{"meta":{"query_hash":"b4afff0fe0bd","filters":{"venue":"International Journal of Data Science and Analytics"},"cohort_total":37,"direct_labels_cover":0,"predictions_cover":37,"exported":37,"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/b4afff0fe0bd","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Journal+of+Data+Science+and+Analytics"},"results":[{"id":"W2212891330","doi":"10.1007/s41060-018-0161-7","title":"Spectral ranking and unsupervised feature selection for point, collective, and contextual anomaly detection","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Anomaly detection; Feature selection; Ranking (information retrieval); Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Computer science; Point (geometry); Anomaly (physics); Selection (genetic algorithm); Machine learning; Data mining; Mathematics; Physics; Linguistics","score_opus":0.033771978519901054,"score_gpt":0.31927220439122783,"score_spread":0.2855002258713268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212891330","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":[0.15893254,0.00007176547,0.8386636,0.0018984467,0.00015944323,0.00010519536,0.000019533236,0.00001934759,0.0001301594],"genre_scores_gemma":[0.952659,0.00012724106,0.046685025,0.00020889261,0.00026046915,0.0000016334072,0.000001355666,0.0000031696852,0.000053180058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905896,0.000012927212,0.00019757645,0.0002760756,0.00033341313,0.00012106235],"domain_scores_gemma":[0.99841833,0.000070294736,0.00018979279,0.0001388578,0.0010984157,0.000084331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081816857,0.00007703187,0.000106908876,0.0003209407,0.00036885773,0.00046369433,0.00069253694,0.000035524386,0.0000020020996],"category_scores_gemma":[0.0001697432,0.00006614563,0.000019636069,0.00046294744,0.00035482013,0.0021504671,0.00024236538,0.00010423585,2.51276e-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":[0.00037281355,0.00021310375,0.013751173,0.00002781986,0.00031246105,0.0000114165205,0.0017353187,0.000015252851,0.208609,0.054741494,0.0040208017,0.7161893],"study_design_scores_gemma":[0.0017753153,0.0014974717,0.025293192,0.00007842285,0.00007850025,0.0018978092,0.00041659072,0.8852018,0.050723035,0.015352244,0.017335713,0.000349915],"about_ca_topic_score_codex":0.000016352084,"about_ca_topic_score_gemma":0.000053253214,"teacher_disagreement_score":0.88518655,"about_ca_system_score_codex":0.00007183621,"about_ca_system_score_gemma":0.00018529338,"threshold_uncertainty_score":0.4471415},"labels":[],"label_agreement":null},{"id":"W2419390560","doi":"10.1007/s41060-016-0011-4","title":"Similarity-based probabilistic category-based location recommendation utilizing temporal and geographical influence","year":2016,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dynamic time warping; Computer science; Similarity (geometry); Probabilistic logic; Matching (statistics); Component (thermodynamics); Data mining; Information retrieval; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Image (mathematics)","score_opus":0.06415753661921661,"score_gpt":0.36987120329393297,"score_spread":0.30571366667471633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2419390560","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":[0.7119695,0.000120138466,0.1915588,0.09500986,0.0004217358,0.00027813786,0.00016581787,0.000040101324,0.00043592945],"genre_scores_gemma":[0.99772745,0.00009027234,0.0014073566,0.0005893914,0.00014708599,0.0000010936934,0.000024994675,0.0000032144321,0.000009153716],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979626,0.00012323096,0.00043177494,0.00029231506,0.0010134879,0.00017657937],"domain_scores_gemma":[0.9965067,0.00043173242,0.00035059633,0.00021400204,0.0023090022,0.00018796245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047868057,0.00008718051,0.0001377166,0.00048973097,0.0004200997,0.000330212,0.00090672355,0.00005207121,0.000052528016],"category_scores_gemma":[0.0030017411,0.000064521235,0.000031650055,0.00069800584,0.0016566227,0.0019233754,0.00009343593,0.000119673816,0.0000017559827],"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":[0.00024239857,0.0007943946,0.53653395,0.00008789447,0.00020457817,0.000027440447,0.0015863066,0.0032126494,0.0026246742,0.036072563,0.00091318367,0.4177],"study_design_scores_gemma":[0.00600454,0.00081680715,0.22130212,0.0015662784,0.0008146503,0.00003912255,0.0078337025,0.5753283,0.0012235991,0.033071827,0.15039131,0.0016077625],"about_ca_topic_score_codex":0.0008208881,"about_ca_topic_score_gemma":0.0015612947,"teacher_disagreement_score":0.5721156,"about_ca_system_score_codex":0.00016622458,"about_ca_system_score_gemma":0.0016612329,"threshold_uncertainty_score":0.61038953},"labels":[],"label_agreement":null},{"id":"W2424687972","doi":"10.1007/s41060-016-0012-3","title":"Exact and approximate Boolean matrix decomposition with column-use condition","year":2016,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Univerzita Palackého v Olomouci","keywords":"Logical matrix; Matrix (chemical analysis); Complete Boolean algebra; Boolean function; Mathematics; Combinatorics; Discrete mathematics; Column (typography); Heuristic; Ideal (ethics); Maximum satisfiability problem; Heuristics; Boolean circuit; Algorithm; Two-element Boolean algebra; Algebra over a field; Pure mathematics; Mathematical optimization; Physics; Quantum mechanics","score_opus":0.021829510330628205,"score_gpt":0.3398350894567677,"score_spread":0.3180055791261395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2424687972","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":[0.25350252,0.000053729254,0.74146485,0.004621658,0.00019945537,0.000033496617,0.00003615284,0.000014284009,0.00007384675],"genre_scores_gemma":[0.9567117,0.00022888478,0.042712018,0.00016173835,0.00010970589,1.8112e-7,0.000004099356,0.0000028748398,0.00006878142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987486,0.000022133268,0.00019840171,0.0002166675,0.00069811236,0.00011611366],"domain_scores_gemma":[0.9988134,0.00010208937,0.0002452579,0.000213292,0.0005157458,0.0001102047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087430683,0.00006800986,0.00009408638,0.00023480259,0.00010896379,0.00064989575,0.0010875608,0.000014886055,0.0000042438423],"category_scores_gemma":[0.00014872225,0.00004040332,0.000011456591,0.00018728469,0.00025012667,0.004932373,0.00033657148,0.00008136428,0.0000014027747],"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":[0.00020189579,0.0003803363,0.093497954,0.000035037247,0.00035839278,0.00069438666,0.00075026177,0.000569386,0.030752713,0.07222739,0.0036545785,0.7968777],"study_design_scores_gemma":[0.0029980121,0.00089749915,0.065763965,0.0006960465,0.000079499856,0.0045009917,0.00016209063,0.90304697,0.002194612,0.0051566088,0.013997021,0.0005067137],"about_ca_topic_score_codex":0.000011334213,"about_ca_topic_score_gemma":0.0000034248053,"teacher_disagreement_score":0.90247756,"about_ca_system_score_codex":0.000036059664,"about_ca_system_score_gemma":0.0001302665,"threshold_uncertainty_score":0.626696},"labels":[],"label_agreement":null},{"id":"W2541373928","doi":"10.1007/s41060-017-0053-2","title":"Entropy-based time-varying window width selection for nonlinear-type time–frequency analysis","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Laser-Matter Interactions and Applications","field":"Physics and Astronomy","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spectral width; Window (computing); Dipole; Window function; Harmonics; Laser; Moment (physics); Rendering (computer graphics)","score_opus":0.034445805239438326,"score_gpt":0.3619583317690687,"score_spread":0.32751252652963037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2541373928","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":[0.5722507,0.00003041431,0.40696102,0.013339364,0.0010697132,0.00038303202,0.0027626993,0.000035012523,0.0031680032],"genre_scores_gemma":[0.9752458,0.000004900287,0.023608819,0.000120258635,0.0005899641,0.0000014259107,0.00018405238,0.00000684949,0.00023795577],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989495,0.000008309569,0.00029633738,0.00020511192,0.00041061183,0.0001301275],"domain_scores_gemma":[0.9976244,0.00006162257,0.00054451637,0.00034041208,0.0013425661,0.00008650689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053404976,0.00008322606,0.0001528476,0.000282736,0.00046597855,0.0006849333,0.0012799456,0.000014928563,0.00019101273],"category_scores_gemma":[0.00010300171,0.000069348185,0.00008311865,0.00026859448,0.00016439997,0.0017162324,0.00012949978,0.00009959056,0.000019328429],"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":[0.00029986358,0.0023251525,0.5024601,0.000027800508,0.007792145,0.000016356536,0.00022507031,0.014456179,0.3083995,0.013087714,0.023720859,0.12718922],"study_design_scores_gemma":[0.0008347841,0.00010193183,0.006942988,0.00005013229,0.0008018273,0.000011362325,0.000031029256,0.96764284,0.0068829055,0.002554078,0.013934906,0.0002112088],"about_ca_topic_score_codex":0.00008170656,"about_ca_topic_score_gemma":0.0000054609163,"teacher_disagreement_score":0.9531867,"about_ca_system_score_codex":0.000045344015,"about_ca_system_score_gemma":0.00031800594,"threshold_uncertainty_score":0.66048276},"labels":[],"label_agreement":null},{"id":"W2754529182","doi":"10.1007/s41060-017-0072-z","title":"Visual analytics of high-frequency lake monitoring data","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of the Environment, Conservation and Parks; University of Saskatchewan; Nipissing University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Visual analytics; Analytics; Data science; Computer science; Remote sensing; Visualization; Geography; Data