{"meta":{"query_hash":"ab92b74a1c85","filters":{"venue":"Statistical Science"},"cohort_total":32,"direct_labels_cover":1,"predictions_cover":32,"exported":32,"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/ab92b74a1c85","api":"https://metacan.xera.ac/api/v1/cohort?venue=Statistical+Science"},"results":[{"id":"W1607848239","doi":"10.1214/ss/1009212815","title":"Bayesian backfitting (with comments and a rejoinder by the authors","year":2000,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Additive model; Generalization; Generalized additive model; Mathematics; Nonparametric statistics; Bayesian probability; Computer science; Mathematical optimization; Modular design; Econometrics; Artificial intelligence; Statistics","score_opus":0.04640613272490587,"score_gpt":0.375692202853479,"score_spread":0.32928607012857314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607848239","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":[0.027399892,0.000015681087,0.94408715,0.001811043,0.000045105207,0.00024344583,0.00011066139,0.000043301294,0.026243718],"genre_scores_gemma":[0.50277215,0.0000049116843,0.49604368,0.00056075706,0.000016426276,0.0000126215255,0.000001163846,0.0000095573205,0.00057873124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998423,0.00012472832,0.00020556725,0.0003432557,0.00049133773,0.00041214674],"domain_scores_gemma":[0.9969312,0.0025099027,0.000040860403,0.00022530365,0.00005089162,0.00024182258],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012380561,0.00011938107,0.00014918199,0.000018173392,0.00048482817,0.00016120952,0.0002652302,0.000028346301,0.0013838186],"category_scores_gemma":[0.001986077,0.00006389188,0.000008494185,0.0003174967,0.0015899037,0.00008412459,0.000056520294,0.0001885256,0.00001955595],"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":[0.000019451727,0.00004853464,0.000609613,0.000017064858,0.000005203963,0.000007440834,0.00031928363,4.6784467e-7,0.00013263976,0.7113792,0.0059827836,0.28147835],"study_design_scores_gemma":[0.0003963351,0.0002828231,0.010942934,0.00006651118,0.000035153073,0.000045072873,0.00024064512,0.022563584,0.00023247262,0.96085066,0.0040456224,0.00029818778],"about_ca_topic_score_codex":0.000063398715,"about_ca_topic_score_gemma":0.0000074234813,"teacher_disagreement_score":0.47537225,"about_ca_system_score_codex":0.000025657651,"about_ca_system_score_gemma":0.000053586806,"threshold_uncertainty_score":0.99952906},"labels":[],"label_agreement":null},{"id":"W1986014248","doi":"10.1214/09-sts283","title":"A Conversation with James Hannan","year":2010,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Military service; History; Feeling; China; World War II; Fall of man; Sociology; Management; Operations research; Gerontology; Psychology; Medicine; Law; Archaeology; Engineering; Political science; Politics","score_opus":0.11054459628420174,"score_gpt":0.4443533261635207,"score_spread":0.333808729879319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986014248","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":[0.08385284,0.0000015951847,0.9052867,0.0009860414,0.00088122266,0.00016601842,0.00006572849,0.000096422715,0.008663402],"genre_scores_gemma":[0.42173764,5.805184e-7,0.57786465,0.00008772495,0.00002591516,0.0000083738705,0.0000021861165,0.000003884206,0.00026903267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905354,0.00003290879,0.000116191375,0.00022657236,0.00034245316,0.0002283519],"domain_scores_gemma":[0.9977098,0.0017277151,0.000052191037,0.00019609387,0.00017371349,0.00014047606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008695095,0.000071134265,0.0000924381,0.000058081445,0.00014949207,0.00007709574,0.00019001066,0.000024717456,0.0006802969],"category_scores_gemma":[0.010336583,0.000049113823,0.000007021362,0.00027200967,0.001260606,0.000091219335,0.000029331613,0.00014066114,0.000058521273],"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":[0.000008188842,0.000027498201,0.0005932685,0.000008980245,0.0000015275147,0.0000023723217,0.0005570254,1.0056718e-7,0.0024203707,0.98480546,0.0040889713,0.0074862167],"study_design_scores_gemma":[0.0002299981,0.000103213664,0.023714073,0.000008512508,0.000016995325,0.000023090091,0.00093988294,0.0007228448,0.0053034257,0.96421766,0.004548122,0.00017215832],"about_ca_topic_score_codex":0.000026506079,"about_ca_topic_score_gemma":0.00004233302,"teacher_disagreement_score":0.33788478,"about_ca_system_score_codex":0.000018382327,"about_ca_system_score_gemma":0.00026855225,"threshold_uncertainty_score":0.9979998},"labels":[],"label_agreement":null},{"id":"W2015928670","doi":"10.1214/088342306000000033","title":"Elaboration on Two Points Raised in “Classifier Technology and the Illusion of Progress”","year":2006,"lang":"en","type":"article","venue":"Statistical Science","topic":"Mathematics Education and Teaching Techniques","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Elaboration; Illusion; Illusion of control; Elaboration likelihood model","score_opus":0.013158409313027176,"score_gpt":0.37363279327985655,"score_spread":0.36047438396682935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015928670","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":[0.5663338,0.000075868425,0.16720766,0.044930823,0.00029397002,0.00154252,0.00001895603,0.00023098137,0.21936542],"genre_scores_gemma":[0.9733074,0.000004223147,0.026550619,0.000045396264,0.000013341624,0.000016426273,6.0356706e-7,0.0000015686919,0.00006047353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99913436,0.000113871516,0.00015082781,0.0001354576,0.0003250069,0.00014047977],"domain_scores_gemma":[0.99941325,0.0003160006,0.000066270404,0.00009998898,0.000076760356,0.000027708704],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021821377,0.000038856462,0.00007789501,0.0001641957,0.00027332557,0.00004277225,0.00018281663,0.000027992925,0.000048641083],"category_scores_gemma":[0.0016303753,0.000024945488,0.0000053866347,0.00085392955,0.0040154033,0.00006750009,0.000034627938,0.000084105384,0.0000027728909],"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":[0.000006606063,0.00004257145,0.0012474572,0.000002484124,1.7205089e-7,2.664258e-7,0.00096316123,1.7829896e-7,0.00012945144,0.9901323,0.000090979585,0.0073844194],"study_design_scores_gemma":[0.0002687549,0.000025084377,0.008942013,0.000024177969,0.0000014949537,2.8764768e-7,0.0004390646,0.0009347547,0.00035835427,0.98799944,0.00096309156,0.000043495213],"about_ca_topic_score_codex":0.0003526206,"about_ca_topic_score_gemma":0.00028281595,"teacher_disagreement_score":0.40697354,"about_ca_system_score_codex":0.0000420693,"about_ca_system_score_gemma":0.00014371173,"threshold_uncertainty_score":0.9986951},"labels":[],"label_agreement":null},{"id":"W2018261002","doi":"10.1214/ss/1030550863","title":"A conversation with Samuel Kotz","year":2002,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"George (robot); Library science; Hebrew; Chapel; Compendium; Honor; Encyclopedia; Mathematics; Classics; Management; History; Computer science; Art history","score_opus":0.1103343508054152,"score_gpt":0.36598542371879855,"score_spread":0.25565107291338335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018261002","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":[0.002932537,0.0000024946169,0.9771137,0.001179132,0.000028339236,0.00017179213,0.000184239,0.000098569944,0.01828915],"genre_scores_gemma":[0.86306,0.0000012066117,0.13650855,0.00014957113,0.000013021665,0.00002928305,0.000010695266,0.000005014707,0.00022264203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987824,0.000019020015,0.00017346755,0.00026834552,0.00049888314,0.0002578719],"domain_scores_gemma":[0.998769,0.0006052821,0.00005239661,0.0001931616,0.00017049302,0.00020966565],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021468953,0.000083844585,0.00009585091,0.00004353716,0.00025081675,0.00007696847,0.00016908796,0.000020800007,0.0037919027],"category_scores_gemma":[0.0016908747,0.00006377329,0.000010169957,0.0005780158,0.0009617556,0.00014540939,0.0000240718,0.00007842792,0.0005262127],"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":[0.000002647501,0.00006757499,0.00006213976,0.0000075905323,0.0000016063418,0.0000022360098,0.0000967872,0.0000015785292,0.00015693443,0.99031967,0.004143366,0.005137877],"study_design_scores_gemma":[0.00061939127,0.00016722706,0.02347877,0.00002627213,0.000041768024,0.000033271404,0.0002349031,0.18106143,0.0006130451,0.7903327,0.0030165191,0.00037471572],"about_ca_topic_score_codex":0.000007947007,"about_ca_topic_score_gemma":0.0000040557597,"teacher_disagreement_score":0.8601275,"about_ca_system_score_codex":0.000074474134,"about_ca_system_score_gemma":0.000038015954,"threshold_uncertainty_score":0.9971188},"labels":[],"label_agreement":null},{"id":"W2046736307","doi":"10.1214/07-sts241","title":"A.