],"label_agreement":null},{"id":"W2185351175","doi":"10.1080/10691898.2010.11889593","title":"To Ski or Not to Ski: Estimating Transition Matrices to Predict Tomorrow's Snowfall Using Real Data","year":2010,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Climate variability and models","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Snow; Econometrics; Computer science; Statistics; Mathematics; Meteorology; Geography","score_opus":0.050389242103961555,"score_gpt":0.35812288962509803,"score_spread":0.30773364752113647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185351175","genre_codex":"empirical","genre_gemma":"methods","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":[0.6186159,7.1092245e-7,0.37884945,0.0009960907,0.00094324624,0.00020261724,0.0002737546,0.00000632616,0.0001118759],"genre_scores_gemma":[0.39363873,0.0000039801125,0.6054895,0.0004385601,0.00034299784,0.0000027432195,0.000034085788,0.000010863789,0.000038521022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860287,0.000043093314,0.0005031786,0.00023419644,0.00042072125,0.00019592253],"domain_scores_gemma":[0.9988335,0.0001846449,0.0002198716,0.00033532668,0.00009005161,0.00033663522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009394345,0.000111699286,0.000162538,0.00011528728,0.00012848256,0.00013824891,0.0003838351,0.00005174934,0.0005428735],"category_scores_gemma":[0.00076194666,0.000098522636,0.000018602177,0.00027203723,0.00002664138,0.00046351296,0.00012103795,0.00018631507,0.000060088016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010045462,0.0018430873,0.004666494,0.00027833416,0.00004900773,0.000028203447,0.032980032,0.39596674,0.31082726,0.0013215074,0.0751401,0.17589468],"study_design_scores_gemma":[0.0011116787,0.0019888878,0.08751683,0.00070365635,0.0005986543,0.0004733329,0.0034632122,0.8793269,0.0030163322,0.006253108,0.014281065,0.0012663604],"about_ca_topic_score_codex":0.0009976823,"about_ca_topic_score_gemma":0.00062487385,"teacher_disagreement_score":0.48336014,"about_ca_system_score_codex":0.00020899095,"about_ca_system_score_gemma":0.00020681141,"threshold_uncertainty_score":0.59440845},"labels":[],"label_agreement":null},{"id":"W2185685412","doi":"10.1080/10691898.2003.11910695","title":"Multiple-Choice Randomization","year":2003,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Randomization; Cheating; Randomized experiment; Computer science; Randomized controlled trial; Sample (material); Mathematics education; Psychology; Statistics; Econometrics; Mathematics; Social psychology; Medicine","score_opus":0.007929292996903231,"score_gpt":0.27150498234746295,"score_spread":0.26357568935055975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185685412","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":[0.004077123,0.00013175524,0.9929078,0.00027267545,0.0017204585,0.000042749754,0.0000012652365,0.00000900848,0.0008371277],"genre_scores_gemma":[0.41857806,0.00003175169,0.58059263,0.00013214907,0.00019887502,0.0000012535928,0.000002635908,0.000004870852,0.00045777252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992374,0.00013652968,0.0002772449,0.000070505375,0.00019770548,0.000080602396],"domain_scores_gemma":[0.99848664,0.0005994071,0.00036181495,0.00011127622,0.00037199334,0.00006888619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045616104,0.00005615357,0.00010261984,0.000112162365,0.00006509893,0.00008793164,0.00017600467,0.000021056374,0.000021910968],"category_scores_gemma":[0.0034825278,0.000048317106,0.000026196654,0.0001561931,0.000009832815,0.0002333473,0.0000074862905,0.00013465503,0.000008713582],"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":[0.00003552794,0.0006738794,0.031320464,0.000056656576,0.00005667724,0.000008867046,0.0022039432,0.0055108694,0.0005803936,0.4183388,0.045846056,0.49536785],"study_design_scores_gemma":[0.013787172,0.000851898,0.108852744,0.00027090262,0.000146534,0.0010212797,0.00049749535,0.37372607,0.002338281,0.14732745,0.3502383,0.0009418788],"about_ca_topic_score_codex":0.000009889578,"about_ca_topic_score_gemma":0.0000015592243,"teacher_disagreement_score":0.49442598,"about_ca_system_score_codex":0.000035901325,"about_ca_system_score_gemma":0.00035600315,"threshold_uncertainty_score":0.41691628},"labels":[],"label_agreement":null},{"id":"W2188140823","doi":"10.1080/10691898.2013.11889688","title":"The Evidence for Efficacy of HPV Vaccines: Investigations in Categorical Data Analysis","year":2013,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Cervical