{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":5,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":5,"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","author_layer_release":"2026-06-26"},"query_hash":"5d0a88660265","filters":{"venue":"Proceedings of the 2022 International Conference on Management of Data"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Chenhao Ma","is_ca":false},{"name":"Yixiang Fang","is_ca":false},{"name":"Reynold Cheng","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true},{"name":"Xiaolin Han","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06422309090837273,"gpt":0.2962473222413728,"spread":0.232024231333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004804088,0.0001492091,0.0001796403,0.0001709663,0.0001786705,0.0001287972,0.006392463,0.00001693516,0.00001406432],"category_scores_gemma":[0.00003509528,0.0001248652,0.00009866092,0.0006215093,0.00009523641,0.0005453807,0.00543437,0.0001812067,2.752435e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004515264,"about_ca_system_score_gemma":0.00001774023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004721988,"about_ca_topic_score_gemma":3.405726e-7,"domain_scores_codex":[0.9979525,0.00001376933,0.0003336172,0.0006005149,0.000890944,0.0002086267],"domain_scores_gemma":[0.9986861,0.00005334781,0.0004652582,0.0005456965,0.0002208708,0.00002876585],"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":[0.0001217979,0.0003679331,0.0005195693,0.0001290247,0.0001977185,7.890182e-7,0.00007999368,0.001752818,0.0008750056,0.9828885,0.001835809,0.01123107],"study_design_scores_gemma":[0.001013209,0.0002631854,0.001231529,0.0001321304,0.00007331053,0.000007701024,0.001117279,0.9761641,0.001347363,0.01290027,0.005416006,0.0003338885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1088692,0.0003040541,0.833984,0.008358441,0.003830393,0.006517866,0.001975733,0.0005720554,0.03558838],"genre_scores_gemma":[0.9272701,0.00003768687,0.0715167,0.0001041052,0.00002427725,0.0002141792,0.0001243355,0.00001284323,0.0006957473],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9744113,"threshold_uncertainty_score":0.9989834,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Michael Abebe","is_ca":true},{"name":"Horatiu Lazu","is_ca":true},{"name":"Khuzaima Daudjee","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07251230446442274,"gpt":0.2891402640180174,"spread":0.2166279595535947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008691322,0.0001362179,0.0001599065,0.0001534453,0.0002000755,0.00008774382,0.007959985,0.00001565572,0.00005478459],"category_scores_gemma":[0.00002786493,0.0001146199,0.00008482329,0.0003282044,0.00005303166,0.0001055989,0.01011094,0.0001653897,0.000001892707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009203583,"about_ca_system_score_gemma":0.00002866051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000870833,"about_ca_topic_score_gemma":4.839826e-7,"domain_scores_codex":[0.9980913,0.00001708509,0.0003265438,0.0005267138,0.0008626721,0.0001756364],"domain_scores_gemma":[0.9986655,0.0000405285,0.0004810753,0.0005946519,0.0001917907,0.00002646852],"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":[0.00008168839,0.00029403,0.00005863875,0.0001085285,0.0003184892,0.000001176906,0.0002434624,0.001803342,0.0002888821,0.9357973,0.01525304,0.04575146],"study_design_scores_gemma":[0.00101417,0.0005022001,0.001076084,0.0002591386,0.00006902024,0.000003239829,0.003092213,0.914784,0.0006472237,0.02391801,0.0543307,0.0003040633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2347824,0.0004431228,0.2363595,0.09374557,0.01159751,0.01451393,0.002748931,0.0009039417,0.4049051],"genre_scores_gemma":[0.9751356,0.000009909634,0.01998149,0.0001410835,0.00004941313,0.0001928562,0.00002176743,0.00001137384,0.004456494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9129806,"threshold_uncertainty_score":0.9978951,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Linguan Yang","is_ca":true},{"name":"Xinan Yan","is_ca":true},{"name":"Bernard Wong","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06239947719482861,"gpt":0.2938453584648005,"spread":0.2314458812699719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005920526,0.0001053972,0.0001398566,0.00009526395,0.00017709,0.0001122096,0.003189613,0.00002100517,0.00003335876],"category_scores_gemma":[0.00002852223,0.00009544691,0.00005924338,0.0003788439,0.00002649879,0.0008354929,0.0009199358,0.0001123038,5.575893e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009324665,"about_ca_system_score_gemma":0.00002298212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001104189,"about_ca_topic_score_gemma":6.44126e-7,"domain_scores_codex":[0.9983574,0.00001298061,0.0003735521,0.0003990243,0.0007304454,0.0001265557],