{"meta":{"query_hash":"81a69d3f0a61","filters":{"venue":"Data Science and Engineering"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/81a69d3f0a61","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data+Science+and+Engineering"},"results":[{"id":"W3155426438","doi":"10.1007/s41019-021-00156-2","title":"A Workload-Adaptive Streaming Partitioner for Distributed Graph Stores","year":2021,"lang":"en","type":"article","venue":"Data Science and Engineering","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Exploit; Workload; Graph traversal; Graph; Tree traversal; Latency (audio); Theoretical computer science; Distributed computing; Operating system; Algorithm","score_opus":0.026221650197992386,"score_gpt":0.23748156179220617,"score_spread":0.21125991159421378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155426438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01629318,0.00030556225,0.9826739,0.00013609741,0.0002573034,0.00005419837,0.00017693522,0.00007597521,0.00002686814],"genre_scores_gemma":[0.9007758,0.000044968107,0.0989461,0.00006303794,0.000060124683,0.000015850514,0.00008147783,0.000004535519,0.000008117374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904853,0.000006479405,0.00008655414,0.000418012,0.00018002784,0.0002604252],"domain_scores_gemma":[0.9991845,0.00007668322,0.000018669198,0.00052209815,0.00010210984,0.00009597628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005023404,0.00007682752,0.0000780118,0.00007822841,0.00023753737,0.00025932977,0.0007196992,0.000017217297,0.0000016361417],"category_scores_gemma":[0.0001975615,0.00007187761,0.000014461297,0.0008995446,0.00009278141,0.0017077824,0.0004523599,0.000055071378,0.0000010677461],"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":[0.0000099825675,0.000119551034,0.00034391388,0.00007947017,0.000059258793,0.00008339995,0.000995478,0.009546425,0.048605196,0.77879107,0.001455919,0.15991037],"study_design_scores_gemma":[0.000245792,0.000036229416,0.0030402972,0.00008135838,0.000009530792,0.00002938597,0.0002111498,0.9783466,0.0068608453,0.0057073846,0.005157685,0.00027375444],"about_ca_topic_score_codex":0.0000024955064,"about_ca_topic_score_gemma":0.0000014847519,"teacher_disagreement_score":0.9688002,"about_ca_system_score_codex":0.000012097886,"about_ca_system_score_gemma":0.00006729442,"threshold_uncertainty_score":0.29310837},"labels":[],"label_agreement":null},{"id":"W4243973573","doi":"10.1007/s41019-017-0053-1","title":"Sliding Window Top-K Monitoring over Distributed Data Streams","year":2017,"lang":"en","type":"article","venue":"Data Science and Engineering","topic":"Data Management and Algorithms","field":"Computer Science","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":"York University","funders":"National Key Research and Development Program of China; Natural Science Foundation of Shandong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Scalability; Sliding window protocol; Distributed computing; Overhead (engineering); Data stream mining; Distributed Computing Environment; Distributed algorithm; Aggregate (composite); Window (computing); Data stream; Real-time computing; Data mining; Database; Operating system","score_opus":0.06100806266574163,"score_gpt":0.2964756951502873,"score_spread":0.2354676324845457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243973573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110952236,0.0003019855,0.8813727,0.0010429416,0.0035425103,0.00025004585,0.0014274786,0.00044445758,0.00066565775],"genre_scores_gemma":[0.9587761,0.00013897356,0.040398516,0.00001713022,0.00030232928,0.0000023208524,0.0003348603,0.000007696809,0.00002208261],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982539,0.0000031604466,0.000121339,0.00078739616,0.00044433118,0.0003898717],"domain_scores_gemma":[0.9946198,0.000026019477,0.000059880298,0.0051323585,0.000030609586,0.00013136712],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.0010963974,0.00012169081,0.00010512486,0.00009794666,0.0007027101,0.0031264392,0.010981954,0.00001973652,0.0000016858763],"category_scores_gemma":[0.0004513682,0.00011328382,0.0000063272973,0.00027431472,0.00008403722,0.017487697,0.013336392,0.00009992831,0.000007220816],"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":[0.0000030978574,0.00007361923,0.04368083,0.00011982535,0.000065403234,0.00017399086,0.0003049994,0.0007323258,0.018088695,0.034617417,0.006391246,0.89574856],"study_design_scores_gemma":[0.00016248785,0.000008438465,0.07451992,0.000056315705,0.0000073695774,0.000005125585,0.00002392729,0.9027177,0.000720812,0.000028375955,0.021521224,0.00022831025],"about_ca_topic_score_codex":0.00008497927,"about_ca_topic_score_gemma":0.0000018443773,"teacher_disagreement_score":0.90198535,"about_ca_system_score_codex":0.000023093624,"about_ca_system_score_gemma":0.00003921987,"threshold_uncertainty_score":0.9979084},"labels":[],"label_agreement":null},{"id":"W4292512861","doi":"10.1007/s41019-022-00193-5","title":"Dimensionality