Cancer and HPV Research","field":"Medicine","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":"University of Toronto","funders":"National Cancer Institute; Centers for Disease Control and Prevention","keywords":"Categorical variable; Biostatistics; Contingency table; Context (archaeology); Statistical inference; Logistic regression; Statistics; Statistical hypothesis testing; Computer science; Data science; Psychology; Medicine; Econometrics; Mathematics; Public health","score_opus":0.18262433259587088,"score_gpt":0.4771627287071205,"score_spread":0.29453839611124966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188140823","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":[0.3136887,0.01132113,0.6068211,0.06108349,0.0019933875,0.0033439633,0.0002864037,0.00001232892,0.0014495046],"genre_scores_gemma":[0.9778545,0.00073489425,0.02074937,0.00009813509,0.0002691124,0.00001759471,0.000079213234,0.000005946942,0.00019124307],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989357,0.00004832616,0.0005194428,0.00008988794,0.0003006622,0.000105962215],"domain_scores_gemma":[0.9958681,0.0021349967,0.00025551493,0.00030607058,0.0013117522,0.00012358991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065412925,0.00004849445,0.00020164515,0.00021845571,0.000049839946,0.00003295105,0.00022736078,0.000026489284,0.0004330645],"category_scores_gemma":[0.0068690935,0.000031050316,0.000044508713,0.0006040375,0.000052170002,0.00014663307,0.000029097891,0.00016171481,0.000003149325],"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":[0.00054463634,0.0009843386,0.16054605,0.00044573745,0.0005598621,0.0000019533663,0.0010780338,0.00021927914,0.0003368811,0.008880813,0.14584811,0.68055433],"study_design_scores_gemma":[0.00049218483,0.00018140665,0.98205745,0.00002175408,0.00047455807,0.000005942814,0.0003828282,0.0062396377,0.000035546767,0.009184595,0.000891155,0.00003296686],"about_ca_topic_score_codex":0.0005219581,"about_ca_topic_score_gemma":0.0002466443,"teacher_disagreement_score":0.8215114,"about_ca_system_score_codex":0.000110726636,"about_ca_system_score_gemma":0.0013376808,"threshold_uncertainty_score":0.82234424},"labels":[],"label_agreement":null},{"id":"W223726334","doi":"10.1080/10691898.2006.11910584","title":"The Language of Conditional Probability","year":2006,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","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":"Columbia College","funders":"U.S. National Library of Medicine","keywords":"Vocabulary; Computer science; Mathematics education; Statistical analysis; Statistical learning; Conditional probability; Natural language processing; Artificial intelligence; Psychology; Linguistics; Statistics; Mathematics","score_opus":0.0829490936061876,"score_gpt":0.4203260498839845,"score_spread":0.33737695627779685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W223726334","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":[0.18257348,0.0007508098,0.806627,0.0013867745,0.0041234116,0.00036793054,0.0005534549,0.000017206914,0.0035999313],"genre_scores_gemma":[0.26131475,0.000038816954,0.73605317,0.000032508186,0.00039047265,0.000007607733,0.000040027287,0.000010409869,0.0021122065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988086,0.00016376497,0.0006135328,0.00005413019,0.00027010153,0.00008982905],"domain_scores_gemma":[0.99433565,0.0037378003,0.0008618178,0.00013836415,0.00089360937,0.000032743977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010899071,0.00006641563,0.00015059389,0.00006390276,0.000079818485,0.000024842355,0.00013463994,0.000030235475,0.000080311875],"category_scores_gemma":[0.0055097453,0.000045264387,0.000041466243,0.00008925917,0.00014033145,0.000044195287,0.0000096252215,0.00011129829,0.0000026520845],"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":[0.000019153471,0.0002674635,0.00082624186,0.00006217482,0.000015798287,4.961712e-7,0.00043702972,0.0000066196653,0.00046712824,0.77005684,0.22183196,0.006009071],"study_design_scores_gemma":[0.00013170317,0.000051663268,0.018223735,0.000020859727,0.00004579136,0.00002985589,0.0015576311,0.000014580299,0.0014880724,0.97321284,0.0051758774,0.0000473827],"about_ca_topic_score_codex":0.00003403383,"about_ca_topic_score_gemma":0.000027838585,"teacher_disagreement_score":0.21665609,"about_ca_system_score_codex":0.000068465946,"about_ca_system_score_gemma":0.0006953405,"threshold_uncertainty_score":0.6596078},"labels":[],"label_agreement":null},{"id":"W2274624192","doi":"10.1080/10691898.2015.11889745","title":"Calibrating