-M. Guerry’s Moral Statistics of France: Challenges for Multivariable Spatial Analysis","year":2007,"lang":"en","type":"article","venue":"Statistical Science","topic":"Census and Population Estimation","field":"Mathematics","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variety (cybernetics); Multivariate statistics; Thematic map; Multivariate analysis; Spatial analysis; Literacy; Foundation (evidence)","score_opus":0.08649883077657106,"score_gpt":0.40226199249817723,"score_spread":0.3157631617216062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046736307","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":[0.008416663,0.000019270834,0.9893301,0.00006197338,0.00013989526,0.00022131813,0.0006230691,0.00002263249,0.0011650875],"genre_scores_gemma":[0.57582045,0.000002949453,0.42405206,0.000008283971,0.000029546965,0.0000041605385,0.000025391042,0.00000459837,0.000052540567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99841195,0.000018335271,0.00043903323,0.0002744015,0.0005222928,0.00033399503],"domain_scores_gemma":[0.99748766,0.0016045815,0.0001843764,0.00020726546,0.000386245,0.00012984339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016481844,0.00009869374,0.0002578578,0.00017374677,0.00015087053,0.000018679884,0.0001695543,0.00004512053,0.00017145126],"category_scores_gemma":[0.0029823694,0.00008616834,0.00003994138,0.00058046536,0.00036238786,0.0000982583,0.00003238358,0.00005842601,0.000003437466],"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":[0.000026818776,0.000086490494,0.0044671185,0.000081248974,0.000025189287,0.0000011867816,0.0002586081,0.0001755058,0.00031836398,0.957176,0.00014188097,0.037241567],"study_design_scores_gemma":[0.0004006741,0.0001259379,0.31902573,0.000013704606,0.00021756082,8.930528e-7,0.000067719026,0.24045856,0.0007351324,0.43836904,0.00040803643,0.000177006],"about_ca_topic_score_codex":0.00021653542,"about_ca_topic_score_gemma":0.00028745068,"teacher_disagreement_score":0.5674038,"about_ca_system_score_codex":0.00004329304,"about_ca_system_score_gemma":0.000069966016,"threshold_uncertainty_score":0.357039},"labels":[],"label_agreement":null},{"id":"W2049645191","doi":"10.1214/08-sts272","title":"A Conversation with Martin Bradbury Wilk","year":2010,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Statistical Methods and Models","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":true,"ca_institutions":"McGill University; Université Laval; Statistics Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Iowa State University; American Association for the Advancement of Science","keywords":"Statistician; Conversation; Library science; Management; Operations research; Sociology; Statistics; Mathematics; Computer science; Economics","score_opus":0.05654453792667748,"score_gpt":0.4258454905908548,"score_spread":0.36930095266417734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049645191","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":[0.027851535,9.2000346e-7,0.96634686,0.0003768779,0.00014941696,0.00016269322,0.000040758936,0.000060987997,0.0050099315],"genre_scores_gemma":[0.43045035,2.8579177e-7,0.56936455,0.00006517143,0.000023579716,0.000008429954,0.0000010992968,0.000006555495,0.00007997681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984965,0.000033844317,0.00018598425,0.00038122822,0.0005173646,0.00038509714],"domain_scores_gemma":[0.99797845,0.0012367426,0.00006135944,0.00030797604,0.00014136196,0.000274085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084596424,0.00010957863,0.0001492004,0.00004485175,0.00018302104,0.00006113396,0.00027116048,0.000035660014,0.0004557919],"category_scores_gemma":[0.0066557107,0.00007605104,0.000011532818,0.00030178827,0.0013868652,0.00021289905,0.00008191293,0.00025058628,0.000030936208],"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":[0.00002198388,0.00003593905,0.00018374718,0.000012588015,0.000001640734,0.000013023704,0.00010205415,0.0000011275532,0.0073672794,0.9687601,0.00024362128,0.023256928],"study_design_scores_gemma":[0.00023615442,0.00011672379,0.0024473593,0.0000094281995,0.000013423902,0.000017956265,0.000052559513,0.0142746745,0.0011697231,0.98104537,0.00046101454,0.00015559376],"about_ca_topic_score_codex":0.000014814859,"about_ca_topic_score_gemma":0.000038121532,"teacher_disagreement_score":0.40259883,"about_ca_system_score_codex":0.000024553528,"about_ca_system_score_gemma":0.0001369099,"threshold_uncertainty_score":0.7967988},"labels":[],"label_agreement":null},{"id":"W2052561043","doi":"10.1214/09-sts301","title":"The Impact of Levene’s Test of Equality of Variances on Statistical Theory and Practice","year":2009,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":650,"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; National Science Foundation","keywords":"Levene's test; Mathematics; F-test of equality of variances; Statistics; Test (biology); Econometrics; Statistical hypothesis testing","score_opus":0.15129792034578257,"score_gpt":0.5467800411769967,"score_spread":0.39548212083121415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052561043","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":[0.0042335233,0.000036573983,0.98845166,0.00011951883,0.000030960997,0.00018141922,0.00081129355,0.000007928256,0.0061271135],"genre_scores_gemma":[0.58705103,0.000017962251,0.41288725,0.000017653294,0.000006741065,0.000001635577,6.246195e-7,0.0000033817505,0.00001371598],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975276,0.00057444227,0.0005966143,0.00030663266,0.0006613941,0.0003333469],"domain_scores_gemma":[0.9186488,0.08022306,0.0003293374,0.00031008528,0.0003274753,0.00016122997],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.006671376,0.00013750266,0.00037913298,0.00003894065,0.00015152429,0.000021290585,0.00028596597,0.000038053677,0.00004115491],"category_scores_gemma":[0.1314929,0.000078402416,0.000034978828,0.00029187088,0.002923136,0.0001453931,0.00006086084,0.00015082651,7.57556e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033401357,0.00028112967,0.00003126317,0.0000334652,0.000009292427,0.0000024296535,0.00016040918,0.000017392684,0.0049467445,0.9274985,0.000045384415,0.06663997],"study_design_scores_gemma":[0.00019206182,0.0015490466,0.016276918,0.00004344415,0.000034955843,0.000006583099,0.00014208765,0.0020003465,0.0013053274,0.97834843,0.00001119963,0.00008957943],"about_ca_topic_score_codex":0.000048597314,"about_ca_topic_score_gemma":0.000002455309,"teacher_disagreement_score":0.58281755,"about_ca_system_score_codex":0.000038367816,"about_ca_system_score_gemma":0.00022741946,"threshold_uncertainty_score":0.9997903},"labels":[],"label_agreement":null},{"id":"W2056621649","doi":"10.1214/10-sts321","title":"Identification, Inference and Sensitivity Analysis for Causal Mediation Effects","year":2010,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1558,"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":"York University; University of Wisconsin-Madison; University of Pennsylvania; Harvard University; National Science Foundation","keywords":"Causal inference; Estimator; Robustness (evolution); Identification (biology); Sensitivity (control systems); Randomized experiment; Inference; Causal model; Parametric statistics","score_opus":0.05207382361030993,"score_gpt":0.4371451219746848,"score_spread":0.38507129836437487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056621649","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":[0.18196751,0.000001050317,0.8173853,0.000081725404,0.00008277083,0.00025845933,0.000057069694,0.00009072391,0.00007535482],"genre_scores_gemma":[0.7764116,0.0000014634646,0.22346887,0.000023325589,0.000022454999,0.00004510211,0.000007246261,0.0000043623463,0.000015575552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987804,0.000040717165,0.00021147699,0.00037923042,0.00033488488,0.00025323688],"domain_scores_gemma":[0.99408096,0.005082025,0.00010447693,0.00026225278,0.00031784826,0.00015244556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016607294,0.000098535515,0.00018165815,0.00014770863,0.00022145496,0.000104654115,0.00010115028,0.000051454812,0.00001976052],"category_scores_gemma":[0.023385517,0.00008530857,0.00002013267,0.0006903958,0.00084091845,0.00031484847,0.000064305255,0.00013764962,0.0000037598386],"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":[0.0000031213578,0.000022621021,0.003487406,0.000028107042,0.000008956951,0.0000018878368,0.00008474752,0.0000019666754,0.14909129,0.8422166,0.00003918402,0.005014085],"study_design_scores_gemma":[0.000077205026,0.000044522072,0.09991317,0.0000041834155,0.00009859279,0.000002692269,0.000011114556,0.022031447,0.036300242,0.84135634,0.000018941853,0.00014157593],"about_ca_topic_score_codex":0.00002195275,"about_ca_topic_score_gemma":0.00034688856,"teacher_disagreement_score":0.5944441,"about_ca_system_score_codex":0.000030140995,"about_ca_system_score_gemma":0.000080307356,"threshold_uncertainty_score":0.9848409},"labels":[],"label_agreement":null},{"id":"W2058153057","doi":"10.1214/088342306000000268","title":"Maty’s