{"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040397912,0.00033779445,0.95731264,0.000110593406,0.00005832216,0.000036936555,0.00016135056,0.0011371376,0.00044735093],"genre_scores_gemma":[0.6633077,0.0002600269,0.33249888,0.00008474308,0.00024389275,0.00012701246,0.0013930281,0.00023025814,0.0018544503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835217,0.00044833284,0.000100857906,0.000336499,0.00055507466,0.0002071976],"domain_scores_gemma":[0.9970282,0.0011990711,0.00028834227,0.00055238174,0.00079802866,0.00013411399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019663929,0.0009427776,0.0018433557,0.0029235873,0.0008418314,0.0011601218,0.0017117254,0.00090207567,0.0011672109],"category_scores_gemma":[0.0060849176,0.0002911862,0.001319558,0.0027528428,0.0005981455,0.0014960449,0.0011426036,0.0011429503,0.0007644268],"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":[0.0005774291,0.00060240336,0.009908732,0.00016013057,0.000343729,0.0002077824,0.00015719188,0.13994096,0.024316521,0.009469042,0.009348407,0.80496764],"study_design_scores_gemma":[0.000014326866,0.0000721864,0.0025269499,0.000005820968,0.000036862977,0.000102831866,0.000050111754,0.98466337,0.0031028334,0.008530624,0.00087295746,0.00002111439],"about_ca_topic_score_codex":0.0033987744,"about_ca_topic_score_gemma":0.0056895744,"teacher_disagreement_score":0.0033987744,"about_ca_system_score_codex":0.00042200997,"about_ca_system_score_gemma":0.0011923721,"threshold_uncertainty_score":0.010399401},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32566795,0.0028138491,0.6596156,0.0007032041,0.0003705586,0.00037198124,0.0030380285,0.0016994623,0.005719419],"genre_scores_gemma":[0.92373466,0.0004803067,0.06926335,0.00013648409,0.00021119743,0.00014037662,0.0028891864,0.00004700275,0.0030974238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812084,0.00024855058,0.00016882212,0.0005428339,0.0007212938,0.00019760056],"domain_scores_gemma":[0.99670875,0.0013543147,0.00026435233,0.00033074876,0.0011633068,0.00017849909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009632082,0.0007825274,0.0018732037,0.0051537766,0.00089510245,0.0011243359,0.0029881955,0.0014315302,0.001907162],"category_scores_gemma":[0.0054422244,0.00045250304,0.001505499,0.0057702665,0.00044493395,0.002095133,0.0013314013,0.0007682472,0.0012349372],"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":[0.0018550853,0.0016397799,0.113486245,0.00070222083,0.0012823663,0.00076304784,0.0006075558,0.18725485,0.0154548995,0.007640166,0.01876852,0.6505452],"study_design_scores_gemma":[0.00003203307,0.00012835793,0.007528071,0.000024038956,0.0001343964,0.00024520996,0.00010433953,0.98671085,0.0012900117,0.0027654623,0.0009955497,0.00004171331],"about_ca_topic_score_codex":0.024903538,"about_ca_topic_score_gemma":0.04608628,"teacher_disagreement_score":0.024903538,"about_ca_system_score_codex":0.000733826,"about_ca_system_score_gemma":0.0012626034,"threshold_uncertainty_score":0.049517155},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014892829,0.00044134047,0.97634876,0.00074389327,0.00020387195,0.000075782555,0.00060131017,0.0007364923,0.0059558186],"genre_scores_gemma":[0.43364307,0.0007506523,0.55182165,0.00066295016,0.0005763057,0.00034366513,0.0023566603,0.00046030167,0.009384796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964826,0.00094461243,0.00016086099,0.000504926,0.0015049493,0.00040208825],"domain_scores_gemma":[0.98875207,0.006687867,0.00046958544,0.0021975448,0.0015759428,0.00031706755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002538986,0.0015972232,0.0016986601,0.0012611048,0.00073380326,0.002625351,0.0021576139,0.0018588506,0.015796166],"category_scores_gemma":[0.023180513,0.0005783684,0.00095627026,0.0025172,0.0016834361,0.0061114547,0.0022695204,0.003063312,0.0026637109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012601736,0.0004798182,0.0018480079,0.0007733736,0.0001534656,0.00037206514,0.00019251286,0.25100207,0.008509047,0.40421417,0.043093573,0.2881018],"study_design_scores_gemma":[0.000045380377,0.000048659258,0.00019568467,0.000026554106,0.000018326484,0.00009983946,0.000038383692,0.758113,0.0017657778,0.23813862,0.0014909355,0.000018696766],"about_ca_topic_score_codex":0.002294174,"about_ca_topic_score_gemma":0.0034990446,"teacher_disagreement_score":0.015796166,"about_ca_system_score_codex":0.0010558064,"about_ca_system_score_gemma":0.0022560144,"threshold_uncertainty_score":0.052843392},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021603644,0.00047102623,0.9766117,0.000060523056,0.000052184685,0.000027735385,0.00014078718,0.00059121434,0.00044129306],"genre_scores_gemma":[0.41013592,0.00085587124,0.5839345,0.0001029156,0.00021807624,0.00013849996,0.0015775983,0.0004118057,0.0026248859],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952114,0.00012400234,0.00004791959,0.00012584921,0.00012743726,0.0000536632],"domain_scores_gemma":[0.99827385,0.0010696098,0.00010990272,0.00015542861,0.00030523262,0.00008586261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013320722,0.0007196461,0.00087593414,0.0010485651,0.0003707791,0.0007554981,0.0007494961,0.00056072813,0.0022595332],"category_scores_gemma":[0.0042390223,0.0002624254,0.0006962758,0.00085074484,0.00029038003,0.0009600925,0.0008592874,0.00085804006,0.0010116551],"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":[0.0014730914,0.00029619609,0.0030521841,0.00024482523,0.000200394,0.00019256107,0.0001441498,0.07374844,0.11355402,0.006753852,0.0033242726,0.79701596],"study_design_scores_gemma":[0.000023004226,0.00006421139,0.0023787327,0.000014242978,0.000051690156,0.000082154176,0.000024270372,0.9786925,0.014857726,0.0024848853,0.0013036263,0.000022921382],"about_ca_topic_score_codex":0.0015474727,"about_ca_topic_score_gemma":0.002487779,"teacher_disagreement_score":0.0022595332,"about_ca_system_score_codex":0.00023067492,"about_ca_system_score_gemma":0.00063410884,"threshold_uncertainty_score":0.0075588822},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5239964,0.0020044772,0.41178557,0.0030833015,0.0004336836,0.00026003763,0.015789218,0.026695773,0.01595147],"genre_scores_gemma":[0.9175246,0.0008465833,0.07375162,0.00018066877,0.00016626107,0.000063749,0.0042743282,0.0004908502,0.0027014094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998467,0.000020320476,0.000010327775,0.000020438683,0.00007085431,0.000031308315],"domain_scores_gemma":[0.999204,0.0003397455,0.000110604306,0.00006495156,0.00020488609,0.00007579817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038474074,0.0004879676,0.0003033234,0.0027497292,0.00025225742,0.0015847288,0.00034670616,0.0003922186,0.004962024],"category_scores_gemma":[0.001614302,0.00017025413,0.00032371568,0.0016057548,0.00018388624,0.0008655537,0.0008795757,0.00050761306,0.00046851384],"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