the Difficulty of an Assessment Tool: The Blooming of a Statistics Examination","year":2015,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Taxonomy (biology); Computer science; Bloom's taxonomy; Mathematics education; Test (biology); Statistics; Machine learning; Artificial intelligence; Cognition; Psychology; Mathematics; Ecology","score_opus":0.1948871322534769,"score_gpt":0.47645813475276666,"score_spread":0.2815710024992898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274624192","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":[0.17306747,0.00007461601,0.8239279,0.00032213272,0.0016650148,0.0002720327,0.00034492565,0.0000071296454,0.0003187926],"genre_scores_gemma":[0.31172648,0.000032899246,0.68774366,0.000045205274,0.00020244959,0.000008960176,0.000038648508,0.000016702194,0.000184987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969844,0.00088704913,0.0011816468,0.000105641084,0.0006971044,0.00014415274],"domain_scores_gemma":[0.9895817,0.0054414887,0.0023575255,0.00031969085,0.0022121076,0.00008748514],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004115537,0.00014179821,0.00032968097,0.00012761522,0.00010918221,0.00006169231,0.00034268064,0.000056662157,0.000036562986],"category_scores_gemma":[0.012788651,0.00008536291,0.00004358197,0.00022008576,0.00018701742,0.00016120853,0.00003708181,0.00026266708,6.644945e-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":[0.00005754524,0.0012993783,0.0015088499,0.00033821104,0.00014031699,0.0000024390883,0.020976776,0.00028971353,0.001958633,0.778139,0.07070149,0.12458767],"study_design_scores_gemma":[0.0011925413,0.0010321175,0.09778121,0.00028446087,0.00079674233,0.00015207125,0.0709053,0.010234312,0.0039113727,0.8113042,0.0020645948,0.0003410477],"about_ca_topic_score_codex":0.000046360034,"about_ca_topic_score_gemma":0.000024532115,"teacher_disagreement_score":0.13865903,"about_ca_system_score_codex":0.00012944806,"about_ca_system_score_gemma":0.0016815127,"threshold_uncertainty_score":0.995527},"labels":[],"label_agreement":null},{"id":"W2559671103","doi":"10.1080/10691898.2016.1246953","title":"Play It Again: Teaching Statistics With Monte Carlo Simulation","year":2016,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Monte Carlo method; Coding (social sciences); Code (set theory); Software; Statistical learning; Statistical analysis; Computational statistics; Statistical software; Source code; Theoretical computer science; Software engineering; Machine learning; Artificial intelligence; Programming language; Statistics; Mathematics","score_opus":0.12392470184484022,"score_gpt":0.4378505355674088,"score_spread":0.3139258337225686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559671103","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":[0.015610231,0.000051808365,0.98007727,0.0010554602,0.0018979808,0.00021781962,0.0005175846,0.000025998912,0.00054582785],"genre_scores_gemma":[0.2673882,0.00007367593,0.72837377,0.00019948695,0.00043859202,0.00000873817,0.000010546943,0.000041792173,0.0034652066],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765855,0.00037376254,0.0009205641,0.00019310386,0.0005876167,0.000266401],"domain_scores_gemma":[0.98893166,0.007785908,0.0013689222,0.00028699078,0.0014322635,0.0001942356],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013782695,0.00023126595,0.00038673604,0.00029212897,0.00016222615,0.00007616854,0.00022241675,0.000087524575,0.0001999643],"category_scores_gemma":[0.012270419,0.00014992486,0.00004458667,0.00011971939,0.000112019465,0.00025251057,0.000021376565,0.00028955677,0.000018859633],"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":[0.000246633,0.00065019145,0.0022022307,0.00018422247,0.00017984296,0.0000203018,0.0049217152,0.0009042689,0.0004621614,0.2430228,0.60822296,0.13898265],"study_design_scores_gemma":[0.0038347826,0.0018905422,0.015052381,0.0017577776,0.0010855392,0.00044935165,0.009602323,0.0033071332,0.0009420453,0.81996465,0.1407459,0.0013675707],"about_ca_topic_score_codex":0.000018449386,"about_ca_topic_score_gemma":0.000030079924,"teacher_disagreement_score":0.57694185,"about_ca_system_score_codex":0.0003007148,"about_ca_system_score_gemma":0.0011249154,"threshold_uncertainty_score":0.99604964},"labels":[],"label_agreement":null},{"id":"W2594361895","doi":"10.1080/10691898.2017.1286960","title":"Long-Term and Seasonal Trends of Wastewater Chemicals in Lake Mead: An Introduction to Time