Biography of Abraham De Moivre, Translated, Annotated and Augmented","year":2007,"lang":"en","type":"article","venue":"Statistical Science","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Murdoch University; University of Chicago; University of Oxford; Université Laval; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Biography; Generalization; Binomial (polynomial); Mathematics; Philosophy; Classics; Art history; History; Statistics; Epistemology","score_opus":0.047024176506161364,"score_gpt":0.42348863862412095,"score_spread":0.3764644621179596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058153057","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":[0.3167883,0.00004120201,0.67896426,0.00014238164,0.000026430598,0.0002182316,0.00020914244,0.000038545993,0.0035714833],"genre_scores_gemma":[0.8362656,0.000010244008,0.1636511,0.00002909574,0.000004955272,0.0000031073193,0.0000025930967,0.0000056581807,0.000027634444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794513,0.000060067974,0.0003622402,0.0003232813,0.0006768146,0.000632479],"domain_scores_gemma":[0.99693674,0.0022402569,0.00004475403,0.00018996735,0.00018132286,0.00040698115],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0031847672,0.000104028244,0.00019627051,0.00018537985,0.00016511731,0.000037489583,0.00025693377,0.00005507066,0.00016425419],"category_scores_gemma":[0.0038130172,0.000085084335,0.000025435806,0.0011167014,0.002891272,0.0001036136,0.000057844263,0.00017696945,0.000005363899],"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":[0.00011841711,0.0002092128,0.0022677535,0.00016056222,0.00001065393,0.00003295763,0.0003947924,4.4431215e-7,0.013411407,0.9594002,0.00020259929,0.023791047],"study_design_scores_gemma":[0.00037512317,0.00023686538,0.06933154,0.00003640346,0.000016448212,0.00001151013,0.00007064835,0.0034232973,0.006873558,0.9193661,0.00012419613,0.00013429661],"about_ca_topic_score_codex":0.000118931064,"about_ca_topic_score_gemma":0.00006086282,"teacher_disagreement_score":0.5194773,"about_ca_system_score_codex":0.00003914283,"about_ca_system_score_gemma":0.00013722958,"threshold_uncertainty_score":0.99982226},"labels":[],"label_agreement":null},{"id":"W2105640027","doi":"10.1214/08-sts273","title":"Accurate Parametric Inference for Small Samples","year":2008,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":59,"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":"Université de Neuchâtel; University of Toronto; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Inference; Parametric statistics; Statistical inference; Logistic regression; Focus (optics); Computer science; Sampling (signal processing); Parametric model; Mathematics; Variety (cybernetics); Econometrics; Asymptotic analysis; Applied mathematics; Statistics; Machine learning; Artificial intelligence","score_opus":0.28638891724177035,"score_gpt":0.4476443073628183,"score_spread":0.16125539012104795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105640027","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":[0.007878119,0.000010143044,0.9890676,0.0001026003,0.0001840704,0.00035417252,0.00033509207,0.00008218712,0.0019859902],"genre_scores_gemma":[0.34731004,0.000009323454,0.6524559,0.00007888075,0.000036480873,0.000046608267,0.0000030244748,0.000008831318,0.000050885337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977503,0.00007599081,0.00040812604,0.00057159876,0.0004928881,0.00070112007],"domain_scores_gemma":[0.98361045,0.0152535215,0.000109560715,0.0003376298,0.0003316987,0.0003571228],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010853232,0.00018580104,0.0003233399,0.00014915492,0.0005631314,0.00009346634,0.0005688912,0.000057225036,0.00027203132],"category_scores_gemma":[0.05732296,0.00014434571,0.00004321177,0.0010566813,0.0017629795,0.00014691663,0.00011792421,0.00015624643,0.0000440282],"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":[0.000016441028,0.00006290995,0.00063117535,0.00003810471,0.0000032753328,0.000011654788,0.00007027836,8.3884106e-7,0.00020997413,0.9639087,0.0005491818,0.034497518],"study_design_scores_gemma":[0.00022842306,0.00019233779,0.020944705,0.0000190453,0.000016485079,0.00001938237,0.000022388509,0.007536409,0.0005617568,0.96973217,0.00048474464,0.0002421636],"about_ca_topic_score_codex":0.000055875174,"about_ca_topic_score_gemma":0.000011746734,"teacher_disagreement_score":0.33943194,"about_ca_system_score_codex":0.000063807,"about_ca_system_score_gemma":0.00037959628,"threshold_uncertainty_score":0.9506176},"labels":[],"label_agreement":null},{"id":"W2191641151","doi":"10.1214/15-sts524","title":"Functional Data Analysis of Amplitude and Phase Variation","year":2015,"lang":"en","type":"article","venue":"Statistical Science","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":177,"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":"Functional data analysis; Amplitude; Computer science; Variation (astronomy); Curse of dimensionality; Phase (matter); Algorithm; Representation (politics); Variance (accounting); Function (biology); Mathematics; Mathematical optimization; Artificial intelligence; Machine learning; Physics; Optics","score_opus":0.2320737521945765,"score_gpt":0.4232358640783437,"score_spread":0.1911621118837672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191641151","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":[0.027229853,0.00000568851,0.9710753,0.00009615077,0.00004218619,0.000044214634,0.00043763462,0.000010453416,0.0010585476],"genre_scores_gemma":[0.7523932,6.459251e-7,0.24749838,0.00002363866,0.000011392366,0.0000012210829,0.00004843581,0.0000011132897,0.000022005253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990376,0.000029523253,0.00017802414,0.00025792935,0.00038770807,0.00010916638],"domain_scores_gemma":[0.9988093,0.0005747564,0.000065278655,0.0002918035,0.00012403967,0.00013481676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013383363,0.000043158463,0.00013088879,0.0001115522,0.00006361157,0.00003545861,0.0001868862,0.000018425928,0.0002840039],"category_scores_gemma":[0.004383461,0.00003165565,0.0000088767565,0.0010248539,0.0002946149,0.00015048891,0.00016424994,0.0000389679,0.000004433078],"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":[0.000009180992,0.00015544813,0.000742251,0.000003513736,0.00003227916,0.0000011378017,0.000042289168,0.000011297433,0.0006674364,0.9945074,0.0014715659,0.0023562561],"study_design_scores_gemma":[0.0007472946,0.00015829901,0.28199673,0.0000039788274,0.0006149457,0.0000031682937,0.00009102239,0.2504488,0.00005282333,0.4653255,0.0004153039,0.00014214961],"about_ca_topic_score_codex":0.00004792143,"about_ca_topic_score_gemma":0.00000547663,"teacher_disagreement_score":0.7251633,"about_ca_system_score_codex":0.000018116176,"about_ca_system_score_gemma":0.0000780138,"threshold_uncertainty_score":0.5247729},"labels":[],"label_agreement":null},{"id":"W2278053714","doi":"10.1214/15-sts531","title":"Analysis Methods for Computer Experiments: How to Assess and What Counts?","year":2016,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","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 British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Smoothness; Computer science; Gaussian process; Bayesian probability; Bayes' theorem; Regression; Regression analysis; Code (set theory); Exponential function; Function (biology); Machine learning; Statistics; Algorithm; Econometrics; Artificial intelligence; Gaussian; Data mining; Mathematics","score_opus":0.050557874987754145,"score_gpt":0.425066255779265,"score_spread":0.37450838079151083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2278053714","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":[0.000014204388,0.000021507194,0.9984357,0.0007039174,0.0005443088,0.00013716839,0.000011000175,0.00003765089,0.00009459258],"genre_scores_gemma":[0.0047228853,0.000012355067,0.994805,0.00028064047,0.000024705525,0.00002578148,6.195653e-7,0.0000033519677,0.0001247015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891436,0.00004455049,0.00008882953,0.0004935049,0.00021211393,0.00024661628],"domain_scores_gemma":[0.9985144,0.00080557074,0.000033567234,0.00023316806,0.00021393436,0.00019932308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050246005,0.00007710162,0.0001232566,0.00013104218,0.0001318232,0.0005328524,0.00040506548,0.000016064965,0.000031145686],"category_scores_gemma":[0.00053803035,0.000051961124,0.000017485801,0.0008574218,0.00025718522,0.0013233164,0.00021088845,0.000020752252,0.0000137192565],"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":[0.0000017516419,0.00001353629,0.000029701045,0.0000013926622,0.000011595897,9.1631995e-7,0.0000873218,0.00011458584,0.0013156103,0.08413006,0.0001484767,0.91414505],"study_design_scores_gemma":[0.00026975104,0.00011522698,0.0023455035,0.000013326691,0.000018917232,0.0000021540184,0.00003911765,0.97925055,0.0030928086,0.004833137,0.009779171,0.00024032396],"about_ca_topic_score_codex":9.596188e-7,"about_ca_topic_score_gemma":4.4451536e-7,"teacher_disagreement_score":0.979136,"about_ca_system_score_codex":0.00006956003,"about_ca_system_score_gemma":0.00004644133,"threshold_uncertainty_score":0.5138308},"labels":[],"label_agreement":null},{"id":"W2574504272","doi":"10.1214/16-sts573","title":"Bayes, Reproducibility