{"meta":{"query_hash":"fb1763f2f70b","filters":{"venue":"Journal of Data Science"},"cohort_total":25,"direct_labels_cover":0,"predictions_cover":25,"exported":25,"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/fb1763f2f70b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Data+Science"},"results":[{"id":"W2181556329","doi":"10.6339/jds.2004.02(1).135","title":"The Poisson Inverse Gaussian Regression Model in the Analysis of Clustered Counts Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph; Western University","funders":"","keywords":"Poisson regression; Statistics; Mathematics; Covariate; Poisson distribution; Negative binomial distribution; Count data; Inverse Gaussian distribution; Regression analysis; Generalized linear model; Regression; Distribution (mathematics); Population","score_opus":0.14271075028666894,"score_gpt":0.3991228810900525,"score_spread":0.25641213080338354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181556329","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":[0.0017344581,0.00034055187,0.9936621,0.0032400773,0.00017695322,0.000026887014,0.000037116144,0.0000016578662,0.0007802075],"genre_scores_gemma":[0.26982984,0.00061326375,0.7287197,0.0006596601,0.000052257717,2.553277e-7,0.000012588888,0.0000030717015,0.00010935409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998357,0.00019007717,0.0003165695,0.0002591974,0.0007285899,0.00014853853],"domain_scores_gemma":[0.9967541,0.00016867107,0.00031473153,0.0025514376,0.00015762282,0.000053413267],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0066403393,0.00005603813,0.00015542268,0.00016554294,0.00013945352,0.00021011638,0.008004703,0.00002205919,0.0000036298266],"category_scores_gemma":[0.00043516792,0.000026368043,0.000034607085,0.002247252,0.00020502036,0.0020396756,0.0014957784,0.00018001696,8.720458e-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":[0.000055887882,0.0004171719,0.0009515773,0.000031946693,0.000273274,0.0003326146,0.0058833207,0.0034025365,0.016124416,0.10482712,0.07292892,0.7947712],"study_design_scores_gemma":[0.00008878438,0.000008989372,0.0009495883,0.000031967927,0.000051236282,0.000034728917,0.00007699144,0.99320066,0.00014991783,0.0035197514,0.0018475626,0.000039794442],"about_ca_topic_score_codex":0.0000075371745,"about_ca_topic_score_gemma":0.00006124757,"teacher_disagreement_score":0.9897981,"about_ca_system_score_codex":0.000018955157,"about_ca_system_score_gemma":0.00055228936,"threshold_uncertainty_score":0.9973625},"labels":[],"label_agreement":null},{"id":"W2181591901","doi":"10.6339/jds.2008.06(3).508","title":"Evaluating Aortic Stenosis Using the Archimedean Copula Methodology","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods and Inference","field":"Mathematics","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":"University of Northern British Columbia","funders":"","keywords":"Copula (linguistics); Stenosis; China; Statistics; Econometrics; Actuarial science; Mathematics; Medicine; Cardiology; Internal medicine; Business; Geography","score_opus":0.8478728438504952,"score_gpt":0.6353580343979097,"score_spread":0.2125148094525855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181591901","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":[0.2971866,0.00007152477,0.7017448,0.00044673117,0.00032753104,0.00003935173,0.000017769904,0.0000029578496,0.0001627156],"genre_scores_gemma":[0.08308332,0.000017505914,0.91661817,0.00015971443,0.00010530475,2.5093644e-7,4.3495123e-7,0.000004985994,0.000010332457],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972565,0.00093370496,0.0005566085,0.00021716338,0.0007884051,0.00024760966],"domain_scores_gemma":[0.9914322,0.006620479,0.0004963205,0.00076472096,0.0005719274,0.00011435763],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01583181,0.00007505135,0.00025524193,0.0000680932,0.00026941017,0.00012134124,0.0014135359,0.00002106633,0.00012447861],"category_scores_gemma":[0.06214725,0.000043646345,0.000037348535,0.0005804625,0.0006242409,0.00045787237,0.00065320154,0.00028191748,0.0000015830955],"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":[0.00003319631,0.00017849432,0.001964483,0.0000840271,0.00007553044,0.00010998802,0.0016423019,0.00008167928,0.37904656,0.193218,0.000533426,0.4230323],"study_design_scores_gemma":[0.00044226198,0.00029636626,0.0054073837,0.00031218724,0.0003702934,0.0010166261,0.0026955642,0.17537323,0.019441752,0.7942369,0.00017351912,0.000233909],"about_ca_topic_score_codex":0.0000086519185,"about_ca_topic_score_gemma":0.0000017976536,"teacher_disagreement_score":0.6010189,"about_ca_system_score_codex":0.000040209143,"about_ca_system_score_gemma":0.00078956195,"threshold_uncertainty_score":0.9457527},"labels":[],"label_agreement":null},{"id":"W2182961570","doi":"10.6339/jds.2004.02(1).142","title":"A Two-Stage Bayesian Model for Predicting Winners in Major League Baseball","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":43,"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; Korea Science and Engineering Foundation","keywords":"League; Markov chain Monte Carlo; Bayesian probability; Bayesian inference; Computer science; Econometrics; Field (mathematics); Markov chain; Inference; Artificial intelligence; Operations research; Machine learning; Mathematics","score_opus":0.09328473143994379,"score_gpt":0.3027483287623079,"score_spread":0.2094635973223641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182961570","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":[0.47063914,0.0016032779,0.5171114,0.0021175328,0.0009229393,0.00017856243,0.0014207949,0.000008174851,0.0059981784],"genre_scores_gemma":[0.9789901,0.00018706206,0.0197134,0.0002622072,0.00012112241,9.3343874e-7,0.000014741066,0.000007786875,0.0007026966],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985933,0.0000030586737,0.0007177817,0.0003144714,0.000099557605,0.0002718539],"domain_scores_gemma":[0.9987273,0.000036443806,0.00054940884,0.00046124385,0.00011644331,0.00010911091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030902806,0.00007657336,0.00025696415,0.0003067024,0.00011096227,0.0001507452,0.00088677206,0.000025820913,0.00010699957],"category_scores_gemma":[0.00038650064,0.000077381934,0.000054564265,0.0005636302,0.00011364603,0.0020630967,0.00018162443,0.00015969356,0.0000037309314],"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":[0.00009410277,0.00037724408,0.5565434,0.00013831054,0.000063139145,0.00017854365,0.0014093777,0.30243644,0.0011179015,0.13070527,0.0035514235,0.0033848248],"study_design_scores_gemma":[0.0005843013,0.000027319003,0.0032034528,0.00003651033,0.0000045132247,0.000020583191,0.00015868049,0.9902189,0.00008116342,0.0010947877,0.0044711656,0.00009862907],"about_ca_topic_score_codex":0.000055067216,"about_ca_topic_score_gemma":0.0001832306,"teacher_disagreement_score":0.68778247,"about_ca_system_score_codex":0.00008306821,"about_ca_system_score_gemma":0.00035045555,"threshold_uncertainty_score":0.31555435},"labels":[],"label_agreement":null},{"id":"W2185241920","doi":"10.6339/jds.201101_09(1).0005","title":"Estimating