{"meta":{"query_hash":"42798c2100f6","filters":{"venue":"The American Statistician"},"cohort_total":60,"direct_labels_cover":1,"predictions_cover":60,"exported":60,"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/42798c2100f6","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+American+Statistician"},"results":[{"id":"W1609447734","doi":"10.1080/00031305.2015.1033985","title":"Advanced Placement Statistics: Expanding the Scope of Statistics Education","year":2015,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","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":"","keywords":"Statistics; Statistics education; Scope (computer science); Quarter (Canadian coin); Descriptive statistics; Summary statistics; Mathematics education; Computer science; Psychology; Mathematics; Geography","score_opus":0.17090548150606014,"score_gpt":0.4657031647904276,"score_spread":0.2947976832843675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1609447734","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":[0.00914921,0.00025915203,0.98166466,0.0005253345,0.001330737,0.0007019465,0.0022573695,0.00006658319,0.0040450017],"genre_scores_gemma":[0.06846176,0.00020249843,0.9283324,0.0007918397,0.0001720819,0.00015726086,0.00012558381,0.00005749747,0.0016990795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973729,0.00074617565,0.0006579412,0.00026121226,0.0005856818,0.00037606352],"domain_scores_gemma":[0.9903797,0.007155,0.0010264416,0.0006994466,0.00057975494,0.00015964861],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014556351,0.00024903315,0.00046421017,0.00010130131,0.0002191026,0.00005926259,0.00051379466,0.000022957587,0.000118880365],"category_scores_gemma":[0.009009567,0.00015641682,0.00003400553,0.00040690065,0.000967911,0.000052557443,0.000106079635,0.00021191496,0.000052091986],"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":[0.00016284219,0.00018106229,0.00015218648,0.00006835621,0.00007364569,0.0000021596131,0.00391454,0.00007100596,0.0001766124,0.5014018,0.3040787,0.18971713],"study_design_scores_gemma":[0.00085621513,0.0008307693,0.0049588224,0.00012131153,0.0003899822,0.00002349551,0.06464148,0.0004954318,0.0016174063,0.9028283,0.022674074,0.00056273997],"about_ca_topic_score_codex":0.00041721907,"about_ca_topic_score_gemma":0.00014569462,"teacher_disagreement_score":0.4014265,"about_ca_system_score_codex":0.00016177396,"about_ca_system_score_gemma":0.0009270976,"threshold_uncertainty_score":0.999338},"labels":[],"label_agreement":null},{"id":"W1763804216","doi":"10.1198/0003130031072","title":"Statistics and Ethics","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of the North Atlantic","funders":"","keywords":"Advice (programming); Statistics; Work (physics); Sociology; Psychology; Computer science; Mathematics; Engineering","score_opus":0.2657415008978894,"score_gpt":0.4875637517411046,"score_spread":0.22182225084321522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1763804216","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":[0.009063623,0.0000688252,0.9832043,0.00090228365,0.00039150365,0.00019648005,0.00049424433,0.00008227874,0.0055964803],"genre_scores_gemma":[0.0758514,0.00018155409,0.9204137,0.0019789387,0.000045031153,0.000024287812,0.000009156599,0.00003398519,0.0014619606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998091,0.00095777295,0.0002497918,0.00019384577,0.00023465819,0.0002729739],"domain_scores_gemma":[0.9836054,0.015596124,0.0002543993,0.00032397587,0.00012442017,0.000095717376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013868281,0.00015115924,0.00026749828,0.00004867565,0.00027737793,0.00005463217,0.00013916499,0.000027500735,0.00014851043],"category_scores_gemma":[0.02085653,0.00010765349,0.000016633474,0.00019964158,0.00091485697,0.000019700881,0.000029161638,0.00034109756,0.000034431563],"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":[0.000009029926,0.000023639905,0.00030602777,0.000023814522,0.000022798855,0.0000045477755,0.0018216792,4.7444814e-7,0.000027869331,0.94230616,0.038181428,0.017272502],"study_design_scores_gemma":[0.0001377556,0.00009567642,0.006336242,0.000008752966,0.00007493922,0.000030763014,0.0050357524,0.00005941727,0.00009848327,0.9552973,0.032637034,0.00018792186],"about_ca_topic_score_codex":0.00009801687,"about_ca_topic_score_gemma":0.00008539726,"teacher_disagreement_score":0.06678778,"about_ca_system_score_codex":0.000026316844,"about_ca_system_score_gemma":0.00015032735,"threshold_uncertainty_score":0.98739123},"labels":[],"label_agreement":null},{"id":"W1965544836","doi":"10.1198/000313002753631321","title":"Thoughts on the Origins, Concepts, and Pedagogy of Statistics as a “Separate Discipline”","year":2002,"lang":"en","type":"article","venue":"The American Statistician","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 Manitoba","funders":"","keywords":"Discipline; Subject (documents); Field (mathematics); Statistics; Statistics education; Mathematics education; Sociology; Epistemology; Mathematics; Social science; Computer science; Library science; Philosophy","score_opus":0.18099864238006144,"score_gpt":0.48182816395389355,"score_spread":0.30082952157383214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965544836","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":[0.30948138,0.00046198955,0.65084046,0.012509718,0.0014726995,0.0016374837,0.0056601786,0.00020998692,0.0177261],"genre_scores_gemma":[0.74203444,0.00073737354,0.24900463,0.0020583675,0.00036378385,0.00008227293,0.000022837949,0.000065135784,0.005631147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813896,0.000652958,0.0003865373,0.00023042259,0.00030339544,0.00028774093],"domain_scores_gemma":[0.9845389,0.014213363,0.0005440027,0.00050391606,0.00011852361,0.00008127701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056308595,0.00020888759,0.00040852607,0.00005521243,0.00024184801,0.000042951826,0.00030038046,0.000021844844,0.00033776293],"category_scores_gemma":[0.004239709,0.00011490207,0.00003168831,0.00025054472,0.0014975588,0.000021809139,0.00006765951,0.00020534181,0.000093311115],"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":[0.00004514517,0.00008139226,0.000092357244,0.000025443387,0.00005311984,0.0000063898397,0.0048807305,0.0000032370508,0.000060390936,0.8852592,0.08501903,0.02447356],"study_design_scores_gemma":[0.00048681424,0.0009290472,0.0060958555,0.00006173665,0.00026800955,0.000037227986,0.018132856,0.00228465,0.0006916897,0.92428756,0.046278477,0.00044606373],"about_ca_topic_score_codex":0.00021802894,"about_ca_topic_score_gemma":0.000099255616,"teacher_disagreement_score":0.43255308,"about_ca_system_score_codex":0.000036707916,"about_ca_system_score_gemma":0.00006328618,"threshold_uncertainty_score":0.5517818},"labels":[],"label_agreement":null},{"id":"W1966264920","doi":"10.1198/000313008x269738","title":"Confidence Intervals for a Discrete Population Median","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","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":"HEC Montréal","funders":"","keywords":"Confidence interval; CDF-based nonparametric confidence interval; Robust confidence intervals; Statistics; Population; Confidence distribution; Confidence region; Statistic; Sign test; Mathematics; Credible interval; Sign (mathematics); Computer science; Medicine; Mann–Whitney U test; Wilcoxon signed-rank test","score_opus":0.5415881943883241,"score_gpt":0.581522353994503,"score_spread":0.039934159606178965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966264920","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":[0.016037963,0.00000951914,0.9797811,0.0016754714,0.00035238016,0.00081859395,0.0006053085,0.00010539451,0.0006142992],"genre_scores_gemma":[0.4084019,0.000017027469,0.5901673,0.0007966327,0.00027043995,0.0001155584,0.000007511937,0.000035419853,0.00018821518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732363,0.000769955,0.0008036396,0.0003331472,0.0003736427,0.00039595857],"domain_scores_gemma":[0.9370082,0.06155063,0.00064664177,0.0005223149,0.00012676045,0.00014544622],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016768596,0.0002031731,0.00072324823,0.000050861625,0.0002690107,0.0000274724,0.0004198055,0.000035815414,0.00012536542],"category_scores_gemma":[0.07583276,0.00013817128,0.00013233908,0.00025654002,0.0010467008,0.00004897544,0.00006866048,0.00018706915,0.00003665268],"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":[0.000405165,0.000075800635,0.0010113871,0.00006883101,0.00011815824,0.000024754016,0.00093752274,0.0000033486003,0.00011103748,0.915164,0.016599817,0.065480195],"study_design_scores_gemma":[0.00037340954,0.00034862358,0.01524994,0.000042031843,0.000102986276,0.000015355527,0.0001970076,0.0010557817,0.00008294741,0.9819951,0.00033478392,0.00020203728],"about_ca_topic_score_codex":0.00054466404,"about_ca_topic_score_gemma":0.00009604495,"teacher_disagreement_score":0.39236394,"about_ca_system_score_codex":0.000054587086,"about_ca_system_score_gemma":0.000046554484,"threshold_uncertainty_score":0.9319519},"labels":[],"label_agreement":null},{"id":"W1967757406","doi":"10.1198/tast.2009.0028","title":"Design Effect Caveats","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Water Quality and Resources Studies","field":"Environmental Science","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":"Statistics Canada","funders":"","keywords":"Simple (philosophy); Variance (accounting); Statistics; Computer science; Design of experiments; Econometrics; Mathematics; Economics; Epistemology","score_opus":0.0334271747039749,"score_gpt":0.26767573986853643,"score_spread":0.23424856516456152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967757406","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":[0.8572154,0.000064237196,0.10888619,0.0044004344,0.000088121364,0.00050967146,0.000017550063,0.00013540026,0.028683016],"genre_scores_gemma":[0.99388367,0.000010762955,0.003359348,0.0021716987,0.00003538678,0.0000061463193,0.0000011343845,0.000005394065,0.00052643445],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990434,0.00029557795,0.00009651491,0.00014469358,0.00018188305,0.00023793805],"domain_scores_gemma":[0.99941087,0.0002876607,0.00007227029,0.00018068236,0.0000019559147,0.000046589117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029189757,0.00009933006,0.00015284834,0.000009187614,0.00024234643,0.000019470197,0.00019794676,0.0000070842693,0.00013752576],"category_scores_gemma":[0.00003823555,0.000055356497,0.00002313588,0.00016487998,0.00059881725,0.000023887707,0.000048834077,0.00007291781,0.0006374442],"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":[0.00030904773,0.00011243323,0.010227378,0.0000059401164,0.000062077495,0.00007271884,0.010316006,0.004482415,0.007652356,0.00065405987,0.052554887,0.9135507],"study_design_scores_gemma":[0.0003583534,0.00271872,0.9683888,0.0000131262,0.000085540785,0.00001793027,0.00071236864,0.0013752176,0.0029953895,0.00897019,0.013910555,0.00045383972],"about_ca_topic_score_codex":0.0009560414,"about_ca_topic_score_gemma":0.000032138985,"teacher_disagreement_score":0.9581614,"about_ca_system_score_codex":0.00004102724,"about_ca_system_score_gemma":0.0000019112906,"threshold_uncertainty_score":0.8193268},"labels":[],"label_agreement":null},{"id":"W1978954330","doi":"10.1198/0003130043277","title":"Bootstrap Methods for Developing Predictive Models","year":2004,"lang":"en","type":"article","venue":"The American Statistician","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":620,"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; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Resampling; Feature selection; Model selection; Computer science; Statistics; Predictive modelling; Selection (genetic algorithm); Bootstrap aggregating; Variables; Machine learning; Econometrics; Artificial intelligence; Mathematics","score_opus":0.035676760719567685,"score_gpt":0.3619012094975819,"score_spread":0.32622444877801426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978954330","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":[0.021300796,0.000014972206,0.97305554,0.0011540405,0.000030432837,0.00016378847,0.000028482149,0.00003192077,0.0042200126],"genre_scores_gemma":[0.58783126,0.000009874397,0.41053098,0.0014706193,0.00002203521,0.000044317934,0.0000058831056,0.000008767274,0.000076245386],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99917406,0.000112441594,0.00014485537,0.00021198351,0.00009485089,0.0002618085],"domain_scores_gemma":[0.9993488,0.000294053,0.000120527686,0.00018258701,0.000007601126,0.000046441142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035531027,0.00010053569,0.0001815439,0.000020002632,0.00024740116,0.000011442105,0.00022385432,0.000016914079,0.0000697531],"category_scores_gemma":[0.0000680084,0.000071624,0.000048600148,0.0002776659,0.00071150303,0.00007993823,0.00005986656,0.000076882396,0.00006205683],"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":[0.0003372935,0.00010697625,0.001961472,0.000009118893,0.00037651183,0.000013253652,0.006941964,0.42910573,0.0022519953,0.08609217,0.0020733108,0.4707302],"study_design_scores_gemma":[0.00044034136,0.00036147586,0.021446496,0.000007424278,0.0002247071,0.000009034681,0.0008415794,0.12934993,0.001227286,0.8417782,0.0039727674,0.00034071572],"about_ca_topic_score_codex":0.0013826541,"about_ca_topic_score_gemma":0.00028557377,"teacher_disagreement_score":0.7556861,"about_ca_system_score_codex":0.000120164616,"about_ca_system_score_gemma":0.000024976789,"threshold_uncertainty_score":0.2920742},"labels":[],"label_agreement":null},{"id":"W1991138897","doi":"10.1198/tast.2009.0008","title":"Influence Measures for General Linear Models With Correlated Errors","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Inference","field":"Mathematics","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":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Generalized linear model; General linear model; Linear regression; Linear model; Mathematics; Hierarchical generalized linear model; Simple (philosophy); Proper linear model; Statistics; Log-linear model; Generalized linear mixed model; Standard error; Econometrics; Applied mathematics; Simple linear regression; Bayesian multivariate linear regression","score_opus":0.07501124733594747,"score_gpt":0.3786968497289507,"score_spread":0.30368560239300324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991138897","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":[0.16198407,0.00001243152,0.83608127,0.00037913743,0.000023383716,0.00036953695,0.00016641822,0.000078922596,0.00090485055],"genre_scores_gemma":[0.42235696,0.000006246213,0.57636064,0.0010705796,0.00004416514,0.000028732862,0.0000042774504,0.000019644207,0.0001087807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998592,0.00016292126,0.0003083499,0.000253698,0.00029345974,0.00038954613],"domain_scores_gemma":[0.99725544,0.0017501737,0.00027822738,0.00036427996,0.00023621196,0.00011566443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000365848,0.00020794521,0.00039767183,0.000042027597,0.00018616495,0.00003100085,0.0002817505,0.000025134545,0.000012278292],"category_scores_gemma":[0.0013071813,0.00012530155,0.000039405644,0.00028654517,0.00043644226,0.00005521751,0.00001703329,0.00017799163,0.000007437755],"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":[0.0003403199,0.00007235902,0.000068595495,0.000013387329,0.000051020423,0.000009463973,0.000608714,0.003532717,0.00031092874,0.8997861,0.0013697895,0.09383662],"study_design_scores_gemma":[0.00035926938,0.001160144,0.006354511,0.000041088562,0.00012442212,0.000010852802,0.00019744982,0.13574702,0.00014402765,0.85535425,0.00023153977,0.00027542858],"about_ca_topic_score_codex":0.00025077738,"about_ca_topic_score_gemma":0.0000357917,"teacher_disagreement_score":0.26037288,"about_ca_system_score_codex":0.000032439097,"about_ca_system_score_gemma":0.000074305375,"threshold_uncertainty_score":0.5109649},"labels":[],"label_agreement":null},{"id":"W2014058093","doi":"10.1198/000313006x89947","title":"The PDF of a Function of a Random Variable","year":2006,"lang":"en","type":"article","venue":"The American Statistician","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","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":"McGill University; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Probability density function; Random variable; Mathematics; Probability mass function; Variable (mathematics); Inverse function; Function (biology); Inverse; Analogy; Applied mathematics; Statistical