and the Quest for Truth","year":2016,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; York University; University of Toronto; University of British Columbia","funders":"","keywords":"Bayes' theorem; Prior probability; Mathematics; Bayes factor; Statistics; Computer science; Mathematical economics; Bayesian probability; Econometrics","score_opus":0.1288360619024471,"score_gpt":0.4732471539066497,"score_spread":0.3444110920042026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574504272","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":[0.0012065498,0.000018238921,0.9948718,0.0018938244,0.00013433391,0.0003812833,0.0002514776,0.000030306504,0.0012122196],"genre_scores_gemma":[0.3281774,0.000007456001,0.6714981,0.00007352819,0.000039729555,0.000039281,2.9018247e-7,0.000005662247,0.00015851506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813837,0.00011042724,0.00024640094,0.0009141094,0.0002630203,0.00032767985],"domain_scores_gemma":[0.979733,0.019285416,0.000055571774,0.0006402404,0.00013289679,0.00015286145],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0072811153,0.00008988724,0.00019856571,0.000015704789,0.00027968743,0.000039286264,0.00020784944,0.000020587002,0.000039187267],"category_scores_gemma":[0.11578936,0.00003750528,0.000019608595,0.00011287647,0.0034956154,0.00011447986,0.000099394325,0.000051173367,0.0000030382594],"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":[0.00006689254,0.000014359713,0.000014096252,0.000013030159,0.0000013747274,5.0328106e-7,0.00003959313,5.0028635e-8,0.00029081543,0.895717,0.00015714687,0.1036851],"study_design_scores_gemma":[0.00063651736,0.000058648227,0.00071959017,0.000014692821,0.000013684238,0.0000030855597,0.000011711104,0.0010845967,0.0004271449,0.9963685,0.00058069447,0.000081115104],"about_ca_topic_score_codex":0.000006904852,"about_ca_topic_score_gemma":0.000006941978,"teacher_disagreement_score":0.32697085,"about_ca_system_score_codex":0.000033594097,"about_ca_system_score_gemma":0.00006626059,"threshold_uncertainty_score":0.9992163},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2949308593","doi":"10.1214/088342306000000187","title":"Evaluating Pricing Strategy Using e-Commerce Data: Evidence and Estimation Challenges","year":2006,"lang":"en","type":"article","venue":"Statistical Science","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":65,"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":"York University","keywords":"Estimation; Econometrics; Computer science; Data science; Economics","score_opus":0.27880005044210465,"score_gpt":0.4203782375386332,"score_spread":0.14157818709652853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949308593","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":[0.89694667,0.0010435041,0.09420919,0.0004976041,0.00024223133,0.000308663,0.000009657601,0.00011878774,0.006623725],"genre_scores_gemma":[0.97914284,0.000016255919,0.020583747,0.00006899488,0.00015685437,0.0000025566126,0.000009578857,0.000008100321,0.000011092091],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832565,0.000020895504,0.00024237264,0.0005411465,0.00052842236,0.0003414919],"domain_scores_gemma":[0.99899197,0.00043083171,0.00011682397,0.00030774073,0.00013154677,0.00002106589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023911274,0.00012303436,0.00013049078,0.0001369009,0.00056951825,0.00063847203,0.00038025572,0.000023970713,0.000069517715],"category_scores_gemma":[0.0013322928,0.00011193874,0.000007631259,0.0004964114,0.00036673743,0.0029492774,0.00050146785,0.00010554647,0.000015960723],"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":[0.0000137298875,0.000042534924,0.022831183,0.00022400566,0.0000022330896,0.000011846392,0.000036419842,0.0010879146,0.007977902,0.0943935,0.000060497157,0.87331825],"study_design_scores_gemma":[0.000095565294,0.000007945847,0.30191302,0.00011369373,0.00005047433,0.0000053904087,0.00007682875,0.69049156,0.000011093604,0.0070164823,0.000064986976,0.00015294093],"about_ca_topic_score_codex":0.0026390483,"about_ca_topic_score_gemma":0.00019587419,"teacher_disagreement_score":0.8731653,"about_ca_system_score_codex":0.000033027336,"about_ca_system_score_gemma":0.000070667105,"threshold_uncertainty_score":0.6156801},"labels":[],"label_agreement":null},{"id":"W2963175784","doi":"10.1214/19-sts706","title":"Comment: Minimalist $g$-Modeling","year":2019,"lang":"en","type":"article","venue":"Statistical Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Computer science; Simple (philosophy); Bayes' theorem; Nonparametric statistics; Maximum likelihood; Machine learning; Artificial intelligence; Mathematical optimization; Econometrics; Algorithm; Mathematics; Bayesian probability; Statistics","score_opus":0.01871884721556452,"score_gpt":0.3057036943803385,"score_spread":0.286984847164774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963175784","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":[0.0012231256,0.000018647996,0.97253346,0.0024770298,0.00039217324,0.00011362577,0.000006473215,0.000070511356,0.023164926],"genre_scores_gemma":[0.41663176,0.0000014987037,0.5818769,0.001394075,0.000014355112,0.0000024551491,5.138018e-7,0.0000026470727,0.000075836106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821365,0.000055212244,0.00017650884,0.00056784204,0.0005262632,0.0004605273],"domain_scores_gemma":[0.99894905,0.00017633909,0.00003100439,0.000523183,0.00008550964,0.00023488577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011574621,0.000101978854,0.00013598318,0.00007139251,0.00017705862,0.00028268268,0.0012765257,0.000027299082,0.000097264536],"category_scores_gemma":[0.00015348093,0.00008253151,0.000023194765,0.0005740289,0.00021725809,0.00052470545,0.00036777346,0.000123007,0.00027368718],"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":[0.0000013987662,0.000015489151,0.000057545887,0.000004665999,7.815482e-7,0.000004202468,0.00009295712,0.00001703195,0.0008422747,0.9640021,0.0003003159,0.034661256],"study_design_scores_gemma":[0.00012371677,0.0000573238,0.00023392873,0.000009331923,0.0000015569186,0.0000075112985,0.0000059718477,0.78427094,0.0002755247,0.21261671,0.0022550202,0.00014247214],"about_ca_topic_score_codex":0.000029307612,"about_ca_topic_score_gemma":0.0000012312967,"teacher_disagreement_score":0.7842539,"about_ca_system_score_codex":0.000046586963,"about_ca_system_score_gemma":0.00013935684,"threshold_uncertainty_score":0.35177863},"labels":[],"label_agreement":null},{"id":"W3033114400","doi":"10.1214/22-sts879","title":"The Role of Exchangeability in Causal Inference","year":2023,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Causal inference; Inference; Property (philosophy); Contrast (vision); Bayesian probability; Predictive inference; Bayesian inference; Econometrics; Causal model; Frequentist inference; Computer science; Causal structure; Statistical inference; Mathematics; Artificial intelligence; Epistemology; Statistics; Philosophy","score_opus":0.12924522197799054,"score_gpt":0.4691296344740189,"score_spread":0.33988441249602835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033114400","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":[0.6048015,0.00007308428,0.34320036,0.0007552733,0.00030237884,0.001318288,0.00021311695,0.00089602417,0.04844],"genre_scores_gemma":[0.97739583,0.000017667799,0.022469485,0.000007466938,0.00000749516,0.00003749531,8.818486e-7,0.000004762094,0.000058926442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998578,0.000057891106,0.00027403477,0.00023676486,0.00046312137,0.0003901738],"domain_scores_gemma":[0.9953895,0.004022928,0.00006396997,0.00032960845,0.00011812024,0.00007585051],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019334125,0.00007699207,0.0001345626,0.00007839992,0.00012796327,0.00002697176,0.0004584997,0.000028745526,0.0000446387],"category_scores_gemma":[0.013070271,0.00005111047,0.000012123216,0.0012216482,0.0016127657,0.00013659878,0.00022605699,0.00013742417,0.00002272515],"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":[0.0000045722873,0.000018829149,0.0032691874,0.0000100381185,4.818703e-7,0.0000023494306,0.00016613207,0.0000019045751,0.0047685606,0.95010996,0.000055068078,0.041592892],"study_design_scores_gemma":[0.000033356107,0.000048218502,0.02519238,0.000015884762,0.0000013205337,4.9067256e-7,0.00022170837,0.0029598144,0.0071575847,0.9640683,0.00023751086,0.00006340807],"about_ca_topic_score_codex":0.00007425215,"about_ca_topic_score_gemma":0.0002695524,"teacher_disagreement_score":0.37259436,"about_ca_system_score_codex":0.000071993585,"about_ca_system_score_gemma":0.00013895592,"threshold_uncertainty_score":0.9952431},"labels":[],"label_agreement":null},{"id":"W3083830176","doi":"10.1214/20-sts786","title":"On