Transmissibility of Seasonal Influenza Virus by Surveillance Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada","keywords":"Transmissibility (structural dynamics); Outbreak; Estimation; Transmission (telecommunications); Flu season; Seasonal influenza; Virus; Vaccination; Influenza A virus; Virology; Statistics; Biology; Computer science; Medicine; Mathematics; Coronavirus disease 2019 (COVID-19); Disease; Engineering; Infectious disease (medical specialty)","score_opus":0.23217288171701067,"score_gpt":0.4759016103250826,"score_spread":0.24372872860807193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185241920","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":[0.97667366,0.00922522,0.008379192,0.0015135906,0.00027138388,0.00017105756,0.0032054414,0.000012221923,0.0005482211],"genre_scores_gemma":[0.85462093,0.00054552,0.1437077,0.0007272205,0.0002546216,6.0688325e-7,0.00009236294,0.000013962447,0.00003709118],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99652904,0.0001016975,0.00071063766,0.00044800996,0.0018686949,0.0003419226],"domain_scores_gemma":[0.9956803,0.00034871337,0.0003964177,0.0019343672,0.0013607328,0.00027948266],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006580694,0.000109848545,0.00042269065,0.000098464385,0.00016592798,0.00006264912,0.0022054268,0.000031395917,0.00009393124],"category_scores_gemma":[0.012021629,0.00008261368,0.00004139932,0.00089316146,0.0012022138,0.0022943218,0.0013583404,0.0003927136,0.0000039695074],"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":[0.00054154906,0.00070709956,0.21947801,0.0005746724,0.00020402581,0.00029422468,0.00045918504,0.00010555797,0.68593895,0.00003674521,0.023126021,0.06853398],"study_design_scores_gemma":[0.008539447,0.001199046,0.6130591,0.0020595037,0.00030476204,0.0019387503,0.00095681974,0.13824143,0.14434952,0.00035119255,0.08822603,0.00077442144],"about_ca_topic_score_codex":0.000039970415,"about_ca_topic_score_gemma":0.00001624939,"teacher_disagreement_score":0.54158944,"about_ca_system_score_codex":0.00007930442,"about_ca_system_score_gemma":0.0025949779,"threshold_uncertainty_score":0.9963005},"labels":[],"label_agreement":null},{"id":"W2185363721","doi":"10.6339/jds.2010.08(1).585","title":"A Bayesian Estimator of the Intracluster Correlation Coefficient from Correlated Binary Responses","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Water Quality and Resources Studies","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mathematics; Estimator; Statistics; Beta-binomial distribution; Negative binomial distribution; Poisson distribution","score_opus":0.05897463788431407,"score_gpt":0.2840856813768295,"score_spread":0.22511104349251543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185363721","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":[0.98855066,0.00019726162,0.008221807,0.0019353206,0.00057040266,0.00005614392,0.00007147002,0.0000036867254,0.00039323402],"genre_scores_gemma":[0.9958688,0.000025836436,0.0037337972,0.00013648784,0.00003112259,1.7748903e-7,0.0000036799865,0.0000030260462,0.00019707288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99825865,0.00016071879,0.00039787363,0.00021001624,0.0008216094,0.00015111337],"domain_scores_gemma":[0.9987224,0.0002173837,0.00039048566,0.0005382271,0.000059748832,0.00007176922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012935211,0.000071197486,0.00014340546,0.000039090748,0.000310807,0.000047011086,0.0011817707,0.000031343592,0.00023468617],"category_scores_gemma":[0.0008117645,0.000041417024,0.000040780793,0.0007065236,0.0014287444,0.0007823008,0.0014650857,0.000181962,0.0000182453],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005959272,0.0011975802,0.4711885,0.0000345871,0.00011168209,0.0002695934,0.016273785,0.10371444,0.37138245,0.00018887768,0.022670213,0.012372384],"study_design_scores_gemma":[0.00089523377,0.00022155965,0.7749177,0.00037145044,0.000131253,0.00029800256,0.0029213096,0.18336922,0.024814153,0.00045974262,0.011338327,0.00026203846],"about_ca_topic_score_codex":0.000074030235,"about_ca_topic_score_gemma":0.000025549984,"teacher_disagreement_score":0.3465683,"about_ca_system_score_codex":0.000075022384,"about_ca_system_score_gemma":0.00013071347,"threshold_uncertainty_score":0.5264268},"labels":[],"label_agreement":null},{"id":"W2188439980","doi":"10.6339/jds.201404_12(2).0008","title":"SENSITIVITY ANALYSIS OF BAYES FACTOR FOR CATEGORICAL DATA WITH EMPHASIS ON SPARSE MULTINOMIAL DATA","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Newfoundland and Labrador","funders":"","keywords":"Categorical variable; Multinomial distribution; Contingency table; Bayes factor; Prior probability; Dirichlet distribution; Computer science; Bayes' theorem; Bayesian probability; Sensitivity (control systems); Context (archaeology); Econometrics; Statistics; Consistency (knowledge bases); Factor analysis; Data mining; Mathematics; Artificial intelligence; Machine learning","score_opus":0.2991029132364069,"score_gpt":0.4089341009435077,"score_spread":0.10983118770710076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188439980","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":[0.9264234,0.00007049247,0.048880424,0.0012219539,0.00014474858,0.00008689805,0.023129797,0.000005622992,0.000036665686],"genre_scores_gemma":[0.93284047,0.000046442492,0.06588476,0.000093781404,0.00017163267,1.6464159e-7,0.0009511833,7.02193e-7,0.0000108414615],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9975293,0.00026316437,0.00048941793,0.0007221811,0.00075130153,0.00024458134],"domain_scores_gemma":[0.995061,0.0027785276,0.00045624145,0.0009969957,0.00051050115,0.00019674373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034398488,0.00011987759,0.0005418054,0.00007034904,0.00020664577,0.00014066383,0.0025017892,0.000040334922,0.00015225871],"category_scores_gemma":[0.005224105,0.000042433738,0.00007595112,0.002108755,0.00039652758,0.0013331083,0.000993519,0.00013922463,9.408042e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048686296,0.0008458038,0.015095707,0.000013753,0.0009269539,0.00021069178,0.00006567787,0.00032549506,0.2993062,0.00052233285,0.0011470777,0.68105346],"study_design_scores_gemma":[0.0006302563,0.0010172905,0.6311952,0.0000463446,0.00314434,0.00013382838,0.0008636329,0.33530596,0.011787885,0.000121636476,0.015279877,0.00047373382],"about_ca_topic_score_codex":0.00010948977,"about_ca_topic_score_gemma":0.0010528327,"teacher_disagreement_score":0.6805797,"about_ca_system_score_codex":0.000019731144,"about_ca_system_score_gemma":0.00013119506,"threshold_uncertainty_score":0.62541187},"labels":[],"label_agreement":null},{"id":"W2189164006","doi":"10.6339/jds.2004.02(2).144","title":"Wavelet Analysis of Tide-affected Low Streamflows Series","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Series (stratigraphy); Streamflow; Wavelet; Environmental science; Quantile; Flow (mathematics); Noise (video); Frequency domain; Wavelet transform; Geology; Mathematics; Statistics; Computer science; Geography; Mathematical analysis; Drainage basin","score_opus":0.04068391126091666,"score_gpt":0.33389003210052914,"score_spread":0.2932061208396125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189164006","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":[0.1713868,0.00026870487,0.8268139,0.0005225147,0.00042519404,0.000026784326,0.000047732534,0.000011287652,0.00049710064],"genre_scores_gemma":[0.33959916,0.00012984584,0.65999687,0.00013085066,0.00004395191,1.2939526e-7,0.000008598392,0.0000032099067,0.000087365566],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977916,0.00019186764,0.0004915312,0.000335744,0.0009571777,0.00023206798],"domain_scores_gemma":[0.9969163,0.00018578439,0.0004531297,0.0013409372,0.0009694245,0.00013440382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033611364,0.00009132154,0.00037662347,0.00057068747,0.00012924075,0.00031300762,0.003586734,0.000026325408,0.000029161485],"category_scores_gemma":[0.0012263267,0.000071958195,0.00011271378,0.006106427,0.00033501824,0.007973767,0.0009420873,0.00015792828,0.0000025445559],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039756498,0.00039652293,0.001483463,0.000047366826,0.0006112453,0.0010953377,0.0009813667,0.0017183117,0.8042411,0.007310686,0.0017129821,0.18036182],"study_design_scores_gemma":[0.0010760337,0.00047683995,0.07205319,0.00023443035,0.0008708742,0.0011890993,0.000249233,0.23347232,0.6856671,0.0015829543,0.002621515,0.000506452],"about_ca_topic_score_codex":0.00001525909,"about_ca_topic_score_gemma":0.000017973296,"teacher_disagreement_score":0.231754,"about_ca_system_score_codex":0.00003110023,"about_ca_system_score_gemma":0.0008881874,"threshold_uncertainty_score":0.66651034},"labels":[],"label_agreement":null},{"id":"W2190667587","doi":"10.6339/jds.2003.01(2).131","title":"Analysis of Unbalanced Microarray Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Microarray analysis techniques; China; Data science; Microarray databases; Library science; Data analysis; Data mining; Computer science; Statistics; Political science; Mathematics; Biology; Gene","score_opus":0.06929950204773849,"score_gpt":0.36920503824217027,"score_spread":0.2999055361944318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2190667587","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":[0.9524938,0.0028713918,0.042043988,0.00086890924,0.00043761314,0.000035631183,0.0005520707,0.0000016560972,0.0006949537],"genre_scores_gemma":[0.99228954,0.0006030778,0.006496013,0.00010861062,0.00006910665,1.0159069e-7,0.00034228005,0.000002000958,0.00008928684],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991241,0.00002735226,0.0002364811,0.00026395786,0.00026611768,0.00008195655],"domain_scores_gemma":[0.9977617,0.000006508385,0.00028490424,0.0015523039,0.0003350336,0.000059538062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007697123,0.000039156734,0.00011722371,0.00011334444,0.000037087626,0.00002697405,0.0018077868,0.00002374832,0.000029959701],"category_scores_gemma":[0.0003418654,0.000031434825,0.00003203641,0.0009511275,0.00017053755,0.000044553697,0.0006426651,0.000044002532,5.3815785e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000107488895,0.000029627983,0.0030650818,0.0000022657114,0.00006434225,0.0000013892551,0.000009616234,0.000040514806,0.9890066,0.000010203807,0.004068903,0.0036907045],"study_design_scores_gemma":[0.00024495603,0.000047224323,0.030266652,0.00001615716,0.00021965992,0.000025648542,0.00022744513,0.0013294232,0.8843977,0.000007971822,0.08314189,0.000075260235],"about_ca_topic_score_codex":0.0000016812022,"about_ca_topic_score_gemma":0.000008907719,"teacher_disagreement_score":0.10460889,"about_ca_system_score_codex":0.000006355207,"about_ca_system_score_gemma":0.0005758295,"threshold_uncertainty_score":0.33593476},"labels":[],"label_agreement":null},{"id":"W2514070870","doi":"10.6339/jds.201604_14(2).0002","title":"Comparing Pre-Post Change Across Groups: Guidelines for Choosing between Difference Scores, ANCOVA, and Residual Change Scores","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":60,"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":"Analysis of covariance; Residual; Statistics; Significant difference; Psychology; Mathematics","score_opus":0.732100748033184,"score_gpt":0.5505718425854673,"score_spread":0.18152890544771672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514070870","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":[0.9079538,0.0012290069,0.08835369,0.0013561689,0.00018859477,0.00040302964,0.00045280685,0.00005559841,0.0000073283904],"genre_scores_gemma":[0.6879482,0.0005213979,0.31016865,0.00027050357,0.0010131341,0.000016188449,0.00003118515,0.000020696067,0.000010015403],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973553,0.000052430434,0.00082772836,0.0004925734,0.0007447835,0.00052721746],"domain_scores_gemma":[0.9959034,0.0006640108,0.00076882495,0.00072143256,0.0017286022,0.00021373235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029668652,0.00021629126,0.0005489197,0.00016101132,0.0003989036,0.00037794985,0.0015865645,0.00007019262,0.0000028475483],"category_scores_gemma":[0.0063472423,0.00017372421,0.00004289964,0.0004975356,0.00064790697,0.004406527,0.0015209322,0.00029914785,5.524422e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003279537,0.00050902483,0.4392118,0.001786777,0.00017111636,0.00020049427,0.012501156,0.000003955518,0.17716405,0.023382071,0.005195928,0.3395457],"study_design_scores_gemma":[0.0027998954,0.0015441752,0.6957232,0.009362725,0.00035919074,0.0010939627,0.003352721,0.0059393556,0.09026293,0.18566373,0.0021834124,0.0017147146],"about_ca_topic_score_codex":0.000045947396,"about_ca_topic_score_gemma":0.0002020703,"teacher_disagreement_score":0.33783096,"about_ca_system_score_codex":0.00008516822,"about_ca_system_score_gemma":0.000196058,"threshold_uncertainty_score":0.75987005},"labels":[],"label_agreement":null},{"id":"W2564423956","doi":"10.6339/jds.201407_12(3).0001","title":"Factorial ANOVA with unbalanced data: A fresh look at the types of sums of squares","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"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":"Confusion; Factorial; Factorial analysis; Analysis of variance; Statistics; Type (biology); Econometrics; Mathematics; Factorial experiment; Explained sum of squares; Lack-of-fit sum of squares; Generalized least squares; Computer science; Arithmetic; Psychology; Non-linear least