":[0.0019920778,0.00035372085,0.03341123,0.0017875698,0.00029019342,0.00203187,0.0032158433,0.10445958,0.16315195,0.012354097,0.055647627,0.62130415],"study_design_scores_gemma":[0.00010916514,0.00021151602,0.06588909,0.000285653,0.000120854165,0.00089018024,0.001980893,0.82270825,0.03127007,0.026320627,0.05010576,0.00010791092],"about_ca_topic_score_codex":0.004034815,"about_ca_topic_score_gemma":0.0051567825,"teacher_disagreement_score":0.004962024,"about_ca_system_score_codex":0.0002652576,"about_ca_system_score_gemma":0.00038878652,"threshold_uncertainty_score":0.016599655},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71123385,0.0016029741,0.2640372,0.0007131059,0.00014017029,0.00023829196,0.014140169,0.0017257797,0.006168537],"genre_scores_gemma":[0.9200028,0.00036977217,0.06929291,0.000050785715,0.00005866801,0.00008926296,0.008988923,0.000057496633,0.0010892173],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986034,0.00019912128,0.00016968226,0.00043924004,0.00043959185,0.00014899079],"domain_scores_gemma":[0.99543935,0.0021152447,0.0007955235,0.0007354682,0.000692522,0.00022189876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006269143,0.0007912348,0.00081564503,0.0058934037,0.0005988545,0.0017168238,0.0012890139,0.0008155039,0.001865061],"category_scores_gemma":[0.0061803805,0.0004793795,0.0012014643,0.008878174,0.00047100036,0.0026795631,0.0011452929,0.0009519949,0.0011987453],"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":[0.0013161154,0.0008646792,0.552585,0.000828613,0.0014266976,0.0051308023,0.0011008665,0.10737601,0.012812895,0.012534955,0.013020624,0.29100275],"study_design_scores_gemma":[0.000052076124,0.00018885967,0.07307338,0.0001118596,0.0005121493,0.0023523543,0.0014192547,0.87317973,0.0049778903,0.03592463,0.00814584,0.000061932165],"about_ca_topic_score_codex":0.008905873,"about_ca_topic_score_gemma":0.019184107,"teacher_disagreement_score":0.008905873,"about_ca_system_score_codex":0.00044352617,"about_ca_system_score_gemma":0.0010238664,"threshold_uncertainty_score":0.017708123},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020615903,0.00035293878,0.75876516,0.0003595995,0.00012366439,0.00024503606,0.008494374,0.2274397,0.0021579582],"genre_scores_gemma":[0.06588608,0.0007144292,0.8709725,0.0006839565,0.00010553712,0.000692945,0.03127045,0.024453111,0.0052209673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996157,0.00081683096,0.0004924883,0.0009862771,0.00130964,0.00023784924],"domain_scores_gemma":[0.9933073,0.0028455292,0.00024597108,0.002559891,0.00074737205,0.00029396353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004797739,0.0024258867,0.0018307301,0.002203522,0.0008845676,0.006204493,0.0058940463,0.0017199927,0.04503987],"category_scores_gemma":[0.021767247,0.0025101607,0.002671044,0.0028291338,0.0011380515,0.009766327,0.0062787444,0.004113149,0.021337321],"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":[0.001981035,0.00069862406,0.0043340386,0.001979566,0.000779442,0.00049080147,0.000993141,0.022164475,0.009369441,0.08157659,0.26814255,0.6074903],"study_design_scores_gemma":[0.0009093452,0.00034583316,0.0015512047,0.00045638793,0.0003111018,0.0006211731,0.00053609326,0.49104017,0.035209116,0.25289163,0.21584322,0.00028473896],"about_ca_topic_score_codex":0.005081676,"about_ca_topic_score_gemma":0.006884064,"teacher_disagreement_score":0.04503987,"about_ca_system_score_codex":0.0008591576,"about_ca_system_score_gemma":0.0029570577,"threshold_uncertainty_score":0.15067333},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023180721,0.000037402115,0.9963509,0.00005139163,0.000031707335,0.00002648565,0.00005937567,0.00059976656,0.00052489096],"genre_scores_gemma":[0.048750248,0.000085688735,0.94787496,0.000106841384,0.00004048707,0.00021768386,0.00039079876,0.00089332636,0.0016398899],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856335,0.00053228997,0.000080501384,0.0002387428,0.00047863653,0.00010656537],"domain_scores_gemma":[0.9975938,0.00077228935,0.00015519495,0.0005478922,0.0008011882,0.00012963438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002406264,0.0008766731,0.0006665978,0.0015328352,0.0007299452,0.0016977555,0.0011109277,0.0008893319,0.0064100046],"category_scores_gemma":[0.008923352,0.00054712454,0.0010391799,0.0012915068,0.0012817009,0.0010864333,0.002070875,0.002252177,0.004780902],"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":[0.00017132642,0.00015715515,0.0018603952,0.00026727258,0.00010207145,0.00013830062,0.00036718274,0.13809781,0.022497939,0.2767017,0.019859742,0.5397791],"study_design_scores_gemma":[0.00001999947,0.00005981026,0.00039344036,0.00004900186,0.000011736861,0.000072516814,0.00005840648,0.85957754,0.0061277486,0.12276257,0.01083557,0.000031671338],"about_ca_topic_score_codex":0.0017946057,"about_ca_topic_score_gemma":0.002143036,"teacher_disagreement_score":0.0064100046,"about_ca_system_score_codex":0.0006124618,"about_ca_system_score_gemma":0.0019624887,"threshold_uncertainty_score":0.021443605},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03615867,0.00096608844,0.961079,0.00041384457,0.00019210204,0.00009489358,0.00016737918,0.0003531741,0.0005749258],"genre_scores_gemma":[0.7051296,0.0008789705,0.2888438,0.00040018331,0.0006421884,0.00033216522,0.001311876,0.00014163747,0.0023194554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972138,0.0013273566,0.00021759678,0.00043791783,0.0005790734,0.00022440066],"domain_scores_gemma":[0.9832751,0.011402856,0.0009978096,0.00212491,0.00184192,0.00035738744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013089406,0.0009405087,0.0021420096,0.0017490425,0.0010175422,0.0015597949,0.00309123,0.001764568,0.0016322215],"category_scores_gemma":[0.033536978,0.0007677447,0.0012035593,0.0014076775,0.001009157,0.0027764328,0.0021170801,0.0020699124,0.0004809235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010144947,0.00042774453,0.009013041,0.0002062589,0.0003974247,0.0002480937,0.00039087344,0.70912945,0.0034200202,0.04222272,0.005979295,0.22755055],"study_design_scores_gemma":[0.000016163634,0.000024624956,0.0002850081,0.000009328875,0.000015473639,0.000012613798,0.00001836757,0.98964053,0.00035377726,0.009269538,0.00034935612,0.000005226118],"about_ca_topic_score_codex":0.00635886,"about_ca_topic_score_gemma":0.006447055,"teacher_disagreement_score":0.013089406,"about_ca_system_score_codex":0.0012101952,"about_ca_system_score_gemma":0.0014379539,"threshold_uncertainty_score":0.06922424},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41862106,0.00036280908,0.5780848,0.00079293473,0.000033455286,0.00009034659,0.00037347045,0.00024527794,0.0013958714],"genre_scores_gemma":[0.9752421,0.00005282377,0.024148557,0.000028989127,0.000018079965,0.0000239673,0.00012278557,0.000010215335,0.00035237198],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