Nearly Assumption-Free Tests of Nominal Confidence Interval Coverage for Causal Parameters Estimated by Machine Learning","year":2020,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Shanghai University of Finance and Economics; University of Toronto; Eidgenössische Technische Hochschule Zürich; University of Washington; Office of Naval Research; Harvard University; National Science Foundation","keywords":"Estimator; Mathematics; Smoothness; Statistics; Confidence interval; Null hypothesis; Null (SQL); Algorithm; Computer science; Mathematical analysis","score_opus":0.14827249785666008,"score_gpt":0.42738724172025827,"score_spread":0.2791147438635982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083830176","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":[0.07653661,0.000006662123,0.92188567,0.00029929905,0.000038409013,0.0003351156,0.00052307895,0.00014766985,0.00022751518],"genre_scores_gemma":[0.70495695,0.0000019434008,0.29481432,0.00014980909,0.0000066134608,0.000022502662,0.0000142269455,0.000012204469,0.00002144146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982417,0.00005419803,0.00037730052,0.00043466466,0.0005218887,0.0003702349],"domain_scores_gemma":[0.9954509,0.003709844,0.00019181994,0.00023082805,0.00018039286,0.00023622013],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005505922,0.00017069055,0.00029985374,0.000047339377,0.00013793535,0.00007333191,0.0005515435,0.000048632402,0.000109977685],"category_scores_gemma":[0.026883721,0.00015056331,0.00003382602,0.00028476666,0.00089947035,0.00024337905,0.00014920534,0.0002689288,0.000013084111],"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":[0.0003118929,0.00014888264,0.00079055224,0.00019172934,0.00001195906,0.000017970324,0.0004322147,0.0003183645,0.11568566,0.87005985,0.003989927,0.008041013],"study_design_scores_gemma":[0.00069008284,0.003284235,0.0012172231,0.00017727276,0.00003933303,0.000007445393,0.000040565257,0.16835305,0.0338299,0.79188895,0.000088985245,0.00038294334],"about_ca_topic_score_codex":0.00008126993,"about_ca_topic_score_gemma":0.0000123328355,"teacher_disagreement_score":0.62842035,"about_ca_system_score_codex":0.000082253326,"about_ca_system_score_gemma":0.0001010529,"threshold_uncertainty_score":0.9813132},"labels":[],"label_agreement":null},{"id":"W3088631473","doi":"10.1214/23-sts885","title":"Parameter Restrictions for the Sake of Identification: Is There Utility in Asserting That Perhaps a Restriction Holds?","year":2023,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Statistical model; Key (lock); Context (archaeology); Computer science; Bayesian probability; Value (mathematics); Mathematical economics; Econometrics; Mathematics; Artificial intelligence; Machine learning","score_opus":0.2103441734683346,"score_gpt":0.45051168967869337,"score_spread":0.24016751621035878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088631473","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":[0.03858122,0.000012500613,0.9592257,0.00060030766,0.0001954915,0.0004386763,0.00025573475,0.00004350241,0.00064686243],"genre_scores_gemma":[0.77577966,0.000028100416,0.22401308,0.0000228828,0.00001845399,0.000076880635,0.000002532245,0.000006388346,0.00005204862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982095,0.000115487215,0.00044878956,0.00037688765,0.0004997423,0.00034960906],"domain_scores_gemma":[0.98630273,0.012925002,0.00015027694,0.00037760148,0.0001674681,0.00007689234],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002704561,0.000098510434,0.00017924231,0.0001191583,0.0003771883,0.000097307384,0.00035826635,0.000049291328,0.000112580106],"category_scores_gemma":[0.01307397,0.000066171495,0.000041546497,0.0016222099,0.000662873,0.00013704358,0.000057374804,0.00015345555,0.000011850841],"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":[0.00001832059,0.000060224356,0.007446714,0.00007432067,0.000005276315,0.0000022687386,0.00042461368,0.0000014329968,0.00058702525,0.94818693,0.0010282189,0.04216467],"study_design_scores_gemma":[0.000087664375,0.000033782682,0.33856797,0.000026244115,0.000016820792,8.9983644e-7,0.00037588488,0.03683068,0.0005252949,0.6233417,0.0001305615,0.00006252742],"about_ca_topic_score_codex":0.00019890335,"about_ca_topic_score_gemma":0.00007696786,"teacher_disagreement_score":0.7371984,"about_ca_system_score_codex":0.000046213503,"about_ca_system_score_gemma":0.00014824522,"threshold_uncertainty_score":0.9952393},"labels":[],"label_agreement":null},{"id":"W3099982168","doi":"10.1214/23-sts889","title":"Causal Inference Methods for Combining Randomized Trials and Observational Studies: A Review","year":2024,"lang":"en","type":"review","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"National Institute on Aging; U.S. Food and Drug Administration","keywords":"Observational study; Causal inference; Inference; Randomized controlled trial; Econometrics; Computer science; Statistics; Medicine; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.85000118132543,"score_gpt":0.7220045213661083,"score_spread":0.12799665995932175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099982168","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.8316657e-9,0.5264271,0.47004446,0.0000688063,0.00018406058,0.0028380489,0.00021037082,0.00011054069,0.00011658328],"genre_scores_gemma":[9.695627e-8,0.5241299,0.4738301,0.00007671751,0.00003762766,0.0018177717,0.0000219868,0.000023340206,0.000062420935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930138,0.0022084746,0.0026463207,0.0010135731,0.0005784366,0.0005393767],"domain_scores_gemma":[0.81605923,0.18155572,0.001057007,0.000458257,0.0006379003,0.00023187713],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045170214,0.0005765579,0.008347887,0.00020825601,0.00023023659,0.00017198206,0.00057429826,0.00015645317,0.000076559714],"category_scores_gemma":[0.44532037,0.0003403054,0.00042910653,0.0009466724,0.0025195752,0.00023268689,0.0004763764,0.0004998031,0.000010464306],"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":[0.00003063781,0.0000073250094,4.9486997e-9,0.044592272,0.000079759375,0.0000016509663,0.000024014596,4.30375e-9,3.0347377e-7,0.5188706,0.001372183,0.43502128],"study_design_scores_gemma":[0.0013545627,0.000059179656,1.6954552e-8,0.05300898,0.0038504296,0.000012825291,0.000008235234,0.00016972848,8.5732574e-7,0.75610656,0.18510321,0.00032541988],"about_ca_topic_score_codex":0.000002775722,"about_ca_topic_score_gemma":0.0000012800932,"teacher_disagreement_score":0.43469587,"about_ca_system_score_codex":0.0002475097,"about_ca_system_score_gemma":0.0011683056,"threshold_uncertainty_score":0.9999049},"labels":[],"label_agreement":null},{"id":"W3210093870","doi":"10.1214/23-sts888","title":"Living on the Edge: An Unified Approach to Antithetic Sampling","year":2024,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Agence Nationale de la Recherche; European Commission","keywords":"Mathematics; Estimator; Markov chain Monte Carlo; Sampling (signal processing); Monte Carlo method; Applied mathematics; Markov chain; Mathematical optimization; Computer science; Statistics","score_opus":0.17420648527956095,"score_gpt":0.4392437903483808,"score_spread":0.26503730506881984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210093870","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":[0.0035085,0.000006840819,0.96945703,0.0003291732,0.00026517242,0.00023885487,0.00006275786,0.000119404394,0.026012238],"genre_scores_gemma":[0.4218529,7.936626e-7,0.5778091,0.00019633978,0.000057023568,0.000017605194,4.5685664e-7,0.000011019091,0.00005478682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978692,0.00017295059,0.00023670033,0.000597565,0.00063216913,0.00049141067],"domain_scores_gemma":[0.991035,0.008140561,0.000021276584,0.00041652884,0.00007727234,0.00030940352],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026465121,0.00015133321,0.0001669259,0.00010106685,0.0004380429,0.0005796841,0.00058986514,0.00003456713,0.00030092202],"category_scores_gemma":[0.00964886,0.000087908345,0.000023423187,0.00095393055,0.0006785658,0.0001201077,0.00013638064,0.00027176054,0.00015820302],"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":[0.0000031306317,0.00006383239,0.000008884855,0.00004015599,0.000002360248,0.000004932822,0.00045306026,0.0000020839975,0.0005445067,0.95128083,0.00033981187,0.04725642],"study_design_scores_gemma":[0.000018133143,0.00016479356,0.0020651373,0.00016645764,0.000015324345,0.000009975551,0.00021796269,0.03822864,0.00012937907,0.95847785,0.00032369074,0.00018263083],"about_ca_topic_score_codex":0.000018805415,"about_ca_topic_score_gemma":0.0000023501927,"teacher_disagreement_score":0.4183444,"about_ca_system_score_codex":0.00006354065,"about_ca_system_score_gemma":0.00015577424,"threshold_uncertainty_score":0.9986933},"labels":[],"label_agreement":null},{"id":"W4205708523","doi":"10.1214/21-sts829","title":"A