squares","score_opus":0.7074570963113356,"score_gpt":0.5968141994031163,"score_spread":0.11064289690821927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564423956","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55755675,0.0008891036,0.4217253,0.0019054568,0.0059185424,0.0005733939,0.009597329,0.000018548455,0.0018155571],"genre_scores_gemma":[0.20522629,0.0000989788,0.79411256,0.000044310444,0.00045632612,3.2227874e-7,0.00000754377,0.000009523447,0.00004416821],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970808,0.00030091076,0.0009388548,0.0002832031,0.0012210042,0.00017520972],"domain_scores_gemma":[0.9769497,0.018956238,0.001209696,0.002039701,0.0007513733,0.00009330993],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007997203,0.00008831879,0.0005194033,0.000047902267,0.000070435955,0.000044924593,0.002866848,0.00004080647,0.00022160732],"category_scores_gemma":[0.11479868,0.00004559166,0.0000371144,0.00060632377,0.0014719588,0.0006638664,0.0014303633,0.00021942417,0.0000019082518],"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":[0.004687378,0.0024142563,0.036660336,0.0014186723,0.0012628728,0.0005066034,0.0016824164,0.00010755562,0.5707844,0.17813545,0.15383235,0.04850769],"study_design_scores_gemma":[0.0068426738,0.0022103528,0.010255878,0.0019791613,0.0011855724,0.00044950724,0.0014986453,0.0015431829,0.37851304,0.58486634,0.010013839,0.00064180285],"about_ca_topic_score_codex":0.00001093551,"about_ca_topic_score_gemma":0.00005547603,"teacher_disagreement_score":0.4067309,"about_ca_system_score_codex":0.00002700373,"about_ca_system_score_gemma":0.0007903302,"threshold_uncertainty_score":0.89265776},"labels":[],"label_agreement":null},{"id":"W3047907238","doi":"10.6339/jds.202007_18(3).0015","title":"COVID-19 Fatality: A Cross-Sectional Study using Adaptive Lasso Penalized Sliced Inverse Regression","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"COVID-19 epidemiological studies","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":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Case fatality rate; Lasso (programming language); Coronavirus disease 2019 (COVID-19); Outbreak; Feature selection; Regression; Pandemic; Regression analysis; Population; Statistics; Medicine; Computer science; Disease; Mathematics; Infectious disease (medical specialty); Virology; Artificial intelligence; Environmental health; Internal medicine","score_opus":0.723200934496076,"score_gpt":0.58094962354606,"score_spread":0.14225131095001609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047907238","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":[0.978149,0.00010888088,0.019991595,0.0008857669,0.00040891374,0.00021389374,0.000121956444,0.000024664321,0.00009530933],"genre_scores_gemma":[0.93557113,0.000048059817,0.06258841,0.0014752164,0.00022657671,0.0000020881507,0.000005269304,0.000009858567,0.00007340601],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99598503,0.0005573085,0.0010058298,0.0006044346,0.0014957295,0.00035165844],"domain_scores_gemma":[0.9934072,0.003213124,0.0011587131,0.0008723917,0.00087720103,0.0004713965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011724955,0.0001765539,0.0005421838,0.00016403758,0.000818791,0.00021350264,0.0015720829,0.000062374536,0.00021457404],"category_scores_gemma":[0.09476079,0.0001169835,0.00010881764,0.0010918395,0.0008968957,0.0018994722,0.00243331,0.000415446,0.000006140687],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000654063,0.0017067977,0.9625285,0.00013624097,0.00028573145,0.0012827613,0.0022457212,0.0005061773,0.0175616,0.0037744988,0.008964414,0.00035345947],"study_design_scores_gemma":[0.011637725,0.0016345684,0.7973773,0.0005506745,0.00060444017,0.0023942012,0.016321696,0.035416234,0.0012972315,0.11613999,0.01520053,0.0014254035],"about_ca_topic_score_codex":0.00016519372,"about_ca_topic_score_gemma":0.00018558082,"teacher_disagreement_score":0.16515124,"about_ca_system_score_codex":0.0007819641,"about_ca_system_score_gemma":0.0025135202,"threshold_uncertainty_score":0.91286445},"labels":[],"label_agreement":null},{"id":"W3053629049","doi":"10.6339/jds.202007_18(3).0018","title":"Data Visualization and Descriptive Analysis for Understanding Epidemiological Characteristics of COVID-19: A Case Study of a Dataset from January 22, 2020 to March 29, 2020","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"COVID-19 epidemiological studies","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":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Case fatality rate; Epidemiology; Coronavirus disease 2019 (COVID-19); Coronavirus; Incubation period; Medicine; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Nonparametric statistics; Disease; Internal medicine; Pathology; Statistics; Psychology; Incubation; Infectious disease (medical specialty); Outbreak","score_opus":0.6960204092600549,"score_gpt":0.5511004728700827,"score_spread":0.14491993638997225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3053629049","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":[0.41419816,0.00014315719,0.5497556,0.0011391204,0.000057498608,0.0003419453,0.034358993,0.0000041211165,0.0000014183914],"genre_scores_gemma":[0.94303584,0.00026629627,0.05467123,0.0005284995,0.000081602906,0.0000039338433,0.0014052101,0.0000060328157,0.0000013301981],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9961742,0.00066558644,0.0015206164,0.0007665899,0.00060686894,0.0002661126],"domain_scores_gemma":[0.98311293,0.013207726,0.0014639706,0.0014080384,0.00043047912,0.00037683354],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01144667,0.0001721722,0.0012138326,0.0002101476,0.00026730698,0.000056798923,0.001644897,0.00005833986,0.000043919637],"category_scores_gemma":[0.14093016,0.00012315536,0.00006226088,0.0018214446,0.00053783646,0.0008630788,0.0038578848,0.00018352241,2.4100407e-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":[0.0024478224,0.0068559395,0.6735767,0.0014055922,0.0063562854,0.008175047,0.016528027,0.00060818007,0.008603422,0.010540777,0.2625439,0.0023583174],"study_design_scores_gemma":[0.0096619055,0.00910592,0.18419077,0.0008614925,0.018555947,0.0024601321,0.34647304,0.29458737,0.0002420644,0.12141358,0.010251922,0.002195869],"about_ca_topic_score_codex":0.00041138649,"about_ca_topic_score_gemma":0.000803528,"teacher_disagreement_score":0.5288377,"about_ca_system_score_codex":0.00022168168,"about_ca_system_score_gemma":0.0004898361,"threshold_uncertainty_score":0.8663061},"labels":[],"label_agreement":null},{"id":"W3127126615","doi":"10.6339/21-jds997","title":"A Vine Copula Model for Climate Trend Analysis using Canadian Temperature Data","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University; Actua; University of Waterloo","funders":"","keywords":"Copula (linguistics); Vine copula; Multivariate statistics; Econometrics; Computer science; Climate change; Climate model; Data mining; Mathematics; Machine