{"meta":{"query_hash":"dd146784d1e0","filters":{"venue":"Journal of Computational and Graphical Statistics"},"cohort_total":83,"direct_labels_cover":0,"predictions_cover":83,"exported":83,"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/dd146784d1e0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Computational+and+Graphical+Statistics"},"results":[{"id":"W1607933843","doi":"10.1080/10618600.2016.1237363","title":"Divide-and-Conquer With Sequential Monte Carlo","year":2016,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Vetenskapsrådet","keywords":"Divide and conquer algorithms; Computer science; Probabilistic logic; Graphical model; Inference; Monte Carlo method; Algorithm; Class (philosophy); Theoretical computer science; Machine learning; Artificial intelligence; Mathematics; Statistics","score_opus":0.007713407732557479,"score_gpt":0.222033098086382,"score_spread":0.2143196903538245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1607933843","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":[0.029661065,0.00012309084,0.96670204,0.0033652522,0.00006331795,0.000025940475,0.00002379976,0.000007263822,0.000028208999],"genre_scores_gemma":[0.85953313,0.000070121,0.14014348,0.00018237163,0.000047475663,5.416572e-7,3.0916752e-7,0.0000031810143,0.000019398407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99912703,0.000031246116,0.00026625607,0.00012587449,0.0003282696,0.00012134245],"domain_scores_gemma":[0.99895847,0.00032158164,0.00019042639,0.000051259212,0.00032311576,0.0001551388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013262268,0.00009212769,0.0001563266,0.00008361196,0.00007956648,0.00011722454,0.00015844665,0.000030828447,0.000007677155],"category_scores_gemma":[0.000039378912,0.00004857021,0.000022009124,0.000120863566,0.00016377955,0.00029939172,0.000054956396,0.000098917066,9.486499e-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":[0.000051803607,0.000046372963,0.008718745,0.000030076671,0.000070690796,0.00014479125,0.00012669124,0.00030655533,0.00003248298,0.8678696,0.0007036934,0.12189846],"study_design_scores_gemma":[0.0008652377,0.0005022351,0.10099654,0.000092337505,0.000022987719,0.0006894494,0.0000033220088,0.0068466724,0.000015091367,0.8889593,0.0008637823,0.00014304645],"about_ca_topic_score_codex":0.000004031295,"about_ca_topic_score_gemma":0.0000034481432,"teacher_disagreement_score":0.8298721,"about_ca_system_score_codex":0.00000812065,"about_ca_system_score_gemma":0.00009764926,"threshold_uncertainty_score":0.19806358},"labels":[],"label_agreement":null},{"id":"W1763412770","doi":"10.1080/10618600.2015.1043010","title":"Reinforced Angle-Based Multicategory Support Vector Machines","year":2015,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation; National Institutes of Health; National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; National Center for Research Resources; National Institute of Mental Health","keywords":"Support vector machine; Coordinate descent; Quadratic programming; Consistency (knowledge bases); Binary classification; Computer science; Machine learning; Dual (grammatical number); Mathematical optimization; Artificial intelligence; Quadratic equation; Sequential quadratic programming; Class (philosophy); Mathematics; Algorithm","score_opus":0.023325030408022324,"score_gpt":0.26742443207681543,"score_spread":0.2440994016687931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1763412770","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":[0.016515374,0.00004560248,0.9814196,0.0015760444,0.0002933648,0.000039921186,0.000026090389,0.000015512314,0.00006848051],"genre_scores_gemma":[0.6631099,0.0000070111437,0.33601224,0.00072965183,0.000085925356,0.0000010190485,0.000023623166,0.000004314849,0.0000263108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891007,0.000056824912,0.0003607068,0.000099007,0.00046044515,0.00011293738],"domain_scores_gemma":[0.9985371,0.00036289266,0.00021262497,0.00005988156,0.00056772423,0.000259778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027985318,0.00008958985,0.0001587341,0.00014214472,0.000062399005,0.00008995703,0.0001771835,0.000044420653,0.000014482857],"category_scores_gemma":[0.00016730871,0.0000670971,0.00004550046,0.00016905628,0.000071298375,0.00022672351,0.00003656944,0.00015325792,0.000008263471],"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":[0.00060132955,0.00048267675,0.0054156827,0.00013949495,0.00017050325,0.00063094887,0.0010147195,0.11549201,0.00050318695,0.630499,0.11992233,0.12512814],"study_design_scores_gemma":[0.0016118016,0.00060133403,0.01258682,0.000027203718,0.000018148392,0.00014595452,0.000015808992,0.7363041,0.000087799825,0.2465359,0.0019112655,0.00015386727],"about_ca_topic_score_codex":0.0000035289854,"about_ca_topic_score_gemma":6.463268e-7,"teacher_disagreement_score":0.6465945,"about_ca_system_score_codex":0.000011180395,"about_ca_system_score_gemma":0.00016392424,"threshold_uncertainty_score":0.27361405},"labels":[],"label_agreement":null},{"id":"W1964782536","doi":"10.1198/106186008x343785","title":"The Fast-τ Estimator for Regression","year":2008,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Resampling; Heuristic; Mathematics; Computer science; Regression; Algorithm; Extremum estimator; Bootstrapping (finance); M-estimator; Statistics; Mathematical optimization; Econometrics","score_opus":0.08631111371913629,"score_gpt":0.4154602009907002,"score_spread":0.3291490872715639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964782536","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":[0.005498856,0.00018570959,0.99329007,0.0006500804,0.000136049,0.00009642319,0.00011291374,0.000005560764,0.000024326777],"genre_scores_gemma":[0.059344634,0.0001424964,0.94026387,0.00007050734,0.00009743868,0.0000036285103,0.0000033284211,0.000010044488,0.00006408285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989251,0.00006489519,0.0004737706,0.0000821611,0.0003174497,0.00013661751],"domain_scores_gemma":[0.98992586,0.009094951,0.0003022551,0.00004861926,0.0004980259,0.00013026332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039351787,0.00009587901,0.00022289585,0.000039003226,0.0004663355,0.000021352827,0.00008506477,0.000039302973,0.000003492565],"category_scores_gemma":[0.0020581966,0.00005259296,0.00006350962,0.00006723258,0.00025171807,0.00005323534,0.000019018287,0.00016169132,2.4881746e-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":[0.00014148466,0.00004984219,0.00006925848,0.000028384306,0.000032137676,0.000021132171,0.000058950613,0.00040896164,0.000008225336,0.9569866,0.0065413597,0.035653643],"study_design_scores_gemma":[0.0005136868,0.00023851045,0.0017241634,0.000028001867,0.000029821978,0.00023889517,0.000020505555,0.033578876,0.0000057865204,0.96101314,0.0025397,0.00006893098],"about_ca_topic_score_codex":3.2021524e-7,"about_ca_topic_score_gemma":5.777451e-7,"teacher_disagreement_score":0.053845778,"about_ca_system_score_codex":0.00000915489,"about_ca_system_score_gemma":0.000056168974,"threshold_uncertainty_score":0.3586723},"labels":[],"label_agreement":null},{"id":"W1966109447","doi":"10.1080/10618600.2000.10474871","title":"Note on “Obtaining the Maximum Likelihood Estimates in Incomplete<i>R</i>×<i>C</i>Contingency Tables Using a Poisson Generalized Linear Model”","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","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":"York University","funders":"","keywords":"Contingency table; Mathematics; Macro; Statistics; Poisson distribution; Standard error; Table (database); Generalized linear model; Missing data; Applied mathematics; Design matrix; Maximum likelihood; Algorithm; Linear model; Computer science; Data mining","score_opus":0.04626384178380755,"score_gpt":0.3564908719570994,"score_spread":0.31022703017329184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966109447","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":[0.12585413,0.00008035271,0.8731925,0.0005042831,0.00005229013,0.000099465884,0.00013992214,0.000008143637,0.00006890336],"genre_scores_gemma":[0.18458761,0.000058201185,0.8149039,0.00033802146,0.00008651034,0.0000017049389,0.0000054421853,0.00001567911,0.0000029202658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979975,0.000199068,0.00085531594,0.00016892479,0.00049699424,0.00028220273],"domain_scores_gemma":[0.99512047,0.0040888814,0.0003247149,0.00008574123,0.00024108116,0.00013911295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082734256,0.00020047238,0.0004495078,0.00014030862,0.00019910667,0.000076844706,0.0001680506,0.000077681594,0.000088025845],"category_scores_gemma":[0.00090719707,0.00013336206,0.000073628,0.0002712576,0.0001644091,0.00008239321,0.000029049726,0.0004388809,0.0000012434685],"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":[0.00038660734,0.00032518271,0.0015012309,0.000096893185,0.0000732019,0.00010628427,0.000597474,0.048436314,0.00010128774,0.8115237,0.00030189657,0.13654996],"study_design_scores_gemma":[0.00045548994,0.00012371679,0.0015988537,0.000097892174,0.000037150872,0.000049246508,0.000011089302,0.44467324,0.0000061068727,0.55282223,0.00003321625,0.00009176252],"about_ca_topic_score_codex":0.00003468304,"about_ca_topic_score_gemma":0.000014649987,"teacher_disagreement_score":0.39623693,"about_ca_system_score_codex":0.000028698892,"about_ca_system_score_gemma":0.00009954708,"threshold_uncertainty_score":0.5438347},"labels":[],"label_agreement":null},{"id":"W1970792239","doi":"10.1198/jcgs.2009.07118","title":"Boosting for Correlated Binary Classification","year":2010,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Boosting (machine learning); Gradient boosting; Computer science; Gradient descent; Stochastic gradient descent; Binary number; Binary classification; Binary data; Source code; Machine learning; Artificial intelligence; Data mining; Algorithm; Mathematics; Random forest; Support vector machine; Artificial neural network","score_opus":0.013017065009308857,"score_gpt":0.2825035728589893,"score_spread":0.2694865078496804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970792239","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":[0.49599123,0.00011201446,0.5028365,0.00056851504,0.0003235727,0.000071484836,0.00004724813,0.0000026104237,0.000046819358],"genre_scores_gemma":[0.9461194,0.0000469338,0.053332686,0.00014736842,0.00019384388,0.0000032982643,0.00010458749,0.0000065444847,0.00004530516],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99943584,0.000020127887,0.00025704774,0.00009454714,0.00012366578,0.00006874152],"domain_scores_gemma":[0.9991655,0.00008982049,0.00022143363,0.000046461475,0.00039831575,0.000078520316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017361021,0.000060296865,0.00007961751,0.000060243077,0.00008399265,0.000021251803,0.0000604699,0.00007969145,0.0000067015235],"category_scores_gemma":[0.00020060799,0.000050717365,0.000038597096,0.00006556279,0.00007099541,0.000004334382,0.000012339816,0.00012726705,3.5750745e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005773412,0.00020784332,0.008848035,0.0000489528,0.00009506905,0.0000034280642,0.000060720125,0.0018842939,0.8206529,0.084638014,0.029694065,0.05328932],"study_design_scores_gemma":[0.0036045418,0.0017554581,0.60818624,0.000050218005,0.000118877055,0.00028511725,0.00014971083,0.08119591,0.0047863224,0.18280481,0.11661551,0.00044726653],"about_ca_topic_score_codex":3.882784e-7,"about_ca_topic_score_gemma":0.0000012538657,"teacher_disagreement_score":0.8158666,"about_ca_system_score_codex":0.0000025241418,"about_ca_system_score_gemma":0.000066441884,"threshold_uncertainty_score":0.20681942},"labels":[],"label_agreement":null},{"id":"W1972260379","doi":"10.1198/jcgs.2011.10106","title":"Local-EM and the EMS Algorithm","year":2011,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Algorithm; Context (archaeology); Expectation–maximization algorithm; Piecewise; Computer science; Mathematics; Likelihood function; Maximum likelihood; Statistics; Estimation theory","score_opus":0.025670159727348738,"score_gpt":0.20660892166286438,"score_spread":0.18093876193551564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972260379","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":[0.011646438,0.001291914,0.98603266,0.00035414315,0.00010715708,0.000029699786,0.0003265222,0.0000020123932,0.00020947088],"genre_scores_gemma":[0.9307897,0.00056693103,0.068116635,0.00040646637,0.00007042867,8.483816e-7,0.000016740354,0.000005051606,0.000027168293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992864,0.00002169438,0.0004680735,0.00008526253,0.000060504808,0.00007806038],"domain_scores_gemma":[0.999162,0.00030051937,0.00032629294,0.00004182415,0.00008853833,0.00008079613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004034136,0.000067189365,0.00025174193,0.00010237433,0.00008842272,0.00004255119,0.00008180606,0.000032514105,0.00010312864],"category_scores_gemma":[0.00007447587,0.000045729746,0.00005401312,0.00012634705,0.00026680063,0.0000757249,0.000025903008,0.0001322314,0.000006596952],"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":[0.00007073815,0.000047318972,0.0048946175,0.000008697174,0.00016357239,0.000016703569,0.0005098972,0.00015437097,5.085639e-8,0.929671,0.0007930488,0.06366997],"study_design_scores_gemma":[0.00069521513,0.00007746204,0.1175556,0.000004618309,0.000027858128,0.000054128934,0.00006000757,0.061898492,3.3017986e-7,0.81825066,0.0013119815,0.00006365389],"about_ca_topic_score_codex":0.000117364885,"about_ca_topic_score_gemma":0.000010788844,"teacher_disagreement_score":0.9191433,"about_ca_system_score_codex":0.0000045024694,"about_ca_system_score_gemma":0.000008428118,"threshold_uncertainty_score":0.18648049},"labels":[],"label_agreement":null},{"id":"W1983531885","doi":"10.1198/106186002510","title":"On Markov chain Monte Carlo Algorithms for Computing Conditional Expectations Based on Sufficient Statistics","year":2002,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":5,"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":"Memorial University of Newfoundland; National Science Foundation","keywords":"Mathematics; Markov chain Monte Carlo; Statistic; Monte Carlo method; Statistics; Sufficient statistic; Markov chain; Algorithm; Computer science","score_opus":0.05024182247687973,"score_gpt":0.33716374330664345,"score_spread":0.2869219208297637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983531885","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":[0.015352101,0.000076326956,0.9808771,0.0006314616,0.0003265301,0.00025483398,0.0023550522,0.000015500558,0.00011107795],"genre_scores_gemma":[0.4054681,0.000008649223,0.5937901,0.00043849077,0.00015705432,0.0000062321196,0.00005679789,0.000020955058,0.00005361472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772245,0.0001980422,0.0008224167,0.00021932325,0.0007822833,0.00025547776],"domain_scores_gemma":[0.98697037,0.01131012,0.0005478135,0.00009534626,0.00084239896,0.00023395846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063764275,0.000234018,0.00042503673,0.00031278084,0.0002985017,0.000073719806,0.0001211529,0.000087812274,0.00004216154],"category_scores_gemma":[0.0015432264,0.00019832258,0.00014201026,0.00018677588,0.00015918152,0.000040934607,0.00001784633,0.0003297985,2.0457205e-7],"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":[0.00022502913,0.0010303844,0.00011753829,0.00015386009,0.00013975172,0.000087607536,0.00052200595,0.088093705,0.000003943334,0.85091203,0.039328337,0.019385803],"study_design_scores_gemma":[0.0015957436,0.0010413043,0.00070680236,0.00007643483,0.000064669846,0.0000307372,0.00011745868,0.7543796,0.000002856903,0.24143985,0.00036554507,0.00017903853],"about_ca_topic_score_codex":0.0000013939339,"about_ca_topic_score_gemma":0.0000024838557,"teacher_disagreement_score":0.6662859,"about_ca_system_score_codex":0.0000615677,"about_ca_system_score_gemma":0.000054618085,"threshold_uncertainty_score":0.808736},"labels":[],"label_agreement":null},{"id":"W1992601594","doi":"10.1080/10618600.2015.1005213","title":"Tweedie’s Compound Poisson Model With Grouped Elastic Net","year":2015,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":41,"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":"Poisson distribution; Mathematics; Library science; Statistics; Computer science","score_opus":0.06901214203725027,"score_gpt":0.33499392125358884,"score_spread":0.2659817792163386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992601594","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":[0.13324572,0.00009385864,0.8657525,0.00043551886,0.000098799756,0.00006307507,0.0000574637,0.000008866391,0.0002442054],"genre_scores_gemma":[0.45880258,0.000011647898,0.5408974,0.00012186922,0.000094653005,8.2285976e-7,0.00000770612,0.000011737427,0.000051572162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985515,0.000101061516,0.00047980866,0.00011138151,0.0006002365,0.00015603883],"domain_scores_gemma":[0.99725413,0.0012606919,0.0003339904,0.00006035411,0.00075995736,0.00033085572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006524216,0.00014745003,0.00035451233,0.00011959151,0.00006786632,0.000053639575,0.00009405854,0.000059651713,0.0000027642097],"category_scores_gemma":[0.00041478305,0.00010114139,0.000048605212,0.00013551195,0.00014267405,0.00008820045,0.000029264394,0.0002653561,4.2741476e-8],"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":[0.00056249165,0.0002687446,0.0012857295,0.00009880475,0.00017399332,0.00016530862,0.0005456446,0.031106634,0.000015514095,0.94966143,0.013079501,0.0030362103],"study_design_scores_gemma":[0.0014286658,0.0005905012,0.0011020699,0.000045476558,0.0001005824,0.00034063874,0.0000810373,0.2705889,0.0000013641054,0.7250999,0.0004925016,0.00012835738],"about_ca_topic_score_codex":0.0000042775673,"about_ca_topic_score_gemma":0.000010825191,"teacher_disagreement_score":0.32555684,"about_ca_system_score_codex":0.000026054617,"about_ca_system_score_gemma":0.00013207573,"threshold_uncertainty_score":0.41244262},"labels":[],"label_agreement":null},{"id":"W1998269350","doi":"10.1198/jcgs.2011.09189","title":"Conditional Logistic Regression With Longitudinal Follow-up and Individual-Level Random Coefficients: A Stable and Efficient Two-Step Estimation Method","year":2011,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Parks Canada","keywords":"Statistics; Expectation–maximization algorithm; Mathematics; Likelihood function; Dimension (graph theory); Population; Computer science; Selection (genetic algorithm); Logistic regression; Random effects model; Econometrics; Estimation theory; Maximum likelihood; Artificial intelligence; Meta-analysis","score_opus":0.04198617404020803,"score_gpt":0.29383424487761073,"score_spread":0.2518480708374027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998269350","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":[0.27755934,0.00032270813,0.72174585,0.000027386093,0.00005366544,0.00007515287,0.00019804906,0.000001681544,0.000016151245],"genre_scores_gemma":[0.5861755,0.000015062392,0.4136476,0.00004366649,0.000027808544,0.0000015992182,0.00007262434,0.0000051191346,0.000011010431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989963,0.00009217553,0.0003057418,0.00018266022,0.00029738256,0.00012572152],"domain_scores_gemma":[0.9990852,0.00021333812,0.0002318717,0.000047648307,0.0002751711,0.00014678776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030859595,0.0001381758,0.0001996496,0.00007396565,0.00013924515,0.000034593162,0.000059051243,0.00006360345,0.000011965823],"category_scores_gemma":[0.00011447882,0.00009799102,0.000025512667,0.000070356655,0.00029097032,0.00000672489,0.00004571643,0.00012523774,1.59048e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011787026,0.0018857339,0.069663964,0.0004334263,0.0016867989,0.00008921681,0.0018700378,0.3495182,0.000874163,0.4876118,0.0032085262,0.07137109],"study_design_scores_gemma":[0.009300341,0.0028249284,0.76834846,0.00011328432,0.00033331296,0.0009842726,0.000116513496,0.048092622,0.0001490769,0.16931912,0.00009855534,0.00031949324],"about_ca_topic_score_codex":0.0000071637146,"about_ca_topic_score_gemma":0.0000046267887,"teacher_disagreement_score":0.6986845,"about_ca_system_score_codex":0.000004108643,"about_ca_system_score_gemma":0.00007015294,"threshold_uncertainty_score":0.39959577},"labels":[],"label_agreement":null},{"id":"W2003144493","doi":"10.1198/jcgs.2010.08111","title":"Combining Mixture Components for Clustering","year":2010,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":348,"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":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Mixture model; Cluster analysis; Mathematics; Determining the number of clusters in a data set; Gaussian; Entropy (arrow of time); Piecewise; Cluster (spacecraft); Computer science; Statistics; Correlation clustering; CURE data clustering algorithm; Physics","score_opus":0.01577668605565137,"score_gpt":0.280924284971499,"score_spread":0.26514759891584766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003144493","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":[0.008619989,0.000048220903,0.9895879,0.0010239475,0.00058161444,0.00006354139,0.000031371477,0.000008646407,0.000034765464],"genre_scores_gemma":[0.30874178,0.0000063231523,0.6908777,0.00027022537,0.00008890734,8.2557466e-7,0.0000040890836,0.000003878346,0.0000062905797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991261,0.00004425117,0.0003422043,0.00011421289,0.00024429226,0.00012898598],"domain_scores_gemma":[0.9984448,0.0007855499,0.0002186642,0.00006470796,0.00033603664,0.00015023284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046658705,0.00009165982,0.00020303781,0.00010145828,0.00012627366,0.000110095054,0.00023814013,0.000061974846,0.0000023745495],"category_scores_gemma":[0.00010157215,0.00007283157,0.000062406536,0.00010655243,0.000065940294,0.00014944172,0.000056040775,0.0003089091,2.4815898e-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":[0.000029698207,0.00006147537,0.00023095138,0.000028217111,0.0000366881,0.000016732549,0.00014370942,0.0003278636,0.00068636367,0.901702,0.0010620512,0.095674254],"study_design_scores_gemma":[0.00042879916,0.00013309147,0.0064019216,0.000013772244,0.000011097991,0.00019123286,0.0000014157368,0.2819791,0.000018074414,0.7092867,0.0014566922,0.000078066696],"about_ca_topic_score_codex":0.0000011021642,"about_ca_topic_score_gemma":0.0000022841048,"teacher_disagreement_score":0.30012178,"about_ca_system_score_codex":0.0000037240584,"about_ca_system_score_gemma":0.000038908776,"threshold_uncertainty_score":0.29699853},"labels":[],"label_agreement":null},{"id":"W2005955505","doi":"10.1198/106186005x47291","title":"Distance Measures and Smoothing Methodology for Imputing Features of Documents","year":2005,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Image Retrieval and Classification Techniques","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 Toronto","funders":"","keywords":"Categorical