physics; Statistics; Mathematical analysis; Geometry; Physics","score_opus":0.004906086841960577,"score_gpt":0.22151449896902503,"score_spread":0.21660841212706444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014058093","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":[0.0027055289,0.00009138419,0.9922117,0.00053517695,0.000043641317,0.000106952124,0.000018548168,0.000015400132,0.004271645],"genre_scores_gemma":[0.8937675,0.000023902625,0.10515629,0.00012518745,0.0000665935,0.00004166908,0.0000046447544,0.000004619945,0.00080959324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993964,0.00006759963,0.00018901155,0.000091565526,0.00014580427,0.00010962665],"domain_scores_gemma":[0.9987417,0.0005669383,0.00025688412,0.00034058423,0.00008030156,0.00001362931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022838044,0.000047742233,0.00010835043,0.00001836655,0.00016766411,0.000013862618,0.0003759758,0.0000051761676,0.000010186019],"category_scores_gemma":[0.000024060362,0.000027706315,0.000024867615,0.0004773068,0.00033845648,0.000042120933,0.000048537106,0.000041509622,0.0000150019605],"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":[0.000026578138,0.000048891816,0.00008031757,0.0000026982343,0.000015340931,1.8699455e-7,0.000050702656,0.00062006724,0.001119858,0.9366482,0.0047608768,0.056626275],"study_design_scores_gemma":[0.0009398217,0.00046884175,0.20863628,0.00001944913,0.00007172714,0.000008929263,0.0004052345,0.18780203,0.000532435,0.55899465,0.04190984,0.00021077666],"about_ca_topic_score_codex":0.0016471202,"about_ca_topic_score_gemma":0.000034368695,"teacher_disagreement_score":0.89106196,"about_ca_system_score_codex":0.000009311309,"about_ca_system_score_gemma":0.000050389473,"threshold_uncertainty_score":0.2489964},"labels":[],"label_agreement":null},{"id":"W2021098222","doi":"10.1198/tast.2011.11018","title":"Statistics in the News","year":2011,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","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":"University of Toronto; HEC Montréal","funders":"","keywords":"Mathematics education; Statistics education; Course (navigation); Information literacy; Computer science; Key (lock); Literacy; Data science; Statistics; Library science; Sociology; Mathematics; Pedagogy; Engineering","score_opus":0.3374795160313217,"score_gpt":0.4504248488064071,"score_spread":0.1129453327750854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021098222","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":[0.020578006,0.00003483518,0.95111173,0.0010711682,0.00054206076,0.00055212073,0.0006359494,0.00008737199,0.025386779],"genre_scores_gemma":[0.20565316,0.00006827898,0.7898271,0.0036374754,0.00009530348,0.00009318287,0.00001704031,0.00003373909,0.00057472906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801445,0.0008759946,0.00034684862,0.00018189507,0.00025267332,0.00032815273],"domain_scores_gemma":[0.9924728,0.006552,0.00030318156,0.0005614056,0.00006446422,0.000046094327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010413897,0.00015763627,0.00026579876,0.00007253021,0.00013208188,0.000035352597,0.0005676241,0.000016374725,0.00027707074],"category_scores_gemma":[0.0037250663,0.00008752365,0.00002785932,0.0004033585,0.00063232356,0.000025348423,0.000042764394,0.00023131365,0.00010209613],"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":[0.000040672,0.00011373152,0.0016530044,0.000012259634,0.00001937097,0.000024823821,0.014820233,3.7840718e-7,0.000007672984,0.81122386,0.11754048,0.05454349],"study_design_scores_gemma":[0.00014934239,0.00014572045,0.09006525,0.000008441894,0.000059820853,0.000018463781,0.025672384,0.00007485447,0.0000257111,0.87711215,0.0064928527,0.00017500373],"about_ca_topic_score_codex":0.002002371,"about_ca_topic_score_gemma":0.001282699,"teacher_disagreement_score":0.18507515,"about_ca_system_score_codex":0.000032615364,"about_ca_system_score_gemma":0.000082650426,"threshold_uncertainty_score":0.44595215},"labels":[],"label_agreement":null},{"id":"W2025559840","doi":"10.1198/tast.2010.09147","title":"Strategies for Pulling the Goalie in Hockey","year":2010,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":32,"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":"Ice hockey; League; Markov chain; Computer science; Bayesian probability; Estimation; Econometrics; Markov chain Monte Carlo; Operations research; Simulation; Engineering; Machine learning; Artificial intelligence; Mathematics; Economics; Physical medicine and rehabilitation; Management","score_opus":0.02623175888914076,"score_gpt":0.2618707400671466,"score_spread":0.23563898117800586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025559840","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":[0.9278842,0.00020806922,0.052454624,0.0033517627,0.0005464533,0.00037466438,0.0004897583,0.00002247607,0.014667995],"genre_scores_gemma":[0.99733806,0.000074937096,0.0012543553,0.0008755664,0.00016551251,0.000037348364,0.000009529449,0.000015311758,0.00022938641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992624,0.0000053040967,0.00029992094,0.00016276939,0.000025830823,0.00024380044],"domain_scores_gemma":[0.99919343,0.00017763954,0.0002924445,0.0002909714,0.000018233502,0.000027280073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005179642,0.000089497385,0.00021451271,0.00006049336,0.00015482496,0.00011107222,0.00028609845,0.000015015899,0.0001199801],"category_scores_gemma":[0.00005132392,0.000060710296,0.000042314598,0.00020876751,0.0002575447,0.00006437356,0.000020425234,0.00018697346,0.00006063538],"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":[0.000016619859,0.000017520002,0.021737222,0.00000568544,0.000015544003,0.0000013355665,0.0006842035,0.0006095543,0.00001762184,0.96860015,0.0015037779,0.0067907623],"study_design_scores_gemma":[0.00033520814,0.00014000197,0.3335536,0.000008004265,0.00001370788,0.0000037073567,0.0039316434,0.11388442,0.000014114767,0.3222334,0.22552893,0.00035324015],"about_ca_topic_score_codex":0.0035696046,"about_ca_topic_score_gemma":0.0033466907,"teacher_disagreement_score":0.6463668,"about_ca_system_score_codex":0.00001453995,"about_ca_system_score_gemma":0.000029060157,"threshold_uncertainty_score":0.5396198},"labels":[],"label_agreement":null},{"id":"W2030031047","doi":"10.1198/tast.2009.0001","title":"Splitting a Predictor at the Upper Quarter or Third and the Lower Quarter or Third","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":192,"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":"Quarter (Canadian coin); Mathematics; Statistics; Voting; Linear regression; Econometrics; Simple (philosophy); Regression analysis; Simple linear regression; Regression; Geography; Political science; Philosophy; Politics","score_opus":0.050893470110711776,"score_gpt":0.3687126660059382,"score_spread":0.31781919589522645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030031047","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":[0.9698534,0.000076903576,0.0039311782,0.020643791,0.00050797523,0.00052006496,0.00018389836,0.000064202344,0.004218561],"genre_scores_gemma":[0.98255074,0.000024723124,0.0014328706,0.011260589,0.0002780979,0.000025459249,0.0000025943864,0.000020694351,0.0044042366],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99634135,0.00066804554,0.0009057528,0.0006270954,0.0009257186,0.00053203973],"domain_scores_gemma":[0.98820627,0.009394536,0.0007418272,0.0013658706,0.00014927029,0.00014224056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034270543,0.00030700344,0.000622344,0.00009290566,0.00093489245,0.00079975557,0.0013471197,0.00004637711,0.00074777106],"category_scores_gemma":[0.0021160028,0.00010202258,0.0001555922,0.0006039458,0.0018233124,0.00018476177,0.00021803715,0.0003460881,0.00070803],"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":[0.0038592117,0.00013087432,0.0014920649,0.0000015258228,0.000048645576,0.00026335355,0.009308543,0.00002803225,0.000027372242,0.0025234704,0.24565999,0.7366569],"study_design_scores_gemma":[0.006421682,0.0075679747,0.32436997,0.00022017975,0.00075044704,0.0024125895,0.0972733,0.022441518,0.000042582524,0.32626477,0.2101112,0.0021237973],"about_ca_topic_score_codex":0.00029254166,"about_ca_topic_score_gemma":0.0006352388,"teacher_disagreement_score":0.73453313,"about_ca_system_score_codex":0.00006375643,"about_ca_system_score_gemma":0.00010503977,"threshold_uncertainty_score":0.91005296},"labels":[],"label_agreement":null},{"id":"W2033411871","doi":"10.1198/0003130031450","title":"Type I Error Inflation in the Presence of a Ceiling Effect","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":125,"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 Clinical Evaluative Sciences","funders":"","keywords":"Statistics; Ceiling (cloud); Econometrics; Statistical significance; Variables; Ceiling effect; Type I and type II errors; Mathematics; Standard error; Alcohol consumption; Variable (mathematics); Linear regression; Psychology; Medicine; Engineering; Biology; Alcohol","score_opus":0.09602044591037069,"score_gpt":0.43714101278193035,"score_spread":0.34112056687155967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033411871","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":[0.84511846,0.00002736659,0.14945863,0.0001083464,0.000037086884,0.00059947436,0.000011702774,0.00006431257,0.0045746104],"genre_scores_gemma":[0.9612555,0.000007696263,0.03856019,0.00010279504,0.000010474845,0.000030294448,0.0000012941189,0.000011936568,0.000019825859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987663,0.00054852566,0.00023122289,0.000101874226,0.00018947244,0.00016258682],"domain_scores_gemma":[0.9955008,0.0038180295,0.00027070843,0.00034429095,0.00005133187,0.000014813303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008896797,0.00009536771,0.00021322492,0.000044493016,0.000045060588,0.00000972187,0.00022356368,0.000013287327,0.00001592903],"category_scores_gemma":[0.0038017475,0.000054039127,0.000019329022,0.00047079803,0.0002885575,0.000046345667,0.000017893297,0.0001502585,0.0000051470715],"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":[0.000147515,0.00011157322,0.010418754,0.00011370801,0.00003161253,0.000017701568,0.008092303,0.00022015153,0.00779716,0.93554187,0.0010534199,0.036454216],"study_design_scores_gemma":[0.00027246567,0.0011740319,0.02410483,0.00014613388,0.00007346521,0.000015044214,0.0035254217,0.0015706086,0.011255934,0.9570352,0.00054158905,0.00028531702],"about_ca_topic_score_codex":0.00018716908,"about_ca_topic_score_gemma":0.00011713366,"teacher_disagreement_score":0.11613703,"about_ca_system_score_codex":0.000025117066,"about_ca_system_score_gemma":0.000031815198,"threshold_uncertainty_score":0.45513216},"labels":[],"label_agreement":null},{"id":"W2034554153","doi":"10.1198/000313001317098158","title":"The National Hockey League Entry Draft, 1969–1995","year":2001,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"League; Rank (graph theory); Championship; Statistics; Mathematics; Econometrics; Demographic economics; Operations research; Operations management; Advertising; Economics; Combinatorics; Business","score_opus":0.030208379675356126,"score_gpt":0.2569900151265436,"score_spread":0.2267816354511875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034554153","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":[0.5264875,0.002950374,0.031831447,0.019202797,0.0014676861,0.0005927299,0.0014772875,0.00013168225,0.41585845],"genre_scores_gemma":[0.98870987,0.0015558617,0.00023100554,0.0026729638,0.00036409832,0.000016995942,0.000018067405,0.000019789013,0.006411331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894464,0.000014054042,0.00040056033,0.00021841758,0.00009386523,0.00032843926],"domain_scores_gemma":[0.99895144,0.00022355227,0.00045182378,0.00025956432,0.000050230603,0.000063394735],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053486286,0.00012472308,0.00023049416,0.00006422918,0.00048194223,0.00012779211,0.00036220756,0.000016224292,0.0003618308],"category_scores_gemma":[0.00011759185,0.000087611894,0.00006494865,0.00034918974,0.00038958463,0.00006466509,0.000044217657,0.00015539773,0.0007848063],"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":[0.00006785384,0.00006641387,0.09950565,0.0000046851796,0.00013112936,0.000013107254,0.0005685096,0.0008143574,0.0000035776002,0.7983314,0.07063151,0.029861823],"study_design_scores_gemma":[0.0001492453,0.00006243236,0.22097823,0.0000041702915,0.0000075107832,0.000010372827,0.00025715484,0.017189642,0.0000023797654,0.029144488,0.7320065,0.00018786089],"about_ca_topic_score_codex":0.0018225261,"about_ca_topic_score_gemma":0.00036069128,"teacher_disagreement_score":0.7691869,"about_ca_system_score_codex":0.0000781916,"about_ca_system_score_gemma":0.000035369332,"threshold_uncertainty_score":0.9999932},"labels":[],"label_agreement":null},{"id":"W2040022986","doi":"10.1080/00031305.2000.10474518","title":"Late-Game Reversals in Professional Basketball, Football, and Hockey","year":2000,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","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":"Okanagan University College; Okanagan College","funders":"","keywords":"Basketball; League; Football; Ice hockey; Poisson distribution; Period (music); Probabilistic logic; American football; Econometrics; Psychology; Applied psychology; Statistics; Mathematics; Geography; Physical medicine and rehabilitation","score_opus":0.015896105304651912,"score_gpt":0.23767086419442127,"score_spread":0.22177475888976936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040022986","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":[0.9898606,0.00035946793,0.0001998586,0.0014509343,0.00012081658,0.00013521443,0.00021386295,0.000014693433,0.007644534],"genre_scores_gemma":[0.99236226,0.0009702028,0.00037563973,0.0017878029,0.00006563327,0.000012818872,0.000012809273,0.000016954455,0.0043958668],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990316,0.000017161903,0.0003765856,0.0002534768,0.000044016357,0.00027712618],"domain_scores_gemma":[0.9993855,0.00008196602,0.00022407684,0.00023195517,0.000010816443,0.00006570853],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031181128,0.00012143815,0.0003318049,0.000090728216,0.00008100046,0.00004296415,0.00017647601,0.00002267534,0.0014969535],"category_scores_gemma":[0.000027854834,0.00010175559,0.000028915323,0.00027720115,0.00023507494,0.00008923556,0.00003166456,0.0001577365,0.00027986168],"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":[0.00021212873,0.00017360254,0.72780627,0.000033330507,0.00008600661,0.000050372866,0.0029377246,0.00086304115,0.000013454048,0.12179136,0.011229692,0.134803],"study_design_scores_gemma":[0.0002999679,0.00009276803,0.8984141,0.000020818707,0.0000059624167,0.0000034360698,0.00028760932,0.0124502275,0.000002214141,0.01785808,0.07034013,0.00022472779],"about_ca_topic_score_codex":0.003122625,"about_ca_topic_score_gemma":0.00034917553,"teacher_disagreement_score":0.17060776,"about_ca_system_score_codex":0.00003997454,"about_ca_system_score_gemma":0.000020551015,"threshold_uncertainty_score":0.9994158},"labels":[],"label_agreement":null},{"id":"W2042412758","doi":"10.1198/000313008x303928","title":"Is the Overtime Period in an NHL Game Long Enough? An Example for Teaching Estimation and Hypothesis Testing in the Presence of Censored Data","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","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":"Royal Military College of Canada","funders":"","keywords":"Overtime; League; Estimation; Econometrics; Statistics; Computer science; Operations research; Psychology; Mathematics; Economics; Management; Labour