learning; Ecology","score_opus":0.24212649655141386,"score_gpt":0.3988594280744594,"score_spread":0.15673293152304554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127126615","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":[0.9908478,0.0002920107,0.000048969545,0.0033884293,0.00008786546,0.00007798778,0.005213985,0.000004599645,0.00003835001],"genre_scores_gemma":[0.9924967,0.00020817186,0.005444326,0.00021367092,0.00023835557,5.0451604e-7,0.0012980847,6.168258e-7,0.00009953432],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793637,0.00004202181,0.00036333624,0.00046590387,0.0006473073,0.0005450504],"domain_scores_gemma":[0.99824005,0.00009729605,0.00016223056,0.0003379933,0.0006374868,0.0005249235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015498562,0.00011187207,0.0002710157,0.00006695727,0.0006614571,0.00050461304,0.0025868276,0.000053948414,0.00009985681],"category_scores_gemma":[0.00070837425,0.000036520145,0.00009039604,0.0025536697,0.00019155559,0.0026448998,0.0007191066,0.00018132468,0.0000017177944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024804925,0.000058910937,0.0016409161,0.000010526786,0.00009077259,0.00006075107,0.000080454105,0.0006944499,0.980514,0.00007999948,0.0023743345,0.014370073],"study_design_scores_gemma":[0.00032805244,0.00018904473,0.031909443,0.000084292034,0.0006538999,0.0003198465,0.0016595346,0.9442412,0.0052969,0.000091405636,0.014783995,0.00044234723],"about_ca_topic_score_codex":0.0025848995,"about_ca_topic_score_gemma":0.17926814,"teacher_disagreement_score":0.9752171,"about_ca_system_score_codex":0.000088301706,"about_ca_system_score_gemma":0.00039377826,"threshold_uncertainty_score":0.8357081},"labels":[],"label_agreement":null},{"id":"W3135587851","doi":"10.6339/jds.201807_16(3).0002","title":"Minimum Profile Hellinger Distance Estimation for A Two-Sample Location-Shifted Model","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Hellinger distance; Nonparametric statistics; Parametric statistics; Robustness (evolution); Mathematics; Asymptotic distribution; Parametric model; Statistics; Semiparametric regression; Sample size determination; Consistency (knowledge bases); Estimation theory; Applied mathematics; Semiparametric model; Estimator","score_opus":0.24353646812470423,"score_gpt":0.46553765814242265,"score_spread":0.22200119001771842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135587851","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":[0.004180179,0.000071174596,0.99468404,0.00033468695,0.00014834388,0.0001051634,0.0003616832,0.0000062281792,0.0001084936],"genre_scores_gemma":[0.08543681,0.000009065781,0.91435754,0.00006460801,0.00005876124,0.0000037941652,0.000016599059,0.000005943924,0.000046845853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986331,0.00003596408,0.0004513132,0.00022547429,0.00046844513,0.00018571343],"domain_scores_gemma":[0.9961177,0.0017923337,0.00035917998,0.0004948264,0.00112853,0.00010742758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020111043,0.00007416882,0.0001832401,0.00005812961,0.00014501472,0.0001281328,0.0006955267,0.000020482394,0.00003593604],"category_scores_gemma":[0.022784108,0.000058785423,0.000024884224,0.0005022013,0.00021144243,0.0009751854,0.00012114995,0.00010140751,0.0000021903124],"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":[0.000087505585,0.00041582898,0.00008809698,0.00033373717,0.000025027615,0.000010854034,0.0006151959,0.0033797855,0.0148665635,0.8967551,0.00558013,0.07784216],"study_design_scores_gemma":[0.00018143088,0.00003112304,0.000025552117,0.00008025086,0.00001978907,0.00001051877,0.000044731147,0.6520442,0.002906324,0.34448746,0.00011307882,0.000055556702],"about_ca_topic_score_codex":0.0000017945302,"about_ca_topic_score_gemma":0.000003887304,"teacher_disagreement_score":0.6486644,"about_ca_system_score_codex":0.000043106767,"about_ca_system_score_gemma":0.0008099211,"threshold_uncertainty_score":0.9854474},"labels":[],"label_agreement":null},{"id":"W3136368678","doi":"10.6339/jds.201407_12(3).0007","title":"Copulas Applications in Estimating Value-at-Risk (VaR): Iranian Crude Oil Prices","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","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 Northern British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Economics; Econometrics; Crude oil; Normality; Risk management; Petroleum; Value at risk; Profit (economics); Multivariate statistics; Financial economics; Finance; Statistics; Microeconomics; Mathematics; Engineering","score_opus":0.07526248261515965,"score_gpt":0.3051591706552883,"score_spread":0.22989668804012864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136368678","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":[0.8797281,0.0026834651,0.115186915,0.0003124041,0.00032925725,0.00004127573,0.00023210731,0.0000060543807,0.0014804318],"genre_scores_gemma":[0.8350365,0.0006104063,0.1640917,0.0000575311,0.00013247592,0.0000015797715,0.000010996891,0.0000069233274,0.0000518883],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984019,0.000013315241,0.00084378134,0.00037253875,0.00012793043,0.00024053332],"domain_scores_gemma":[0.99830973,0.00010017346,0.00079221977,0.0005944596,0.00010763788,0.00009577288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002844356,0.000082244216,0.00027174913,0.00024967888,0.00030153827,0.0001440799,0.0010794,0.00003873107,0.000035969882],"category_scores_gemma":[0.0013839018,0.00008580221,0.000045078286,0.0009456638,0.00015283618,0.0017754177,0.00039424497,0.0002422709,0.000033488344],"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":[0.000030934683,0.0005216552,0.8327982,0.00012903743,0.000027632048,0.00004616056,0.002716323,0.020903602,0.0016273545,0.07522748,0.00042095018,0.06555066],"study_design_scores_gemma":[0.0007928425,0.00006226862,0.18190026,0.00016600956,0.00001926362,0.00007092435,0.0003668892,0.7504246,0.00044636143,0.029658327,0.035707887,0.00038433622],"about_ca_topic_score_codex":0.00017806531,"about_ca_topic_score_gemma":0.000114177594,"teacher_disagreement_score":0.72952104,"about_ca_system_score_codex":0.00016037728,"about_ca_system_score_gemma":0.00023516355,"threshold_uncertainty_score":0.34989125},"labels":[],"label_agreement":null},{"id":"W3138069980","doi":"10.6339/jds.201207_10(3).0006","title":"A Data Mining Approach to Comparing American and Canadian Grade 10 Students’ PISA Science Test Performance","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":20,"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":"Test (biology); Academic achievement; Mathematics education; Achievement test; Psychology; Political science; Standardized