variable; Smoothing; Computer science; Class (philosophy); Missing data; Distance measures; Data mining; Artificial intelligence; Machine learning","score_opus":0.03319004123874491,"score_gpt":0.3298004024824565,"score_spread":0.2966103612437116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005955505","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":[0.0018946609,0.0007825027,0.9956866,0.0014838047,0.000051790423,0.000055958448,0.000016277474,0.00000830065,0.000020142237],"genre_scores_gemma":[0.42325258,0.00008093037,0.57653177,0.00008984684,0.00003397534,6.067899e-7,0.0000011086893,0.000001940963,0.0000072498688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99908483,0.00008070692,0.00039100315,0.00010227472,0.00024945624,0.00009174709],"domain_scores_gemma":[0.99787724,0.0012024778,0.00036019302,0.000043525735,0.00045056836,0.00006600713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068801705,0.000071359216,0.00019347263,0.00009845273,0.00008551833,0.00005581469,0.000148973,0.00003941608,7.7436755e-7],"category_scores_gemma":[0.00031769293,0.000055318953,0.00003967429,0.00011870663,0.00011294917,0.00017780109,0.00003842063,0.0001142546,3.9975898e-8],"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":[0.000036916448,0.000031784017,0.00033162875,0.000035811216,0.00003137947,0.0000016329863,0.00018917336,0.000114191665,0.0003681272,0.6593113,0.00028072763,0.33926737],"study_design_scores_gemma":[0.0005713487,0.00030132514,0.043287504,0.000045101242,0.0000268541,0.00012783511,0.00002720748,0.028849522,0.0014775759,0.9229331,0.0022402098,0.00011239262],"about_ca_topic_score_codex":0.000002530934,"about_ca_topic_score_gemma":0.000001239547,"teacher_disagreement_score":0.42135793,"about_ca_system_score_codex":0.000009339701,"about_ca_system_score_gemma":0.000037103007,"threshold_uncertainty_score":0.22558413},"labels":[],"label_agreement":null},{"id":"W2007402758","doi":"10.1198/106186001317114901","title":"Computational Algorithms for Censored-Data Problems Using Intersection Graphs","year":2001,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Censoring (clinical trials); Mathematics; Algorithm; Bivariate analysis; Intersection (aeronautics); Intersection graph; Graph; Nonparametric statistics; Computer science; Mathematical optimization; Discrete mathematics; Statistics; Line graph","score_opus":0.05423319711498033,"score_gpt":0.3320901280037434,"score_spread":0.27785693088876307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007402758","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":[0.0032875617,0.00019973307,0.995171,0.0006550979,0.00038406387,0.00013233186,0.0001395685,0.0000146252205,0.000016013595],"genre_scores_gemma":[0.07841685,0.00005016488,0.9210658,0.0002460568,0.00015933362,0.00000128634,0.000045277695,0.000008545439,0.000006665371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847037,0.000100940924,0.00057249184,0.0002510243,0.00041973498,0.00018542496],"domain_scores_gemma":[0.99795115,0.0007063116,0.000371521,0.0001280543,0.0006785521,0.00016440828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068362406,0.00014061423,0.00025762222,0.00024141606,0.00018703856,0.00015732758,0.00041696514,0.00006734417,0.0000035207672],"category_scores_gemma":[0.00009990378,0.000117853764,0.00007401053,0.0003409556,0.000106581305,0.00045727467,0.000109278546,0.00020288465,2.930445e-7],"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":[0.00006212935,0.00015917385,0.00046147744,0.000044662294,0.000122384,0.000034917302,0.000180084,0.058371354,0.000020626196,0.74540514,0.0014805791,0.19365747],"study_design_scores_gemma":[0.0004011035,0.00013830762,0.0015674622,0.000020886726,0.000019387391,0.00042902035,0.0000037786724,0.500366,8.256669e-7,0.496426,0.0005517068,0.0000755339],"about_ca_topic_score_codex":0.0000067685387,"about_ca_topic_score_gemma":0.000002287989,"teacher_disagreement_score":0.44199464,"about_ca_system_score_codex":0.00002189191,"about_ca_system_score_gemma":0.00011026359,"threshold_uncertainty_score":0.4805937},"labels":[],"label_agreement":null},{"id":"W2009789458","doi":"10.1198/106186007x208966","title":"Testing Uniformity of a Spatial Point Pattern","year":2007,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Point process; Computer science; Point (geometry); Statistics; Mathematics; Econometrics; Artificial intelligence; Geometry","score_opus":0.009024007963942805,"score_gpt":0.21951453846708102,"score_spread":0.2104905305031382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009789458","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":[0.18217587,0.000041590643,0.817592,0.000018732584,0.000066237044,0.00001715595,0.000020114694,0.0000063102543,0.00006196171],"genre_scores_gemma":[0.9065512,0.000011536378,0.093355075,0.000019041725,0.000052416843,8.2324e-8,0.0000050477856,0.0000048613488,7.6102265e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99934584,0.0000060678694,0.0003543561,0.000033630033,0.0001864674,0.00007366174],"domain_scores_gemma":[0.9992607,0.00030803637,0.00012505283,0.000017625167,0.00022556115,0.00006299539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020397927,0.00005684314,0.000117645985,0.00008960144,0.000026399932,0.000011712785,0.000036266967,0.00002914499,0.000009626334],"category_scores_gemma":[0.00006657774,0.00004758858,0.000019559531,0.00007836043,0.00003438022,0.000049451523,0.000008017275,0.000111577065,1.5593649e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035456218,0.000052740896,0.026367372,0.00025093314,0.00005728558,0.000031162086,0.0001503738,0.732161,0.00003918289,0.0036846297,0.000103512015,0.23706637],"study_design_scores_gemma":[0.0003824738,0.00014460475,0.58462137,0.00005036111,0.000021024924,0.00006924252,0.000013802535,0.34940216,0.00017398338,0.06498394,0.000053250315,0.000083747924],"about_ca_topic_score_codex":0.000012057355,"about_ca_topic_score_gemma":0.0000070231076,"teacher_disagreement_score":0.7243753,"about_ca_system_score_codex":0.000007453277,"about_ca_system_score_gemma":0.000012416269,"threshold_uncertainty_score":0.1940606},"labels":[],"label_agreement":null},{"id":"W2016116954","doi":"10.1080/10618600.2014.988337","title":"Parameter Expanded Algorithms for Bayesian Latent Variable Modeling of Genetic Pleiotropy Data","year":2014,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"National Institute of Diabetes and Digestive and Kidney Diseases","keywords":"Latent variable; Bayesian probability; Computer science; Markov chain Monte Carlo; Bayesian hierarchical modeling; Latent variable model; Pleiotropy; Algorithm; Posterior probability; Bayesian inference; Machine learning; Artificial intelligence; Data mining","score_opus":0.0422801346652598,"score_gpt":0.3027630919014125,"score_spread":0.26048295723615267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016116954","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":[0.0010611181,0.00014404728,0.99816525,0.000269713,0.00016541833,0.00008020026,0.00009977772,0.0000054056172,0.00000907399],"genre_scores_gemma":[0.1586403,0.000033098193,0.8410621,0.00015121963,0.00008861823,0.0000010740927,0.000014210277,0.000006017106,0.0000033194117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985974,0.000110794674,0.00060295116,0.00019949602,0.00033563908,0.0001537387],"domain_scores_gemma":[0.997899,0.0010369532,0.00029700872,0.00019452085,0.00042985933,0.00014265563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007294361,0.0001095209,0.00030868783,0.00011079218,0.0000740099,0.0000709136,0.00047115688,0.00005782168,0.0000025295415],"category_scores_gemma":[0.00022398998,0.00008499975,0.000051288578,0.00014519908,0.000055608827,0.00017034786,0.00011233109,0.0001312747,9.9476175e-8],"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":[0.000052367785,0.00012230685,0.00022040647,0.00007775908,0.00010421501,0.0000056094714,0.00008769375,0.08407614,0.00004641268,0.74015296,0.0005282847,0.17452587],"study_design_scores_gemma":[0.00033810618,0.00016164411,0.0004950317,0.000015909298,0.000021888152,0.000033859287,6.439463e-7,0.52150035,0.0000030073293,0.47730392,0.0000723586,0.000053297164],"about_ca_topic_score_codex":0.0000054458196,"about_ca_topic_score_gemma":5.908299e-7,"teacher_disagreement_score":0.43742418,"about_ca_system_score_codex":0.000005950049,"about_ca_system_score_gemma":0.00007714436,"threshold_uncertainty_score":0.34661892},"labels":[],"label_agreement":null},{"id":"W2018198263","doi":"10.1080/10618600.2013.837828","title":"The Conditional-Potts Clustering Model","year":2013,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Cluster analysis; Mathematics; Adjacency list; Posterior probability; Bayesian inference; Correlation clustering; Computer science; Algorithm; Bayesian probability; Statistics","score_opus":0.009403747627858285,"score_gpt":0.2532570640417436,"score_spread":0.2438533164138853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018198263","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":[0.082897745,0.00033294165,0.9151035,0.0014312506,0.00007878478,0.00004874537,0.000022380182,0.0000013671345,0.00008328944],"genre_scores_gemma":[0.9803034,0.00023291963,0.018838512,0.00036314045,0.000097796496,0.000003924222,0.000029854831,0.0000043200143,0.0001261391],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994608,0.000026439639,0.00021195787,0.000063708845,0.00016907517,0.00006800565],"domain_scores_gemma":[0.99937963,0.00006415089,0.00013380214,0.000041006253,0.00030986778,0.000071567534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000097338685,0.00005158017,0.00005740515,0.000025873522,0.00012828565,0.000047181107,0.000069658956,0.000034215722,0.000008302644],"category_scores_gemma":[0.000053717034,0.00003353897,0.000029721838,0.00003809857,0.00009068225,0.0000051068682,0.00002365988,0.00007152081,0.000001393861],"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":[0.00033781008,0.00022406818,0.0035128044,0.000052782052,0.00030301043,0.0000066738685,0.00013057071,0.35638,0.05782501,0.205865,0.28573027,0.08963203],"study_design_scores_gemma":[0.00071817136,0.00024248398,0.07619515,0.000013908271,0.000018815199,0.00009504526,0.000060987866,0.27931938,0.00032851507,0.6284047,0.014464619,0.000138238],"about_ca_topic_score_codex":8.119954e-7,"about_ca_topic_score_gemma":0.0000014749806,"teacher_disagreement_score":0.8974056,"about_ca_system_score_codex":0.0000036705796,"about_ca_system_score_gemma":0.000049120135,"threshold_uncertainty_score":0.13676795},"labels":[],"label_agreement":null},{"id":"W2021405587","doi":"10.1198/106186002718","title":"Detecting Clusters and Nonlinearity in Three-Dimensional Dynamic Graphs","year":2002,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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":"York University","funders":"","keywords":"Cluster (spacecraft); Nonlinear system; Computer science; Diagonal; Artificial intelligence; Mathematics; Pattern recognition (psychology); Data mining; Physics; Geometry","score_opus":0.052521466278716976,"score_gpt":0.356511468138576,"score_spread":0.303990001859859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021405587","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":[0.2313269,0.00021390126,0.7679649,0.0003001295,0.000058011563,0.000058192825,0.00006204377,0.000004753876,0.000011198192],"genre_scores_gemma":[0.44191954,0.00003482207,0.5579473,0.00007262283,0.000013591977,5.969085e-7,0.0000014173663,0.000006622902,0.0000035281696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99870133,0.00009148415,0.0005754672,0.00013922744,0.00033028936,0.00016219263],"domain_scores_gemma":[0.9959331,0.0034436376,0.0002378134,0.00004102848,0.00019189359,0.00015248731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043043715,0.00012646036,0.00031196143,0.00016554672,0.000095386036,0.000026878884,0.000052944917,0.00006371013,0.000018220033],"category_scores_gemma":[0.0008198803,0.00010301827,0.000041626576,0.00016004662,0.00017996812,0.00008845748,0.00003712423,0.00037540524,2.828127e-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":[0.0002106969,0.00050590996,0.004553381,0.00023880291,0.000119117554,0.00031421252,0.0003155421,0.010916398,0.00004547125,0.7724802,0.00024685808,0.21005341],"study_design_scores_gemma":[0.00049035414,0.00011717042,0.009235727,0.000037029415,0.000018957677,0.00013299736,0.000008848792,0.38786376,4.5612381e-7,0.60201186,0.000011212146,0.000071665745],"about_ca_topic_score_codex":0.0000046714135,"about_ca_topic_score_gemma":0.000053848446,"teacher_disagreement_score":0.37694734,"about_ca_system_score_codex":0.000016301203,"about_ca_system_score_gemma":0.000013586076,"threshold_uncertainty_score":0.4200963},"labels":[],"label_agreement":null},{"id":"W2034304555","doi":"10.1198/106186001317243412","title":"CriSP: A Tool for Bump Hunting","year":2001,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":10,"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":"Smoothing; Bootstrapping (finance); Test statistic; Mathematics; Resampling; Statistic; Function (biology); Statistics; Statistical hypothesis testing; Algorithm; Computer science; Econometrics","score_opus":0.07553251069649514,"score_gpt":0.4139923701140274,"score_spread":0.33845985941753226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034304555","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":[0.024577364,0.00006807331,0.9745168,0.00043647358,0.0001076861,0.00010655559,0.0001344975,0.000007969017,0.000044592092],"genre_scores_gemma":[0.11386424,0.000046814373,0.8856764,0.00019576712,0.00015458096,0.0000031025993,0.0000054665325,0.000012366859,0.000041257004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877816,0.000056290624,0.0005927456,0.00010870565,0.00029463126,0.00016948226],"domain_scores_gemma":[0.99368924,0.005284603,0.000308444,0.000043070635,0.00055564556,0.000118993026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005235657,0.00011037517,0.00029883615,0.00008449053,0.00012520177,0.000038406466,0.00007054995,0.00004965159,0.000019649868],"category_scores_gemma":[0.0021107513,0.000086746906,0.00007585107,0.00010554616,0.00009127793,0.00008725677,0.000019313246,0.0001715705,3.8328906e-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":[0.00013669106,0.00009254296,0.00046549505,0.00006873807,0.000047214842,0.00002991234,0.00005339304,0.0006651316,0.000020576363,0.9525841,0.0013374717,0.04449873],"study_design_scores_gemma":[0.000734527,0.00026286082,0.0031403457,0.000036541853,0.00006475831,0.00016861767,0.000020869227,0.028590886,0.0000032046846,0.9644016,0.0024655666,0.000110219255],"about_ca_topic_score_codex":8.862105e-7,"about_ca_topic_score_gemma":0.0000011905336,"teacher_disagreement_score":0.08928688,"about_ca_system_score_codex":0.000011289179,"about_ca_system_score_gemma":0.00003726948,"threshold_uncertainty_score":0.3537436},"labels":[],"label_agreement":null},{"id":"W2037392129","doi":"10.1198/jcgs.2011.10021","title":"Penalized Nonlinear Least Squares Estimation of Time-Varying Parameters in Ordinary Differential Equations","year":2011,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Institute of Allergy and Infectious Diseases; King Abdullah University of Science and Technology","keywords":"Ode; Ordinary differential equation; Applied mathematics; Nonlinear system; Mathematics; Non-linear least squares; Ordinary least squares; Least-squares function approximation; Function (biology); Mathematical optimization; Polynomial; Estimation theory; Algorithm; Differential equation; Statistics; Mathematical analysis","score_opus":0.024963762130448715,"score_gpt":0.2653934609609376,"score_spread":0.24042969883048887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037392129","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":[0.32888314,0.000015157179,0.6708991,0.0000307776,0.00004905356,0.000035812514,0.0000400545,0.0000015048005,0.000045404508],"genre_scores_gemma":[0.9046039,0.000005197202,0.095287174,0.0000110488,0.000038977036,9.661253e-7,0.000036299534,0.000004382226,0.00001208496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917424,0.00005729432,0.0004353995,0.00006806576,0.00018558351,0.00007940167],"domain_scores_gemma":[0.999241,0.00026431575,0.000266593,0.000027789361,0.00013358553,0.00006670761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008210022,0.00007607848,0.00018651612,0.0001266698,0.000044524015,0.000013966194,0.000049593516,0.00002360903,0.00022938401],"category_scores_gemma":[0.000014851912,0.000063618005,0.000057282443,0.00012469207,0.0000813865,0.00009259192,0.000011262342,0.0001521332,0.000001046877],"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":[0.0006867458,0.0009903751,0.006665721,0.000051241932,0.00021631065,0.000015596435,0.00070407137,0.8045516,0.000118923424,0.081094,0.00035374032,0.10455165],"study_design_scores_gemma":[0.000711705,0.00014805417,0.009877947,0.000041570493,0.000034972487,0.0000075654175,0.000023024544,0.8348039,0.00004035621,0.1542345,0.0000057831617,0.000070659094],"about_ca_topic_score_codex":0.00003153304,"about_ca_topic_score_gemma":5.64202e-7,"teacher_disagreement_score":0.5757207,"about_ca_system_score_codex":0.0000046435043,"about_ca_system_score_gemma":0.00003144456,"threshold_uncertainty_score":0.2594267},"labels":[],"label_agreement":null},{"id":"W2044676318","doi":"10.1080/10618600.2012.681237","title":"The Generalized Ridge Trace Plot: Visualizing Bias<i>and</i>Precision","year":2012,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Plot (graphics); Univariate; Covariance; Mathematics; TRACE (psycholinguistics); Statistics; Ridge; Bivariate analysis; Algorithm; Multivariate statistics; Computer science","score_opus":0.12150972289259729,"score_gpt":0.4251971058374141,"score_spread":0.3036873829448168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044676318","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":[0.077631354,0.0012397061,0.9203196,0.00042350928,0.00019414819,0.000072315335,0.00008760388,0.000007549406,0.000024180594],"genre_scores_gemma":[0.2364615,0.00037475806,0.7628497,0.000100932855,0.00017219181,0.0000017163725,0.000002786991,0.000013342121,0.000023063949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998329,0.00026337543,0.0006284063,0.00009327668,0.0004554979,0.00023044519],"domain_scores_gemma":[0.98867667,0.010370886,0.00035633604,0.000056766497,0.00027706227,0.0002622966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013906921,0.00013360096,0.00028837007,0.000060920927,0.000305778,0.00006633917,0.00008194259,0.000055474273,0.000007019034],"category_scores_gemma":[0.002067543,0.00008015369,0.000057551988,0.00010724452,0.00019787083,0.00013815555,0.000043875636,0.00026369598,5.8798804e-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":[0.000091847476,0.00007757161,0.0002602543,0.000025928772,0.000044354478,0.0000075278153,0.00020445517,0.00014510966,0.00003510946,0.9437299,0.0011152567,0.054262724],"study_design_scores_gemma":[0.00054957584,0.00013805002,0.0052414727,0.000032997148,0.00006797199,0.00017395549,0.000035843812,0.01621367,0.000014820481,0.9731907,0.0042318497,0.00010906323],"about_ca_topic_score_codex":0.0000016566014,"about_ca_topic_score_gemma":8.340696e-7,"teacher_disagreement_score":0.15883015,"about_ca_system_score_codex":0.000012608378,"about_ca_system_score_gemma":0.000025497135,"threshold_uncertainty_score":0.32685727},"labels":[],"label_agreement":null},{"id":"W2047978125","doi":"10.1198/jcgs.2009.06134","title":"Examples of Adaptive MCMC","year":2009,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":1078,"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":"Markov chain Monte Carlo; Metropolis–Hastings algorithm; Gibbs sampling; Markov chain; Computer science; Algorithm; Logarithm; Dimension (graph theory); Multivariate statistics; Mathematics; Artificial intelligence; Machine learning; Bayesian probability","score_opus":0.058553184144160234,"score_gpt":0.34562072589299764,"score_spread":0.2870675417488374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047978125","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":[0.10413415,0.00019083424,0.8949464,0.00028477836,0.000062433406,0.000044222255,0.0000662048,0.0000035484268,0.00026741167],"genre_scores_gemma":[0.49150613,0.00003933818,0.5083071,0.00007982179,0.000049161263,1.37263e-7,0.0000017120464,0.00000298188,0.000013609423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893147,0.00009363394,0.0004973593,0.00006343063,0.00032765194,0.00008647561],"domain_scores_gemma":[0.99732065,0.0016842639,0.00038084888,0.00004083948,0.00047540406,0.00009800933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047959812,0.000083096704,0.00028754663,0.000105838604,0.000038168244,0.000011441136,0.00006726487,0.000042654956,0.000008886655],"category_scores_gemma":[0.00044616743,0.000062258165,0.000070192706,0.00010986913,0.000090109665,0.000042616826,0.000011251092,0.00014472574,9.723732e-9],"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":[0.000114835915,0.00013650265,0.0002480379,0.000029311059,0.00005239222,0.000022148417,0.00017023527,0.00022238708,0.00006997374,0.9606035,0.0023337507,0.035996955],"study_design_scores_gemma":[0.000472597,0.0006655096,0.012610597,0.00004586666,0.000049600592,0.00007654084,0.00006158901,0.0037021195,0.000029262923,0.9817947,0.00042037189,0.00007125843],"about_ca_topic_score_codex":0.0000015545164,"about_ca_topic_score_gemma":0.0000015388521,"teacher_disagreement_score":0.387372,"about_ca_system_score_codex":0.0000070275,"about_ca_system_score_gemma":0.00004084712,"threshold_uncertainty_score":0.25388142},"labels":[],"label_agreement":null},{"id":"W2050605581","doi":"10.1198/1061860031220","title":"Feature Extraction for Nonparametric Discriminant Analysis","year":2003,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Linear discriminant analysis; Pattern recognition (psychology); Optimal discriminant analysis; Kernel Fisher discriminant analysis; Multiple discriminant analysis; Mathematics; Artificial intelligence; Discriminant; Dimensionality reduction; Nonparametric statistics; Curse of dimensionality; Projection pursuit; Parametric statistics; Gaussian; Statistics; Computer science; Facial recognition