economics","score_opus":0.16066606080385287,"score_gpt":0.30405033048356217,"score_spread":0.1433842696797093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042412758","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":[0.9886354,0.000115912415,0.009836302,0.0004819783,0.000016308091,0.0002799152,0.00043673968,0.000005573252,0.00019183765],"genre_scores_gemma":[0.9876812,0.00006134986,0.011762866,0.00037946756,0.000037908478,0.000017785169,0.000027579588,0.000014403199,0.00001745822],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99898094,0.000055616052,0.00040897695,0.00028486265,0.000057249636,0.000212384],"domain_scores_gemma":[0.99793947,0.00090314454,0.00041558986,0.0006963962,0.000019153007,0.00002625983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011774615,0.00010376747,0.00026704537,0.00008112637,0.0002060705,0.000057585694,0.00054707495,0.000014506268,0.00001390461],"category_scores_gemma":[0.000548505,0.000069509864,0.00001549295,0.00024398063,0.0003559438,0.00025808427,0.00005592671,0.00013165176,0.000001987152],"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":[0.00012695363,0.00030026943,0.7308013,0.0000631038,0.00004173245,0.000014731735,0.0832994,0.008095992,0.000048835904,0.0267904,0.00043311657,0.14998421],"study_design_scores_gemma":[0.00009849757,0.000095712196,0.51897717,0.00000983692,0.000005353662,0.0000054603966,0.0013918851,0.4768298,0.000002092537,0.0022695777,0.00024199889,0.00007263415],"about_ca_topic_score_codex":0.0204335,"about_ca_topic_score_gemma":0.0016743158,"teacher_disagreement_score":0.46873382,"about_ca_system_score_codex":0.000020120313,"about_ca_system_score_gemma":0.000022613855,"threshold_uncertainty_score":0.9860895},"labels":[],"label_agreement":null},{"id":"W2056003895","doi":"10.1198/0003130032431","title":"Detecting Dependence With Kendall Plots","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Plot (graphics); Copula (linguistics); Mathematics; Bivariate analysis; Curvature; Statistics; Scatter plot; Marginal distribution; Multivariate normal distribution; Multivariate statistics; Econometrics; Random variable; Geometry","score_opus":0.08951286293598788,"score_gpt":0.4099378926318419,"score_spread":0.320425029695854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056003895","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":[0.027841786,0.000017738414,0.96635723,0.00006992277,0.0000411274,0.00020338889,0.000042537427,0.00008784779,0.0053384495],"genre_scores_gemma":[0.4445409,0.0000050301305,0.554997,0.00024141915,0.00001863396,0.000020700125,4.459268e-7,0.000030530045,0.00014536004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839735,0.0003581275,0.00023919858,0.0002808796,0.00029711874,0.0004273328],"domain_scores_gemma":[0.99570084,0.0034333,0.0002710911,0.0003951038,0.000080404665,0.000119276025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048719664,0.00019077782,0.00032788588,0.000033089455,0.00024731387,0.000032203145,0.00019589455,0.000014569582,0.000053721073],"category_scores_gemma":[0.0024379008,0.00011697581,0.000027947412,0.00027259628,0.00044036223,0.00005200639,0.000026671018,0.0002317819,0.000018563802],"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":[0.000075302465,0.000048159785,0.00016512835,0.000023294351,0.000046609945,0.00006129463,0.00064160535,0.000070630194,0.00032096388,0.8572058,0.00016541022,0.14117578],"study_design_scores_gemma":[0.00030871943,0.00045576546,0.0008269056,0.00004132063,0.000101721445,0.000087222754,0.0020196608,0.0011608112,0.00078685564,0.9924668,0.0013819673,0.00036226984],"about_ca_topic_score_codex":0.00011024632,"about_ca_topic_score_gemma":0.00017940534,"teacher_disagreement_score":0.41669908,"about_ca_system_score_codex":0.000040431998,"about_ca_system_score_gemma":0.0000565092,"threshold_uncertainty_score":0.4770135},"labels":[],"label_agreement":null},{"id":"W2060343609","doi":"10.1198/000313007x188414","title":"Early Evidence-Based Medicine","year":2007,"lang":"en","type":"article","venue":"The American Statistician","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":5,"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":"Representativeness heuristic; Medical statistics; Statistician; Sample size determination; Population; Randomization; Sample (material); Statistics; History; Randomized controlled trial; Medicine; Demography; Mathematics; Sociology; Pathology","score_opus":0.21402363396248206,"score_gpt":0.46413807923223926,"score_spread":0.25011444526975724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060343609","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":[0.11160457,0.00007698969,0.87650084,0.005739371,0.00006792607,0.00035632474,0.000044182627,0.00009502977,0.005514785],"genre_scores_gemma":[0.94464993,0.000012940732,0.053253524,0.0015590984,0.00016586915,0.000015454645,0.000002670826,0.000023442864,0.00031705713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976629,0.00031516884,0.0004154965,0.00025226807,0.0007782074,0.00057593046],"domain_scores_gemma":[0.97655797,0.022305368,0.00018827047,0.00055116165,0.00017660843,0.000220648],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034279493,0.00015688846,0.00035372205,0.0000878401,0.00021151186,0.00002841025,0.00046419873,0.000022026006,0.00036559935],"category_scores_gemma":[0.016731635,0.000095188974,0.000042422434,0.00058255973,0.0021635538,0.000056147757,0.00005616286,0.0003109874,0.00011969675],"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":[0.0004993133,0.000089846355,0.0013878584,0.000074956835,0.000034274475,0.00008115197,0.0007366408,0.0000016154493,0.0003946988,0.78804946,0.009975994,0.19867422],"study_design_scores_gemma":[0.0003495598,0.0011846476,0.15608911,0.0001986286,0.000072733885,0.00000472752,0.0005943622,0.0007620209,0.00019808763,0.8388015,0.0015104779,0.00023415548],"about_ca_topic_score_codex":0.0019422972,"about_ca_topic_score_gemma":0.0004480593,"teacher_disagreement_score":0.83304536,"about_ca_system_score_codex":0.000098433564,"about_ca_system_score_gemma":0.00010527808,"threshold_uncertainty_score":0.99155086},"labels":[],"label_agreement":null},{"id":"W2064662029","doi":"10.1198/000313001317098239","title":"A Computer-Based Lab Supplement to Courses in Introductory Statistics","year":2001,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Frequentist inference; Computer science; Curriculum; Mathematics education; Simple (philosophy); Mathematics; Psychology; Artificial intelligence; Pedagogy; Bayesian probability; Bayesian inference","score_opus":0.11081841853754852,"score_gpt":0.43043444297623246,"score_spread":0.3196160244386839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064662029","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":[0.04128487,0.00001177931,0.95176804,0.004228474,0.00066350936,0.00048176333,0.0012514599,0.00008426626,0.000225861],"genre_scores_gemma":[0.10242634,0.000020718158,0.89314175,0.0035606064,0.0002722995,0.000090142086,0.00007303012,0.00004050891,0.00037460844],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978474,0.0005749532,0.00045722164,0.00031540063,0.00033322728,0.00047184713],"domain_scores_gemma":[0.99353033,0.0054036966,0.00026653428,0.000515965,0.00014537596,0.0001380828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087864575,0.00021883611,0.00042903927,0.00020140696,0.00011424673,0.000054192813,0.00036083118,0.000017018858,0.00040995557],"category_scores_gemma":[0.0022449591,0.00017390956,0.000027118876,0.0005701019,0.0003559645,0.000020633412,0.00007081447,0.00017805082,0.00009754147],"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":[0.00022949964,0.00040134124,0.0055026915,0.000048365528,0.00004538913,0.00007673356,0.0026923772,0.00041515895,0.00009645248,0.24561396,0.6193991,0.12547897],"study_design_scores_gemma":[0.0026047241,0.0025215398,0.24176174,0.00017769085,0.0003009365,0.00005825658,0.015948435,0.0129727125,0.0004482029,0.40317187,0.31817228,0.001861617],"about_ca_topic_score_codex":0.0008001318,"about_ca_topic_score_gemma":0.0013804443,"teacher_disagreement_score":0.30122676,"about_ca_system_score_codex":0.00016149925,"about_ca_system_score_gemma":0.00020903288,"threshold_uncertainty_score":0.7091826},"labels":[],"label_agreement":null},{"id":"W2071800806","doi":"10.1080/00031305.2012.755361","title":"A Few Counter Examples Useful in Teaching Central Limit Theorems","year":2012,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Distribution Estimation and Applications","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":"University of Alberta","funders":"","keywords":"Mathematics; Sequence (biology); Limit (mathematics); Convergence (economics); Probabilistic logic; Central limit theorem; Distribution (mathematics); Convergence of random variables; Weak convergence; Applied mathematics; Random variable; Calculus (dental); Mathematical economics; Statistics; Mathematical analysis; Computer science","score_opus":0.0851317892525428,"score_gpt":0.38904536796119393,"score_spread":0.3039135787086511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071800806","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":[0.20312467,0.000021597805,0.78933835,0.0009914027,0.000072338706,0.0003130842,0.00058625865,0.00009631017,0.005456004],"genre_scores_gemma":[0.97392213,0.00000664883,0.02479487,0.0008956198,0.000111527435,0.00007228233,0.000058022433,0.000023692719,0.000115177754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984808,0.0002573468,0.00033998856,0.00015596113,0.00023450892,0.0005314106],"domain_scores_gemma":[0.9971554,0.0021323003,0.00021102694,0.00031759762,0.000034682573,0.00014893818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005037866,0.00015525315,0.0002476433,0.000049313334,0.00019282938,0.00004936683,0.00022150492,0.000019058763,0.00029654722],"category_scores_gemma":[0.0012080545,0.0001129351,0.00003847733,0.00023427136,0.0004090429,0.00008712054,0.000043037784,0.0002462469,0.00014177176],"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":[0.000015482789,0.00016558143,0.005485751,0.000009832023,0.000013841868,0.0000012390211,0.0015249541,0.0000039223646,0.000041310017,0.9739381,0.0061388384,0.012661168],"study_design_scores_gemma":[0.00037865518,0.0000578318,0.72083414,0.000045354685,0.00008039347,0.000016716418,0.0037503883,0.0033984152,0.000039033366,0.25489572,0.016133014,0.0003703306],"about_ca_topic_score_codex":0.00041342466,"about_ca_topic_score_gemma":0.00011866726,"teacher_disagreement_score":0.7707975,"about_ca_system_score_codex":0.00011009342,"about_ca_system_score_gemma":0.000029562076,"threshold_uncertainty_score":0.46053597},"labels":[],"label_agreement":null},{"id":"W2085360857","doi":"10.1198/tas.2011.11077","title":"An Overview of Current Software Procedures for Fitting Linear Mixed Models","year":2011,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":67,"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 of Aging","funders":"National Institute on Aging","keywords":"Current (fluid); Software; Computer science; Statistics; Econometrics; Data science; Mathematics; Engineering; Programming language","score_opus":0.3300457036600927,"score_gpt":0.4672241114054354,"score_spread":0.13717840774534268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085360857","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":[0.0059485785,0.0001694461,0.99249494,0.000017435836,0.000084184765,0.00042794595,0.0006573513,0.00006201707,0.00013808245],"genre_scores_gemma":[0.12880097,0.00005744712,0.8708528,0.00009425575,0.00006772394,0.00007858867,0.000008629699,0.000034471657,0.000005068948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998547,0.00022734723,0.00045856892,0.0002452597,0.0002078968,0.00031393344],"domain_scores_gemma":[0.99631816,0.0024354833,0.0005187125,0.00041666816,0.00020893416,0.00010206414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005040065,0.00018303333,0.0004795519,0.0000453025,0.00011687584,0.000013621248,0.0003690998,0.000019776604,0.000049381608],"category_scores_gemma":[0.0027467452,0.00012514066,0.00007024264,0.00019965455,0.00039158764,0.000066836445,0.000043983637,0.000120053395,0.0000028532263],"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":[0.00007025249,0.00014338382,0.00013023525,0.0004005578,0.000025696663,9.692537e-7,0.0013692365,0.0000020299778,0.000039786715,0.6539303,0.00040410226,0.34348345],"study_design_scores_gemma":[0.00015218247,0.00045551217,0.002101716,0.00016748164,0.0001211653,0.000002159537,0.00057611504,0.012474088,0.0003332759,0.9833855,0.000045288332,0.00018551231],"about_ca_topic_score_codex":0.00016341615,"about_ca_topic_score_gemma":0.00005196844,"teacher_disagreement_score":0.34329793,"about_ca_system_score_codex":0.000016394239,"about_ca_system_score_gemma":0.00010443339,"threshold_uncertainty_score":0.5103088},"labels":[],"label_agreement":null},{"id":"W2094806835","doi":"10.1198/tast.2009.08042","title":"Teaching Variation Reduction Using a Virtual Manufacturing Environment","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Design Education and Practice","field":"Engineering","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":"Login; Process (computing); Variation (astronomy); Computer science; Software; Plan (archaeology); Reduction (mathematics); Software engineering; Manufacturing engineering; Engineering; Operating system; Mathematics","score_opus":0.013882766518984511,"score_gpt":0.2648116070288507,"score_spread":0.2509288405098662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094806835","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":[0.3461048,0.00002043271,0.6496926,0.0005950641,0.00029028358,0.00012629217,0.000008112236,0.00015387718,0.0030085645],"genre_scores_gemma":[0.9827299,0.000018324168,0.016603163,0.00028311927,0.00022065906,0.0000033554816,0.0000055769888,0.000015605943,0.00012029776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999354,0.00011331901,0.00013936241,0.000103846534,0.00012931609,0.00016014947],"domain_scores_gemma":[0.9995998,0.00009489963,0.00008845273,0.00016823137,0.0000045441475,0.000044040058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002187235,0.00009807669,0.00009587894,0.00005053844,0.00016404002,0.00004494515,0.000085643274,0.000011169994,0.000059477465],"category_scores_gemma":[0.000022949289,0.00008669691,0.000016912256,0.000054702454,0.000039690898,0.00013559763,0.0000056319627,0.00018618214,0.000061891726],"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":[0.000031899246,0.000053070416,0.0000063853977,0.0000051747134,0.000045986082,0.0000034872419,0.0055409134,0.096231274,0.041784886,0.005364291,0.0010354707,0.84989715],"study_design_scores_gemma":[0.0009850154,0.0011287417,0.22376455,0.00008799328,0.0006307621,0.0003991416,0.018609721,0.62613726,0.01330736,0.016946375,0.095838085,0.0021649837],"about_ca_topic_score_codex":0.00026792698,"about_ca_topic_score_gemma":0.000001156455,"teacher_disagreement_score":0.8477322,"about_ca_system_score_codex":0.00013643119,"about_ca_system_score_gemma":0.00001111784,"threshold_uncertainty_score":0.35353974},"labels":[],"label_agreement":null},{"id":"W2101508305","doi":"10.1198/000313008x269602","title":"Student's<i>z</i>,<i>t</i>, and<i>s</i>","year":2008,"lang":"he","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","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":"McGill University","funders":"","keywords":"Statistic; Documentation; Rework; Mathematics education; Mathematics; Work (physics); Calculus (dental); Statistics; Computer science; Engineering","score_opus":0.1477300252802811,"score_gpt":0.4293276293051706,"score_spread":0.28159760402488954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101508305","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":[0.7160688,0.004045756,0.22659561,0.010954452,0.0052103535,0.0023362732,0.0036116508,0.0005612127,0.0306159],"genre_scores_gemma":[0.6771259,0.009399987,0.28714988,0.009614871,0.00086409174,0.00010177509,0.00003980842,0.0001776286,0.015526104],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99652916,0.0011117606,0.00065397203,0.0004885315,0.0005519982,0.0006645781],"domain_scores_gemma":[0.9895038,0.008475929,0.0007652024,0.00081883016,0.00018476856,0.00025144755],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0009316673,0.00042814857,0.00081117684,0.000110215806,0.00083398324,0.00009715475,0.0005421583,0.000048207396,0.00035211572],"category_scores_gemma":[0.0027530666,0.00031580354,0.00008298441,0.00051945023,0.0034795962,0.000051714924,0.0002443126,0.00044550883,0.00047909125],"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":[0.00020262743,0.00060456526,0.011510122,0.00019992243,0.00049178605,0.00023878507,0.03970823,0.0000049464115,0.00028709308,0.25357664,0.609801,0.08337429],"study_design_scores_gemma":[0.0019459848,0.0016516472,0.54556763,0.00019759909,0.0014805788,0.0011766595,0.06753068,0.00036671245,0.00043398942,0.14958781,0.22787242,0.0021882856],"about_ca_topic_score_codex":0.00058557827,"about_ca_topic_score_gemma":0.00007447587,"teacher_disagreement_score":0.5340575,"about_ca_system_score_codex":0.00007936099,"about_ca_system_score_gemma":0.00026638317,"threshold_uncertainty_score":0.9999294},"labels":[],"label_agreement":null},{"id":"W2105139890","doi":"10.1080/00031305.2000.10474533","title":"Dawson, K. S., Gennings, C., and Carter, W. H. (1997), “Two Graphical Techniques Useful in Detecting Correlation Structure in Repeated Measures Data,” <i>The American Statistician</i> , 51, 