785846,0.0011110855,0.00014622314,0.000372909,0.0003122874,0.00019909877],"domain_scores_gemma":[0.982582,0.011049002,0.002511344,0.0018190746,0.0014744668,0.0005641502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041738697,0.0005802261,0.000778459,0.0017121972,0.0007518202,0.0022806635,0.0012815503,0.0013571713,0.0009719432],"category_scores_gemma":[0.023259968,0.0004821796,0.00096392934,0.0013813192,0.0008812068,0.003313676,0.0012903694,0.0016209394,0.00020681274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032553327,0.00021314673,0.10187338,0.000089159636,0.0003157582,0.00041869,0.0012773903,0.831049,0.0020990225,0.015994463,0.0011429697,0.045201413],"study_design_scores_gemma":[0.0000016607847,0.0000144635005,0.0017775232,0.0000059608765,0.000008161628,0.000022447442,0.000057835907,0.9933745,0.00020103433,0.004428888,0.0001007954,0.000006594239],"about_ca_topic_score_codex":0.015621827,"about_ca_topic_score_gemma":0.01670522,"teacher_disagreement_score":0.015621827,"about_ca_system_score_codex":0.0014621448,"about_ca_system_score_gemma":0.00074560253,"threshold_uncertainty_score":0.031061828},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03872891,0.0013053567,0.95652395,0.00017405633,0.00011558342,0.000094802796,0.00026400495,0.0010171189,0.0017761723],"genre_scores_gemma":[0.4177994,0.0011843762,0.57714224,0.00009188974,0.000098369936,0.00015067065,0.0011194008,0.00007579462,0.0023378392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712104,0.000527324,0.00036558133,0.00046565256,0.0013592875,0.00016109413],"domain_scores_gemma":[0.9944194,0.0027011053,0.00036717817,0.0008570586,0.0015532,0.00010213123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024763555,0.0006738475,0.0022932976,0.005032569,0.00089368667,0.0034357912,0.0017461941,0.00091970223,0.0017424328],"category_scores_gemma":[0.012833488,0.000668165,0.0015732545,0.0053133015,0.00037224908,0.0027016567,0.0016102515,0.0012017562,0.0007317823],"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":[0.00051411457,0.00036599216,0.00629083,0.00037267577,0.00048524755,0.00042480664,0.00058953755,0.18534528,0.0043877447,0.013979263,0.0047724796,0.78247213],"study_design_scores_gemma":[0.00001730871,0.000050685714,0.0009290605,0.00005179865,0.0001847076,0.00016115446,0.00009165183,0.9820832,0.0022275082,0.012245625,0.0019377767,0.000019480705],"about_ca_topic_score_codex":0.006975624,"about_ca_topic_score_gemma":0.0049541756,"teacher_disagreement_score":0.006975624,"about_ca_system_score_codex":0.00086335855,"about_ca_system_score_gemma":0.0013549706,"threshold_uncertainty_score":0.01387006},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97523266,0.00062592473,0.021399237,0.00021725219,0.00021209737,0.000083417326,0.0011739436,0.00040740657,0.00064806355],"genre_scores_gemma":[0.9914021,0.000096525684,0.005918839,0.000048499795,0.000052866595,0.00003054424,0.0020674288,0.000022882297,0.00036036436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99821424,0.00051058596,0.00022609715,0.00039774357,0.00044306656,0.00020836534],"domain_scores_gemma":[0.9913902,0.0049098367,0.00070854154,0.0005901532,0.002094251,0.0003070962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005120871,0.00074592413,0.0008474034,0.0010737348,0.00043461728,0.0009705473,0.00089503557,0.0014748275,0.0006725489],"category_scores_gemma":[0.010309944,0.0001612128,0.0007651668,0.00040882474,0.0003381156,0.0007179743,0.0003861906,0.00079556234,0.000565499],"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":[0.004775579,0.001513718,0.6296408,0.00020819054,0.0005099781,0.0005862159,0.00022833551,0.08304487,0.015705833,0.0003969892,0.0056142258,0.2577752],"study_design_scores_gemma":[0.000097047785,0.0017139626,0.18745978,0.000071235874,0.00030073564,0.00064346706,0.00024245838,0.7931227,0.014539986,0.0005406986,0.0012118092,0.000056085373],"about_ca_topic_score_codex":0.0034371286,"about_ca_topic_score_gemma":0.0030401163,"teacher_disagreement_score":0.005120871,"about_ca_system_score_codex":0.0004206356,"about_ca_system_score_gemma":0.00090193306,"threshold_uncertainty_score":0.027082086},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1473689,0.0014994652,0.8346343,0.0007833741,0.00026347835,0.00049101136,0.0020813623,0.002725758,0.010152373],"genre_scores_gemma":[0.9035959,0.00093971327,0.087090015,0.0001298057,0.0003031582,0.00011464668,0.0023491005,0.00014562623,0.005332001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800366,0.0003322528,0.00015950148,0.0004904018,0.00073029177,0.00028385498],"domain_scores_gemma":[0.9956494,0.0016064818,0.0004654338,0.00063084095,0.0014028182,0.00024507722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018505519,0.0010581964,0.0018452967,0.007996021,0.0008478202,0.002091147,0.0015676364,0.0011527088,0.0034611386],"category_scores_gemma":[0.0062515237,0.00042316064,0.0013593173,0.0049006343,0.00097575755,0.00334979,0.0023832233,0.0011248174,0.0022505973],"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":[0.0027845257,0.0011957067,0.045356043,0.0008264699,0.00060507975,0.0019113616,0.00095774914,0.037044886,0.046576433,0.031921092,0.012005501,0.8188151],"study_design_scores_gemma":[0.000057457793,0.0003779805,0.013651063,0.00004991306,0.00045967268,0.0016921391,0.0005903209,0.9452651,0.012755286,0.02050446,0.0045253104,0.00007119342],"about_ca_topic_score_codex":0.0046890387,"about_ca_topic_score_gemma":0.0050235065,"teacher_disagreement_score":0.007996021,"about_ca_system_score_codex":0.0007642942,"about_ca_system_score_gemma":0.0014762488,"threshold_uncertainty_score":0.011578679},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.092535555,0.0023508964,0.89615446,0.0013641368,0.0002625292,0.00012498608,0.0028905603,0.0009495872,0.003367274],"genre_scores_gemma":[0.90882033,0.0019011231,0.07032604,0.00036125726,0.00030299064,0.0003002511,0.0033694967,0.00011203375,0.014506362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882895,0.00035002202,0.00009442959,0.0003366363,0.00021451418,0.00017540342],"domain_scores_gemma":[0.9945642,0.0041346867,0.00033652468,0.00032924427,0.00048713144,0.00014820824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002070617,0.0009491773,0.0027562394,0.0017860755,0.00072791375,0.0015011387,0.003365304,0.002380565,0.006060798],"category_scores_gemma":[0.0067676324,0.001090554,0.0017974852,0.0023619775,0.0009454029,0.0028166387,0.0010985306,0.0022814688,0.0014848065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005030502,0.00023288831,0.004082119,0.0002455876,0.00025888835,0.00024700892,0.00013752392,0.9043088,0.0010962727,0.045086868,0.0036060386,0.04019503],"study_design_scores_gemma":[0.00001282158,0.000018295319,0.00023562342,0.000007423343,0.000024616273,0.000019636267,0.0000041320945,0.99225265,0.00006370481,0.007163324,0.0001889514,0.000008904597],"about_ca_topic_score_codex":0.03