{"meta":{"query_hash":"5d0a88660265","filters":{"venue":"Proceedings of the 2022 International Conference on Management of Data"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"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/5d0a88660265","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+2022+International+Conference+on+Management+of+Data"},"results":[{"id":"W4281747838","doi":"10.1145/3514221.3526161","title":"Natto: Providing Distributed Transaction Prioritization for High-Contention Workloads","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":9,"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":"Computer science; Database transaction; Timestamp; Distributed transaction; Transaction processing; Latency (audio); Prioritization; Online transaction processing; Distributed database; Database; Distributed computing; Computer network; Business; Telecommunications","score_opus":0.062399477194828606,"score_gpt":0.29384535846480053,"score_spread":0.23144588126997193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281747838","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":[0.11013305,0.0017556287,0.81768155,0.00090390176,0.0011101844,0.00045713683,0.0008162817,0.052205604,0.014936705],"genre_scores_gemma":[0.7237583,0.0007712639,0.2581912,0.00072613923,0.0004972507,0.0002932988,0.0019064132,0.0022517128,0.011604508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983619,0.00024411494,0.00016176258,0.00022245158,0.0008041797,0.00020558717],"domain_scores_gemma":[0.9948468,0.00092981884,0.00037885844,0.0020889167,0.001174628,0.00058088993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020087413,0.0007736311,0.0007286203,0.0009511807,0.0010539291,0.001979583,0.0032824432,0.00061221694,0.0046252725],"category_scores_gemma":[0.006673001,0.0005892897,0.00031740227,0.0008831376,0.00051097485,0.0029673001,0.002698326,0.0011663607,0.0018769858],"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":[0.004136104,0.0006699095,0.022182867,0.0007224374,0.0002968524,0.0011420954,0.0011585364,0.048639536,0.17491905,0.038142968,0.08911568,0.61887395],"study_design_scores_gemma":[0.00072242616,0.0007325889,0.0056098714,0.00008803771,0.00016997331,0.001385004,0.00046984694,0.7159179,0.08917107,0.027716577,0.15777147,0.00024535492],"about_ca_topic_score_codex":0.0029295231,"about_ca_topic_score_gemma":0.0053750584,"teacher_disagreement_score":0.0046252725,"about_ca_system_score_codex":0.0007963777,"about_ca_system_score_gemma":0.0019423631,"threshold_uncertainty_score":0.015473068},"labels":[],"label_agreement":null},{"id":"W4281775561","doi":"10.1145/3514221.3517834","title":"Proteus: Autonomous Adaptive Storage for Mixed Workloads","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":17,"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":"Online transaction processing; Online analytical processing; Computer science; Workload; Distributed transaction; Transaction processing; Database; Database transaction; Transaction processing system; Operating system; Distributed computing; Data warehouse","score_opus":0.07251230446442274,"score_gpt":0.2891402640180174,"score_spread":0.21662795955359465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281775561","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":[0.5258267,0.0019705303,0.35876298,0.0004859612,0.00033204388,0.00049924257,0.0009736796,0.09667637,0.014472495],"genre_scores_gemma":[0.89320993,0.00028332838,0.09966961,0.00017436672,0.000043910706,0.00015419937,0.00091383536,0.0010504304,0.004500487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933225,0.00012637464,0.000036371814,0.00012552674,0.00026526893,0.00011418979],"domain_scores_gemma":[0.99873704,0.0002860549,0.00010731347,0.00049481174,0.000245841,0.00012897392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006483825,0.00088068855,0.0004037199,0.00054969033,0.00059511885,0.001120823,0.0025677762,0.00037996945,0.0022251117],"category_scores_gemma":[0.0019480555,0.0005020799,0.00027906883,0.00057139766,0.00063104765,0.0017381997,0.001457646,0.0006645904,0.00061267987],"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":[0.0038012778,0.0009748929,0.014388149,0.000702619,0.00033499402,0.00082681095,0.0007434134,0.2016307,0.2472511,0.017965797,0.06733185,0.44404843],"study_design_scores_gemma":[0.00023379031,0.0008071595,0.0036032128,0.000031843534,0.000077292054,0.000573015,0.00024023982,0.8483532,0.1094636,0.0066650226,0.029838486,0.00011312921],"about_ca_topic_score_codex":0.0033807629,"about_ca_topic_score_gemma":0.0042706747,"teacher_disagreement_score":0.0033807629,"about_ca_system_score_codex":0.00071457156,"about_ca_system_score_gemma":0.0013073244,"threshold_uncertainty_score":0.007443726},"labels":[],"label_agreement":null},{"id":"W4281779720","doi":"10.1145/3514221.3517837","title":"A Convex-Programming Approach for Efficient Directed Densest Subgraph Discovery","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":29,"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 British Columbia","funders":"University of Hong Kong","keywords":"Scalability; Parameterized complexity; Computer science; Bipartite graph; Approximation algorithm; Linear programming; Matching (statistics); Theoretical computer science; Induced subgraph isomorphism problem; Directed graph; Graph; Mathematical optimization; Algorithm; Mathematics; Line