Series Decomposition","year":2017,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Water Quality and Pollution Assessment","field":"Environmental Science","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":"Quest University Canada","funders":"Harvard University","keywords":"Series (stratigraphy); Time series; Linear regression; Missing data; Regression; Computer science; Regression analysis; Statistics; Term (time); Decomposition; Econometrics; Data mining; Machine learning; Mathematics; Ecology","score_opus":0.013547339210607181,"score_gpt":0.32770048508745614,"score_spread":0.31415314587684895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594361895","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":[0.99413604,0.0000041227527,0.0014131082,0.0040556225,0.00021624692,0.000037870726,0.0000412515,0.0000012665905,0.000094491836],"genre_scores_gemma":[0.9781347,0.0000097980965,0.021070901,0.000036667203,0.00019410392,0.0000017197436,0.000039351744,0.0000037935727,0.0005089803],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99935037,0.000051485593,0.000265089,0.0000859347,0.00017405287,0.000073087256],"domain_scores_gemma":[0.9994575,0.00001132203,0.00029854567,0.00011481699,0.00003267104,0.0000851938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003269577,0.000055405668,0.00010757939,0.00006331511,0.00006427858,0.000053982454,0.00009153811,0.000026274956,0.0007367676],"category_scores_gemma":[0.000037953752,0.000049866056,0.00001194554,0.000036161826,0.00007550644,0.00046802816,0.00002958197,0.00006163567,0.000008658107],"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":[0.00049679907,0.0013380771,0.38439077,0.000101115875,0.00003788293,0.0000063837233,0.006448099,0.0004559401,0.40953276,0.0016970091,0.021288738,0.17420644],"study_design_scores_gemma":[0.00017062669,0.00018335007,0.9791372,0.000026831927,0.00001601224,0.000038488575,0.00004338961,0.000045111654,0.018587682,0.00086807733,0.0008191446,0.000064085914],"about_ca_topic_score_codex":0.000023429257,"about_ca_topic_score_gemma":0.00018192793,"teacher_disagreement_score":0.5947464,"about_ca_system_score_codex":0.00008774618,"about_ca_system_score_gemma":0.000026615387,"threshold_uncertainty_score":0.8067089},"labels":[],"label_agreement":null},{"id":"W2731892372","doi":"10.1080/10691898.2008.11889564","title":"Developing a Biostatistical Collaboration Course in a Health Science Research Methodology Program","year":2008,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Health and Medical Research Impacts","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Course (navigation); Computer science; Mathematics education; Research methodology; Medical education; Management science; Psychology; Medicine; Engineering","score_opus":0.6360916457714515,"score_gpt":0.684654739067078,"score_spread":0.04856309329562647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731892372","genre_codex":"empirical","genre_gemma":"methods","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":[0.4480992,0.0017717759,0.295315,0.24948834,0.0017851959,0.0028343997,0.000041350402,0.000025566358,0.00063914957],"genre_scores_gemma":[0.2961316,0.0013596225,0.70074385,0.0013597681,0.00028615093,0.00001895014,0.000013082689,0.0000085646125,0.00007841279],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996331,0.00046420787,0.0007766016,0.0001471719,0.0015295133,0.0007515283],"domain_scores_gemma":[0.9920559,0.0011658078,0.0002755498,0.00012293918,0.0039232373,0.0024565784],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013985908,0.000070109185,0.00030912814,0.0008964926,0.00022601277,0.000027513861,0.0001169579,0.000059119466,0.00003380448],"category_scores_gemma":[0.09966776,0.000057658417,0.000013264752,0.0019001375,0.000720699,0.00015193333,0.000020757716,0.0007218515,0.000008850564],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006148874,0.001705762,0.013122895,0.00084993156,0.000016160533,0.00028775982,0.005954631,0.0000032864277,0.0007287369,0.06166226,0.072071664,0.842982],"study_design_scores_gemma":[0.0045536463,0.013814361,0.83052635,0.0026387186,0.00003094426,0.0051691146,0.012594234,0.002178852,0.0010715792,0.025903124,0.10123114,0.0002879142],"about_ca_topic_score_codex":0.00019635598,"about_ca_topic_score_gemma":0.000055412173,"teacher_disagreement_score":0.8426941,"about_ca_system_score_codex":0.0017226529,"about_ca_system_score_gemma":0.20775202,"threshold_uncertainty_score":0.9079161},"labels":[],"label_agreement":null},{"id":"W2772013839","doi":"10.1080/10691898.2002.11910547","title":"More