205339,"about_ca_topic_score_gemma":0.03877445,"teacher_disagreement_score":0.03205339,"about_ca_system_score_codex":0.0014881025,"about_ca_system_score_gemma":0.0018325069,"threshold_uncertainty_score":0.06373364},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12084381,0.001515356,0.83649933,0.008822908,0.0015651726,0.0015192941,0.0032731174,0.010707389,0.015253576],"genre_scores_gemma":[0.5559317,0.0002775764,0.43293864,0.0015060181,0.000762969,0.0012856562,0.0020225227,0.0010151294,0.0042597894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.80830693,0.12363256,0.014295678,0.020384155,0.029410105,0.003970493],"domain_scores_gemma":[0.34303993,0.50536126,0.031978227,0.07430529,0.03879348,0.006521732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17224576,0.0013380693,0.002556107,0.007355189,0.00449791,0.013805743,0.004369085,0.00575311,0.006393644],"category_scores_gemma":[0.5280723,0.0014795926,0.0012455775,0.0053779474,0.0068865293,0.013116839,0.011374866,0.0043862327,0.0026141405],"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":[0.00656094,0.00077401445,0.13417129,0.0024029333,0.0016690945,0.0005946335,0.010985945,0.015530325,0.012408667,0.18997432,0.04715417,0.5777737],"study_design_scores_gemma":[0.0016047931,0.00062705023,0.018387612,0.0006560889,0.00076571206,0.00068356964,0.005105112,0.27859867,0.04195296,0.59901565,0.052249085,0.0003536449],"about_ca_topic_score_codex":0.003286383,"about_ca_topic_score_gemma":0.0033481682,"teacher_disagreement_score":0.17224576,"about_ca_system_score_codex":0.0031484207,"about_ca_system_score_gemma":0.010764375,"threshold_uncertainty_score":0.9109335},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44332048,0.0019105951,0.53419423,0.00346822,0.0009922105,0.0009979084,0.0024582625,0.0014003182,0.011257796],"genre_scores_gemma":[0.96854603,0.00008627727,0.029286964,0.0003085612,0.00020224613,0.00034762514,0.0006166094,0.00019345853,0.00041216874],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8415381,0.10177542,0.008258536,0.021346001,0.025209472,0.0018724024],"domain_scores_gemma":[0.17157778,0.7157265,0.026338933,0.06626151,0.017952586,0.002142683],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14439763,0.000966095,0.0019345519,0.0038781806,0.0017688122,0.0050478275,0.0040188045,0.003424897,0.0036436075],"category_scores_gemma":[0.62524515,0.00056998886,0.002743644,0.0048426446,0.011505779,0.005577407,0.003669973,0.003416045,0.0009222825],"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":[0.005129197,0.00087511126,0.55655473,0.0018053493,0.008931457,0.0012527752,0.004296195,0.12648363,0.0073097195,0.10571409,0.012154339,0.16949332],"study_design_scores_gemma":[0.0009877972,0.0041481326,0.19355525,0.000645295,0.0023960257,0.0023072248,0.0023476083,0.51030034,0.019709641,0.24873441,0.014364866,0.00050337886],"about_ca_topic_score_codex":0.0024282963,"about_ca_topic_score_gemma":0.0009719807,"teacher_disagreement_score":0.8556024,"about_ca_system_score_codex":0.0015089745,"about_ca_system_score_gemma":0.0019597206,"threshold_uncertainty_score":0.7636568},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031907817,0.00009563727,0.99602985,0.00006874449,0.00002933227,0.00003601777,0.000075719836,0.00023199232,0.0002418685],"genre_scores_gemma":[0.16574813,0.00045650025,0.8232882,0.00021216672,0.0001427857,0.0005246772,0.0021388025,0.00040899214,0.0070797154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751353,0.000810985,0.0001380893,0.0006908621,0.00065172586,0.00019478133],"domain_scores_gemma":[0.99692094,0.001223101,0.00017120563,0.0004835277,0.0010897665,0.00011136282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032275654,0.0009117702,0.0021706666,0.0018800962,0.0014262662,0.0019951654,0.0044986447,0.001571092,0.004339202],"category_scores_gemma":[0.008649982,0.00067359005,0.0021516944,0.0030050187,0.0010652848,0.0031667948,0.0023670055,0.002790842,0.0014919271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046814317,0.0001953687,0.0034121766,0.00024761842,0.0003764877,0.00014933124,0.000340377,0.70231134,0.0039049042,0.051038098,0.0069928733,0.23056334],"study_design_scores_gemma":[0.000008611216,0.000016878732,0.00020418526,0.000008076299,0.000016934891,0.000027736147,0.000023512417,0.9865398,0.00062018586,0.011514802,0.0010070719,0.000012322087],"about_ca_topic_score_codex":0.013303317,"about_ca_topic_score_gemma":0.015170023,"teacher_disagreement_score":0.013303317,"about_ca_system_score_codex":0.001171741,"about_ca_system_score_gemma":0.0028816578,"threshold_uncertainty_score":0.026451766},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029934896,0.0013519196,0.993682,0.0004974065,0.0001236571,0.0000142602275,0.000071181224,0.00023118452,0.0010348262],"genre_scores_gemma":[0.2156913,0.0062024957,0.7733433,0.0003605035,0.00088519976,0.0001055085,0.0003702683,0.00020902738,0.0028324],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981552,0.0006420639,0.0001681646,0.00024970004,0.00072719017,0.000057739144],"domain_scores_gemma":[0.98989546,0.008164827,0.00040321163,0.00078551035,0.00061994465,0.00013094385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024258255,0.0007935423,0.0008525805,0.0028471223,0.00041075496,0.0021123416,0.00079189136,0.0010579601,0.0021488573],"category_scores_gemma":[0.013653091,0.00040245012,0.001110259,0.0038146623,0.0018711418,0.0019733177,0.0013903884,0.002190067,0.00080398674],"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":[0.0002072651,0.00019873894,0.003241711,0.0006848485,0.00025952674,0.0004629623,0.00044108773,0.11909326,0.024596492,0.24084309,0.0041519054,0.60581917],"study_design_scores_gemma":[0.00003116439,0.00006762903,0.0013149948,0.000068105386,0.000041321877,0.0006159176,0.00013020256,0.7288854,0.00595018,0.25185195,0.010998091,0.000045025557],"about_ca_topic_score_codex":0.0014579243,"about_ca_topic_score_gemma":0.0007804835,"teacher_disagreement_score":0.0028471223,"about_ca_system_score_codex":0.0005896613,"about_ca_system_score_gemma":0.0010494371,"threshold_uncertainty_score":0.012829125},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069462303,0.029094536,0.19670051,0.7363617,0.002423007,0.00017526161,0.0004991208,0.00038961548,0.027410043],"genre_scores_gemma":[0.46130767,0.07495655,0.38959825,0.044088084,0.014592472,0.0012444216,0.0017964562,0.0003095965,0.012106416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9849225,0.0075966376,0.0008753713,0.0014267542,0.004360724,0.0008179864],"domain_scores_gemma":[0.897967,0.072467685,0.0028878632,0.010294572,0.011877151,0.0045057307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030130915,0.0011900653,0.0024226015,0.0033759433,0.004709273,0.026210878,0.0072062016,0.012527548,0.010632744],"category_scores_gemma":[0.05596173,0.001383902,0.0012600152,0.0059154276,0.031531565,0.044540003,0.009195374,0.017613148,0.0028814152