275–283: Comment by Keselman, Algina, and Kowalchuk","year":2000,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","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":"University of Manitoba","funders":"","keywords":"Statistician; Correlation; Statistics; Statistical graphics; Mathematics; Computer science; Graphics; Computer graphics (images)","score_opus":0.04792635438704322,"score_gpt":0.3800085704919814,"score_spread":0.33208221610493815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105139890","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":[0.35283288,0.00033116274,0.64157224,0.0014486724,0.00004508443,0.0009853811,0.0025825896,0.000120640136,0.00008133998],"genre_scores_gemma":[0.75502735,0.0005143649,0.24241887,0.0016828198,0.00005483528,0.00006344168,0.00013627128,0.00007669116,0.00002536597],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99581254,0.0012796596,0.0008802497,0.0008214672,0.0004935382,0.00071252155],"domain_scores_gemma":[0.99403214,0.004179538,0.00065024116,0.0008714517,0.000082949526,0.00018365387],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013240513,0.00047205994,0.0009132491,0.00015333737,0.00032902733,0.00011815045,0.0004959301,0.00005667688,0.000019847641],"category_scores_gemma":[0.0012465649,0.00034045996,0.000029813442,0.0007885029,0.00168107,0.00016917747,0.00018024244,0.0008288262,0.0000011293538],"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":[0.0004638846,0.00012654606,0.0073285154,0.000060827293,0.000080146136,0.00008029159,0.0029299415,0.00008382257,0.0012004984,0.009380151,0.003822727,0.97444266],"study_design_scores_gemma":[0.003577286,0.0024123068,0.09487478,0.00072407105,0.0007867705,0.000290305,0.008945993,0.11415245,0.00079415494,0.7504874,0.02008778,0.0028667005],"about_ca_topic_score_codex":0.0062638153,"about_ca_topic_score_gemma":0.0048221457,"teacher_disagreement_score":0.971576,"about_ca_system_score_codex":0.000116474104,"about_ca_system_score_gemma":0.00004498856,"threshold_uncertainty_score":0.99990475},"labels":[],"label_agreement":null},{"id":"W2129813332","doi":"10.1080/00031305.2014.904250","title":"On a Simple Construction of a Bivariate Probability Function With a Common Marginal","year":2014,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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":"Université de Sherbrooke","funders":"","keywords":"Bivariate analysis; Simple (philosophy); Mathematics; Statistics; Econometrics; Function (biology); Biology","score_opus":0.009802170898168941,"score_gpt":0.2512180360990115,"score_spread":0.24141586520084257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129813332","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":[0.05920851,0.0000018200562,0.9382883,0.000351201,0.000051872074,0.0001563055,0.000011057928,0.000043751963,0.0018872105],"genre_scores_gemma":[0.5726255,5.1671344e-7,0.4269993,0.00033876367,0.0000167887,0.0000086859945,0.0000012827384,0.000004329223,0.000004821723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99878305,0.00044801563,0.00016727932,0.00023307417,0.00019734712,0.00017124624],"domain_scores_gemma":[0.99866515,0.000415527,0.00028516,0.00052166503,0.00006325087,0.00004927103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004942711,0.000107814434,0.0002347513,0.000046769088,0.00009903138,0.000032593405,0.00027749123,0.0000118371945,0.000006099558],"category_scores_gemma":[0.00005796387,0.00006584241,0.00002532908,0.00036259845,0.00040060584,0.000063695836,0.000042874035,0.000111194444,0.0000041376975],"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":[0.00012005097,0.000025086583,0.00022067365,0.000006991475,0.000011404668,5.501463e-7,0.00013142206,0.000028612661,0.00008114501,0.67228264,0.00006594848,0.32702547],"study_design_scores_gemma":[0.0002584222,0.0017517661,0.029782554,0.000017444712,0.00002897906,0.00001502242,0.000028107032,0.030610034,0.00013434465,0.9369582,0.00028966146,0.0001254663],"about_ca_topic_score_codex":0.0005425708,"about_ca_topic_score_gemma":0.000073202194,"teacher_disagreement_score":0.513417,"about_ca_system_score_codex":0.000021884525,"about_ca_system_score_gemma":0.000041152674,"threshold_uncertainty_score":0.26849756},"labels":[],"label_agreement":null},{"id":"W2140541004","doi":"10.1198/tas.2009.0033","title":"The History of the Cluster Heat Map","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":925,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Engineers Without Borders Canada","funders":"","keywords":"Row; Row and column spaces; Column (typography); Cluster (spacecraft); Computer science; TRACE (psycholinguistics); Matrix (chemical analysis); Tile; Hierarchical clustering; Computer graphics (images); Combinatorics; Data mining; Mathematics; Cluster analysis; Geometry; Artificial intelligence; Geography; Database; Archaeology; Materials science; Connection (principal bundle)","score_opus":0.005116835551283146,"score_gpt":0.21905727621224458,"score_spread":0.21394044066096143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140541004","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":[0.60002273,0.023530977,0.16937089,0.07629038,0.009798353,0.0035405306,0.0005658375,0.00009010654,0.11679018],"genre_scores_gemma":[0.987464,0.00013552679,0.0005971574,0.007498018,0.00018919693,0.0000050098943,0.000010147299,0.000009503649,0.004091408],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936986,0.000075762815,0.00018229002,0.000087585315,0.00010045135,0.0001840743],"domain_scores_gemma":[0.9992398,0.00004806358,0.00014952404,0.00050067966,0.00003321939,0.00002872316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019160494,0.00008852927,0.00010174073,0.0000061503088,0.00012277506,0.000010481844,0.00039086016,0.000020632215,0.000005420447],"category_scores_gemma":[0.000027227994,0.0000417112,0.000061491985,0.00004590178,0.0005840715,0.0000010402024,0.00007252309,0.000089917645,0.000006781129],"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":[0.00020559767,0.00004148287,0.00020005024,0.00000946761,0.00009427833,6.823669e-7,0.0008129307,0.00035323703,0.015769755,0.006350104,0.774787,0.20137538],"study_design_scores_gemma":[0.00027957777,0.00046948908,0.01604708,0.000012880061,0.00004855726,0.000009678674,0.0005410399,0.0021091406,0.00078784965,0.0033734099,0.97613585,0.00018545172],"about_ca_topic_score_codex":0.00008356035,"about_ca_topic_score_gemma":0.00008709664,"teacher_disagreement_score":0.38744128,"about_ca_system_score_codex":0.000031271233,"about_ca_system_score_gemma":0.00008130173,"threshold_uncertainty_score":0.21520358},"labels":[],"label_agreement":null},{"id":"W2148939588","doi":"10.1198/tast.2009.0012","title":"Where's Waldo? Visualizing Collinearity Diagnostics","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Engineers Without Borders Canada","funders":"","keywords":"Collinearity; Biplot; Salient; Computer science; Rank (graph theory); Statistics; Software; Simple (philosophy); Matrix (chemical analysis); Data mining; Mathematics; Pattern recognition (psychology); Artificial intelligence; Combinatorics; Programming language","score_opus":0.09706303419290631,"score_gpt":0.46706704157905027,"score_spread":0.370004007386144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148939588","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":[0.007438352,0.00012699307,0.9879232,0.001309027,0.000092774186,0.00029812605,0.00021085185,0.00013962503,0.0024610702],"genre_scores_gemma":[0.18922737,0.00032135978,0.8076728,0.0022558589,0.00019290682,0.00001894375,0.00000691523,0.00003798621,0.0002658602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812263,0.00032046222,0.00041059835,0.0003022756,0.0003446245,0.00049940374],"domain_scores_gemma":[0.99334294,0.0055756057,0.00032144188,0.0004737459,0.00011829742,0.00016794771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050816487,0.00023840934,0.0004978385,0.00004323236,0.0002903626,0.000057603498,0.00030714952,0.000028150262,0.00005602451],"category_scores_gemma":[0.003567367,0.00017022168,0.00006298516,0.00034056397,0.0004272332,0.00005827015,0.000048766815,0.00027768678,0.00003224202],"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":[0.00005303482,0.00012626892,0.0000537607,0.000018946756,0.000023243041,0.000042066815,0.00039310544,0.000021256723,0.00016343941,0.7685071,0.008715265,0.22188249],"study_design_scores_gemma":[0.0002340948,0.00047931063,0.0032275037,0.000049044804,0.000103780585,0.000011136583,0.00046695545,0.005068413,0.00011151888,0.98365325,0.006279771,0.0003152519],"about_ca_topic_score_codex":0.00012872278,"about_ca_topic_score_gemma":0.0000790883,"teacher_disagreement_score":0.22156724,"about_ca_system_score_codex":0.0000617323,"about_ca_system_score_gemma":0.000046628204,"threshold_uncertainty_score":0.6941439},"labels":[],"label_agreement":null},{"id":"W2155808502","doi":"10.1080/00031305.2012.703888","title":"On the Boundedness and Nonmonotonicity of Generalized Score Statistics","year":2012,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","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":"Dalhousie University","funders":"","keywords":"Score; Statistic; Mathematics; Estimator; Bounded function; Statistics; Sufficient statistic; Context (archaeology); Variance (accounting); Applied mathematics","score_opus":0.1361649711648581,"score_gpt":0.42270008412837445,"score_spread":0.28653511296351636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155808502","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":[0.17685226,0.00004405849,0.8211157,0.00023204964,0.00008442812,0.00030012467,0.00069959386,0.000020321422,0.00065150025],"genre_scores_gemma":[0.5788959,0.00003599197,0.4202151,0.0006592989,0.000050756167,0.000031035124,0.000004276075,0.000027991857,0.00007960987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982811,0.000471443,0.00035433972,0.00017487217,0.00030328037,0.00041491535],"domain_scores_gemma":[0.99009746,0.008815326,0.0004165503,0.00046172118,0.00008242475,0.00012650057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081964984,0.00020029132,0.00044336604,0.0000316421,0.00023840825,0.000022750626,0.00022352027,0.00002047096,0.00006848959],"category_scores_gemma":[0.0022804718,0.00010798726,0.000033971828,0.00017056262,0.0012524888,0.000044315006,0.00008359148,0.00020527357,0.0000065489085],"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":[0.00008717675,0.000077038276,0.00016329672,0.000027492491,0.000039625585,0.0000015932379,0.0007151524,0.0000072364255,0.00015331278,0.9683822,0.0016941058,0.028651772],"study_design_scores_gemma":[0.00020707086,0.00019714636,0.0048118955,0.000025171428,0.000108265944,0.0000058665896,0.0005343536,0.0020703962,0.0002722452,0.9911952,0.00039441296,0.00017794812],"about_ca_topic_score_codex":0.00022038649,"about_ca_topic_score_gemma":0.000036490088,"teacher_disagreement_score":0.40204367,"about_ca_system_score_codex":0.000032128442,"about_ca_system_score_gemma":0.000033843316,"threshold_uncertainty_score":0.46148473},"labels":[],"label_agreement":null},{"id":"W2158029818","doi":"10.1198/tast.2011.09217","title":"Previously Unrecognized Links Between Statistical Dependence and Some Common Modes of Convergence","year":2011,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","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":"McGill University","funders":"","keywords":"Convergence (economics); Mathematics; Convergence of random variables; Limit (mathematics); Probability distribution; Heuristics; Sequence (biology); Simple (philosophy); Random variable; Square (algebra); Statistical physics; Statistics; Applied mathematics; Mathematical optimization; Physics; Mathematical analysis","score_opus":0.2646631902177337,"score_gpt":0.4282702303060795,"score_spread":0.1636070400883458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158029818","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":[0.42203486,0.00009370125,0.5751437,0.00010345885,0.00015863948,0.000395738,0.0009658998,0.00007580695,0.0010282145],"genre_scores_gemma":[0.65927315,0.00012237721,0.34029868,0.00014948357,0.000033060154,0.000020289383,0.000012044163,0.000019365923,0.00007154128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99805874,0.00060759054,0.000511147,0.00025612948,0.00024668738,0.00031973136],"domain_scores_gemma":[0.99060905,0.008226311,0.00053496636,0.0003847857,0.000108308916,0.00013656134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085484586,0.00019219646,0.0005987991,0.00006786198,0.00011176476,0.000017271277,0.0003260277,0.00004839241,0.00017337945],"category_scores_gemma":[0.0031578797,0.00014249458,0.000030646024,0.00016671987,0.0014235144,0.000055150213,0.00010315463,0.0002816951,0.00001813202],"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":[0.00017912786,0.00012884857,0.021354036,0.00018772804,0.00015633716,0.000011538938,0.006852224,5.240498e-7,0.00030179435,0.81974274,0.0029126455,0.14817248],"study_design_scores_gemma":[0.00026763894,0.00034342252,0.12632781,0.000045902238,0.00027429467,0.000009668348,0.0034677363,0.00028830956,0.0022346373,0.8664107,0.00007592447,0.00025399693],"about_ca_topic_score_codex":0.0010966879,"about_ca_topic_score_gemma":0.00008003973,"teacher_disagreement_score":0.23723829,"about_ca_system_score_codex":0.000022074404,"about_ca_system_score_gemma":0.000099996396,"threshold_uncertainty_score":0.581076},"labels":[],"label_agreement":null},{"id":"W2158803120","doi":"10.1198/000313008x298439","title":"Survival Analysis","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Petro-Canada","funders":"","keywords":"Observational study; Econometrics; Mistake; Proportional hazards model; Estimator; Survival analysis; Psychology; Statistics; Mathematics","score_opus":0.10385345694741992,"score_gpt":0.377329843071578,"score_spread":0.2734763861241581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158803120","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":[0.94649196,0.000089426096,0.036034837,0.001211302,0.000053149743,0.00010069731,0.000043209744,0.000057071313,0.015918346],"genre_scores_gemma":[0.9928552,0.000054956276,0.0038133406,0.0025838416,0.00011545615,0.0000053558933,0.000016788837,0.000008071053,0.00054700347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991205,0.000055331562,0.0001428028,0.00014482843,0.00032196566,0.00021457138],"domain_scores_gemma":[0.9993124,0.00012902285,0.00010247192,0.0002885885,0.00006806918,0.00009941902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012950876,0.00008383369,0.00032699155,0.00007362119,0.0001558511,0.000006980139,0.00010485009,0.000007988484,0.00016249955],"category_scores_gemma":[0.00009867788,0.000055100274,0.00009459106,0.001076865,0.0004570591,0.000021831736,0.00002205423,0.000104257204,0.0000858922],"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":[0.00059903925,0.000070025984,0.91868985,0.000008207255,0.0016135232,0.0008793333,0.0014368665,0.00022746841,0.00035774006,0.0040077637,0.017248906,0.05486127],"study_design_scores_gemma":[0.00014956671,0.00020625892,0.9942286,0.000004500416,0.0006585315,0.000058005935,0.00083853444,0.00061982713,0.000029382367,0.00010313788,0.0030225397,0.000081102735],"about_ca_topic_score_codex":0.004665972,"about_ca_topic_score_gemma":0.00034162923,"teacher_disagreement_score":0.075538754,"about_ca_system_score_codex":0.000042388358,"about_ca_system_score_gemma":0.0000728468,"threshold_uncertainty_score":0.70535856},"labels":[],"label_agreement":null},{"id":"W2159445569","doi":"10.1198/0003130032369","title":"Raindrop Plots","year":2003,"lang":"en","type":"article","venue":"The American Statistician","topic":"Forest ecology and management","field":"Environmental Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Izaak Walton Killam Health Centre","funders":"","keywords":"Mathematics; Plot (graphics); Statistics; Cutoff; Range (aeronautics); Coverage probability; Normality; Confidence interval; Dimension (graph theory); Likelihood function; Maximum