Conversation with Ross Prentice","year":2022,"lang":"en","type":"article","venue":"Statistical Science","topic":"Cancer Risks and Factors","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Waterloo; Harvard University; American Association for Cancer Research","keywords":"Biostatistics; Statistician; Epidemiology; Public health; Conversation; Library science; Population; Gerontology; Medicine; Sociology; Demography; Pathology; Computer science","score_opus":0.010032419413305441,"score_gpt":0.2968069063300402,"score_spread":0.28677448691673474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205708523","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":[0.93373513,0.00003644478,0.056639995,0.0014576451,0.00029978922,0.0003769051,0.00015114296,0.00006040533,0.007242569],"genre_scores_gemma":[0.99737406,0.0000011619292,0.002159177,0.00023354992,0.00001497326,0.000014494861,0.000007583211,0.000002684852,0.00019232143],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991173,0.000008853607,0.00005589221,0.00017053637,0.0004992676,0.00014812144],"domain_scores_gemma":[0.99970585,0.000037931255,0.000018362573,0.00008886269,0.00003872317,0.00011028062],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017167817,0.000033830886,0.00005738307,0.000030147521,0.00019950075,0.000019446801,0.000060745515,0.0000039472275,0.0013392814],"category_scores_gemma":[0.00006696296,0.000024885081,0.0000063248276,0.00034341824,0.00037566005,0.000053164415,0.000045518438,0.00008601058,0.000011291559],"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":[0.003322,0.0011339664,0.38589534,0.000156549,0.00007955133,0.0006623243,0.011646354,0.00049941946,0.025032379,0.33444402,0.016958453,0.22016965],"study_design_scores_gemma":[0.0015197255,0.0016979169,0.9612963,0.000013240285,0.00007455374,0.0001140912,0.0011213263,0.009337149,0.0007552429,0.0010409785,0.022857858,0.00017157677],"about_ca_topic_score_codex":0.00022120585,"about_ca_topic_score_gemma":0.00001222356,"teacher_disagreement_score":0.575401,"about_ca_system_score_codex":0.00013254973,"about_ca_system_score_gemma":0.00025279805,"threshold_uncertainty_score":0.99957365},"labels":[],"label_agreement":null},{"id":"W4313035772","doi":"10.1214/22-sts866","title":"In Praise (and Search) of J. V. Uspensky","year":2022,"lang":"en","type":"article","venue":"Statistical Science","topic":"History and Theory of Mathematics","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Praise; Mathematical proof; Subject (documents); Classics; Computer science; Mathematical economics; Mathematics; Sociology; History; Literature; Library science; Art","score_opus":0.0506324444195543,"score_gpt":0.3555073648379917,"score_spread":0.30487492041843745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313035772","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":[0.9582297,0.00002826785,0.01746479,0.00026272234,0.00013181783,0.00022480228,0.0000804825,0.000018865941,0.023558538],"genre_scores_gemma":[0.96761245,8.407283e-7,0.031891115,0.000034441444,0.0000046779323,0.0000057366783,2.9541116e-7,0.000004210012,0.00044624583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898964,0.00008343452,0.00017104935,0.00015173212,0.0004323524,0.00017178695],"domain_scores_gemma":[0.9989042,0.0008278657,0.000037053782,0.00013536829,0.000023142135,0.0000723605],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019647046,0.00004547764,0.000118887205,0.00008307961,0.00017639413,0.0000073254637,0.00021034857,0.000007896982,0.0013009312],"category_scores_gemma":[0.0012841333,0.00004188149,0.000008456066,0.00028494545,0.00089023286,0.00007546389,0.00019895443,0.00012293003,0.000006992835],"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":[0.000010009563,0.000087406705,0.00004604556,0.000041530482,6.980962e-7,0.0000164021,0.0019333337,0.0000044793933,0.00087844406,0.9958109,0.00046591967,0.0007048203],"study_design_scores_gemma":[0.00015409036,0.00009564394,0.00047781077,0.000007806833,0.0000033689018,0.000019614134,0.00048131795,0.001148918,0.0003883506,0.99552894,0.0016273326,0.00006678849],"about_ca_topic_score_codex":0.000015908941,"about_ca_topic_score_gemma":0.000006789403,"teacher_disagreement_score":0.023112291,"about_ca_system_score_codex":0.000054186312,"about_ca_system_score_gemma":0.00009019626,"threshold_uncertainty_score":0.99961203},"labels":[],"label_agreement":null},{"id":"W4321505814","doi":"10.1214/22-sts877","title":"A Conversation with Mary E. Thompson","year":2023,"lang":"en","type":"article","venue":"Statistical Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"University of Waterloo; Royal Society; Royal Society of Canada","keywords":"Honour; Medal; Annals; Gold medal; Library science; Conversation; Statistician; Management; Sociology; Mathematics; History; Political science; Law; Classics; Statistics; Art history; Computer science","score_opus":0.01362446477603719,"score_gpt":0.2841100491595704,"score_spread":0.2704855843835332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321505814","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":[0.001007015,0.0000037260215,0.9892286,0.001796205,0.00017803986,0.00008629791,0.0000053861236,0.0001974249,0.007497277],"genre_scores_gemma":[0.33900872,0.000002791102,0.6605273,0.0002382701,0.00001824452,0.000006466101,0.0000014071094,0.0000027177387,0.00019411261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859434,0.00004570595,0.0000916941,0.0004193852,0.0004991428,0.00034973392],"domain_scores_gemma":[0.999245,0.0002032652,0.000026476397,0.00028942456,0.00006874852,0.00016711318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009234807,0.00007249333,0.00008231632,0.00010420248,0.00017467806,0.00017211803,0.00059982843,0.000019066383,0.000031276177],"category_scores_gemma":[0.00014541077,0.00005085352,0.000009508516,0.0016446818,0.00039577976,0.0004484123,0.00016254798,0.0000769248,0.00015597274],"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":[0.0000029092953,0.000006223252,0.00009323568,0.0000040062364,8.9619397e-7,0.000030796036,0.00027134529,0.00000533226,0.0007844372,0.85621184,0.00069515075,0.14189385],"study_design_scores_gemma":[0.00033549758,0.00024003374,0.056672033,0.000022838229,0.0000055553332,0.000033917746,0.000041541356,0.49347132,0.0015520166,0.44576576,0.001553737,0.000305754],"about_ca_topic_score_codex":0.000012879957,"about_ca_topic_score_gemma":0.0000025928514,"teacher_disagreement_score":0.493466,"about_ca_system_score_codex":0.000031310046,"about_ca_system_score_gemma":0.00018081503,"threshold_uncertainty_score":0.20737463},"labels":[],"label_agreement":null},{"id":"W4379415007","doi":"10.1214/23-sts865a","title":"Comment: A Quarter Century of Methodological Research in Response-Adaptive Randomization","year":2023,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Econometrics; Randomization; Statistics; Computer science; Mathematics; History; Medicine; Randomized controlled trial; Archaeology","score_opus":0.18301209058970766,"score_gpt":0.45778046848013415,"score_spread":0.2747683778904265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379415007","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":[0.0010763076,0.000009538497,0.9955247,0.0022661272,0.00015429647,0.00035967812,0.000016818864,0.00007577759,0.0005167545],"genre_scores_gemma":[0.39743355,0.000016393213,0.6023893,0.00009836421,0.0000074785708,0.000033631084,0.0000022740162,0.0000038641588,0.000015153258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995485,0.0019658518,0.00034761018,0.00060939224,0.0010311548,0.0005609831],"domain_scores_gemma":[0.9909456,0.00806685,0.00007350104,0.00034294813,0.00042407343,0.00014705233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012239044,0.00009539649,0.00022544105,0.0006861391,0.00020995605,0.00007108558,0.0008623017,0.00004565821,0.000023570898],"category_scores_gemma":[0.0070557827,0.0000792178,0.000021765498,0.0062461034,0.0011830708,0.0004904619,0.00046083934,0.00023910376,0.000055441407],"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":[0.0013434388,0.0002022061,0.00026393458,0.000012729733,0.0000047497215,0.000091823356,0.0027952688,0.011488021,0.004708337,0.93494314,0.00048924645,0.043657094],"study_design_scores_gemma":[0.0017409009,0.00029709985,0.022181954,0.000027235783,0.0000010844896,0.0000037600237,0.00042499835,0.9122732,0.0008420886,0.061810136,0.0002590722,0.00013842185],"about_ca_topic_score_codex":0.000022446613,"about_ca_topic_score_gemma":0.0000031155748,"teacher_disagreement_score":0.9007852,"about_ca_system_score_codex":0.00018288742,"about_ca_system_score_gemma":0.00022652444,"threshold_uncertainty_score":0.844694},"labels":[],"label_agreement":null},{"id":"W4388460787","doi":"10.1214/23-sts909","title":"Editorial: Special Issue on Reproducibility and Replicability","year":2023,"lang":"en","type":"editorial","venue":"Statistical Science","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"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":"Reproducibility; Computer science; Data science; Statistics; Mathematics","score_opus":0.07983773611749603,"score_gpt":0.44332107671701615,"score_spread":0.36348334059952014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388460787","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006546111,0.0000041727994,0.0009255497,0.0006616797,0.98549855,0.00037348567,0.0017685265,0.0001710676,0.010531505],"genre_scores_gemma":[0.000072982075,0.00000765037,0.001327061,0.000032226188,0.9928499,0.000014228094,0.00008078983,0.000018538265,0.00559663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97388875,0.00046268667,0.0013463489,0.010105001,0.013274428,0.0009227919],"domain_scores_gemma":[0.91415876,0.06380686,0.00077451364,0.017355539,0.0027432218,0.001161084],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10291302,0.00036792463,0.00068621774,0.00047095824,0.00094894174,0.0027353955,0.00367227,0.0003102967,0.00081437203],"category_scores_gemma":[0.6739906,0.0002672543,0.00008081783,0.0033276035,0.0038106835,0.00032808902,0.0031596464,0.0009372569,0.0034706863],"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":[0.00004314896,0.000059697177,0.000024123428,0.000013252496,0.0000027722356,0.0000073267174,0.000065143,0.0000059248805,0.0000028370198,0.0016069141,0.9107819,0.087386966],"study_design_scores_gemma":[0.00012650131,0.00016475617,0.0013381685,0.000025173587,0.000012135378,1.8506636e-7,0.000058144797,0.00040020954,0.000004714609,0.058149483,0.9394363,0.00028418875],"about_ca_topic_score_codex":0.00029007753,"about_ca_topic_score_gemma":0.00008946154,"teacher_disagreement_score":0.5710776,"about_ca_system_score_codex":0.00028535712,"about_ca_system_score_gemma":0.00085074996,"threshold_uncertainty_score":0.99997795},"labels":[],"label_agreement":null},{"id":"W4391933919","doi":"10.1214/23-sts919","title":"Emerging Directions in Bayesian Computation","year":2024,"lang":"en","type":"article","venue":"Statistical Science","topic":"Gaussian Processes and Bayesian Inference","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":"University of British Columbia","funders":"Office of Naval Research; National Institutes of Health; European Commission","keywords":"Bayesian probability; Computer science; Computation; Approximate Bayesian computation; Artificial intelligence; Machine learning; Algorithm; Inference","score_opus":0.01065958484695598,"score_gpt":0.3056126727917594,"score_spread":0.2949530879448034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391933919","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":[0.00041715207,0.000110229965,0.9863355,0.0015175372,0.0005101766,0.00006366925,0.00000478432,0.00019329264,0.01084764],"genre_scores_gemma":[0.863127,0.000010705606,0.13671026,0.00006650494,0.000021981803,0.000008033231,8.8142815e-7,0.0000032218759,0.000051385843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851465,0.000023048005,0.00018925195,0.00053170574,0.00037936572,0.00036198224],"domain_scores_gemma":[0.9994719,0.00017744304,0.000016451888,0.00015031852,0.000048415444,0.00013549015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045371416,0.00008609422,0.00008387671,0.0002832553,0.00018607348,0.0007222198,0.0005352834,0.000020922407,0.000046141457],"category_scores_gemma":[0.00015829765,0.000073859184,0.000014701941,0.0027491094,0.00025805295,0.00094182114,0.00013662588,0.00014524093,0.00009567705],"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":[3.2473991e-7,0.000012536224,0.00014204637,0.00001723453,6.0620243e-7,0.000041587133,0.00023790273,0.000055724544,0.0001818529,0.7305189,0.0001398812,0.2686514],"study_design_scores_gemma":[0.0000391218,0.00003036054,0.013181494,0.00005925193,0.0000013467284,0.000022065647,0.000021235044,0.7655576,0.000131458,0.2194714,0.001358356,0.00012634418],"about_ca_topic_score_codex":0.00006460132,"about_ca_topic_score_gemma":0.000035443532,"teacher_disagreement_score":0.8627099,"about_ca_system_score_codex":0.00008984296,"about_ca_system_score_gemma":0.0003241868,"threshold_uncertainty_score":0.69643825},"labels":[],"label_agreement":null},{"id":"W4391944190","doi":"10.1214/23-sts907","title":"Past, Present and Future of Software for Bayesian Inference","year":2024,"lang":"en","type":"article","venue":"Statistical Science","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Office of Naval Research; Javna Agencija za Raziskovalno Dejavnost RS","keywords":"Computer science; Inference; Bayesian inference; Bayesian probability; Software; Artificial intelligence; Machine learning; Econometrics; Data science; Data mining; Mathematics; Programming language","score_opus":0.02079020362936505,"score_gpt":0.3162545814338298,"score_spread":0.2954643778044647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391944190","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":[0.0002616813,0.00036773115,0.99620384,0.0021737635,0.000368905,0.00013157314,0.00005620152,0.00010931183,0.0003269863],"genre_scores_gemma":[0.57256633,0.00002251412,0.4270901,0.000058073038,0.00020532802,0.000015828964,0.0000015488673,0.000004058037,0.000036206744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985223,0.00002008501,0.00019763772,0.00054702634,0.00037922445,0.0003337574],"domain_scores_gemma":[0.9987407,0.0005710237,0.000027322747,0.0002675275,0.00018898016,0.00020444761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048485678,0.00010802096,0.00013464248,0.00009343469,0.00014185908,0.00033264785,0.0006543035,0.000039213133,0.000014445235],"category_scores_gemma":[0.00013710425,0.00008417116,0.000019949006,0.00069711835,0.0005463273,0.00044290663,0.00022330637,0.000105183666,0.000005004834],"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":[0.0000017151154,0.000009431608,0.000045440327,0.00006141536,0.0000018445111,0.0000033409215,0.00017547984,0.0000111985255,0.00022511555,0.64140683,0.00063270284,0.3574255],"study_design_scores_gemma":[0.000089047055,0.00021636214,0.001892201,0.00007565884,0.000008175109,0.000012528471,0.00002512887,0.64581007,0.00059619284,0.3423986,0.00867708,0.0001989424],"about_ca_topic_score_codex":0.000016362568,"about_ca_topic_score_gemma":0.0000013426286,"teacher_disagreement_score":0.64579886,"about_ca_system_score_codex":0.000020577083,"about_ca_system_score_gemma":0.00033298094,"threshold_uncertainty_score":0.34324002},"labels":[],"label_agreement":null},{"id":"W4400119980","doi":"10.1214/23-sts916","title":"A General Construction of Multivariate Dependence Structures with Nonmonotone Mappings and Its Applications","year":2024,"lang":"en","type":"article","venue":"Statistical Science","topic":"Fuzzy Systems and Optimization","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Multivariate statistics; Computer science; Mathematics; Applied mathematics; Statistics","score_opus":0.019458891396563316,"score_gpt":0.3138457855035256,"score_spread":0.2943868941069623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400119980","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":[0.06653753,0.000077512945,0.9320582,0.00005378573,0.00006165076,0.00033119117,0.00009208777,0.000042922587,0.0007451029],"genre_scores_gemma":[0.6819362,0.0000060652856,0.3179611,0.000004103281,0.00001929216,0.000020676025,0.0000018403402,0.0000042840243,0.00004644323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99918485,0.000013830956,0.00015870981,0.00025177235,0.00026149303,0.00012933713],"domain_scores_gemma":[0.99948144,0.00020920875,0.00004530203,0.000087832705,0.000105838,0.00007035295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002111402,0.00006733035,0.00009942761,0.00006229863,0.00010451078,0.00007245463,0.00008262971,0.000024439722,0.000029625782],"category_scores_gemma":[0.00017952416,0.000047409583,0.000006622176,0.00035607716,0.00039475938,0.00016164662,0.00003241499,0.000058183105,0.0000017098754],"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":[0.000004592985,0.0000063602174,0.000045977846,0.0001444392,0.0000044323165,0.0000020016796,0.00016628891,0.00005669,0.0063760034,0.9894818,0.000012644611,0.0036987693],"study_design_scores_gemma":[0.0003139859,0.00013708322,0.0043595578,0.00019887423,0.00005850441,0.00016315097,0.00018865599,0.41432434,0.006723124,0.57281166,0.00043811658,0.00028295515],"about_ca_topic_score_codex":0.000047735026,"about_ca_topic_score_gemma":0.000010351761,"teacher_disagreement_score":0.61539865,"about_ca_system_score_codex":0.000023011138,"about_ca_system_score_gemma":0.00009386151,"threshold_uncertainty_score":0.19333068},"labels":[],"label_agreement":null},{"id":"W4400120136","doi":"10.1214/24-sts926","title":"Antoine