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019566247,0.00010165817,0.0005579167,0.00044058895,0.000014210372,0.000044377884,0.00036806476,0.0015056061,0.00012050972,0.9566037,0.01585445,0.024369504],"study_design_scores_gemma":[0.0000076333245,0.000007330305,0.000071740295,0.00016309551,0.0000034537293,0.000034145196,0.0008202333,0.005321371,0.00007500336,0.9744899,0.018994667,0.000011402432],"about_ca_topic_score_codex":0.004509994,"about_ca_topic_score_gemma":0.0035579703,"teacher_disagreement_score":0.030130915,"about_ca_system_score_codex":0.010020687,"about_ca_system_score_gemma":0.020969132,"threshold_uncertainty_score":0.15934938},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22804332,0.005138223,0.7549301,0.0013023989,0.00046414707,0.00017781583,0.00181304,0.0044625797,0.0036683213],"genre_scores_gemma":[0.8831682,0.0008041762,0.09961859,0.000835684,0.00038363144,0.00013410032,0.0035336036,0.00034449453,0.011177469],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858487,0.00045913347,0.00007180103,0.00042539652,0.00021775908,0.00024111387],"domain_scores_gemma":[0.9937861,0.0042558713,0.00021063682,0.00088033214,0.0005804621,0.00028661062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023748553,0.0016077352,0.0029114098,0.0016441059,0.00084243884,0.0014330981,0.0030878359,0.0029658435,0.0031636353],"category_scores_gemma":[0.0069692982,0.0012106196,0.0014015071,0.0024764815,0.0008391324,0.0031223688,0.002023035,0.0033738792,0.0023373521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002035775,0.00210862,0.019965218,0.00065706216,0.0012549469,0.0007053451,0.00060450844,0.47593486,0.014943147,0.008435844,0.028394386,0.44496036],"study_design_scores_gemma":[0.000016871245,0.00009016101,0.00073904207,0.000011320059,0.000042927906,0.000048576334,0.000038527767,0.99405813,0.0009601334,0.0034494463,0.00052876736,0.000016054928],"about_ca_topic_score_codex":0.014537259,"about_ca_topic_score_gemma":0.039587144,"teacher_disagreement_score":0.014537259,"about_ca_system_score_codex":0.00085544976,"about_ca_system_score_gemma":0.0012858338,"threshold_uncertainty_score":0.028905272},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017801454,0.0004312046,0.9795939,0.00022324332,0.000112896654,0.000029379262,0.00011977112,0.0004304047,0.0012576727],"genre_scores_gemma":[0.4476783,0.0010062456,0.54579264,0.0002587299,0.00029924407,0.000096736796,0.0005328618,0.00017511609,0.0041601933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994122,0.00015433088,0.000024734443,0.00010838897,0.00024622714,0.000054049007],"domain_scores_gemma":[0.9989114,0.00041977293,0.00008668962,0.00018640257,0.00031563657,0.00008005415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071051193,0.00064017146,0.00087641005,0.00090801803,0.00035801268,0.0010104442,0.0010942734,0.0009990861,0.0018914263],"category_scores_gemma":[0.0034154966,0.00031503628,0.00071087223,0.0015007342,0.00037440975,0.0018373284,0.0009259066,0.001136772,0.0011447202],"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":[0.00051742507,0.00068418536,0.0036880919,0.00028990945,0.0002436368,0.00018606051,0.0002586826,0.25760764,0.05112117,0.037296575,0.0127007095,0.6354059],"study_design_scores_gemma":[0.000009072046,0.00004074201,0.0003403608,0.000005005322,0.000019093666,0.00003250941,0.000024329789,0.9920087,0.0012066631,0.005209119,0.0010947121,0.000009624807],"about_ca_topic_score_codex":0.0032932127,"about_ca_topic_score_gemma":0.0049508135,"teacher_disagreement_score":0.0032932127,"about_ca_system_score_codex":0.00026110018,"about_ca_system_score_gemma":0.00047818833,"threshold_uncertainty_score":0.0065481067},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3021764,0.003653862,0.65608084,0.00059339625,0.00053539244,0.00029602644,0.011706298,0.018855212,0.006102502],"genre_scores_gemma":[0.67530507,0.0011101806,0.28546566,0.00021628973,0.00029598057,0.00027593196,0.026003087,0.00052445254,0.010803266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996885,0.000019170653,0.000026577922,0.000094897856,0.00009569434,0.00007517183],"domain_scores_gemma":[0.99963355,0.000097338445,0.000043625998,0.000071647715,0.00011831924,0.000035485446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033370164,0.0008823381,0.00086400367,0.002655483,0.0005323082,0.000820299,0.00066768157,0.0005975503,0.003983214],"category_scores_gemma":[0.0011373931,0.00023241942,0.0009097262,0.001673103,0.00015700002,0.00077826245,0.0010549513,0.0006413867,0.002728089],"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":[0.0005434795,0.0002544962,0.009857595,0.00016218192,0.00008864684,0.00032482602,0.00007197555,0.0028956179,0.09120314,0.00080671196,0.014580305,0.8792111],"study_design_scores_gemma":[0.00015792587,0.00078319054,0.11787249,0.000116353105,0.0003698424,0.0020165616,0.00045254442,0.61932325,0.18685009,0.010845412,0.061083686,0.00012874104],"about_ca_topic_score_codex":0.002392209,"about_ca_topic_score_gemma":0.0028927566,"teacher_disagreement_score":0.003983214,"about_ca_system_score_codex":0.00024792805,"about_ca_system_score_gemma":0.00055404485,"threshold_uncertainty_score":0.013325155},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007399484,0.9807359,0.0035337694,0.0014200135,0.000219651,0.002443371,0.003087329,0.00012147763,0.0010389715],"genre_scores_gemma":[0.09041093,0.8755853,0.019782862,0.002792196,0.00017925895,0.0063994518,0.004167029,0.00014930626,0.00053375243],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9730698,0.011888374,0.008168371,0.0020985636,0.0043550837,0.00041975453],"domain_scores_gemma":[0.7919881,0.17728187,0.013000814,0.0047128303,0.011970483,0.0010458839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038090594,0.0016407422,0.006929612,0.02446498,0.001293891,0.0044615446,0.0040733167,0.0028217663,0.0062524513],"category_scores_gemma":[0.17805925,0.0014264542,0.007146804,0.013560626,0.0016905965,0.0061138505,0.0044895927,0.0018980182,0.0010313577],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003380784,0.00012283439,0.004008833,0.77973837,0.00676418,0.00021283023,0.0022720585,0.0002855341,0.0003298524,0.0007476494,0.006969151,0.19821061],"study_design_scores_gemma":[0.0004130591,0.00040096848,0.009040834,0.88751197,0.04384386,0.0006446145,0.003188533,0.0005295587,0.0006333449,0.0020133362,0.051613133,0.00016682144],"about_ca_topic_score_codex":0.005766558,"about_ca_topic_score_gemma":0.02294522,"teacher_disagreement_score":0.038090594,"about_ca_system_score_codex":0.0034115806,"about_ca_system_score_gemma":0.021316474,"threshold_uncertainty_score":0.20144475},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2502157,0.005405062,0.72362196,0.0040657683,0.0005546733,0.00021436033,0.002821364,0.0049098916,0.0081912065],"genre_scores_gemma":[0.92914116,0.00081724377,0.05979594,0.00069447403,0.00018887404,0.00013259085,0.003161427,0.