test","score_opus":0.10987572929409287,"score_gpt":0.36575051924651825,"score_spread":0.2558747899524254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138069980","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":[0.97201276,0.0001083208,0.022040337,0.0044338745,0.00027791547,0.000056165976,0.000051054354,0.000019426603,0.0010001528],"genre_scores_gemma":[0.75658125,0.00003571608,0.24288927,0.00035210053,0.000079641904,1.4205719e-7,0.00000521869,0.0000035382968,0.000053120937],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968207,0.0000318846,0.0003520878,0.00078556495,0.0014486061,0.00056118966],"domain_scores_gemma":[0.99640733,0.00010282062,0.00027270467,0.0019849495,0.00040815127,0.0008240441],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0043240734,0.00011948337,0.00024793137,0.0005661916,0.0007169619,0.0017089177,0.013607549,0.000012461835,0.0000015847199],"category_scores_gemma":[0.0017209238,0.000103890525,0.000012566834,0.004309228,0.0010978885,0.005762088,0.005574811,0.0002825989,0.0000057993834],"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":[0.0000062567237,0.0006922846,0.84627944,0.00005394688,0.000034250643,0.00023290532,0.0030461443,0.002528361,0.0062564295,0.0009613115,0.0055822493,0.13432641],"study_design_scores_gemma":[0.00019843574,0.00016129487,0.17443843,0.00011322902,0.000015476287,0.0006936764,0.0008877355,0.81445986,0.00013650181,0.00000920536,0.008658362,0.00022781496],"about_ca_topic_score_codex":0.00069059245,"about_ca_topic_score_gemma":0.0011221764,"teacher_disagreement_score":0.8119315,"about_ca_system_score_codex":0.00012106662,"about_ca_system_score_gemma":0.0033985444,"threshold_uncertainty_score":0.9993274},"labels":[],"label_agreement":null},{"id":"W3157762174","doi":"10.6339/21-jds993","title":"Testing for COVID-19: Some Statistical Issues","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"SARS-CoV-2 detection and testing","field":"Medicine","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; Canada Research Chairs","keywords":"Coronavirus disease 2019 (COVID-19); Coronavirus; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Test (biology); Computer science; Statistical hypothesis testing; Statistical analysis; Statistics; Virology; Medicine; Mathematics; Outbreak; Biology","score_opus":0.27624816157876786,"score_gpt":0.47801977626905207,"score_spread":0.2017716146902842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157762174","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71394646,0.0017869961,0.2662633,0.014402199,0.0017669149,0.0003237295,0.00029233724,0.000088493696,0.0011295691],"genre_scores_gemma":[0.433285,0.000009509319,0.5568482,0.00892177,0.00085740665,9.675399e-7,0.000009089345,0.000010199902,0.00005780367],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99882346,0.00001928143,0.00030635696,0.00020086375,0.00046661825,0.00018343117],"domain_scores_gemma":[0.9979582,0.0008144599,0.0001840356,0.00030106795,0.00052361656,0.00021864678],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017770403,0.00005431661,0.00016404697,0.0001151627,0.00019391516,0.00008955463,0.0003262788,0.000018334384,0.000028096701],"category_scores_gemma":[0.059190117,0.000042727694,0.000021042566,0.0005150358,0.00027121985,0.0008601853,0.00014699076,0.00015018259,0.000005294452],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043840682,0.00009071966,0.004816713,0.00008566799,0.000013003304,0.0005050303,0.00009698358,0.0000043271634,0.96263057,0.0012564308,0.0054410575,0.025015676],"study_design_scores_gemma":[0.0057061706,0.0022125242,0.01779018,0.00069051515,0.0003481931,0.029241433,0.001911423,0.04889923,0.5755649,0.009894229,0.3072731,0.00046810214],"about_ca_topic_score_codex":0.000011486541,"about_ca_topic_score_gemma":0.0000023056791,"teacher_disagreement_score":0.38706565,"about_ca_system_score_codex":0.00007570266,"about_ca_system_score_gemma":0.0020084095,"threshold_uncertainty_score":0.9487347},"labels":[],"label_agreement":null},{"id":"W3215602957","doi":"10.6339/22-jds1047","title":"A Review on Graph Neural Network Methods in Financial Applications","year":2022,"lang":"en","type":"review","venue":"Journal of Data Science","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":122,"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":"Institute for Catastrophic Loss Reduction","keywords":"Computer science; Graph; Categorization; Artificial neural network; Financial modeling; Data mining; Data science; Finance; Artificial intelligence; Theoretical computer science; Business","score_opus":0.19864865051033517,"score_gpt":0.48307997417449006,"score_spread":0.2844313236641549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215602957","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1535014e-8,0.78103435,0.21731248,0.00014285989,0.0008427524,0.00055868377,0.000020196643,0.000015973186,0.000072693496],"genre_scores_gemma":[4.259521e-8,0.7644638,0.23416394,0.0010173429,0.0002775799,0.000049837887,0.000011313764,0.000011980042,0.000004180936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99491334,0.0007972986,0.0016112874,0.0010107316,0.001032551,0.0006348083],"domain_scores_gemma":[0.99323416,0.0012003831,0.0022461063,0.0029675548,0.00011172056,0.00024008087],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.008679627,0.00036936134,0.0016223742,0.00077386305,0.0003662109,0.00016832493,0.017546333,0.00007852393,0.000017206845],"category_scores_gemma":[0.000818335,0.00027700153,0.0003575596,0.012282567,0.00037228272,0.002926539,0.003467009,0.0019471283,0.0000054320312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.706417e-7,0.00003529955,3.5587598e-7,0.0011483269,0.0000043183254,0.00003809642,0.0000031379336,0.00027883786,8.9073026e-8,0.0027818505,0.0043709483,0.9913378],"study_design_scores_gemma":[0.0000603741,0.00010714198,0.0000026814407,0.011732688,0.00007091598,0.0005201115,5.2828335e-7,0.00076597265,4.3511346e-8,0.002017345,0.9844719,0.00025026314],"about_ca_topic_score_codex":0.0000010980832,"about_ca_topic_score_gemma":0.0000020197917,"teacher_disagreement_score":0.9910875,"about_ca_system_score_codex":0.00019283804,"about_ca_system_score_gemma":0.0014344838,"threshold_uncertainty_score":0.99996823},"labels":[],"label_agreement":null},{"id":"W4210580103","doi":"10.6339/22-jds1034","title":"Computational Challenges of t and Related Copulas","year":2022,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Copula (linguistics); Skew; Quantile; Computer science; Marginal distribution; Applied mathematics; Mathematics; Econometrics; Random variable; Statistics","score_opus":0.12877524547984,"score_gpt":0.29539751068358244,"score_spread":0.16662226520374243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210580103","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":[0.98323125,0.0101037,0.0035423245,0.0011202825,0.00032644975,0.000038125236,0.00024949084,0.000002388149,0.0013859763],"genre_scores_gemma":[0.995,0.00048658712,0.004469322,0.000016846443,0.000013722943,1.6628687e-7,0.0000026408377,0.0000020522875,0.000008654887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921,0.000008585505,0.00045788984,0.00014588101,0.00009876237,0.000078873505],"domain_scores_gemma":[0.99922055,0.000041107065,0.0004800413,0.0001681381,0.00005406223,0.00003607471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025449237,0.000032049218,0.00015348759,0.0001967236,0.00014551297,0.000015214997,0.00053318735,0.00001004632,0.00004802323],"category_scores_gemma":[0.0002191208,0.000034558383,0.000017879975,0.00024492762,0.00017262084,0.00076616975,0.00032809164,0.00012402647,0.0000016680395],"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":[0.000047519487,0.00020210443,0.037323102,0.00003556937,0.000026524045,0.000011533271,0.0024583833,0.027524794,0.000109481036,0.9067809,0.00045680813,0.025023269],"study_design_scores_gemma":[0.0006950299,0.00034880513,0.117643096,0.000023051563,0.00000691378,0.00015498794,0.0006325201,0.6107587,0.000012754207,0.26071268,0.008862898,0.00014857462],"about_ca_topic_score_codex":0.000016117665,"about_ca_topic_score_gemma":0.000001020969,"teacher_disagreement_score":0.6460682,"about_ca_system_score_codex":0.00002972912,"about_ca_system_score_gemma":0.000083091,"threshold_uncertainty_score":0.140925},"labels":[],"label_agreement":null},{"id":"W4392752805","doi":"10.6339/24-jds1121","title":"Testing