system","score_opus":0.014343301322935882,"score_gpt":0.28878006122655664,"score_spread":0.27443675990362076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050605581","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":[0.012592137,0.00015449773,0.986118,0.0008523383,0.00017145494,0.000049607563,0.00003279906,0.0000049543432,0.000024210023],"genre_scores_gemma":[0.4476545,0.000048722915,0.5521119,0.000121286816,0.000023508184,0.0000015375587,0.000011300987,0.0000021482026,0.000025072679],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992209,0.00005523824,0.00023216994,0.000110306995,0.00028169775,0.00009967618],"domain_scores_gemma":[0.99846315,0.0007465727,0.0002364318,0.00004723332,0.00040290476,0.00010371862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002716637,0.00007333754,0.00017771134,0.0003784398,0.000112600464,0.00009673467,0.000094055904,0.00004764285,0.0000050915137],"category_scores_gemma":[0.00022128047,0.00005391878,0.00010549597,0.0007120033,0.00003088809,0.00020887122,0.00001021526,0.00012744218,6.994949e-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":[0.00010279136,0.00041617922,0.0041586105,0.00006922675,0.0006319643,0.000048776783,0.00019922371,0.026356338,0.00021210511,0.8508772,0.020334272,0.09659328],"study_design_scores_gemma":[0.0007637118,0.00036736112,0.07601929,0.000019117646,0.0003164696,0.0001516519,0.000033012064,0.19164434,0.00009669215,0.72293425,0.007491765,0.00016232797],"about_ca_topic_score_codex":9.3523255e-7,"about_ca_topic_score_gemma":0.0000013379471,"teacher_disagreement_score":0.43506235,"about_ca_system_score_codex":0.000009244658,"about_ca_system_score_gemma":0.00003975729,"threshold_uncertainty_score":0.2198744},"labels":[],"label_agreement":null},{"id":"W2053652664","doi":"10.1080/10618600.2013.841584","title":"Parallel Bayesian Additive Regression Trees","year":2014,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"Office of Science; U.S. Department of Energy","keywords":"Markov chain Monte Carlo; Computer science; Bayesian probability; Boosting (machine learning); Approximate Bayesian computation; Bayesian inference; Inference; Computation; Machine learning; Algorithm; Artificial intelligence","score_opus":0.007996393648830565,"score_gpt":0.24549760152655614,"score_spread":0.23750120787772558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053652664","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":[0.0011812861,0.0000841874,0.99669147,0.0016834649,0.00011646924,0.000025912137,0.000017355038,0.000010630448,0.00018925351],"genre_scores_gemma":[0.59687316,0.000048513495,0.402731,0.00025858107,0.00007125547,5.1469715e-7,0.000003545736,0.0000028442594,0.000010561923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988847,0.00007508211,0.0003696555,0.00013755925,0.00039748257,0.0001355416],"domain_scores_gemma":[0.998534,0.0005623002,0.00031061185,0.00007058605,0.00034347142,0.00017902942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021869125,0.00010990969,0.000203586,0.0001227798,0.00012323595,0.00013372905,0.00027525326,0.000046967034,0.000014341451],"category_scores_gemma":[0.0001401353,0.00007571774,0.000047245394,0.00020578821,0.00010411291,0.00025054402,0.000055811903,0.00019070903,0.00000225358],"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":[0.000025515923,0.00005464186,0.0005793546,0.000014004884,0.000019758514,0.000026324671,0.00010105406,0.0008142871,0.0000033477659,0.86256975,0.0025302297,0.13326173],"study_design_scores_gemma":[0.00037118563,0.000306753,0.050632033,0.000051988496,0.000008859745,0.00014272096,0.0000066999733,0.1411783,0.000005108753,0.805434,0.0017667932,0.0000955595],"about_ca_topic_score_codex":0.000001666933,"about_ca_topic_score_gemma":0.0000022141562,"teacher_disagreement_score":0.5956919,"about_ca_system_score_codex":0.000007893298,"about_ca_system_score_gemma":0.000072690586,"threshold_uncertainty_score":0.30876797},"labels":[],"label_agreement":null},{"id":"W2072240935","doi":"10.1198/106186008x321068","title":"Adjusted Empirical Likelihood and its Properties","year":2008,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":207,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASL Environmental Sciences (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Empirical likelihood; Likelihood function; Restricted maximum likelihood; Mathematics; Maximization; Expectation–maximization algorithm; Likelihood principle; Statistics; Mathematical optimization; Econometrics; Maximum likelihood; Computer science; Quasi-maximum likelihood; Confidence interval","score_opus":0.15607019570708372,"score_gpt":0.353252275367028,"score_spread":0.1971820796599443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072240935","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":[0.4956645,0.00054717076,0.5028055,0.0006796296,0.000079153026,0.00006960484,0.00006733573,0.0000094777915,0.0000776383],"genre_scores_gemma":[0.64632666,0.00017072863,0.3532394,0.00017385068,0.00006529036,9.3702226e-7,0.0000013366509,0.000007038806,0.000014783382],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868304,0.0001242187,0.00053100975,0.000110337496,0.00040174133,0.00014967704],"domain_scores_gemma":[0.997012,0.0019826472,0.00021044504,0.00003571213,0.0005342379,0.00022496628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028706514,0.0001217793,0.0003186315,0.000092897695,0.0001431908,0.000025373338,0.000065803295,0.00006322092,0.000030117795],"category_scores_gemma":[0.0017409585,0.00008362722,0.000036974005,0.0001287168,0.0002164377,0.000064574604,0.000035884226,0.00026080353,0.0000012498188],"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":[0.00025269313,0.00040538932,0.009742261,0.0002672649,0.000161111,0.00027146036,0.00085644674,0.000059263617,0.000086943335,0.9518283,0.005875467,0.030193409],"study_design_scores_gemma":[0.0005886345,0.00042379863,0.07890843,0.00005685447,0.000051166895,0.0008371325,0.000029800503,0.015746517,0.000018029743,0.90296185,0.0002543553,0.00012341363],"about_ca_topic_score_codex":0.0000015179289,"about_ca_topic_score_gemma":9.076595e-7,"teacher_disagreement_score":0.15066214,"about_ca_system_score_codex":0.000008237195,"about_ca_system_score_gemma":0.00008228958,"threshold_uncertainty_score":0.3410219},"labels":[],"label_agreement":null},{"id":"W2080972498","doi":"10.1080/10618600.2000.10474879","title":"Markov Chain Sampling Methods for Dirichlet Process Mixture Models","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2212,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Dirichlet distribution; Hierarchical Dirichlet process; Markov chain Monte Carlo; Metropolis–Hastings algorithm; Markov chain; Dirichlet process; Mathematics; Prior probability; Conjugate prior; Computer science; Sampling (signal processing); Mathematical optimization; Applied mathematics; Statistics; Bayesian probability","score_opus":0.026056546071332128,"score_gpt":0.3550975326748263,"score_spread":0.3290409866034942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080972498","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":[0.00075478584,0.0005908089,0.9968912,0.001351629,0.00013055153,0.00011966213,0.000049318598,0.0000137733905,0.000098276156],"genre_scores_gemma":[0.017723335,0.00011490999,0.9812755,0.0006920618,0.00013100162,0.0000044980934,0.0000068138506,0.000009536401,0.0000423416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861145,0.00017554774,0.00050958944,0.00020398265,0.00029553342,0.00020387913],"domain_scores_gemma":[0.9975937,0.0014225312,0.00022253502,0.000085766005,0.00047874294,0.00019670697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545322,0.00014907985,0.00031741703,0.0001293733,0.00015778778,0.00012993516,0.00031630762,0.00008485125,0.000012552368],"category_scores_gemma":[0.00010241538,0.00011488226,0.000096546326,0.00027524686,0.00007231227,0.0002832073,0.00002537238,0.00024619457,2.5069468e-7],"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":[0.00004749068,0.000050016657,0.000008689816,0.000038013568,0.000036414007,0.000005503342,0.00019992213,0.010335753,0.000009194619,0.38175908,0.0004257402,0.60708416],"study_design_scores_gemma":[0.00029778449,0.000112482005,0.00028479283,0.000018467159,0.000016064141,0.00009059925,0.0000020837076,0.42082125,0.000005446339,0.5772555,0.0010092694,0.00008626935],"about_ca_topic_score_codex":9.2706875e-7,"about_ca_topic_score_gemma":3.06515e-7,"teacher_disagreement_score":0.6069979,"about_ca_system_score_codex":0.000010358478,"about_ca_system_score_gemma":0.00009096467,"threshold_uncertainty_score":0.46847627},"labels":[],"label_agreement":null},{"id":"W2087043468","doi":"10.1198/106186007x257025","title":"On Using Truncated Sequential Probability Ratio Test Boundaries for Monte Carlo Implementation of Hypothesis Tests","year":2007,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Institutes of Health; University of Lethbridge","keywords":"Resampling; Monte Carlo method; Mathematics; Estimator; Sequential probability ratio test; Minimax; Statistical hypothesis testing; Algorithm; Optimal stopping; Boundary (topology); Statistics; Computer science; Mathematical optimization","score_opus":0.117921852029038,"score_gpt":0.4014752359088856,"score_spread":0.28355338387984763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087043468","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":[0.36941153,0.000009845499,0.62983316,0.0000780613,0.000069193506,0.00014888596,0.0004412596,0.0000033564838,0.0000047184867],"genre_scores_gemma":[0.50489306,0.0000016251204,0.4950232,0.00003441458,0.000036632133,0.0000010831316,0.0000026907526,0.000005973275,0.0000013034705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99820435,0.00008744847,0.0009915462,0.000119412805,0.00043630533,0.0001609186],"domain_scores_gemma":[0.98182,0.016378423,0.0006514285,0.00005357781,0.0009884121,0.00010818045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011923442,0.0001277451,0.00034710218,0.0001266933,0.00016400787,0.00006177341,0.000068622234,0.000057297828,0.000026935473],"category_scores_gemma":[0.0066179223,0.00010145653,0.000073450654,0.00015921069,0.0003066272,0.00007470159,0.000014311865,0.00013311798,9.565474e-8],"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":[0.00038806064,0.00033886306,0.004950316,0.00025408718,0.00011794784,0.000009501608,0.0002960481,0.0007658717,0.00063307397,0.96561646,0.00043118547,0.026198603],"study_design_scores_gemma":[0.0008019606,0.0008694979,0.062405642,0.00004458361,0.00011221841,0.000024515552,0.00006672682,0.0120162945,0.00034744156,0.92319065,0.000021349544,0.000099127836],"about_ca_topic_score_codex":0.000024381761,"about_ca_topic_score_gemma":0.00003860866,"teacher_disagreement_score":0.13548157,"about_ca_system_score_codex":0.00004258739,"about_ca_system_score_gemma":0.000201063,"threshold_uncertainty_score":0.7922749},"labels":[],"label_agreement":null},{"id":"W2090439194","doi":"10.1080/10618600.2000.10474890","title":"Users, Programmers, and Statistical Software","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Software analytics; Software engineering; Software; Programmer; Software construction; Data science; Software development; Human–computer interaction; Programming language","score_opus":0.009443144865113733,"score_gpt":0.25656438406069376,"score_spread":0.24712123919558002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090439194","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":[0.0146379545,0.0001489885,0.98427254,0.0006202273,0.000040771854,0.000052606858,0.00016288365,0.000036489273,0.00002754026],"genre_scores_gemma":[0.11774131,0.00014219603,0.88181883,0.00022526576,0.000033445227,0.0000010757831,0.000021438189,0.00000533202,0.000011111301],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988611,0.00006411462,0.00037190298,0.00016060338,0.00038659124,0.00015568544],"domain_scores_gemma":[0.998702,0.00069809717,0.00013126097,0.00008328272,0.0001755734,0.00020977858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002501104,0.000111480054,0.00019689913,0.000107605265,0.00009617242,0.00018520176,0.0002349172,0.00004692112,0.00003435783],"category_scores_gemma":[0.00012895813,0.0000915655,0.000023149847,0.00017829197,0.00021383025,0.00026339368,0.00006415017,0.0002049374,0.0000018704768],"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":[0.00002836007,0.0000811953,0.0035425527,0.00001895865,0.0000350446,0.00011842169,0.00008512578,0.000073780975,0.0000010507647,0.28877875,0.007645368,0.6995914],"study_design_scores_gemma":[0.0005269334,0.0007158358,0.1075243,0.000040877145,0.000028658107,0.0007925289,0.00000767933,0.02034842,0.0000031062311,0.8602011,0.009623846,0.0001866925],"about_ca_topic_score_codex":0.0000070350443,"about_ca_topic_score_gemma":0.0000013517466,"teacher_disagreement_score":0.69940466,"about_ca_system_score_codex":0.000008904783,"about_ca_system_score_gemma":0.000058857484,"threshold_uncertainty_score":0.37339327},"labels":[],"label_agreement":null},{"id":"W2108273125","doi":"10.1080/10618600.2012.679223","title":"Stochastic Stepwise Ensembles for Variable Selection","year":2012,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Feature selection; Selection (genetic algorithm); Mathematics; Computer science; Artificial intelligence","score_opus":0.06160899670397949,"score_gpt":0.35204429865891623,"score_spread":0.2904353019549367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108273125","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":[0.011369752,0.000103746446,0.9878906,0.0001242028,0.00021375892,0.000101365025,0.00015252648,0.000007266241,0.000036753005],"genre_scores_gemma":[0.23192883,0.0000045939796,0.76773757,0.00009099336,0.00020345686,0.000002699233,0.0000043000014,0.000008716274,0.000018879393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988989,0.00008224518,0.00047084535,0.0000727115,0.0002782829,0.00019697474],"domain_scores_gemma":[0.99251604,0.0064339936,0.00027425596,0.00002998608,0.00054936117,0.00019634223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006926739,0.00010458323,0.0002589223,0.00009164606,0.00011354792,0.000032610627,0.000053979493,0.000057208126,0.00004595017],"category_scores_gemma":[0.0024112295,0.00008102207,0.00004485972,0.00013544613,0.000077145916,0.00008665913,0.0000138759,0.00015683427,6.8755287e-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":[0.00008609794,0.00013981527,0.0003842731,0.00007461813,0.00005345708,9.18707e-7,0.00006756154,0.0005173319,0.00004123212,0.9882304,0.0023842636,0.008020014],"study_design_scores_gemma":[0.0005016265,0.00030998158,0.0071147704,0.000034947207,0.00010619079,0.00014106311,0.000020872852,0.02666089,0.000006132322,0.9646336,0.00037112043,0.00009879213],"about_ca_topic_score_codex":0.0000016923018,"about_ca_topic_score_gemma":4.2796114e-7,"teacher_disagreement_score":0.22055908,"about_ca_system_score_codex":0.000016179054,"about_ca_system_score_gemma":0.000055547942,"threshold_uncertainty_score":0.3303984},"labels":[],"label_agreement":null},{"id":"W2138868843","doi":"10.1198/106186002317375631","title":"A Brief History of the Mosaic Display","year":2002,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mosaic; Computer science; Computer graphics (images); Artificial intelligence; Geography; Archaeology","score_opus":0.018858655242182307,"score_gpt":0.2492495687104026,"score_spread":0.2303909134682203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138868843","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":[0.0018487314,0.00040479933,0.99625975,0.0010002849,0.000269962,0.000022294365,0.000051136627,0.0000037812915,0.0001392694],"genre_scores_gemma":[0.8904844,0.00020420416,0.107103534,0.0015639233,0.00007629446,3.47464e-7,0.00000783097,0.0000064264127,0.0005530462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905866,0.00005449847,0.0003505974,0.000068023095,0.0004005658,0.000067632645],"domain_scores_gemma":[0.9990362,0.000246294,0.0003066243,0.00008010258,0.00025720947,0.00007359595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013853918,0.000058047244,0.00012734276,0.00007093872,0.000040764964,0.000027213255,0.00028872935,0.000023087898,0.000028387674],"category_scores_gemma":[0.000109990724,0.00003794231,0.000052025996,0.00020034134,0.00015084825,0.00013207161,0.00006285147,0.000112549395,9.291475e-7],"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":[0.0000032903174,0.00012033893,0.0013250855,0.000019032017,0.00003015274,0.000009264965,0.00025531664,0.0016818361,0.0000089024625,0.92307585,0.06520429,0.0082666185],"study_design_scores_gemma":[0.0004732675,0.00012786657,0.02476968,0.000034029268,0.00002595456,0.00011633099,0.000006497917,0.74202216,0.000003413633,0.18166079,0.050670546,0.00008946952],"about_ca_topic_score_codex":0.0000021697874,"about_ca_topic_score_gemma":0.0000011148722,"teacher_disagreement_score":0.8891562,"about_ca_system_score_codex":0.000022243716,"about_ca_system_score_gemma":0.00005511633,"threshold_uncertainty_score":0.15472426},"labels":[],"label_agreement":null},{"id":"W2144832675","doi":"10.1080/10618600.2013.844700","title":"Bayesian Estimation of Discrete Multivariate Latent Structure Models With Structural Zeros","year":2013,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":55,"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":"Memorial University of Newfoundland; National Science Foundation","keywords":"Categorical variable; Local independence; Conditional independence; Latent class model; Mathematics; Posterior probability; Bayesian probability; Latent variable; Econometrics; Computer science; Latent variable model; Statistics","score_opus":0.008773760577415121,"score_gpt":0.2503721420045232,"score_spread":0.24159838142710804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144832675","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":[0.03648087,0.000056529127,0.96277034,0.00044228332,0.000075600874,0.000105229425,0.000054060947,0.0000068412573,0.000008250144],"genre_scores_gemma":[0.49946895,0.0000036647757,0.5004547,0.00004722048,0.000015053617,4.7758004e-7,0.0000043874475,0.0000034450895,0.0000021011924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986929,0.0000944288,0.00048081533,0.00014344932,0.00044929344,0.00013906677],"domain_scores_gemma":[0.998563,0.0002671989,0.00042364362,0.000089684836,0.0004972904,0.00015921744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001376353,0.00013939782,0.00027994532,0.00012274325,0.00007884826,0.00010327775,0.0002091145,0.000058503923,0.000010250838],"category_scores_gemma":[0.00002821515,0.00008804619,0.000046071167,0.00019244086,0.00011474527,0.00053234556,0.00004559337,0.00021397237,1.7085722e-7],"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":[0.000033170254,0.000020545427,0.00026454488,0.000036885656,0.000072400464,0.000011015623,0.00031250532,0.25344223,0.00010955992,0.65710175,0.00006054361,0.088534854],"study_design_scores_gemma":[0.00029423583,0.00013971943,0.016081033,0.000020787127,0.0000128450165,0.00007519321,0.000001747942,0.4970749,0.000018295033,0.48622087,8.5991286e-7,0.000059525417],"about_ca_topic_score_codex":0.00002273609,"about_ca_topic_score_gemma":0.0000013923841,"teacher_disagreement_score":0.46298808,"about_ca_system_score_codex":0.000010027448,"about_ca_system_score_gemma":0.00006325052,"threshold_uncertainty_score":0.35904193},"labels":[],"label_agreement":null},{"id":"W2162021827","doi":"10.1198/1061860043001","title":"A Split-Merge Markov chain Monte Carlo Procedure for the Dirichlet Process Mixture Model","year":2004,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":475,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Markov chain Monte Carlo; Metropolis–Hastings algorithm; Hierarchical Dirichlet process; Dirichlet distribution; Rejection sampling; Dirichlet process; Markov chain; Slice sampling; Computer science; Algorithm; Monte Carlo method; Merge (version control); Hybrid Monte Carlo; Mathematics; Bayesian probability; Artificial intelligence; Latent Dirichlet allocation; Machine learning; Statistics; Topic model","score_opus":0.011245201410113275,"score_gpt":0.2784303576061979,"score_spread":0.2671851561960846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162021827","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":[0.0044899206,0.000765975,0.9869781,0.007298457,0.00013934722,0.00020996947,0.000092845934,0.000011562371,0.00001378097],"genre_scores_gemma":[0.31129026,0.00006376345,0.6876686,0.00083046645,0.00010619623,0.000008544285,0.0000020192779,0.000007758885,0.000022398019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986659,0.000043074975,0.00043039402,0.00019399448,0.00045871406,0.00020788243],"domain_scores_gemma":[0.99829435,0.00053574867,0.0002871034,0.00009981736,0.0006210398,0.0001619088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000533215,0.0001602078,0.00025095118,0.000092942704,0.00023250075,0.00012463436,0.00040547265,0.00007843803,8.961514e-7],"category_scores_gemma":[0.00015470175,0.0000978698,0.00010298055,0.00027792208,0.00010354685,0.00019004165,0.000045864937,0.00030212736,1.5718317e-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":[0.00007410368,0.00010336055,0.00004695313,0.000090697315,0.00007770558,0.000018578694,0.0006759507,0.16432518,0.000007320963,0.8034155,0.001639788,0.029524885],"study_design_scores_gemma":[0.00045593275,0.00010783026,0.0009492292,0.000024135785,0.000024963576,0.00009606746,0.0000069239277,0.4646638,0.0000032814426,0.53348213,0.00010804754,0.00007762013],"about_ca_topic_score_codex":0.0000024836431,"about_ca_topic_score_gemma":0.0000044541025,"teacher_disagreement_score":0.30680034,"about_ca_system_score_codex":0.000017649432,"about_ca_system_score_gemma":0.00025149604,"threshold_uncertainty_score":0.39910147},"labels":[],"label_agreement":null},{"id":"W2165084744","doi":"10.1198/1061860032283","title":"Multivariate Normal Probabilities: Implementing an Old Idea of Plackett's","year":2003,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Multivariate statistics; Multivariate normal distribution; Computation; Multivariate analysis; Computer science; Key (lock); Statistics; Mathematics; Econometrics; Algorithm","score_opus":0.05978480149004771,"score_gpt":0.37181750896245586,"score_spread":0.31203270747240813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165084744","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":[0.36709064,0.000032710417,0.63209605,0.000110433866,0.000046796027,0.00013268067,0.00028802935,0.000005738964,0.00019690346],"genre_scores_gemma":[0.6019069,0.0000081898415,0.3979951,0.000030418603,0.00002470156,0.00000155388,0.00000806328,0.0000074053514,0.000017649656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755496,0.00033125377,0.0009785717,0.00013940828,0.00072257145,0.00027322312],"domain_scores_gemma":[0.99373317,0.004706591,0.0003848358,0.000086890024,0.00084973493,0.00023879197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019006113,0.00012846322,0.0003639823,0.00012824094,0.00012963879,0.000045901586,0.00012897015,0.0000642425,0.0001323144],"category_scores_gemma":[0.004722155,0.00010253906,0.00007099474,0.00018209711,0.00029620167,0.0001658247,0.000038188253,0.00032035055,5.741742e-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":[0.00011550231,0.00034885193,0.0029996533,0.00026187007,0.000069376016,0.000017351163,0.00039722116,0.000283833,0.00003747537,0.99212927,0.00022449679,0.0031150926],"study_design_scores_gemma":[0.00085015496,0.000585812,0.012921281,0.000042939268,0.00004083734,0.00006126515,0.00014945635,0.00742741,0.00004170073,0.97752863,0.00024321553,0.000107308035],"about_ca_topic_score_codex":0.000015470821,"about_ca_topic_score_gemma":0.000017014918,"teacher_disagreement_score":0.23481628,"about_ca_system_score_codex":0.000022735145,"about_ca_system_score_gemma":0.00016233619,"threshold_uncertainty_score":0.5653202},"labels":[],"label_agreement":null},{"id":"W2234615877","doi":"10.1080/10618600.2018.1546593","title":"A