mining","score_opus":0.12019800888902016,"score_gpt":0.4235599393987042,"score_spread":0.303361930509684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754529182","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":[0.09437887,0.00034293177,0.88877606,0.0082365,0.0050600194,0.00011951674,0.0017183787,0.000036542744,0.0013311856],"genre_scores_gemma":[0.9606281,0.00088630215,0.037850544,0.00010352077,0.0004179081,7.05965e-8,0.000064242806,0.0000056020444,0.00004369256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967439,0.000022919778,0.00068872515,0.00043487348,0.0018983557,0.00021119067],"domain_scores_gemma":[0.99421203,0.00008604674,0.0012371952,0.0023002794,0.001971869,0.00019256532],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0025887578,0.00012903701,0.00026710032,0.00048520975,0.00029234987,0.0014877107,0.018061014,0.00003894287,0.00001151492],"category_scores_gemma":[0.002245907,0.00010892889,0.000034063192,0.00038865377,0.0006391804,0.011409043,0.005481088,0.0001708855,0.0000036747253],"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":[0.000067250396,0.0014374737,0.3335275,0.00010728266,0.001409645,0.0008468797,0.0007100698,0.0007183083,0.010874597,0.26793474,0.009920569,0.37244567],"study_design_scores_gemma":[0.0016894249,0.0002518031,0.070857495,0.00048445768,0.0002332364,0.00032967882,0.00033338848,0.90243083,0.0033431305,0.006408236,0.013059372,0.00057892996],"about_ca_topic_score_codex":0.000055350967,"about_ca_topic_score_gemma":0.000043639262,"teacher_disagreement_score":0.90171254,"about_ca_system_score_codex":0.000040611354,"about_ca_system_score_gemma":0.0007149347,"threshold_uncertainty_score":0.99954885},"labels":[],"label_agreement":null},{"id":"W2767552437","doi":"10.1007/s41060-017-0079-5","title":"Discovering co-location patterns with aggregated spatial transactions and dependency rules","year":2017,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"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; Canadian Institutes of Health Research","keywords":"Association rule learning; Computer science; Data mining; Dependency (UML); Database transaction; Contrast (vision); Spatial analysis; Common spatial pattern; Spatial ecology; Artificial intelligence; Statistics; Mathematics","score_opus":0.04159857979522947,"score_gpt":0.3375766672262661,"score_spread":0.29597808743103665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767552437","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":[0.12069861,0.000029154142,0.87703973,0.0018513829,0.00012716911,0.000026813806,0.00014458789,0.000005585465,0.000076940916],"genre_scores_gemma":[0.96843326,0.0003188883,0.031094907,0.000042418458,0.00008107307,5.254981e-7,0.0000128045995,0.000002475016,0.0000136678855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885666,0.0000063057837,0.00019225635,0.00022887813,0.0006142946,0.000101627265],"domain_scores_gemma":[0.99860406,0.000030609273,0.00032897058,0.0005061144,0.00043436326,0.00009590817],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00051243225,0.00006711558,0.000085823245,0.00014861218,0.00040318797,0.001501568,0.0026254102,0.000014892478,0.0000027370695],"category_scores_gemma":[0.00009626222,0.000050444705,0.000009515407,0.00008571192,0.0002807338,0.00578009,0.0002478261,0.00009930476,0.000001088285],"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":[0.000012866932,0.00010133499,0.01484475,0.000008954562,0.00009098656,0.000057155965,0.0005197781,0.00012327552,0.0007316926,0.004160285,0.000044174787,0.97930473],"study_design_scores_gemma":[0.00093920116,0.00017447826,0.13579983,0.00031475077,0.000065554705,0.0009374031,0.00040403398,0.8568245,0.0014361179,0.0009534326,0.0018711091,0.00027958612],"about_ca_topic_score_codex":0.00021596249,"about_ca_topic_score_gemma":0.00012276834,"teacher_disagreement_score":0.9790252,"about_ca_system_score_codex":0.000025438045,"about_ca_system_score_gemma":0.00024070122,"threshold_uncertainty_score":0.99953496},"labels":[],"label_agreement":null},{"id":"W2806326686","doi":"10.1007/s41060-018-0130-1","title":"FACTORBASE: multi-relational structure learning with SQL all the way","year":2018,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"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; China Scholarship Council; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Statistical relational learning; Relational database; SQL; Relational model; Database design; Database model; Bayesian network; Relational database management system; Data definition language; Database; Machine learning; Artificial intelligence; Data mining","score_opus":0.09284649269330404,"score_gpt":0.34530226866371233,"score_spread":0.2524557759704083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806326686","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":[0.048110027,0.000059221085,0.9474202,0.0039220694,0.00033228163,0.000021538815,0.00001905616,0.000009074186,0.00010656424],"genre_scores_gemma":[0.9458467,0.00004168498,0.053326014,0.00050801353,0.00023052238,7.498291e-8,0.000004420889,0.0000024466628,0.000040172486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983018,0.000025566334,0.00022174642,0.00022026872,0.0010872873,0.00014334795],"domain_scores_gemma":[0.997867,0.00008307526,0.00024460937,0.0002818842,0.0014301426,0.000093273724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009230549,0.00008003561,0.00008193051,0.00014522437,0.0002169941,0.000500072,0.0029099064,0.000023295657,0.000015048283],"category_scores_gemma":[0.00025611682,0.000044431054,0.000015430702,0.00030924001,0.0005324135,0.0023997992,0.0004897666,0.00026348667,0.0000029471362],"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":[0.00020760675,0.00048458346,0.070177555,0.00001906377,0.0012264523,0.00035990507,0.011659236,0.019575726,0.034834195,0.37579462,0.008525337,0.47713572],"study_design_scores_gemma":[0.00039532236,0.00019893539,0.010156757,0.00006101766,0.000024188725,0.00043639107,0.00013822732,0.97499716,0.0006813369,0.0015901532,0.011175991,0.00014449224],"about_ca_topic_score_codex":0.000011668059,"about_ca_topic_score_gemma":0.000019108435,"teacher_disagreement_score":0.95542145,"about_ca_system_score_codex":0.000036368732,"about_ca_system_score_gemma":0.0003733755,"threshold_uncertainty_score":0.54073787},"labels":[],"label_agreement":null},{"id":"W2997087822","doi":"10.1007/s41060-020-00227-z","title":"A consistently oriented basis for eigenanalysis","year":2020,"lang":"en","type":"preprint","venue":"International Journal of Data Science and Analytics","topic":"Scientific Research and Discoveries","field":"Physics and Astronomy","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":"University of Technology Sydney; York University; Massachusetts Institute of Technology","keywords":"Python (programming language); Interpretability; Eigenvalues and eigenvectors; Computer science; Algorithm; Basis (linear algebra); Artificial intelligence; Implementation; Machine learning; Mathematics; Programming language","score_opus":0.1137284844806762,"score_gpt":0.40194341108149045,"score_spread":0.28821492660081427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997087822","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":[0.20320916,0.0008981019,0.7192615,0.03396328,0.0064623784,0.00078298047,0.0277574,0.000023891887,0.007641289],"genre_scores_gemma":[0.9902094,0.00009243815,0.008312015,0.0001452282,0.0007877527,0.000002227428,0.00032542634,0.000006376216,0.000119127835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974748,0.00001766133,0.0004726332,0.00040690886,0.0014346456,0.00019336087],"domain_scores_gemma":[0.9962281,0.00012547683,0.00053109654,0.00038733022,0.0024850552,0.00024291506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013658392,0.00012427851,0.00027427258,0.00037436627,0.00012942548,0.0008991176,0.002435081,0.000024979621,0.00009194735],"category_scores_gemma":[0.00075735396,0.000096490505,0.0001462008,0.0003507375,0.00051797036,0.0010076016,0.0018149099,0.00023149431,0.0000025567708],"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":[0.0016741658,0.0020392542,0.15202542,0.00042443487,0.017765302,0.0003048907,0.0042602913,0.0034820477,0.019757051,0.22042105,0.28889576,0.28895032],"study_design_scores_gemma":[0.0045467657,0.00060605526,0.0058218385,0.0013125681,0.0028713937,0.00006450352,0.018145582,0.56024766,0.011678894,0.12605864,0.26679426,0.0018518178],"about_ca_topic_score_codex":0.000063583895,"about_ca_topic_score_gemma":0.0000052863656,"teacher_disagreement_score":0.78700024,"about_ca_system_score_codex":0.000054706798,"about_ca_system_score_gemma":0.0018473219,"threshold_uncertainty_score":0.8670212},"labels":[],"label_agreement":null},{"id":"W3176378653","doi":"10.1007/s41060-021-00256-2","title":"Biased resampling strategies for imbalanced spatio-temporal forecasting","year":2021,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Resampling; Computer science; Relevance (law); Set (abstract data type); Machine learning; Sampling (signal processing); Data mining; Artificial intelligence","score_opus":0.16509422418002845,"score_gpt":0.38022736019206177,"score_spread":0.21513313601203332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176378653","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":[0.0047449814,0.000053467793,0.991873,0.0026405076,0.0003612337,0.000041768737,0.00011688314,0.000019388515,0.00014871349],"genre_scores_gemma":[0.53967446,0.00006519698,0.45979863,0.00026569032,0.000114096496,7.942325e-7,0.00006586199,0.0000028913616,0.000012365606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828386,0.000016755956,0.00042550603,0.00030339754,0.0008088168,0.0001616847],"domain_scores_gemma":[0.99618065,0.00018193404,0.00044035882,0.0004802408,0.0026355446,0.000081280545],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016505617,0.000077784425,0.00013953213,0.0002581402,0.00013322684,0.0010617666,0.0028422163,0.000024884615,0.0000031655186],"category_scores_gemma":[0.0013708217,0.000068974696,0.000030192377,0.00049163966,0.00016635511,0.005578002,0.00062164984,0.00010406119,4.974691e-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":[0.00010594014,0.0003321528,0.009123576,0.0000686392,0.00024515705,0.00033250224,0.00084565295,0.0009987568,0.061404787,0.6227474,0.014534231,0.28926116],"study_design_scores_gemma":[0.0006972843,0.00010563862,0.00169026,0.00017385778,0.000021383688,0.0004401463,0.00064011355,0.9134382,0.0135272555,0.0472549,0.021780476,0.00023049528],"about_ca_topic_score_codex":0.000006099111,"about_ca_topic_score_gemma":0.0000136488225,"teacher_disagreement_score":0.9124394,"about_ca_system_score_codex":0.000069905815,"about_ca_system_score_gemma":0.0013299644,"threshold_uncertainty_score":0.9999752},"labels":[],"label_agreement":null},{"id":"W3212301104","doi":"10.1007/s41060-021-00294-w","title":"Personalized