likelihood; Combinatorics; Physics","score_opus":0.006542340120135166,"score_gpt":0.23156176776362986,"score_spread":0.2250194276434947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159445569","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":[0.5227514,0.000014350269,0.07281795,0.0015059984,0.0002640705,0.00039150252,0.00001520788,0.00009415776,0.40214536],"genre_scores_gemma":[0.9911212,0.0000064066962,0.003542986,0.002966201,0.000008634387,0.00001605867,0.0000011956379,0.0000078045605,0.0023295283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99937177,0.000105846455,0.000077771794,0.0001286981,0.000105822175,0.0002101234],"domain_scores_gemma":[0.9996072,0.00008668446,0.00006727582,0.00019517733,0.0000016159399,0.000042025968],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018247703,0.000065299646,0.00008183591,0.00000987076,0.00015030058,0.000008747064,0.00015509395,0.0000063002,0.002611182],"category_scores_gemma":[0.000074584816,0.000045152563,0.000014939254,0.0001682067,0.0006956737,0.000025959864,0.00005265533,0.000059401187,0.0025090233],"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":[0.00004103022,0.0001529381,0.040024135,0.0000037313082,0.000059258888,0.000088812296,0.0015787184,0.0013283114,0.00023663875,0.70061153,0.19789313,0.05798177],"study_design_scores_gemma":[0.00017121722,0.00020536811,0.71638054,0.0000014971034,0.00002855496,0.000009652042,0.0005520287,0.00022530569,0.00007333146,0.062067002,0.22010368,0.0001818254],"about_ca_topic_score_codex":0.00056314707,"about_ca_topic_score_gemma":0.00049775164,"teacher_disagreement_score":0.6763564,"about_ca_system_score_codex":0.000043890795,"about_ca_system_score_gemma":0.0000045582183,"threshold_uncertainty_score":0.99830055},"labels":[],"label_agreement":null},{"id":"W2614013743","doi":"10.1080/00031305.2018.1459315","title":"Simple Measures of Individual Cluster-Membership Certainty for Hard Partitional Clustering","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simple (philosophy); Cluster (spacecraft); Cluster analysis; Mathematics; Certainty; Econometrics; Statistics; Computer science; Philosophy; Epistemology","score_opus":0.07860951827381393,"score_gpt":0.33514756504687654,"score_spread":0.2565380467730626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614013743","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":[0.004583224,0.000014739172,0.9932465,0.0007873701,0.0001559372,0.0002375694,0.00018618812,0.000044368557,0.00074411085],"genre_scores_gemma":[0.53527075,0.0000014170022,0.46313074,0.0013576833,0.00016560941,0.000025687084,0.000007043264,0.00000917378,0.00003188822],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853355,0.0002621711,0.00026998174,0.00027269518,0.0003251782,0.00033643137],"domain_scores_gemma":[0.9982967,0.0007203399,0.0002762167,0.00044240043,0.00017869016,0.00008566432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097247295,0.00013447419,0.000263083,0.000058769587,0.00020610809,0.00007880863,0.00082801015,0.000019851346,0.000018791286],"category_scores_gemma":[0.00020710762,0.000099265024,0.00006830096,0.00025866958,0.00055607565,0.00010013545,0.00018402512,0.00008262629,0.0000067628785],"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":[0.00015472523,0.00005784723,0.00024239915,0.000033403503,0.000119746255,0.0000021389612,0.0038214917,0.000088534776,0.00069430546,0.28449425,0.014631437,0.69565976],"study_design_scores_gemma":[0.0012451089,0.0019983447,0.037733957,0.00006376797,0.00015187876,0.00003101851,0.0005653207,0.22243766,0.0036291075,0.71727884,0.014110774,0.00075419195],"about_ca_topic_score_codex":0.0001747403,"about_ca_topic_score_gemma":0.00019098756,"teacher_disagreement_score":0.6949055,"about_ca_system_score_codex":0.000022168451,"about_ca_system_score_gemma":0.000082638006,"threshold_uncertainty_score":0.40479103},"labels":[],"label_agreement":null},{"id":"W2752232660","doi":"10.1080/00031305.2017.1395365","title":"Modeling Offensive Player Movement in Professional Basketball","year":2017,"lang":"en","type":"article","venue":"The American Statistician","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Offensive; Basketball; League; Computer science; Leverage (statistics); Movement (music); Ball (mathematics); Human–computer interaction; Artificial intelligence; Operations research; Mathematics; Geography","score_opus":0.04584094132041121,"score_gpt":0.28439502209581446,"score_spread":0.23855408077540324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752232660","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":[0.97179455,0.0001235097,0.009325729,0.0024049734,0.0005879548,0.00019484216,0.00025349087,0.000010879496,0.015304068],"genre_scores_gemma":[0.9955748,0.00011048925,0.00048418797,0.0020702227,0.00009440031,0.000016739454,0.000007804804,0.000014882648,0.0016264829],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999107,0.000007808982,0.00035349122,0.00022415574,0.00005007144,0.00025744384],"domain_scores_gemma":[0.9989736,0.00003278491,0.00043896603,0.00048215687,0.000025861995,0.00004662149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036917577,0.00010635045,0.000287844,0.000073434225,0.00030568053,0.00008530808,0.0003592271,0.00001545496,0.00023195993],"category_scores_gemma":[0.00007621038,0.00008789454,0.000037766633,0.0000569175,0.00016314603,0.00007509419,0.00009143246,0.0001449983,0.00016095977],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001229002,0.00016732975,0.36929113,0.000023083727,0.000094297946,0.000050859708,0.0019227838,0.02889037,0.000013763956,0.5797459,0.005690162,0.0139874425],"study_design_scores_gemma":[0.0002219097,0.0000417462,0.3992443,0.000019552239,0.0000036278796,5.3874055e-7,0.0002994437,0.56829756,0.000002969969,0.027664296,0.0040358393,0.00016821495],"about_ca_topic_score_codex":0.011141475,"about_ca_topic_score_gemma":0.0010448084,"teacher_disagreement_score":0.5520816,"about_ca_system_score_codex":0.000055599132,"about_ca_system_score_gemma":0.000023299328,"threshold_uncertainty_score":0.9954434},"labels":[],"label_agreement":null},{"id":"W2753035968","doi":"10.1080/00031305.2017.1375984","title":"On An Intriguing Distributional Identity","year":2017,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Inference","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":"Université de Sherbrooke","funders":"","keywords":"Identity (music); Random variable; Mathematics; Distribution (mathematics); Continuous variable; Function (biology); Variance (accounting); Probability density function; Combinatorics; Variable (mathematics); Statistics; Discrete mathematics; Mathematical analysis; Physics; Economics","score_opus":0.10563840955061554,"score_gpt":0.46597122159010573,"score_spread":0.3603328120394902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753035968","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":[0.19860643,0.0000019691986,0.79516023,0.0005052827,0.00015635231,0.00011355743,0.0005484715,0.000043250217,0.0048644408],"genre_scores_gemma":[0.86537796,0.000002877165,0.13399848,0.0003749279,0.00014408136,0.000012966748,0.000009386885,0.000014386017,0.000064947155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874014,0.00023621428,0.00021327013,0.00021341119,0.00032932864,0.00026765125],"domain_scores_gemma":[0.9962895,0.0022724448,0.00040675688,0.0008321196,0.000084863284,0.00011435266],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006563046,0.00013203426,0.00025144298,0.000022257245,0.00086959783,0.0002489314,0.0006729057,0.000015351996,0.00024386744],"category_scores_gemma":[0.0095397495,0.00008904293,0.000034366418,0.00006105359,0.00091416313,0.00012862847,0.00010425947,0.0001936682,0.00007983482],"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":[0.0000351435,0.000053404212,0.0004453788,0.0000049729183,0.00001374725,0.000010342105,0.00006588335,5.1263044e-7,0.000043339558,0.9260456,0.0014135742,0.07186813],"study_design_scores_gemma":[0.00010373899,0.00021194639,0.12885131,0.000017399623,0.000027645343,0.0000030524034,0.00010625996,0.0009115716,0.000046829497,0.8694239,0.00017449728,0.000121826946],"about_ca_topic_score_codex":0.00062976277,"about_ca_topic_score_gemma":0.00012170532,"teacher_disagreement_score":0.66677153,"about_ca_system_score_codex":0.0000469422,"about_ca_system_score_gemma":0.000036194775,"threshold_uncertainty_score":0.9988033},"labels":[],"label_agreement":null},{"id":"W2766225997","doi":"10.1080/00031305.2017.1377111","title":"Bayesian Analysis on a Noncentral Fisher–Student’s Hypersphere","year":2017,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","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":"Université de Sherbrooke","funders":"","keywords":"Hypersphere; Mathematics; False discovery rate; Statistical hypothesis testing; Bayes factor; Null distribution; Null hypothesis; Bayesian probability; p-value; Bayes' theorem; Multiple comparisons problem; Weibull distribution; Statistics; Applied mathematics; Test statistic; Geometry","score_opus":0.3520839162328059,"score_gpt":0.5716076458469133,"score_spread":0.21952372961410738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766225997","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":[0.11230932,0.00001411635,0.8242672,0.0055386354,0.00094538706,0.0009905735,0.0011082225,0.00022908559,0.054597463],"genre_scores_gemma":[0.6248642,0.000016024454,0.3728736,0.001239515,0.00033778758,0.0000352375,0.0000024916542,0.00004350048,0.0005876486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964729,0.0009752191,0.0007063585,0.00054160476,0.00069616415,0.000607752],"domain_scores_gemma":[0.9716646,0.024638547,0.0011916579,0.0021614318,0.00009644981,0.00024730162],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016405035,0.00031204204,0.0011577478,0.000069527465,0.0007773218,0.00032524692,0.0014829666,0.000051458806,0.0008453594],"category_scores_gemma":[0.03607605,0.00021114694,0.00031610872,0.00036760108,0.0015745985,0.00005662706,0.00020189078,0.00040889517,0.00013524578],"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":[0.0008952403,0.0009719179,0.052848455,0.000056482735,0.004960492,0.0003205887,0.001410347,0.00006371406,0.000075912525,0.51336324,0.034447372,0.39058626],"study_design_scores_gemma":[0.0007595912,0.00047526992,0.42851713,0.00004352485,0.0025512583,0.0000027940093,0.00091353746,0.001830235,0.000040302697,0.56341034,0.00096885074,0.0004871661],"about_ca_topic_score_codex":0.0007169673,"about_ca_topic_score_gemma":0.00037788518,"teacher_disagreement_score":0.5125549,"about_ca_system_score_codex":0.00009523822,"about_ca_system_score_gemma":0.000053024505,"threshold_uncertainty_score":0.9720435},"labels":[],"label_agreement":null},{"id":"W2790711374","doi":"10.1080/00031305.2018.1555101","title":"The World of Research Has Gone Berserk: Modeling the Consequences of Requiring “Greater Statistical Stringency” for Scientific Publication","year":2019,"lang":"en","type":"preprint","venue":"The American Statistician","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reliability (semiconductor); Publication; Incentive; Odds; Statistical power; Sample size determination; Sample (material); Econometrics; Statistical model; Affect (linguistics); Management science; Actuarial science; Computer science; Power (physics); Operations research; Psychology; Statistics; Economics; Political science; Mathematics; Law; Microeconomics; Logistic regression","score_opus":0.8567728382291895,"score_gpt":0.5943493876722813,"score_spread":0.2624234505569082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790711374","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":[0.08738007,0.001394741,0.87782407,0.014115155,0.0014263862,0.007045175,0.004094555,0.000013139623,0.006706711],"genre_scores_gemma":[0.9795583,0.000034092354,0.013378685,0.00007764501,0.000078693534,0.00030977104,0.000072987605,0.000025566402,0.006464284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9665165,0.015927307,0.007642181,0.0013431187,0.007921984,0.0006489392],"domain_scores_gemma":[0.9310172,0.04639962,0.009766219,0.007156698,0.0055480273,0.00011224226],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.18600692,0.00033171754,0.0026196442,0.0006610028,0.0016566762,0.002479822,0.0062729386,0.000041044732,0.0012707744],"category_scores_gemma":[0.05299664,0.0001234254,0.0007104693,0.0027576427,0.0064637526,0.0000912727,0.0013087289,0.0007153363,0.00011517791],"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":[0.00040116327,0.00016767731,0.0051211077,0.00077146,0.0019951467,0.000003269314,0.010074,0.05376052,0.00061761506,0.5767694,0.21718943,0.13312921],"study_design_scores_gemma":[0.00022625964,0.00026252962,0.0030403621,0.00025244243,0.00093475165,0.0000050005497,0.022232011,0.5892829,0.00016921679,0.33772418,0.045399513,0.00047087672],"about_ca_topic_score_codex":0.0009796015,"about_ca_topic_score_gemma":0.0006328837,"teacher_disagreement_score":0.8921782,"about_ca_system_score_codex":0.00010970796,"about_ca_system_score_gemma":0.0009066565,"threshold_uncertainty_score":0.999643},"labels":[],"label_agreement":null},{"id":"W2801323879","doi":"10.1080/00031305.2018.1438699","title":"Introduction: Special Issue on Data Science","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data science; Computer science","score_opus":0.07468234379272098,"score_gpt":0.34399219176750007,"score_spread":0.2693098479747791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801323879","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07538558,0.000035292418,0.04360405,0.1000076,0.022646181,0.0010395796,0.0006204318,0.0006159968,0.7560453],"genre_scores_gemma":[0.62551457,0.000018673012,0.0020945035,0.015634082,0.3551821,0.0000074243703,0.00018845186,0.000037293128,0.0013229088],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99860954,0.000009177653,0.00016264488,0.00047513083,0.00042432753,0.00031914978],"domain_scores_gemma":[0.9982478,0.000051785795,0.0002212765,0.0012336457,0.0002323878,0.0000131229845],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00052326266,0.00012914183,0.00014335326,0.00014857775,0.00063739246,0.0004048862,0.0016953404,0.000008465171,0.003703366],"category_scores_gemma":[0.00060194713,0.000088283785,0.000010528804,0.0016310106,0.0032433276,0.0010743954,0.00060923095,0.00010855329,0.007758349],"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":[0.00006229798,0.000030604304,0.00016841802,0.000005862074,0.0000054211278,0.0000027657293,0.000028785997,0.0000019785002,0.0000980493,0.05835161,0.5950428,0.34620136],"study_design_scores_gemma":[0.00003950729,0.00003238436,0.011561854,0.000007983961,0.000022695389,0.000002631809,0.00026868377,0.0014660453,0.00008987907,0.0014815298,0.984886,0.00014084068],"about_ca_topic_score_codex":0.0011543928,"about_ca_topic_score_gemma":0.00025224814,"teacher_disagreement_score":0.75472236,"about_ca_system_score_codex":0.000023359573,"about_ca_system_score_gemma":0.000045967117,"threshold_uncertainty_score":0.9994693},"labels":[],"label_agreement":null},{"id":"W2803189886","doi":"10.1080/00031305.2018.1497537","title":"Visualizing Tests for Equality of Covariance Matrices","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate analysis of variance; Covariance; Variety (cybernetics); Analysis of covariance; Multivariate statistics; Statistics; Covariance matrix; Test (biology); Econometrics; Plot (graphics); Computer science; Mathematics; Statistical hypothesis testing; Estimation of covariance matrices","score_opus":0.23362593522876668,"score_gpt":0.5405334951375262,"score_spread":0.30690755990875956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803189886","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":[0.008605765,0.000025509658,0.9892348,0.00013886266,0.000085471635,0.000338353,0.0005645773,0.000043085227,0.00096358795],"genre_scores_gemma":[0.30153337,0.0000076098195,0.6979372,0.00026046133,0.00012637666,0.000031078474,0.0000027263359,0.000022399625,0.00007875479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863935,0.00021464242,0.0004153119,0.00022131564,0.00020192645,0.00030744306],"domain_scores_gemma":[0.99191344,0.006840448,0.0005719995,0.0003640452,0.00024394732,0.00006612821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000832668,0.00013990288,0.00042931453,0.00003468395,0.00016908244,0.00001535773,0.00024788806,0.000016748501,0.000027866667],"category_scores_gemma":[0.003422256,0.00009795982,0.00005004675,0.00026135606,0.0009346213,0.000043129294,0.000052075284,0.00007063158,0.000006136007],"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":[0.00013467888,0.00005424103,0.000034751705,0.00009033972,0.000034256846,8.1268485e-7,0.00057724566,0.000003045413,0.001328247,0.9052438,0.0012632987,0.09123529],"study_design_scores_gemma":[0.0002219348,0.0005646497,0.00079812587,0.000042140124,0.00008713411,0.0000022311954,0.0004853371,0.0041351393,0.0011372268,0.99045223,0.0019089199,0.00016494819],"about_ca_topic_score_codex":0.00018276041,"about_ca_topic_score_gemma":0.00006251048,"teacher_disagreement_score":0.29292762,"about_ca_system_score_codex":0.000024393452,"about_ca_system_score_gemma":0.000042441872,"threshold_uncertainty_score":0.40970075},"labels":[],"label_agreement":null},{"id":"W2803912231","doi":"10.1080/00031305.2018.1475304","title":"Two-Tailed <i>p</i> -Values and Coherent Measures of Evidence","year":2018,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","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":"York University","funders":"","keywords":"Null hypothesis; p-value; Null (SQL); Statistical hypothesis testing; Interpretation (philosophy); Alternative hypothesis; Econometrics; Mathematics; Value (mathematics); Statistics; Set (abstract data type); Measure (data warehouse); Statistical evidence; Statistical significance; Mathematical economics; Computer science; Data mining; Linguistics; Philosophy","score_opus":0.3190207158526712,"score_gpt":0.4897757391841812,"score_spread":0.17075502333151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803912231","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":[0.044311315,0.00014032479,0.95378315,0.00022374892,0.00006004407,0.00023662117,0.000088929344,0.00003557203,0.0011202943],"genre_scores_gemma":[0.515821,0.000067854024,0.48368597,0.00021998439,0.000071238464,0.00001328382,4.302085e-7,0.0000163591,0.000103872124],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857134,0.00036259202,0.000313248,0.00021792056,0.00029333308,0.00024159922],"domain_scores_gemma":[0.9947106,0.004327714,0.00033374783,0.00035007717,0.00018997358,0.000087891814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006533041,0.00014655905,0.0004040087,0.000030252417,0.0001302796,0.000016332295,0.00018789816,0.000011267535,0.000036059504],"category_scores_gemma":[0.0032287054,0.00008368707,0.000028620103,0.00016438431,0.0019148447,0.00004918238,0.00007857529,0.00009721339,0.00000655214],"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":[0.0002949295,0.00007185863,0.0005944262,0.000078493795,0.00008465396,0.0000064557535,0.0021138163,0.000003473133,0.005175688,0.4341122,0.0019350483,0.55552894],"study_design_scores_gemma":[0.00022086353,0.00064472447,0.0020881668,0.00013539764,0.00013052874,0.000006529671,0.00088231656,0.0014118245,0.001532514,0.9924193,0.000349123,0.00017872336],"about_ca_topic_score_codex":0.0002196051,"about_ca_topic_score_gemma":0.00009157609,"teacher_disagreement_score":0.5583071,"about_ca_system_score_codex":0.000017648877,"about_ca_system_score_gemma":0.000033822045,"threshold_uncertainty_score":0.70553255},"labels":[],"label_agreement":null},{"id":"W2891886352","doi":"10.1080/00031305.2020.1717621","title":"Reconnecting <i>p</i> -Value and Posterior Probability Under One- and Two-Sided Tests","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistics; Mathematics; Posterior probability; Value (mathematics); p-value; Statistical hypothesis testing; Bayesian probability","score_opus":0.525964131273974,"score_gpt":0.5256489015127478,"score_spread":0.00031522976122622115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891886352","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":[0.7734604,0.000042390795,0.21181007,0.012095737,0.00012209339,0.0010207907,0.00028315416,0.0001787287,0.0009866225],"genre_scores_gemma":[0.40642878,0.000011722683,0.588656,0.0046828603,0.00015668444,0.000021652348,7.752411e-7,0.000033735614,0.000007794532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966971,0.0014310017,0.00071323867,0.00053413125,0.00026358743,0.00036092842],"domain_scores_gemma":[0.92829806,0.070477836,0.00049276627,0.00037082922,0.00007747733,0.00028303277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018306004,0.00023727497,0.00081282714,0.000021394655,0.00018877692,0.00009310053,0.00020840556,0.000034581244,0.0000559943],"category_scores_gemma":[0.09677657,0.00017710737,0.00004361076,0.0002694933,0.0011877726,0.00004870069,0.00023626658,0.00034211576,0.000012547769],"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":[0.0009052863,0.00020533006,0.004813096,0.00046092263,0.00030443593,0.000036221398,0.0031422174,0.000010924638,0.0057120174,0.55249333,0.00092701154,0.4309892],"study_design_scores_gemma":[0.00066201,0.00053969526,0.021443632,0.00007034932,0.0001912291,0.000016683794,0.0007379218,0.00097093615,0.00024069945,0.9748377,0.000026995707,0.00026214076],"about_ca_topic_score_codex":0.00021951395,"about_ca_topic_score_gemma":0.000060850696,"teacher_disagreement_score":0.43072706,"about_ca_system_score_codex":0.000031218864,"about_ca_system_score_gemma":0.000051305866,"threshold_uncertainty_score":0.9108317},"labels":[],"label_agreement":null},{"id":"W2922738421","doi":"10.1080/00031305.2018.1564697","title":"A Proposed Hybrid Effect Size Plus <i>p</i> -Value Criterion: Empirical Evidence Supporting its Use","year":2019,"lang":"en","type":"article","venue":"The American Statistician","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Value (mathematics); Mathematics; Statistics","score_opus":0.614450181809646,"score_gpt":0.5502659135980562,"score_spread":0.06418426821158973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922738421","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":[0.9719843,0.00019790893,0.022033084,0.002280387,0.00035349224,0.0019564715,0.0000944587,0.000024285811,0.0010755662],"genre_scores_gemma":[0.98200464,0.000013855,0.0070777577,0.0041213115,0.00011899461,0.00004299417,0.0000047338513,0.000030811112,0.006584875],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9688624,0.018587425,0.005545392,0.0012588777,0.00512157,0.000624338],"domain_scores_gemma":[0.9324388,0.055751022,0.0065742116,0.0040916507,0.00086704234,0.00027729545],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.061539527,0.00045971732,0.0040178625,0.00014405456,0.0002610645,0.0016775778,0.0023997552,0.00002621855,0.0064754435],"category_scores_gemma":[0.15893364,0.00019577619,0.0009830205,0.0015613338,0.0003278854,0.00048313622,0.00030196167,0.00030716223,0.013533305],"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":[0.0008330949,0.00019252085,0.27169555,0.0006092319,0.001099044,0.0005389761,0.0056178756,0.0012815524,0.008381963,0.0047374642,0.44384825,0.26116446],"study_design_scores_gemma":[0.0017636052,0.0044759717,0.50840116,0.0010648756,0.0027856166,0.0005312678,0.0042049726,0.2758874,0.0015533563,0.0059969705,0.19058135,0.002753461],"about_ca_topic_score_codex":0.00023108536,"about_ca_topic_score_gemma":0.000018137009,"teacher_disagreement_score":0.27460584,"about_ca_system_score_codex":0.00009581132,"about_ca_system_score_gemma":0.00022445232,"threshold_uncertainty_score":0.9993588},"labels":[],"label_agreement":null},{"id":"W2924029102","doi":"10.1080/00031305.2018.1556735","title":"The <i>p</i> -value Function and Statistical Inference","year":2019,"lang":"en","type":"article","venue":"The American Statistician","topic":"Data Analysis with R","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Inference; Function (biology); Statistical inference; Scalar (mathematics); Value (mathematics); Mathematics; Power function; Statistics; Computer science; Artificial intelligence; Mathematical analysis","score_opus":0.006202599462732283,"score_gpt":0.25972193317835646,"score_spread":0.2535193337156242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924029102","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":[0.013481973,0.000051732095,0.98309606,0.0015492922,0.00017055312,0.00014182225,0.000050387367,0.000058390247,0.0013998009],"genre_scores_gemma":[0.97678643,0.000048846465,0.02072718,0.002118343,0.00003658722,0.000012192935,0.000009563434,0.000008884737,0.00025198687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986452,0.0002417983,0.00019101486,0.00030431018,0.00032612353,0.00029158688],"domain_scores_gemma":[0.99689305,0.0019653547,0.00018011412,0.0008316489,0.000050365197,0.000079484555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044834006,0.000120128694,0.00017995601,0.000031954034,0.0002808324,0.00033331572,0.0008141983,0.000009298768,0.000016260557],"category_scores_gemma":[0.00021843209,0.00006569122,0.000018058057,0.00041830252,0.0005062866,0.0001753975,0.00029055713,0.00015155284,0.00033101218],"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":[0.000016950962,0.000009349311,0.0028856806,0.0000024893848,0.000031353065,0.000002449177,0.000105035055,0.000033204502,0.00008153482,0.7695325,0.0027841614,0.22451526],"study_design_scores_gemma":[0.0003700695,0.00075136556,0.5829065,0.00001567056,0.00010943735,0.00001736441,0.00064823293,0.22873963,0.000025281404,0.1466296,0.03933896,0.000447874],"about_ca_topic_score_codex":0.00060612103,"about_ca_topic_score_gemma":0.00011171433,"teacher_disagreement_score":0.96330446,"about_ca_system_score_codex":0.000021171118,"about_ca_system_score_gemma":0.000063148924,"threshold_uncertainty_score":0.42546022},"labels":[],"label_agreement":null},{"id":"W2940269847","doi":"10.1080/00031305.2019.1604432","title":"On a Proper Bayes, but Inadmissible Estimator","year":2019,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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":"Université de Sherbrooke","funders":"","keywords":"Bayes' theorem; Mathematics; Statistics; Estimator; Mean squared error; Bayes estimator; Binomial (polynomial); Point estimation; Efficient estimator; Negative binomial distribution; Minimum-variance unbiased estimator; Applied mathematics; Bayesian probability; Poisson distribution","score_opus":0.06933036670836826,"score_gpt":0.41908410835140575,"score_spread":0.3497537416430375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940269847","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":[0.05814009,0.000012932127,0.9261687,0.00047014208,0.0001256495,0.000550544,0.00019947777,0.00010739077,0.014225121],"genre_scores_gemma":[0.34425378,0.0000055430746,0.6511359,0.0012278414,0.0000505784,0.00004829991,0.000004255966,0.000058154783,0.0032156182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984131,0.00021821441,0.00028531777,0.0003344561,0.00033070787,0.0004182374],"domain_scores_gemma":[0.9958534,0.0030882207,0.0002362472,0.0005962405,0.00006745295,0.0001584357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003405467,0.00021900197,0.0004419881,0.000047867747,0.00014308213,0.000037085865,0.00028255896,0.000021159864,0.00037934203],"category_scores_gemma":[0.0017341537,0.00013388989,0.000047898095,0.00020958483,0.00029031181,0.00004724395,0.00006478477,0.00024426135,0.0004165897],"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":[0.0001413706,0.000084900385,0.000046169993,0.000043090044,0.00002931292,0.000018343359,0.00015872977,0.000053632542,0.0004148138,0.9202286,0.004329408,0.07445165],"study_design_scores_gemma":[0.0003125393,0.0006789043,0.00067391933,0.000063777625,0.000048110203,0.000010582172,0.00038404393,0.008248923,0.00021828485,0.9864547,0.0026147105,0.00029146936],"about_ca_topic_score_codex":0.00015637834,"about_ca_topic_score_gemma":0.000013011109,"teacher_disagreement_score":0.28611368,"about_ca_system_score_codex":0.000057864185,"about_ca_system_score_gemma":0.0000791334,"threshold_uncertainty_score":0.54598707},"labels":[],"label_agreement":null},{"id":"W2994409524","doi":"10.1080/00031305.2020.1816214","title":"Null Hypothesis Significance Testing Interpreted and Calibrated by Estimating Probabilities of Sign Errors: A Bayes-Frequentist Continuum","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"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":"Bayes factor; Frequentist inference; Posterior probability; Bayesian probability; Statistics; Bayes' theorem; Mathematics; p-value; Statistical hypothesis testing; Sign (mathematics); Null hypothesis; Prior probability; Alternative hypothesis; Statistical power; Econometrics; Bayesian inference; Mathematical analysis","score_opus":0.36817545539381347,"score_gpt":0.4518311482418546,"score_spread":0.08365569284804114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994409524","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":[0.101112366,0.00004973148,0.8932944,0.0014407071,0.00012611861,0.0011297263,0.0017492702,0.00024568284,0.0008519814],"genre_scores_gemma":[0.36735445,0.000002462898,0.63184106,0.000588876,0.00008349469,0.000052248415,0.0000021434128,0.000052149426,0.000023105935],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955253,0.0017139498,0.0013625029,0.00055243407,0.00039435015,0.0004514423],"domain_scores_gemma":[0.89258564,0.10512488,0.001406964,0.0004294578,0.00021362324,0.00023946099],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001482716,0.00034229807,0.0012527165,0.000037716098,0.00014023644,0.000082385224,0.00047645922,0.00005224674,0.000099498815],"category_scores_gemma":[0.20389616,0.00026000422,0.000076842276,0.0006448548,0.0023034369,0.00007323117,0.0001581667,0.0003551701,0.0000072229486],"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":[0.0023908925,0.00073154893,0.008218993,0.003684911,0.001319089,0.00013081699,0.013750354,0.00007439631,0.10367113,0.07198223,0.059734292,0.73431134],"study_design_scores_gemma":[0.0010550021,0.001891505,0.0024005356,0.00055986404,0.0005195353,0.000011357612,0.002924074,0.05728111,0.005282698,0.9271859,0.00009929095,0.00078913633],"about_ca_topic_score_codex":0.00057786965,"about_ca_topic_score_gemma":0.000024743302,"teacher_disagreement_score":0.8552037,"about_ca_system_score_codex":0.000039681567,"about_ca_system_score_gemma":0.00009418105,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W3114650575","doi":"10.1080/00031305.2020.1865199","title":"Hurdle Blockmodels for Sparse Network Modeling","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Model selection; Variety (cybernetics); Selection (genetic algorithm); Random graph; Goodness of fit; Exponential random graph models; Graph; Data mining; Theoretical computer science; Machine learning; Artificial intelligence","score_opus":0.04329076685591112,"score_gpt":0.3001625163344384,"score_spread":0.2568717494785273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114650575","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":[0.017631212,0.000025372152,0.979324,0.0010447733,0.000019638595,0.00027025078,0.000104592466,0.00009293598,0.0014872623],"genre_scores_gemma":[0.9334259,0.0000025452405,0.06401696,0.0012934686,0.0010777788,0.00007389074,0.000046003268,0.000030672993,0.000032803295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989897,0.00006087274,0.00024321605,0.00023966611,0.00011914429,0.00034738678],"domain_scores_gemma":[0.99919593,0.00020496268,0.00018048345,0.00026232688,0.000056938046,0.00009936135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001311728,0.00015064691,0.00032069092,0.000014722623,0.00021938521,0.000048387406,0.00030740132,0.000006558869,0.00009768749],"category_scores_gemma":[0.000010132784,0.00012031805,0.00011526501,0.000323028,0.00010967064,0.00003121189,0.00008104471,0.00011429946,0.000017993521],"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":[0.00013954964,0.000053452004,0.0018314369,0.000008581578,0.0003558046,0.0000015109812,0.00079444866,0.54007435,0.00013625399,0.1901683,0.056052227,0.21038407],"study_design_scores_gemma":[0.000094874325,0.00008245201,0.000043238342,0.000005798832,0.00010524665,9.854015e-8,0.00027798064,0.9330237,0.000021452563,0.062586494,0.0036037697,0.00015491046],"about_ca_topic_score_codex":0.0006106545,"about_ca_topic_score_gemma":0.00001742395,"teacher_disagreement_score":0.9157947,"about_ca_system_score_codex":0.00001129095,"about_ca_system_score_gemma":0.000029906601,"threshold_uncertainty_score":0.49064276},"labels":[],"label_agreement":null},{"id":"W3209485542","doi":"10.1080/00031305.2021.2000495","title":"Comparative Probability Metrics: Using Posterior Probabilities to Account for Practical Equivalence in A/B tests","year":2021,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":12,"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":"Mathematics; Statistics; Equivalence (formal languages); Posterior probability; Bayesian probability; Discrete