General Hybrid Clustering Technique","year":2018,"lang":"en","type":"preprint","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Division of Mathematical Sciences; Defense Threat Reduction Agency","keywords":"Cluster analysis; Single-linkage clustering; Complete-linkage clustering; Dendrogram; Complete linkage; Correlation clustering; CURE data clustering algorithm; Series (stratigraphy); Regular polygon; Mathematics; k-medians clustering; Computer science; Joins; Hamming distance; Combinatorics; Data mining; Artificial intelligence; Geometry","score_opus":0.020955277286332633,"score_gpt":0.3180252457379465,"score_spread":0.2970699684516139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2234615877","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":[0.0026892922,0.00022959262,0.9956621,0.00054707495,0.000578626,0.00016124133,0.00008034919,0.000028439303,0.000023313576],"genre_scores_gemma":[0.03935481,0.00013560474,0.9598658,0.00015148381,0.00042630866,0.000008999169,0.000012929479,0.000015818829,0.000028248238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99775565,0.00012818606,0.00069106556,0.0003118791,0.00085417443,0.00025907642],"domain_scores_gemma":[0.9974967,0.0005151413,0.00052130496,0.00020301432,0.0010109505,0.0002528754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004794802,0.00022559961,0.00041169242,0.00036229767,0.00012935032,0.00027530678,0.00080029806,0.000119288634,0.0000050683925],"category_scores_gemma":[0.00018335946,0.00019902916,0.00010233911,0.00018251133,0.00023383703,0.00016250885,0.001429167,0.00097455055,0.0000017780337],"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":[0.0002214491,0.00058043667,0.00050510734,0.0018270188,0.00082191685,0.0035284054,0.00058797264,0.4636712,0.00024957585,0.13508223,0.013333252,0.3795914],"study_design_scores_gemma":[0.00020669187,0.0002135841,0.0022687858,0.00012572871,0.000010887249,0.00067088654,9.5149414e-7,0.45569018,0.00004104571,0.54030013,0.00031795818,0.00015318733],"about_ca_topic_score_codex":0.000005981103,"about_ca_topic_score_gemma":0.0000010083354,"teacher_disagreement_score":0.4052179,"about_ca_system_score_codex":0.00006271652,"about_ca_system_score_gemma":0.00026714726,"threshold_uncertainty_score":0.8116174},"labels":[],"label_agreement":null},{"id":"W2256665692","doi":"10.1080/10618600.2012.723569","title":"An Adaptive Interacting Wang–Landau Algorithm for Automatic Density Exploration","year":2012,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Algorithm; Artificial intelligence; Statistical physics; Physics","score_opus":0.07624063086788722,"score_gpt":0.3818334136523043,"score_spread":0.30559278278441704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256665692","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":[0.07671965,0.00005448379,0.92263275,0.00010526651,0.00028564624,0.000112034984,0.00006454003,0.000009937238,0.000015658256],"genre_scores_gemma":[0.35165203,0.0000074375266,0.6480037,0.00005405606,0.00025236997,0.000002661828,0.0000132650375,0.000008308767,0.0000061630535],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886036,0.00015925265,0.00047352863,0.00007724095,0.0002739933,0.00015561613],"domain_scores_gemma":[0.9961054,0.0026879017,0.00041485266,0.000047169222,0.00055229466,0.00019241973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010563566,0.000110278175,0.00026501884,0.00010387311,0.0001265542,0.000044074277,0.000058106874,0.00005375774,0.000006074295],"category_scores_gemma":[0.00057342066,0.000086308646,0.00006872655,0.00007882809,0.00004971303,0.00035785735,0.00001515463,0.0001656317,3.5123627e-8],"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":[0.00017924584,0.0005777957,0.0010525604,0.0001453718,0.00021877936,0.0000151719405,0.0024271568,0.00033004925,0.00006684643,0.32404813,0.002890035,0.66804886],"study_design_scores_gemma":[0.00065804383,0.0005906207,0.0020879325,0.00005790168,0.00011035814,0.00011461614,0.00047661498,0.47731492,0.000034471628,0.5181554,0.0002645536,0.00013455172],"about_ca_topic_score_codex":0.0000021407377,"about_ca_topic_score_gemma":0.0000029142964,"teacher_disagreement_score":0.66791433,"about_ca_system_score_codex":0.000023761962,"about_ca_system_score_gemma":0.000034809203,"threshold_uncertainty_score":0.35195643},"labels":[],"label_agreement":null},{"id":"W2297082043","doi":"10.1080/10618600.2018.1513365","title":"Adaptive Component-Wise Multiple-Try Metropolis Sampling","year":2018,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Metropolis–Hastings algorithm; Markov chain; Ergodicity; Markov chain Monte Carlo; Component (thermodynamics); Algorithm; Computer science; Mathematics; Set (abstract data type); Additive Markov chain; Mathematical optimization; Distribution (mathematics); Variable-order Markov model; Markov model; Artificial intelligence; Machine learning; Statistics; Bayesian probability","score_opus":0.08135597292753999,"score_gpt":0.36876271864346916,"score_spread":0.28740674571592917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297082043","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":[0.13614137,0.00012273056,0.8629355,0.0001997298,0.00025149787,0.00006505547,0.00013029309,0.000009340689,0.0001445183],"genre_scores_gemma":[0.46962768,0.000022956705,0.52991545,0.00012232242,0.00028142586,5.7830255e-7,0.00000468057,0.000009587677,0.000015286132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99849814,0.00015612032,0.00059448363,0.00012538552,0.00045082986,0.0001750596],"domain_scores_gemma":[0.99507046,0.0033892994,0.00040901778,0.00006803494,0.0008515421,0.00021165652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006251179,0.00014551294,0.00035592847,0.0001774373,0.00016490214,0.000042594304,0.0001103666,0.00006976757,0.000022888986],"category_scores_gemma":[0.000975493,0.00011347636,0.000097669,0.00017081492,0.00031107297,0.00007278622,0.00004943564,0.0002657072,1.3753943e-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":[0.0005916667,0.00037623142,0.003965838,0.00010601085,0.00038912313,0.000075796896,0.00062277267,0.00032288578,0.00020012747,0.95009315,0.008747424,0.03450895],"study_design_scores_gemma":[0.0013365127,0.0007210493,0.010164622,0.00008759873,0.00012526296,0.0001952849,0.00022849366,0.045330945,0.000040388506,0.93915886,0.0023980355,0.00021292832],"about_ca_topic_score_codex":0.0000091156935,"about_ca_topic_score_gemma":0.00001251548,"teacher_disagreement_score":0.33348632,"about_ca_system_score_codex":0.000026587108,"about_ca_system_score_gemma":0.000051903186,"threshold_uncertainty_score":0.46274316},"labels":[],"label_agreement":null},{"id":"W2325530052","doi":"10.1080/10618600.2017.1385468","title":"Fast and Exact Simulation of Complex-Valued Stationary Gaussian Processes Through Embedding Circulant Matrix","year":2017,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Air Force Office of Scientific Research; Agence Nationale de la Recherche","keywords":"Circulant matrix; Gaussian; Embedding; Applied mathematics; Covariance matrix; Matrix (chemical analysis); Covariance function; Mathematics; Gaussian noise; Function (biology); Statistical physics; Covariance; Simple (philosophy); Gaussian process; Algorithm; Computer science; Mathematical optimization; Physics; Artificial intelligence; Statistics; Quantum mechanics","score_opus":0.05722692399551344,"score_gpt":0.3258920297182836,"score_spread":0.2686651057227702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2325530052","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":[0.2735066,0.00056160626,0.7251197,0.00020538838,0.00006348951,0.000053923195,0.0004126968,0.0000024805274,0.000074100426],"genre_scores_gemma":[0.9096625,0.00023536666,0.08997206,0.000030667554,0.00006085983,5.191908e-7,0.000024549503,0.0000071102513,0.0000063625153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888533,0.000015091701,0.00074963894,0.00013469424,0.00011052027,0.00010470238],"domain_scores_gemma":[0.9981886,0.0003306585,0.0010543272,0.000069350805,0.000292206,0.00006486381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031003254,0.00009717371,0.0003439141,0.000113842274,0.0002848088,0.00009526445,0.00009705231,0.00005264573,0.000018053377],"category_scores_gemma":[0.0004986072,0.00009506414,0.000041943647,0.00006833401,0.00016997397,0.0003325404,0.00003273823,0.00012598692,8.0793086e-7],"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":[0.000153216,0.00014207691,0.11648044,0.00037825044,0.00009766639,0.0000137424095,0.00093105057,0.3322322,0.000008982337,0.5433713,0.00009527613,0.006095739],"study_design_scores_gemma":[0.00031173482,0.000069670736,0.22586063,0.00002965604,0.0000085203765,0.000008724915,0.000021074158,0.389482,5.8622123e-7,0.38404185,0.00010786991,0.00005768195],"about_ca_topic_score_codex":0.000039760507,"about_ca_topic_score_gemma":0.0000058589358,"teacher_disagreement_score":0.6361559,"about_ca_system_score_codex":0.00001309323,"about_ca_system_score_gemma":0.00004610424,"threshold_uncertainty_score":0.38766032},"labels":[],"label_agreement":null},{"id":"W2416022617","doi":"10.1080/10618600.2016.1195273","title":"Locally Sparse Estimator for Functional Linear Regression Models","year":2016,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Toronto","funders":"","keywords":"Mathematics; Estimator; Linear model; Linear regression; Computer science; Statistics; Artificial intelligence","score_opus":0.10976346705495489,"score_gpt":0.36286634772272613,"score_spread":0.25310288066777126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2416022617","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":[0.007970904,0.000050353203,0.99033284,0.00097003113,0.00018854732,0.00009427008,0.00035109065,0.000009225252,0.00003270685],"genre_scores_gemma":[0.14396152,0.000031719544,0.855663,0.00011479057,0.00016696524,0.0000036823963,0.000004854691,0.000012301524,0.00004116477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985852,0.00007436312,0.00061423145,0.00013306513,0.00043689393,0.00015623072],"domain_scores_gemma":[0.9910969,0.0074306615,0.00034264033,0.000056268385,0.00087303296,0.00020050403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049671205,0.00013393877,0.00030605818,0.00009517387,0.00011510686,0.000022445285,0.00008091988,0.000073814364,0.000054177694],"category_scores_gemma":[0.002283183,0.00007393936,0.00007846395,0.00008339613,0.00018471046,0.0000997011,0.000025562727,0.00012644935,0.0000013412879],"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":[0.0002763591,0.00009904731,0.00020231387,0.00005243677,0.00004603802,0.00001101589,0.000014426329,0.00059912005,0.00005197779,0.95148,0.0059411842,0.0412261],"study_design_scores_gemma":[0.0010420553,0.0003672912,0.003294529,0.00015146186,0.000051059153,0.00007919611,0.000006037466,0.09821142,0.000016392007,0.89635193,0.00032238997,0.00010624819],"about_ca_topic_score_codex":7.044529e-7,"about_ca_topic_score_gemma":5.4396907e-7,"teacher_disagreement_score":0.13599062,"about_ca_system_score_codex":0.00001736626,"about_ca_system_score_gemma":0.000103876344,"threshold_uncertainty_score":0.30151597},"labels":[],"label_agreement":null},{"id":"W2516700508","doi":"10.1080/10618600.2015.1124041","title":"A Functional Estimate of Covariation","year":2015,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Covariance; Mathematics; Covariance function; Covariance matrix; Smoothing; Bivariate analysis; Estimation of covariance matrices; Functional data analysis; Rational quadratic covariance function; Statistics; Residual; Data set; Representation (politics); Sampling (signal processing); Applied mathematics; Algorithm; Computer science; Covariance intersection","score_opus":0.0208504176801952,"score_gpt":0.2550651859011391,"score_spread":0.2342147682209439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516700508","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":[0.11460989,0.00003280981,0.88459134,0.00024787002,0.00014391069,0.000028515153,0.000054531,0.0000024267208,0.00028869655],"genre_scores_gemma":[0.814561,0.000007073114,0.18529007,0.000076117896,0.000032384214,3.5126655e-7,0.000014771438,0.0000030675876,0.000015167186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990847,0.000028835015,0.00032220455,0.000059537255,0.00043695146,0.00006773162],"domain_scores_gemma":[0.9991841,0.0002614635,0.00025587753,0.000024173298,0.00014920325,0.00012522814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002946365,0.000054807806,0.000121849764,0.000046568028,0.00003528797,0.000013677596,0.000042306936,0.000024862777,0.00008793195],"category_scores_gemma":[0.00022966196,0.00004540086,0.000021824713,0.00012761871,0.00013197903,0.00007214732,0.000031013467,0.00007921026,0.000005455869],"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":[0.00032885253,0.00029975933,0.10695744,0.00003892675,0.000107524545,0.000051435294,0.0005055255,0.4599044,0.00016544804,0.34648475,0.042758256,0.042397678],"study_design_scores_gemma":[0.0005183368,0.00017855802,0.41269967,0.000008501074,0.000021907354,0.00007018584,0.000018456643,0.054564606,0.0000045967786,0.53111017,0.0007550726,0.000049974584],"about_ca_topic_score_codex":0.000025790077,"about_ca_topic_score_gemma":0.000004377958,"teacher_disagreement_score":0.6999511,"about_ca_system_score_codex":0.00001916132,"about_ca_system_score_gemma":0.000036174602,"threshold_uncertainty_score":0.18513933},"labels":[],"label_agreement":null},{"id":"W2804134309","doi":"10.1080/10618600.2018.1476250","title":"Optimal Designs for Multi-Response Nonlinear Regression Models With Several Factors via Semidefinite Programming","year":2018,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of General Medical Sciences","keywords":"Semidefinite programming; Optimal design; Mathematical optimization; Mathematics; Bivariate analysis; Design matrix; Linear model; Nonlinear system; Computation; Linear programming; Computer science; Algorithm; Statistics","score_opus":0.19381600922201345,"score_gpt":0.44673970487015846,"score_spread":0.252923695648145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804134309","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":[0.24217366,0.000050218176,0.75729597,0.00010606594,0.000108310844,0.00015133973,0.0001043328,0.000007186588,0.0000029220696],"genre_scores_gemma":[0.31733647,0.0000026207065,0.6824673,0.000074002746,0.00007038446,0.000002400078,0.0000072711887,0.000011987421,0.000027564169],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969905,0.00043646403,0.0008433437,0.0002658185,0.0012243316,0.00023951776],"domain_scores_gemma":[0.99153674,0.0057797804,0.0006167866,0.00009448654,0.0016844228,0.0002877924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024966062,0.00020144758,0.00040039272,0.0003117153,0.0002948001,0.00022194404,0.00025379285,0.000086957225,0.00002138564],"category_scores_gemma":[0.0013172975,0.00011791905,0.0001067212,0.0004225798,0.0004663178,0.0003634457,0.000052901538,0.00021269356,0.0000017680677],"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":[0.05962659,0.0025478306,0.014894756,0.000083209794,0.0007400046,0.00034503557,0.00806698,0.67387563,0.006850563,0.044907592,0.004035939,0.18402585],"study_design_scores_gemma":[0.0015790194,0.0033009017,0.008169041,0.00004808635,0.000037062342,0.00016065601,0.00022320735,0.9000634,0.00036543657,0.08538292,0.00047179507,0.00019845528],"about_ca_topic_score_codex":0.000003409093,"about_ca_topic_score_gemma":0.0000016877374,"teacher_disagreement_score":0.22618777,"about_ca_system_score_codex":0.000027694146,"about_ca_system_score_gemma":0.00014779103,"threshold_uncertainty_score":0.48085994},"labels":[],"label_agreement":null},{"id":"W2954648680","doi":"10.1080/10618600.2020.1840995","title":"Likelihood Evaluation of Jump-Diffusion Models Using Deterministic Nonlinear Filters","year":2020,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Nvidia","keywords":"Stochastic volatility; Jump; Mathematics; Likelihood function; Particle filter; Jump diffusion; Nonlinear system; Volatility (finance); Econometrics; Applied mathematics; Maximum likelihood; Kalman filter; Statistics; Physics","score_opus":0.10269853560347117,"score_gpt":0.28406105773310847,"score_spread":0.1813625221296373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954648680","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":[0.4457541,0.0003940556,0.55335355,0.00014814084,0.00006591835,0.000045077304,0.0002170011,0.0000016200052,0.000020535454],"genre_scores_gemma":[0.8907819,0.000080677186,0.10890493,0.00012231118,0.00008891369,3.534687e-7,0.000013388835,0.000007064123,4.6577242e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998669,0.00003175083,0.0008735971,0.00012854238,0.00019431881,0.0001027724],"domain_scores_gemma":[0.9986296,0.00016962223,0.000616393,0.000039432438,0.00042580228,0.000119128876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061350194,0.00008828247,0.0003270423,0.00012764824,0.00006590861,0.000023811837,0.00007731505,0.000056361856,0.000022784174],"category_scores_gemma":[0.000346318,0.00009008209,0.00007679537,0.00016504702,0.000065237306,0.00013408126,0.000026319352,0.00015076959,0.0000010620662],"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":[0.00025077007,0.00024631948,0.015501688,0.00017241336,0.00010963017,0.000011156162,0.0013383565,0.8112098,0.000075412274,0.14865075,0.0001565359,0.022277158],"study_design_scores_gemma":[0.00043140378,0.00012698788,0.0054525794,0.000017087124,0.000027782173,0.0000051373167,0.000014466567,0.6012698,0.0000019360702,0.3925706,0.000027662736,0.00005451789],"about_ca_topic_score_codex":0.000019532401,"about_ca_topic_score_gemma":0.0000017450885,"teacher_disagreement_score":0.44502777,"about_ca_system_score_codex":0.00002226909,"about_ca_system_score_gemma":0.00008182103,"threshold_uncertainty_score":0.36734408},"labels":[],"label_agreement":null},{"id":"W2962861789","doi":"10.1080/10618600.2019.1598872","title":"Adaptive Incremental Mixture Markov Chain Monte Carlo","year":2019,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Center for Advanced Study, University of Illinois at Urbana-Champaign; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Center for Advanced Study in the Behavioral Sciences, Stanford University; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Insight SFI Research Centre for Data Analytics; Science Foundation Ireland; National Institutes of Health; National Science Foundation","keywords":"Markov chain Monte Carlo; Computer science; Kernel (algebra); Mixture model; Gaussian process; Mathematics; Bayesian probability; Semiparametric regression; Algorithm; Mathematical optimization; Parametric statistics; Artificial intelligence; Gaussian; Statistics","score_opus":0.021498321762273426,"score_gpt":0.298824804278164,"score_spread":0.27732648251589054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962861789","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":[0.5644001,0.00036554513,0.43320918,0.00053775316,0.0004183269,0.00021953105,0.00023754477,0.000011880425,0.0006001731],"genre_scores_gemma":[0.638027,0.00003944606,0.3614358,0.00020162303,0.00011496165,0.0000010320091,0.0000043198247,0.000012326365,0.00016350903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984925,0.00017281757,0.00052624237,0.00013112443,0.0005165594,0.0001607992],"domain_scores_gemma":[0.9978099,0.0011776604,0.00037325555,0.00006997736,0.000402397,0.00016679824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069144246,0.0001541313,0.00037073952,0.00013510545,0.00006541178,0.00003563233,0.000107809865,0.000082933475,0.000041869236],"category_scores_gemma":[0.000230191,0.00011852021,0.0001064463,0.00013490987,0.00008399425,0.00007883243,0.000048276,0.00033464568,1.5780402e-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":[0.0010571507,0.00049849227,0.010876748,0.0003381289,0.00069055555,0.00026770006,0.0010673075,0.0018099754,0.00025802734,0.911483,0.02855194,0.043100975],"study_design_scores_gemma":[0.0032444438,0.0015094483,0.01639331,0.00021003204,0.0001954076,0.00050245004,0.00059628533,0.080687396,0.00002713064,0.89272237,0.0034360196,0.0004756929],"about_ca_topic_score_codex":0.000006963016,"about_ca_topic_score_gemma":0.0000080503805,"teacher_disagreement_score":0.07887742,"about_ca_system_score_codex":0.000029054096,"about_ca_system_score_gemma":0.00005737293,"threshold_uncertainty_score":0.4833114},"labels":[],"label_agreement":null},{"id":"W3121888169","doi":"10.1080/10618600.2021.1873144","title":"False Discovery Rates to Detect Signals from Incomplete Spatially Aggregated Data","year":2021,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Geochemistry and Geologic Mapping","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 Toronto","funders":"Australian Research Council; Ministry of Science and Technology, Taiwan; Division of Social and Economic Sciences; National Sleep Foundation; National Aeronautics and Space Administration","keywords":"False discovery rate; Nonparametric statistics; Null hypothesis; Statistical hypothesis testing; Inference; SIGNAL (programming language); Null (SQL); Statistical inference; Computer science; Algorithm; Multiple comparisons problem; Pixel; Statistics; Pattern recognition (psychology); Type I and type II errors; Data mining; Mathematics; Artificial intelligence","score_opus":0.028691427621305197,"score_gpt":0.2726817872880555,"score_spread":0.24399035966675028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121888169","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":[0.04415839,0.00032367805,0.95066863,0.004244935,0.0001525785,0.000034626042,0.0003776029,0.00000946976,0.000030081945],"genre_scores_gemma":[0.6167407,0.000039615374,0.38223174,0.0007258398,0.00010635107,4.7149825e-7,0.00012371318,0.0000021337885,0.00002944435],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854237,0.00011869509,0.000494968,0.0002696488,0.00041913052,0.00015520785],"domain_scores_gemma":[0.99740463,0.0012673966,0.00026571442,0.0002189748,0.00065278495,0.0001904941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003042403,0.00012287905,0.00026307217,0.00006681012,0.00011416081,0.00028890648,0.0005770335,0.000048710088,0.000027665214],"category_scores_gemma":[0.00083480496,0.00010241005,0.000039927105,0.00034210278,0.00006338724,0.0003332136,0.0004657241,0.0002044968,0.00000306186],"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":[0.0005414703,0.0008461933,0.020374157,0.0002859778,0.0015870971,0.007392416,0.0012240838,0.29551584,0.022372643,0.28649628,0.04466203,0.31870183],"study_design_scores_gemma":[0.00047552754,0.0001419542,0.04878321,0.00008126185,0.000027254215,0.00017999078,0.000014182912,0.10810276,0.00061058433,0.836,0.00539613,0.00018710371],"about_ca_topic_score_codex":0.000019163335,"about_ca_topic_score_gemma":0.000019613075,"teacher_disagreement_score":0.5725823,"about_ca_system_score_codex":0.000008293552,"about_ca_system_score_gemma":0.00018079372,"threshold_uncertainty_score":0.41761604},"labels":[],"label_agreement":null},{"id":"W3131114373","doi":"10.1080/10618600.2022.2110883","title":"Cross-Validated