on Venn Diagrams for Regression","year":2002,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Venn diagram; Variance (accounting); Contrast (vision); Regression analysis; Statistics; Value (mathematics); Linear regression; Regression; Mathematics; Diagram; Computer science; Artificial intelligence; Mathematics education","score_opus":0.19062228069432038,"score_gpt":0.48878547213541274,"score_spread":0.2981631914410924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772013839","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":[0.0031155853,0.00012840117,0.99464434,0.0005814015,0.00084400934,0.00017376806,0.00009344965,0.0000067181363,0.000412349],"genre_scores_gemma":[0.03831479,0.00011506325,0.9599949,0.00016877615,0.00041989933,0.000013735835,0.000006845712,0.000023156495,0.00094282976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904543,0.000050508806,0.0004321366,0.0000960584,0.00023921591,0.00013663255],"domain_scores_gemma":[0.9970066,0.0018237986,0.00049513404,0.00013229762,0.00042844896,0.000113744885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030346977,0.000104332634,0.00021973594,0.00008322631,0.000075315525,0.000021158876,0.00009289738,0.000048621278,0.0000745021],"category_scores_gemma":[0.003751146,0.000077655735,0.00005405849,0.00006060433,0.000032782482,0.00007555919,0.000006632865,0.00015204922,0.0000042763727],"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":[0.000052533407,0.000527868,0.000017038758,0.000107889886,0.000017344855,0.0000033740996,0.00064366584,0.000024015979,0.00014727605,0.5069259,0.10972863,0.38180447],"study_design_scores_gemma":[0.0003764746,0.000463815,0.00013877546,0.00021227713,0.000069002635,0.000022858996,0.0002358256,0.0034594564,0.0002596763,0.98537016,0.009283822,0.00010785822],"about_ca_topic_score_codex":5.394728e-7,"about_ca_topic_score_gemma":4.9725725e-7,"teacher_disagreement_score":0.47844425,"about_ca_system_score_codex":0.000077862154,"about_ca_system_score_gemma":0.0000550802,"threshold_uncertainty_score":0.4490743},"labels":[],"label_agreement":null},{"id":"W2773649145","doi":"10.1080/10691898.2001.11910656","title":"Issues in Teaching the Comparison of Variability to Non-Statistics Students","year":2001,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","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 Ottawa","funders":"","keywords":"Homoscedasticity; Perspective (graphical); Statistics; Statistics education; Mathematics education; Psychology; Inclusion (mineral); Computer science; Mathematics; Social psychology; Artificial intelligence; Heteroscedasticity","score_opus":0.1445649149147247,"score_gpt":0.5372942438490687,"score_spread":0.392729328934344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773649145","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":[0.14800829,0.000058653277,0.84819806,0.00081396126,0.002015457,0.0003147527,0.0001143009,0.0000055893915,0.0004709341],"genre_scores_gemma":[0.37358496,0.00006203824,0.62552905,0.00009092467,0.0001687492,0.000008769208,0.000009321216,0.000013717794,0.00053248694],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997068,0.0007504135,0.0012726419,0.00013348079,0.00058690214,0.00018858591],"domain_scores_gemma":[0.991042,0.0067654513,0.0009916282,0.00029876473,0.00079750153,0.00010461727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050506033,0.00014590724,0.0004629098,0.0002526723,0.000088761604,0.00005931348,0.00045336672,0.00005857369,0.000093511175],"category_scores_gemma":[0.023876391,0.000111104826,0.00003724536,0.0002439305,0.00007494632,0.00007484147,0.0000530823,0.000407515,0.0000070680176],"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":[0.00015449325,0.0033852484,0.25851634,0.0002608792,0.00008280477,0.0000048537063,0.032359954,0.0001691296,0.00040136755,0.23056276,0.37876186,0.09534029],"study_design_scores_gemma":[0.00053938216,0.00039526698,0.28199154,0.0002822123,0.00018119675,0.00004045419,0.015380301,0.0005863123,0.00042835873,0.6861293,0.013798171,0.0002475396],"about_ca_topic_score_codex":0.00012729953,"about_ca_topic_score_gemma":0.000078690275,"teacher_disagreement_score":0.4555665,"about_ca_system_score_codex":0.00018246146,"about_ca_system_score_gemma":0.00049552333,"threshold_uncertainty_score":0.9843459},"labels":[],"label_agreement":null},{"id":"W2781252204","doi":"10.1080/10691898.2017.1381055","title":"Twin Data that Made a Big Difference, and that Deserve to be Better-Known and Used