000119844924,0.0059484844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954814,0.00009067996,0.000039387232,0.00012296104,0.00006643176,0.00013225249],"domain_scores_gemma":[0.99928063,0.00029805533,0.000079182304,0.00004597253,0.00022118245,0.00007497037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011972665,0.0012596768,0.0010629618,0.0014610821,0.00044353717,0.0009837426,0.0018597604,0.0018477126,0.003066099],"category_scores_gemma":[0.002403898,0.00057458767,0.001041711,0.0011560417,0.00042788754,0.0014135292,0.0013436403,0.0026466527,0.0008847235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002433764,0.0002795958,0.009620612,0.0001527281,0.00018092943,0.00025652113,0.000081664606,0.80383503,0.0017914254,0.0034453194,0.008161038,0.17195167],"study_design_scores_gemma":[0.0000035404305,0.000010022724,0.00020492844,0.000008803072,0.000006484142,0.0000071517366,0.0000070214405,0.9982961,0.0001637715,0.0010887524,0.00020066276,0.0000026983694],"about_ca_topic_score_codex":0.023828072,"about_ca_topic_score_gemma":0.01813035,"teacher_disagreement_score":0.023828072,"about_ca_system_score_codex":0.0013124376,"about_ca_system_score_gemma":0.0018201892,"threshold_uncertainty_score":0.04737872},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00239938,0.0003488225,0.99621993,0.00047070655,0.000041297495,0.000020828298,0.000039189537,0.00007207956,0.00038783552],"genre_scores_gemma":[0.28716043,0.0021980442,0.6983933,0.0008528053,0.0007974668,0.0008187097,0.0008340552,0.00066768395,0.008277481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98987025,0.0068876157,0.00043920628,0.0011564639,0.0012258717,0.00042054013],"domain_scores_gemma":[0.9356316,0.05655362,0.0014802837,0.0027421943,0.0025298176,0.0010624345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01851678,0.0018001932,0.004593355,0.0023813,0.0014633065,0.004474631,0.0072170584,0.005840503,0.0045998204],"category_scores_gemma":[0.09904212,0.0036987686,0.002565495,0.0037534074,0.008122442,0.010106264,0.0078005544,0.010435952,0.00078923703],"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":[0.00014522947,0.000084032654,0.0008122814,0.00025166114,0.00014665634,0.00006517345,0.00030142177,0.27321684,0.00043760246,0.69667655,0.002109896,0.025752556],"study_design_scores_gemma":[0.000029758301,0.000014124256,0.00007904949,0.000023937202,0.000017595297,0.000012870183,0.000010945234,0.6938586,0.0001009431,0.30523968,0.00059252186,0.000019889181],"about_ca_topic_score_codex":0.014226029,"about_ca_topic_score_gemma":0.010696094,"teacher_disagreement_score":0.01851678,"about_ca_system_score_codex":0.0046771364,"about_ca_system_score_gemma":0.005643527,"threshold_uncertainty_score":0.09792727},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039582685,0.0011217631,0.9554034,0.00016944481,0.00049102306,0.00003932122,0.00013365141,0.0007362973,0.0023224473],"genre_scores_gemma":[0.5965802,0.0006446919,0.38702708,0.00018797314,0.00019975776,0.000099083794,0.0009032664,0.00035428663,0.014003598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843377,0.000498161,0.00011769517,0.0003374499,0.0004711481,0.00014179212],"domain_scores_gemma":[0.9978927,0.0005975317,0.000098104625,0.00031372978,0.0010229807,0.00007489509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020980882,0.0006021248,0.0018912841,0.0008346225,0.0006656893,0.0011689228,0.0023206396,0.0013521893,0.0033447538],"category_scores_gemma":[0.0050862636,0.00049105956,0.0012162101,0.0014912793,0.00046704995,0.0017932585,0.0017230969,0.0019044634,0.001425962],"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":[0.00069785496,0.00030993955,0.0039542965,0.00019504143,0.0003438599,0.00016858868,0.000106075255,0.42540303,0.0060119946,0.013529714,0.009802698,0.53947693],"study_design_scores_gemma":[0.0000059093227,0.000020267447,0.00015103524,0.0000035345554,0.000016412843,0.000025593836,0.0000068965064,0.99787295,0.00071629346,0.0007689105,0.00040721337,0.0000050335284],"about_ca_topic_score_codex":0.0075265504,"about_ca_topic_score_gemma":0.006759384,"teacher_disagreement_score":0.0075265504,"about_ca_system_score_codex":0.00055504567,"about_ca_system_score_gemma":0.0012695779,"threshold_uncertainty_score":0.014965475},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019348783,0.0008746567,0.9778187,0.00014614624,0.00011876904,0.000052186388,0.0000893248,0.000613731,0.00093776133],"genre_scores_gemma":[0.5274608,0.00058071525,0.4673849,0.00026316804,0.00044271443,0.00014245337,0.00073122326,0.00028671377,0.0027072981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99049157,0.002922638,0.00066759705,0.0016046665,0.003939303,0.00037421595],"domain_scores_gemma":[0.9828508,0.0071389265,0.000911873,0.0026184528,0.0062393914,0.00024059539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006697795,0.00096654333,0.0027778193,0.00267571,0.0013927971,0.0017168762,0.0034543392,0.002146996,0.0016328559],"category_scores_gemma":[0.029313797,0.00072900817,0.0016018517,0.0024644672,0.0010056889,0.0030529173,0.002286861,0.002409587,0.0010954707],"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":[0.00060807646,0.0003052816,0.0060418383,0.00030060197,0.0003810336,0.00015919619,0.00039066595,0.23715647,0.008980708,0.012133308,0.005242454,0.72830033],"study_design_scores_gemma":[0.000010486622,0.000058136215,0.00073451863,0.000013934101,0.000055733002,0.00008974197,0.000023716722,0.98968154,0.002025088,0.006348556,0.0009345644,0.000024045656],"about_ca_topic_score_codex":0.007068911,"about_ca_topic_score_gemma":0.0072526117,"teacher_disagreement_score":0.007068911,"about_ca_system_score_codex":0.0009972726,"about_ca_system_score_gemma":0.0013748902,"threshold_uncertainty_score":0.03542173},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087739274,0.0008668849,0.89456797,0.0025917673,0.00009228993,0.0001428139,0.00041114245,0.00063864025,0.012949244],"genre_scores_gemma":[0.85195345,0.00091440044,0.1392308,0.00033619622,0.00006002191,0.00020314855,0.00055912544,0.00044065545,0.0063021313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732876,0.001905412,0.000084829335,0.00026209984,0.00028927188,0.00012957657],"domain_scores_gemma":[0.93593955,0.057909198,0.0010270141,0.002976999,0.0016307924,0.0005165151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008502777,0.0006133386,0.0011088469,0.001531431,0.00088817975,0.005126525,0.0018905138,0.0017232479,0.009709797],"category_scores_gemma":[0.05363946,0.00068232114,0.0017524351,0.0019149975,0.0017244682,0.005762216,0.0019160458,0.0017603541,0.0011461213],"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":[0.0002010894,0.00008567933,0.0029544898,0.0002417712,0.00010846283,0.00009337855,0.0016225544,0.40962344,0.00060226826,0.545399,0.0015742024,0.037493713],"study_design_scores_gemma":[0.000014971714,0.00002783577,0.00019430768,0.00003084841,0.000020685355,0.000021