Loss-based Covariance Matrix Estimator Selection in High Dimensions","year":2022,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Deafness and Other Communication Disorders; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Estimator; Curse of dimensionality; Covariance matrix; Dimensionality reduction; Estimation of covariance matrices; Mathematics; Sample size determination; Covariance; Model selection; Selection (genetic algorithm); Computer science; Mathematical optimization; Statistics; Artificial intelligence","score_opus":0.007898124488251633,"score_gpt":0.2743379380396968,"score_spread":0.2664398135514452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131114373","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":[0.7207197,0.00011419237,0.27864337,0.00018084352,0.00012115619,0.00004177459,0.00017473007,0.000002404313,0.0000018311715],"genre_scores_gemma":[0.94922,0.00001962547,0.050338034,0.00020441791,0.00005537969,0.0000024973156,0.00013320881,0.000008862068,0.000017961082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9991138,0.00006713767,0.00034389546,0.00012279405,0.00024170133,0.00011068218],"domain_scores_gemma":[0.9994498,0.000094012335,0.0001565275,0.00003101656,0.00019504903,0.00007357928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021557612,0.00008600136,0.0001404977,0.000094112074,0.00017512178,0.000030738196,0.000076215256,0.000047220106,0.00003772123],"category_scores_gemma":[0.00006576311,0.00008291747,0.000042554017,0.0001872526,0.000089364046,0.00000503324,0.000024585268,0.00021404712,3.052928e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009801124,0.0004424708,0.09248175,0.000030856,0.000064404296,0.00007911171,0.000019163896,0.86805785,0.02335933,0.013098076,0.0007168619,0.0006699915],"study_design_scores_gemma":[0.008959905,0.0034843038,0.61019665,0.00004591594,0.000102474296,0.00076777977,0.000026740145,0.26383108,0.0033592123,0.102375,0.006214586,0.00063633296],"about_ca_topic_score_codex":0.000021026432,"about_ca_topic_score_gemma":0.00000860544,"teacher_disagreement_score":0.60422677,"about_ca_system_score_codex":0.000018206401,"about_ca_system_score_gemma":0.00013629739,"threshold_uncertainty_score":0.3381276},"labels":[],"label_agreement":null},{"id":"W3213258851","doi":"10.1080/10618600.2021.1999825","title":"Mixtures of Matrix-Variate Contaminated Normal Distributions","year":2021,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Random variate; Cluster analysis; Computer science; Expectation–maximization algorithm; Data mining; Matrix (chemical analysis); Data Matrix; Algorithm; Artificial intelligence; Statistics; Mathematics; Maximum likelihood; Random variable","score_opus":0.00868830389333632,"score_gpt":0.275012658105719,"score_spread":0.2663243542123827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213258851","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":[0.007304056,0.0005105906,0.9908609,0.0009130321,0.00017238091,0.000024314926,0.00015970923,0.0000051835123,0.000049876267],"genre_scores_gemma":[0.38332552,0.0000522267,0.6164835,0.000077612356,0.000029897968,2.4140294e-7,0.000013357482,0.0000021012415,0.000015575955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988381,0.00014859647,0.00047757354,0.000106638974,0.00031420484,0.00011484508],"domain_scores_gemma":[0.9980315,0.0005899434,0.00028888302,0.00007297185,0.00089045486,0.00012627196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031070894,0.00008497441,0.00024413371,0.0000822509,0.00007722945,0.00005839425,0.00016374867,0.000053709588,0.000012114505],"category_scores_gemma":[0.0001656473,0.000069110385,0.000073978685,0.00031237167,0.000092577284,0.00013503556,0.00006611187,0.00019058303,3.347132e-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":[0.000015349711,0.000096430136,0.000309057,0.000023446566,0.000060154154,0.00011746569,0.000069594375,0.0003444777,0.000279963,0.97887695,0.0006885961,0.019118508],"study_design_scores_gemma":[0.00056330924,0.00014939475,0.039161447,0.00003076989,0.000038066013,0.0004760034,0.000004290132,0.038089283,0.00042270377,0.9205288,0.00044333976,0.00009256488],"about_ca_topic_score_codex":0.0000031402876,"about_ca_topic_score_gemma":0.0000013138583,"teacher_disagreement_score":0.37602144,"about_ca_system_score_codex":0.000007826875,"about_ca_system_score_gemma":0.00015810199,"threshold_uncertainty_score":0.28182396},"labels":[],"label_agreement":null},{"id":"W4234894698","doi":"10.1198/106186002321018849","title":"Detecting Clusters and Nonlinearity in Three-Dimensional Dynamic Graphs","year":2002,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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":"York University","funders":"","keywords":"Computer science; Nonlinear system; Theoretical computer science; Algorithm; Physics","score_opus":0.010451391268419685,"score_gpt":0.2540165866985389,"score_spread":0.2435651954301192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234894698","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":[0.7034807,0.00018774669,0.29594028,0.00025960352,0.000027726415,0.00004115404,0.000032144264,0.000004561213,0.000026035073],"genre_scores_gemma":[0.92041296,0.000011075561,0.07947339,0.00004730788,0.000038581726,6.6461587e-7,0.000008011276,0.0000051235447,0.0000028902107],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991223,0.000043416072,0.00039659982,0.000103958795,0.00021864536,0.00011502985],"domain_scores_gemma":[0.9990946,0.00045559788,0.00019662986,0.0000334246,0.00013349643,0.000086254615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018986099,0.00009654896,0.00021506949,0.00018144277,0.000085816675,0.00003754277,0.000052882722,0.000025833177,0.000053972664],"category_scores_gemma":[0.000014739582,0.00008419348,0.000054866792,0.00021456461,0.00010445687,0.00006782459,0.000037199283,0.00027701375,3.494462e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109335786,0.0006243716,0.5217487,0.00004536051,0.00038110468,0.00007706467,0.00022635714,0.041836012,0.00004396408,0.1306576,0.00091612124,0.303334],"study_design_scores_gemma":[0.00029321623,0.00005791899,0.09520152,0.000019662073,0.000021101427,0.000017827851,0.0000077621335,0.49234104,6.015458e-7,0.41194898,0.00002739998,0.00006297014],"about_ca_topic_score_codex":0.000033898184,"about_ca_topic_score_gemma":0.000060660746,"teacher_disagreement_score":0.45050502,"about_ca_system_score_codex":0.000008888466,"about_ca_system_score_gemma":0.000010531428,"threshold_uncertainty_score":0.34333107},"labels":[],"label_agreement":null},{"id":"W4237076065","doi":"10.1198/jcgs.2011.09166b","title":"Comment","year":2011,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Data Visualization and Analytics","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":"Carleton University","funders":"","keywords":"Perspective (graphical); Relation (database); Computer science; Cognition; Table (database); Psychology; Cognitive psychology; Artificial intelligence; Data mining","score_opus":0.03274139259601863,"score_gpt":0.28920280013943866,"score_spread":0.25646140754342006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237076065","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":[0.0006975202,0.000042255368,0.9977356,0.0012082438,0.00010429227,0.000015573538,0.000019345549,0.0000068301065,0.0001702912],"genre_scores_gemma":[0.33025908,0.000060651826,0.6672439,0.0023841453,0.000031248703,1.9324831e-7,0.0000070428337,0.000002887284,0.0000108363065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992651,0.000037648802,0.00029844025,0.000064631255,0.00026191326,0.00007231226],"domain_scores_gemma":[0.9992471,0.00014595622,0.00017340206,0.00005183215,0.00026370687,0.00011805785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000195171,0.000055517514,0.00010832691,0.00010127311,0.000055196357,0.00005319506,0.00020609608,0.00001944257,0.000022887967],"category_scores_gemma":[0.000046600806,0.00004334652,0.0000277097,0.00016612362,0.000058961265,0.00016875134,0.000054904907,0.000086157415,0.0000027560634],"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":[0.0000050802264,0.00008338589,0.00095379935,0.0000052505857,0.000021359869,0.000023996396,0.00015625052,0.00006873106,7.2878083e-7,0.9840953,0.0068678143,0.0077183256],"study_design_scores_gemma":[0.000360032,0.00022822295,0.027491784,0.000012235238,0.000013598465,0.00010152141,0.000015288659,0.090066135,0.00000821402,0.8722765,0.009343857,0.00008261421],"about_ca_topic_score_codex":0.0000017295363,"about_ca_topic_score_gemma":4.4131312e-7,"teacher_disagreement_score":0.33049172,"about_ca_system_score_codex":0.0000049743303,"about_ca_system_score_gemma":0.000034190187,"threshold_uncertainty_score":0.17676198},"labels":[],"label_agreement":null},{"id":"W4237780050","doi":"10.2307/1390653","title":"Markov Chain Sampling Methods for Dirichlet Process Mixture Models","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":508,"is_retracted":false,"has_abstract":false,"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":"Dirichlet process; Markov chain; Mathematics; Dirichlet distribution; Sampling (signal processing); Slice sampling; Markov chain Monte Carlo; Hierarchical Dirichlet process; Computer science; Markov renewal process; Applied mathematics; Statistics; Econometrics; Statistical physics; Markov model; Variable-order Markov model; Bayesian probability; Mathematical analysis","score_opus":0.026056546071332128,"score_gpt":0.3550975326748263,"score_spread":0.3290409866034942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237780050","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":[0.00075478584,0.0005908089,0.9968912,0.001351629,0.00013055153,0.00011966213,0.000049318598,0.0000137733905,0.000098276156],"genre_scores_gemma":[0.017723335,0.00011490999,0.9812755,0.0006920618,0.00013100162,0.0000044980934,0.0000068138506,0.000009536401,0.0000423416],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861145,0.00017554774,0.00050958944,0.00020398265,0.00029553342,0.00020387913],"domain_scores_gemma":[0.9975937,0.0014225312,0.00022253502,0.000085766005,0.00047874294,0.00019670697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010545322,0.00014907985,0.00031741703,0.0001293733,0.00015778778,0.00012993516,0.00031630762,0.00008485125,0.000012552368],"category_scores_gemma":[0.00010241538,0.00011488226,0.000096546326,0.00027524686,0.00007231227,0.0002832073,0.00002537238,0.00024619457,2.5069468e-7],"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":[0.00004749068,0.000050016657,0.000008689816,0.000038013568,0.000036414007,0.000005503342,0.00019992213,0.010335753,0.000009194619,0.38175908,0.0004257402,0.60708416],"study_design_scores_gemma":[0.00029778449,0.000112482005,0.00028479283,0.000018467159,0.000016064141,0.00009059925,0.0000020837076,0.42082125,0.000005446339,0.5772555,0.0010092694,0.00008626935],"about_ca_topic_score_codex":9.2706875e-7,"about_ca_topic_score_gemma":3.06515e-7,"teacher_disagreement_score":0.6069979,"about_ca_system_score_codex":0.000010358478,"about_ca_system_score_gemma":0.00009096467,"threshold_uncertainty_score":0.46847627},"labels":[],"label_agreement":null},{"id":"W4250766106","doi":"10.1198/jcgs.2011.09224","title":"Functional Boxplots","year":2011,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":417,"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":"King Abdullah University of Science and Technology; University of Windsor; National Science Foundation","keywords":"Functional data analysis; Outlier; Computer science; Generalization; Exploratory data analysis; Anomaly detection; Envelope (radar); Artificial intelligence; Statistics; Data mining; Mathematics; Machine learning","score_opus":0.15056388113600172,"score_gpt":0.37483896033699754,"score_spread":0.22427507920099582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250766106","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":[0.009713349,0.00006508465,0.9895315,0.00010083567,0.00015919835,0.00004166462,0.000073457675,0.000008812672,0.00030606677],"genre_scores_gemma":[0.19952372,0.000025202165,0.8002076,0.00012002295,0.000076099495,9.3925905e-7,0.0000031554105,0.00000921431,0.000034059147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988468,0.00007415766,0.0004974521,0.000097583725,0.00035718805,0.00012680696],"domain_scores_gemma":[0.99744123,0.0016420615,0.00026130528,0.00004370527,0.00043448427,0.00017722163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034091464,0.00010392602,0.00024083887,0.00009389988,0.000081074955,0.000013660667,0.00006262342,0.00004678668,0.0001389129],"category_scores_gemma":[0.0006602133,0.000078664045,0.000055331904,0.000098501514,0.0001543946,0.00009328518,0.000022971773,0.00021121255,0.000001838851],"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":[0.00010920217,0.00013263342,0.00027945184,0.000025128093,0.000051270064,0.000043905166,0.00010936498,0.00009071273,0.000008122581,0.9810767,0.0023839895,0.015689492],"study_design_scores_gemma":[0.00044468103,0.00025344163,0.024164727,0.000018824148,0.000051808685,0.00017517328,0.000022658287,0.0023762197,0.000009887646,0.97209334,0.00029652615,0.00009272834],"about_ca_topic_score_codex":0.0000013763764,"about_ca_topic_score_gemma":9.236361e-7,"teacher_disagreement_score":0.18981037,"about_ca_system_score_codex":0.0000092588725,"about_ca_system_score_gemma":0.00004202575,"threshold_uncertainty_score":0.32078266},"labels":[],"label_agreement":null},{"id":"W4283370965","doi":"10.1080/10618600.2022.2069780","title":"Analytic Permutation Testing for Functional Data ANOVA","year":2022,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sheridan College; Lakehead University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Pacific Institute for the Mathematical Sciences","keywords":"Permutation (music); Resampling; Univariate; Nonparametric statistics; Statistical hypothesis testing; Mathematics; Omnibus test; Multiple comparisons problem; Sample size determination; Algorithm; Parametric statistics; Computer science; Multivariate statistics; Statistics","score_opus":0.07933935138083462,"score_gpt":0.3144627546212596,"score_spread":0.235123403240425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283370965","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":[0.0049064187,0.00006642214,0.99301606,0.0015170749,0.00014331526,0.00008643379,0.00021266914,0.000022482673,0.000029108653],"genre_scores_gemma":[0.44560575,0.0000022579366,0.55363035,0.0005766546,0.000054085027,0.000003846793,0.00011024,0.000004302761,0.000012490286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986665,0.00010222447,0.00042331236,0.00017121177,0.000539361,0.00009735694],"domain_scores_gemma":[0.9974571,0.0014370861,0.00035440485,0.0001173788,0.00056237937,0.00007165818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094616885,0.000076030396,0.00014232601,0.00021723931,0.00030714882,0.00011574898,0.00039319685,0.000019450215,0.0000103459315],"category_scores_gemma":[0.00036918465,0.00007174582,0.000032476226,0.0004214243,0.0000471975,0.00035615504,0.00021830111,0.00021376634,2.5727678e-7],"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":[0.000056519588,0.00016160362,0.0017140141,0.000022042908,0.00006941507,0.000018237648,0.0001722067,0.0754923,0.000053019503,0.87676984,0.011182131,0.03428869],"study_design_scores_gemma":[0.00032330718,0.0003555995,0.019715374,0.000003592681,0.000015706144,0.0002097465,0.000016887003,0.55922115,0.0000020328027,0.4179466,0.0021221482,0.00006786256],"about_ca_topic_score_codex":0.0000023111936,"about_ca_topic_score_gemma":9.40562e-7,"teacher_disagreement_score":0.48372883,"about_ca_system_score_codex":0.00002432042,"about_ca_system_score_gemma":0.00020982006,"threshold_uncertainty_score":0.29257095},"labels":[],"label_agreement":null},{"id":"W4286608159","doi":"10.1080/10618600.2022.2104858","title":"Using CVX to Construct Optimal Designs for Biomedical Studies with Multiple Objectives","year":2022,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Optimal design; Computer science; Construct (python library); MATLAB; Mathematical optimization; Code (set theory); Software; Machine learning; Mathematics; Programming language","score_opus":0.2339448673563404,"score_gpt":0.4839443142539315,"score_spread":0.24999944689759107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286608159","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":[0.15124644,0.00021965186,0.84753734,0.00032306512,0.00020707116,0.00016344026,0.0002949728,0.0000035398318,0.0000044657063],"genre_scores_gemma":[0.40280288,0.0000022719787,0.59698087,0.00015312564,0.000041528383,0.000005137897,0.0000023570929,0.0000056648237,0.0000061274],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99705416,0.00038159863,0.00069695595,0.00021912405,0.0014787166,0.00016945915],"domain_scores_gemma":[0.98910874,0.009327639,0.00038284063,0.000058235066,0.0008965426,0.00022602975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020562445,0.00012447803,0.0003991605,0.00038901035,0.00043801335,0.00009186889,0.0002238464,0.000023334771,0.000039611827],"category_scores_gemma":[0.00255231,0.00008388057,0.00007225209,0.0006237481,0.00043047007,0.000115179195,0.00012945847,0.00018976505,4.2385986e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058604334,0.0007425734,0.013390822,0.000037847643,0.000804018,0.00028198204,0.004218376,0.79105514,0.0038462097,0.10909461,0.007655417,0.06301258],"study_design_scores_gemma":[0.0032336607,0.0075837686,0.012814011,0.00003477433,0.00010799266,0.0014775596,0.008808469,0.35834357,0.00015948385,0.60403097,0.0030375647,0.00036814407],"about_ca_topic_score_codex":0.0000024104697,"about_ca_topic_score_gemma":6.379551e-7,"teacher_disagreement_score":0.49493638,"about_ca_system_score_codex":0.000057423087,"about_ca_system_score_gemma":0.0001873653,"threshold_uncertainty_score":0.34205505},"labels":[],"label_agreement":null},{"id":"W4297019279","doi":"10.1080/10618600.2022.2127738","title":"Beyond Linear Dynamic Functional Connectivity: A Vine Copula Change Point Model","year":2022,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Vine copula; Inference; Copula (linguistics); Dynamic functional connectivity; Sliding window protocol; Artificial intelligence; Functional magnetic resonance imaging; Machine learning; Algorithm; Econometrics; Mathematics; Window (computing); Psychology","score_opus":0.04210046127206046,"score_gpt":0.27649775414176136,"score_spread":0.2343972928697009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297019279","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":[0.37201723,0.0002685451,0.60481226,0.020069368,0.0009266438,0.00024855678,0.0015121421,0.000033481374,0.00011176237],"genre_scores_gemma":[0.9822314,0.000040136685,0.011340652,0.0061081727,0.00015485805,0.000019647488,0.000025182175,0.00001675746,0.000063188534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99790776,0.00020410544,0.0004299211,0.00026924428,0.0009974833,0.00019148878],"domain_scores_gemma":[0.9940303,0.005162319,0.00033072484,0.000064156295,0.00027738168,0.0001351328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045821685,0.0001623339,0.00029544372,0.0002703012,0.0006477706,0.00003374858,0.00011909654,0.000032664513,0.0000992196],"category_scores_gemma":[0.0017594662,0.00015015317,0.00009817108,0.00037574922,0.00022548616,0.0001997019,0.00018383196,0.00053076196,0.0000023430493],"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":[0.0012143916,0.0010155212,0.0024251775,0.00006469887,0.00015016473,0.00030817674,0.00046941868,0.4740029,0.0016698434,0.49667174,0.015585222,0.0064227483],"study_design_scores_gemma":[0.0008348672,0.0005802879,0.017617818,0.0000061997544,0.00003138677,0.0006882505,0.00004140051,0.47911766,0.000015285337,0.50001085,0.0009099251,0.00014605398],"about_ca_topic_score_codex":0.0000040172267,"about_ca_topic_score_gemma":0.0000067797046,"teacher_disagreement_score":0.6102142,"about_ca_system_score_codex":0.00009149541,"about_ca_system_score_gemma":0.00011536157,"threshold_uncertainty_score":0.61230683},"labels":[],"label_agreement":null},{"id":"W4311305973","doi":"10.1080/10618600.2022.2157835","title":"Dependence Model Assessment and Selection with DecoupleNets","year":2022,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Anomaly Detection Techniques and Applications","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":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Model selection; Computer science; Econometrics; Mathematics; Statistics; Artificial intelligence","score_opus":0.009588893686394585,"score_gpt":0.2711973733594322,"score_spread":0.26160847967303763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311305973","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":[0.036101155,0.000038345093,0.96318585,0.0005663487,0.000012829529,0.000046441663,0.000015531064,0.000013535797,0.00001998072],"genre_scores_gemma":[0.5551342,0.000020259207,0.44471648,0.00010851287,0.0000072518087,0.0000046850364,9.968583e-7,0.0000017762728,0.000005852428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927205,0.000030252158,0.00019170949,0.00010572777,0.00033258414,0.00006770471],"domain_scores_gemma":[0.9994265,0.00012569212,0.00016979752,0.000030039335,0.00017375794,0.00007420113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018483617,0.000056507444,0.00008883843,0.00009636638,0.0003023604,0.000059662212,0.000111802714,0.000013463573,0.0000060575135],"category_scores_gemma":[0.000004142633,0.00004673986,0.0000146040975,0.00021186861,0.000043503514,0.00012243596,0.000071167146,0.00019970212,5.7410116e-8],"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":[0.000018829103,0.00008607285,0.0019571993,0.0000065517816,0.000024025938,0.000010094873,0.000051081537,0.24196297,0.000060894152,0.73001796,0.00050165824,0.025302662],"study_design_scores_gemma":[0.00014074465,0.00032796114,0.020569416,0.0000019618938,0.0000061859655,0.00042394176,0.000007007458,0.64451367,0.00000526868,0.33380008,0.0001568178,0.00004697105],"about_ca_topic_score_codex":0.0000031305535,"about_ca_topic_score_gemma":0.000002235195,"teacher_disagreement_score":0.519033,"about_ca_system_score_codex":0.000024644778,"about_ca_system_score_gemma":0.00010601556,"threshold_uncertainty_score":0.23255423},"labels":[],"label_agreement":null},{"id":"W4312132359","doi":"10.1080/10618600.2022.2156522","title":"Probabilistic <i>K</i> -means with Local Alignment for Clustering and Motif Discovery in Functional Data","year":2022,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Stroke Foundation","keywords":"Cluster analysis; Motif (music); Probabilistic logic; Computer science; Artificial intelligence; Computational biology; Data