multi-faceted trust modeling to determine trust links in social media and its potential for misinformation management","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Access Control and Trust","field":"Social Sciences","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 Waterloo","funders":"","keywords":"Misinformation; Computer science; Social media; Popularity; Context (archaeology); Set (abstract data type); Cluster analysis; Data science; Internet privacy; Recommender system; World Wide Web; Computer security; Artificial intelligence; Psychology","score_opus":0.09913148508559601,"score_gpt":0.3803917413536482,"score_spread":0.28126025626805223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212301104","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":[0.92800874,0.00026429107,0.05031428,0.018516986,0.0013424965,0.00046409946,0.0005436868,0.000012922846,0.00053248816],"genre_scores_gemma":[0.99626756,0.0001468692,0.00289013,0.00032265787,0.00027292303,0.0000032967444,0.000021027898,0.0000030783767,0.000072434894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982013,0.000029752462,0.0003415216,0.00015799115,0.0010939525,0.00017546795],"domain_scores_gemma":[0.99912274,0.000050429502,0.00018637175,0.0000555806,0.0004823703,0.00010253634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022286233,0.00006421145,0.00012929109,0.00044929745,0.0005860121,0.00027724679,0.0009800592,0.000028544653,0.000031454965],"category_scores_gemma":[0.00041119845,0.00006054483,0.00002818608,0.00033594607,0.00012464047,0.0016384835,0.00040646395,0.00015090857,4.6822706e-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":[0.0026210186,0.001016974,0.0058190553,0.000111013534,0.0006915441,0.00039202967,0.10325582,0.051560435,0.0023008161,0.14288053,0.0026419277,0.68670887],"study_design_scores_gemma":[0.0018397705,0.00003320949,0.0011047968,0.000016852471,0.000043098156,0.000013531259,0.011546217,0.97946024,0.00000559111,0.00063948706,0.0051933844,0.00010381877],"about_ca_topic_score_codex":0.000036735066,"about_ca_topic_score_gemma":0.00009752274,"teacher_disagreement_score":0.92789984,"about_ca_system_score_codex":0.00014223273,"about_ca_system_score_gemma":0.00020121378,"threshold_uncertainty_score":0.45071906},"labels":[],"label_agreement":null},{"id":"W4205284473","doi":"10.1007/s41060-021-00304-x","title":"Knowledgebase approximation using association rule aggregation","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Association rule learning; Pooling; Computer science; Set (abstract data type); Data mining; Knowledge extraction; Association (psychology); Artificial intelligence","score_opus":0.06659777893143116,"score_gpt":0.33121282195494856,"score_spread":0.2646150430235174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205284473","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":[0.25278592,0.00045043882,0.7325172,0.008302239,0.0038143485,0.00012997407,0.000128049,0.000031104428,0.0018407098],"genre_scores_gemma":[0.9341813,0.00007879467,0.065134145,0.00034239487,0.00021865008,4.1965652e-7,0.000014158134,0.000002602524,0.000027558162],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787956,0.000043157823,0.00028993192,0.00018359344,0.0014865112,0.0001172259],"domain_scores_gemma":[0.99828637,0.00006079673,0.00052016316,0.0002280801,0.0008443679,0.000060200775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029544288,0.000052777177,0.00008510775,0.00034565275,0.0002860051,0.00041321683,0.0022887716,0.000013192561,0.0000119643155],"category_scores_gemma":[0.00044071418,0.000046727215,0.000022450333,0.0006033251,0.00005254254,0.0035172363,0.0010782293,0.00013955114,0.0000015388847],"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":[0.000058923673,0.000859945,0.02931056,0.000019367111,0.0002994846,0.00021186315,0.0028604895,0.020938165,0.010741669,0.068691164,0.009409418,0.856599],"study_design_scores_gemma":[0.00026464855,0.000052116906,0.0009796575,0.000010599297,0.000014775092,0.00015297798,0.0001501263,0.98703575,0.00017903215,0.0039500515,0.0071335225,0.000076751996],"about_ca_topic_score_codex":0.000010587339,"about_ca_topic_score_gemma":0.0000012494404,"teacher_disagreement_score":0.9660976,"about_ca_system_score_codex":0.00040969558,"about_ca_system_score_gemma":0.00042899078,"threshold_uncertainty_score":0.42531452},"labels":[],"label_agreement":null},{"id":"W4206899722","doi":"10.1007/s41060-021-00296-8","title":"The validation of chest tube management after lung resection surgery using a random forest classifier","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; Dalhousie University","funders":"Department of Medicine, Ottawa Hospital; Ontario Medical Association; Ontario Ministry of Health and Long-Term Care","keywords":"Random forest; Classifier (UML); Lung; Medicine; Chest tube; Resection; Radiology; Computer science; Surgery; Artificial intelligence; Internal medicine","score_opus":0.06469924393754112,"score_gpt":0.3353173416258536,"score_spread":0.27061809768831246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206899722","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":[0.07681984,0.0001872887,0.9178229,0.0036253128,0.0011318814,0.00013533143,0.00009518071,0.000014820149,0.00016744272],"genre_scores_gemma":[0.98596865,0.00033883442,0.013488363,0.0000921491,0.00006797112,0.0000033875212,0.000014188189,0.0000030283363,0.000023419832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976914,0.00007025553,0.00047126116,0.00020416622,0.001440519,0.00012242363],"domain_scores_gemma":[0.9980155,0.00020586293,0.00054635614,0.0005048538,0.00068471464,0.000042673415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004385635,0.00006161583,0.00010752556,0.00044778574,0.00027831158,0.00034479192,0.0025844064,0.000011925423,0.0000053508447],"category_scores_gemma":[0.00027646217,0.00004633648,0.000036857247,0.0006886004,0.00022608302,0.002597259,0.0013366699,0.00013422908,2.3364696e-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":[0.002615894,0.0015012388,0.21986656,0.00025192523,0.0016943235,0.0006440362,0.0022291734,0.01190244,0.03465063,0.17604196,0.05904172,0.4895601],"study_design_scores_gemma":[0.0007703405,0.00008666329,0.025650753,0.000123039,0.000071829585,0.00040067374,0.0005152845,0.9340694,0.0058264993,0.004627405,0.027640698,0.0002174426],"about_ca_topic_score_codex":0.0000090015365,"about_ca_topic_score_gemma":0.0000032141763,"teacher_disagreement_score":0.92216694,"about_ca_system_score_codex":0.00017875247,"about_ca_system_score_gemma":0.00026176497,"threshold_uncertainty_score":0.48025128},"labels":[],"label_agreement":null},{"id":"W4210299703","doi":"10.1007/s41060-021-00302-z","title":"Fake news detection based on news content and social contexts: a transformer-based approach","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":270,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unavailability; Computer science; Exploit; Fake news; Economic shortage; Social media; Encoder; Transformer; Artificial intelligence; Machine learning; Computer security; World Wide Web; Internet privacy; Engineering","score_opus":0.1382122536767137,"score_gpt":0.36902561951164464,"score_spread":0.23081336583493095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210299703","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":[0.68902075,0.00018606026,0.18622711,0.08586822,0.0027309216,0.0007780161,0.0011072434,0.00005926183,0.034022424],"genre_scores_gemma":[0.9959363,0.000049707098,0.00042605374,0.0033745202,0.00014652342,5.051063e-7,0.000016948175,0.0000026739167,0.00004680231],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763733,0.00007025196,0.00030855325,0.0001371444,0.001691253,0.00015548925],"domain_scores_gemma":[0.9989906,0.00007514618,0.00027640254,0.000089342284,0.0004376649,0.0001308636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021435106,0.00006907052,0.00011670944,0.00037583426,0.00076546584,0.00036230485,0.0007544495,0.00002271603,0.00006200732],"category_scores_gemma":[0.00036673382,0.00005854648,0.000036629568,0.00033199677,0.00041423732,0.0014773275,0.000054336768,0.0001861867,7.22212e-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":[0.0011155925,0.0009687634,0.0033120702,0.00003602164,0.00016162159,0.000036643432,0.034762878,0.003945223,0.0030860172,0.019658992,0.0063877758,0.9265284],"study_design_scores_gemma":[0.006539668,0.0011701353,0.0068820813,0.000074954216,0.00013012307,0.000088347864,0.1597462,0.45243672,0.0005961716,0.00050016807,0.37126175,0.0005737023],"about_ca_topic_score_codex":0.00024853979,"about_ca_topic_score_gemma":0.00020500367,"teacher_disagreement_score":0.9259547,"about_ca_system_score_codex":0.00019065432,"about_ca_system_score_gemma":0.0008015288,"threshold_uncertainty_score":0.58874214},"labels":[],"label_agreement":null},{"id":"W4286817176","doi":"10.1007/s41060-022-00343-y","title":"Semantic enhanced Markov model for sequential E-commerce product recommendation","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Markov chain; Stochastic matrix; Computer science; Context (archaeology); Markov model; Recommender system; Product (mathematics); Information retrieval; Data mining; Theoretical computer science; Artificial intelligence; Machine