in Teaching","year":2017,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Demographic Trends and Gender Preferences","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Appeal; Computer science; Big data; Data science; Human immunodeficiency virus (HIV); Constant (computer programming); Psychology; Data mining; Law; Political science; Medicine","score_opus":0.19846542019439017,"score_gpt":0.4005147435760152,"score_spread":0.202049323381625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781252204","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":[0.98794,0.00020426483,0.0026148472,0.0075487085,0.0005799242,0.0000781891,0.000076631346,0.0000024334504,0.00095496187],"genre_scores_gemma":[0.9872603,0.00036095036,0.011719958,0.00016390081,0.00018079531,0.0000017996655,0.0000095563,0.000004399056,0.00029833367],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991149,0.00013221324,0.0001829862,0.0001474469,0.00028026095,0.00014224571],"domain_scores_gemma":[0.9990054,0.0002447427,0.00031597086,0.00022265276,0.00005402724,0.0001572448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009779545,0.00007685864,0.00015374625,0.0001861587,0.00043664317,0.0005021155,0.00043082036,0.000045364945,0.000012236321],"category_scores_gemma":[0.00058191456,0.00006432263,0.000010529039,0.000045623194,0.00013533434,0.0003117288,0.00010801522,0.00019106326,2.8388519e-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":[0.0000076160795,0.00005863892,0.6412422,0.000011550249,0.000011754884,0.0000019676766,0.014617978,1.4100988e-7,0.00003417615,0.003885587,0.0019000121,0.33822834],"study_design_scores_gemma":[0.00017241357,0.00004435439,0.968251,0.00008510844,0.000024583429,0.000004228759,0.0078070215,0.000032351163,0.000003998014,0.019152528,0.004339002,0.000083440595],"about_ca_topic_score_codex":0.0023229527,"about_ca_topic_score_gemma":0.019843874,"teacher_disagreement_score":0.3381449,"about_ca_system_score_codex":0.000024383602,"about_ca_system_score_gemma":0.0002488139,"threshold_uncertainty_score":0.9980414},"labels":[],"label_agreement":null},{"id":"W3048636303","doi":"10.1080/10691898.2020.1807429","title":"The Impact of Assignments and Quizzes on Exam Grades: A Difference-in-Difference Approach","year":2020,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"School Choice and Performance","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Significant difference; Mathematics education; Psychology; Medical education; Mathematics; Medicine; Statistics","score_opus":0.0590522682196578,"score_gpt":0.37564299779167143,"score_spread":0.3165907295720136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048636303","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":[0.99626017,0.00020805957,0.0013880965,0.0008304275,0.00020842181,0.00008813814,0.0000121417925,0.0000016848887,0.0010028455],"genre_scores_gemma":[0.99736184,0.0010633979,0.0011328596,0.000072825795,0.00025964447,0.0000024238939,0.0000016295468,0.0000031056131,0.00010228562],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991622,0.00011478241,0.0002500957,0.00006229689,0.0003000908,0.00011050846],"domain_scores_gemma":[0.99904186,0.00035655065,0.00031524544,0.000049802355,0.00012758294,0.000108973145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003358672,0.000059432983,0.000120045275,0.000045528293,0.00013193356,0.000064119224,0.000153981,0.00003009661,0.000012144095],"category_scores_gemma":[0.0005800171,0.00003721569,0.000024284142,0.00014735232,0.00009912672,0.00008409284,0.00000789862,0.00016686252,9.2352064e-7],"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":[0.00028734328,0.00063625723,0.7887415,0.00008353445,0.00007067901,0.0000015870047,0.06748987,0.00012494686,0.00079399603,0.017025558,0.013505024,0.1112397],"study_design_scores_gemma":[0.0002030725,0.00038600704,0.9875484,0.000058558067,0.0000130299495,0.0000014431238,0.0068197283,0.00039046505,0.00003102866,0.0042685806,0.00022304761,0.000056626006],"about_ca_topic_score_codex":0.00037421176,"about_ca_topic_score_gemma":0.00006677998,"teacher_disagreement_score":0.19880691,"about_ca_system_score_codex":0.00008102008,"about_ca_system_score_gemma":0.0006025445,"threshold_uncertainty_score":0.15176117},"labels":[],"label_agreement":null},{"id":"W3091953943","doi":"10.1080/10691898.2020.1834475","title":"The Flipped Classroom in Introductory Statistics: Early Evidence From a Systematic Review and Meta-Analysis","year":2020,"lang":"en","type":"review","venue":"Journal of Statistics