mining; Biology; Physics","score_opus":0.012692114045678056,"score_gpt":0.22682571545923966,"score_spread":0.2141336014135616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312132359","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":[0.07091541,0.00021672262,0.9279339,0.0002497223,0.000065106266,0.00009700861,0.0005149542,6.268695e-7,0.000006587791],"genre_scores_gemma":[0.9638294,0.00004226078,0.03536487,0.00026908904,0.00007605035,0.0000054323723,0.0003920626,0.0000063736725,0.000014489795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934626,0.000023930692,0.00026144306,0.000112135094,0.0001657414,0.000090495436],"domain_scores_gemma":[0.9996134,0.00009506016,0.00012350077,0.000058168964,0.000058023317,0.000051820658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026679094,0.00006952637,0.00010906095,0.000037104695,0.00009318856,0.00002989038,0.00007965149,0.0000226307,0.0000024746587],"category_scores_gemma":[0.000017530183,0.000056186513,0.000014963927,0.000045196048,0.00009625552,0.000009899079,0.00014824227,0.00010519074,2.0497394e-8],"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":[0.0014053234,0.0001863316,0.0034763806,0.000122525,0.00015993012,0.000017409335,0.00008317551,0.9501332,0.000103052276,0.021040719,0.004423768,0.018848201],"study_design_scores_gemma":[0.0032551961,0.002132542,0.030025776,0.000031708725,0.00007103279,0.0006275616,0.0002525512,0.8462753,0.000004938486,0.10803993,0.009030926,0.0002525042],"about_ca_topic_score_codex":0.000002388283,"about_ca_topic_score_gemma":0.000026584032,"teacher_disagreement_score":0.89291394,"about_ca_system_score_codex":0.000010949691,"about_ca_system_score_gemma":0.00007041859,"threshold_uncertainty_score":0.22912195},"labels":[],"label_agreement":null},{"id":"W4385963506","doi":"10.1080/10618600.2023.2233581","title":"Functional Nonlinear Learning","year":2023,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Functional principal component analysis; Functional data analysis; Principal component analysis; Computer science; Multivariate statistics; Generalization; Nonlinear system; Artificial intelligence; Representation (politics); Pattern recognition (psychology); Data mining; Machine learning; Mathematics","score_opus":0.01122446183980309,"score_gpt":0.25314412752160215,"score_spread":0.24191966568179907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385963506","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":[0.8051842,0.0005347203,0.1930962,0.0007280292,0.00025737064,0.000032564236,0.000060207054,0.000006482975,0.00010020374],"genre_scores_gemma":[0.9646617,0.0011423064,0.033149738,0.00016313826,0.0004283217,8.990888e-7,0.00014812779,0.000009190337,0.0002965649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9994127,0.000028424934,0.00020617156,0.000079095975,0.00018319886,0.00009041879],"domain_scores_gemma":[0.9994922,0.00009129127,0.00011108157,0.000023002236,0.00021981608,0.0000626005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020425662,0.00006217304,0.000112435744,0.00009743939,0.00009408715,0.000016603006,0.00003717469,0.000035710087,0.000013244731],"category_scores_gemma":[0.00019659697,0.000050838884,0.000044991823,0.00015184082,0.00006683906,0.0000024547137,0.000039177274,0.000115641975,0.000003405762],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014827674,0.0005791701,0.13300177,0.00020496389,0.0023774544,0.00026141896,0.00025091466,0.16386738,0.058210935,0.31613395,0.24591008,0.07771918],"study_design_scores_gemma":[0.0018507594,0.0014964395,0.6660939,0.000017394339,0.000087047745,0.0002758816,0.00013830047,0.016372425,0.0004706318,0.17702803,0.13584995,0.0003192569],"about_ca_topic_score_codex":5.977433e-7,"about_ca_topic_score_gemma":8.835448e-7,"teacher_disagreement_score":0.5330921,"about_ca_system_score_codex":0.0000022204551,"about_ca_system_score_gemma":0.000032633958,"threshold_uncertainty_score":0.20731495},"labels":[],"label_agreement":null},{"id":"W4386022565","doi":"10.1080/10618600.2023.2250411","title":"Supervised Principal Component Regression for Functional Responses with High Dimensional Predictors","year":2023,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Principal component analysis; Subspace topology; Functional principal component analysis; Covariance; Computer science; Principal component regression; Covariate; Residual; Regression; Estimator; Covariance matrix; Artificial intelligence; Mathematics; Statistics; Machine learning; Algorithm","score_opus":0.0766674021052579,"score_gpt":0.3379953317703796,"score_spread":0.2613279296651217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386022565","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":[0.4784727,0.000015790009,0.5202554,0.0005171512,0.00015862114,0.00010698145,0.00045144284,0.000016784074,0.0000051528327],"genre_scores_gemma":[0.44387785,0.000011824812,0.5557534,0.00008742007,0.00013008702,0.0000075297535,0.00006728988,0.000014659256,0.000049957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818516,0.00014860093,0.0005745159,0.00016115994,0.00073705043,0.00019349852],"domain_scores_gemma":[0.98933715,0.009372258,0.0002867912,0.000060493545,0.00073919777,0.00020413064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068645156,0.00015807875,0.00034331734,0.00020214063,0.00019546095,0.000037805337,0.000079223064,0.00006625845,0.000048171103],"category_scores_gemma":[0.0013513125,0.00009989261,0.00006312701,0.00024482823,0.00021500717,0.000056760902,0.000038387498,0.00021029978,0.0000013362585],"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":[0.0027450956,0.000239058,0.006066385,0.00016132234,0.0001964523,0.00008314559,0.00010445784,0.0023948685,0.00013350611,0.9715459,0.009658553,0.006671289],"study_design_scores_gemma":[0.0013781154,0.0008340847,0.24693814,0.000111496614,0.000074464304,0.000094482086,0.000018838284,0.03604777,0.000016343585,0.7141011,0.0002648217,0.00012038745],"about_ca_topic_score_codex":0.0000021044696,"about_ca_topic_score_gemma":0.0000013180556,"teacher_disagreement_score":0.2574448,"about_ca_system_score_codex":0.000018604318,"about_ca_system_score_gemma":0.00013228874,"threshold_uncertainty_score":0.40735024},"labels":[],"label_agreement":null},{"id":"W4386608500","doi":"10.1080/10618600.2023.2257258","title":"Clustering Sequence Data with Mixture Markov Chains with Covariates Using Multiple Simplex Constrained Optimization Routine (MSiCOR)","year":2023,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","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 Toronto","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Expectation–maximization algorithm; Cluster analysis; Computer science; Covariate; Context (archaeology); Maximization; Simplex; Markov chain; Mixture model; Mathematical optimization; Data mining; Artificial intelligence; Machine learning; Mathematics; Statistics; Maximum likelihood","score_opus":0.04511387327722369,"score_gpt":0.30332949743915777,"score_spread":0.2582156241619341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386608500","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":[0.003847301,0.000034114844,0.9948973,0.0007881108,0.00007367859,0.000094849274,0.00022887929,0.000029216639,0.000006534907],"genre_scores_gemma":[0.23299472,0.000027121885,0.7666654,0.00016292269,0.0000554694,5.1788766e-7,0.00008097281,0.000008779545,0.0000041211456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861544,0.00011879356,0.00037381222,0.00024988822,0.00044096584,0.00020109612],"domain_scores_gemma":[0.9981696,0.0007674664,0.00033395685,0.00016771677,0.00040491787,0.00015636413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005502633,0.00015514692,0.0002614376,0.00017257556,0.00017884717,0.00017680677,0.00036549213,0.00005344625,0.0000036966273],"category_scores_gemma":[0.00011774941,0.000106541214,0.000020707152,0.00063293555,0.00015720756,0.0003830329,0.00015504578,0.00021961662,1.4315667e-7],"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":[0.00016631531,0.00005676716,0.0019957367,0.000063784304,0.00014111376,0.0003313609,0.0002416607,0.89602363,0.0000539092,0.06648555,0.00019713573,0.034243047],"study_design_scores_gemma":[0.00092129497,0.00022156184,0.0032626863,0.00008025047,0.000037012214,0.0006411871,0.000012691631,0.9712538,0.0000024167612,0.023379438,0.00003563079,0.00015202138],"about_ca_topic_score_codex":0.000010147304,"about_ca_topic_score_gemma":0.000009802628,"teacher_disagreement_score":0.22914742,"about_ca_system_score_codex":0.000015058216,"about_ca_system_score_gemma":0.00018707817,"threshold_uncertainty_score":0.43446246},"labels":[],"label_agreement":null},{"id":"W4389126399","doi":"10.1080/10618600.2023.2289532","title":"Model-Based Smoothing with Integrated Wiener Processes and Overlapping Splines","year":2023,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research; St. Michael's Hospital; University of Waterloo; University of Toronto","funders":"","keywords":"Smoothing; Computer science; Smoothing spline; Econometrics; Mathematics; Mathematical optimization; Algorithm; Statistics","score_opus":0.05858149059133981,"score_gpt":0.31366986845052763,"score_spread":0.2550883778591878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389126399","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":[0.09389721,0.0001150106,0.90530485,0.00053486926,0.00004764629,0.00003622214,0.000041357493,0.000014520773,0.000008289324],"genre_scores_gemma":[0.80100906,0.00002378562,0.19878855,0.00010550466,0.000032343403,8.5558924e-7,0.0000062788586,0.0000061591363,0.000027482705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853367,0.00003683752,0.00044549335,0.00014007025,0.00072912994,0.00011477945],"domain_scores_gemma":[0.9959745,0.0026694702,0.00020972818,0.000044411136,0.0009796374,0.0001222634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007950642,0.00010007695,0.00022231929,0.00029826225,0.000116125964,0.00014874808,0.00011274582,0.000039106035,0.0000044596645],"category_scores_gemma":[0.0018530535,0.000057508296,0.000020784111,0.0008272425,0.0001701435,0.00013250191,0.000021417763,0.00015911614,9.1477045e-7],"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":[0.00007666212,0.000023992274,0.002325285,0.00004421479,0.000022617302,0.000038716986,0.000106243664,0.9631642,0.000020881089,0.028804766,0.0007615492,0.0046108486],"study_design_scores_gemma":[0.00026685154,0.000097837634,0.010671993,0.000056598994,0.000013875364,0.000032276057,0.00003856921,0.6674014,9.32189e-7,0.32123134,0.00012549284,0.00006287359],"about_ca_topic_score_codex":0.0000017111976,"about_ca_topic_score_gemma":0.0000031836305,"teacher_disagreement_score":0.70711184,"about_ca_system_score_codex":0.000007181172,"about_ca_system_score_gemma":0.00021236151,"threshold_uncertainty_score":0.23451202},"labels":[],"label_agreement":null},{"id":"W4389312611","doi":"10.1080/10618600.2023.2285337","title":"Smooth Multi-Period Forecasting With Application to Prediction of COVID-19 Cases","year":2023,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Coronavirus disease 2019 (COVID-19); Period (music); Econometrics; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Statistics; Mathematics; Virology; Medicine; Infectious disease (medical specialty)","score_opus":0.14253342998563678,"score_gpt":0.3946894444252252,"score_spread":0.2521560144395884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389312611","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":[0.11581994,0.0000145608055,0.88198644,0.0015383647,0.000025313284,0.0001399251,0.00044037178,0.00002195276,0.0000131124],"genre_scores_gemma":[0.7586394,0.0000074934874,0.2411447,0.00011904777,0.0000362799,0.000008243268,0.000023871626,0.0000056185704,0.00001536439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815917,0.00005374861,0.000709337,0.00016440403,0.00080507074,0.00010828647],"domain_scores_gemma":[0.99627423,0.0020471856,0.0005166648,0.00009278223,0.00082889525,0.00024026494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001084332,0.00008408357,0.0002101733,0.00040003916,0.00017533354,0.000060745184,0.00017905145,0.00003903192,0.000011101268],"category_scores_gemma":[0.002224859,0.00005755489,0.000042360854,0.0012405812,0.0001494618,0.00007980586,0.000046315086,0.0001135322,0.0000028111758],"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":[0.0005916281,0.00044841506,0.06458411,0.00012478812,0.000101136364,0.00015684804,0.0016880295,0.44015872,0.00052935694,0.19226468,0.042696804,0.25665548],"study_design_scores_gemma":[0.00061501266,0.0008601654,0.12694858,0.00004022205,0.000032524204,0.00048195085,0.00030397487,0.46337178,0.000017600185,0.39869165,0.0085203145,0.00011619046],"about_ca_topic_score_codex":0.000019867008,"about_ca_topic_score_gemma":0.000020348998,"teacher_disagreement_score":0.64281946,"about_ca_system_score_codex":0.000018891973,"about_ca_system_score_gemma":0.00012377325,"threshold_uncertainty_score":0.2663525},"labels":[],"label_agreement":null},{"id":"W4390618520","doi":"10.1080/10618600.2024.2302528","title":"A Bayesian Collocation Integral Method for Parameter Estimation in Ordinary Differential Equations","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Discovery Eye Foundation","keywords":"Ode; Ordinary differential equation; Collocation (remote sensing); Collocation method; Applied mathematics; Nonlinear system; Bayesian probability; Computer science; Orthogonal collocation; Mathematics; Mathematical optimization; Bayes estimator; Estimation theory; Gaussian; Basis (linear algebra); Numerical integration; Algorithm; Differential equation; Mathematical analysis; Artificial intelligence; Machine learning","score_opus":0.01458855396392059,"score_gpt":0.3136028009829331,"score_spread":0.29901424701901247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390618520","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":[0.00065327605,0.00015067476,0.9972751,0.0015298272,0.00022753875,0.00010645725,0.000037578997,0.000013617052,0.00000588891],"genre_scores_gemma":[0.4730597,0.000008009029,0.5268382,0.0000478603,0.000021925865,0.0000051763022,0.000009608152,0.0000030102576,0.0000065020877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894667,0.0000605654,0.00046666682,0.00015598835,0.00024991325,0.00012021304],"domain_scores_gemma":[0.99773836,0.0017603968,0.0001310531,0.00004802287,0.00024136294,0.00008079515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028853034,0.000098711105,0.00017481355,0.0003141909,0.00006854751,0.00028567621,0.00015979564,0.000052349922,0.000008298211],"category_scores_gemma":[0.00020448337,0.0000777218,0.000056410587,0.00043249465,0.000043214168,0.0003560106,0.000022301878,0.00018143996,6.7206764e-7],"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":[0.00002441425,0.00006467187,0.000052918098,0.000100280995,0.000029411636,0.000017851506,0.00021287076,0.0117896395,0.000010156262,0.7454953,0.00026059215,0.24194187],"study_design_scores_gemma":[0.00015899779,0.00014332405,0.002109404,0.000056141173,0.000012354593,0.000044008473,0.0000047236676,0.52617234,0.000003859226,0.47120002,0.000045773402,0.00004901199],"about_ca_topic_score_codex":0.000005617853,"about_ca_topic_score_gemma":0.0000057929674,"teacher_disagreement_score":0.5143827,"about_ca_system_score_codex":0.000029240315,"about_ca_system_score_gemma":0.00018208216,"threshold_uncertainty_score":0.3169403},"labels":[],"label_agreement":null},{"id":"W4392033304","doi":"10.1080/10618600.2024.2322561","title":"Hammock Plots: Visualizing Categorical and Numerical Variables","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Data Visualization and Analytics","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":false,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Categorical variable; Mathematics; Statistics; Econometrics; Computer science; Artificial intelligence","score_opus":0.015345263605094658,"score_gpt":0.30025821888867443,"score_spread":0.2849129552835798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392033304","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":[0.0007856259,0.00081908883,0.99673593,0.0013249444,0.00021504906,0.000023383926,0.00003242902,0.000027612987,0.00003591823],"genre_scores_gemma":[0.74892396,0.00027701393,0.2500044,0.0005805662,0.00015227399,5.3636336e-7,0.000018953528,0.000009733589,0.00003252495],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998826,0.00006353967,0.00041847583,0.00016344704,0.00040235935,0.00012617033],"domain_scores_gemma":[0.9987268,0.00072434376,0.000100015655,0.00005019575,0.00020280405,0.00019582652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028788662,0.000103938764,0.00019266352,0.00019451881,0.00009912644,0.0004663472,0.00016040806,0.000044885448,0.000010041144],"category_scores_gemma":[0.00012380899,0.00008016427,0.000036786998,0.0004289445,0.000087037704,0.00033497237,0.00009130821,0.00019639933,0.0000027496685],"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":[0.0000051891393,0.00004567671,0.0002661819,0.00004398061,0.0000498803,0.0001238029,0.00011592403,0.0007321936,0.000008373754,0.9796451,0.004240862,0.014722834],"study_design_scores_gemma":[0.00014984899,0.00012406203,0.0020673107,0.00003025478,0.000023030647,0.00039636673,0.0000106839625,0.5485783,0.0000023867194,0.4398024,0.008729287,0.00008606679],"about_ca_topic_score_codex":0.0000036400697,"about_ca_topic_score_gemma":2.977186e-7,"teacher_disagreement_score":0.74813837,"about_ca_system_score_codex":0.000012951654,"about_ca_system_score_gemma":0.000098547054,"threshold_uncertainty_score":0.44969967},"labels":[],"label_agreement":null},{"id":"W4396688170","doi":"10.1080/10618600.2024.2350476","title":"Variance-Reduced Stochastic Optimization for Efficient Inference of Hidden Markov Models","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Fisheries and Oceans Canada; Dalhousie University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Fisheries and Oceans Canada; Canada Foundation for Innovation","keywords":"Hidden Markov model; Inference; Algorithm; Data set; Computer science; Set (abstract data type); Computation; Variance (accounting); Expectation–maximization algorithm; Statistical inference; Mathematical optimization; Mathematics; Artificial intelligence; Statistics; Maximum likelihood","score_opus":0.017910052971675323,"score_gpt":0.26792845352503847,"score_spread":0.25001840055336316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396688170","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":[0.030839043,0.00027422348,0.96824783,0.00022241879,0.00010329188,0.00010811192,0.00010306866,0.0000044282415,0.00009758857],"genre_scores_gemma":[0.7756547,0.000060655217,0.22418834,0.000042117044,0.000030078496,0.0000025525287,0.0000069992966,0.0000053194685,0.000009265374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904746,0.000024394274,0.0003853955,0.000110026005,0.00033585017,0.00009689317],"domain_scores_gemma":[0.9989087,0.0007410229,0.00014983123,0.000029256442,0.00010028724,0.000070884584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021955516,0.00008339203,0.00017785213,0.00004972714,0.00005836689,0.000028187043,0.00007926187,0.00002824022,0.00013521139],"category_scores_gemma":[0.00012973126,0.00006593827,0.000050483373,0.00019132893,0.00012808254,0.00007619712,0.00006586372,0.000090522386,0.0000010547905],"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":[0.000052871233,0.000053313623,0.000114324284,0.00007739777,0.000040667845,0.0000038538933,0.00008151962,0.93268573,0.0000094500865,0.040838458,0.00061913463,0.025423303],"study_design_scores_gemma":[0.00019660413,0.0001999275,0.009432849,0.000053648477,0.000047687754,0.000014546191,0.000006923785,0.8365218,0.0000010746832,0.1533978,0.00006510877,0.00006201721],"about_ca_topic_score_codex":0.00002061772,"about_ca_topic_score_gemma":0.000005039566,"teacher_disagreement_score":0.74481565,"about_ca_system_score_codex":0.00002959607,"about_ca_system_score_gemma":0.000029980263,"threshold_uncertainty_score":0.26888847},"labels":[],"label_agreement":null},{"id":"W4398162108","doi":"10.1080/10618600.2024.2335182","title":"Dynamic Survival Prediction Using Sparse Longitudinal Images via Multi-Dimensional Functional Principal Component Analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Principal component analysis; Functional principal component analysis; Component (thermodynamics); Computer science; Pattern recognition (psychology); Artificial intelligence; Mathematics; Algorithm","score_opus":0.09073121337460423,"score_gpt":0.36224534566664,"score_spread":0.2715141322920358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398162108","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":[0.152755,0.00023142887,0.8455327,0.00012512514,0.0005444703,0.00006870974,0.00071493123,0.000021462436,0.0000061345568],"genre_scores_gemma":[0.4874488,0.000014990801,0.5123681,0.000017638471,0.00008211629,0.0000010077088,0.000043732387,0.00001095504,0.000012688765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975037,0.00021018516,0.0009173864,0.00026319321,0.00089219684,0.00021336928],"domain_scores_gemma":[0.9954074,0.0033789007,0.0002765445,0.00007366487,0.0006288138,0.00023466563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000849931,0.00021583811,0.0004953867,0.0004648627,0.00017804316,0.00012191882,0.000085008745,0.00008944834,0.00017331849],"category_scores_gemma":[0.0004238775,0.0001698454,0.00020291634,0.0005812718,0.0002625619,0.00012853065,0.000056026976,0.00044586894,0.0000024044898],"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":[0.0005787844,0.001494444,0.040466916,0.0006617213,0.006165935,0.0009101066,0.00020047885,0.19875677,0.0012973782,0.7287965,0.0013288617,0.019342095],"study_design_scores_gemma":[0.00027369914,0.00010827999,0.1894429,0.000044345976,0.00064930116,0.00018733599,0.000006709367,0.5089927,0.0000031985899,0.30017304,0.000019570236,0.00009894236],"about_ca_topic_score_codex":0.000013220081,"about_ca_topic_score_gemma":0.000008906603,"teacher_disagreement_score":0.42862347,"about_ca_system_score_codex":0.00007129784,"about_ca_system_score_gemma":0.00012950883,"threshold_uncertainty_score":0.6926094},"labels":[],"label_agreement":null},{"id":"W4398183818","doi":"10.1080/10618600.2024.2358156","title":"Nonparametric High-Dimensional Multi-Sample Tests based on Graph Theory","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Computer science; Sample (material); Mathematics; Econometrics; Statistics","score_opus":0.0543335384810146,"score_gpt":0.3573869778430195,"score_spread":0.3030534393620049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398183818","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":[0.012639479,0.0001985286,0.98567,0.0003730147,0.00035328264,0.000079752834,0.0006339601,0.000022759687,0.000029233206],"genre_scores_gemma":[0.3421798,0.000011085248,0.65741754,0.00028049847,0.00007354147,0.0000016890795,0.000012264149,0.000013425692,0.000010134608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99805933,0.00025210058,0.00062539004,0.0001922615,0.0006856593,0.00018524595],"domain_scores_gemma":[0.96506625,0.0340764,0.00017449887,0.00007494897,0.0003961595,0.00021174748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009769482,0.00018291156,0.0003435451,0.00045583156,0.00010838721,0.00010258064,0.00010987578,0.0000820757,0.00017500667],"category_scores_gemma":[0.00550192,0.00012866115,0.00010295963,0.00054500904,0.00022123152,0.000051978113,0.000023785507,0.00045521144,0.0000052201694],"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":[0.000106704465,0.0002630262,0.00028584662,0.00010567602,0.00007208501,0.000112878704,0.0000194844,0.002931358,0.000006602256,0.94861907,0.0017086037,0.045768663],"study_design_scores_gemma":[0.0003674906,0.00048058238,0.017236082,0.00013453396,0.000073824456,0.000043983167,0.0000036839917,0.20597425,0.0000053164613,0.77545583,0.00010073158,0.00012370734],"about_ca_topic_score_codex":0.0000052749774,"about_ca_topic_score_gemma":0.0000012030251,"teacher_disagreement_score":0.3295403,"about_ca_system_score_codex":0.000022265624,"about_ca_system_score_gemma":0.00012692023,"threshold_uncertainty_score":0.65867096},"labels":[],"label_agreement":null},{"id":"W4399203487","doi":"10.1080/10618600.2024.2362219","title":"Iterated