mathematics","score_opus":0.2844714646661516,"score_gpt":0.5027176178365009,"score_spread":0.21824615317034934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209485542","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":[0.205436,0.00001562577,0.79143995,0.0011790176,0.00008387363,0.0010869111,0.00046474035,0.00003252271,0.0002613399],"genre_scores_gemma":[0.23372321,0.0000016399124,0.7655104,0.0005017131,0.000050120037,0.0001693046,0.0000036746085,0.000019230994,0.000020748254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972322,0.0007306961,0.0006154346,0.0005067688,0.00036733667,0.0005475927],"domain_scores_gemma":[0.9818524,0.01666597,0.00030396442,0.0005302334,0.0004994,0.00014799954],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001186372,0.00024389997,0.000767624,0.000097239026,0.00015150016,0.00012423033,0.00024956572,0.000031175485,0.00007166648],"category_scores_gemma":[0.022644525,0.00018293406,0.000062742896,0.001079166,0.0005891947,0.0001026401,0.00017156455,0.00022535534,0.000010275437],"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":[0.00041564633,0.00056827895,0.0024887593,0.0004036205,0.00006777311,0.000059927712,0.004614784,0.00002049251,0.002788653,0.9409472,0.0006368591,0.04698803],"study_design_scores_gemma":[0.00024358428,0.00046253565,0.016077472,0.00012445157,0.00008837808,0.000039567512,0.003470222,0.0047105635,0.0008051866,0.9735093,0.00014321541,0.0003255125],"about_ca_topic_score_codex":0.00031817667,"about_ca_topic_score_gemma":0.0006315158,"teacher_disagreement_score":0.046662517,"about_ca_system_score_codex":0.00026556224,"about_ca_system_score_gemma":0.0005647173,"threshold_uncertainty_score":0.98558813},"labels":[],"label_agreement":null},{"id":"W4224213250","doi":"10.1080/00031305.2022.2066725","title":"Bias Analysis for Misclassification Errors in both the Response Variable and Covariate","year":2022,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Variable (mathematics); Econometrics; Inference; Computer science; Observational error; Variables; Mathematics; Artificial intelligence","score_opus":0.13364623097300488,"score_gpt":0.3955855856048989,"score_spread":0.26193935463189405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224213250","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":[0.03439834,0.000015854052,0.9621208,0.0020364197,0.000042178806,0.00041825298,0.00072678336,0.000021769496,0.00021962973],"genre_scores_gemma":[0.4618998,0.000005274641,0.5369026,0.0006521707,0.0000175302,0.00030746075,0.000012179012,0.000018016895,0.0001849876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971955,0.0017265546,0.0003387734,0.00024929963,0.0002273519,0.0002625581],"domain_scores_gemma":[0.98339325,0.015781743,0.00033866323,0.00040054266,0.00003954959,0.000046277553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034209702,0.00012450233,0.0003493216,0.00013386415,0.0004569264,0.000052696952,0.0002815127,0.0000110849705,0.00014050028],"category_scores_gemma":[0.0038456356,0.00007844736,0.000044382396,0.0013042962,0.00036038796,0.000020826137,0.00008864312,0.00018829394,0.0000012509479],"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":[0.00095628627,0.000080485,0.0016588616,0.000016455646,0.0001912124,0.000004860276,0.0020131103,0.000110325316,0.0002969607,0.97032064,0.0013487192,0.02300211],"study_design_scores_gemma":[0.0002943348,0.00029820268,0.1421232,0.000005554041,0.0004994793,0.000004789313,0.0042698816,0.044343203,0.0000077143,0.80519223,0.0027845008,0.00017686865],"about_ca_topic_score_codex":0.00093553896,"about_ca_topic_score_gemma":0.00015966687,"teacher_disagreement_score":0.42750144,"about_ca_system_score_codex":0.00007520691,"about_ca_system_score_gemma":0.00008698043,"threshold_uncertainty_score":0.46038628},"labels":[],"label_agreement":null},{"id":"W4251610920","doi":"10.1198/tas.2009.0021","title":"Comment","year":2009,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics","score_opus":0.18364449225361962,"score_gpt":0.4710982106444673,"score_spread":0.28745371839084766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251610920","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":[0.011586192,0.000032489635,0.9238104,0.0472973,0.00044855507,0.00030441006,0.00015495226,0.00021530526,0.016150374],"genre_scores_gemma":[0.30485222,0.000031210937,0.66771156,0.026384294,0.00013023482,0.000015789528,0.000010529762,0.000015576325,0.00084861723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99909985,0.00024972076,0.00017931857,0.000114845236,0.00015208822,0.00020419282],"domain_scores_gemma":[0.9967167,0.0026777713,0.00018639419,0.00031837035,0.000046082565,0.00005468778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004283001,0.00009832217,0.00019498027,0.000033980195,0.00012633429,0.000028002476,0.00020867019,0.000007906397,0.00011279128],"category_scores_gemma":[0.0016706315,0.00006476352,0.000026646034,0.00017012983,0.0002250917,0.000013026335,0.000016720285,0.000096830954,0.00006993909],"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":[0.000013627733,0.00004439591,0.000036309706,0.000002170068,0.000009238032,0.0000022643758,0.00053409755,4.2313292e-7,0.00003642713,0.6165805,0.26087403,0.12186651],"study_design_scores_gemma":[0.00010477614,0.00019224457,0.017112512,0.000006334075,0.000038215367,0.0000065112945,0.0020261118,0.000075534306,0.00012918381,0.92533076,0.054850638,0.00012718012],"about_ca_topic_score_codex":0.00005199794,"about_ca_topic_score_gemma":0.000008495586,"teacher_disagreement_score":0.30875024,"about_ca_system_score_codex":0.000032396438,"about_ca_system_score_gemma":0.000031921005,"threshold_uncertainty_score":0.26409796},"labels":[],"label_agreement":null},{"id":"W4318485822","doi":"10.1080/00031305.2022.2160590","title":"Object Oriented Data Analysis","year":2023,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Database Systems and Queries","field":"Computer Science","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","funders":"","keywords":"Computer science","score_opus":0.03783203117561788,"score_gpt":0.3352063899743726,"score_spread":0.2973743587987547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318485822","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":[0.0031946318,0.000019610236,0.9943684,0.0005163492,0.00013275293,0.00008134496,0.00094734045,0.00029430684,0.00044531064],"genre_scores_gemma":[0.51826334,0.00010255416,0.47713274,0.001582438,0.00022027048,0.00004172111,0.0014708514,0.000030993502,0.0011551235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870044,0.00013588574,0.00018814993,0.00041082932,0.0002726736,0.0002920141],"domain_scores_gemma":[0.9970443,0.0003757096,0.00018235728,0.002292423,0.00004148273,0.0000637123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040421096,0.00010470641,0.00024935804,0.00016380246,0.00021140171,0.000045191504,0.0011628742,0.000005653678,0.00001155862],"category_scores_gemma":[0.00018799065,0.00007026732,0.00003333956,0.0047186026,0.00022634823,0.00026901517,0.0008411965,0.00007369256,0.00025496702],"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":[0.000021170474,0.000032860862,0.0036991981,0.00001324802,0.0007846866,0.00018630306,0.0018372724,0.0010895613,0.0001948546,0.6914719,0.047769293,0.25289968],"study_design_scores_gemma":[0.00022353228,0.00016814022,0.1859312,0.00001553779,0.00032916554,0.000013127009,0.0027340732,0.48846024,0.000059616716,0.0028102538,0.3186731,0.00058199535],"about_ca_topic_score_codex":0.0017083618,"about_ca_topic_score_gemma":0.0005805711,"teacher_disagreement_score":0.68866163,"about_ca_system_score_codex":0.000015542968,"about_ca_system_score_gemma":0.000046936537,"threshold_uncertainty_score":0.327717},"labels":[],"label_agreement":null},{"id":"W4320057135","doi":"10.1080/00031305.2022.2139293","title":"Bayes Factors and Posterior Estimation: Two Sides of the Very Same Coin","year":2022,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","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":"University of British Columbia","funders":"","keywords":"Bayes factor; Bayes' rule; Prior probability; Bayes' theorem; Bayesian probability; Posterior probability; Odds; Point estimation; Bayes estimator; Estimation; Statistics; Mathematics; Econometrics; Computer science; Economics; Logistic regression","score_opus":0.041926484876412824,"score_gpt":0.3594317233608289,"score_spread":0.3175052384844161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320057135","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":[0.6626723,0.000030965526,0.33458814,0.0007676806,0.00014796594,0.0002988617,0.0009856737,0.00003290789,0.00047554958],"genre_scores_gemma":[0.77326006,0.0000025861789,0.22627805,0.0003604888,0.00001744947,0.000022386665,0.0000032745495,0.000016546173,0.000039184608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984157,0.000574591,0.0003107533,0.00017274338,0.00032737842,0.00019879574],"domain_scores_gemma":[0.9942155,0.00494008,0.0003958449,0.0003570875,0.00004110729,0.000050401213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036980002,0.0001473049,0.0003503233,0.000035936708,0.00036697774,0.00003172745,0.00030844918,0.0000075850567,0.00022776471],"category_scores_gemma":[0.0015121008,0.00008387035,0.000045462115,0.0002944579,0.0008230847,0.00002974678,0.00025958868,0.00018713292,0.0000016499607],"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":[0.0001124923,0.000103859566,0.016588423,0.00009321286,0.000094487266,0.000010773428,0.004171534,0.000020281706,0.0010238761,0.7488186,0.0014723008,0.22749017],"study_design_scores_gemma":[0.00022453797,0.00034718285,0.15920717,0.000031536303,0.00013083707,0.000031389533,0.004187852,0.0030256812,0.0004195978,0.83204544,0.000146796,0.00020200606],"about_ca_topic_score_codex":0.000996338,"about_ca_topic_score_gemma":0.00008870038,"teacher_disagreement_score":0.22728817,"about_ca_system_score_codex":0.000036562793,"about_ca_system_score_gemma":0.000061373095,"threshold_uncertainty_score":0.34201336},"labels":[],"label_agreement":null},{"id":"W4386562232","doi":"10.1080/00031305.2023.2257237","title":"Statistical Challenges in Online Controlled Experiments: A Review of A/B Testing Methodology","year":2023,"lang":"en","type":"review","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"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":"Data science; The Internet; Computer science; Scale (ratio); Big data; World Wide Web; Marketing; Business; Data mining; Geography","score_opus":0.9449757609267309,"score_gpt":0.7096567412494859,"score_spread":0.235319019677245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386562232","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":[5.186626e-7,0.94729453,0.044542827,0.00021875736,0.00035512156,0.0036226804,0.003222942,0.00011250455,0.00063013274],"genre_scores_gemma":[9.6089614e-8,0.5375277,0.46142006,0.00016645058,0.00016851594,0.00053314265,0.000025942045,0.00012658254,0.000031495143],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9696804,0.021822803,0.00579107,0.0009955093,0.0008417498,0.00086841],"domain_scores_gemma":[0.58023256,0.41439053,0.00394371,0.0010657244,0.0002143029,0.00015314687],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.016219392,0.0008837228,0.014849555,0.00035611694,0.00006813382,0.000017980543,0.0012532093,0.00020534128,0.00021501347],"category_scores_gemma":[0.5453734,0.0005533636,0.00059390656,0.0016300702,0.0016269524,0.000023812418,0.00042971232,0.0012439693,0.000079214275],"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":[0.000095569754,0.00024422852,4.792701e-7,0.094039395,0.00050664286,0.00009889769,0.00005465731,6.5205455e-8,2.0837531e-7,0.079221934,0.00091112655,0.8248268],"study_design_scores_gemma":[0.0021516774,0.0013002865,0.000035863864,0.26741457,0.0066743265,0.000056074226,0.0006784787,0.00006328825,2.979798e-7,0.67049015,0.050021518,0.0011134798],"about_ca_topic_score_codex":0.00022390766,"about_ca_topic_score_gemma":0.00006504169,"teacher_disagreement_score":0.8237133,"about_ca_system_score_codex":0.00018565531,"about_ca_system_score_gemma":0.0005422517,"threshold_uncertainty_score":0.999776},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4387362492","doi":"10.1080/00031305.2023.2267597","title":"Causal Quartets: Different Ways to Attain the Same Average Treatment Effect","year":2023,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Variation (astronomy); Context (archaeology); Simple (philosophy); Epistemology; Mathematical economics; Mathematics; Computer science; Econometrics; Sociology; Philosophy; History; Physics","score_opus":0.10626714617887423,"score_gpt":0.4161824036868427,"score_spread":0.30991525750796844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387362492","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":[0.5336497,0.000013459196,0.45855114,0.0033942824,0.00014843333,0.0017623196,0.00043639864,0.0011492642,0.00089503784],"genre_scores_gemma":[0.9893496,0.000045396166,0.007827071,0.001204652,0.00016421107,0.00071533513,0.00003576782,0.00008523885,0.00057274365],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979881,0.00037219436,0.00033088913,0.00032994733,0.00036820988,0.0006106565],"domain_scores_gemma":[0.992121,0.0065979906,0.0002261863,0.0008960207,0.000042262538,0.00011657344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044525668,0.000374517,0.0005718151,0.00010038352,0.00031631324,0.00006437115,0.000463023,0.000024869434,0.00007694253],"category_scores_gemma":[0.00081356685,0.00017772331,0.00009719453,0.0006172624,0.00037276663,0.000037385882,0.00013483877,0.00019399232,0.00038337673],"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":[0.00037123862,0.00027877442,0.0010284835,0.0000770482,0.0004306315,0.00023991051,0.01276988,0.00031118467,0.0058224658,0.4155166,0.08387211,0.4792817],"study_design_scores_gemma":[0.0009944552,0.011090647,0.02729815,0.0001810887,0.0004747386,0.00003615129,0.0041236337,0.0036241256,0.009862268,0.9261406,0.014802052,0.0013720873],"about_ca_topic_score_codex":0.0009384574,"about_ca_topic_score_gemma":0.0007961535,"teacher_disagreement_score":0.510624,"about_ca_system_score_codex":0.00029804374,"about_ca_system_score_gemma":0.000032200667,"threshold_uncertainty_score":0.72473466},"labels":[],"label_agreement":null},{"id":"W4389233698","doi":"10.1080/00031305.2023.2290720","title":"Hitting a Prime by Rolling a Die with Infinitely Many Faces","year":2023,"lang":"en","type":"article","venue":"The American Statistician","topic":"Experimental and Theoretical Physics Studies","field":"Physics and Astronomy","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":"Dalhousie University","funders":"","keywords":"Die (integrated circuit); Prime (order theory); Combinatorics; Mathematics; Arithmetic; Psychology; Computer science; Operating system","score_opus":0.0076238206710642535,"score_gpt":0.26203459242866733,"score_spread":0.25441077175760307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389233698","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":[0.82255733,0.000117826465,0.053018708,0.00095019944,0.00006638052,0.0003571007,0.0005130597,0.0002304616,0.12218892],"genre_scores_gemma":[0.9986555,0.000005869683,0.0006125944,0.0001736266,0.00011116872,0.000049843602,0.000038684477,0.000024659996,0.0003280655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913335,0.000050338826,0.00013736311,0.00018488952,0.00016301668,0.00033102534],"domain_scores_gemma":[0.99929714,0.00033297826,0.00013660321,0.00015396842,0.000023898894,0.00005540693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080833626,0.00015418915,0.00022863777,0.000022267564,0.0003030901,0.000047470603,0.00015552591,0.0000042041343,0.000037778962],"category_scores_gemma":[0.000006365005,0.00009516635,0.000035412748,0.00030382982,0.00058274774,0.000036981088,0.00009749723,0.00011477417,0.00016098254],"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":[0.00017346194,0.0001787138,0.014799491,0.000013749818,0.00060988375,0.00001535694,0.00681134,0.00012770164,0.006091324,0.85356396,0.0036815256,0.11393349],"study_design_scores_gemma":[0.0012748172,0.0011952625,0.0107351225,0.00014185772,0.00024025865,0.0000012793614,0.06024436,0.00564706,0.015257783,0.8972257,0.0067125764,0.0013239159],"about_ca_topic_score_codex":0.000750743,"about_ca_topic_score_gemma":0.0000036611102,"teacher_disagreement_score":0.17609814,"about_ca_system_score_codex":0.000010476444,"about_ca_system_score_gemma":0.000013899902,"threshold_uncertainty_score":0.38807714},"labels":[],"label_agreement":null},{"id":"W4392662318","doi":"10.1080/00031305.2024.2327535","title":"Thick Data Analytics (TDA): An Iterative and Inductive Framework for Algorithmic Improvement","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"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":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; School of Medicine, Stanford University; National Institutes of Health; Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; SAFER; Subject-matter expert; USable; Data science; Analytics; Domain (mathematical analysis); Machine learning; Data mining; Domain knowledge; Frame (networking); Artificial intelligence; Risk analysis (engineering); Expert