Perceptual Accuracy in a U.S. General Population Survey Using Stacked Bar Charts","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bar chart; Visualization; Perception; Computer science; Bar (unit); Data visualization; Information visualization; Pie chart; Population; Key (lock); Data science; Survey data collection; Human–computer interaction; Data mining; Psychology; Statistics; Mathematics; Geography","score_opus":0.24662321875917856,"score_gpt":0.4300851825046271,"score_spread":0.18346196374544851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392752805","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":[0.6868399,0.00011727346,0.31200036,0.00018574289,0.0006845215,0.000048558835,0.000069316906,0.000025007743,0.000029340048],"genre_scores_gemma":[0.924145,0.000017660717,0.075569615,0.00010625701,0.0001199243,6.949025e-8,0.000028038281,0.0000044613635,0.0000090075655],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815625,0.00010308593,0.00047459736,0.00032955027,0.0007115194,0.00022501637],"domain_scores_gemma":[0.9987277,0.0002138615,0.00019419915,0.00050385593,0.0002452486,0.00011514407],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0044902605,0.000081775885,0.00013654905,0.00048614966,0.00012405164,0.0011021567,0.0023681545,0.000020639476,0.0000128328575],"category_scores_gemma":[0.0023480628,0.000067500616,0.000018058194,0.0025367087,0.00011149725,0.0111363465,0.00073210377,0.00015900322,0.000008169129],"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":[0.000026612552,0.00051085965,0.4794505,0.00017827441,0.000049193182,0.00087338424,0.005223976,0.017497225,0.10221811,0.04809641,0.0072043827,0.33867106],"study_design_scores_gemma":[0.00007382543,0.000023752049,0.14939281,0.000100103345,0.0000032360012,0.00009645964,0.000023174045,0.8497407,0.000041393956,0.00011936153,0.00030582806,0.00007937441],"about_ca_topic_score_codex":0.0002407559,"about_ca_topic_score_gemma":0.000038428763,"teacher_disagreement_score":0.83224344,"about_ca_system_score_codex":0.00010762006,"about_ca_system_score_gemma":0.0006612935,"threshold_uncertainty_score":0.9999348},"labels":[],"label_agreement":null},{"id":"W4394949264","doi":"10.6339/24-jds1122","title":"BIE: Binary Image Encoding for the Classification of Tabular Data","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Adversarial Robustness in Machine Learning","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":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Encoding (memory); Pattern recognition (psychology); Convolutional neural network; Contextual image classification; Benchmark (surveying); Image (mathematics); Deep learning; Feature (linguistics); Field (mathematics); Binary image; Image processing; Mathematics","score_opus":0.1344438530442302,"score_gpt":0.40138674335794516,"score_spread":0.266942890313715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394949264","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":[0.0016566869,0.0008709146,0.99142015,0.0044632624,0.0013163311,0.00009583672,0.000049009144,0.000018592984,0.000109201406],"genre_scores_gemma":[0.653806,0.00013248395,0.34567735,0.000043452364,0.00030189648,7.7719505e-7,0.000009957498,0.0000064667315,0.000021634034],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981767,0.000052231102,0.00041348176,0.00041331418,0.00075070024,0.0001935754],"domain_scores_gemma":[0.9963021,0.0008389234,0.00036980442,0.0021874225,0.00024168774,0.00006004443],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.007706206,0.00007802618,0.00013078842,0.00024355145,0.00028113867,0.00050188496,0.013248257,0.000022077644,0.0000061152728],"category_scores_gemma":[0.0020508447,0.00004887885,0.000032903674,0.0013129638,0.0004870626,0.010661931,0.0030033654,0.00028036904,0.0000035504868],"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":[0.00003547081,0.00010303747,0.0004391841,0.00020054315,0.00008028596,0.00007782885,0.0012545828,0.006732252,0.5858502,0.10898707,0.022087311,0.27415222],"study_design_scores_gemma":[0.00009036637,0.000053999545,0.0013056806,0.00009931105,0.000026311036,0.00005923465,0.00013907597,0.98283434,0.0005814522,0.000547315,0.0142007535,0.00006218494],"about_ca_topic_score_codex":0.0000060747784,"about_ca_topic_score_gemma":8.6149663e-7,"teacher_disagreement_score":0.97610205,"about_ca_system_score_codex":0.000043605687,"about_ca_system_score_gemma":0.00071158627,"threshold_uncertainty_score":0.9920905},"labels":[],"label_agreement":null},{"id":"W4398770290","doi":"10.6339/24-jds1131","title":"Evaluating Perceptual Judgements on 3D Printed Bar Charts","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bar (unit); Bar chart; Perception; Computer science; Engineering drawing; Psychology; Statistics; Mathematics; Engineering; Geology","score_opus":0.15466865673993677,"score_gpt":0.3983999130363163,"score_spread":0.2437312562963795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398770290","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":[0.923427,0.00054848654,0.07301013,0.00022955645,0.001162048,0.000041530297,0.00003129485,0.00008151535,0.0014684569],"genre_scores_gemma":[0.99200225,0.00007216065,0.007644075,0.00003677481,0.00017726296,2.2699318e-7,0.0000030443048,0.000007734611,0.0000564955],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987356,0.0000126418145,0.0002518274,0.00016553774,0.00067215005,0.0001622269],"domain_scores_gemma":[0.9994685,0.000032957956,0.00003263184,0.00029656469,0.00008665791,0.00008266592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018525012,0.00006903847,0.00010292387,0.00024979343,0.00007712385,0.00018954303,0.0007630649,0.00001446765,0.00014662505],"category_scores_gemma":[0.00018678384,0.000052150477,0.00003356529,0.00041747733,0.00006696502,0.0010355145,0.00011284405,0.0002034894,0.00009687713],"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":[0.000008822029,0.00005653867,0.00013710491,0.00009565298,0.00014739927,0.000092256596,0.0015038339,0.45610514,0.13043888,0.0001296964,0.0071991757,0.40408552],"study_design_scores_gemma":[0.000056534394,0.00004952357,0.00018502983,0.00018730033,0.000032836408,0.000018386696,0.00008623123,0.99794704,0.00043105916,0.000018650653,0.00092586596,0.00006152874],"about_ca_topic_score_codex":0.0000011110808,"about_ca_topic_score_gemma":3.5324732e-7,"teacher_disagreement_score":0.5418419,"about_ca_system_score_codex":0.00006568603,"about_ca_system_score_gemma":0.00008980424,"threshold_uncertainty_score":0.21266347},"labels":[],"label_agreement":null},{"id":"W4400245371","doi":"10.6339/24-jds1143","title":"Physician