Education","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Flipped classroom; Mathematics education; Class (philosophy); Psychology; Statistics education; Meta-analysis; Active learning (machine learning); Statistics; Moderation; Computer science; Mathematics; Medicine","score_opus":0.17143430536022913,"score_gpt":0.48149405671700474,"score_spread":0.3100597513567756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091953943","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3394988e-7,0.9455819,0.051108856,0.001202898,0.0004688709,0.0012388198,0.00036163413,0.0000054437073,0.00003111242],"genre_scores_gemma":[0.0000040791233,0.90553546,0.09349407,0.00015960267,0.00032719353,0.00008239004,0.000028190494,0.000024374465,0.00034462952],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.986031,0.009784761,0.0026885213,0.0003173134,0.000932338,0.00024606433],"domain_scores_gemma":[0.9810383,0.012159248,0.005024791,0.00039409267,0.0012283941,0.00015521793],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012074909,0.00033506737,0.005049948,0.00042046135,0.0003062352,0.00032501318,0.00074418634,0.00013520638,0.000118307034],"category_scores_gemma":[0.037149314,0.00020778258,0.0005031685,0.0016283672,0.00024581622,0.00024546162,0.000055713805,0.0010865944,0.000013298557],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000125872175,0.00016685973,0.000046386835,0.61498183,0.11297647,0.000026233749,0.016363742,9.3357454e-7,2.698321e-7,0.051062874,0.02266167,0.18170014],"study_design_scores_gemma":[0.00003570705,0.000055831213,0.000052376778,0.03552833,0.8282375,0.000007030726,0.0008208231,0.0000040409586,2.426409e-8,0.007470828,0.12748648,0.0003010815],"about_ca_topic_score_codex":0.0009045684,"about_ca_topic_score_gemma":0.0006617846,"teacher_disagreement_score":0.715261,"about_ca_system_score_codex":0.0006916712,"about_ca_system_score_gemma":0.003713655,"threshold_uncertainty_score":0.9709612},"labels":[],"label_agreement":null},{"id":"W4299723234","doi":"10.1080/10691898.2000.12131298","title":"A Simplified Introduction to Correlation and Regression","year":2000,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistics; Linear regression; Regression; Standardized coefficient; Regression analysis; Mathematics; Correlation; Simple linear regression; Correlation coefficient; Line (geometry); Regression diagnostic; Scale (ratio); Proper linear model; Pearson product-moment correlation coefficient; Segmented regression; Polynomial regression","score_opus":0.07617537617937507,"score_gpt":0.42187061882089255,"score_spread":0.34569524264151746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299723234","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":[0.17196952,0.0001721587,0.8159157,0.0055452758,0.004756077,0.00034279213,0.000059216025,0.000029782148,0.0012094512],"genre_scores_gemma":[0.0515541,0.0002521939,0.94015986,0.00026443892,0.001480794,0.000008347239,0.00002461248,0.00002069946,0.0062349318],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989273,0.000139809,0.00048631465,0.000121020465,0.000218296,0.000107272965],"domain_scores_gemma":[0.9981091,0.00079383055,0.00034912495,0.00013744226,0.0004770824,0.00013340083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006802526,0.00010100858,0.00019046056,0.00019802929,0.00008370269,0.0000480816,0.000071789655,0.000052444277,0.00062262826],"category_scores_gemma":[0.0039734566,0.00008489296,0.0000205545,0.00016231377,0.00003330666,0.000112077054,0.000008422765,0.00014632395,0.000024366875],"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":[0.00010766968,0.00015987734,0.00028307285,0.000045920962,0.000014605921,8.261587e-7,0.0018014084,0.000034155026,0.00039886576,0.065125935,0.55359936,0.3784283],"study_design_scores_gemma":[0.00051534973,0.00042732505,0.020238567,0.00015691393,0.00017218036,0.00032051324,0.0021930789,0.00029074468,0.0006324005,0.80147326,0.17331477,0.0002649227],"about_ca_topic_score_codex":0.000006661855,"about_ca_topic_score_gemma":0.0000028663871,"teacher_disagreement_score":0.7363473,"about_ca_system_score_codex":0.000083325525,"about_ca_system_score_gemma":0.0002479505,"threshold_uncertainty_score":0.68173426},"labels":[],"label_agreement":null},{"id":"W4302054000","doi":"10.1080/10691898.2000.12131292","title":"Replacing a 'Striped-Box' with the Normal Approximation","year":2000,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"Advanced Statistical Process Monitoring","field":"Decision 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":"Western