{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"81a69d3f0a61","filters":{"venue":"Data Science and Engineering"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1561659719154234,"gpt":0.4220003777894886,"spread":0.2658344058740651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004566518,0.0001988997,0.00074347,0.0004043675,0.00009510049,0.00004068912,0.001823653,0.00003803099,0.000006311624],"category_scores_gemma":[0.001195671,0.0001837983,0.00004194101,0.002962818,0.00007560166,0.001529855,0.002122661,0.0002772656,6.277223e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001657953,"about_ca_system_score_gemma":0.0003992485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000121668,"about_ca_topic_score_gemma":1.626364e-7,"domain_scores_codex":[0.997844,0.0001193155,0.0005403595,0.0008019376,0.0004632409,0.0002311646],"domain_scores_gemma":[0.9982416,0.000146761,0.000192007,0.001229403,0.000111611,0.00007863948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[4.321496e-7,0.00002299721,4.135522e-8,0.01286721,0.000007333738,0.000002925765,0.00002650431,0.01350208,0.000006110146,0.001424738,0.00001140598,0.9721282],"study_design_scores_gemma":[0.00005372821,0.000009819757,3.01241e-7,0.008015121,0.00001997394,0.00003376438,0.000003782509,0.8195848,0.000001229624,0.0000223969,0.1720854,0.0001696565],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.045451e-7,0.5995379,0.3999264,0.00001300916,0.0002305395,0.0002260809,0.00002381637,0.00002864189,0.00001349078],"genre_scores_gemma":[3.980572e-7,0.6631464,0.336727,0.000008227668,0.000006746959,0.00002504337,0.00007694728,0.000007222803,0.000002007569],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9719586,"threshold_uncertainty_score":0.7495077,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02622165019799239,"gpt":0.2374815617922062,"spread":0.2112599115942138,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005023404,0.00007682752,0.0000780118,0.00007822841,0.0002375374,0.0002593298,0.0007196992,0.0000172173,0.000001636142],"category_scores_gemma":[0.0001975615,0.00007187761,0.0000144613,0.0008995446,0.00009278141,0.001707782,0.0004523599,0.00005507138,0.000001067746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001209789,"about_ca_system_score_gemma":0.00006729442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002495506,"about_ca_topic_score_gemma":0.000001484752,"domain_scores_codex":[0.9990485,0.000006479405,0.00008655414,0.000418012,0.0001800278,0.0002604252],"domain_scores_gemma":[0.9991845,0.00007668322,0.0000186692,0.0005220982,0.0001021098,0.00009597628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009982567,0.000119551,0.0003439139,0.00007947017,0.00005925879,0.00008339995,0.000995478,0.009546425,0.0486052,0.7787911,0.001455919,0.1599104],"study_design_scores_gemma":[0.000245792,0.00003622942,0.003040297,0.00008135838,0.000009530792,0.00002938597,0.0002111498,0.9783466,0.006860845,0.005707385,0.005157685,0.0002737544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01629318,0.0003055623,0.9826739,0.0001360974,0.0002573034,0.00005419837,0.0001769352,0.00007597521,0.00002686814],"genre_scores_gemma":[0.9007758,0.00004496811,0.0989461,0.00006303794,0.00006012468,0.00001585051,0.00008147783,0.000004535519,0.000008117374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9688002,"threshold_uncertainty_score":0.2931084,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06100806266574163,"gpt":0.2964756951502873,"spread":0.2354676324845457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.001096397,0.0001216908,0.0001051249,0.00009794666,0.0007027101,0.003126439,0.01098195,0.00001973652,0.000001685876],"category_scores_gemma":[0.0004513682,0.0001132838,0.000006327297,0.0002743147,0.00008403722,0.0174877,0.01333639,0.00009992831,0.000007220816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002309362,"about_ca_system_score_gemma":0.00003921987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008497927,"about_ca_topic_score_gemma":0.000001844377,"domain_scores_codex":[0.9982539,0.000003160447,0.000121339,0.0007873962,0.0004443312,0.0003898717],"domain_scores_gemma":[0.9946198,0.00002601948,0.0000598803,0.005132359,0.00003060959,0.0001313671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003097857,0.00007361923,0.04368083,0.0001198254,0.00006540323,0.0001739909,0.0003049994,0.0007323258,0.01808869,0.03461742,0.006391246,0.8957486],"study_design_scores_gemma":[0.0001624878,0.000008438465,0.07451992,0.0000563157,0.000007369577,0.000005125585,0.00002392729,0.9027177,0.000720812,0.00002837595,0.02152122,0.0002283103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1109522,0.0003019855,0.8813727,0.001042942,0.00354251,0.0002500459,0.001427479,0.0004444576,0.0006656577],"genre_scores_gemma":[0.9587761,0.0001389736,0.04039852,0.00001713022,0.0003023293,0.000002320852,0.0003348603,0.000007696809,0.00002208261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9019853,"threshold_uncertainty_score":0.9979084,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02326652083480183,"gpt":0.2920903359651108,"spread":0.268823815130309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000894608,0.0001202158,0.0001182481,0.0001131502,0.0002760286,0.0008785868,0.001337061,0.00002728187,4.688527e-7],"category_scores_gemma":[0.000135751,0.0001062465,0.000009205484,0.0007909129,0.0001727675,0.003513636,0.001304555,0.0003867598,0.000001426452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003093424,"about_ca_system_score_gemma":0.00004256487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001614688,"about_ca_topic_score_gemma":0.00000338447,"domain_scores_codex":[0.9988489,0.00001713741,0.0001225666,0.0004304187,0.0002908319,0.000290103],"domain_scores_gemma":[0.9988428,0.0001833506,0.00001495903,0.0008432626,0.00001461591,0.0001010097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008052615,0.00005701877,0.001284994,0.0003392472,0.00005377454,0.00006718458,0.001409307,0.01182268,0.03081673,0.1551633,0.01822453,0.7807533],"study_design_scores_gemma":[0.00006519502,0.00008232503,0.0009316095,0.0002871334,0.000009595586,0.00002394468,0.00002221946,0.8750728,0.002398155,0.002347656,0.1183404,0.0004189318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09116597,0.0007877307,0.906614,0.0003438916,0.0002629699,0.00007905855,0.000108142,0.0004068856,0.0002313356],"genre_scores_gemma":[0.9669591,0.0004821863,0.03220599,0.0001618109,0.00008656699,0.000005395996,0.00007028532,0.000006762157,0.00002195378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8757931,"threshold_uncertainty_score":0.8472233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}