system","score_opus":0.0671994435639882,"score_gpt":0.4028620339116792,"score_spread":0.33566259034769097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392662318","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":[0.0052647796,0.00017260425,0.98700064,0.0061094314,0.0003100148,0.0004471759,0.0005067501,0.00014651145,0.000042079628],"genre_scores_gemma":[0.39988014,0.000030290637,0.59773475,0.0018999475,0.0003042706,0.000046320372,0.0000443928,0.000023863866,0.000036045356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983098,0.00021940173,0.00022879633,0.00066893094,0.00024647918,0.0003265781],"domain_scores_gemma":[0.99699354,0.0014789901,0.00015136773,0.0011641028,0.00009125167,0.00012071708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005984974,0.00017219516,0.00023090879,0.00008660072,0.00026904125,0.00044590147,0.0011834557,0.00002762986,0.0000056474746],"category_scores_gemma":[0.0003644418,0.00012383642,0.000018890581,0.00049243274,0.0003122531,0.0003387626,0.00049413426,0.00046202337,0.000007735952],"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":[0.000010075899,0.000018328243,0.00011723575,0.000046695957,0.000059202423,0.000013215683,0.0047513843,0.000034888344,0.000022677094,0.35496375,0.0005003568,0.63946223],"study_design_scores_gemma":[0.00006337857,0.0009578747,0.0038368264,0.000058970814,0.000036187135,0.000007548812,0.0010675231,0.89038515,0.000013200628,0.1001067,0.0032627939,0.00020385986],"about_ca_topic_score_codex":0.0011856743,"about_ca_topic_score_gemma":0.00009805004,"teacher_disagreement_score":0.8903502,"about_ca_system_score_codex":0.000062978754,"about_ca_system_score_gemma":0.0001627837,"threshold_uncertainty_score":0.5049903},"labels":[],"label_agreement":null},{"id":"W4399726225","doi":"10.1080/00031305.2024.2368794","title":"High-Dimensional Propensity Score and Its Machine Learning Extensions in Residual Confounding Control","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Propensity score matching; Confounding; Residual; Computer science; Proxy (statistics); Exploit; Causal inference; Parametric statistics; Machine learning; Econometrics; Artificial intelligence; Data mining; Statistics; Algorithm; Mathematics","score_opus":0.12057004770728635,"score_gpt":0.39189234053654654,"score_spread":0.2713222928292602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399726225","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":[0.9411444,0.00036521643,0.056046367,0.0010746703,0.00008331317,0.00055218156,0.00013211326,0.00040313054,0.00019862926],"genre_scores_gemma":[0.98444796,0.000041807813,0.014851331,0.000332033,0.000054449192,0.00003162512,0.0000107952565,0.000037534493,0.00019249188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863946,0.00026899046,0.0002865076,0.0002808539,0.0002296313,0.00029455323],"domain_scores_gemma":[0.99730337,0.002248378,0.0001386288,0.0001700152,0.000071757524,0.00006787832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005871254,0.00018145287,0.0003951644,0.000117279444,0.000171867,0.00006204726,0.0001149357,0.000023645605,0.000049028666],"category_scores_gemma":[0.001282953,0.00012568593,0.0000201018,0.00027522,0.00033561318,0.000099630604,0.00009714024,0.00050504145,0.000017660097],"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":[0.00019901413,0.00005673265,0.0020354947,0.00011443428,0.000084032035,0.0005437787,0.0009814316,0.00021900966,0.0128379725,0.9527827,0.001108532,0.029036885],"study_design_scores_gemma":[0.0010463246,0.0011764589,0.05082829,0.0012876204,0.00030596257,0.00029374118,0.000760612,0.08463199,0.0022276326,0.85568464,0.00069734437,0.0010593934],"about_ca_topic_score_codex":0.0006763979,"about_ca_topic_score_gemma":0.00039692133,"teacher_disagreement_score":0.097098045,"about_ca_system_score_codex":0.0000704745,"about_ca_system_score_gemma":0.00006422827,"threshold_uncertainty_score":0.51253235},"labels":[],"label_agreement":null},{"id":"W4402407033","doi":"10.1080/00031305.2024.2402898","title":"When Heavy Tails Disrupt Statistical Inference","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","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 Calgary","funders":"","keywords":"Statistical inference; Inference; Econometrics; Computer science; Statistics; Mathematics; Statistical physics; Artificial intelligence; Physics","score_opus":0.03880810499610163,"score_gpt":0.2962289158894527,"score_spread":0.2574208108933511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402407033","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":[0.066885516,0.0014372389,0.9202366,0.0018502835,0.00042989728,0.00018357417,0.00209073,0.00013512753,0.006751055],"genre_scores_gemma":[0.9867421,0.00014447687,0.0117124235,0.00063547166,0.00018482476,0.00002737129,0.000035762478,0.000034437522,0.00048317082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99849755,0.00004055915,0.0005321571,0.00044361592,0.000070306196,0.00041582805],"domain_scores_gemma":[0.9986528,0.0006914859,0.00015261296,0.0003756989,0.000025217336,0.00010219509],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000500641,0.00017891992,0.0004150652,0.000114376315,0.00017576903,0.00022718926,0.0002916104,0.000027912218,0.00043657585],"category_scores_gemma":[0.0004852312,0.00015404288,0.00006495925,0.00032185024,0.00044508374,0.00013491388,0.00007371856,0.00028672352,0.0015300117],"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":[0.000028682036,0.000025698342,0.004642788,0.000029251074,0.000032359563,0.00002213779,0.0013558327,0.000055578963,0.0000046830473,0.9121287,0.005083185,0.076591104],"study_design_scores_gemma":[0.00010497108,0.00020367655,0.052165017,0.00004149649,0.000021673817,0.000004771562,0.00028966795,0.15243201,0.0000066743946,0.7212689,0.07307912,0.00038202628],"about_ca_topic_score_codex":0.004652467,"about_ca_topic_score_gemma":0.0002240944,"teacher_disagreement_score":0.91985655,"about_ca_system_score_codex":0.00008895768,"about_ca_system_score_gemma":0.000063395695,"threshold_uncertainty_score":0.99924743},"labels":[],"label_agreement":null},{"id":"W4403867438","doi":"10.1080/00031305.2024.2421370","title":"Cross-Validatory Z-Residual for Diagnosing Shared Frailty Models","year":2024,"lang":"en","type":"article","venue":"The American Statistician","topic":"Frailty in Older Adults","field":"Medicine","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":"Dalhousie University; University of Saskatchewan","funders":"","keywords":"Residual; Statistics; Computer science; Mathematics; Algorithm","score_opus":0.06678084858081718,"score_gpt":0.39010266550030365,"score_spread":0.32332181691948647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403867438","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":[0.49875546,0.002198008,0.46790925,0.013638735,0.0013276034,0.0025075404,0.006616346,0.0010583743,0.0059886705],"genre_scores_gemma":[0.9742465,0.000048218404,0.018931609,0.0032095164,0.000714562,0.00021776081,0.000226826,0.00010244008,0.002302588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839336,0.00006401692,0.0003198991,0.0004114608,0.00034599472,0.0004652642],"domain_scores_gemma":[0.99748635,0.0016607305,0.00009884614,0.00048158475,0.00011823403,0.00015423041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027466947,0.00021920387,0.00038128867,0.00009696699,0.00018411814,0.00018913351,0.00022145665,0.000035231256,0.00018250667],"category_scores_gemma":[0.0005218421,0.00016003527,0.000107231324,0.0003012919,0.0007204274,0.00014638368,0.00006455948,0.00025849513,0.00011644527],"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":[0.0008105362,0.0002283616,0.0027865989,0.00084250915,0.00075841416,0.0005267493,0.006851212,0.0010668907,0.0032619708,0.02476804,0.31006625,0.6480324],"study_design_scores_gemma":[0.0064445855,0.005600205,0.2642276,0.0030629002,0.002840212,0.00062559015,0.0051052356,0.32038385,0.0077292933,0.09663504,0.28452498,0.0028205377],"about_ca_topic_score_codex":0.00074266276,"about_ca_topic_score_gemma":0.00008217514,"teacher_disagreement_score":0.64521194,"about_ca_system_score_codex":0.00013014785,"about_ca_system_score_gemma":0.0002180052,"threshold_uncertainty_score":0.6526049},"labels":[],"label_agreement":null},{"id":"W4411882452","doi":"10.1080/00031305.2025.2526545","title":"LASSO-Based Survival Prediction Modeling with Multiply Imputed Data: A Case Study in Tuberculosis Mortality Prediction","year":2025,"lang":"en","type":"article","venue":"The American Statistician","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control; St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Lasso (programming language); Statistics; Econometrics; Mathematics; Computer science; Data mining","score_opus":0.05416784748200714,"score_gpt":0.3684578644543723,"score_spread":0.31429001697236514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411882452","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":[0.4727404,0.00000709917,0.52582043,0.00040356177,0.00014712788,0.00047792352,0.00020030556,0.00016373252,0.000039391663],"genre_scores_gemma":[0.9798167,0.0000025966417,0.019635966,0.000318134,0.00005076178,0.000087453525,0.00006727494,0.000015752505,0.0000053563067],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99682164,0.0011243513,0.00047513872,0.00074601517,0.00046537854,0.00036748176],"domain_scores_gemma":[0.9972352,0.0006286465,0.00022132834,0.001681211,0.00015050375,0.00008312094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013520226,0.00021205496,0.0003405094,0.00022312447,0.0003187908,0.00013301996,0.0009158043,0.000026401322,0.000001627987],"category_scores_gemma":[0.00027753867,0.00016164944,0.000020611405,0.0015791577,0.00013092942,0.00026493598,0.00033268039,0.0004683664,0.0000019008764],"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":[0.00007989838,0.0002927909,0.7424753,0.00004247715,0.000100956604,0.0005807001,0.0017222285,0.22400148,0.0000040622576,0.0006034405,0.0000633825,0.030033296],"study_design_scores_gemma":[0.00046368872,0.0003087838,0.2867033,0.00003307017,0.000045429864,0.000024235973,0.0016824922,0.71057373,5.5578874e-7,0.00006736927,0.000006554159,0.00009079003],"about_ca_topic_score_codex":0.11244704,"about_ca_topic_score_gemma":0.03917812,"teacher_disagreement_score":0.50707626,"about_ca_system_score_codex":0.00018901569,"about_ca_system_score_gemma":0.00033099225,"threshold_uncertainty_score":0.9783544},"labels":[],"label_agreement":null},{"id":"W4412709116","doi":"10.1080/00031305.2025.2539241","title":"A Fisher’s Exact Test Justification of the TF–IDF Term-Weighting Scheme","year":2025,"lang":"en","type":"article","venue":"The American Statistician","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Term (time); Weighting; Statistics; Mathematics; Test (biology); Physics","score_opus":0.07572393262271854,"score_gpt":0.4222604066798787,"score_spread":0.34653647405716015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412709116","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":[0.69042796,0.00009295605,0.22439447,0.00674784,0.0009569836,0.00078093697,0.00022183603,0.00010036526,0.07627667],"genre_scores_gemma":[0.9556899,0.0000037183904,0.03948314,0.0008420637,0.00007315548,0.000026802776,0.0000019030193,0.00001568974,0.0038636418],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99654275,0.0010330393,0.000779644,0.00042237647,0.00091129163,0.00031089704],"domain_scores_gemma":[0.9767629,0.020239236,0.0011662655,0.0014336964,0.00034477998,0.000053112395],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0042114803,0.0001723609,0.00039891235,0.00018000444,0.00041396572,0.00013877393,0.001745126,0.000026187372,0.00014713727],"category_scores_gemma":[0.044188965,0.000091722344,0.00011172024,0.002682966,0.0011235416,0.00007549428,0.00032137596,0.00024375715,0.000037912516],"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":[0.000048303584,0.00005711124,0.08662386,0.000011850396,0.00003065791,0.0000015374894,0.00071323436,0.000023325585,0.008158942,0.0062015457,0.024371343,0.8737583],"study_design_scores_gemma":[0.00015561994,0.00008457971,0.95424443,0.00007993625,0.000065627355,0.0000048190773,0.0018150299,0.011300553,0.0014612859,0.02459729,0.006035996,0.00015480704],"about_ca_topic_score_codex":0.00041678088,"about_ca_topic_score_gemma":0.00009681709,"teacher_disagreement_score":0.87360346,"about_ca_system_score_codex":0.0000679752,"about_ca_system_score_gemma":0.00019964091,"threshold_uncertainty_score":0.96386224},"labels":[],"label_agreement":null},{"id":"W4414351985","doi":"10.1080/00031305.2025.2562891","title":"Moving Forward From the COVID-19 Pandemic","year":2025,"lang":"en","type":"article","venue":"The American Statistician","topic":"COVID-19 epidemiological studies","field":"Mathematics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Pandemic; Salient; Action (physics); Exploit; Value (mathematics); Public policy; Coronavirus disease 2019 (COVID-19)","score_opus":0.22388260942896104,"score_gpt":0.4640775369174704,"score_spread":0.24019492748850935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414351985","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":[0.11527513,0.00053664244,0.81879526,0.060148496,0.00023126736,0.000735874,0.00053012895,0.00042712223,0.003320094],"genre_scores_gemma":[0.8736061,0.00021608596,0.013277462,0.11194034,0.00018704569,0.00012745071,0.000011046854,0.000024479114,0.0006100045],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99780566,0.0007535154,0.00044258437,0.00035029778,0.000229542,0.00041842338],"domain_scores_gemma":[0.9473599,0.05147583,0.0003567656,0.00066774455,0.000043799006,0.00009594179],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001263843,0.0002241051,0.00056540983,0.000031785206,0.0006586777,0.000042131007,0.0007419403,0.000030326382,0.000120600926],"category_scores_gemma":[0.032310475,0.00011231684,0.00010782662,0.00047408277,0.001103155,0.000022966353,0.0004004239,0.00031870545,0.00005227802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017664343,0.00007274154,0.22215556,0.000060843366,0.0005370852,0.000020217425,0.0030693344,0.00011214242,0.00009971111,0.28163093,0.4124675,0.07959728],"study_design_scores_gemma":[0.00022640747,0.000054479126,0.08992131,0.00002312144,0.00019800727,0.0000015516819,0.0027173704,0.00062222336,0.000002798452,0.8113726,0.09467712,0.00018303274],"about_ca_topic_score_codex":0.014472888,"about_ca_topic_score_gemma":0.0031540631,"teacher_disagreement_score":0.8055178,"about_ca_system_score_codex":0.00028700824,"about_ca_system_score_gemma":0.00015083989,"threshold_uncertainty_score":0.9920898},"labels":[],"label_agreement":null},{"id":"W7116726263","doi":"10.1080/00031305.2025.2606079","title":"Probabilistic Parameter Estimates that Require Less Small Print","year":2025,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","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":"McGill University","funders":"","keywords":"Probabilistic logic; Estimation theory; Statistical model; Estimation; Bayesian probability","score_opus":0.10987777437965937,"score_gpt":0.3954648102331808,"score_spread":0.2855870358535214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116726263","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":[0.020878261,0.00002764388,0.97010297,0.0010108924,0.00026884506,0.0004968625,0.0001113578,0.00014926333,0.006953898],"genre_scores_gemma":[0.3033552,0.000008066122,0.6949621,0.00084958837,0.00004075548,0.00011738438,0.0000047656317,0.00002956666,0.00063258223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980398,0.0003600527,0.00043341296,0.0004145051,0.00024092637,0.00051134493],"domain_scores_gemma":[0.98589325,0.012830286,0.00031849075,0.00074607664,0.00010878366,0.00010312438],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005500191,0.000294548,0.00059871963,0.000080080645,0.0002406465,0.00013275238,0.00053856714,0.00003895113,0.000093094626],"category_scores_gemma":[0.008776093,0.00019335518,0.00007640062,0.00043805846,0.0011695657,0.000045844674,0.0001747808,0.00030960457,0.00002724027],"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":[0.000046272773,0.000072800816,0.0012211315,0.00013859151,0.000051969593,0.00001717215,0.00018754898,0.0000014037569,0.00003393524,0.7482907,0.0019931954,0.24794528],"study_design_scores_gemma":[0.0001494099,0.00012346638,0.027484633,0.00012538864,0.00016054204,0.000006918837,0.0005018006,0.0038842706,0.00015163767,0.9665829,0.0005858484,0.00024321339],"about_ca_topic_score_codex":0.00044237857,"about_ca_topic_score_gemma":0.00016043217,"teacher_disagreement_score":0.28247693,"about_ca_system_score_codex":0.00008402665,"about_ca_system_score_gemma":0.00012142413,"threshold_uncertainty_score":0.9995734},"labels":[],"label_agreement":null}]}