learning; Mathematics","score_opus":0.08763348725034148,"score_gpt":0.36290812922905397,"score_spread":0.2752746419787125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286817176","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":[0.0028008018,0.00003326123,0.9834898,0.012327948,0.00089796685,0.000106284635,0.00007860259,0.000014683368,0.00025065037],"genre_scores_gemma":[0.9058328,0.00007977527,0.093280494,0.0005340192,0.00015320901,0.0000044022854,0.000023801493,0.0000041006756,0.00008738611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983062,0.00003648284,0.00040943682,0.00030392583,0.00079281704,0.0001511308],"domain_scores_gemma":[0.99835557,0.000057863916,0.00041442216,0.0003573457,0.0007474295,0.00006734311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031371356,0.00007802886,0.00013541563,0.00035379292,0.00026641946,0.00036825726,0.003323146,0.000010546808,0.000009544943],"category_scores_gemma":[0.00016173298,0.000069082496,0.000038442886,0.00032537384,0.00006998129,0.0028797346,0.0014053788,0.00014103738,3.0598954e-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":[0.0000939217,0.00044536183,0.0005173179,0.000037317008,0.00025089967,0.000023426146,0.0015033425,0.002114344,0.025048237,0.031245628,0.06347561,0.8752446],"study_design_scores_gemma":[0.00028345516,0.000095027564,0.000055089182,0.000014989278,0.000013130113,0.00016991983,0.00009132202,0.978408,0.0016645784,0.002510914,0.016591873,0.00010173845],"about_ca_topic_score_codex":0.000013464045,"about_ca_topic_score_gemma":0.0000047569183,"teacher_disagreement_score":0.9762936,"about_ca_system_score_codex":0.00013424498,"about_ca_system_score_gemma":0.00040680313,"threshold_uncertainty_score":0.61752874},"labels":[],"label_agreement":null},{"id":"W4294084767","doi":"10.1007/s41060-022-00359-4","title":"Dbias: detecting biases and ensuring fairness in news articles","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Python (programming language); Set (abstract data type); Extension (predicate logic); Open source; Information retrieval; Machine learning; Software; Programming language","score_opus":0.21995985545416435,"score_gpt":0.4483360134583283,"score_spread":0.22837615800416394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294084767","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":[0.987087,0.00016053898,0.00007978946,0.0116718495,0.00027393244,0.000023951208,0.000018780247,0.0000031096959,0.0006810342],"genre_scores_gemma":[0.9983779,0.0006586176,0.00038060258,0.00039888424,0.00016451397,1.8657742e-7,7.9409546e-7,0.000002072332,0.000016423977],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9983063,0.00007109878,0.00022933261,0.00012545298,0.0011168827,0.00015094964],"domain_scores_gemma":[0.99885166,0.0003288055,0.00017909202,0.00007884903,0.0004572098,0.00010438201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048384424,0.000040303723,0.000087777415,0.0002836681,0.000560033,0.00044909152,0.0008697519,0.000015840013,0.000017728116],"category_scores_gemma":[0.0047542187,0.000038177393,0.000013666068,0.00042516403,0.00048345106,0.0020871325,0.00052987377,0.00022773075,1.8468243e-7],"study_design_candidate":"qualitative","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":[0.00010386198,0.00036280762,0.3281586,0.000011868085,0.00012897198,0.00050249527,0.077286236,0.0013707844,0.005421533,0.051332343,0.0007700886,0.5345504],"study_design_scores_gemma":[0.0033331,0.0006634171,0.10339055,0.00061959977,0.00014034666,0.000442265,0.6858562,0.04938977,0.0012378535,0.088137306,0.06570004,0.001089553],"about_ca_topic_score_codex":0.0016439391,"about_ca_topic_score_gemma":0.002302342,"teacher_disagreement_score":0.60857,"about_ca_system_score_codex":0.00011459964,"about_ca_system_score_gemma":0.0005152408,"threshold_uncertainty_score":0.56915873},"labels":[],"label_agreement":null},{"id":"W4366003831","doi":"10.1007/s41060-023-00389-6","title":"Statistical power, accuracy, reproducibility and robustness of a graph clusterability test","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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":"Memorial University of Newfoundland; University of Toronto","funders":"University of Toronto","keywords":"Statistical hypothesis testing; Statistic; Mathematics; Graph; Test statistic; Cluster analysis; Robustness (evolution); Computer science; Combinatorics; Statistics; Algorithm","score_opus":0.05412285085499116,"score_gpt":0.38137613758015304,"score_spread":0.32725328672516185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366003831","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":[0.95227224,0.000033411096,0.045829058,0.0010569638,0.00013357145,0.000057673646,0.00044180805,0.0000094697425,0.00016582348],"genre_scores_gemma":[0.9955401,0.000051287803,0.0042349156,0.000013603501,0.00012112044,2.947799e-7,0.000029296,0.000002694199,0.000006709284],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998343,0.0000274486,0.00047616713,0.00038369757,0.00064971106,0.000119992656],"domain_scores_gemma":[0.9975092,0.0005151119,0.0003310913,0.000593378,0.00096490496,0.00008631509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038699585,0.00007263874,0.00019610267,0.00025531306,0.00006591366,0.000115777,0.0009124395,0.000011795114,0.0000408714],"category_scores_gemma":[0.0014639383,0.00005840627,0.000032974887,0.0006008916,0.0005910999,0.000821996,0.0007148783,0.000121299025,4.0504682e-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":[0.000054074884,0.00044880455,0.89349264,0.00002124716,0.00024802078,0.000016161363,0.00020352175,0.0006438497,0.00247601,0.008623743,0.006215223,0.08755672],"study_design_scores_gemma":[0.0008751815,0.00029524812,0.6101856,0.00017918696,0.00023885313,0.000059345602,0.0011861888,0.33667904,0.0012228141,0.046082467,0.0026248228,0.00037123397],"about_ca_topic_score_codex":0.000045661658,"about_ca_topic_score_gemma":0.0000066384255,"teacher_disagreement_score":0.3360352,"about_ca_system_score_codex":0.000018517821,"about_ca_system_score_gemma":0.00018444176,"threshold_uncertainty_score":0.23817386},"labels":[],"label_agreement":null},{"id":"W4382794929","doi":"10.1007/s41060-023-00422-8","title":"Cluster weighted model based on TSNE algorithm for high-dimensional data","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster (spacecraft); Computer science; Algorithm; Data mining","score_opus":0.08185738340875104,"score_gpt":0.3724881720827192,"score_spread":0.2906307886739682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382794929","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":[0.0004751802,0.00001817526,0.9889569,0.009227345,0.0006667166,0.000059153102,0.0005264778,0.000015535967,0.000054499465],"genre_scores_gemma":[0.034241777,0.00004858513,0.9630077,0.0022007679,0.0002790581,6.558564e-7,0.0001314818,0.000006267538,0.000083706385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975087,0.000029210078,0.00036391764,0.00047829142,0.0013999236,0.00021994785],"domain_scores_gemma":[0.99743265,0.00028746028,0.00023862266,0.0009251062,0.0009633036,0.00015288364],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0038393354,0.00011007163,0.0001686965,0.0005616972,0.00013920874,0.00036894812,0.0058604046,0.00003676356,0.0000029226412],"category_scores_gemma":[0.0003456966,0.000082110215,0.000031321342,0.0005976085,0.00016119836,0.0028026036,0.0015407489,0.00014446254,0.0000037005184],"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":[0.000036776586,0.00013213792,0.000016695692,0.00000580587,0.00007049762,0.00006212903,0.000058363144,0.005220727,0.0005260946,0.03223272,0.03452467,0.92711335],"study_design_scores_gemma":[0.0005849409,0.00007195515,0.00005121017,0.000041801602,0.00001756698,0.000030823143,0.000003851295,0.97521824,0.00016978696,0.02242375,0.001287626,0.00009847228],"about_ca_topic_score_codex":0.00000420053,"about_ca_topic_score_gemma":0.000001584926,"teacher_disagreement_score":0.96999747,"about_ca_system_score_codex":0.000043391385,"about_ca_system_score_gemma":0.0006767726,"threshold_uncertainty_score":0.9995184},"labels":[],"label_agreement":null},{"id":"W4383645786","doi":"10.1007/s41060-023-00409-5","title":"Applications of the discrete-time Fourier transform to data analysis","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Scientific Research and Discoveries","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Probability mass function; Probability-generating function; Random variable; Characteristic function (probability theory); Fourier transform; Discrete-time stochastic process; Discrete Fourier transform (general); Mathematics; Random function; Discrete-time Fourier transform; Function (biology); Applied mathematics; Variable (mathematics); Discrete time and continuous time; Fourier analysis; Probability density function; Algorithm; Stochastic process; Mathematical analysis; Fractional Fourier transform; Statistics; Continuous-time stochastic process","score_opus":0.05059634054103507,"score_gpt":0.391844785633456,"score_spread":0.3412484450924209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383645786","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":[0.27953717,0.00010455918,0.63909113,0.040690348,0.00085981056,0.0006291659,0.023334108,0.000017878894,0.01573584],"genre_scores_gemma":[0.9977549,0.00001695202,0.001354674,0.00003961364,0.00014613694,8.200311e-7,0.0001739167,0.0000020219943,0.00051098294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983279,0.000010250923,0.00024199657,0.00018281497,0.0011180005,0.00011899653],"domain_scores_gemma":[0.9985587,0.00006205138,0.00013137294,0.0006696894,0.0004765741,0.000101607555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001479371,0.000044018543,0.00010267726,0.00037073385,0.00011419718,0.00022429271,0.0036415302,0.0000060433226,0.00010341573],"category_scores_gemma":[0.000117552874,0.000026864189,0.00004648984,0.0022206435,0.00032557006,0.0012770036,0.0009480502,0.00006263979,0.000009105075],"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":[0.00013534355,0.00049024017,0.1910058,0.000022179222,0.004340836,0.000012537867,0.0017232319,0.003942534,0.013530858,0.030973002,0.13271393,0.62110955],"study_design_scores_gemma":[0.0008529476,0.00009538094,0.045882918,0.000091155845,0.0009795587,0.000009355646,0.0052080215,0.7212819,0.004873785,0.021052612,0.19930089,0.00037151147],"about_ca_topic_score_codex":0.00005096008,"about_ca_topic_score_gemma":0.000014688526,"teacher_disagreement_score":0.71821773,"about_ca_system_score_codex":0.000010916324,"about_ca_system_score_gemma":0.0003306675,"threshold_uncertainty_score":0.67669296},"labels":[],"label_agreement":null},{"id":"W4387403737","doi":"10.1007/s41060-023-00465-x","title":"Theoretical