Gombaud, Chevalier de Méré","year":2024,"lang":"fr","type":"article","venue":"Statistical Science","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University","funders":"","keywords":"Humanities; Mathematics; Art","score_opus":0.0783825922826476,"score_gpt":0.45791378123565657,"score_spread":0.37953118895300897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400120136","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":[0.0024715662,0.0031516666,0.93446726,0.0108194165,0.0013311526,0.0003920327,0.0015495599,0.00014849214,0.045668848],"genre_scores_gemma":[0.49580678,0.00047076264,0.45766532,0.00038262684,0.0005165295,0.00004779458,0.000015353668,0.0000564969,0.04503833],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948682,0.00027866257,0.00050673285,0.00093397155,0.001667834,0.0017445899],"domain_scores_gemma":[0.9911034,0.007020948,0.000027756678,0.0004843665,0.00026246588,0.0011010296],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0062590777,0.0002549545,0.00033255536,0.00014508284,0.0003993816,0.00090168865,0.0007542299,0.00016438012,0.0109943515],"category_scores_gemma":[0.02952122,0.00022171464,0.00007377404,0.0016035867,0.006848124,0.00042750646,0.0003850622,0.00085692096,0.0033015353],"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":[0.000016389613,0.00018336314,0.000032357584,0.0011640986,0.000014222867,0.00050705194,0.0004129845,0.0000032739456,0.0008829621,0.8104545,0.014670712,0.17165807],"study_design_scores_gemma":[0.00010751122,0.00020207696,0.00094118854,0.00030857523,0.000051605235,0.00009887638,0.000044758963,0.14459902,0.0004093333,0.807784,0.045208905,0.00024415055],"about_ca_topic_score_codex":0.00020298744,"about_ca_topic_score_gemma":0.000049088583,"teacher_disagreement_score":0.49333522,"about_ca_system_score_codex":0.00087432144,"about_ca_system_score_gemma":0.0025817426,"threshold_uncertainty_score":0.9974745},"labels":[],"label_agreement":null},{"id":"W4414298519","doi":"10.1214/25-sts1002","title":"An Adaptive Transfer Learning Perspective on Classification in Nonstationary Environments","year":2025,"lang":"en","type":"article","venue":"Statistical Science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Perspective (graphical); Regret; Class (philosophy); Covariate; Transfer of learning; Sequence (biology); Gradient descent","score_opus":0.021870121039291233,"score_gpt":0.3174130453699864,"score_spread":0.2955429243306951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414298519","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":[0.0049474174,0.000008342554,0.9641646,0.00076779875,0.00009836227,0.00014167388,0.0000034475643,0.000047547175,0.029820822],"genre_scores_gemma":[0.957976,0.000004881054,0.04133131,0.0004504841,0.000006730053,0.000018237515,0.0000034151435,0.0000031294007,0.00020582815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982358,0.00017739098,0.00018406186,0.00062559114,0.00048786792,0.00028927348],"domain_scores_gemma":[0.99924535,0.00034242167,0.000024802795,0.00021850069,0.000052146865,0.00011680136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006628207,0.0000999692,0.000094313196,0.00028839402,0.0003217966,0.0001467417,0.0005531122,0.000032170512,0.000048869777],"category_scores_gemma":[0.00031364147,0.00009732015,0.000014300387,0.0010356192,0.00044544475,0.00083044486,0.00004260937,0.00027029307,0.00007429839],"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":[0.000022762844,0.00009699046,0.00039187534,9.56828e-7,0.0000014353399,0.000006439802,0.0011909079,0.0044519636,0.0033179002,0.95280087,0.000010009879,0.03770788],"study_design_scores_gemma":[0.00035197946,0.00029808856,0.2991477,0.000021701835,0.0000021287449,0.0000010088719,0.0024062817,0.6531583,0.00022721896,0.043564767,0.00066936656,0.00015145807],"about_ca_topic_score_codex":0.00004464798,"about_ca_topic_score_gemma":0.000013554077,"teacher_disagreement_score":0.95302856,"about_ca_system_score_codex":0.00038593262,"about_ca_system_score_gemma":0.00022665963,"threshold_uncertainty_score":0.39686006},"labels":[],"label_agreement":null},{"id":"W642399624","doi":"10.1214/088342304000000189","title":"The Reverend Thomas Bayes, FRS: A Biography to Celebrate the Tercentenary of His Birth","year":2004,"lang":"en","type":"article","venue":"Statistical Science","topic":"Philosophy and History of Science","field":"Arts and Humanities","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":"Western University","funders":"University of Edinburgh; Presbyterian Historical Society","keywords":"Biography; Bayes' theorem; Character (mathematics); History; Epistemology; Sociology; Classics; Philosophy; Bayesian probability; Computer science; Artificial intelligence; Art history; Mathematics","score_opus":0.023380680097491884,"score_gpt":0.2380154953419277,"score_spread":0.2146348152444358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W642399624","genre_codex":"other","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":[0.18023217,0.0017208008,0.013632214,0.060485367,0.005597493,0.0017884113,0.0021500145,0.00028031642,0.7341132],"genre_scores_gemma":[0.99724245,0.00002041637,0.0012273998,0.0007803179,0.00010472286,0.00000976119,8.546377e-7,0.000003995821,0.0006100762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985757,0.000030231502,0.00019929465,0.0002857129,0.00054863584,0.0003604652],"domain_scores_gemma":[0.9991896,0.0001898984,0.000062724284,0.0002867497,0.000115504154,0.00015549352],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0006746702,0.000096305324,0.000099679484,0.000091369984,0.0020084982,0.00021337447,0.0008924433,0.000010859187,0.00019857503],"category_scores_gemma":[0.00017841515,0.000047387242,0.000042226788,0.00034390867,0.008092128,0.0002390023,0.000114883565,0.00010506019,0.00006517778],"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":[0.000013098615,0.000031337495,0.00002301121,0.0000049122323,0.0000023807086,0.0000030250371,0.006227413,0.0000039670012,0.00060303794,0.9882651,0.002520051,0.0023026413],"study_design_scores_gemma":[0.00019094691,0.0004866786,0.005255678,0.000053238135,0.000013233533,0.0000051032057,0.0022708396,0.00005540673,0.0003540502,0.45613214,0.534953,0.00022966838],"about_ca_topic_score_codex":0.0004629479,"about_ca_topic_score_gemma":0.00091524696,"teacher_disagreement_score":0.8170103,"about_ca_system_score_codex":0.000042671698,"about_ca_system_score_gemma":0.0001359185,"threshold_uncertainty_score":0.99929076},"labels":[],"label_agreement":null},{"id":"W7118628814","doi":"10.1214/25-sts1001","title":"Sample-Based Planning and Learning with Function Approximation","year":2025,"lang":"","type":"article","venue":"Statistical Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Function approximation; Core (optical fiber); Focus (optics); Dimension (graph theory); Function (biology); Approximation algorithm; Optimism","score_opus":0.015498831904994551,"score_gpt":0.28179290718513256,"score_spread":0.266294075280138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118628814","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":[0.0013297846,0.000072296214,0.9928828,0.00045910885,0.00044050792,0.00032318648,0.0000039596075,0.000121520774,0.0043668724],"genre_scores_gemma":[0.7320212,0.0000024992833,0.26737165,0.00028809754,0.000020310474,0.000010032485,0.000006760847,0.0000065697336,0.00027285056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647367,0.0001989344,0.0004132342,0.0010342652,0.0011118393,0.00076803257],"domain_scores_gemma":[0.99692476,0.0019072565,0.00020618885,0.00039243855,0.00031259458,0.00025678796],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019359196,0.00026813048,0.00024887736,0.00039277851,0.001826012,0.0015378342,0.0006532875,0.00007795977,0.000050811326],"category_scores_gemma":[0.003144329,0.00023584187,0.000018329683,0.002424832,0.0020007084,0.00090622547,0.0003574946,0.00067556737,0.000016907507],"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":[0.000063680876,0.000019627114,0.009864411,0.0001081234,0.00000934935,0.0000060089183,0.00035642614,0.59633327,0.00016118168,0.33646446,0.000028894061,0.056584567],"study_design_scores_gemma":[0.00052511785,0.0007725439,0.04181777,0.0003134123,0.000042031203,0.0000030356907,0.00013678722,0.9528265,0.00012463689,0.0024142545,0.000758955,0.0002649639],"about_ca_topic_score_codex":0.00006124946,"about_ca_topic_score_gemma":0.000001518596,"teacher_disagreement_score":0.73069143,"about_ca_system_score_codex":0.00019113126,"about_ca_system_score_gemma":0.0009823946,"threshold_uncertainty_score":0.99949867},"labels":[],"label_agreement":null}]}