162286,0.00016972402,0.90260714,0.00018099329,0.09544215,0.0012765542,0.000013626469],"about_ca_topic_score_codex":0.010946446,"about_ca_topic_score_gemma":0.009673664,"teacher_disagreement_score":0.010946446,"about_ca_system_score_codex":0.002688851,"about_ca_system_score_gemma":0.0021944405,"threshold_uncertainty_score":0.044967532},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6913803,0.010885006,0.21234119,0.015301673,0.001921841,0.00063550164,0.004330489,0.002930136,0.06027382],"genre_scores_gemma":[0.9549793,0.0011655504,0.03401045,0.0008398809,0.0008884791,0.00027402272,0.0028542308,0.00057648605,0.00441166],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9839977,0.008135396,0.0010670517,0.0021978954,0.003917029,0.0006848919],"domain_scores_gemma":[0.8047562,0.1559989,0.008271168,0.01199719,0.015291948,0.003684607],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014001915,0.00079272,0.00093608437,0.010014469,0.0021422969,0.008445439,0.0019136346,0.0023043281,0.004941438],"category_scores_gemma":[0.16804515,0.0006056066,0.0007207776,0.010700061,0.0026818032,0.014857933,0.006041397,0.0030721945,0.0020125294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017914267,0.0006115535,0.25813323,0.0026116138,0.00075252895,0.0018062607,0.044722524,0.0061264164,0.012254319,0.09306535,0.030910306,0.5472145],"study_design_scores_gemma":[0.0002308968,0.00053737056,0.16105756,0.0019099639,0.0012865567,0.003022018,0.043260157,0.23988128,0.017628249,0.3585889,0.17230494,0.00029213377],"about_ca_topic_score_codex":0.0025254064,"about_ca_topic_score_gemma":0.0030100057,"teacher_disagreement_score":0.9859981,"about_ca_system_score_codex":0.0014758321,"about_ca_system_score_gemma":0.0019857914,"threshold_uncertainty_score":0.07405013},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19394128,0.0014399139,0.79542893,0.0007263742,0.000266517,0.00018365405,0.0026728301,0.0026393917,0.0027009987],"genre_scores_gemma":[0.798529,0.0005773914,0.19053128,0.00014386067,0.00018178705,0.000165712,0.0058786524,0.00020306499,0.003789252],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994337,0.00011339698,0.000042802654,0.00022349079,0.00012929339,0.000057388694],"domain_scores_gemma":[0.9985267,0.00068425713,0.00015858785,0.00027594165,0.00026725294,0.00008733873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037340348,0.00069101516,0.00077739824,0.002666191,0.00045837756,0.00084415206,0.0010389488,0.0009839502,0.0018795897],"category_scores_gemma":[0.002274432,0.00024079367,0.000747417,0.0022144364,0.00040235903,0.0016118529,0.0007539317,0.0011003483,0.0008773993],"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":[0.0007031588,0.00085938314,0.0124306865,0.00042585985,0.00022934384,0.00037043687,0.00025467065,0.064848304,0.021607466,0.014695626,0.01839887,0.8651762],"study_design_scores_gemma":[0.00002734999,0.000115264,0.00231892,0.000034740737,0.00005812954,0.00020265591,0.000116351854,0.9608377,0.002821485,0.030697571,0.0027532424,0.000016544527],"about_ca_topic_score_codex":0.0020071885,"about_ca_topic_score_gemma":0.0037603173,"teacher_disagreement_score":0.002666191,"about_ca_system_score_codex":0.00037430998,"about_ca_system_score_gemma":0.0005882524,"threshold_uncertainty_score":0.006287873},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003206902,0.00007054397,0.99590045,0.00010650979,0.000018008493,0.00001659408,0.00004176102,0.00024874875,0.00039052157],"genre_scores_gemma":[0.30503604,0.00031799544,0.6899161,0.00020801157,0.0002140055,0.00014924271,0.0006223267,0.00022219653,0.003314148],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982439,0.00041888902,0.000069638685,0.00044154093,0.0006810298,0.00014499061],"domain_scores_gemma":[0.997207,0.0013797671,0.00027498807,0.00029574815,0.0007045121,0.00013811587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002031254,0.000921993,0.0015298029,0.002181129,0.0008123709,0.0013990406,0.003140075,0.00168157,0.0020385853],"category_scores_gemma":[0.0073974584,0.00067875494,0.0011906305,0.001833134,0.0008250849,0.003599113,0.0025892153,0.0025540628,0.0006520107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002791008,0.0003306817,0.0040079574,0.00014491036,0.00024364413,0.00023369568,0.00018714991,0.52839744,0.009494817,0.07766701,0.0050309654,0.37398267],"study_design_scores_gemma":[0.0000045401093,0.000011594957,0.00015459058,0.0000028016532,0.000013636711,0.000030539755,0.0000043848536,0.9880485,0.00060635153,0.010648969,0.0004665434,0.0000075202133],"about_ca_topic_score_codex":0.006527501,"about_ca_topic_score_gemma":0.00881041,"teacher_disagreement_score":0.006527501,"about_ca_system_score_codex":0.0009032092,"about_ca_system_score_gemma":0.0018734185,"threshold_uncertainty_score":0.012979031},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078517705,0.0004318207,0.91326225,0.0012936195,0.00016879744,0.00030745912,0.0034335593,0.0015166379,0.0010681072],"genre_scores_gemma":[0.6893348,0.0003530927,0.30054438,0.000300568,0.00020717893,0.0006507189,0.006325371,0.000102316284,0.00218166],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986524,0.00048260798,0.00011586402,0.00034469177,0.0003046555,0.00009989313],"domain_scores_gemma":[0.99284947,0.005372273,0.00037998092,0.00036500787,0.00084955344,0.00018372531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002544755,0.0011184643,0.0013895385,0.0031037177,0.0006047581,0.0019166633,0.0025392505,0.0016190623,0.001533368],"category_scores_gemma":[0.010936791,0.0008514337,0.0016568168,0.0027425352,0.00045464607,0.0015190743,0.0012277173,0.0025243545,0.0006431919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023631295,0.00076120737,0.019247392,0.00014923714,0.0003241448,0.00023274246,0.00009663772,0.8712152,0.0010832209,0.009391296,0.0033645015,0.09389815],"study_design_scores_gemma":[0.000004398322,0.000014100975,0.00039025024,0.0000046785876,0.000007807859,0.0000128604925,0.000008098597,0.9960341,0.00015773822,0.0031809483,0.00017977851,0.0000053421313],"about_ca_topic_score_codex":0.012412072,"about_ca_topic_score_gemma":0.017063038,"teacher_disagreement_score":0.012412072,"about_ca_system_score_codex":0.0012072899,"about_ca_system_score_gemma":0.002212083,"threshold_uncertainty_score":0.02467966},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02132024,0.27891082,0.060750335,0.54817086,0.0043409434,0.00013976461,0.00091441686,0.00074544497,0.084707305],"genre_scores_gemma":[0.3984086,0.47757256,0.07556567,0.022400472,0.0045795697,0.00030997218,0.0011936256,0.00017553878,0.019794008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979754,0.0007341172,0.00007312073,0.0002379514,0.0006466845,0.00033267078],"domain_scores_gemma":[0.99220276,0.002901104,0.00045230216,0.000389399,0.002756911,0.001297569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058584167,0.00089908706,0.00088793354,0.0015598105,