and practical data science and analytics: challenges and solutions","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Data science; Cloud computing; Analytics; Computer science; Data analysis; Business intelligence; The Internet; Focus (optics); Knowledge management; World Wide Web; Data mining","score_opus":0.3191882207103572,"score_gpt":0.4219101829844512,"score_spread":0.10272196227409403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387403737","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":[0.59699637,0.009123111,0.013627661,0.3599603,0.0042389967,0.0005688345,0.0011393107,0.00017084797,0.014174583],"genre_scores_gemma":[0.9835437,0.014115304,0.0011185532,0.0006497852,0.0005199765,2.7482113e-7,0.000036722577,0.0000061372175,0.000009559733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745375,0.000007745575,0.00033175154,0.00051368284,0.0014084618,0.00028462816],"domain_scores_gemma":[0.99753714,0.00018722453,0.00024136748,0.00047780806,0.0014773287,0.000079148995],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005424612,0.000120527366,0.00017108228,0.00080172025,0.0003752279,0.0014150033,0.0016305745,0.000036313555,0.00002539932],"category_scores_gemma":[0.0050809016,0.00009213175,0.000009380713,0.00092688436,0.0039412426,0.012719487,0.0049932594,0.00019217542,0.000008296313],"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":[0.000048702685,0.00010850076,0.0036710263,0.00007466173,0.00008397916,0.00015885723,0.00011295397,0.0000075506214,0.0009005658,0.8339181,0.0051060272,0.15580909],"study_design_scores_gemma":[0.00058700185,0.000052942607,0.04549097,0.00028929717,0.0003047831,0.0010020896,0.0025399409,0.81976366,0.000042349715,0.038214996,0.091283776,0.00042820798],"about_ca_topic_score_codex":0.000026526324,"about_ca_topic_score_gemma":0.000029690033,"teacher_disagreement_score":0.8197561,"about_ca_system_score_codex":0.000022932069,"about_ca_system_score_gemma":0.00030862706,"threshold_uncertainty_score":0.9996216},"labels":[],"label_agreement":null},{"id":"W4388304181","doi":"10.1007/s41060-023-00467-9","title":"Tackling cold-start with deep personalized transfer of user preferences for cross-domain recommendation","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Bridge (graph theory); Cold start (automotive); Domain (mathematical analysis); Recommender system; Task (project management); Deep learning; Domain knowledge; Code (set theory); Transfer of learning; Quality (philosophy); Artificial intelligence; Machine learning; Engineering","score_opus":0.08551935414361735,"score_gpt":0.36710359712448404,"score_spread":0.2815842429808667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388304181","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":[0.10789163,0.000031416686,0.88959557,0.0018787102,0.00028569545,0.0001003142,0.00007260539,0.000017454016,0.00012660069],"genre_scores_gemma":[0.9301793,0.00024220535,0.06931373,0.000116142364,0.000085208434,0.0000023612818,0.00001866461,0.0000041809694,0.000038189086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855494,0.00001839593,0.00039257435,0.00021842752,0.00067853264,0.00013714872],"domain_scores_gemma":[0.99823767,0.000110199595,0.00022118716,0.00020169643,0.0011636174,0.00006563099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022555117,0.000075358555,0.00015918403,0.00035697673,0.00009756526,0.00037470978,0.0018031464,0.000023527142,0.000005869271],"category_scores_gemma":[0.000083157975,0.000053517917,0.000033921133,0.0004885642,0.00019495281,0.0027773867,0.00019521292,0.0000708252,4.428927e-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":[0.00080889155,0.00086740364,0.13628191,0.0004441098,0.0017182346,0.00013689778,0.01130135,0.0010063814,0.04269309,0.5168454,0.018796554,0.2690998],"study_design_scores_gemma":[0.0072556953,0.0025453633,0.023534166,0.0014082238,0.00015527841,0.0005455073,0.0037289483,0.67865413,0.03340212,0.025491452,0.22217065,0.0011084623],"about_ca_topic_score_codex":0.000013016191,"about_ca_topic_score_gemma":0.000017997563,"teacher_disagreement_score":0.8222877,"about_ca_system_score_codex":0.000035092642,"about_ca_system_score_gemma":0.0002408011,"threshold_uncertainty_score":0.36133352},"labels":[],"label_agreement":null},{"id":"W4389455239","doi":"10.1007/s41060-023-00464-y","title":"Enhancing e-commerce recommendations with a novel scale-aware spectral graph wavelets framework","year":2023,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Wavelet; Embedding; Graph; Smoothing; Collaborative filtering; Eigenvalues and eigenvectors; Scale (ratio); Recommender system; Artificial intelligence; Machine learning; Theoretical computer science; Data mining; Computer vision","score_opus":0.06010432902480681,"score_gpt":0.3485235941154597,"score_spread":0.28841926509065285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389455239","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":[0.012801912,0.000020336563,0.9693669,0.016880184,0.00059100334,0.000050489394,0.000054434757,0.000049706494,0.00018501961],"genre_scores_gemma":[0.73732495,0.00034322529,0.2614559,0.00058627833,0.00023235162,0.0000010886263,0.000013486693,0.000006883326,0.000035868936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998007,0.000019267938,0.000415198,0.00031128014,0.0010174003,0.00022983707],"domain_scores_gemma":[0.99812764,0.0001596708,0.00033287166,0.0004852297,0.0007527025,0.00014189038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018331113,0.00010853772,0.00017499352,0.0006963122,0.00018720512,0.0006634089,0.00334531,0.000034044893,0.000005773813],"category_scores_gemma":[0.00015255046,0.00008072901,0.000035339257,0.0013676751,0.00016110852,0.003354137,0.0007848194,0.0002469578,0.0000032746284],"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":[0.00013235457,0.0009598559,0.03815224,0.000104685285,0.0011964036,0.000851586,0.008993173,0.0004903002,0.022989117,0.36059102,0.06214184,0.50339746],"study_design_scores_gemma":[0.0041410476,0.0023471043,0.06854971,0.005638433,0.00024055544,0.009067506,0.005812185,0.64644414,0.030498633,0.094668426,0.1298996,0.0026926626],"about_ca_topic_score_codex":0.000031553613,"about_ca_topic_score_gemma":0.00004634588,"teacher_disagreement_score":0.724523,"about_ca_system_score_codex":0.00006534794,"about_ca_system_score_gemma":0.00029456278,"threshold_uncertainty_score":0.6397267},"labels":[],"label_agreement":null},{"id":"W4396953092","doi":"10.1007/s41060-024-00552-7","title":"Feature extraction for exoplanet detection","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Stellar, planetary, and galactic studies","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Vector Institute; Dalhousie University","funders":"","keywords":"Exoplanet; Computer science; Feature (linguistics); Extraction (chemistry); Feature extraction; Artificial intelligence; Computer vision; Chromatography; Chemistry; Stars","score_opus":0.036347484182628266,"score_gpt":0.33834147687023874,"score_spread":0.30199399268761046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396953092","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":[0.248306,0.008391714,0.64395297,0.028263712,0.02976282,0.0006085944,0.0019517433,0.00007996245,0.038682494],"genre_scores_gemma":[0.9973882,0.00013518623,0.0010064223,0.000039733455,0.0012367149,3.000323e-7,0.00004509967,0.0000026916612,0.00014568117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993195,0.000004253931,0.00011938272,0.00012849375,0.00034822014,0.00008012612],"domain_scores_gemma":[0.9993635,0.00012861582,0.00008342963,0.00007906301,0.000304965,0.00004044014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047086348,0.000053484287,0.00007197946,0.0001521707,0.000080752485,0.00025443113,0.00032852785,0.000012688342,0.00001857852],"category_scores_gemma":[0.00005124666,0.000040303737,0.00002449737,0.00011773642,0.000079837264,0.0009838664,0.00005309037,0.00009905367,0.0000025595996],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011084036,0.000084894695,0.17046998,0.00003479453,0.00081047276,0.000047352853,0.00035326215,0.00015134194,0.0028509845,0.004329307,0.039495487,0.78126127],"study_design_scores_gemma":[0.0008544859,0.00026861756,0.071554855,0.0002234146,0.00046724643,0.0005711533,0.0011086165,0.15263051,0.0032753595,0.0058073606,0.76289576,0.00034262973],"about_ca_topic_score_codex":0.000014476838,"about_ca_topic_score_gemma":0.0000051306924,"teacher_disagreement_score":0.78091866,"about_ca_system_score_codex":0.000020300447,"about_ca_system_score_gemma":0.000105141175,"threshold_uncertainty_score":0.24534853},"labels":[],"label_agreement":null},{"id":"W4399281748","doi":"10.1007/s41060-024-00567-0","title":"Automatic user story generation: a comprehensive systematic literature review","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Persona Design and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Systematic review; Computer science; MEDLINE; Political science","score_opus":0.07858855502867235,"score_gpt":0.36104252675781096,"score_spread":0.2824539717291386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399281748","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":[0.0028001892,0.3566393,0.59026384,0.046945855,0.002407491,0.0004377311,0.00012687063,0.00009669145,0.00028201268],"genre_scores_gemma":[0.59382415,0.20931852,0.17655432,0.017066568,0.002333886,0.000019889458,0.00009608194,0.000028703795,0.0007578978],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982346,0.000047477108,0.00036027838,0.00024758987,0.0010094645,0.00010058384],"domain_scores_gemma":[0.9980706,0.00012447835,0.00017443532,0.00043303976,0.0010977123,0.000099714154],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001397074,0.00008483297,0.00017979606,0.00032281323,0.000101869344,0.0011441358,0.0026510763,0.000019046807,0.0000061125],"category_scores_gemma":[0.00023429163,0.000059651666,0.000041643052,0.0008696752,0.00012477723,0.003690555,0.00034764965,0.00017224724,0.0000134237325],"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":[0.00000423761,0.00030615134,0.000056581568,0.0360172,0.0010160056,0.0020541404,0.0033324743,0.000092085196,0.025318388,0.38112882,0.3914966,0.15917732],"study_design_scores_gemma":[0.00010743399,0.000036514968,0.000062190054,0.032574903,0.000095182964,0.002171071,0.000059047776,0.93197817,0.00006950412,0.00036440248,0.0323364,0.00014519137],"about_ca_topic_score_codex":4.649812e-7,"about_ca_topic_score_gemma":5.1473637e-7,"teacher_disagreement_score":0.9318861,"about_ca_system_score_codex":0.000073065705,"about_ca_system_score_gemma":0.00044510467,"threshold_uncertainty_score":0.9998928},"labels":[],"label_agreement":null},{"id":"W4399483161","doi":"10.1007/s41060-024-00558-1","title":"Deep