graph","score_opus":0.06422309090837273,"score_gpt":0.2962473222413728,"score_spread":0.23202423133300004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281779720","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":[0.0029677642,0.00023267206,0.9941459,0.00038251045,0.000032637512,0.000071455754,0.00016949093,0.00044212322,0.0015554852],"genre_scores_gemma":[0.119913824,0.00050254865,0.87286085,0.00050797575,0.0001359103,0.0004978063,0.0014865217,0.00044639182,0.0036482443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981431,0.0006251662,0.000079873054,0.00047480155,0.0004657024,0.00021144716],"domain_scores_gemma":[0.9956252,0.0030082508,0.00026099023,0.00040808032,0.00049786665,0.00019960347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026347034,0.0022552996,0.002469963,0.0017249214,0.0008877677,0.002370255,0.0029363907,0.0019528125,0.005153056],"category_scores_gemma":[0.008887184,0.0012963772,0.0019004152,0.0034536566,0.0013249145,0.0030880943,0.0024203472,0.0045864256,0.0016342688],"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":[0.000116842,0.00027633447,0.0008791861,0.00024402108,0.00008142119,0.00014065369,0.000105006526,0.8255715,0.0010999402,0.043579217,0.013390968,0.11451492],"study_design_scores_gemma":[0.000007748699,0.000011337517,0.0000389311,0.000007202016,0.000004686598,0.000019550727,0.000012320287,0.9861492,0.00018051668,0.012887507,0.0006776462,0.0000033392532],"about_ca_topic_score_codex":0.007935644,"about_ca_topic_score_gemma":0.010798108,"teacher_disagreement_score":0.007935644,"about_ca_system_score_codex":0.0023220135,"about_ca_system_score_gemma":0.0032938875,"threshold_uncertainty_score":0.017238677},"labels":[],"label_agreement":null},{"id":"W4281788841","doi":"10.1145/3514221.3517904","title":"FILA: Online Auditing of Machine Learning Model Accuracy under Finite Labelling Budget","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"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","keywords":"Audit; Pipeline (software); Computer science; Process (computing); Training set; Artificial intelligence; Machine learning; Data modeling; Labelling; Software engineering; Accounting; Programming language","score_opus":0.10600199055667883,"score_gpt":0.32951755703808333,"score_spread":0.2235155664814045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281788841","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":[0.115777396,0.0016200909,0.7223246,0.0023493557,0.0009840757,0.00077563385,0.008537092,0.13665493,0.010976782],"genre_scores_gemma":[0.7682915,0.00030873035,0.20646788,0.00070479687,0.00031976835,0.00071165024,0.013687839,0.0039716517,0.005536242],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9877465,0.0043965573,0.0008211723,0.0020431709,0.003907669,0.0010848244],"domain_scores_gemma":[0.9276262,0.032409597,0.0042398125,0.02572016,0.007967071,0.0020371208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01463815,0.0021639739,0.0024341433,0.0032975806,0.0017226762,0.0043730424,0.006299646,0.0033934566,0.010647804],"category_scores_gemma":[0.09741161,0.0011586959,0.0011580604,0.0019278526,0.0021925536,0.007761076,0.0073459134,0.00505098,0.0060441177],"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":[0.005669194,0.0012792506,0.03571964,0.0010990814,0.0006353305,0.0005961398,0.0004791223,0.2258074,0.015831603,0.022445831,0.11869248,0.5717449],"study_design_scores_gemma":[0.00013248973,0.00022059424,0.002372875,0.000055328936,0.000029283985,0.000109517874,0.00006729644,0.97107273,0.007990278,0.014050524,0.0038501448,0.000048969614],"about_ca_topic_score_codex":0.007262623,"about_ca_topic_score_gemma":0.01036108,"teacher_disagreement_score":0.01463815,"about_ca_system_score_codex":0.0029771633,"about_ca_system_score_gemma":0.005640576,"threshold_uncertainty_score":0.07741487},"labels":[],"label_agreement":null},{"id":"W4282597468","doi":"10.1145/3514221.3517900","title":"One Size Does Not Fit All: A Bandit-Based Sampler Combination Framework with Theoretical Guarantees","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Sample (material); Population; Set (abstract data type); Sampling (signal processing); Measure (data warehouse); Data mining; Mathematical optimization; Mathematics","score_opus":0.07058486992079954,"score_gpt":0.31386200692866906,"score_spread":0.24327713700786952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282597468","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":[0.007911635,0.0007087525,0.98841524,0.00063671975,0.00003829854,0.0001231781,0.00009394367,0.00047934006,0.001592943],"genre_scores_gemma":[0.5237663,0.0011247571,0.4660354,0.0012916869,0.00047855312,0.0011991339,0.0005470797,0.0003823297,0.0051748916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921537,0.0044249767,0.0002990814,0.0011087902,0.0013665048,0.0006468167],"domain_scores_gemma":[0.9706308,0.023378065,0.0018027748,0.0015902288,0.0017116956,0.00088649837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016398994,0.0029562395,0.0039603757,0.0019429318,0.0013744282,0.003304729,0.004273809,0.0033698333,0.0037322629],"category_scores_gemma":[0.041143145,0.0021109218,0.0020972546,0.0021998284,0.0024557854,0.0052568014,0.004000609,0.004442994,0.0009994131],"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":[0.00046286828,0.00023248147,0.0033259415,0.0002507836,0.0003031818,0.00030337542,0.00031236908,0.82389283,0.0014684359,0.08436814,0.0038190242,0.08126056],"study_design_scores_gemma":[0.000036179877,0.00005714237,0.00012435511,0.000020687346,0.000033895278,0.000040850467,0.000012314139,0.9770452,0.0002496162,0.021785729,0.00058182055,0.000012135581],"about_ca_topic_score_codex":0.00395804,"about_ca_topic_score_gemma":0.0037134767,"teacher_disagreement_score":0.016398994,"about_ca_system_score_codex":0.0023297234,"about_ca_system_score_gemma":0.0031717764,"threshold_uncertainty_score":0.0867272},"labels":[],"label_agreement":null}]}