"domain_scores_gemma":[0.9988031,0.00002152975,0.0004798927,0.0003219635,0.0003542446,0.00001926919],"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":[0.0001026733,0.0002056395,0.0002658563,0.0002066532,0.0001527341,3.48416e-7,0.00008062709,0.0003239882,0.003790503,0.9732628,0.003727983,0.01788017],"study_design_scores_gemma":[0.004971721,0.000781646,0.01062264,0.001622681,0.0002315941,0.00001262441,0.005428751,0.8504345,0.01291281,0.07250894,0.03962405,0.0008480268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02421271,0.000078517,0.9536161,0.008746656,0.002747063,0.002009024,0.00334783,0.0001133666,0.005128745],"genre_scores_gemma":[0.9953728,0.00002507025,0.00350166,0.00003480684,0.00002895745,0.0001373757,0.0004113949,0.000006511799,0.0004814232],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9711601,"threshold_uncertainty_score":0.5927147,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jinglin Peng","is_ca":true},{"name":"Bolin Ding","is_ca":false},{"name":"Jiannan Wang","is_ca":true},{"name":"Kai Zeng","is_ca":false},{"name":"Jingren Zhou","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07058486992079954,"gpt":0.3138620069286691,"spread":0.2432771370078695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.000768778,0.0001484621,0.0001790712,0.0001340234,0.00010226,0.0001496097,0.007705489,0.00002595594,0.0005592139],"category_scores_gemma":[0.0001583028,0.0001046598,0.00004239507,0.0002940072,0.0001962127,0.0005565677,0.00489004,0.0002588078,0.000001445333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005962787,"about_ca_system_score_gemma":0.00003374383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001352591,"about_ca_topic_score_gemma":9.564192e-7,"domain_scores_codex":[0.9975532,0.00002485331,0.0003074454,0.0005197566,0.001437603,0.0001571608],"domain_scores_gemma":[0.9983569,0.0001862691,0.0004070224,0.0007896041,0.0002341041,0.00002607907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001569912,0.0003730424,0.0003944496,0.00005872671,0.0001547328,0.000001014358,0.0000862914,0.000007219305,0.0005299217,0.9930882,0.001874222,0.003275193],"study_design_scores_gemma":[0.002375108,0.001742318,0.009483857,0.001598517,0.0002455522,0.000007330477,0.00121525,0.1547249,0.03208428,0.7883603,0.007359374,0.0008032326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2372356,0.00004475602,0.4216555,0.2197318,0.002648212,0.00564062,0.01076424,0.001386132,0.1008931],"genre_scores_gemma":[0.8915988,0.00001829693,0.107574,0.0004818452,0.00001258437,0.00007478274,0.00009209997,0.0000101042,0.000137504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6543632,"threshold_uncertainty_score":0.9976633,"prediction_status":"machine_predicted_unvalidated"},"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,"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","keywords":"Audit; Pipeline (software); Computer science; Process (computing); Training set; Artificial intelligence; Machine learning; Data modeling; Labelling; Software engineering; Accounting; Programming language","authors":[{"name":"Naiqing Guan","is_ca":true},{"name":"Nick Koudas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1060019905566788,"gpt":0.3295175570380833,"spread":0.2235155664814045,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008681192,0.0001179188,0.0001576705,0.0001729679,0.0001569592,0.0000581225,0.004966399,0.00001695986,0.0001332201],"category_scores_gemma":[0.0002274941,0.0001040813,0.00004749417,0.0003470493,0.00004433669,0.0005922347,0.005497443,0.00037283,0.000001578712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003758943,"about_ca_system_score_gemma":0.0000346035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003159336,"about_ca_topic_score_gemma":0.000001619123,"domain_scores_codex":[0.9981307,0.00002830248,0.0004255594,0.0004101492,0.0008805349,0.0001247609],"domain_scores_gemma":[0.9982321,0.0001111272,0.0009228186,0.0004820549,0.000230042,0.00002184209],"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":[0.00005609847,0.0003424824,0.001718706,0.0002002529,0.0001772161,5.009333e-7,0.0002373316,0.06650443,0.004790291,0.9024962,0.001149485,0.02232707],"study_design_scores_gemma":[0.000261154,0.00005920517,0.0007473597,0.0001092361,0.0000226823,0.000001059958,0.000502049,0.989136,0.0003758832,0.006795807,0.001895671,0.00009391975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1884836,0.0004051517,0.6243018,0.06258444,0.001852498,0.001908151,0.007458113,0.0004570449,0.1125492],"genre_scores_gemma":[0.9734048,0.0001817604,0.02429051,0.0001147447,0.00001820763,0.0000112777,0.000564348,0.000009288126,0.001405084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9226316,"threshold_uncertainty_score":0.9228888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}