learning-based approach for COVID-19 spread prediction","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":8,"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":"Kungliga Tekniska Högskolan; Lunds Universitet; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Autoregressive integrated moving average; Computer science; Deep learning; Autoencoder; Coronavirus disease 2019 (COVID-19); Econometrics; Artificial intelligence; Key (lock); Machine learning; Infectious disease (medical specialty); Time series; Disease; Mathematics; Computer security; Medicine","score_opus":0.36256571370105417,"score_gpt":0.4922212792509322,"score_spread":0.129655565549878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399483161","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":[0.001793399,0.00040595414,0.9904011,0.0067045833,0.00030792545,0.000086462955,0.000118519434,0.000028957753,0.00015309702],"genre_scores_gemma":[0.9263335,0.000447989,0.070887156,0.0015377868,0.0006402764,0.0000039083625,0.00005218799,0.000009677257,0.00008752377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836785,0.00003545691,0.00042154713,0.00027629756,0.00075182295,0.00014701184],"domain_scores_gemma":[0.99683607,0.0020887805,0.00020854238,0.00015661739,0.0005615231,0.00014848632],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004529536,0.000087644585,0.00018123102,0.00027275734,0.00015798674,0.0002157926,0.000973697,0.000035889312,0.000014252284],"category_scores_gemma":[0.023613784,0.00005996273,0.00006158466,0.00029067078,0.00035351748,0.0007201701,0.00026496078,0.0001880707,9.730262e-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":[0.0009681008,0.0017928192,0.080979854,0.0024048458,0.0029873552,0.0004642351,0.0030072366,0.21554431,0.0026077488,0.27377462,0.21657594,0.19889292],"study_design_scores_gemma":[0.00026817402,0.00012730995,0.00028349165,0.000050342518,0.000089974026,0.00004579258,0.00019682792,0.91802263,0.000020386444,0.020138765,0.06068501,0.00007129231],"about_ca_topic_score_codex":0.000010760281,"about_ca_topic_score_gemma":0.0000054489383,"teacher_disagreement_score":0.9245401,"about_ca_system_score_codex":0.00022850199,"about_ca_system_score_gemma":0.00045152384,"threshold_uncertainty_score":0.98461074},"labels":[],"label_agreement":null},{"id":"W4399799131","doi":"10.1007/s41060-024-00580-3","title":"Implicitly adaptive optimal proposal in variational inference for Bayesian learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Inference; Bayesian inference; Bayesian probability; Computer science; Machine learning; Artificial intelligence","score_opus":0.037284725672156835,"score_gpt":0.34915518342993906,"score_spread":0.3118704577577822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399799131","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":[0.0016701164,0.00014039486,0.99336433,0.004119809,0.00039336487,0.000053601114,0.000030362857,0.000012419642,0.00021561784],"genre_scores_gemma":[0.83362436,0.000099900346,0.16599293,0.000091764006,0.00016127544,0.0000011606357,0.000005015157,0.000003321618,0.000020287993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826664,0.000016303127,0.00038125424,0.00033922007,0.00080077344,0.00019581619],"domain_scores_gemma":[0.9984753,0.00022614036,0.00016413373,0.00016830544,0.0008701469,0.00009595374],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015536281,0.00009391477,0.00013000681,0.0005476767,0.00008729446,0.0010655448,0.002512532,0.00003079258,0.000006512694],"category_scores_gemma":[0.0005762473,0.00007446546,0.000029334456,0.00068549253,0.00015819051,0.004948841,0.00052896753,0.00023352203,0.0000019967863],"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":[0.000031489482,0.00007391284,0.0019086945,0.000027442018,0.00006701115,0.0001301362,0.00070658984,0.0023518365,0.0008142507,0.8463666,0.00030804085,0.14721404],"study_design_scores_gemma":[0.00019422644,0.00016182692,0.0016847108,0.00015280058,0.000009394729,0.00015787312,0.00009244921,0.9732369,0.00010700789,0.022460502,0.0016392197,0.00010309729],"about_ca_topic_score_codex":0.0000102203585,"about_ca_topic_score_gemma":0.00000845814,"teacher_disagreement_score":0.97088504,"about_ca_system_score_codex":0.00009033743,"about_ca_system_score_gemma":0.0019174918,"threshold_uncertainty_score":0.99997145},"labels":[],"label_agreement":null},{"id":"W4399847064","doi":"10.1007/s41060-024-00589-8","title":"Twin neural network improved k-nearest neighbor regression","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; Perimeter Institute; University of Waterloo","funders":"Mitacs","keywords":"Artificial neural network; Regression; k-nearest neighbors algorithm; Artificial intelligence; Pattern recognition (psychology); Computer science; Statistics; Mathematics","score_opus":0.04646352333519553,"score_gpt":0.34085379085422907,"score_spread":0.2943902675190335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399847064","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":[0.22807577,0.0071866396,0.6752317,0.062690526,0.023427052,0.00028213597,0.00021729479,0.00021904563,0.0026698194],"genre_scores_gemma":[0.9768567,0.00063989137,0.020810494,0.00073046295,0.00086292333,3.36126e-7,0.000011157198,0.0000048452307,0.00008320807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983529,0.000020134636,0.00030303508,0.0002802142,0.0008693205,0.00017441207],"domain_scores_gemma":[0.9987628,0.00009968621,0.00014256222,0.00029477876,0.0005692882,0.00013087832],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011889287,0.000083636885,0.00010422052,0.0002728811,0.00011106957,0.0011969295,0.0025411856,0.000028364648,0.000015038074],"category_scores_gemma":[0.00021439882,0.000055833563,0.00003526057,0.0005586133,0.0001486908,0.005336446,0.0008779272,0.0001959662,0.000009287833],"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":[0.00004270152,0.00009181028,0.0011269264,0.000022755663,0.00011367326,0.0005883134,0.00036852658,0.00080275437,0.021001779,0.00982073,0.061682716,0.9043373],"study_design_scores_gemma":[0.00015896693,0.00006819865,0.0006372954,0.00028746613,0.000014046023,0.00028522426,0.00004708281,0.96804696,0.0005873211,0.002088516,0.027683446,0.000095494135],"about_ca_topic_score_codex":0.00000794579,"about_ca_topic_score_gemma":0.0000030842943,"teacher_disagreement_score":0.9672442,"about_ca_system_score_codex":0.000039269642,"about_ca_system_score_gemma":0.000322832,"threshold_uncertainty_score":0.9998399},"labels":[],"label_agreement":null},{"id":"W4401900459","doi":"10.1007/s41060-024-00624-8","title":"A nearest neighbor-based approach for improving the reliability of multiclass probabilistic classifiers","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"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":"Probabilistic logic; Probabilistic classification; k-nearest neighbors algorithm; Reliability (semiconductor); Artificial intelligence; Computer science; Benchmark (surveying); Multiclass classification; Machine learning; Multivariate statistics; Class (philosophy); Pattern recognition (psychology); Support vector machine; Data mining; Naive Bayes classifier","score_opus":0.059764479937032586,"score_gpt":0.34094200030587785,"score_spread":0.28117752036884525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401900459","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":[0.0057668067,0.00010863691,0.9880603,0.0053952485,0.0003652295,0.00009804415,0.00008280197,0.000012568171,0.00011036804],"genre_scores_gemma":[0.914734,0.000015362923,0.08501385,0.00009924276,0.00010209553,0.0000014968116,0.000018959776,0.0000029771252,0.000012030925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983611,0.00003813604,0.0003755935,0.00031035423,0.0007933027,0.00012151043],"domain_scores_gemma":[0.99769026,0.0004831797,0.00025436332,0.00054476806,0.0009614111,0.000066028275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036692799,0.0000716389,0.000107135915,0.00020761741,0.000109183384,0.0006113321,0.0030305008,0.00002348657,0.0000010893024],"category_scores_gemma":[0.0027533243,0.000043241576,0.000042353426,0.0004799801,0.00044815513,0.0017352575,0.00035112465,0.00017939325,3.7903695e-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":[0.00015898413,0.00065671536,0.0073965457,0.000651634,0.00017692258,0.000026396416,0.0013063473,0.04273214,0.016884938,0.24918751,0.003157773,0.6776641],"study_design_scores_gemma":[0.00015391885,0.00006578201,0.0012812959,0.00003554012,0.000024523406,0.000019940864,0.00008165255,0.99381787,0.00013049014,0.0006849658,0.00365354,0.000050483166],"about_ca_topic_score_codex":0.000024381532,"about_ca_topic_score_gemma":0.0000024445883,"teacher_disagreement_score":0.95108575,"about_ca_system_score_codex":0.00007124379,"about_ca_system_score_gemma":0.000858118,"threshold_uncertainty_score":0.58950895},"labels":[],"label_agreement":null},{"id":"W4403155585","doi":"10.1007/s41060-024-00653-3","title":"A comparative exploration of two diffusion generative models on tabular data synthesis","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University","funders":"","keywords":"Generative grammar; Diffusion; Computer science; Artificial