Reduction in Surrogate Modeling: A Review of Combined Methods","year":2022,"lang":"en","type":"review","venue":"Data Science and Engineering","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Surrogate model; Dimensionality reduction; Curse of dimensionality; Computer science; Uncertainty quantification; Reduction (mathematics); Artificial intelligence; Mathematical optimization; Machine learning; Mathematics","score_opus":0.15616597191542345,"score_gpt":0.42200037778948857,"score_spread":0.26583440587406515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292512861","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0454513e-7,0.5995379,0.3999264,0.000013009159,0.00023053953,0.00022608094,0.000023816368,0.000028641885,0.000013490781],"genre_scores_gemma":[3.9805718e-7,0.6631464,0.33672702,0.000008227668,0.0000067469587,0.000025043375,0.000076947275,0.000007222803,0.0000020075693],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997844,0.000119315526,0.00054035947,0.0008019376,0.00046324093,0.00023116457],"domain_scores_gemma":[0.9982416,0.00014676098,0.000192007,0.0012294033,0.00011161102,0.00007863948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045665177,0.00019889968,0.00074347004,0.00040436746,0.00009510049,0.000040689123,0.0018236525,0.00003803099,0.000006311624],"category_scores_gemma":[0.0011956708,0.0001837983,0.000041941013,0.0029628177,0.00007560166,0.0015298553,0.002122661,0.00027726564,6.277223e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.3214956e-7,0.000022997214,4.1355218e-8,0.01286721,0.0000073337383,0.0000029257649,0.00002650431,0.013502077,0.0000061101464,0.0014247376,0.000011405977,0.9721282],"study_design_scores_gemma":[0.000053728207,0.000009819757,3.0124104e-7,0.008015121,0.000019973935,0.000033764376,0.0000037825089,0.81958485,0.0000012296235,0.000022396902,0.17208537,0.00016965649],"about_ca_topic_score_codex":0.000012166797,"about_ca_topic_score_gemma":1.6263637e-7,"teacher_disagreement_score":0.9719586,"about_ca_system_score_codex":0.00016579531,"about_ca_system_score_gemma":0.00039924847,"threshold_uncertainty_score":0.7495077},"labels":[],"label_agreement":null},{"id":"W4393347796","doi":"10.1007/s41019-023-00239-2","title":"Uncovering Flat and Hierarchical Topics by Community Discovery on Word Co-occurrence Network","year":2024,"lang":"en","type":"article","venue":"Data Science and Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; University of Alberta","funders":"Centre National de la Recherche Scientifique; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Hierarchy; Identification (biology); Topic model; Word (group theory); Exploit; Data science; Tree (set theory); Information retrieval; Linguistics","score_opus":0.023266520834801834,"score_gpt":0.2920903359651108,"score_spread":0.26882381513030895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393347796","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09116597,0.0007877307,0.906614,0.00034389165,0.00026296993,0.000079058555,0.00010814203,0.0004068856,0.00023133557],"genre_scores_gemma":[0.96695906,0.00048218627,0.032205988,0.0001618109,0.000086566986,0.0000053959957,0.00007028532,0.000006762157,0.000021953778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988489,0.000017137407,0.00012256656,0.0004304187,0.00029083193,0.00029010302],"domain_scores_gemma":[0.9988428,0.00018335058,0.000014959029,0.00084326265,0.000014615913,0.00010100969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089460803,0.00012021584,0.000118248136,0.00011315023,0.00027602864,0.00087858684,0.001337061,0.000027281874,4.6885268e-7],"category_scores_gemma":[0.00013575098,0.00010624648,0.000009205484,0.00079091295,0.00017276745,0.0035136363,0.0013045548,0.0003867598,0.0000014264516],"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":[0.000008052615,0.00005701877,0.0012849937,0.0003392472,0.000053774536,0.000067184585,0.0014093069,0.011822677,0.030816726,0.15516326,0.018224528,0.78075325],"study_design_scores_gemma":[0.000065195025,0.00008232503,0.0009316095,0.00028713339,0.000009595586,0.000023944682,0.00002221946,0.87507284,0.0023981547,0.0023476558,0.11834038,0.00041893177],"about_ca_topic_score_codex":0.000016146882,"about_ca_topic_score_gemma":0.0000033844703,"teacher_disagreement_score":0.8757931,"about_ca_system_score_codex":0.000030934243,"about_ca_system_score_gemma":0.00004256487,"threshold_uncertainty_score":0.8472233},"labels":[],"label_agreement":null}]}