0.0015575242,0.011427375,0.0022794541,0.0051288726,0.014913492],"category_scores_gemma":[0.0050311466,0.0002917684,0.00064222387,0.0045508225,0.004543801,0.012710902,0.0052137263,0.004487997,0.00341334],"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":[0.00012726683,0.00029443568,0.0051417607,0.002612448,0.00007301262,0.00014756496,0.0008102064,0.006797926,0.001567587,0.53275144,0.11122245,0.33845392],"study_design_scores_gemma":[0.000024512072,0.00015252795,0.0015764897,0.001880859,0.000046413556,0.00019655032,0.011262456,0.014719866,0.0012162045,0.5185061,0.45035174,0.000066170534],"about_ca_topic_score_codex":0.0062148212,"about_ca_topic_score_gemma":0.013399832,"teacher_disagreement_score":0.014913492,"about_ca_system_score_codex":0.0028220543,"about_ca_system_score_gemma":0.011967924,"threshold_uncertainty_score":0.049890637},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99909484,0.00003308698,0.000057912563,0.000053005173,0.000012614831,0.0000063979414,0.0002820099,0.0000034053269,0.00045680505],"genre_scores_gemma":[0.9981558,0.00002917589,0.00006871819,0.000037080656,0.000019670037,0.000014977438,0.00064509135,0.0000047697513,0.0010246864],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99918085,0.00024628357,0.000055484103,0.0001317685,0.00020653885,0.00017902067],"domain_scores_gemma":[0.99121255,0.002742946,0.0024750233,0.00046099175,0.0019358945,0.0011726529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016088346,0.00023691,0.00032265822,0.00058307004,0.0005622628,0.0013019677,0.0003783155,0.00074132433,0.0027443497],"category_scores_gemma":[0.0077787437,0.00018635223,0.00061059115,0.0007462,0.0002602358,0.0009891471,0.000688201,0.0011345408,0.0012011342],"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":[0.0007032847,0.0010487069,0.9855483,0.00003581575,0.00019742182,0.000110990164,0.0008745156,0.00047600988,0.0017941457,0.00011278651,0.0012883161,0.007809555],"study_design_scores_gemma":[0.0000058671562,0.00029371795,0.99613297,0.000007991693,0.00006162462,0.000035522848,0.00082341034,0.0018039888,0.00028820924,0.00004864983,0.00048302524,0.0000150722935],"about_ca_topic_score_codex":0.009531543,"about_ca_topic_score_gemma":0.015637057,"teacher_disagreement_score":0.009531543,"about_ca_system_score_codex":0.00042521057,"about_ca_system_score_gemma":0.0004357878,"threshold_uncertainty_score":0.018952131},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98474634,0.00020951555,0.0017038684,0.00033983786,0.00008472527,0.0000654477,0.010687066,0.00010849639,0.0020547248],"genre_scores_gemma":[0.98574835,0.00015749836,0.0026603756,0.000057118887,0.00008374501,0.0000957065,0.009872187,0.000012187855,0.0013126642],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995441,0.00013885129,0.000057394598,0.00009192769,0.00010521224,0.00006242293],"domain_scores_gemma":[0.9977914,0.0011384309,0.00033774902,0.00015520661,0.00035593074,0.00022125398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046181798,0.0003420033,0.0002698,0.0019635658,0.0003576105,0.0006036731,0.00038942578,0.0005532148,0.0012051642],"category_scores_gemma":[0.0027831104,0.00009759649,0.0003413964,0.001485421,0.00016759313,0.00042752587,0.00041661502,0.00042411961,0.0007910802],"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":[0.0014166017,0.0012222619,0.8156605,0.0006360829,0.0004720025,0.0014109182,0.0037611064,0.007896021,0.011234278,0.0010449298,0.01586348,0.13938184],"study_design_scores_gemma":[0.00002621017,0.00047472728,0.9085588,0.0001533676,0.00021610134,0.0007614613,0.008020185,0.062407654,0.004544858,0.0010398506,0.013737254,0.000059661597],"about_ca_topic_score_codex":0.008391068,"about_ca_topic_score_gemma":0.01548992,"teacher_disagreement_score":0.008391068,"about_ca_system_score_codex":0.00025699518,"about_ca_system_score_gemma":0.0004108828,"threshold_uncertainty_score":0.016684473},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042358804,0.0005925516,0.9539271,0.0006531546,0.00010648504,0.00008972979,0.00039722494,0.00061089173,0.0012640035],"genre_scores_gemma":[0.650162,0.0008242686,0.3358129,0.00044054605,0.0004728048,0.00046852138,0.003240581,0.00051463535,0.008063829],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99403834,0.0030443876,0.0002734665,0.0013258772,0.0008418623,0.000476104],"domain_scores_gemma":[0.9741392,0.02060796,0.00086762727,0.001979109,0.0018914287,0.0005146256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0131840855,0.0010772403,0.0030136425,0.002660747,0.0015985089,0.0030118134,0.0034742116,0.0025357627,0.0049335985],"category_scores_gemma":[0.04527277,0.0010931492,0.0019758127,0.0022184777,0.0020197893,0.004314807,0.0028810222,0.003742596,0.0024311314],"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":[0.0013630855,0.00047490746,0.017172744,0.000436819,0.0004449832,0.0002588336,0.0008514204,0.4518918,0.0050611985,0.11714377,0.012488756,0.39241162],"study_design_scores_gemma":[0.000046330977,0.00003803613,0.0017342326,0.000041224524,0.0000337995,0.000084072286,0.000045059616,0.9406273,0.0008728148,0.055178065,0.001264293,0.000034935725],"about_ca_topic_score_codex":0.0118309185,"about_ca_topic_score_gemma":0.013620188,"teacher_disagreement_score":0.0131840855,"about_ca_system_score_codex":0.001830217,"about_ca_system_score_gemma":0.0029562481,"threshold_uncertainty_score":0.06972492},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020290328,0.00036172481,0.97586626,0.00036076948,0.00003961898,0.00014149994,0.0013580557,0.0008325016,0.0007492582],"genre_scores_gemma":[0.18653895,0.0003055476,0.80738163,0.00018582963,0.00007004785,0.00045035884,0.004133775,0.00009415187,0.0008397521],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99672747,0.0007837194,0.00041727597,0.00084768445,0.0010100476,0.00021374544],"domain_scores_gemma":[0.99062854,0.0041505587,0.0016042854,0.0012952739,0.0020115646,0.00030974808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031904746,0.000851175,0.00095247896,0.00858827,0.001397309,0.002529406,0.002432176,0.0016446227,0.0017252169],"category_scores_gemma":[0.014378815,0.00042514634,0.0017514194,0.007064026,0.0012081118,0.0042807544,0.003182004,0.0021318751,0.0006131968],"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":[0.00043693656,0.00038332635,0.06771916,0.0011417586,0.00030180713,0.0008708021,0.0040480285,0.111147664,0.019574026,0.07413267,0.010605168,0.70963866],"study_design_scores_gemma":[0.000015780337,0.00007695606,0.006999819,0.0001300782,0.000048860533,0.00021452573,0.0011661983,0.935713,0.0025113916,0.043710254,0.009357186,0.00005593085],"about_ca_topic_score_codex":0.008807187,"about_ca_topic_score_gemma":0.019220933,"teacher_disagreement_score":0.008807187,"about_ca_system_score_codex":0.0016076273,"about_ca_system_score_gemma":0.0017547698,"threshold_uncertainty_score":0.017511845},"labels":[],"label_agreement":null}]}