intelligence; Physics","score_opus":0.25329261161035516,"score_gpt":0.4105372524801282,"score_spread":0.15724464086977302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403155585","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":[0.010180502,0.00038435656,0.970907,0.017062448,0.0005613082,0.00005482144,0.0005341006,0.000031064705,0.00028444367],"genre_scores_gemma":[0.8059487,0.0008694009,0.19293995,0.00009305272,0.00010247672,6.198457e-7,0.000037203474,0.0000029547405,0.000005676799],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750704,0.00004190389,0.0004212708,0.00047530027,0.001423654,0.00013084279],"domain_scores_gemma":[0.9952033,0.00035079705,0.00028109385,0.003389961,0.00071225676,0.000062545914],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0019506894,0.000105567255,0.00019807466,0.00060892664,0.00008166103,0.0005837109,0.03588823,0.000027683143,0.0000036662368],"category_scores_gemma":[0.005206475,0.00007913583,0.000021375696,0.00072078774,0.00038674087,0.014919609,0.03905484,0.000198979,0.0000029334458],"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":[0.000094777,0.0008448978,0.00020703016,0.00006007803,0.00083832623,0.00049819506,0.0017769231,0.0071665407,0.038149603,0.46511865,0.15010278,0.3351422],"study_design_scores_gemma":[0.000112427224,0.00005668104,0.000013592011,0.00020979921,0.000020794116,0.00002962158,0.00013192624,0.91996825,0.006541333,0.071887426,0.0009525336,0.000075600685],"about_ca_topic_score_codex":0.000016135362,"about_ca_topic_score_gemma":0.000009425318,"teacher_disagreement_score":0.91280174,"about_ca_system_score_codex":0.00008070161,"about_ca_system_score_gemma":0.00041009954,"threshold_uncertainty_score":0.9988582},"labels":[],"label_agreement":null},{"id":"W4405127663","doi":"10.1007/s41060-024-00693-9","title":"AI-generated or AI touch-up? Identifying AI contribution in text data","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Data science","score_opus":0.1328814845314103,"score_gpt":0.4163926192477443,"score_spread":0.283511134716334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405127663","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":[0.012056289,0.00048141583,0.96121234,0.02372802,0.0023075158,0.00004391217,0.00011965699,0.00001793004,0.000032935666],"genre_scores_gemma":[0.99012256,0.00036411986,0.0070908354,0.0019428139,0.0003550848,2.177152e-7,0.000043561875,0.0000035617809,0.00007724706],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766207,0.000029251218,0.00051102374,0.00045021664,0.00115148,0.00019598148],"domain_scores_gemma":[0.9981402,0.00009069626,0.0001319104,0.0006504382,0.0008866827,0.00010003948],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024579263,0.00008843244,0.00014076516,0.00058631296,0.00008115689,0.0019605388,0.00537567,0.000032178923,0.000016201633],"category_scores_gemma":[0.0007696345,0.000066573244,0.00001844594,0.0009105675,0.0001231802,0.010583052,0.0019640431,0.00030270006,0.0000070354477],"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":[0.00012903928,0.000329383,0.00792354,0.00009015176,0.00047794916,0.0036930903,0.0017536901,0.007831796,0.028827187,0.18754564,0.06692675,0.6944718],"study_design_scores_gemma":[0.00023990277,0.000023973393,0.00024207002,0.00019489297,0.000012952975,0.00028473412,0.00004188548,0.9852044,0.00045053632,0.002179276,0.011039436,0.0000859136],"about_ca_topic_score_codex":0.00005273513,"about_ca_topic_score_gemma":0.00009221342,"teacher_disagreement_score":0.97806627,"about_ca_system_score_codex":0.0001378837,"about_ca_system_score_gemma":0.0010771694,"threshold_uncertainty_score":0.99907553},"labels":[],"label_agreement":null},{"id":"W4406609300","doi":"10.1007/s41060-025-00717-y","title":"Supervised graph embedding for classification using discriminating frequent patterns","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Dhaka; University Grants Commission of Bangladesh; University of Manitoba","keywords":"Pattern recognition (psychology); Artificial intelligence; Embedding; Computer science; Graph; Machine learning; Theoretical computer science","score_opus":0.12141518112245384,"score_gpt":0.4118745984518881,"score_spread":0.29045941732943426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406609300","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":[0.047608256,0.00010840652,0.94962174,0.0018296384,0.0007160056,0.000053669217,0.000024510142,0.0000073421247,0.000030403891],"genre_scores_gemma":[0.8394482,0.00018795508,0.15991555,0.00033652526,0.000097924494,5.179459e-7,0.00000618243,0.0000025138897,0.0000045850197],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855906,0.00001559265,0.00037937268,0.00028016386,0.00060138415,0.0001644189],"domain_scores_gemma":[0.9981257,0.00015465295,0.0002916209,0.00032529834,0.0010369079,0.000065839595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000997276,0.00008011644,0.00011614708,0.0005171829,0.0001786247,0.00044552525,0.0028371753,0.000021343294,7.092131e-7],"category_scores_gemma":[0.00028309316,0.000067186535,0.000040334686,0.000584332,0.00014468495,0.0037311583,0.0005666717,0.00011292793,8.799462e-8],"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":[0.00004572167,0.00020440231,0.022826688,0.000054082433,0.00021492488,0.000053624186,0.00058283476,0.009635101,0.10232366,0.26050925,0.0009598847,0.6025898],"study_design_scores_gemma":[0.0002664328,0.00002455245,0.0020141227,0.00014937918,0.000017259988,0.000034174824,0.00017786262,0.9865249,0.00077886105,0.00949673,0.00043977535,0.000075975644],"about_ca_topic_score_codex":0.000004841449,"about_ca_topic_score_gemma":0.000003121501,"teacher_disagreement_score":0.9768898,"about_ca_system_score_codex":0.00008535914,"about_ca_system_score_gemma":0.00019775284,"threshold_uncertainty_score":0.5272225},"labels":[],"label_agreement":null},{"id":"W4408166864","doi":"10.1007/s41060-025-00737-8","title":"Enhanced anomaly detection through a Bayesian framework with a novel network merging structure learning approach","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Research Manitoba","keywords":"Anomaly detection; Bayesian network; Anomaly (physics); Computer science; Artificial intelligence; Bayesian probability; Machine learning; Physics","score_opus":0.02783018688427642,"score_gpt":0.3090371544783123,"score_spread":0.2812069675940359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408166864","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":[0.009411202,0.00010896179,0.98883027,0.00068989967,0.00042156526,0.000029616882,0.0000053286985,0.000015565265,0.00048756305],"genre_scores_gemma":[0.730105,0.00006536747,0.26939592,0.000276658,0.00013303536,2.021606e-7,0.0000018098436,0.000002471018,0.000019562636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828887,0.000023161818,0.00030728494,0.00036080938,0.00080551533,0.00021433002],"domain_scores_gemma":[0.99837667,0.00008268917,0.00029625016,0.0003251291,0.00084730034,0.000071973875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080748624,0.00011457035,0.0001626882,0.00022703278,0.00023258266,0.0006841927,0.0024882308,0.000049921866,0.0000020482414],"category_scores_gemma":[0.0002700914,0.000086705615,0.00002389696,0.0011340957,0.0002063735,0.0028084347,0.00051964185,0.00043596313,2.1973018e-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":[0.00021262674,0.00030068806,0.004164698,0.00005354077,0.0007684881,0.00007196117,0.003505856,0.33205894,0.038898613,0.3633652,0.00041158602,0.2561878],"study_design_scores_gemma":[0.0003176071,0.000098598655,0.00051581935,0.0002797959,0.00003499729,0.00015809572,0.00018815338,0.98405975,0.0016693914,0.011779806,0.0007480165,0.0001499846],"about_ca_topic_score_codex":0.000015636126,"about_ca_topic_score_gemma":0.000009755759,"teacher_disagreement_score":0.72069377,"about_ca_system_score_codex":0.00006444445,"about_ca_system_score_gemma":0.0004737079,"threshold_uncertainty_score":0.6597686},"labels":[],"label_agreement":null},{"id":"W4410728601","doi":"10.1007/s41060-025-00799-8","title":"A data-driven approach for predicting crime occurrence using machine learning models","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.3388764596217803,"score_gpt":0.4783996502889309,"score_spread":0.13952319066715058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410728601","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":[0.041323423,0.00051602186,0.95008314,0.0014057952,0.00088823924,0.00014708942,0.0020427224,0.000014501081,0.003579054],"genre_scores_gemma":[0.9728684,0.0003036898,0.026181558,0.00011742166,0.00026242714,4.6154668e-7,0.0001427345,0.0000026590176,0.000120666955],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984983,0.000037935624,0.00035025264,0.00024895594,0.00069850584,0.00016605505],"domain_scores_gemma":[0.9982739,0.000111246954,0.000278743,0.00023278256,0.0010257281,0.0000775763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029032212,0.00006234704,0.000121821795,0.00031792079,0.00048715653,0.00045581604,0.0026162337,0.000024618796,0.00001625473],"category_scores_gemma":[0.0012980083,0.00005508192,0.000037610225,0.00033164478,0.00039135237,0.003258864,0.0007925255,0.00016265053,1.9994954e-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":[0.00047278652,0.0029137675,0.3160058,0.0004083999,0.0028286073,0.00008194404,0.017081596,0.14160146,0.006759717,0.20082572,0.04182116,0.26919904],"study_design_scores_gemma":[0.00019669729,0.000021717386,0.00014281149,0.00010288209,0.000070244976,0.000008386055,0.0017571775,0.98682,0.000014169794,0.000540175,0.0102699725,0.000055804547],"about_ca_topic_score_codex":0.00041974857,"about_ca_topic_score_gemma":0.00011252073,"teacher_disagreement_score":0.93154496,"about_ca_system_score_codex":0.00009012336,"about_ca_system_score_gemma":0.0006469128,"threshold_uncertainty_score":0.48616567},"labels":[],"label_agreement":null},{"id":"W4411713554","doi":"10.1007/s41060-025-00856-2","title":"Toward sustainable smart cities: applications, challenges, and future directions","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Smart Cities and Technologies","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Architectural engineering; Environmental