Data Sharpening","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Sharpening; Computer science; Artificial intelligence; Mathematics; Algorithm","score_opus":0.14548908453833034,"score_gpt":0.41053536403263885,"score_spread":0.2650462794943085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399203487","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":[0.008064119,0.00046608676,0.9899573,0.0005123142,0.00024449895,0.000035256726,0.0005860891,0.00001541869,0.00011892005],"genre_scores_gemma":[0.21944684,0.000047982838,0.780205,0.00009702338,0.00013935713,3.5885745e-7,0.00003091508,0.000009510051,0.0000230074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880624,0.00008698482,0.0005069373,0.00013787433,0.00035137654,0.00011059497],"domain_scores_gemma":[0.9943489,0.005064075,0.00011450815,0.0000823465,0.00026425647,0.00012595495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064801215,0.00009534411,0.00021788935,0.00011508279,0.000060095816,0.00016339855,0.00017001833,0.00004164405,0.00013051386],"category_scores_gemma":[0.0015909644,0.00006818346,0.000027975184,0.0002091742,0.00010251069,0.00012602628,0.00007357222,0.00028728123,0.0000030862911],"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":[0.000020479189,0.000033514025,0.00012691168,0.00011108718,0.00007414934,0.00014817326,0.000063376734,0.000040881594,0.000012998428,0.9317748,0.011898822,0.05569483],"study_design_scores_gemma":[0.00013615347,0.000109195054,0.002409313,0.00012685273,0.000060161157,0.00020636898,0.000009743392,0.16649067,0.0000018230634,0.8280997,0.002276737,0.00007322897],"about_ca_topic_score_codex":0.0000016523763,"about_ca_topic_score_gemma":6.816026e-7,"teacher_disagreement_score":0.21138273,"about_ca_system_score_codex":0.000007873439,"about_ca_system_score_gemma":0.00007860599,"threshold_uncertainty_score":0.27804407},"labels":[],"label_agreement":null},{"id":"W4402469547","doi":"10.1080/10618600.2024.2402279","title":"Optimal Subsampling for Functional Quasi-Mode Regression with Big Data","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Control Systems and Identification","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Regression analysis; Regression; Statistics; Big data; Mathematics; Econometrics; Artificial intelligence; Data mining","score_opus":0.038850709364129446,"score_gpt":0.27642046494984607,"score_spread":0.23756975558571664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402469547","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":[0.026898108,0.0008824141,0.97080314,0.00020770106,0.0006134851,0.00006406379,0.00050490286,0.000020404932,0.0000057887437],"genre_scores_gemma":[0.94860065,0.000055225195,0.05048671,0.000010945393,0.0005543581,0.0000026231726,0.00025582855,0.000013851416,0.00001983203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926335,0.000011485718,0.00030449388,0.00009988083,0.00024063415,0.00008018208],"domain_scores_gemma":[0.99918014,0.00045382386,0.00005778387,0.000056102683,0.00018577126,0.00006635805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020578218,0.0000793213,0.00013619527,0.00011497701,0.00006382403,0.00012194356,0.00006751453,0.000033615186,0.000003662377],"category_scores_gemma":[0.000035372377,0.000055190732,0.00002711371,0.000107159656,0.00003103562,0.00013864029,0.0000112536645,0.00012588971,4.0811466e-7],"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":[0.00035289692,0.000092750764,0.0006615671,0.00071127,0.0005292132,0.00004460873,0.0001626283,0.7402517,0.00044635645,0.07431027,0.03998697,0.14244977],"study_design_scores_gemma":[0.0003763092,0.00011833019,0.0058005913,0.0001445477,0.000060750008,0.00012583165,0.000015596543,0.9652809,0.0000029152598,0.019869363,0.008123424,0.00008142169],"about_ca_topic_score_codex":0.000002883987,"about_ca_topic_score_gemma":0.0000075066746,"teacher_disagreement_score":0.9217025,"about_ca_system_score_codex":0.000013804101,"about_ca_system_score_gemma":0.000043530956,"threshold_uncertainty_score":0.22506127},"labels":[],"label_agreement":null},{"id":"W4402469571","doi":"10.1080/10618600.2024.2402280","title":"Efficient Convex PCA with Applications to Wasserstein GPCA and Ranked Data","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and 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 Toronto","funders":"University of Toronto","keywords":"Mathematics; Regular polygon; Artificial intelligence; Computer science; Statistics; Data mining; Econometrics; Geometry","score_opus":0.07815119831874055,"score_gpt":0.375214006851606,"score_spread":0.29706280853286543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402469571","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":[0.016388789,0.00029915225,0.98128474,0.0011839912,0.000056995486,0.00015486074,0.00055605086,0.000012788885,0.000062632505],"genre_scores_gemma":[0.29037717,0.000023696208,0.70936567,0.00012938312,0.00006648106,0.0000038685157,0.000013552563,0.000009726283,0.000010461687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880636,0.00006793287,0.00042183735,0.00019411831,0.00038592308,0.00012382591],"domain_scores_gemma":[0.9953747,0.0039025694,0.0001011635,0.000111116926,0.00027921764,0.00023126116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050527573,0.00011612881,0.00025961114,0.00012890276,0.00008895886,0.000121728015,0.0001371487,0.000037802627,0.000026319234],"category_scores_gemma":[0.00041659313,0.0000781192,0.000017840528,0.0002656495,0.00016841083,0.000035257097,0.00007296394,0.00021641515,0.000002202546],"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":[0.00006372623,0.00006908849,0.00011795317,0.0001692417,0.00010712688,0.000041181633,0.00011011957,0.00045278185,0.000014170438,0.9697379,0.0019060504,0.027210684],"study_design_scores_gemma":[0.0003270914,0.00032472145,0.0043324484,0.00013410625,0.00013306325,0.00018798195,0.000048478072,0.15120886,0.0000022726126,0.8407419,0.0024356355,0.00012344815],"about_ca_topic_score_codex":0.0000028562358,"about_ca_topic_score_gemma":0.00000287527,"teacher_disagreement_score":0.2739884,"about_ca_system_score_codex":0.000010310075,"about_ca_system_score_gemma":0.000084628584,"threshold_uncertainty_score":0.31856087},"labels":[],"label_agreement":null},{"id":"W4403839440","doi":"10.1080/10618600.2024.2421248","title":"Multi-label Random Subspace Ensemble Classification","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"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; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Random forest; Random subspace method; Computer science; Classifier (UML); Subspace topology; Artificial intelligence; Ensemble learning; Linear subspace; Machine learning; Pattern recognition (psychology); Multinomial distribution; Multi-label classification; Data mining; Algorithm; Mathematics; Statistics","score_opus":0.03378278262940175,"score_gpt":0.30295361300985085,"score_spread":0.2691708303804491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403839440","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":[0.00512162,0.0012152175,0.9874786,0.0056802747,0.00030704212,0.000058108853,0.000013582037,0.00008575278,0.000039776267],"genre_scores_gemma":[0.5323154,0.00022358648,0.4672695,0.00008036882,0.000032985277,0.0000018014601,0.000004557845,0.0000040910563,0.00006769946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890023,0.000050004095,0.0004056515,0.00016328486,0.00036371095,0.00011714298],"domain_scores_gemma":[0.99867505,0.0007051973,0.00016375806,0.00009006824,0.00027780503,0.00008813359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032272754,0.000100213234,0.00016210928,0.0002643539,0.00009640433,0.00032466245,0.0002666808,0.000063402644,0.0000060565703],"category_scores_gemma":[0.00013527767,0.00007672436,0.00004682037,0.00041547578,0.00012056275,0.00037298384,0.00004913654,0.00023342128,0.000009321779],"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":[0.000016072587,0.0000750331,0.00022809264,0.000027330809,0.00003990757,0.000030476966,0.000112099355,0.00013534253,0.00044529102,0.8312623,0.0042330986,0.16339496],"study_design_scores_gemma":[0.00068461784,0.000111830275,0.012875379,0.000030654097,0.000016044709,0.00009960852,0.000027105529,0.57111645,0.000040264713,0.41180608,0.0031000413,0.000091963935],"about_ca_topic_score_codex":0.0000011984044,"about_ca_topic_score_gemma":0.0000011701061,"teacher_disagreement_score":0.5709811,"about_ca_system_score_codex":0.000020999309,"about_ca_system_score_gemma":0.00009066636,"threshold_uncertainty_score":0.31307274},"labels":[],"label_agreement":null},{"id":"W4405429052","doi":"10.1080/10618600.2024.2441988","title":"Efficient Estimation of Parameters in Marginals in Semiparametric Multivariate Models","year":2024,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Brock University","funders":"Russian Science Foundation","keywords":"Copula (linguistics); Estimator; Mathematics; Univariate; Multivariate statistics; Joint probability distribution; Parametric statistics; Econometrics; Applied mathematics; Statistics","score_opus":0.033567515912302594,"score_gpt":0.2660289044829378,"score_spread":0.23246138857063522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405429052","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":[0.5122948,0.0012088822,0.48620358,0.00008373874,0.00006988487,0.00003716348,0.00008235042,0.0000014206896,0.000018167862],"genre_scores_gemma":[0.89912355,0.00009848695,0.100740544,0.000015593338,0.000008736828,0.0000010153344,0.0000052218065,0.000004980133,0.0000018416589],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871767,0.00002225608,0.00094451825,0.00012447279,0.000085608066,0.00010550814],"domain_scores_gemma":[0.9989974,0.00063253014,0.00023239794,0.000032789423,0.00006164813,0.000043216885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076019095,0.000075087,0.00030551056,0.00084632664,0.000016067748,0.000031117335,0.000054396776,0.00004747548,0.0000043743025],"category_scores_gemma":[0.00025776736,0.00007461137,0.00005156646,0.0006144029,0.0000497686,0.000084146515,0.000013818383,0.00020977715,0.0000013170009],"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":[0.000028128235,0.00007117483,0.0034124777,0.00005523869,0.000009658539,0.000013044664,0.00024333218,0.7427873,4.7075042e-7,0.24965554,0.000009480899,0.0037141447],"study_design_scores_gemma":[0.00018934523,0.000044540247,0.03818909,0.00006169201,0.000002536478,0.000004216616,0.000006436261,0.523048,6.1391694e-7,0.43840995,0.0000056904205,0.000037905935],"about_ca_topic_score_codex":0.00012590818,"about_ca_topic_score_gemma":0.000006534287,"teacher_disagreement_score":0.38682878,"about_ca_system_score_codex":0.000039565453,"about_ca_system_score_gemma":0.00003545879,"threshold_uncertainty_score":0.30425635},"labels":[],"label_agreement":null},{"id":"W4406049757","doi":"10.1080/10618600.2024.2446357","title":"Bayesian Partial Reduced-Rank Regression","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; Consejo Nacional de Ciencia y Tecnología; Università degli Studi di Milano","keywords":"Mathematics; Rank (graph theory); Dimensionality reduction; Regression; Regression analysis; Bayesian probability; Statistics; Curse of dimensionality; Artificial intelligence; Computer science; Combinatorics","score_opus":0.0409694983498707,"score_gpt":0.3722382201307923,"score_spread":0.3312687217809216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406049757","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":[0.017319702,0.00011751603,0.9806106,0.0011451817,0.00027251674,0.000055742137,0.000060808503,0.0000082702,0.00040963799],"genre_scores_gemma":[0.39205235,0.00003884316,0.6075878,0.0001902039,0.00007575554,0.0000010093171,0.000002905772,0.0000050404733,0.000046065088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998607,0.00015574801,0.00063396775,0.00011492892,0.00034929643,0.00013907041],"domain_scores_gemma":[0.9955795,0.003547219,0.00026697654,0.00006203,0.00040752647,0.00013675015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046754398,0.00011891794,0.00031604627,0.00014500409,0.00011893781,0.000047872156,0.000100417165,0.00007108959,0.00006880148],"category_scores_gemma":[0.0020902709,0.00008358056,0.000060713737,0.0002181445,0.0001726276,0.000045180157,0.000034242643,0.00027943298,7.3401543e-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":[0.000095696545,0.00009852867,0.00063130265,0.000067085144,0.00005344046,0.00002925286,0.000041121802,0.00006545975,0.000044916447,0.9425287,0.008485104,0.04785939],"study_design_scores_gemma":[0.0004977896,0.00016508531,0.014350446,0.00015960474,0.000071596325,0.00004278527,0.000018407589,0.014987473,0.0000404909,0.96868646,0.00089313864,0.00008671569],"about_ca_topic_score_codex":0.0000020588473,"about_ca_topic_score_gemma":7.4238744e-7,"teacher_disagreement_score":0.37473264,"about_ca_system_score_codex":0.0000138196465,"about_ca_system_score_gemma":0.00010179253,"threshold_uncertainty_score":0.34083164},"labels":[],"label_agreement":null},{"id":"W4406096298","doi":"10.1080/10618600.2024.2449074","title":"Simultaneous Estimation of Multiple Treatment Effects from Observational Studies","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Instrumental variable; Observational study; Inference; Confounding; Proxy (statistics); Robustness (evolution); Marginal structural model; Computer science; Econometrics; Exploit; Machine learning; Statistics; Mathematics; Data mining; Artificial intelligence","score_opus":0.11160337066313168,"score_gpt":0.42757067412792427,"score_spread":0.31596730346479257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406096298","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":[0.23735106,0.00034379962,0.76181674,0.00019040219,0.000069182955,0.00009701055,0.00011212901,0.000011419545,0.000008261665],"genre_scores_gemma":[0.55730724,0.000090362606,0.4425165,0.000040477284,0.00001559867,0.0000024362005,0.0000153687,0.0000031545387,0.000008847522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895346,0.00006375452,0.00056678744,0.0000841298,0.00025903695,0.00007284408],"domain_scores_gemma":[0.98112154,0.017784659,0.00038375464,0.000048749473,0.0006201781,0.00004112323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012596838,0.000113062546,0.00036628547,0.00012053874,0.000056549045,0.000011717526,0.000058287813,0.00004756541,0.0000036509782],"category_scores_gemma":[0.0033391572,0.000084798994,0.000052009884,0.00014319866,0.00014106566,0.000073457995,0.00002168201,0.00009512793,1.796695e-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":[0.00020452806,0.00043650848,0.004345863,0.0002662754,0.0006291645,0.00004535819,0.00035385822,0.05402788,0.0002168744,0.8669458,0.0008585992,0.0716693],"study_design_scores_gemma":[0.00059270294,0.0003445016,0.01080498,0.00017525547,0.00011342991,0.000005462792,0.000028803614,0.08641617,0.00041038118,0.90100336,0.0000441927,0.000060760904],"about_ca_topic_score_codex":0.0000065388617,"about_ca_topic_score_gemma":0.0000073567435,"teacher_disagreement_score":0.3199562,"about_ca_system_score_codex":0.000051536423,"about_ca_system_score_gemma":0.00006988665,"threshold_uncertainty_score":0.39975244},"labels":[],"label_agreement":null},{"id":"W4406097138","doi":"10.1080/10618600.2024.2447478","title":"Stochastic Gradient Descent-based Inference for Dynamic Network Models with Attractors","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Division of Mathematical Sciences; Division of Social and Economic Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inference; Attractor; Node (physics); Gradient descent; Stochastic gradient descent; Markov chain Monte Carlo; Scaling; Limit (mathematics); Theoretical computer science; Mathematical optimization; Artificial intelligence; Artificial neural network; Mathematics","score_opus":0.009910994604382018,"score_gpt":0.2840213263491029,"score_spread":0.2741103317447209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406097138","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":[0.066593625,0.00005699917,0.9326369,0.00032111452,0.00013517967,0.00010240274,0.00013014505,0.0000027556466,0.000020863925],"genre_scores_gemma":[0.94181234,0.0000029082864,0.05796023,0.00013503357,0.00003670689,0.0000043442433,0.000034819575,0.000004923644,0.000008718183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929726,0.000021482023,0.0003091783,0.000090155525,0.00014820888,0.0001336912],"domain_scores_gemma":[0.9986153,0.0006866739,0.00019528157,0.00003295956,0.0003987416,0.000071034585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001113252,0.00009754966,0.00019356319,0.000076038035,0.00015783758,0.00005907662,0.00007253468,0.00002711301,0.0000034991651],"category_scores_gemma":[0.000012146984,0.00007689113,0.00005539941,0.00017499273,0.00012469433,0.000055921646,0.000011057318,0.00015221933,9.164315e-8],"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":[0.00005377726,0.000050073126,0.0045188274,0.000012003883,0.000058510985,4.182947e-7,0.000011664428,0.5067459,3.8824732e-7,0.48587137,0.00008152184,0.0025955527],"study_design_scores_gemma":[0.00044676915,0.000083360086,0.019801928,0.0000660643,0.000033281973,2.845981e-7,0.000013425394,0.45999914,1.0974261e-7,0.51947254,0.00003496781,0.00004813854],"about_ca_topic_score_codex":0.000009267437,"about_ca_topic_score_gemma":0.0000056055287,"teacher_disagreement_score":0.8752187,"about_ca_system_score_codex":0.000017490234,"about_ca_system_score_gemma":0.00019073409,"threshold_uncertainty_score":0.3135529},"labels":[],"label_agreement":null},{"id":"W4406321275","doi":"10.1080/10618600.2025.2451680","title":"Variable Selection and Basis Learning for Ordinal Classification","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Face and Expression Recognition","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":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Ordinal regression; Ordinal data; Linear discriminant analysis; Mathematics; Ordinal optimization; Basis (linear algebra); Dimension (graph theory); Feature selection; Variable (mathematics); Variables; Statistics; Artificial intelligence; Pattern recognition (psychology); Computer science; Combinatorics","score_opus":0.01272680945528477,"score_gpt":0.2700614872194298,"score_spread":0.25733467776414504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406321275","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":[0.009946335,0.00007425922,0.98858947,0.001169715,0.00010516167,0.0000481942,0.000006048978,0.000008353875,0.00005249592],"genre_scores_gemma":[0.3852308,0.00003668786,0.6144877,0.00016361012,0.000029354294,0.0000025129914,0.000007150907,0.000001717002,0.00004046431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994168,0.000044859185,0.000233935,0.00009663655,0.00013598023,0.000071746836],"domain_scores_gemma":[0.9987657,0.00060479844,0.00014096838,0.000019385954,0.00041861573,0.0000504976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002523076,0.000053700733,0.00010459825,0.00015256093,0.00018252945,0.00010338272,0.000060355476,0.00003994673,0.0000028418085],"category_scores_gemma":[0.00015988073,0.00004539694,0.000020372916,0.00022936267,0.000028136621,0.00017645417,0.000020762302,0.0001273429,2.333754e-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":[0.000052731193,0.000045770004,0.0026945733,0.000049567636,0.00003530254,9.3921767e-7,0.000038876155,0.004505563,0.00029186878,0.8935338,0.002769426,0.095981546],"study_design_scores_gemma":[0.00034617417,0.0001338983,0.027834322,0.000033546454,0.00001616084,0.000022430468,0.00001322886,0.42485026,0.00002143585,0.54422396,0.0024654497,0.000039153667],"about_ca_topic_score_codex":0.0000020602147,"about_ca_topic_score_gemma":7.035174e-7,"teacher_disagreement_score":0.42034468,"about_ca_system_score_codex":0.000009411384,"about_ca_system_score_gemma":0.00006268154,"threshold_uncertainty_score":0.18512335},"labels":[],"label_agreement":null},{"id":"W4406865792","doi":"10.1080/10618600.2025.2459287","title":"Online Kernel-Based Mode Learning","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Adaptive Filtering Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Online learning; Kernel (algebra); Machine learning; Theoretical computer science; Mathematics; World Wide Web; Combinatorics","score_opus":0.007858430918642127,"score_gpt":0.27224090429068387,"score_spread":0.26438247337204174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406865792","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":[0.039141957,0.00015702164,0.9603354,0.00012033811,0.00007264133,0.000022605596,0.00005158843,0.000046631845,0.000051830924],"genre_scores_gemma":[0.6486278,0.00003907728,0.35121763,0.000061780476,0.000024362578,4.2412867e-7,0.0000125052575,0.0000055967134,0.000010794418],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948263,0.000017377042,0.00024834514,0.000047139114,0.00013000311,0.00007450227],"domain_scores_gemma":[0.9994035,0.00031206463,0.00005582089,0.00002299893,0.0001591024,0.00004651512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059659982,0.00007395892,0.00013603382,0.00014026972,0.000039442268,0.000016464941,0.000054805943,0.000032278953,0.000004697525],"category_scores_gemma":[0.00007474536,0.00006705469,0.000028790912,0.00012501706,0.000054719912,0.00004252494,0.000011567023,0.00026599137,2.1881343e-7],"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":[0.000019107718,0.000035828896,0.0008301106,0.000051869043,0.000036002133,0.000016055297,0.000010281348,0.94415504,0.0001269699,0.041561097,0.00065491215,0.012502714],"study_design_scores_gemma":[0.00024587067,0.00007910981,0.02116817,0.00007723594,0.000013936539,0.000009557405,0.0000050024655,0.6499489,0.000060402657,0.32642433,0.0019019837,0.0000654893],"about_ca_topic_score_codex":7.5819173e-7,"about_ca_topic_score_gemma":0.0000010276551,"teacher_disagreement_score":0.60948586,"about_ca_system_score_codex":0.00001926562,"about_ca_system_score_gemma":0.000023186585,"threshold_uncertainty_score":0.27344108},"labels":[],"label_agreement":null},{"id":"W4408144537","doi":"10.1080/10618600.2025.2475139","title":"High-Dimensional Covariate-Dependent Gaussian Graphical Models","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Graphical model; Computer