Effects in Critical Care: A Causal Inference Approach Through Propensity Weighting with Parametric and Super Learning Methods","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Propensity score matching; Weighting; Causal inference; Covariate; Confounding; Inverse probability weighting; Estimator; Parametric statistics; Intensive care unit; Computer science; Medicine; Statistics; Intensive care medicine; Machine learning; Mathematics","score_opus":0.32995507111031813,"score_gpt":0.5379351258148638,"score_spread":0.20798005470454567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400245371","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":[0.15925053,0.0007925133,0.83889264,0.00008422919,0.000070450515,0.00018899488,0.000003262585,0.00005709082,0.0006603087],"genre_scores_gemma":[0.5136003,0.00002849429,0.4863088,0.000019037065,0.0000304724,0.0000023710845,6.4271643e-7,0.0000081023145,0.0000018055879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801666,0.0002532307,0.00036325643,0.00043797534,0.0005882335,0.00034062582],"domain_scores_gemma":[0.99633944,0.002762388,0.00013369524,0.00039032323,0.00027428207,0.000099843746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003244107,0.00016247186,0.00037976578,0.0003242841,0.00014720831,0.00032647024,0.0007325846,0.000049449944,0.0000014323614],"category_scores_gemma":[0.008248367,0.000106223946,0.000020015863,0.0017824899,0.000857624,0.0048086317,0.00052699103,0.00090377417,6.741744e-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":[0.00013012715,0.0005623878,0.016588723,0.0047129137,0.000076463446,0.0010467462,0.015693106,0.00020910623,0.06137669,0.62869716,0.00013563862,0.27077094],"study_design_scores_gemma":[0.0017958652,0.005685781,0.011450324,0.010785124,0.0007080071,0.003157263,0.011229194,0.15454242,0.10064759,0.6957391,0.0017775972,0.0024817302],"about_ca_topic_score_codex":0.000018011688,"about_ca_topic_score_gemma":0.0000046897553,"teacher_disagreement_score":0.35434973,"about_ca_system_score_codex":0.00012156891,"about_ca_system_score_gemma":0.0003896698,"threshold_uncertainty_score":0.9874662},"labels":[],"label_agreement":null},{"id":"W4404422782","doi":"10.6339/24-jds1134","title":"Rethinking Attention Weights as Bidirectional Coefficients","year":2024,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Explainable Artificial Intelligence (XAI)","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":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Ministry of Education, India; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Statistics; Mathematics; Psychology","score_opus":0.08340618000620546,"score_gpt":0.3567068886842551,"score_spread":0.2733007086780496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404422782","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":[0.12792991,0.0007594249,0.8607247,0.0025709933,0.0055993367,0.00008168304,0.00000728474,0.000099328034,0.0022273632],"genre_scores_gemma":[0.9493563,0.00009945274,0.049759574,0.00017449998,0.00032680534,5.693646e-7,0.0000021343428,0.0000065037884,0.0002741364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716824,0.00005583456,0.0004644907,0.0004930762,0.0014989631,0.0003194142],"domain_scores_gemma":[0.99823797,0.0001784307,0.00019302119,0.0007664149,0.00045718695,0.00016695034],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0043440755,0.00010012609,0.00012458413,0.00062281085,0.0003994261,0.001324823,0.0045846174,0.000035917918,0.000036463953],"category_scores_gemma":[0.0005199928,0.000078703204,0.00005763208,0.002487366,0.00037214858,0.0112764295,0.0009043847,0.00030987608,0.0002833696],"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":[0.00001984576,0.00025900998,0.0006059245,0.000051468633,0.000048951122,0.0008319016,0.0033119605,0.0005635715,0.11229081,0.6261635,0.0069128657,0.24894018],"study_design_scores_gemma":[0.00015906074,0.00048048422,0.0018496297,0.00087811303,0.000036015852,0.0030122767,0.00028790385,0.6947091,0.05573184,0.15319404,0.08916653,0.00049498375],"about_ca_topic_score_codex":0.00002296984,"about_ca_topic_score_gemma":0.0000049293267,"teacher_disagreement_score":0.8214264,"about_ca_system_score_codex":0.00015939973,"about_ca_system_score_gemma":0.0009407223,"threshold_uncertainty_score":0.9997119},"labels":[],"label_agreement":null},{"id":"W4415273830","doi":"10.6339/25-jds1200","title":"Q-learning with Compound Outcome and Mixed Misclassification and Measurement Error in Covariates","year":2025,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods and Inference","field":"Mathematics","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":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Covariate; Outcome (game theory); Observational error; Univariate; Estimation; Scope (computer science); Psychological intervention; Binary number","score_opus":0.3429165163248257,"score_gpt":0.45237121675090675,"score_spread":0.10945470042608102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415273830","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":[0.5915924,0.00013326979,0.40640703,0.0011849599,0.00009435283,0.000096372554,0.0000065842446,0.0000044218336,0.00048064275],"genre_scores_gemma":[0.67846006,0.000013199807,0.32149374,0.000019997267,0.0000043555196,3.0446412e-7,1.7314628e-7,0.0000011695452,0.000006982011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99906737,0.0000739658,0.0002877006,0.00013601208,0.00034207682,0.0000928552],"domain_scores_gemma":[0.998902,0.0005163729,0.00018424905,0.00015520467,0.0001921578,0.00004999914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004205763,0.000049471775,0.00015093827,0.0001185261,0.00008341265,0.0000979049,0.00027491295,0.000013256206,0.0000033748397],"category_scores_gemma":[0.0051804767,0.000032010168,0.0000038074802,0.00026089558,0.0003023527,0.000369446,0.00011571593,0.0001461494,1.4370237e-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":[0.00019771425,0.0003068514,0.38002142,0.00040587384,0.000051353076,0.000035437635,0.0009346197,0.000016264521,0.039430063,0.44205907,0.00047362642,0.1360677],"study_design_scores_gemma":[0.0012676314,0.0003320506,0.89191186,0.0007003055,0.00007798708,0.00008088678,0.0013596964,0.02096362,0.0007370124,0.08175113,0.00065565266,0.00016215668],"about_ca_topic_score_codex":0.000007566806,"about_ca_topic_score_gemma":0.000018023271,"teacher_disagreement_score":0.5118905,"about_ca_system_score_codex":0.000035513243,"about_ca_system_score_gemma":0.00013946168,"threshold_uncertainty_score":0.6201889},"labels":[],"label_agreement":null}]}