planning; Business; Geography; Engineering","score_opus":0.02942311108253774,"score_gpt":0.2831123824605666,"score_spread":0.2536892713780288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411713554","genre_codex":"review","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":[0.12798414,0.58052623,0.058754623,0.12461764,0.007494982,0.0007499836,0.00051291037,0.00066403067,0.09869545],"genre_scores_gemma":[0.7684473,0.2280265,0.0026227012,0.00017406628,0.00048256965,0.0000037587315,0.000008344819,0.000005849291,0.00022895154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942404,0.0000024854303,0.00015239322,0.000095854964,0.00022604296,0.00009917766],"domain_scores_gemma":[0.99937034,0.000035179313,0.00003807388,0.00014907008,0.00037537154,0.000031942287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032760893,0.0000522267,0.00008010553,0.0003514634,0.000077967474,0.00013196447,0.00060903945,0.000027185157,0.0000044499893],"category_scores_gemma":[0.0000665412,0.000044564244,0.000011144561,0.00022604466,0.00020158684,0.0008047031,0.00023574506,0.000102962484,3.121543e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007633563,0.000034339395,0.00083483226,0.0001086045,0.00022856484,0.00003777638,0.0004912202,0.00006935905,0.00008437498,0.32695627,0.005833062,0.66531396],"study_design_scores_gemma":[0.000117893615,0.000012979842,0.001909984,0.000029327655,0.000021144087,0.00006837323,0.009222277,0.0038724751,0.000066003595,0.006615147,0.9780055,0.000058872174],"about_ca_topic_score_codex":0.0000061776036,"about_ca_topic_score_gemma":0.0000043701,"teacher_disagreement_score":0.97217244,"about_ca_system_score_codex":0.000057440287,"about_ca_system_score_gemma":0.00009199921,"threshold_uncertainty_score":0.1817277},"labels":[],"label_agreement":null},{"id":"W4412623152","doi":"10.1007/s41060-025-00870-4","title":"Impact of hotel responses to online reviews on customer loyalty and acquisition: a longitudinal sentiment analysis with booking","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Advertising; Loyalty; Loyalty business model; Sentiment analysis; Marketing; Business; Computer science; Artificial intelligence; Service quality; Service (business)","score_opus":0.06655442216595538,"score_gpt":0.45025355130028216,"score_spread":0.3836991291343268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412623152","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":[0.9949408,0.00020171792,0.0005451967,0.0022312202,0.000120049765,0.00006228212,0.00009839254,0.0000027426197,0.0017975835],"genre_scores_gemma":[0.99805033,0.00065356155,0.00074550655,0.00021198031,0.0001065619,2.4302764e-7,0.0000047112717,0.000001490118,0.00022560067],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99841285,0.000072144845,0.00030725254,0.00017375032,0.0009084787,0.00012555053],"domain_scores_gemma":[0.9984187,0.00023062038,0.00026473452,0.00014057287,0.00080972747,0.00013564777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002793361,0.00006911369,0.0002275052,0.0006875727,0.00014454077,0.00022989459,0.00060836005,0.00001960195,0.0000159312],"category_scores_gemma":[0.0014884713,0.00004796848,0.000059318987,0.0011963007,0.0004803167,0.00065544434,0.00015784321,0.000080628124,6.2278065e-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":[0.0009142426,0.00047160164,0.90795225,0.000019960196,0.0014814336,0.000066059605,0.0028524478,0.00022175764,0.00030951315,0.0026525944,0.0034181918,0.07963997],"study_design_scores_gemma":[0.0005295453,0.0003993168,0.9829352,0.0008855259,0.0006476921,0.000010195512,0.0021776627,0.00060523895,0.000042257423,0.00028496914,0.011294051,0.00018832933],"about_ca_topic_score_codex":0.00017188027,"about_ca_topic_score_gemma":0.0002112387,"teacher_disagreement_score":0.07945164,"about_ca_system_score_codex":0.00013026794,"about_ca_system_score_gemma":0.00054856815,"threshold_uncertainty_score":0.22168788},"labels":[],"label_agreement":null},{"id":"W4416776409","doi":"10.1007/s41060-025-00884-y","title":"Social media data mining of human behaviour during bushfire evacuation","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Institute of Standards and Technology","keywords":"Geolocation; Social media; Geotagging; Resource (disambiguation); Data collection; Lexicon; Open data","score_opus":0.16141861766578683,"score_gpt":0.4751142063894374,"score_spread":0.31369558872365055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416776409","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":[0.98525274,0.00019321546,0.00072654814,0.008761218,0.00032429502,0.000040183564,0.00009213424,0.0000056702866,0.0046040197],"genre_scores_gemma":[0.9982762,0.0003772688,0.0010248785,0.000030611503,0.00017067623,1.5843662e-7,0.000065357795,0.0000015088326,0.000053340173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9983168,0.000052990392,0.000386545,0.00013803932,0.0010107071,0.00009487743],"domain_scores_gemma":[0.99779576,0.00012607501,0.000396535,0.00035396084,0.0012827242,0.00004495039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032429446,0.000042279786,0.00010107507,0.00041061104,0.00050966156,0.00022344514,0.0033473023,0.000034989353,0.00001602021],"category_scores_gemma":[0.0016436845,0.000039554816,0.000017880157,0.00058468815,0.0005247502,0.002929281,0.0007917493,0.000105365514,3.0078866e-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":[0.00007639926,0.0008019475,0.31459764,0.000035216286,0.0005468979,0.000022619064,0.038456902,0.00005930081,0.012608958,0.32020757,0.019800195,0.29278636],"study_design_scores_gemma":[0.002381847,0.00006632076,0.8453893,0.0006286937,0.00055700564,0.000024970828,0.08627123,0.023267206,0.0007884148,0.012536958,0.027610132,0.00047789613],"about_ca_topic_score_codex":0.0001224978,"about_ca_topic_score_gemma":0.0003337563,"teacher_disagreement_score":0.5307917,"about_ca_system_score_codex":0.00008702218,"about_ca_system_score_gemma":0.0006945052,"threshold_uncertainty_score":0.6220176},"labels":[],"label_agreement":null},{"id":"W4416940015","doi":"10.1007/s41060-025-00885-x","title":"Sequential Bayesian estimation of the F1 score using the Dirichlet-multinomial model","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Manitoba","funders":"","keywords":"Benchmark (surveying); Metric (unit); Bayesian probability; Sample (material); Point estimation; Sample size determination; Bayesian inference; Prior probability; Class (philosophy)","score_opus":0.0841653532904757,"score_gpt":0.3783429684597155,"score_spread":0.2941776151692398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416940015","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":[0.0138399955,0.000024728464,0.9815343,0.0040353728,0.0003492076,0.000050135066,0.00004151595,0.00000591308,0.00011885408],"genre_scores_gemma":[0.8990269,0.00003298972,0.100559786,0.0003168555,0.00004137453,2.3131662e-7,0.0000027659823,0.000001403404,0.000017711483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985131,0.000028690556,0.0003734988,0.00016873486,0.0008238802,0.000092066635],"domain_scores_gemma":[0.9980291,0.000066256725,0.00044990584,0.00061454554,0.00081240915,0.000027763748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013453262,0.00006034591,0.00008920796,0.00022109848,0.00016398894,0.00029856892,0.005112322,0.000021271599,8.9385946e-7],"category_scores_gemma":[0.000529138,0.000035169913,0.00003052485,0.00061402837,0.00045930292,0.0022790527,0.0012384318,0.00013158971,1.3984605e-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":[0.000057592308,0.0003008887,0.008895353,0.000039093793,0.00025690018,0.000013644049,0.0010318608,0.13590051,0.1141678,0.47871146,0.007291285,0.2533336],"study_design_scores_gemma":[0.00010427342,0.000006354243,0.0009801657,0.0000644358,0.000016923184,0.00002514321,0.000025134766,0.98642063,0.0077484204,0.004370196,0.00020337527,0.000034922312],"about_ca_topic_score_codex":0.000016802594,"about_ca_topic_score_gemma":0.0000034366242,"teacher_disagreement_score":0.8851869,"about_ca_system_score_codex":0.00009048893,"about_ca_system_score_gemma":0.0008571147,"threshold_uncertainty_score":0.9500051},"labels":[],"label_agreement":null},{"id":"W4417145987","doi":"10.1007/s41060-025-00934-5","title":"A novel multilevel taxonomical approach for describing high-dimensional unlabeled movement data","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Morphological variations and asymmetry","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; Linnéuniversitetet","keywords":"Anomaly detection; Movement (music); Outlier; Scale (ratio); Variable (mathematics); Face (sociological concept)","score_opus":0.302275681033034,"score_gpt":0.3948436289704082,"score_spread":0.09256794793737422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417145987","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":[0.024223767,0.00003304535,0.9725649,0.001650746,0.00031572313,0.00011819749,0.0009508702,0.0000052151927,0.00013756147],"genre_scores_gemma":[0.38016757,0.000016104184,0.6189521,0.00054636406,0.00013331845,0.0000011990894,0.00011787453,0.0000033223243,0.000062188315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983567,0.000012053214,0.00051461323,0.00033098855,0.0006295729,0.00015606059],"domain_scores_gemma":[0.99791807,0.0003873817,0.00030653126,0.0004792083,0.0008285826,0.00008022084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002382872,0.00009446447,0.00019731327,0.00028877144,0.00013434513,0.00019549944,0.0023506142,0.000038098005,0.000012051999],"category_scores_gemma":[0.0026245774,0.00006962068,0.000030225556,0.0002339803,0.00018785166,0.0010100197,0.0013484636,0.0001354546,3.862798e-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":[0.00025860092,0.0029199314,0.0021605818,0.00007026908,0.0010413853,0.000023264382,0.000053400145,0.0008381208,0.038143523,0.8168468,0.07092278,0.066721365],"study_design_scores_gemma":[0.001767539,0.00005392543,0.0010965848,0.00010703714,0.00014676065,0.00003550246,0.00013071689,0.9793202,0.0005722831,0.013954339,0.00267133,0.0001437675],"about_ca_topic_score_codex":0.000018348233,"about_ca_topic_score_gemma":0.0000027626036,"teacher_disagreement_score":0.97848207,"about_ca_system_score_codex":0.00008627784,"about_ca_system_score_gemma":0.0003865622,"threshold_uncertainty_score":0.4368065},"labels":[],"label_agreement":null}]}