science; Gaussian; Econometrics; Mathematics; Statistics; Artificial intelligence","score_opus":0.01453389678061359,"score_gpt":0.2733778907991399,"score_spread":0.2588439940185263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408144537","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":[0.002871747,0.0003223299,0.99195844,0.004050948,0.0005437242,0.00006936638,0.000041463754,0.000018101066,0.0001239079],"genre_scores_gemma":[0.38973013,0.00004198995,0.60925597,0.0008809152,0.00004924797,0.0000010528998,0.0000043540163,0.0000042019374,0.000032119795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980182,0.00020041096,0.00068085926,0.00024969573,0.0006351511,0.00021565091],"domain_scores_gemma":[0.9981286,0.0007384434,0.00026161326,0.00013136333,0.00051341264,0.00022659708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069119746,0.0001762374,0.00037441586,0.0003628944,0.00018133067,0.00015250621,0.00037491063,0.000115208204,0.000008698089],"category_scores_gemma":[0.00007613051,0.00013667828,0.00010314639,0.0004621603,0.00014738903,0.00028062018,0.00013989588,0.0004373023,9.963913e-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":[0.00004609189,0.0001151437,0.000070991795,0.000017260892,0.000088814566,0.00007947768,0.00003404586,0.012906568,0.000016807659,0.9563967,0.0016823773,0.028545743],"study_design_scores_gemma":[0.0006530848,0.00012067446,0.0055633583,0.00003646727,0.00003050746,0.00012148782,0.0000013349901,0.24830106,0.000009298961,0.74495393,0.00010285529,0.00010591655],"about_ca_topic_score_codex":0.00001173622,"about_ca_topic_score_gemma":0.0000028071934,"teacher_disagreement_score":0.38685837,"about_ca_system_score_codex":0.000020761554,"about_ca_system_score_gemma":0.00022009424,"threshold_uncertainty_score":0.55735785},"labels":[],"label_agreement":null},{"id":"W4409672286","doi":"10.1080/10618600.2025.2495780","title":"A Stability Framework for Parameter Selection in the Minimum Covariance Determinant Problem","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"U.S. Public Health Service","keywords":"Stability (learning theory); Covariance; Selection (genetic algorithm); Mathematics; Mathematical optimization; Computer science; Applied mathematics; Statistics; Artificial intelligence; Machine learning","score_opus":0.06944171784907366,"score_gpt":0.4137217667928977,"score_spread":0.344280048943824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409672286","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":[0.013440616,0.000051003935,0.98514587,0.000913994,0.00006732734,0.00027186022,0.0000925117,0.000003388431,0.000013413911],"genre_scores_gemma":[0.21498473,0.00001287453,0.78468674,0.00026189943,0.000028901706,0.000014757254,0.0000017087302,0.0000041368617,0.0000042479332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987119,0.00019526998,0.0005980735,0.00012461719,0.00022466465,0.00014547449],"domain_scores_gemma":[0.9816163,0.017735966,0.00023351179,0.000044323435,0.00032549872,0.000044373748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010153586,0.000101050275,0.00027267227,0.00007942513,0.00010082509,0.000040615665,0.00009837,0.00007002312,0.000004218344],"category_scores_gemma":[0.0033511287,0.00006471959,0.000056364846,0.00023338918,0.00012031982,0.000055364686,0.000014300097,0.00030255775,5.7600058e-8],"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":[0.0001889166,0.00016392375,0.00038086798,0.0001515245,0.000025060075,0.000005530491,0.00017075824,0.00047330317,0.000008592501,0.97862804,0.0002806662,0.019522822],"study_design_scores_gemma":[0.00046680938,0.00025251493,0.0059439796,0.00009668329,0.000050290655,0.000024714951,0.000048736514,0.04792197,0.00000694496,0.9448942,0.00022597046,0.00006720416],"about_ca_topic_score_codex":0.0000015082686,"about_ca_topic_score_gemma":0.000008141323,"teacher_disagreement_score":0.2015441,"about_ca_system_score_codex":0.000021419168,"about_ca_system_score_gemma":0.00007531864,"threshold_uncertainty_score":0.40118563},"labels":[],"label_agreement":null},{"id":"W4413013076","doi":"10.1080/10618600.2025.2544182","title":"On Seeded Subgraph-to-Subgraph Matching: The ssSGM Algorithm and Matchability Information Theory","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Induced subgraph isomorphism problem; Subgraph isomorphism problem; Matching (statistics); Seeding; Algorithm; Computer science; Mathematics; Artificial intelligence; Combinatorics; Graph; Statistics; Line graph; Biology","score_opus":0.003457809734509369,"score_gpt":0.22857143812472058,"score_spread":0.2251136283902112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413013076","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":[0.049177296,0.00008914741,0.94743127,0.0027453064,0.00028505785,0.0001290577,0.000055694607,0.000017041368,0.00007011907],"genre_scores_gemma":[0.82002854,0.00004375456,0.17648415,0.0033783412,0.0000369997,0.0000041296194,0.0000067414803,0.000004048391,0.0000133045205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985031,0.0002153106,0.0005345449,0.0001482088,0.00042912664,0.00016969799],"domain_scores_gemma":[0.9968513,0.0022767568,0.00022666443,0.00013754246,0.00035638912,0.00015133462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012980105,0.00015569422,0.00022637122,0.00039639504,0.00034872402,0.00027547314,0.00035602553,0.0000577695,0.0000041497574],"category_scores_gemma":[0.0001695849,0.000101710735,0.00007834539,0.0006873997,0.0002397742,0.00036805216,0.00011331352,0.000345394,0.0000019295846],"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":[0.00006125453,0.00004322506,0.00014608607,0.00001952031,0.00005470223,0.0000051413763,0.00048289748,0.002269907,0.0000022964166,0.88974446,0.00036730693,0.1068032],"study_design_scores_gemma":[0.00041681112,0.00022961863,0.05673231,0.000041712323,0.000021242484,0.000053361793,0.00007854487,0.022347823,0.000006492847,0.919656,0.00031410737,0.00010200595],"about_ca_topic_score_codex":0.0000044922886,"about_ca_topic_score_gemma":8.822472e-7,"teacher_disagreement_score":0.7709471,"about_ca_system_score_codex":0.0000141269065,"about_ca_system_score_gemma":0.00007482942,"threshold_uncertainty_score":0.41476434},"labels":[],"label_agreement":null},{"id":"W4413165906","doi":"10.1080/10618600.2025.2541012","title":"Boosting Prediction with Data Missing Not at Random","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boosting (machine learning); Missing data; Computer science; Artificial intelligence; Random forest; Machine learning; Econometrics; Statistics; Data mining; Mathematics","score_opus":0.02070957838485018,"score_gpt":0.2705212398444851,"score_spread":0.24981166145963493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413165906","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":[0.0180476,0.00011949937,0.9790686,0.0024100922,0.00015088038,0.000040265608,0.00006998729,0.000011141444,0.00008196385],"genre_scores_gemma":[0.5380728,0.000059230086,0.4610327,0.00067150523,0.000060090733,6.3430855e-7,0.00005885494,0.0000033318634,0.000040831594],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908525,0.00005469123,0.00031552784,0.0001373856,0.00032014045,0.000086997745],"domain_scores_gemma":[0.9987224,0.0006537548,0.00018798736,0.000093559145,0.00026785643,0.00007448954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030184886,0.00006999944,0.00013959258,0.00012410899,0.0001992448,0.0001221401,0.00022126999,0.000031821663,0.0000042670104],"category_scores_gemma":[0.00013648186,0.00004952906,0.000017310735,0.0001973337,0.00006174167,0.0003451372,0.00013705406,0.00014027747,7.5597825e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022288593,0.00048350825,0.028557127,0.0003346443,0.0005576431,0.000355393,0.00057144486,0.034651097,0.001004023,0.17651707,0.090121,0.6646182],"study_design_scores_gemma":[0.0023758626,0.00018503894,0.039862357,0.00028525127,0.00005406047,0.00023393075,0.000013584271,0.76853645,0.00007249449,0.18545075,0.002827227,0.00010297534],"about_ca_topic_score_codex":0.0000022729025,"about_ca_topic_score_gemma":0.0000018078633,"teacher_disagreement_score":0.73388535,"about_ca_system_score_codex":0.000012259924,"about_ca_system_score_gemma":0.00007980321,"threshold_uncertainty_score":0.20197365},"labels":[],"label_agreement":null},{"id":"W4414200196","doi":"10.1080/10618600.2025.2560626","title":"Semiparametric Estimation for Error-Prone Partially Linear Single-Index Models","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science and Technology Council","keywords":"Semiparametric model; Semiparametric regression; Estimation; Estimation theory; Linear model; Estimator; Expectation–maximization algorithm","score_opus":0.099807566370477,"score_gpt":0.38613352885231333,"score_spread":0.28632596248183634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414200196","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":[0.010020643,0.000095536365,0.9886992,0.0005723625,0.00017041052,0.0001688165,0.00015598751,0.000011064876,0.00010596256],"genre_scores_gemma":[0.35516664,0.000009746358,0.64460814,0.00013179668,0.00004240146,0.0000039935485,0.000007627579,0.000006456479,0.000023179535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984789,0.000092324044,0.0007716109,0.00013535481,0.00035779175,0.00016404646],"domain_scores_gemma":[0.9913332,0.0073002563,0.0003504072,0.00006223877,0.0008342475,0.00011965501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060283346,0.0001342744,0.0003609538,0.00025585692,0.00011529779,0.00005382596,0.000103052516,0.00008814842,0.000011752328],"category_scores_gemma":[0.0037161298,0.00010869549,0.00007486478,0.00036125054,0.00013338558,0.00008774457,0.00002702145,0.00020886448,3.757899e-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":[0.00014495382,0.00018348866,0.00020814635,0.00016054086,0.000077759236,0.000005096095,0.000038067185,0.034356456,0.000009930023,0.91095686,0.0014876875,0.052371033],"study_design_scores_gemma":[0.0004343963,0.00019939616,0.0017479945,0.00005465847,0.000064277556,0.000010224363,0.0000074820655,0.46578205,0.0000091730835,0.5315633,0.000066961715,0.000060092058],"about_ca_topic_score_codex":0.0000023364962,"about_ca_topic_score_gemma":0.0000019947613,"teacher_disagreement_score":0.43142557,"about_ca_system_score_codex":0.000026506814,"about_ca_system_score_gemma":0.00011820197,"threshold_uncertainty_score":0.4448823},"labels":[],"label_agreement":null},{"id":"W4414384679","doi":"10.1080/10618600.2025.2561900","title":"Concurrent Prediction of Multiple Survival Outcomes with a Refined Stacking Algorithm","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Stacking; Minification; Identification (biology); Expectation–maximization algorithm","score_opus":0.014137165551512915,"score_gpt":0.2735001843192426,"score_spread":0.2593630187677297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414384679","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":[0.009547869,0.00007453408,0.9889868,0.00097379717,0.00021082986,0.000039771632,0.00012716475,0.000010697018,0.000028570494],"genre_scores_gemma":[0.671135,0.000024147526,0.32871515,0.000060480274,0.000017910672,7.4054213e-7,0.00003123558,0.0000021594074,0.000013158214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99893993,0.00008485964,0.00041546175,0.000110692796,0.00037194302,0.00007712679],"domain_scores_gemma":[0.9982087,0.0008647235,0.00033426625,0.000071777715,0.00046379105,0.000056722518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107498,0.00007848821,0.00020897597,0.00017259005,0.00007517487,0.00005139743,0.00015436154,0.00002913757,0.0000016522634],"category_scores_gemma":[0.00019433502,0.000055269407,0.00003114371,0.0002717563,0.00008016246,0.0001375089,0.000040899624,0.00017675431,1.6642883e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003486446,0.00020186348,0.15715672,0.0000678338,0.00015316517,0.000010735348,0.0001154284,0.0057764417,0.00001932657,0.48310038,0.0005271326,0.3528361],"study_design_scores_gemma":[0.0008445606,0.00021354771,0.5999244,0.000048530066,0.000022260409,0.000013351238,0.000011912294,0.3574762,0.0000041781705,0.04053199,0.00086456264,0.000044516706],"about_ca_topic_score_codex":0.000009557272,"about_ca_topic_score_gemma":0.0000039948245,"teacher_disagreement_score":0.6615872,"about_ca_system_score_codex":0.0000118196485,"about_ca_system_score_gemma":0.00009895882,"threshold_uncertainty_score":0.2253821},"labels":[],"label_agreement":null},{"id":"W4414511858","doi":"10.1080/10618600.2025.2559675","title":"Approximations in the Homogeneous Ising Model with Application to Scene Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Theoretical and Computational Physics","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Food and Agriculture","keywords":"Ising model; Homogeneous; Approximations of π; Work (physics)","score_opus":0.003290519442735462,"score_gpt":0.24304964804114476,"score_spread":0.2397591285984093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414511858","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":[0.09277725,0.000013819046,0.9055017,0.001310982,0.000008511594,0.00008089804,0.000059180566,0.0000018892242,0.0002457375],"genre_scores_gemma":[0.906225,6.888584e-7,0.09337741,0.00031707488,0.00003210423,0.000005788513,0.000031926793,0.0000025200004,0.0000074344875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999249,0.000042182986,0.00028798252,0.000092517,0.00024314421,0.00008517825],"domain_scores_gemma":[0.99911296,0.00043399105,0.00010464631,0.000051041145,0.00024837485,0.000048985406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015827661,0.00007758784,0.00016307377,0.00019860697,0.00009950661,0.000056114885,0.000109376,0.000013817833,0.000003882033],"category_scores_gemma":[0.00000810957,0.00004992356,0.000051430638,0.000945642,0.000073323536,0.00004267395,0.00001633807,0.00013520785,5.5499396e-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":[0.000022875493,0.00007825931,0.0024322402,0.0000030407948,0.00008537262,6.8741394e-7,0.000074747375,0.46269104,0.0000026799246,0.52679306,0.000042284548,0.0077736927],"study_design_scores_gemma":[0.0001576559,0.000029039185,0.021009957,0.0000076315255,0.0001108187,0.0000014208273,0.000046652964,0.39071038,0.0000020226462,0.5878661,0.000020350039,0.0000379668],"about_ca_topic_score_codex":0.000008761504,"about_ca_topic_score_gemma":0.0000036462352,"teacher_disagreement_score":0.8134478,"about_ca_system_score_codex":0.00000825413,"about_ca_system_score_gemma":0.000063702704,"threshold_uncertainty_score":0.20358238},"labels":[],"label_agreement":null},{"id":"W4415351738","doi":"10.1080/10618600.2025.2574535","title":"Computationally Efficient Algorithms for Simulating Isotropic Gaussian Random Fields on Graphs with Euclidean Edges","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Point processes and geometric inequalities","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico; Agencia Nacional de Investigación y Desarrollo","keywords":"Random field; Efficient algorithm; Euclidean geometry; Gaussian; Random graph; Isotropy; Gaussian random field","score_opus":0.030553763293131288,"score_gpt":0.32538703542045383,"score_spread":0.2948332721273225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415351738","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":[0.07658404,0.000110712666,0.9217515,0.0010324693,0.00012561533,0.00015981427,0.00010630941,0.000010349553,0.000119188226],"genre_scores_gemma":[0.7672181,0.000013375572,0.23224404,0.00036030906,0.00007362085,0.0000038364237,0.000017481434,0.000008395453,0.000060832623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99858874,0.000054139116,0.00062812254,0.00013513099,0.00042951593,0.00016436653],"domain_scores_gemma":[0.9915871,0.0071435682,0.00036263646,0.000048150156,0.0007765362,0.00008199017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040454953,0.00015006319,0.00036313472,0.00040003212,0.0002106264,0.00007760774,0.00009536546,0.000060728315,0.000008243856],"category_scores_gemma":[0.0007566792,0.00010453373,0.000088796696,0.00039659414,0.00010441728,0.000042900967,0.000018469605,0.00020405807,2.2593721e-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":[0.00046595378,0.0001876523,0.00032682362,0.0002810207,0.00018656312,0.000012098158,0.00017590652,0.1149979,5.1631935e-7,0.87013006,0.0011339978,0.012101495],"study_design_scores_gemma":[0.0028543437,0.0006704308,0.0043597342,0.00018875134,0.00009162468,0.000021418462,0.00010756137,0.1279496,0.0000054362176,0.86337626,0.00025959767,0.0001152562],"about_ca_topic_score_codex":0.0000024359017,"about_ca_topic_score_gemma":0.000003000945,"teacher_disagreement_score":0.6906341,"about_ca_system_score_codex":0.000016644744,"about_ca_system_score_gemma":0.00011117822,"threshold_uncertainty_score":0.42627618},"labels":[],"label_agreement":null},{"id":"W4416967053","doi":"10.1080/10618600.2025.2596057","title":"Robust Multi-Model Subset Selection","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Selection (genetic algorithm); Robustness (evolution); Robust statistics; Cheminformatics; Estimator; Code (set theory); Source code","score_opus":0.10388863209006598,"score_gpt":0.4074373059381189,"score_spread":0.3035486738480529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416967053","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":[0.0052034617,0.000076542616,0.9940174,0.00034774523,0.00009902565,0.00006768404,0.00011290459,0.0000104501805,0.00006477238],"genre_scores_gemma":[0.08230458,0.000042069656,0.9172201,0.000244417,0.000031089625,0.0000015081636,0.000005246795,0.000007633331,0.00014333855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988589,0.000082535524,0.00054195576,0.00011883098,0.00026191803,0.00013582327],"domain_scores_gemma":[0.9971619,0.0019145377,0.00022686015,0.000038955128,0.0005482487,0.00010947974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038649392,0.00011545901,0.00028499792,0.00015456942,0.00012295562,0.0000320049,0.00007182425,0.00006595838,0.000010269548],"category_scores_gemma":[0.00097553444,0.00009259414,0.00005548616,0.0002039321,0.000109241744,0.00007787736,0.000024364186,0.0002782683,3.231091e-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":[0.000069324786,0.00014947003,0.00030649285,0.00006693211,0.000060672697,0.0000115999865,0.00003438939,0.05893367,0.000030852774,0.9278286,0.0028528464,0.00965514],"study_design_scores_gemma":[0.00042436348,0.000057897272,0.0022050692,0.000028394645,0.000047640297,0.000030472123,0.00000700526,0.40752637,0.000004255098,0.58952075,0.000092602924,0.000055168024],"about_ca_topic_score_codex":0.0000012005803,"about_ca_topic_score_gemma":0.0000044556787,"teacher_disagreement_score":0.3485927,"about_ca_system_score_codex":0.000022926844,"about_ca_system_score_gemma":0.00009403792,"threshold_uncertainty_score":0.37758794},"labels":[],"label_agreement":null},{"id":"W4417476629","doi":"10.1080/10618600.2025.2604177","title":"Renewable <i>ℓ</i> <sub>1</sub> -Regularized Linear Support Vector Machine with High-Dimensional Streaming Data","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Alberta Machine Intelligence Institute","keywords":"Support vector machine; Streaming data; Renewable energy; Minification; Data modeling","score_opus":0.007795108113412392,"score_gpt":0.24243370699554276,"score_spread":0.23463859888213037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417476629","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":[0.06671721,0.000106001185,0.92992586,0.0028108286,0.00019685086,0.000050567378,0.00013948751,0.0000225663,0.000030650142],"genre_scores_gemma":[0.61061954,0.000024134839,0.3885487,0.0005242056,0.000073613715,6.19484e-7,0.00014752602,0.000007114124,0.000054573957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984242,0.000105133935,0.00042933898,0.0002692934,0.0005807209,0.00019136883],"domain_scores_gemma":[0.9982815,0.00067428994,0.00028659037,0.00022573644,0.00037425928,0.00015765794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004847609,0.00015986968,0.00030675242,0.0002057749,0.00021134953,0.00012098222,0.00049417256,0.00005523305,0.0000061515275],"category_scores_gemma":[0.0001420714,0.00011742691,0.00003559851,0.0004230157,0.00011210124,0.0002547438,0.00025698415,0.00030037656,0.0000016064679],"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":[0.00077639165,0.0010978014,0.0067837704,0.0002285477,0.0008491183,0.0007781809,0.00014097436,0.35672852,0.0011911071,0.40760705,0.036339596,0.18747893],"study_design_scores_gemma":[0.0021749795,0.0005294299,0.044391662,0.00011056546,0.0000893593,0.00030844423,0.000003470239,0.8475779,0.00014624964,0.10209865,0.002347568,0.00022168671],"about_ca_topic_score_codex":0.000052192165,"about_ca_topic_score_gemma":0.000024562576,"teacher_disagreement_score":0.54390234,"about_ca_system_score_codex":0.000014564694,"about_ca_system_score_gemma":0.00029635837,"threshold_uncertainty_score":0.47885305},"labels":[],"label_agreement":null},{"id":"W7092458970","doi":"10.1080/10618600.2025.2574532","title":"Reproducing Kernel-Based Semiparametric Functional Smoothed Score Estimation with Binary Responses","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Alberta Machine Intelligence Institute","keywords":"Binary data; Binary number; Estimation; Covariate; Functional data analysis; Semiparametric model; Estimation theory; Pattern recognition (psychology)","score_opus":0.027921344379577596,"score_gpt":0.3138558903931978,"score_spread":0.28593454601362017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7092458970","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":[0.2726678,0.00019957595,0.7252274,0.0011310154,0.00032476598,0.00008051725,0.00004222639,0.00001352016,0.00031314243],"genre_scores_gemma":[0.931638,0.00000894851,0.06738128,0.0005891354,0.000073772964,0.0000036446645,0.00006238447,0.000007391609,0.00023542761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9988424,0.00015799701,0.00041589417,0.0001775258,0.0002984863,0.00010766773],"domain_scores_gemma":[0.9977816,0.0012465154,0.0002825833,0.000069860114,0.0005414889,0.00007799859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043238362,0.00010500852,0.00018057512,0.000606771,0.00013357353,0.000039648803,0.0000480031,0.000067972265,0.0001516529],"category_scores_gemma":[0.00035309492,0.00008133358,0.000046017176,0.0005991205,0.0001472525,0.00006552922,0.0000090682925,0.00024216948,0.000004319863],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011116544,0.0020473131,0.08460428,0.000327638,0.0009519584,0.00037998307,0.00043487462,0.18823053,0.00015106898,0.38616776,0.040145088,0.28544295],"study_design_scores_gemma":[0.0021243982,0.0006896845,0.8087396,0.00017060358,0.00012135278,0.00016105024,0.000058990332,0.03231191,0.000017774684,0.15517832,0.00030305792,0.00012327044],"about_ca_topic_score_codex":0.0000059284653,"about_ca_topic_score_gemma":0.000001928798,"teacher_disagreement_score":0.7241353,"about_ca_system_score_codex":0.000023112154,"about_ca_system_score_gemma":0.00016327777,"threshold_uncertainty_score":0.3316687},"labels":[],"label_agreement":null}]}