University","funders":"","keywords":"Statistics; Acceptance sampling; Binomial distribution; Mathematics; Sample size determination; Sample (material); Probability distribution; Quality (philosophy); Sampling (signal processing); Sampling distribution; Binomial (polynomial); Normal distribution; Negative binomial distribution; Simple (philosophy); Computer science; Poisson distribution","score_opus":0.04177383652799056,"score_gpt":0.384821047299374,"score_spread":0.34304721077138345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302054000","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":[0.04860003,0.00010537336,0.94622934,0.001125364,0.00046320548,0.00011072048,0.000019761806,0.000006956371,0.0033392764],"genre_scores_gemma":[0.77224916,0.00002350467,0.2249962,0.00013323239,0.00047915065,0.0000052522987,0.0000036685647,0.000011549057,0.0020982798],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975073,0.00012282998,0.0007369416,0.00015777072,0.0013110006,0.0001642009],"domain_scores_gemma":[0.9960022,0.0016405481,0.0007816029,0.0002458785,0.0012195461,0.00011022299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015116,0.00010428226,0.00018658153,0.00013986272,0.00022634829,0.00024645758,0.00038541123,0.000030995077,0.0004436187],"category_scores_gemma":[0.002601944,0.00005811459,0.000029001034,0.0004951122,0.00010151025,0.0006157844,0.000012383263,0.0002773417,0.000057028916],"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":[0.0002082008,0.00011829159,0.0012298396,0.000013706693,0.000016963606,0.000007851325,0.0017715573,0.004413802,0.00011586889,0.01058943,0.022271104,0.95924336],"study_design_scores_gemma":[0.0024001568,0.0018875665,0.077957235,0.00043904595,0.0003510372,0.0016024751,0.022200273,0.020705681,0.0025841962,0.705106,0.16376208,0.001004202],"about_ca_topic_score_codex":0.0000079713855,"about_ca_topic_score_gemma":0.000006368122,"teacher_disagreement_score":0.9582392,"about_ca_system_score_codex":0.00009146277,"about_ca_system_score_gemma":0.0004726695,"threshold_uncertainty_score":0.48573133},"labels":[],"label_agreement":null},{"id":"W73701489","doi":"10.1080/10691898.2009.11889520","title":"Using Simple Linear Regression to Assess the Success of the Montreal Protocol in Reducing Atmospheric Chlorofluorocarbons","year":2009,"lang":"en","type":"article","venue":"Journal of Statistics Education","topic":"History and advancements in chemistry","field":"Chemistry","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":"National Oceanic and Atmospheric Administration","keywords":"Protocol (science); Simple (philosophy); Simple linear regression; Set (abstract data type); Linear regression; Statistics; Data set; Computer science; Montreal Protocol; Meteorology; Econometrics; Mathematics; Geography","score_opus":0.03801651888880281,"score_gpt":0.3753889352426526,"score_spread":0.3373724163538498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W73701489","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":[0.9861216,0.00005660968,0.008187238,0.00025620777,0.0003807735,0.0025445407,0.000027453789,0.000005332509,0.0024202229],"genre_scores_gemma":[0.9647832,0.000006869939,0.034034833,0.00008793591,0.000405233,0.00026053187,0.0000040724535,0.000013698523,0.00040361064],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989183,0.00003435438,0.00052940554,0.000099772806,0.00029244518,0.00012571254],"domain_scores_gemma":[0.998672,0.00010034695,0.00071864267,0.00023852731,0.00021387848,0.00005657086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023045909,0.000102412756,0.00015816557,0.000013221629,0.00012008963,0.000015547559,0.0003008349,0.000049045055,0.000077378165],"category_scores_gemma":[0.000367283,0.000064155465,0.000039533443,0.00019226257,0.00004638883,0.00009513548,0.000023682942,0.00027980495,2.565853e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040185434,0.0014962957,0.011807545,0.0005309154,0.000039452996,0.00001158608,0.005312046,0.021363772,0.85028625,0.00037277184,0.006447613,0.10192987],"study_design_scores_gemma":[0.0023794326,0.00026065644,0.023051089,0.004601013,0.00021431196,0.00017511545,0.007794624,0.010992988,0.9142899,0.011806264,0.023712602,0.0007220205],"about_ca_topic_score_codex":0.000048565696,"about_ca_topic_score_gemma":0.000008080099,"teacher_disagreement_score":0.10120785,"about_ca_system_score_codex":0.00028632826,"about_ca_system_score_gemma":0.0005584637,"threshold_uncertainty_score":0.26161838},"labels":[],"label_agreement":null}]}